Machines

28 pages, 1326 KB

Open AccessArticle

Adaptive Event-Triggered Sliding Mode Control for Aircraft Antiskid Braking Based on a Hierarchical Prescribed Time Strategy

by Chenglong Zhu, Weilong Li and Xinming Guo

Machines 2026, 14(8), 954; https://doi.org/10.3390/machines14080954 - 21 Aug 2026

Viewed by 200

Abstract

A prescribed time-adaptive event-triggered sliding mode control method is proposed for a second-order aircraft antiskid braking system with unmeasurable longitudinal velocity, subject to unknown actuator faults and external disturbances. Based on the time scale transformation technique, a prescribed-time observer is constructed to estimate [...] Read more.

A prescribed time-adaptive event-triggered sliding mode control method is proposed for a second-order aircraft antiskid braking system with unmeasurable longitudinal velocity, subject to unknown actuator faults and external disturbances. Based on the time scale transformation technique, a prescribed-time observer is constructed to estimate the unmeasurable longitudinal velocity. A practical prescribed-time super-twisting observer with a saturated gain is designed to estimate the disturbance. Within the prescribed time convergence framework, an adaptive update law and a nonsingular integral sliding surface are developed to compensate for actuator faults. Building on this, a time-varying dynamic threshold event-triggering mechanism is incorporated into the prescribed time-sliding mode control process, while excluding Zeno behavior and reducing the control update frequency. The aforementioned prescribed-time observers and the event-triggered adaptive sliding mode controller form a strict temporal hierarchical architecture. Based on Lyapunov stability theory, it is proved that the closed-loop system is practically prescribed-time stable and that all closed-loop signals are uniformly ultimately bounded. Comparative simulation results verify the effectiveness of the proposed method. Full article

(This article belongs to the Special Issue Motion Planning and Control in Autonomous Robotic Systems)

► Show Figures

Figure 1

29 pages, 731 KB

Open AccessArticle

ICBBA-ACO-Based Multi-Robot Task Allocation for Smart Charging Stations

by Meiyu Chang, Zhaoyu Ku, Xuanyu Xing, Tianhao Wang and Huajun Dong

Machines 2026, 14(8), 953; https://doi.org/10.3390/machines14080953 - 21 Aug 2026

Viewed by 290

Abstract

Smart charging stations require mobile charging robots to respond to dynamically arriving charging requests with heterogeneous priorities, varying travel costs, and uneven workloads while maintaining online scheduling feasibility. Conventional single-layer approaches often optimize task assignment or route ordering separately, which limits their ability [...] Read more.

Smart charging stations require mobile charging robots to respond to dynamically arriving charging requests with heterogeneous priorities, varying travel costs, and uneven workloads while maintaining online scheduling feasibility. Conventional single-layer approaches often optimize task assignment or route ordering separately, which limits their ability to coordinate allocation quality, route efficiency, and workload regulation under real-time constraints. This study proposes a hierarchical improved consensus-based bundle algorithm–ant colony optimization (ICBBA-ACO) framework for dynamic multi-robot task allocation. The upper ICBBA layer combines deterministic task clustering, intra-cluster greedy bundling, conflict resolution, and feedback-guided workload-aware reassignment, while the lower ACO layer refines the visiting order of unstarted tasks under fixed ownership using the same normalized four-objective scheduling cost. Complete decision time is evaluated separately against a

200 ms

online requirement, and estimated motion energy is retained only as a distance-derived auxiliary indicator. In a five-method comparison over 100 paired scenarios, ICBBA-ACO achieves a mean composite objective of

J = 0.663052

, a mean decision time of

33.07 ms

, and 100% deadline compliance. GA-MRTA obtains a lower unconstrained mean objective of

J = 0.615790

, but requires approximately

2199.30 ms

on average and satisfies the

200 ms

requirement in only

8.89 %

of the evaluated updates. Thus, ICBBA-ACO provides the lowest mean objective among the compared methods that maintain full deadline compliance, demonstrating a favorable quality–runtime trade-off within the tested operating range. ROS-based engineering verification further completes all 15 repeated trials and all 48 verification tasks with no recorded invariant violations. Full article

(This article belongs to the Section Robotics, Mechatronics and Intelligent Machines)

► Show Figures

Figure 1

22 pages, 6428 KB

Open AccessArticle

MFETA-Net: Multi-Branch Frequency Enhancement and Temporal Attention for Small-Sample Rolling Bearing Fault Diagnosis

by Chiming Wang, Yiying Zhou, Dongke Zheng, Chengming Huang, Shunzhi Zhu, Zhenjun Li, Bingkun Wu and Liangqing Guan

Machines 2026, 14(8), 952; https://doi.org/10.3390/machines14080952 - 20 Aug 2026

Viewed by 263

Abstract

In practical industrial applications, rolling bearing fault samples are often scarce and costly to annotate, making small-sample fault diagnosis challenging. To address this issue, this paper proposes a frequency-aware time–frequency representation learning framework, named Multi-branch Frequency Enhancement Temporal Attention Network (MFETA-Net). In the [...] Read more.

In practical industrial applications, rolling bearing fault samples are often scarce and costly to annotate, making small-sample fault diagnosis challenging. To address this issue, this paper proposes a frequency-aware time–frequency representation learning framework, named Multi-branch Frequency Enhancement Temporal Attention Network (MFETA-Net). In the proposed framework, dual-channel vibration signals are first transformed into time–frequency representations using the Short-Time Fourier Transform (STFT). Then, a multi-branch frequency enhancement encoder is used to extract local frequency-band patterns, cross-band correlations, and frequency variation features. A temporal-frequency dependency modeling mechanism preserves the correspondence between temporal positions and frequency distributions during sequential modeling, while a temporal attention aggregation module emphasizes diagnostically important regions. Extensive experiments on the CWRU and HUST bearing datasets show that MFETA-Net achieves accuracies of 77.26% and 79.60% under the smallest training setting, respectively, indicating its capability to learn discriminative fault representations from limited labeled samples. Ablation studies further verify the effectiveness of each proposed module, while noise experiments confirm the robustness of the proposed framework under controlled noisy conditions. Full article

(This article belongs to the Section Machines Testing and Maintenance)

► Show Figures

Figure 1

26 pages, 2424 KB

Open AccessArticle

A Transferable Sensitivity-Analysis Protocol for Evolutionary Multi-Objective Optimisation in Surrogate-Based Engineering Design: Validation on Synthetic Benchmarks and Enclosed Screw Conveyors

by Suphatchakorn Limhengha and Supattarachai Sudsawat

Machines 2026, 14(8), 951; https://doi.org/10.3390/machines14080951 - 19 Aug 2026

Viewed by 249

Abstract

Applied engineering studies that use evolutionary multi-objective optimisation (MOO) rarely report confidence bounds on the Pareto-optimal solutions they recommend. This paper presents a four-stage sensitivity-analysis protocol that supplies them: cross-algorithm benchmarking, Friedman and Bonferroni-corrected Wilcoxon testing, hyperparameter sensitivity analysis, and ISO/IEC GUM-compliant uncertainty [...] Read more.

Applied engineering studies that use evolutionary multi-objective optimisation (MOO) rarely report confidence bounds on the Pareto-optimal solutions they recommend. This paper presents a four-stage sensitivity-analysis protocol that supplies them: cross-algorithm benchmarking, Friedman and Bonferroni-corrected Wilcoxon testing, hyperparameter sensitivity analysis, and ISO/IEC GUM-compliant uncertainty propagation. The protocol is first validated on the ZDT1, ZDT3 and DTLZ2 benchmarks (n = 2–12 decision variables), then demonstrated on an enclosed screw-conveyor design using Discrete Element Method (DEM) surrogates built by Response Surface Methodology (RSM). On the benchmarks, it correctly identified both algorithmic equivalence (MOGA and NSGA-II indistinguishable on four of five instances) and MOEA/D’s characteristic weakness on the disconnected ZDT3 front, whose hypervolume degraded most with dimensionality. For the engineering case, MOGA matched NSGA-II (p = 0.47–0.79) and remained within 0.5% hypervolume of SMS-EMOA over 12 runs, while hyperparameter variation stayed below 1% (max CV = 0.962%). DEM achieved 8.2% mean absolute percentage error for mass flow rate across 42 CCD operating conditions. The MOGA-optimised 100 mm pitch (4.86°, 138.86 rpm) delivered 0.416 kg/s at 6.95 N·m, a specific energy consumption of 0.0675 kWh/tonne and a 63.0% reduction against the 75 mm baseline. Full article

(This article belongs to the Section Machine Design and Theory)

► Show Figures

Figure 1

34 pages, 3415 KB

Open AccessReview

Artificial Intelligence for Autonomous Mobile Robots in IR4.0–IR6.0: A Unified Review from Perception and Visual Servoing to Decision-Making

by Montaser N. A. Ramadan, Mohammed A. H. Ali and Nik Nazri Nik Ghazali

Machines 2026, 14(8), 950; https://doi.org/10.3390/machines14080950 - 19 Aug 2026

Viewed by 501

Abstract

Reviews of artificial intelligence (AI) for mobile robots usually cover one competence—perception, SLAM, path planning, control, or reinforcement learning—and rarely show how these combine into a working system. We take the opposite view and treat autonomy as one pipeline: sensing, perception, localization and [...] Read more.

Reviews of artificial intelligence (AI) for mobile robots usually cover one competence—perception, SLAM, path planning, control, or reinforcement learning—and rarely show how these combine into a working system. We take the opposite view and treat autonomy as one pipeline: sensing, perception, localization and mapping, prediction, planning, visual servoing and control, high-level decision-making, and continual learning. We survey how AI has reshaped each stage for industrial and service robots across Industry 4.0, 5.0, and the emerging Industry 6.0. Using a structured, PRISMA-informed protocol with explicit search strings, inclusion criteria, and cross-embodiment transfer rules, we screen the literature, analyze a corpus drawn mainly from the last five years, and position it against prior surveys with a coverage matrix that exposes their single-block focus. Four findings stand out. Perception and localization approach engineering maturity through multimodal fusion and foundation vision models. Planning and control stay effective but computationally demanding. Decision-making, now driven by large language and vision–language–action models, is powerful yet unverifiable and fails under safety constraints. Lifelong learning is almost absent from deployed systems. The decisive weaknesses sit at the interfaces: at the perception–planning, planning–control, and control–decision handoffs the sim-to-real gap, limited on-robot compute, and scarce industrial data compound. We compare AI families by technology readiness, catalog datasets and benchmarks, examine the safety-certification barrier, and consolidate cross-cutting gaps. We close with a staged roadmap toward Industry 6.0 and a next-generation architecture coupling a foundation perception backbone, a world model and digital twin, a continual-learning memory, and a reasoning core wrapped by a safety monitor. The aim is to move from cataloging algorithms to engineering integrated autonomy. Full article

(This article belongs to the Special Issue Visual Servoing, Path Planning and Control of Mobile Robots in IR4.0-IR6.0 Applications)

► Show Figures

Figure 1

24 pages, 12574 KB

Open AccessArticle

Fuzzy Adaptive Impedance-Based Force and Position Compliance Control for Industrial Manipulators

by Fan Yang, Ming Hu, Jinfei Bian, Dandan Liu, Yanjie Yang and Jing Yang

Machines 2026, 14(8), 949; https://doi.org/10.3390/machines14080949 - 19 Aug 2026

Viewed by 255

Abstract

When a robot performs a grinding operation, the steady-state force/position tracking accuracy of its end-effector is critical to achieving high grinding quality. To solve this problem, a fuzzy adaptive impedance method is incorporated into the robot’s compliant control framework. Firstly, the robot dynamics [...] Read more.

When a robot performs a grinding operation, the steady-state force/position tracking accuracy of its end-effector is critical to achieving high grinding quality. To solve this problem, a fuzzy adaptive impedance method is incorporated into the robot’s compliant control framework. Firstly, the robot dynamics model is established based on the Newton–Euler method. To describe the robot dynamics more comprehensively, a linear friction compensation model is also introduced. Secondly, a dynamic feedforward trajectory-tracking controller is proposed based on the dynamic model, and its stability is verified using a Lyapunov function. The impedance parameters are adjusted in real time according to the feedback contact force and its rate of change, thereby enabling dynamic equilibrium between the end contact force and end position. This allows the robot end-effector to exhibit compliance during external environmental interactions. Finally, a control platform of a force/position compliance controller was constructed, and two grinding conditions of plane and arc were designed to validate the effectiveness of force/position compliance control based on impedance control. Compared with the fixed impedance approach, the proposed method reduces overshoot by 11.6% (plane) and 12.45% (arc), improves surface roughness from Ra 0.042 μm to Ra 0.021 μm, and achieves faster force tracking with fewer oscillations. Full article

(This article belongs to the Section Automation and Control Systems)

► Show Figures

Figure 1

60 pages, 11445 KB

Open AccessArticle

A Mamba-Driven Spatiotemporal Graph Neural Network for Fault Location in Low-Observability Active Distribution Networks

by Zhengying Hou, Jilong Ma and Xuguang Hu

Machines 2026, 14(8), 948; https://doi.org/10.3390/machines14080948 - 19 Aug 2026

Viewed by 230

Abstract

Accurate fault location in low-observability active distribution networks is hindered by uncertain inter-node relationships, underutilized early transients, and insufficient global context. To address these challenges, this paper proposes an adaptive Mamba-driven spatiotemporal graph neural network (AM-STGNN). It provides a unified task-driven spatiotemporal representation [...] Read more.

Accurate fault location in low-observability active distribution networks is hindered by uncertain inter-node relationships, underutilized early transients, and insufficient global context. To address these challenges, this paper proposes an adaptive Mamba-driven spatiotemporal graph neural network (AM-STGNN). It provides a unified task-driven spatiotemporal representation framework that progressively integrates fault-propagation modeling, global dependency modeling, transient-state learning, and topology-aware discriminative enhancement. Specifically, a prior-guided adaptive implicit topology is first learned to characterize task-dependent electrical coupling relationships among sparse observation nodes. Based on the resulting topology, topology-conditioned multi-order feature propagation and a dual-axis linear-attention module based on the spatiotemporal graph transformer (STGformer) are employed to capture local and global spatiotemporal dependencies. The resulting global spatiotemporal representation is subsequently processed by a Mamba selective state-space encoder to model input-dependent temporal evolution and emphasize informative fault transients. Finally, element-wise gated fusion, topology-aware differential output, and a margin constraint are employed to integrate the STGformer and Mamba representations and enhance the separability of adjacent faulted line sections with similar response characteristics. Extensive experiments demonstrate the effectiveness of AM-STGNN, while additional evaluations confirm its applicability to larger-scale networks, strongly phase-unbalanced conditions, and field-measured operating backgrounds. Robustness tests under individual and multi-level joint disturbances further demonstrate the practical relevance of the proposed architecture. Compared with the baseline models, AM-STGNN achieves consistent improvements in the macro-averaged F1 score (Macro-F1), exact accuracy, and one-hop accuracy under the clean IEEE 123-node condition. More importantly, it maintains clear performance advantages under identical mild, moderate, and severe joint disturbances, demonstrating improved robustness and practical relevance under simulated non-ideal operating conditions. Full article

(This article belongs to the Special Issue Advances in Electrical Power System Design and Artificial Intelligence)

► Show Figures

Figure 1

30 pages, 14017 KB

Open AccessArticle

A Novel Sensor Placement Method for High-Aspect-Ratio Unmanned Aerial Vehicle Wings Based on Chaotic Strengthened Aquila Optimizer

by Pengying Xu, Yu Wang, Shaoyi Liu, Jitang Zhang, Longyang Wang, Chuanmeng Sun, Heming Zhao, Jing Han, Congsi Wang and Yan Wang

Machines 2026, 14(8), 947; https://doi.org/10.3390/machines14080947 - 18 Aug 2026

Viewed by 284

Abstract

Optimal sensor placement (OSP) is critical to building a full-lifecycle health monitoring network for high-aspect-ratio unmanned aerial vehicle wings, as it directly affects the deformation sensing of the wing shape. To address this challenge, this paper proposes a novel sensor placement method for [...] Read more.

Optimal sensor placement (OSP) is critical to building a full-lifecycle health monitoring network for high-aspect-ratio unmanned aerial vehicle wings, as it directly affects the deformation sensing of the wing shape. To address this challenge, this paper proposes a novel sensor placement method for wings based on a chaotic strengthened aquila optimizer (CSAO) that integrates chaotic mapping and a nonlinear search strategy. Specifically, the proposed method introduces a uniform initialization strategy based on the piecewise chaotic map and a nonlinear criterion for switching between exploration and exploitation in the basic aquila optimizer (AO). These enhancements increase the diversity of the initial population and raise the probability of global search in later iterations, thereby accelerating convergence and strengthening global optimization capability. First, the performance of the CSAO is compared with that of other popular intelligent algorithms on 10 benchmark functions. The results show that the proposed method exhibits superior convergence speed, higher-quality solutions, stronger global search ability, and better robustness, making it suitable for OSP problems involving tens of thousands of candidate points. Next, the CSAO is applied to sensor placement on a wing-shaped plate. Compared with other OSP methods, the proposed method offers significant advantages in terms of sensor distribution, computational time, and hardware cost. Finally, experimental validation is conducted using a wing test platform equipped with fiber Bragg grating (FBG) strain sensors. The measurement results demonstrate that the reconstructed shape is in excellent agreement with the measured shape. Therefore, the proposed CSAO-based OSP method, combined with the FBG-based structural monitoring system, offers a promising solution for health monitoring of deformable structures in extreme environments. Full article

(This article belongs to the Section Machine Design and Theory)

► Show Figures

Graphical abstract

30 pages, 3998 KB

Open AccessArticle

Design and Simulation of an Inverted 2RPU–RPS Parallel End Effector for a Compact Maize Seeding Robot

by Zhe Wang, Yuxian Zhang, Tao Liu, Shuofei Yang and Qingjie Wang

Machines 2026, 14(8), 946; https://doi.org/10.3390/machines14080946 - 18 Aug 2026

Viewed by 206

Abstract

Terrain-induced chassis motion can disturb the soil-entry attitude and soil engagement of seeding components on compact agricultural robots. This study develops an inverted 2RPU–RPS rallel mechanism for a maize seeding robot to regulate the end effector without levelling the entire chassis. The mechanism [...] Read more.

Terrain-induced chassis motion can disturb the soil-entry attitude and soil engagement of seeding components on compact agricultural robots. This study develops an inverted 2RPU–RPS rallel mechanism for a maize seeding robot to regulate the end effector without levelling the entire chassis. The mechanism supports the disc opener and terminal seed tube and provides one vertical translation and two rotations. A nonlinear inverse-kinematic model, a unilateral penetration–downforce model, constrained electric-cylinder dynamics, and a coordinated feedforward–PI controller are established. The roll and pitch loops combine chassis-attitude feedforward compensation with end-effector error feedback, while the vertical loop regulates the opener downforce using a stiffness-based penetration reference and force feedback. MATLAB/Simulink simulations are conducted under isolated attitude disturbances, vertical terrain excitation, and multi-row operation. With maximum chassis roll and pitch disturbances of 4.49° and 3.35°, the end-effector RMSE values are 0.109° and 0.114°, respectively. At a prescribed downforce of 400 N, the downforce RMSE is 11.07 N and the mean disc-opener penetration is 34.99 mm. During the 300 s multi-row simulation, the mean penetration remains 34.96 mm and the downforce RMSE is 12.65 N. The results indicate that the strategy can attenuate chassis-induced disturbances and maintain stable soil engagement under the adopted modelling assumptions. Full article

(This article belongs to the Section Robotics, Mechatronics and Intelligent Machines)

► Show Figures

Figure 1

29 pages, 2134 KB

Open AccessArticle

Channel-Selective BO-Fusion-PINN for Parameter-Generalized Fault Diagnosis of Permanent Magnet Synchronous Motors

by Xuan Chang, Jingkai Bao, Shaochi Zhang and Ruisheng Diao

Machines 2026, 14(8), 945; https://doi.org/10.3390/machines14080945 - 18 Aug 2026

Viewed by 202

Abstract

Parameter variation caused by manufacturing tolerances and thermal drift makes PMSM fault-severity estimation difficult, because motor-level offsets and fault effects are coupled in the d–q model. This paper proposes a channel-selective BO-Fusion-PINN for parameter-generalized fault diagnosis. A healthy reference window is first used [...] Read more.

Parameter variation caused by manufacturing tolerances and thermal drift makes PMSM fault-severity estimation difficult, because motor-level offsets and fault effects are coupled in the d–q model. This paper proposes a channel-selective BO-Fusion-PINN for parameter-generalized fault diagnosis. A healthy reference window is first used to estimate motor-parameter deviations through an integral least-squares observer, avoiding neural extrapolation of these offsets. A diagnostic window is then processed by a physics-informed LSTM branch and a data-driven LSTM branch, and Bayesian optimization assigns separate fusion weights to stator-resistance degradation and permanent-magnet flux weakening. Experiments over parameter out-of-distribution buckets and non-ideal simulation settings show that the fused estimator consistently improves on either branch alone. The method is especially effective in the flux channel and remains competitive with high-capacity data baselines while preserving physical interpretability. The primary scientific contribution is an identifiability-guided fusion rule that assigns physics and data trust to each fault channel according to its statistical observability rather than through a single global weight; in practical terms, this yields a compact and interpretable estimator that transfers across the parameter-tolerance band of a machine class and can, in principle, support controlled end-of-line screening and scheduled diagnostic assessment under a matched-window acquisition protocol. Full article

(This article belongs to the Section Machines Testing and Maintenance)

► Show Figures

Figure 1

39 pages, 9225 KB

Open AccessArticle

Prediction and Optimization of Freeform Impeller Machining Parameters Using a Hybrid Taguchi-Artificial Neural Network Model with the Levenberg–Marquardt Algorithm

by Usman Haladu Garba, Taiyong Wang, Ying Tian, Jing Kang and Chong Tian

Machines 2026, 14(8), 944; https://doi.org/10.3390/machines14080944 - 17 Aug 2026

Viewed by 223

Abstract

Freeform machining of impellers involves extended cycle times, leading to high energy consumption and costs necessitating efficient process optimization. This study develops a CAD/CAM-integrated hybrid Taguchi-Artificial Neural Network (ANN) model to optimize machining parameters for a freeform impeller. Four controllable factors, namely cutting [...] Read more.

Freeform machining of impellers involves extended cycle times, leading to high energy consumption and costs necessitating efficient process optimization. This study develops a CAD/CAM-integrated hybrid Taguchi-Artificial Neural Network (ANN) model to optimize machining parameters for a freeform impeller. Four controllable factors, namely cutting feed (

C_{f}

), feed Z (

F_{z}

), retract feed (

R_{f}

), and cutter diameter (

C_{D}

), were investigated at five levels using an L25 orthogonal array, with machining time as the response. Taguchi analysis identified cutting feed as the most dominant factor, while retract feed was insignificant, and a first-order regression model yielded an R² of 95.88%. A two-layer feedforward neural network with six hidden neurons achieved an R² of 0.9999 and a mean absolute error of 0.0976 min. To rigorously validate generalization, leave-one-out cross-validation was employed, identifying three hidden neurons as optimal with a cross-validated R² of 0.9823, RMSE of 0.5350 min, and MAE of 0.3429 min. The final model trained on all samples achieved an R² of 0.9996. Comparison with a quadratic regression model on the same test set confirmed the superior predictive capability of the ANN (

R^{2} = 0.9992

vs.

0.9983

). Optimal parameters (

C_{f} = 12,000 m m / m i n

,

F_{z} = 600 m m / m i n

,

R_{f} = 4000 m m / m i n

,

C_{D} = 6 m m

) were validated through simulation, yielding a machining time of 11.05 min, representing a 52.6% reduction from 23.32 min. The hybrid Taguchi–ANN framework effectively optimizes freeform impeller machining, significantly enhancing productivity while maintaining process reliability. Full article

(This article belongs to the Special Issue Surface Engineering Techniques in Advanced Manufacturing)

► Show Figures

Figure 1

28 pages, 4532 KB

Open AccessArticle

A Remaining Useful Life Prediction Method for Aero-Engines Based on Degradation-Aware Masked Augmentation and a CNN–Transformer Hybrid Network

by Xudong Song, Guohua Wu, Mengdan Wang, Jian Liu, Wenlin Wang, Mengchu Song, Hongxing Lu and Yue Shen

Machines 2026, 14(8), 943; https://doi.org/10.3390/machines14080943 - 17 Aug 2026

Viewed by 275

Abstract

Accurate remaining useful life (RUL) prediction is essential for condition-based maintenance and safe aero-engine operation. To address non-stationary monitoring data, limited informative degradation samples, and the difficulty of jointly modeling local degradation patterns and temporal dependencies, this study proposes a degradation-aware dynamic masking [...] Read more.

Accurate remaining useful life (RUL) prediction is essential for condition-based maintenance and safe aero-engine operation. To address non-stationary monitoring data, limited informative degradation samples, and the difficulty of jointly modeling local degradation patterns and temporal dependencies, this study proposes a degradation-aware dynamic masking augmentation method combined with a multiscale CNN–Transformer network. The 21 sensor variables in the NASA C-MAPSS dataset are first grouped by physical meaning and reconstructed into four-dimensional state features. A degradation-state score integrating local variance and trend slope is then used to adapt temporal masking probabilities across degradation stages, while feature masking probabilities are assigned according to feature importance. Masked positions are filled with adjacent unmasked observations, and invalid augmented samples are removed through trend consistency verification. A multiscale CNN with channel attention extracts local degradation features, and a Transformer encoder captures temporal dependencies. Bayesian optimization is used to determine key hyperparameters. On FD001, the proposed method achieves an MSE of 348.3970, an MAE of 8.3908, and an R² of 0.9227, reducing MSE and MAE by 4.27% and 28.42%, respectively, compared with ML-RFR. It also achieves the highest R² of 0.9369 on FD003. Cross-dataset and multi-seed experiments further confirm its applicability and stability. Full article

(This article belongs to the Section Machines Testing and Maintenance)

► Show Figures

Figure 1

45 pages, 6009 KB

Open AccessReview

Evolution of No-Till Precision Seeding Equipment: From Contact-Dynamic Reshaping to Cyber–Physical System (CPS) Closed-Loop Control

by Chirui Zhang, Yuting Dong, Jiahao Shen, Shiguo Wang, Xiaohu Guo and Zhong Tang

Machines 2026, 14(8), 942; https://doi.org/10.3390/machines14080942 - 17 Aug 2026

Viewed by 382

Abstract

No-till precision seeding is an important component of conservation tillage, but stable operation remains constrained by compacted undisturbed soil, dense crop residues, and uneven field surfaces. This review examines the evolution of no-till precision seeding equipment from mechanical soil–residue interaction to cyber–physical closed-loop [...] Read more.

No-till precision seeding is an important component of conservation tillage, but stable operation remains constrained by compacted undisturbed soil, dense crop residues, and uneven field surfaces. This review examines the evolution of no-till precision seeding equipment from mechanical soil–residue interaction to cyber–physical closed-loop regulation. It first summarizes how soil resistance and residue interference affect furrow opening, seed placement, and seed–soil contact. It then examines the development of residue-management, furrow-opening, covering, and compaction mechanisms, highlighting the transition from passive structural optimization toward active and adaptive operation. Advances in multi-source sensing, electric-drive metering, downforce control, and vibration suppression are further reviewed as enabling technologies for improving seeding stability under variable and high-speed conditions. Despite these advances, persistent trade-offs remain among residue-removal capacity, soil disturbance, energy demand, component durability, system complexity, and operational stability. Emerging approaches based on digital twins, adaptive damping, and cooperative autonomous systems may support further improvements, but their practical implementation still requires robust field performance and effective system integration. Overall, no-till seeding equipment is progressing toward perception-assisted and closed-loop intelligent regulation while continuing to face important mechanical and implementation challenges. Full article

(This article belongs to the Section Machine Design and Theory)

► Show Figures

Figure 1

23 pages, 20110 KB

Open AccessArticle

Fault Diagnosis Method Based on Temperature Rise Detection for Switched Reluctance Motor Drive Systems in Electrical Transportation

by Xiangsu Wang, Zhijie Zhang, Qing Wang and Yongqing Deng

Machines 2026, 14(8), 941; https://doi.org/10.3390/machines14080941 - 15 Aug 2026

Viewed by 263

Abstract

In this paper, a fault diagnosis method based on temperature rise detection is proposed for power converters in switched reluctance motor drive systems used in electrical transportation equipment. First, the total power losses of all power devices are calculated and recorded under different [...] Read more.

In this paper, a fault diagnosis method based on temperature rise detection is proposed for power converters in switched reluctance motor drive systems used in electrical transportation equipment. First, the total power losses of all power devices are calculated and recorded under different operating conditions in both healthy and faulty states. A finite-element electrothermal model is then established to characterize the relationship between fault-induced power-loss redistribution and variations in the temperature rise of the converter devices. Based on the power-loss analysis, temperature rise is used as a key characteristic, and a corresponding fault diagnosis method is proposed. To account for the influence of operating conditions on the diagnostic criterion, three independent backpropagation neural network (BPNN) models are developed to predict fault-specific temperature-rise thresholds using rotor speed, load torque, and ambient temperature as inputs. During diagnosis, the real-time temperature evolution of the power diodes is compared with the selected thresholds to detect power converter faults. Finally, experimental results demonstrate the validity of the proposed fault diagnosis method. Full article

(This article belongs to the Section Machines Testing and Maintenance)

► Show Figures

Figure 1

41 pages, 13249 KB

Open AccessArticle

A Gated Multi-Source Signal Fusion Method for Bearing Fault Diagnosis with a Fusion Negative-Transfer Suppression Mechanism

by Tianhao Gao, Ke Zhang, Nan Wang, Yang Hong and Shijie Wang

Machines 2026, 14(8), 940; https://doi.org/10.3390/machines14080940 - 14 Aug 2026

Viewed by 231

Abstract

Multi-source information fusion is regarded as a key approach for improving bearing fault diagnosis. However, due to the heterogeneity of multi-source information, asymmetric information contributions, and imbalanced discriminative features, negative transfer may occur during fusion. To address this issue, this paper proposes a [...] Read more.

Multi-source information fusion is regarded as a key approach for improving bearing fault diagnosis. However, due to the heterogeneity of multi-source information, asymmetric information contributions, and imbalanced discriminative features, negative transfer may occur during fusion. To address this issue, this paper proposes a negative-transfer-suppression diagnosis framework based on physical-information guidance and adversarially disentangled representation. First, an adaptive preprocessing mechanism guided by acoustic–vibration cross-correlation and mutual information entropy is constructed to extract intrinsic cross-modal correlations, enabling source-end feature reconstruction and commonality enhancement. Second, an attention-based spatial feature extraction operator and an adversarial common-domain representation model are developed to suppress modality-specific interference and disentangle cross-modal shared features. On this basis, sparse coding is employed to fuse common-domain and modality-specific features. Furthermore, a classification effectiveness evaluation index based on fuzzy clustering is introduced into the loss function to dynamically constrain sparse coding weights, thereby reducing interference features and suppressing negative transfer under strong-noise conditions. Experimental results demonstrate that the proposed method effectively achieves the design objective that “fusion outperforms non-fusion,” exhibiting strong noise robustness and high diagnostic accuracy under complex operating conditions. Full article

(This article belongs to the Special Issue Advanced Modeling, Dynamics and Intelligent Monitoring of Rolling Bearings)

► Show Figures

Figure 1

24 pages, 18551 KB

Open AccessArticle

Design and Experimental Assessment of a Continuous Bending Under Tension (CBT) Test Device for Universal Testing Machines

by Rafael Oliveira Santos, Abílio M. R. Borges, Humberto Pereira, Marilena C. Vincze, António B. Pereira, Pedro A. Prates and Gabriela Vincze

Machines 2026, 14(8), 939; https://doi.org/10.3390/machines14080939 - 14 Aug 2026

Viewed by 293

Abstract

Continuous bending under tension (CBT), also known as cyclic bending under tension, is an experimental deformation technique capable of achieving large plastic strains under relatively low tensile loads. However, the broader application of CBT testing remains dependent on the availability of dedicated experimental [...] Read more.

Continuous bending under tension (CBT), also known as cyclic bending under tension, is an experimental deformation technique capable of achieving large plastic strains under relatively low tensile loads. However, the broader application of CBT testing remains dependent on the availability of dedicated experimental setups and the suitable adaptation of conventional mechanical testing systems. This study presents the design and development of a CBT testing device intended for integration with conventional universal testing machines. The proposed system consists of four main subsystems: specimen grips, a roller train, a motor system, and a supporting structure. The developed device was experimentally assessed using DP600 advanced high-strength steel and AA6022-T4 aluminum alloy sheets with nominal thicknesses of 1.5 and 2.0 mm, respectively, under selected CBT operating conditions. The system successfully performed CBT tests, enabling the acquisition of force–elongation responses, cycles to fracture, and post-test specimen observations. The experimental results reproduced the characteristic CBT response, showing significantly higher total elongation compared with uniaxial tensile testing while requiring substantially lower tensile forces. The developed device demonstrated operational and mechanical stability, providing a practical platform for laboratory-scale investigations of sheet metal deformation behavior under CBT loading conditions. Full article

(This article belongs to the Special Issue Design and Manufacturing for Lightweight Components and Structures)

► Show Figures

Figure 1

28 pages, 24288 KB

Open AccessArticle

Reinforcement Learning-Based Interactive Control of an Omnidirectional Mobile Lower Limb Rehabilitation Robot

by Suyang Yu, Yangqing Yu and Changlong Ye

Machines 2026, 14(8), 938; https://doi.org/10.3390/machines14080938 - 14 Aug 2026

Viewed by 298

Abstract

This paper proposes a hierarchical control architecture that is established at both lower limb joint and platform levels based on a simplified admittance model, where compliance is regulated through virtual mass and damping. At the lower limb joint level, admittance control governs lower [...] Read more.

This paper proposes a hierarchical control architecture that is established at both lower limb joint and platform levels based on a simplified admittance model, where compliance is regulated through virtual mass and damping. At the lower limb joint level, admittance control governs lower limb motion tracking, while at the platform level it adjusts the omnidirectional mobile platform velocity in response to human interaction forces. Within this framework, a Sarsa-based reinforcement learning agent dynamically optimizes the parameters of a Sigmoid function using dual state inputs. Based on hip joint angle error and human–robot interaction force, the controller dynamically adjusts virtual mass and damping to optimize the trade-off between tracking error and dynamic compliance. The simulation and experimental results on the prototype system demonstrate that, compared with traditional Sigmoid parameter-tuned admittance control, the proposed approach significantly enhances gait smoothness (dimensionless squared jerk reduced by 65.62% and 36.74% for hip and knee joints), and increases human–robot interaction compliance (RMS interaction force was reduced from 3.2502 N to 2.5109 N; EPUD decreased from 12.14 to 9.53). Moreover, the proposed strategy achieves smaller maximum overshoot (0.45° vs. 0.9°) and faster settling time (2.6 s vs. 4.59 s). These findings indicate that integrating reinforcement learning with Sigmoid parameter adaptation provides a systematic and effective solution for adaptive compliance regulation in mobile exoskeleton systems, enhancing adaptability, safety, and functional relevance for stroke patients undergoing lower limb rehabilitation training. Full article

(This article belongs to the Section Automation and Control Systems)

► Show Figures

Figure 1

44 pages, 12928 KB

Open AccessArticle

Advanced MPPT Optimization for PV Water Pumping with Battery Storage and MPC-Driven BLDC Motor via Swarm and Evolutionary Algorithms

by Nadia Akkari, Malika Ikhlef, Tarek Berghout, Kamel Srairi, Abderazek Hammoudi and Aissa Laouissi

Machines 2026, 14(8), 937; https://doi.org/10.3390/machines14080937 - 13 Aug 2026

Viewed by 302

Abstract

Photovoltaic (PV) pumping systems offer a sustainable alternative to diesel solutions, yet their nonlinearity, intermittent irradiation, and complex motor-pump dynamics challenge energy extraction and reliability. Currently, these systems predominantly rely on classical Maximum Power Point Tracking (MPPT) algorithms such as Perturb and Observe [...] Read more.

Photovoltaic (PV) pumping systems offer a sustainable alternative to diesel solutions, yet their nonlinearity, intermittent irradiation, and complex motor-pump dynamics challenge energy extraction and reliability. Currently, these systems predominantly rely on classical Maximum Power Point Tracking (MPPT) algorithms such as Perturb and Observe (P&O) and Incremental Conductance (INC), which suffer from slow convergence, steady-state oscillations, and an inability to track Global MPP (GMPP) under uniform irradiance variation conditions. Furthermore, existing studies typically address MPPT optimization and motor control in isolation, without considering their coupled interaction, and rarely incorporate economic viability assessments. To address these limitations, this paper proposes an innovative control architecture integrating four advanced metaheuristic MPPT techniques, namely the Genetic Algorithm (GA), Gray Wolf Optimizer (GWO), Cuckoo Search (CS) algorithm, and Horse Herd Optimization Algorithm (HOA), with Model Predictive Control (MPC) for a Brushless DC (BLDC) motor-driven pumping system, supplemented by battery storage. Comprehensive simulations were conducted under both constant and variable irradiance profiles (1000 to 500 to 1000 W/m²) to evaluate dynamic performance, tracking accuracy, and system robustness. The results demonstrate that HOA and GWO significantly outperform GA and CS, achieving superior DC bus voltage stability with ripple values below 2.4 V, faster convergence times, reduced electromagnetic torque oscillations, and enhanced MPPT efficiency exceeding 99%. Under variable irradiance, HOA exhibits the fastest stabilization with minimal overshoot and superior disturbance rejection, while GA suffers from severe oscillations and CS displays sawtooth ripple patterns. A techno-economic analysis further confirms the economic viability of the proposed system, with HOA and GWO strategies yielding lower lifecycle costs, extended converter lifespans from 5 to over 12 years, and improved return on investment compared to conventional approaches. This integrated framework offers a robust, efficient, and economically sustainable solution for autonomous PV water pumping applications. Full article

(This article belongs to the Section Electrical Machines and Drives)

► Show Figures

Figure 1

27 pages, 1083 KB

Open AccessArticle

A Unified Conditional Policy for Multi-Robot Navigation via LiDAR-to-Vision Distillation

by Amir Mahdi Amani, Sajjad Amani and AmirHossein MajidiRad

Machines 2026, 14(8), 936; https://doi.org/10.3390/machines14080936 - 13 Aug 2026

Viewed by 310

Abstract

Mobile-robot navigation policies have typically assumed a fixed sensing input and robot platform. In this work, we investigate a teacher–student policy where teachers learn continuous velocity commands from LiDAR-based Twin Delayed Deep Deterministic Policy Gradient, and the student navigates using either LiDAR or [...] Read more.

Mobile-robot navigation policies have typically assumed a fixed sensing input and robot platform. In this work, we investigate a teacher–student policy where teachers learn continuous velocity commands from LiDAR-based Twin Delayed Deep Deterministic Policy Gradient, and the student navigates using either LiDAR or camera observations. The student has two modalities with separate feature extractors. The extracted features and robot-state variables are fed into a shared encoder and actor, which map them to linear and angular velocity commands. The generalized two-platform configuration includes a Robot-ID token of scalar type. Training and evaluation were performed in ROS-Gazebo using simulated Pioneer 3-DX and TurtleBot3 Waffle robots. Robot-ID conditioning increased generalized LiDAR success to 90.4% on Pioneer 3-DX and to 91.2% on TurtleBot3 Waffle, up from 71.8% and 79.5%, and camera-based success was 87.3% and 84.0%, respectively. Across four controlled LiDAR-to-vision handover conditions, we achieved an overall success rate of 88.8-90.8%. Overall, 85.2-90.1% of the episodes that were still active at the planned switch were completed without resetting or retraining the policy. The results demonstrate that the conditioning on robot identity is very helpful for cross-platform LiDAR performance and that the shared student policy is able to continue navigation after external scheduling of the active sensing branch. The results provide a controlled, simulation-based feasibility assessment of the proposed policy architecture and establish the basis for subsequent physical robot validation. Full article

(This article belongs to the Special Issue Rehabilitation and Assistive Robotics: Enhancing Recovery Through Innovative Device Solutions)

► Show Figures

Figure 1

31 pages, 8278 KB

Open AccessArticle

Dominant Trend Identification of Electromagnetic Excitation and Analysis of Vibration and Noise Characteristics for Variable-Speed Scroll Compressors

by Zhen Wang, Shukai Li, Xichu Wei and Wenguang Fu

Machines 2026, 14(8), 935; https://doi.org/10.3390/machines14080935 - 13 Aug 2026

Viewed by 370

Abstract

Variable-speed operation of scroll compressors is a prevailing trend for energy saving in refrigeration systems; however, complex electromagnetic excitation induces prominent vibration and noise, yet its dominant timing, spatial distribution, and action mechanism remain unclear. An electromagnetic–structural–acoustic sequential coupling model of a scroll [...] Read more.

Variable-speed operation of scroll compressors is a prevailing trend for energy saving in refrigeration systems; however, complex electromagnetic excitation induces prominent vibration and noise, yet its dominant timing, spatial distribution, and action mechanism remain unclear. An electromagnetic–structural–acoustic sequential coupling model of a scroll compressor is established and validated at three speeds (3600–6600 rpm), and a dominance identification method integrating harmonic–modal matching, variational mode decomposition, and electromagnetic correlation identification is proposed. Predicted frequencies agree well with experiments; even-order harmonics migrate linearly with speed, with harmonic–modal matching exceeding 80% at low and medium speeds. At 5400 rpm, the 24th-order harmonic (2160 Hz) coincides with mode 2 (2162 Hz), causing resonance and a threefold amplitude increase. At low and medium speeds, vibration dominance indices range between 0.68 and 0.75, while noise dominance indices decrease from 0.55 to 0.48, dropping to 0.35 and 0.28 at 6600 rpm, indicating noise source transition. Vibration at S1 through S4 shows spatial variation, and far-field noise at F1 through F4 is non-uniform. These findings clarify how electromagnetic excitation dominates the vibration and noise of scroll compressors, providing a theoretical basis for speed-segmented and zone-specific noise source identification and control. Full article

(This article belongs to the Section Electromechanical Energy Conversion Systems)

► Show Figures

Figure 1

35 pages, 11319 KB

Open AccessArticle

A Novel Narrowband Filtering Demodulation Method Based on Adaptive Multi-Level Spectra Segmentation Strategy and Its Application in Bearing Fault Diagnosis

by Yuxuan Wang, Jinying Huang, Hantao Liu, Siyuan Liu, Zhenfang Fan and Yaxu Niu

Machines 2026, 14(8), 934; https://doi.org/10.3390/machines14080934 - 13 Aug 2026

Viewed by 289

Abstract

Rolling bearings, as a key component of rotating machinery, require precise fault diagnosis to ensure the safe and reliable operation of industrial systems. Nevertheless, the performance of traditional narrowband filtering demodulation (NFD) methods is constrained by inherent limitations of spectral segmentation frameworks and [...] Read more.

Rolling bearings, as a key component of rotating machinery, require precise fault diagnosis to ensure the safe and reliable operation of industrial systems. Nevertheless, the performance of traditional narrowband filtering demodulation (NFD) methods is constrained by inherent limitations of spectral segmentation frameworks and insufficient discriminative capability of feature indicators (FIs). To address these limitations, this paper proposes a new NFD method based on an adaptive multi-level spectra segmentation strategy. Firstly, using power spectral density (PSD) as the analysis basis, an iterative framework is constructed to obtain multi-level spectral trend lines (STLs), which achieves multi-perspective characterization of spectral features. Secondly, the local minimum points of the STLs are used as the segmentation boundaries to extract the demodulation frequency band. Subsequently, a robust blind feature indicator, synergistic characterization criterion (SCC), is proposed, which can simultaneously fully evaluate periodicity and impulsiveness, guiding the selection of the optimal demodulation frequency band (ODFB). Finally, based on the enhanced demodulation spectrum, power exponent transformation is introduced to construct a generalized spectral family, and the adaptive determination of the optimal transformation parameter is guided by frequency-domain signal-to-noise ratio (FDSNR), thereby obtaining the generalized enhanced demodulation spectrum (GEDS). Validation experiments on laboratory and public datasets demonstrate that the proposed method outperforms Fast Kurtogram, Autogram, and CFFsgram, with average improvements of 63.86% and 89.06% in mean-peak ratio (MPR) and fault feature coefficient (FFC), respectively, and provides a new perspective for NFD and expands its application potential in bearing fault diagnosis and condition monitoring. Full article

(This article belongs to the Section Machines Testing and Maintenance)

► Show Figures

Figure 1

27 pages, 39069 KB

Open AccessArticle

CESIgram: A Fault Feature Extraction Method for Rolling Bearings in Wind Turbine Equipment Based on Collaborative Filtering Correlation Spectrum

by Junjie Zhu, Yang Ding, Hui Li, Bo Wang, Dongbing Su and Yonggang Xu

Machines 2026, 14(8), 933; https://doi.org/10.3390/machines14080933 - 13 Aug 2026

Viewed by 283

Abstract

To address the difficulty of extracting weak fault features of rolling bearings in wind turbines under strong background noise, a fault feature extraction method based on the collaborative filtering correlation spectrum, named CESIgram, is proposed. The collaborative filtering correlation spectrum (CFCS) based on [...] Read more.

To address the difficulty of extracting weak fault features of rolling bearings in wind turbines under strong background noise, a fault feature extraction method based on the collaborative filtering correlation spectrum, named CESIgram, is proposed. The collaborative filtering correlation spectrum (CFCS) based on Block Matching 3D is designed to suppress random noise while preserving cyclostationary structures, resulting in a clearer cyclic spectral representation. A projection method along the cyclic frequency axis is proposed to obtain the carrier-based enhanced envelope spectrum. An integrated envelope spectrum index combining harmonic significance and periodic impact is proposed to quantify fault feature enrichment in different enhanced envelope spectra. The method works in three stages: spectral representation via Fast-SC, reformulation of the spectral correlation via CFCS, and adaptive band selection via CESI. The method successfully extracted fault characteristic frequencies and their harmonics in simulation and experimental signals under various strong noise conditions, while Fast Kurtogram, Autogram, Infogram, and Fast Entrogram failed to detect any fault-related peaks. Comparative analysis shows that the proposed method has significant advantages in noise suppression and fault feature extraction. The effectiveness is verified using simulation and experimental signals of rolling bearing faults in wind power equipment. Full article

(This article belongs to the Special Issue Health Condition Monitoring, Intelligent Operation and Maintenance of Wind Turbines)

► Show Figures

Figure 1

36 pages, 5128 KB

Open AccessArticle

Kinematic and Dynamic Modeling and Simulation-Based Performance Evaluation of a Novel Central-Actuated Transformable Wheel Design for Mobile Robots

by Nazmi Kaplan and Alper Kadir Tanyıldızı

Machines 2026, 14(8), 932; https://doi.org/10.3390/machines14080932 - 13 Aug 2026

Viewed by 305

Abstract

This paper presents the design, kinematic modeling, and dynamic simulation of a novel conical-slider-based transformable wheel with five deployable wheel-leg elements for mobile robotic systems. The proposed wheel can operate in a closed-wheel configuration for regular terrain and in an open wheel-leg configuration [...] Read more.

This paper presents the design, kinematic modeling, and dynamic simulation of a novel conical-slider-based transformable wheel with five deployable wheel-leg elements for mobile robotic systems. The proposed wheel can operate in a closed-wheel configuration for regular terrain and in an open wheel-leg configuration for enhanced interaction with rough terrain and obstacle profiles. The transformation motion is generated through a central linear actuation input transmitted by a conical slider mechanism integrated into the wheel hub. A CAD-supported mechanical design was developed to examine the geometric feasibility of the proposed wheel structure and to verify the radial deployment motion of the wheel-leg elements. The kinematic formulation was revised in a compact indexed form by consistently considering the angular offsets of all five wheel-leg elements. In addition, a dynamic model including the six-wheel vehicle body, suspension elements, wheel–ground contact, wheel-leg–ground contact, and wheel driving inputs was formulated. A unilateral contact model was used to represent contact, loss of contact, and re-contact events while preventing non-physical tensile normal forces. The proposed wheel concept was evaluated using a MATLAB-based representative mixed-terrain simulation scenario that combines rough-terrain locomotion and traversal of a 0.35 m single obstacle. The simulation results show that the fully deployed wheel-leg configuration successfully traverses the tested 0.35 m obstacle, whereas the closed-wheel configuration fails under the same terrain condition. Because the conical slider is continuously adjustable, an intermediate deployment state was also evaluated: it traverses a 0.30 m obstacle that the closed configuration cannot, yet fails against the 0.35 m obstacle, so that the traversal threshold varies monotonically with the deployment stroke. The comparison demonstrates that the deployed wheel-leg elements improve obstacle traversal capability by increasing the effective contact geometry and providing additional interaction with the obstacle surface. The results indicate that the proposed conical-slider-based transformable wheel has the potential to improve the terrain adaptability and obstacle traversal performance of six-wheel mobile robotic systems. Since the present study is limited to CAD-supported design verification and MATLAB-based dynamic simulation, future work will focus on prototype manufacturing, actuator design, structural analysis, and experimental validation under real terrain conditions. Full article

(This article belongs to the Topic Vehicle Dynamics and Control, 2nd Edition)

► Show Figures

Figure 1

31 pages, 22125 KB

Open AccessArticle

Carbon-Aware Dynamic Human–Robot Collaborative Flexible Job Shop Scheduling Under Safety-Proximity Disruption

by Fan Wu, Yufan Zheng and Wenkang Zhang

Machines 2026, 14(8), 931; https://doi.org/10.3390/machines14080931 - 12 Aug 2026

Viewed by 294

Abstract

Human–robot collaborative flexible job shop scheduling (HRC-FJSP) must coordinate heterogeneous capabilities, mode-dependent processing times, safety feasibility, and carbon constraints. The problem becomes harder when a collaboration mode that is attractive during planning becomes infeasible after a human enters the robot safety separation zone. [...] Read more.

Human–robot collaborative flexible job shop scheduling (HRC-FJSP) must coordinate heterogeneous capabilities, mode-dependent processing times, safety feasibility, and carbon constraints. The problem becomes harder when a collaboration mode that is attractive during planning becomes infeasible after a human enters the robot safety separation zone. Unlike conventional dynamic disturbances such as machine breakdown or order insertion, this event changes the feasible collaboration mode of the unfinished operation remainder rather than only delaying a resource or adding a job. This study formulates a carbon-aware dynamic HRC-FJSP and evaluates a carbon-aware multi-agent deep reinforcement learning scheduler (CA-MADRL) with local recovery after safety-proximity-induced collaboration disruption. The objective combines normalized makespan, carbon emission, and human workload imbalance with carbon accounting based on operation energy and time-varying grid carbon intensity. Across the benchmark cases, CA-MADRL obtains the best average global criterion (0.7235), wins nine of 12 cases, and achieves the lowest average carbon emissions among the compared policies (48.991 kg CO₂e). Sensitivity analysis shows that stronger carbon preference reduces emissions but increases makespan and tardiness, while adaptive collaboration outperforms fixed human–robot, human-only, and robot-only regimes. The results indicate that dynamic mode adaptation and local rescheduling improve carbon-aware collaborative schedules under safety disruption. Full article

(This article belongs to the Special Issue Human-Centred Manufacturing Towards Industry 5.0)

► Show Figures

Figure 1

35 pages, 50176 KB

Open AccessArticle

End-to-End Development and Cross-Platform Validation of a Heavy-Vehicle Anti-Lock Braking System Controller

by Abdul Moiz Awan, Selahattin Çağlar Başlamışlı, Mesut Kaya, Emrecan Hatipoğlu, Oğuzhan Bayram, Rümeysa Gençsev, Kutsihan Pehlivan and Mustafa Göleç

Machines 2026, 14(8), 930; https://doi.org/10.3390/machines14080930 - 12 Aug 2026

Viewed by 380

Abstract

Heavy-vehicle Anti-lock Braking System (ABS) controllers are commonly tested using simulations before vehicle testing, but pneumatic actuation and measurement limitations can affect the results in the field. This paper presents the complete design process of a pneumatic ABS controller. System identification tests, estimation [...] Read more.

Heavy-vehicle Anti-lock Braking System (ABS) controllers are commonly tested using simulations before vehicle testing, but pneumatic actuation and measurement limitations can affect the results in the field. This paper presents the complete design process of a pneumatic ABS controller. System identification tests, estimation experiments, and reverse engineering methods were used to develop the models used for testing, including a vehicle model, pneumatic circuit model, etc. Model-in-the-loop (MIL) and software-in-the-loop (SIL) simulations were used to test and validate the algorithm in the simulation environment. Hardware-in-the-loop (HIL) simulations were also used to test and tune the ABS algorithm using a physical pneumatic circuit before real vehicle testing. Lastly, the ABS controller was deployed to a custom ECU and tested on the real vehicle on dry and wet asphalt. The developed controller prevented sustained wheel lock and produced repeatable deceleration and stopping-distance results during dry- and wet-asphalt testing. Qualitative assessment by the test driver and engineering team also indicated ABS intervention and modulation characteristics broadly consistent with commercial alternatives. Full article

(This article belongs to the Special Issue Advances in Automotive Mechatronics)

► Show Figures

Graphical abstract

38 pages, 4839 KB

Open AccessArticle

Training-Aware Wavelet-Domain Controlled-Noise Augmentation for Residual Network-Based Bearing Fault Diagnosis

by Yifan Li, Jingtao Cheng, Yue Zhao and Ping Song

Machines 2026, 14(8), 929; https://doi.org/10.3390/machines14080929 - 12 Aug 2026

Viewed by 236

Abstract

Strong broadband noise can mask the weak impact responses produced by bearing faults, while wavelet reconstructions selected only by signal-domain scores may not provide useful inputs for diagnosis. To address this problem, this paper presents WPMSR-1D-ResNet, a training-aware wavelet-domain controlled-noise augmentation framework. PKPM-guided [...] Read more.

Strong broadband noise can mask the weak impact responses produced by bearing faults, while wavelet reconstructions selected only by signal-domain scores may not provide useful inputs for diagnosis. To address this problem, this paper presents WPMSR-1D-ResNet, a training-aware wavelet-domain controlled-noise augmentation framework. PKPM-guided particle swarm optimization first generates scale-specific perturbation candidates in the DWT detail coefficients. Signal-fidelity constraints remove distorted reconstructions, and a proxy CNN with identity fallback selects a global candidate according to validation Macro-F1. The final 1D-ResNet is trained jointly with the measured waveform and the selected augmented view, whereas inference uses only the raw signal. Under one fixed data construction and a common fixed 20-epoch budget, WPMSR-1D-ResNet achieved

0.8311 \pm 0.0607

Macro-F1 at the predefined CWRU low-SNR endpoint and ranked third among eleven methods, placing it within the leading statistical group. Its paired mean exceeded raw-signal 1D-ResNet and per-slice PKPM replacement by 0.05582 and 0.05227, respectively, with gains in nine of ten paired computational seeds. Mixed-SNR training increased mean Macro-F1 across eight mismatched-noise conditions from

0.5463 \pm 0.1320

to

0.6105 \pm 0.1292

. The method ranked second on PU and third on acquisition-held-out AT data; on AT, it reduced the normal-state false-alarm rate from 0.2854 to 0.1646 while maintaining 0.9708 fault sensitivity. Raw-only inference required 0.266 ms per slice. WPMSR-1D-ResNet, therefore, aligns wavelet augmentation with diagnostic performance, preserves useful waveform information, and removes wavelet reconstruction and PSO from the deployment path. Full article

(This article belongs to the Section Machines Testing and Maintenance)

► Show Figures

Figure 1

22 pages, 1042 KB

Open AccessArticle

Simulated Corrective Subgoal Supervision for Hierarchical Reinforcement Learning in Long-Horizon AntMaze Navigation

by Lidong Sun, Ye Wang, Zheheng Fan and Fuchun Sun

Machines 2026, 14(8), 928; https://doi.org/10.3390/machines14080928 - 12 Aug 2026

Viewed by 328

Abstract

Long-horizon navigation requires a high-level policy to select locally reachable subgoals, yet a scalar task reward provides little information about how an unsuitable proposal should be changed. We introduce Simulated Corrective Subgoal Supervision for Hierarchical Reinforcement Learning (SCS-HRL), a two-level method in which [...] Read more.

Long-horizon navigation requires a high-level policy to select locally reachable subgoals, yet a scalar task reward provides little information about how an unsuitable proposal should be changed. We introduce Simulated Corrective Subgoal Supervision for Hierarchical Reinforcement Learning (SCS-HRL), a two-level method in which a topology- and clearance-aware programmatic supervisor evaluates each proposed subgoal and returns both a scalar score and a continuous target in the same subgoal space. The score trains the high-level critic, and the target enters a masked regression term for the high-level actor. Primitive actions are always conditioned on the actor’s subgoal; the supervisor is inactive during learned-policy evaluation. In AntMaze, using 6000 training episodes, five seeds, and 100 deterministic evaluation episodes per seed, SCS-HRL attained an

88.4 \pm 7.8 %

final success rate (mean ± sample standard deviation; 95% Student-t confidence interval

[78.7 %, 98.1 %]

). The matched scalar-only condition and HIRO attained 0% rates. Applying the same route rule directly to the SCS-HRL low-level controllers yielded

82.2 \pm 9.9 %

success; the paired difference favored the learned high-level policy by 6.2 percentage points (95% confidence interval

[2.1, 10.3]

,

p = 0.013

). Across three matched seeds, nonzero corrective weights of 0.5, 1.0, and 2.0 remained stable, whereas 0.25 was seed-sensitive. Term-level ablations further show that the continuous target, rather than the exact scalar-shaping formula, was the principal additional signal. Separate fixed-policy tests obtained 0% success rates on two unseen maze layouts. These results indicate that continuous subgoal targets can encode task-specific route information in the source maze, while cross-layout transfer remains unresolved. Full article

(This article belongs to the Special Issue Machine Learning Application in Robots)

► Show Figures

Figure 1

36 pages, 3973 KB

Open AccessArticle

MPC-Informed Dynamic Screening for the Co-Design of Battery–Supercapacitor Hybrid Energy Storage Systems in Electric Vehicles

by Hanlin Lei, Benjamin Chong and Kang Li

Machines 2026, 14(8), 927; https://doi.org/10.3390/machines14080927 - 12 Aug 2026

Viewed by 251

Abstract

Hardware sizing and energy management for hybrid energy storage systems are usually designed sequentially, hiding the interactions between them. This paper proposes an MPC-informed dynamic screening framework in which every candidate configuration is simulated under one model predictive control law over a complete [...] Read more.

Hardware sizing and energy management for hybrid energy storage systems are usually designed sequentially, hiding the interactions between them. This paper proposes an MPC-informed dynamic screening framework in which every candidate configuration is simulated under one model predictive control law over a complete driving cycle, so that operational behaviour, not static metrics, determines selection. A fully documented post-evaluation criterion aggregates tracking, battery electrical stress, soft constraint violations and design overhead into one score normalised against an exact baseline anchor. Because one evaluation costs about 60 ms, the complete exact Pareto front of an electric transit bus case study is screened, not a sample. The static design cost proves almost uninformative regarding dynamic performance: the rank correlation between the two orderings is statistically indistinguishable from zero, the sets that they rank highest share no member, and the statically cheapest design falls far down the dynamic ranking, ending below the baseline. The cause is structural opposition on the pack voltage, which improves the dynamic performance but raises the static cost. The framework returns a leading design family that improves on the baseline overall, quantifies the battery stress that its leaner supercapacitor incurs, and shows the verdict to be robust to controller tuning but dependent on the duty and control strategy. Full article

(This article belongs to the Special Issue Dynamics and Control of Electric Vehicles)

► Show Figures

Graphical abstract

28 pages, 29173 KB

Open AccessArticle

Dynamic Modeling and Structural Angle Dynamic Characteristic Analysis of a Non-Circular Planetary Gear Train

by Haocong Xu, Bingliang Ye, Xuewen Huang, Yaxin Yu, Gaohong Yu and Liang Sun

Machines 2026, 14(8), 926; https://doi.org/10.3390/machines14080926 - 12 Aug 2026

Viewed by 207

Abstract

This study investigates the dynamic response of non-circular gear planetary trains in transplanting mechanisms, focusing on variable transmission effects. A time-varying mesh stiffness model was developed for non-circular gears using pitch curve parameters, incorporating pressure angle, contract ratio, and equivalent teeth number as [...] Read more.

This study investigates the dynamic response of non-circular gear planetary trains in transplanting mechanisms, focusing on variable transmission effects. A time-varying mesh stiffness model was developed for non-circular gears using pitch curve parameters, incorporating pressure angle, contract ratio, and equivalent teeth number as dynamic variables. A dynamic model of the planetary gear train was established to analyze component vibration characteristics. Comparative analysis reveals that non-circular gears’ variable-speed transmission significantly amplifies gear train vibrations compared to that of circular gears. Structural angle effects were examined, demonstrating the structural angle’s critical role in modulating vibration energy distribution between sun and planet gears. Frequency-domain analysis identified optimal structural angle ranges that minimize resonance risks by controlling component center vibrations. This work clarifies the coupling mechanisms between geometric parameters and transmission characteristics in non-circular gear systems. A design criterion based on frequency–energy distribution is proposed to optimize high-speed transplanting mechanisms. These findings advance the understanding of vibration modulation in variable-ratio gear trains and provide theoretical guidance for enhancing operational stability in agricultural machinery. Full article

(This article belongs to the Section Machine Design and Theory)

► Show Figures

Figure 1

24 pages, 1780 KB

Open AccessArticle

End-Effector Obstacle-Avoidance Trajectory Planning for Industrial Robotic Manipulators

by Chenfei Wen, Siyuan Zhang, Maksim A. Grigorev, Ivan Kholodilin, Victor Kushnarev, Dmitry Khriukin and Nikita Maksimov

Machines 2026, 14(8), 925; https://doi.org/10.3390/machines14080925 - 12 Aug 2026

Viewed by 237

Abstract

End-effector obstacle-avoidance trajectory planning is essential for improving the autonomy, safety, and executability of industrial robotic manipulators in constrained workspaces. Conventional Rapidly Exploring Random Tree (RRT) planners provide effective exploration capability but often suffer from stochastic tree expansion, redundant trajectories, and insufficient directional [...] Read more.

End-effector obstacle-avoidance trajectory planning is essential for improving the autonomy, safety, and executability of industrial robotic manipulators in constrained workspaces. Conventional Rapidly Exploring Random Tree (RRT) planners provide effective exploration capability but often suffer from stochastic tree expansion, redundant trajectories, and insufficient directional guidance near obstacle regions, which limits planning efficiency and trajectory quality. This study proposes a clearance-field-guided RRT framework with behavior-cloning-assisted refinement for end-effector obstacle-avoidance trajectory planning of industrial robotic manipulators. The proposed method formulates the planning problem in Cartesian space based on an end-effector kinematic model and introduces local clearance-field guidance into the RRT sampling process. Candidate samples are evaluated by considering obstacle clearance, reference-line deviation, and goal distance, enabling the search tree to preferentially expand toward effective traversable regions while maintaining the exploration capability of conventional RRT. Behavior cloning is further introduced as an offline auxiliary strategy to investigate the influence of expert trajectories on local motion-direction learning and trajectory continuity. A Python–Unity joint simulation–verification framework and a physical manipulator experimental platform are established to evaluate the feasibility and practical executability of the generated trajectories. Python is used for offline trajectory generation, expert dataset construction, behavior-cloning training, and performance evaluation, while Unity is employed for three-dimensional manipulator modeling and trajectory reproduction. The experimental results demonstrate that the proposed Field-guided RRT achieves a better balance among path efficiency, planning time, obstacle-clearance maintenance, and trajectory execution capability compared with conventional RRT-based methods. The proposed framework provides an effective solution for collision-free end-effector trajectory planning in industrial applications such as assembly, welding, component placement, and robotic inspection. Full article

(This article belongs to the Section Robotics, Mechatronics and Intelligent Machines)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Machines, Volume 14, Issue 8 (August 2026) – 121 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI