Machines

16 pages, 7860 KiB

Open AccessArticle

Optimized Variational Mode Decomposition and Convolutional Block Attention Module-Enhanced Hybrid Network for Bearing Fault Diagnosis

by Bin Yuan, Lei Lei and Suifan Chen

Machines 2025, 13(4), 320; https://doi.org/10.3390/machines13040320 (registering DOI) - 14 Apr 2025

Abstract

Accurate fault diagnosis remains a critical but unresolved issue in predictive maintenance, as industrial environments typically involve large amounts of electromagnetic interference and mechanical noise that can severely degrade the signal quality. In this study, we propose an innovative diagnostic framework to address [...] Read more.

Accurate fault diagnosis remains a critical but unresolved issue in predictive maintenance, as industrial environments typically involve large amounts of electromagnetic interference and mechanical noise that can severely degrade the signal quality. In this study, we propose an innovative diagnostic framework to address the challenging problem of bearing fault diagnosis in vibration signals under complex noise conditions. We develop the VMD-CNN-BiLSTM-CBAM model by systematically integrating the variational mode decomposition (VMD), convolutional neural network (CNN), bi-directional long and short-term memory network (BiLSTM), and convolutional block attention module (CBAM). The framework starts with VMD-based signal decomposition, which effectively separates the noise component from the bearing vibration features. Based on this denoising, a CNN architecture is employed to extract multi-scale spatio-temporal features through its hierarchical learning mechanism. The subsequent BiLSTM layer captures bidirectional temporal dependencies to model fault-evolution patterns, while the CBAM module strategically highlights key diagnostic features through adaptive channel spatial attention. Experimental validation using the Case Western Reserve University and Jiangnan University bearing datasets demonstrates the excellent performance of the model, with average accuracies of 99.76% and 99.40%, respectively. Finally, additional validation through our customized testbed confirms the usefulness of the model with an average accuracy of 99.70%. These results demonstrate that the proposed approach greatly improves fault diagnosis in noisy industrial environments through its synergistic architectural design and enhanced noise immunity. Full article

(This article belongs to the Special Issue Advanced Signal Processing Methods and Deep Neural Networks for Machine Fault Diagnosis)

► Show Figures

Figure 1

19 pages, 2177 KiB

Open AccessArticle

Current- and Vibration-Based Detection of Misalignment Faults in Synchronous Reluctance Motors

by Angela Navarro-Navarro, Vicente Biot-Monterde, Jose E. Ruiz-Sarrio and Jose A. Antonino-Daviu

Machines 2025, 13(4), 319; https://doi.org/10.3390/machines13040319 - 14 Apr 2025

Abstract

Misalignment faults in drive systems occur when the motor and load are not properly aligned, leading to deviations in the centerlines of the coupled shafts. These faults can cause significant damage to bearings, shafts, and couplings, making early detection essential. Traditional diagnostic techniques [...] Read more.

Misalignment faults in drive systems occur when the motor and load are not properly aligned, leading to deviations in the centerlines of the coupled shafts. These faults can cause significant damage to bearings, shafts, and couplings, making early detection essential. Traditional diagnostic techniques rely on vibration monitoring, which provides insights into both mechanical and electromagnetic fault signatures. However, its main drawback is the need for external sensors, which may not be feasible in certain applications. Alternatively, motor current signature analysis (MCSA) has proven effective in detecting faults without requiring additional sensors. This study investigates misalignment faults in synchronous reluctance motors (SynRMs) by analyzing both vibration and current signals under different load conditions and operating speeds. Fast Fourier transform (FFT) is applied to extract characteristic frequency components linked to misalignment. Experimental results reveal that the amplitudes of rotational frequency harmonics (

1 x f_{r}

,

2 x f_{r}

, and

3 x f_{r}

) increase in the presence of misalignment, with

1 x f_{r}

exhibiting the most stable progression. Additionally, acceleration-based vibration analysis proves to be a more reliable diagnostic tool compared to velocity measurements. These findings highlight the potential of combining current and vibration analysis to enhance misalignment detection in SynRMs, improving predictive maintenance strategies in industrial applications Full article

(This article belongs to the Special Issue New Advances in Synchronous Reluctance Motors)

► Show Figures

Figure 1

18 pages, 4367 KiB

Open AccessArticle

Efficient Real-Time Tool Chatter Detection Through Bandpass Filtering

by Javier Arenas, Jorge Martínez de Alegría, Patxi X. Aristimuño and Vicente Gómez

Machines 2025, 13(4), 318; https://doi.org/10.3390/machines13040318 - 14 Apr 2025

Abstract

Tool Chatter or Self-Excited Vibration is a common issue in machining processes. This phenomenon arises due to various factors, such as tool rigidity, depth of cut, spindle speed, etc., leading to poor surface finish, excessive tool wear, and premature deterioration of machine components. [...] Read more.

Tool Chatter or Self-Excited Vibration is a common issue in machining processes. This phenomenon arises due to various factors, such as tool rigidity, depth of cut, spindle speed, etc., leading to poor surface finish, excessive tool wear, and premature deterioration of machine components. To prevent tool chatter, a real-time chatter detection algorithm was developed using a low-cost accelerometer in combination with internal machine variables. The algorithm operates without requiring a prior model of the specific tool characteristics, making it capable of detecting chatter by simply knowing the number of teeth of the active tool. Furthermore, the implementation of the detection algorithm meets the strict requirements of real-time embedded systems, ensuring high determinism, low latency, and minimal computational cost. This enables efficient and optimal integration into the machine. The developed chatter detection system was validated through machine-based experimental testing. Full article

(This article belongs to the Special Issue Sensors and Signal Processing in Manufacturing Processes)

► Show Figures

Figure 1

18 pages, 2132 KiB

Open AccessArticle

Intelligent Casting Quality Inspection Method Integrating Anomaly Detection and Semantic Segmentation

by Min-Chieh Chen, Shih-Yu Yen, Yue-Feng Lin, Ming-Yi Tsai and Ting-Hsueh Chuang

Machines 2025, 13(4), 317; https://doi.org/10.3390/machines13040317 - 13 Apr 2025

Abstract

Wind power generation plays an important role in renewable energy, and the core casting components have extremely high requirements for precision and quality. In actual practice, we found that an insufficient workforce limits traditional manual inspection methods and often creates difficulty in unifying [...] Read more.

Wind power generation plays an important role in renewable energy, and the core casting components have extremely high requirements for precision and quality. In actual practice, we found that an insufficient workforce limits traditional manual inspection methods and often creates difficulty in unifying quality judgment standards. Customized optical path design is often required, especially when conducting internal and external defect inspections, which increases overall operational complexity and reduces inspection efficiency. We developed an automated optical inspection (AOI) system to address these challenges. The system integrates a semantic segmentation neural network to handle external surface detection and an anomaly detection model to detect internal defects. In terms of internal defect detection, the GC-AD-Local model we tested achieved 100% accuracy on experimental images, and the results were relatively stable. In the external detection part, we compared five different semantic segmentation models and found that MobileNetV2 performed the best in terms of average accuracy (65.8%). It was incredibly stable when dealing with surface defects with significant shape variations, and the prediction results were more consistent, making it more suitable for introduction into actual production line applications. Overall, this AOI system boosts inspection efficiency and quality consistency, reduces reliance on manual experience, and is of great assistance in quality control and process intelligence for wind power castings. We look forward to further expanding the amount of data and improving the generalization capabilities of the model in the future, making the system more complete and suitable for practical applications. Full article

(This article belongs to the Special Issue Compensation for Geometric Errors and Improvement in Accuracy through Innovative Design and Advanced Control Strategies)

► Show Figures

Figure 1

26 pages, 12604 KiB

Open AccessArticle

Investigation of Lattice Geometries Formed by Metal Powder Additive Manufacturing for Energy Absorption: A Comparative Study on Ti6Al4V, Inconel 718, and AISI 316L

by Ömer Faruk Çakır and Mehmet Erdem

Machines 2025, 13(4), 316; https://doi.org/10.3390/machines13040316 - 13 Apr 2025

Abstract

Impact absorbers are needed in many different areas in terms of energy absorption and crashworthiness. While the design of these structures is expected to increase mechanical performance, they are expected to be lightweight, and when evaluated in this context, lattice structures come to [...] Read more.

Impact absorbers are needed in many different areas in terms of energy absorption and crashworthiness. While the design of these structures is expected to increase mechanical performance, they are expected to be lightweight, and when evaluated in this context, lattice structures come to the fore. In this study, impact absorbers, also known as crash boxes, consisting of lattice structures designed to increase energy absorption performance were fabricated by a new manufacturing method, metal powder additive manufacturing, and their mechanical performance was experimentally investigated under quasi-static axial loading, and energy absorption data were obtained. The specimens were designed from Ti6Al4V, INC 718, and AISI 316L materials by forming 18 matrix structures with square and hexagonal geometries. According to this study, the lattice structures absorbed up to 4.5 times more energy than the shell structures of a similar material group. According to the normalized values among all samples, the hexagonal sample made of Ti6Al4V material showed 4.3 times higher energy absorption efficiency. The AISI 316L material showed the best crushing performance due to its ductile structure. Full article

(This article belongs to the Section Vehicle Engineering)

► Show Figures

Figure 1

15 pages, 5408 KiB

Open AccessArticle

Research on the Configuration of Wheeled Mobile Welding Robots Under Multiple Working Conditions

by Shuyan Yao, Long Xue, Jiqiang Huang, Yong Zou and Ruiying Zhang

Machines 2025, 13(4), 315; https://doi.org/10.3390/machines13040315 - 12 Apr 2025

Abstract

Mobile welding robots have attracted considerable attention due to their flexible movement and robust adaptability, offering substantial market potential. However, the complexity of their operational conditions poses specific demands on robot configurations, with no established design methodology available at the time. To address [...] Read more.

Mobile welding robots have attracted considerable attention due to their flexible movement and robust adaptability, offering substantial market potential. However, the complexity of their operational conditions poses specific demands on robot configurations, with no established design methodology available at the time. To address this challenge, we constructed Lagrange’s equations for wheeled mobile welding robots. Through simplification and deduction analysis, we concluded that larger wheeled mobile welding robots are suited for paths with larger curvature radii, whereas smaller ones are more appropriate for paths with smaller curvature radii. Based on the above analysis and considering the load-bearing capacity of the robot, we proposed a configuration design method for wheeled mobile welding robots, evolving from large to small and micro wheels, including track constraints and wheel number adjustments. Subsequently, prototype robots, including magnetic wheel, tracked, and flexible contour tracing mobile welding robots, have been developed to accommodate various operational conditions. Welding experiments demonstrate that these three configurations, distinguished by their travel path curvature radii, can effectively meet the mobile welding requirements of their respective environments. The effectiveness of the configuration design of wheeled mobile welding robots under different working conditions has been verified. Full article

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

► Show Figures

Figure 1

34 pages, 3804 KiB

Open AccessArticle

EnsembleXAI-Motor: A Lightweight Framework for Fault Classification in Electric Vehicle Drive Motors Using Feature Selection, Ensemble Learning, and Explainable AI

by Md. Ehsanul Haque, Mahe Zabin and Jia Uddin

Machines 2025, 13(4), 314; https://doi.org/10.3390/machines13040314 - 12 Apr 2025

Abstract

As electric vehicles (EVs) are growing, the fault diagnosis in their drive motor becomes more important to have optimal performance and safety. Traditional fault detection methods suffer mainly from high false positive and false negative rates, computational complexity, and lack of transparency in [...] Read more.

As electric vehicles (EVs) are growing, the fault diagnosis in their drive motor becomes more important to have optimal performance and safety. Traditional fault detection methods suffer mainly from high false positive and false negative rates, computational complexity, and lack of transparency in decision-making methods. In addition, existing models are also heavy and inefficient. A lightweight framework for fault diagnosis in EV drive motors is presented with the aid of Recursive Feature Elimination with Cross-Validation (RFE-CV), parameter optimization, and in-depth preprocessing. We further optimize the models and their combination to a hybrid Soft Voting Classifier. These techniques were applied to a dataset of 40,040 data entries that had been simulated by a Variable Frequency Drive (VFD) model. We evaluated eight machine learning models, and our proposed Soft Voting Classifier has the highest test accuracy of 94.52% and a Kappa score of 0.9210 on diagnostic performance. Also, the model has minimal memory usage and low inference latency. In addition, Local Interpretable Model-Agnostic Explanations (LIME) were used to improve transparency and gain an understanding of decisions made through the Soft Voting Classifier. Also, the framework was validated by an additional real-world dataset, thereby further confirming its robustness and consistency in performance for different conditions, which indicates the generalizability of the framework in real-world applications. RFE-CV is found to be very effective in feature selection and helps to construct a lightweight and cost-effective ensemble voting model for enhancing fault diagnosis for EV Drive Motors, overcoming its unsatisfactory transparency, accuracy, and computational efficiency. Finally, it contributes to the development of safer and more reliable EV systems through the development of models supervised on fewer features to give the computing time that is a little lighter without compromising its diagnostic performance. Full article

(This article belongs to the Special Issue Recent Developments in Machine Design, Automation and Robotics)

► Show Figures

Figure 1

19 pages, 1358 KiB

Open AccessArticle

Friction Monitoring in Kaplan Turbines

by Lars-Johan Sandström, Kim Berglund, Pär Marklund and Gregory F. Simmons

Machines 2025, 13(4), 313; https://doi.org/10.3390/machines13040313 - 11 Apr 2025

Abstract

Hydropower is important in the modern power system due to its ability to quickly adjust production. More frequent use of this ability may lead to increased maintenance needs, highlighting the importance of research in condition monitoring for hydropower. This study suggests a model [...] Read more.

Hydropower is important in the modern power system due to its ability to quickly adjust production. More frequent use of this ability may lead to increased maintenance needs, highlighting the importance of research in condition monitoring for hydropower. This study suggests a model approach for friction monitoring of the bearings inside the Kaplan turbine’s hub. The approach is developed for when normal and anomalous data exist. The study compares isolation forest (iForest), local outlier factor (LOF), one-class support vector machine (OC-SVM), and Mahalanobis distance (MD) for anomaly detection, where iForest and OC-SVM appear to be good choices due to their robust performance. A moving decision filter (MDF) is fed with the output from the anomaly detection models to classify the data as normal or anomalous. The parameters in the MDF are optimized with Bayesian optimization to increase the performance of the models. The approach is tested using data from two actual hydropower turbines. The study shows that the model approach works for both turbines. However, the parameter optimization must be performed separately for each turbine. Full article

(This article belongs to the Special Issue Vibration-Based Machines Wear Monitoring and Prediction)

► Show Figures

Figure 1

18 pages, 6221 KiB

Open AccessArticle

A Study on the Wear Characteristics of a Point Contact Pair of Angular Contact Ball Bearings Under Mixed Lubrication

by Yongjian Yu, Zifan Dong, Yujun Xue, Haichao Cai and Jun Ye

Machines 2025, 13(4), 312; https://doi.org/10.3390/machines13040312 - 11 Apr 2025

Abstract

Under mixed lubrication, the macro size is affected by the wear of the surface roughness peaks, which results in degradation of the bearing accuracy. To study the wear characteristics of rolling bearings under mixed lubrication, based on the elastohydrodynamic lubrication theory and Archard [...] Read more.

Under mixed lubrication, the macro size is affected by the wear of the surface roughness peaks, which results in degradation of the bearing accuracy. To study the wear characteristics of rolling bearings under mixed lubrication, based on the elastohydrodynamic lubrication theory and Archard wear model, and considering the coupling of the oil film and roughness, a wear prediction model of angular contact ball bearings under mixed lubrication was established, and the influence of the working parameters and hardness on bearing wear was analyzed. The results show that the wear depth of the outer grove increases with an increase in the load, or a decrease in the rotational speed or the initial viscosity of lubricating oil. The load has the most significant effect on the wear depth of the outer grove. There is a critical value for the load, rotational speed, and initial viscosity of the lubricating oil, which varies with the parameters of other working conditions and the hardness of the materials. When the increase in load exceeds the critical value or the rotational speed and initial viscosity of lubricating oil are less than the critical value, the outer groove fails because the wear depth exceeds the critical value of wear depth. The ratio of the load on the rolling element to the hardness of the outer grove at different entrainment speeds and initial viscosities of lubricating oil can be used to predict the wear degree of the outer grove. When the ratio is greater than a certain threshold, the outer grove is faulted owing to wear, and the threshold decreases with an increase in the initial viscosity of lubricating oil or the decrease in rotational speed. Full article

(This article belongs to the Section Friction and Tribology)

► Show Figures

Figure 1

28 pages, 8808 KiB

Open AccessArticle

Design and Dimension Optimization of Rigid–Soft Hand Function Rehabilitation Robots

by Rui Zhang, Meng Ning, Yuqian Wang and Jun Yang

Machines 2025, 13(4), 311; https://doi.org/10.3390/machines13040311 - 11 Apr 2025

Abstract

The growing population of hand dysfunction patients necessitates advanced rehabilitation technologies. Current robotic solutions face limitations in motion compatibility and systematic design frameworks. This study develops a rigid–soft coupling rehabilitation robot integrating linkage mechanisms with soft components. A machine vision system captures natural [...] Read more.

The growing population of hand dysfunction patients necessitates advanced rehabilitation technologies. Current robotic solutions face limitations in motion compatibility and systematic design frameworks. This study develops a rigid–soft coupling rehabilitation robot integrating linkage mechanisms with soft components. A machine vision system captures natural grasping trajectories, analyzed through polynomial regression. Hierarchical constraint modeling and an improved artificial bee colony algorithm optimize linkage dimensions and control strategies, achieving enhanced human–robot kinematic matching. Finite element simulations using a Yeoh hyperelastic model refine soft component geometry for balance compliance and coordination. Prototype validation demonstrates high-precision trajectory tracking, grasping across 20–70 mm objects, and steady fingertip forces during training. Experimental results confirm the system’s ability to replicate physiological motion patterns and adapt to multiple rehabilitation scenarios. Full article

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

► Show Figures

Figure 1

39 pages, 9094 KiB

Open AccessArticle

Analysis of the Interaction of Robots as Part of a Robotic System for Biomaterial Aliquotation

by Sergey Khalapyan, Larisa Rybak, Dmitry Malyshev, Vladislav Cherkasov and Vladislav Vorobyev

Machines 2025, 13(4), 310; https://doi.org/10.3390/machines13040310 - 11 Apr 2025

Abstract

The paper considers the problem of interaction between robots with parallel and serial structures that are part of a robotic system for aliquoting biomaterials. An approach to selecting the relative position and limiting the ranges of movement of manipulators working nearby to avoid [...] Read more.

The paper considers the problem of interaction between robots with parallel and serial structures that are part of a robotic system for aliquoting biomaterials. An approach to selecting the relative position and limiting the ranges of movement of manipulators working nearby to avoid collisions is presented. The elimination of collisions is ensured by the absence of intersections between work safety zones (a 3D space within which all manipulator links can be located for a given range of robot positions). Universal algorithms for determining work safety zones were developed, including for an individual manipulator and taking into account the work safety zone of the manipulator installed nearby and other obstacles. An analysis of the workspace and safety zones was performed, taking into account both individual limitations and limitations associated with collaboration within the system. The issue of adapting control algorithms of the robotic system to external disturbances in order to minimize the time spent on executing a given trajectory was addressed. In particular, the meeting point (interaction) of robots solving the problem of biomaterial aliquotation was optimized depending on the workload level of each robot. Experiments were carried out to verify the developed approaches. Full article

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

► Show Figures

Figure 1

18 pages, 11807 KiB

Open AccessArticle

Analysis of the Fracture and the Repair of the Screw Spindle of a Friction Screw Press

by Rade Vasiljević and Dragan Pantelić

Machines 2025, 13(4), 309; https://doi.org/10.3390/machines13040309 - 10 Apr 2025

Abstract

The drive mechanism of a friction screw press consists of a screw transmission, a friction transmission and a belt transmission. Improper maintenance and axial misalignment of the screw spindle and the press are the main possible causes of screw spindle failure. The causes [...] Read more.

The drive mechanism of a friction screw press consists of a screw transmission, a friction transmission and a belt transmission. Improper maintenance and axial misalignment of the screw spindle and the press are the main possible causes of screw spindle failure. The causes of the screw spindle fracture are investigated in the first part of this paper. A visual examination of the screw spindle is carried out in the first step. In the second step, the chemical composition and mechanical properties of the material from which the screw spindle of the drive mechanism is made are experimentally examined, and a metallographic examination of the fracture surfaces on the screw spindle is carried out using an electronic microscope. In the second part of this paper, the effects of screw spindle disturbances on the fracture are analyzed by applying the finite element method. The third part of this paper shows how the problem of repairing the damaged screw spindle of the drive mechanism of the friction screw press is solved. Firstly, the repair solution is described. Then, a safety check of the welded joint is presented. The final part refers to the techno-economic justification of the performed repair of the screw spindle. The obtained research results are important because the same problems or similar problems could appear in machine elements of various types of machine tools. Full article

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

► Show Figures

Figure 1

19 pages, 16287 KiB

Open AccessArticle

Effect of In-Situ Pulse Current on Microstructure and Mechanical Properties of AISI 9310 Gear Steel by Laser Powder Directed Energy Deposition

by Cenchao Xie, Fei Yang, Peng He, Wenfa Liu, Qiang Feng, Liucheng Zhou, Ping Liu and Xin Sun

Machines 2025, 13(4), 308; https://doi.org/10.3390/machines13040308 - 10 Apr 2025

Abstract

AISI 9310 gear steel, renowned for its high hardenability, is widely employed in the manufacturing of aerospace gear components. Laser powder directed energy deposition (LP-DED) takes advantage of a laser heat source to melt metal powder, thus creating a molten pool and facilitating [...] Read more.

AISI 9310 gear steel, renowned for its high hardenability, is widely employed in the manufacturing of aerospace gear components. Laser powder directed energy deposition (LP-DED) takes advantage of a laser heat source to melt metal powder, thus creating a molten pool and facilitating the quick achievement of material deposition and shaping. However, the issue of forming quality has been acting as a significant constraint on the development of LP-DED. To address this concern, the present research endeavors to enhance LP-DED by leveraging the assisted application of in situ pulsed current, with the aim of preparing high-quality deposited specimens. It has been observed that the pulsed current does not trigger any phase transformation within the deposition zone. Instead, the Joule heating effect brought about by the current serves as a catalyst for grain growth. Meanwhile, the electric-plastic effect of the pulsed current results in an elevation of plastic deformation. Moreover, it facilitates the transformation of dislocation defects from simple dislocation lines to intricate dislocation networks, consequently leading to a substantial increase in dislocation density. Furthermore, the contraction force induced by the current exerts a compressive influence on the molten pool, which in turn accelerates the discharge of gas. Full article

(This article belongs to the Section Advanced Manufacturing)

► Show Figures

Figure 1

26 pages, 6409 KiB

Open AccessArticle

Design of Rotors in Centrifugal Pumps Using the Topology Optimization Method and Parallel Computing in the Cloud

by Xavier Andrés Arcentales, Danilo Andrés Arcentales and Wilfredo Montealegre

Machines 2025, 13(4), 307; https://doi.org/10.3390/machines13040307 - 10 Apr 2025

Abstract

Designing flow machines is challenging due to numerous free geometrical parameters. This work aims to develop a parallelized computational algorithm in MATLAB version R2020a to design the rotor of a radial flow in a centrifugal pump using the finite-element method (FEM), topology optimization [...] Read more.

Designing flow machines is challenging due to numerous free geometrical parameters. This work aims to develop a parallelized computational algorithm in MATLAB version R2020a to design the rotor of a radial flow in a centrifugal pump using the finite-element method (FEM), topology optimization method (TOM), and parallel cloud computing (bare-metal vs. virtual machine). The goal is to minimize a bi-objective function comprising energy dissipation and vorticity within half a rotor circumference. When only minimizing energy dissipation (wd = 1, wr = 0), the performance achieved is 5.88 Watts. Considering both energy dissipation and vorticity (wd = 0.8, wr = 0.2), the performance is 5.94 Watts. These topology results are then extended to a full 3D model using Ansys Fluent version 18.2 to validate the objective functions minimized by TOM. The algorithm is parallelized and executed on multiple CPU cores in the cloud on two different platforms: Amazon Web Services (virtual machine) and Equinix (bare-metal machine), to accelerate the blade design process. In conclusion, mathematical optimization tools aid engineering designers in achieving non-intuitive designs and enhancing results. Full article

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

► Show Figures

Figure 1

22 pages, 9685 KiB

Open AccessArticle

Fatigue Damage Assessment of a Metro Vehicle Bogie Frame Based on Measured Field Load

by Yangmin Wu and Zunsong Ren

Machines 2025, 13(4), 306; https://doi.org/10.3390/machines13040306 - 9 Apr 2025

Abstract

As the operating conditions of metro vehicles become more complex, the fatigue damage of metro bogie frames under actual operating conditions becomes increasingly difficult to evaluate realistically. After a period of operation of metro trains, the load excitation on the frame and its [...] Read more.

As the operating conditions of metro vehicles become more complex, the fatigue damage of metro bogie frames under actual operating conditions becomes increasingly difficult to evaluate realistically. After a period of operation of metro trains, the load excitation on the frame and its vibrations become more intense, which causes elastic resonance and leads to fatigue damage. Therefore, it is of high importance to establish test load conditions that match the actual operating environment to conduct fatigue reliability research on frames. To address this problem, in this study, we developed a high-precision force measurement frame and performed a long-term field test. The load optimization factor was used to quantify the load amplitude amplification near the modal frequency caused by the frame elastic resonance. The real load conditions and damage conditions of the fatigued weak position were obtained. Additionally, the square of the difference between the damage calculated via the load spectrum and the measured damage was used as the objective function; the calibrated test load spectrum fully covered the fatigued weak position damage as the constraint condition. The load spectrum calibration coefficient was obtained via multi-objective optimization through a genetic algorithm. The results showed that the damage calculated using the calibrated load agreed well with the real damage, and the ratio of the equivalent stress amplitude between the two was in the range of 1–2. The calibrated test load spectrum obtained in this study can be used for the structural optimization and fatigue reliability design of the later frame. The findings reported here can also be applied to other dynamic systems where fatigue failure is a critical issue. Full article

(This article belongs to the Section Vehicle Engineering)

► Show Figures

Figure 1

20 pages, 7512 KiB

Open AccessArticle

Fatigue Crack Growth Simulation of R260 Grade Pearlitic Rail Steel Using the Discrete Element Method

by Hamed Davoodi Jooneghani, Klaus Six, Saham Sadat Sharifi, Maria Cecilia Poletti and Gerald Trummer

Machines 2025, 13(4), 305; https://doi.org/10.3390/machines13040305 - 9 Apr 2025

Abstract

Fatigue-induced crack initiation and propagation are a major concern in pearlitic railway rails and wheels. Rails and wheels undergo significant plastic deformation on their near-surface layers during service, leading to the initiation and propagation of cracks within the deformed region. Existing models typically [...] Read more.

Fatigue-induced crack initiation and propagation are a major concern in pearlitic railway rails and wheels. Rails and wheels undergo significant plastic deformation on their near-surface layers during service, leading to the initiation and propagation of cracks within the deformed region. Existing models typically use finite element models (FEMs) to describe these kinds of fatigue phenomena. However, they fail to establish a strong connection between the microstructure of the undeformed and the deformed materials and their corresponding fatigue properties. Therefore, a model based on the soft-contact discrete element method (DEM) was developed that considers microstructural details such as prior austenite grains (PAGs), pearlite blocks, pearlite colonies, and lamellar orientation of the ferrite–cementite structure of the pearlite. The Voronoi Tessellation method was used to generate a hierarchical mesh to represent these microstructural details, considering the distribution of microstructural details. Crack propagation is simulated by applying damage laws on the microstructural interface level that degrade the stiffness of the fibers connecting the mesh elements. The model’s crack growth predictions are compared with experimental results from the literature to validate its accuracy for different deformation degrees. The developed model can be used in the designing and material selection phase in the railway industry to help select the material with optimum microstructural features. Also, it can be used for the selection of the optimum heat treatment process considering materials resistance to the fatigue crack growth. Full article

(This article belongs to the Special Issue Wheel–Rail Contact: Mechanics, Wear and Analysis)

► Show Figures

Figure 1

17 pages, 2587 KiB

Open AccessArticle

A Cyber Manufacturing IoT System for Adaptive Machine Learning Model Deployment by Interactive Causality-Enabled Self-Labeling

by Yutian Ren, Yuqi He, Xuyin Zhang, Aaron Yen and Guann-Pyng Li

Machines 2025, 13(4), 304; https://doi.org/10.3390/machines13040304 - 8 Apr 2025

Abstract

Machine learning (ML) has been demonstrated to improve productivity in many manufacturing applications. To host these ML applications, several software and Industrial Internet of Things (IIoT) systems have been proposed for manufacturing applications to deploy ML applications and provide real-time intelligence. Recently, an [...] Read more.

Machine learning (ML) has been demonstrated to improve productivity in many manufacturing applications. To host these ML applications, several software and Industrial Internet of Things (IIoT) systems have been proposed for manufacturing applications to deploy ML applications and provide real-time intelligence. Recently, an interactive causality-enabled self-labeling method has been proposed to advance adaptive ML applications in cyber–physical systems, especially manufacturing, by automatically adapting and personalizing ML models after deployment to counter data distribution shifts. The unique features of the self-labeling method require a novel software system to support dynamism at various levels. This paper proposes the AdaptIoT system, comprising an end-to-end data streaming pipeline, ML service integration, and an automated self-labeling service. The self-labeling service consists of causal knowledge bases and automated full-cycle self-labeling workflows to adapt multiple ML models simultaneously. AdaptIoT employs a containerized microservice architecture to deliver a scalable and portable solution for small and medium-sized manufacturers. A field demonstration of a self-labeling adaptive ML application is conducted with a makerspace and shows reliable performance with comparable accuracy at 98.3%. Full article

(This article belongs to the Special Issue Innovative Manufacturing Engineering 2024—Processes, Machines, Tooling and Systems Integration)

► Show Figures

Figure 1

22 pages, 32993 KiB

Open AccessArticle

Leveraging Digital Twin Technology with a Human-Centered Approach to Automate a Workstation in the Logistics Sector of Made in Italy: CHIMAR Use Case

by Annalisa Bertoli, Matteo Nini, Valerio Cibrario, Manuela Vargas, Paolo Perona, Ludovico Rossi, Laura Benedetti, Alberto Nicolinti and Cesare Fantuzzi

Machines 2025, 13(4), 303; https://doi.org/10.3390/machines13040303 - 7 Apr 2025

Abstract

Industry 4.0 has driven the development of important technologies for industrial applications, but the focus has often been on technological advancement rather than on how operators interact with these systems. With the emergence of Industry 5.0, attention has shifted toward the role of [...] Read more.

Industry 4.0 has driven the development of important technologies for industrial applications, but the focus has often been on technological advancement rather than on how operators interact with these systems. With the emergence of Industry 5.0, attention has shifted toward the role of the operators and their interaction with emerging technologies. This paper explores the automation of a fully manual operation in the logistics field while adopting a human-centered approach to reduce risky tasks and enhance the operator’s well-being. A motion capture system and digital human simulation software are utilized to create a digital twin of a real-world industrial case study. This approach enables the virtual testing of various automation solutions to identify the optimal scenario that meets the performance indicator parameters. This study highlights the importance of integrating ergonomic considerations into automation strategies. Full article

(This article belongs to the Special Issue Digital Technologies to Support Human Factors Engineering in Manufacturing System Design: Theory and Applications)

► Show Figures

Figure 1

12 pages, 7226 KiB

Open AccessArticle

Deep Transfer Learning-Based Performance Prediction Considering 3-D Flux in Outer Rotor Interior Permanent Magnet Synchronous Motors

by Moo-Hyun Sung, Soo-Hwan Park, Kyoung-Soo Cha, Jae-Han Sim and Myung-Seop Lim

Machines 2025, 13(4), 302; https://doi.org/10.3390/machines13040302 - 7 Apr 2025

Abstract

Accurate performance prediction in the design phase of permanent magnet synchronous motors (PMSMs) is essential for optimizing efficiency and functionality. While 2-D finite element analysis (FEA) is commonly used due to its low computational cost, it overlooks important 3-D flux components such as [...] Read more.

Accurate performance prediction in the design phase of permanent magnet synchronous motors (PMSMs) is essential for optimizing efficiency and functionality. While 2-D finite element analysis (FEA) is commonly used due to its low computational cost, it overlooks important 3-D flux components such as axial leakage flux (ALF) and fringing flux (FF) that affect motor performance. Although 3-D FEA can account for these flux components, it is computationally expensive and impractical for rapid design iterations. To address this challenge, we propose a performance prediction method for interior permanent magnet synchronous motors (IPMSMs) that incorporates 3-D flux effects while reducing computational time. This method uses deep transfer learning (DTL) to transfer knowledge from a large 2-D FEA dataset to a smaller, computationally costly 3-D FEA dataset. The model is trained in 2-D FEA data and fine-tuned with 3-D FEA data to predict motor performance accurately, considering design variables such as stator diameter, axial length, and rotor design. The method is validated through 3-D FEA simulations and experimental testing, showing that it reduces computational time and accurately predicts motor characteristics compared to traditional 3-D FEA approaches. Full article

(This article belongs to the Special Issue Fault Diagnostics and Fault Tolerance of Synchronous Electric Drives)

► Show Figures

Figure 1

Journal Description

Machines

Latest Articles

Journal Menu

Journal Browser

Highly Accessed Articles

Latest Books

E-Mail Alert

News

Topics

Conferences

Special Issues

Topical Collections

Further Information

Guidelines

MDPI Initiatives

Follow MDPI