Search Results (422)

This review systematically examined the transformative role of machine learning in predicting polymer aging lifetime, addressing critical limitations of conventional methods such as the Arrhenius model, time–temperature superposition principle, and numerical fitting approaches. The primary objective was to establish a comprehensive framework that integrates multi-mechanism coupling with dynamic data-driven modeling to enhance prediction accuracy across complex aging scenarios. Four key machine learning categories demonstrate distinct advantages: support vector machines effectively capture nonlinear interactions in multi-stress environments; neural networks enable cross-scale modeling from molecular dynamics to macroscopic failure; decision tree models provide interpretable feature importance quantification; and hybrid approaches synergistically combine complementary strengths. These methodologies have shown significant success in critical industrial applications, including building trades, photovoltaic systems, and aerospace composites, creating an integrated predictive system that bridges molecular-level dynamics with service-life performance. By transforming life prediction from empirical extrapolation to mechanism-based simulation, this machine-learning-driven paradigm offers robust methodological support for engineering safety design in diverse polymer applications through its capacity to model complex environmental interactions, adapt to real-time monitoring data, and elucidate underlying degradation mechanisms. Full article

The assessment of wheel–rail force states is a key technical issue in the safety monitoring of high-speed railway turnouts. Due to the complex geometry and severe load fluctuations of turnouts, wheel–rail interactions exhibit strong nonlinearity, asymmetry, and multidimensional coupling characteristics. Traditional methods suffer from limitations such as reliance on labeled samples and poor real-time performance. This study proposes an intelligent evaluation method that integrates multivariate statistical analysis with unsupervised clustering, and establishes a multidimensional analytical framework incorporating data preprocessing, time-domain analysis, safety index evaluation, frequency-domain feature extraction, and cluster-based recognition. Using a turnout section of the Beijing–Tianjin Intercity Railway as a case study, four fundamental wheel–rail force components were selected as feature variables to reveal their dynamic patterns. The DBSCAN density-based clustering algorithm was employed to achieve unsupervised state identification, successfully classifying three typical operating states: normal, high-load abnormal, and extreme load. The clustering silhouette coefficient reached 0.563, significantly outperforming K-means and hierarchical clustering. Safety evaluation results indicate that all relevant indicators meet international standards. The proposed method requires no labeled samples and offers strong physical interpretability and engineering applicability, providing effective support for turnout condition awareness and predictive maintenance. Full article

Drones are increasingly being used in maritime engineering for ship maintenance, emergency rescue, and safety monitoring tasks. In these tasks, action recognition is important for human–drone interaction and for detecting abnormal situations such as falls or distress signals. However, the maritime environment is highly challenging, with illumination variations, water spray, and dynamic backgrounds often leading to ambiguity between similar actions. To address this issue, we propose MSG-GCN, a multi-semantic guided graph convolutional network for human action recognition. Specifically, MSG-GCN integrates structured prior semantic information and further introduces a textual–semantic alignment mechanism to improve the consistency and expressiveness of multimodal features. Benefiting from its lightweight hierarchical design, our model offers excellent deployment flexibility, making it well suited for resource-constrained UAV applications. Experimental results on large-scale benchmark datasets, including NTU60, NTU120 and UAV-human, demonstrate that MSG-GCN surpasses state-of-the-art methods in both classification accuracy and computational efficiency. Full article

The aviation industry operates as a complex, dynamic system generating vast volumes of data from aircraft sensors, flight schedules, and external sources. Managing this data is critical for mitigating disruptive and costly events such as mechanical failures and flight delays. This paper presents a comprehensive application of predictive analytics and machine learning to enhance aviation safety and operational efficiency. We address two core challenges: predictive maintenance of aircraft engines and forecasting flight delays. For maintenance, we utilise NASA’s C-MAPSS simulation dataset to develop and compare models, including one-dimensional convolutional neural networks (1D CNNs) and long short-term memory networks (LSTMs), for classifying engine health status and predicting the Remaining Useful Life (RUL), achieving classification accuracy up to 97%. For operational efficiency, we analyse historical flight data to build regression models for predicting departure delays, identifying key contributing factors such as airline, origin airport, and scheduled time. Our methodology highlights the critical role of Exploratory Data Analysis (EDA), feature selection, and data preprocessing in managing high-volume, heterogeneous data sources. The results demonstrate the significant potential of integrating these predictive models into aviation Business Intelligence (BI) systems to transition from reactive to proactive decision-making. The study concludes by discussing the integration challenges within existing data architectures and the future potential of these approaches for optimising complex, networked transportation systems. Full article

Over the service life of several decades, structural damage detection is crucial for ensuring the safety and durability of engineering structures. However, existing methods often overlook the spatiotemporal coupling in multi-sensor data, hindering the full exploitation of structural dynamic evolution and spatial correlations. This paper proposes an autoencoder model integrating Temporal Convolutional Networks (TCN) and Graph Attention Networks (GAT), termed TCNGAT-AE, to establish an unsupervised damage detection method. The model utilizes the TCN module to extract temporal dependencies and dynamic features from vibration signals, while leveraging the GAT module to explicitly capture the spatial topological relationships within the sensor network, thereby achieving deep fusion of spatiotemporal features. The proposed method adopts an “offline training-online detection” framework, requiring only data from the healthy state of the structure for training, and employs reconstruction error as the damage indicator. To validate the proposed method, two sets of experimentally measured data are utilized: one from the Z-24 concrete box-girder bridge under ambient excitation, and the other from the Old Ada Bridge under vehicle load excitation. Additionally, ablation studies are conducted to analyze the effectiveness of the spatiotemporal fusion mechanism. Results demonstrate that the proposed method achieves effective damage detection in both different structural types and excitation scenarios. Furthermore, the explicit modeling of spatiotemporal features significantly enhances detection performance, with the anomaly detection rate showing substantial improvement compared to baseline models utilizing only temporal or spatial modeling. Moreover, this end-to-end framework processes raw vibration signals directly, avoiding complex preprocessing. This makes it highly suitable for practical and near-real-time monitoring. The findings of this study demonstrate that the damage detection method based on TCNGAT-AE can be effectively applied to structural safety monitoring in complex engineering environments, and can be further integrated with real-time monitoring systems of critical structures for online analysis. Full article

This study evaluates four developed external Human–Machine Interface (eHMI) concepts for automated shuttles, focusing on improving communication with other road users, mainly pedestrians and cyclists. Without a human driver to signal intentions, eHMI systems can play a crucial role in conveying the shuttle’s movements and future path, fostering safety and trust. The four eHMI systems’ purple light projections, emotional eyes, auditory alerts, and informative text were tested in a virtual reality (VR) environment. Participant evaluations were collected using an approach inspired by Kansei engineering and Likert scales. Results show that auditory alerts and informative text-eHMI are most appreciated, with participants finding them relatively clear and easy to understand. In contrast, purple light projections were hard to see in daylight, and emotional eyes were often misinterpreted. Principal Component Analysis (PCA) identified three key factors for eHMI success: predictability, endangerment, and practicality. The findings underscore the need for intuitive, simple, and predictable designs, particularly in the absence of a driver. This study highlights how eHMI systems can support the integration of automated shuttles into public transport. It offers insights into design features that improve road safety and user experience, recommending further research on long-term effectiveness in real-world traffic conditions. Full article

Background: In the evolving landscape of pathology, Laboratory Information Systems (LISs) have become essential tools for ensuring traceability, efficiency, and data security in diagnostic workflows. Methods: This study presents a comprehensive comparative analysis of three major LIS platforms used in Italian pathology laboratories in 2025: Armonia (Dedalus), Pathox Web (Tesi Group), and WinSAP 3.0 (Engineering). Each system is evaluated across key parameters, including sample traceability, integration with hospital systems, digital reporting, user interface, and compliance with regulatory standards such as GDPR and ISO 15189. Results: Armonia stands out for its advanced integration capabilities, scalability, and support for digital pathology, making it ideal for large institutions. Pathox Web offers a balanced solution with strong usability and web-based accessibility, suitable for medium-sized laboratories. WinSAP 3.0, while more limited in modern features, remains a stable and cost-effective option for many facilities. This study emphasizes the strategic importance of selecting an LIS aligned with institutional needs, highlighting its role in enhancing diagnostic quality, operational safety, and future integration with artificial intelligence and automation. Conclusions: The findings support informed decision-making in LIS adoption, critically contributing to the management of scientific and economic data of pathology services in Italy. Full article

Titanium (Ti) alloy sheets are important mechanical and structural components. However, thickness deviations may occur during the production of Ti-alloy sheets, significantly compromising product quality and structural safety. Eddy current testing (ECT) is a common method for measuring the thickness deviation of metal sheets. Nevertheless, conventional ECT methods often rely on complex calibration procedures or iterative inversion algorithms, thereby limiting their applicability. It was found that when low-frequency ECT excitation is used, such that the eddy current penetration depth exceeds three times the maximum target thickness of the Ti-alloy sheet, the tangent of the ECT coil impedance phase exhibits a linear relationship with the thickness. Based on this observation, by analyzing the low-frequency ECT response of Ti-alloys and separating the real and imaginary parts of the impedance under approximate conditions, a phase feature model was developed. The model effectively describes the linear dependence of the phase tangent on the thickness of the Ti-alloy sheet, offering a succinct characterization. The measurement method based on this model thereby allows for direct thickness calculation from the measured coil impedance without requiring master-curve calibration or iterative computation. Experiments were conducted using a custom-designed ECT coil and impedance analyzer to measure different Ti-alloy specimens. The results indicate that the measurement error was less than 3.5%. This research provides a theoretical foundation as well as a straightforward engineering solution for online, high-speed thickness measurement of Ti-alloy sheets. Full article

The article examines the use of hydrogen fuel as an alternative to traditional diesel fuel for internal combustion engines (ICE) in railway applications. The main objective of the study is to analyze the operational consumption of hydrogen fuel based on the mathematical modeling of the working cycle of the EMD 12-645E3C engine installed on CIE 071 locomotives used in freight and passenger service. The article provides information on the design features of the EMD 12-645E3C engine, its technical parameters, and the results of bench tests. The indicator parameters of the engine at various controller positions are determined and analyzed, and the results of mathematical modeling of its operation on hydrogen fuel are presented. Particular attention is paid to changes in indicator parameters, including the maximum combustion pressure and the peak gas temperature in the cylinder, as well as comparing the mass consumption of diesel and hydrogen fuel. The study results demonstrate that the use of hydrogen allows the engine to maintain effective power across all operational modes while simultaneously reducing energy costs up to 8%. In this case, the pressure and temperature of the gases in the cylinder increased by 3–6% and 5–8%. Recommendations are also provided regarding technical challenges associated with transitioning to hydrogen fuel, including the modernization of the combustion chamber, fuel system, and safety system. Full article

Over the last couple of decades, significant efforts have been made to develop structural health monitoring solutions. The growing need for the dynamic characterization of structures supports the implementation of condition assessments, maintenance, and monitoring strategies for existing and new civil engineering structures, and to provide increased safety for the public. Wireless monitoring systems are still being improved as the technology is finding a wider use for the monitoring of civil engineering structures, thanks to their easier installation and reduced costs when compared to the wired counterparts. In this context, this paper presents a new wireless network system for the dynamic characterization of civil engineering structures, whose distinguishing features comprise combining cutting-edge accelerometers, excellent signal synchronization, low battery consumption nodes, and a cloud-based framework to support the monitoring operations. The performance characteristics are validated through laboratory tests and are demonstrated on a newly constructed 211 m tall building. Full article

Accurate estimation of the state of health (SOH) of lithium-ion batteries is essential for the safe and efficient operation of electric vehicles (EVs). Conventional approaches, including Coulomb counting, electrochemical impedance spectroscopy, and equivalent circuit models, provide useful insights but face practical limitations such as error accumulation, high equipment requirements, and limited applicability across different conditions. These challenges have encouraged the use of machine learning (ML) methods, which can model nonlinear relationships and temporal degradation patterns directly from cycling data. This paper reviews four machine learning algorithms that are widely applied in SOH estimation: support vector regression (SVR), random forest (RF), convolutional neural networks (CNNs), and long short-term memory networks (LSTMs). Their methodologies, advantages, limitations, and recent extensions are discussed with reference to the existing literature. To complement the review, MATLAB-based simulations were carried out using the NASA Prognostics Center of Excellence (PCoE) dataset. Training was performed on three cells (B0006, B0007, B0018), and testing was conducted on an unseen cell (B0005) to evaluate cross-battery generalisation. The results show that the LSTM model achieved the highest accuracy (RMSE = 0.0146, MAE = 0.0118, R² = 0.980), followed by CNN and RF, both of which provided acceptable accuracy with errors below 2% SOH. SVR performed less effectively (RMSE = 0.0457, MAPE = 4.80%), reflecting its difficulty in capturing sequential dependencies. These outcomes are consistent with findings in the literature, indicating that deep learning models are better suited for modelling long-term battery degradation, while ensemble approaches such as RF remain competitive when supported by carefully engineered features. This review also identifies ongoing and future research directions, including the use of optimisation algorithms for hyperparameter tuning, transfer learning for adaptation across battery chemistries, and explainable AI to improve interpretability. Overall, LSTM and hybrid models that combine complementary methods (e.g., CNN-LSTM) show strong potential for deployment in battery management systems, where reliable SOH prediction is important for safety, cost reduction, and extending battery lifetime. Full article

The safety and reliability of modern power systems are increasingly challenged by adverse environmental conditions. (1) Background: Ice accumulation on power transmission lines is recognized as a severe threat to grid stability, as tower collapse, conductor breakage, and large-scale outages may be caused, thereby making accurate monitoring essential. (2) Methods: A rule-driven and interpretable stereo vision framework is proposed for three-dimensional (3D) detection and quantitative measurement of transmission line icing. The framework consists of three stages. First, adaptive preprocessing and segmentation are applied using multiscale Retinex with nonlinear color restoration, graph-based segmentation with structural constraints, and hybrid edge detection. Second, stereo feature extraction and matching are performed through entropy-based adaptive cropping, self-adaptive keypoint thresholding with circular descriptor analysis, and multi-level geometric validation. Third, 3D reconstruction is realized by fusing segmentation and stereo correspondences through triangulation with shape-constrained refinement, reaching millimeter-level accuracy. (3) Result: An accuracy of 98.35%, sensitivity of 91.63%, specificity of 99.42%, and precision of 96.03% were achieved in contour extraction, while a precision of 90%, recall of 82%, and an F1-score of 0.8594 with real-time efficiency (0.014–0.037 s) were obtained in stereo matching. Millimeter-level accuracy (Mean Absolute Error: 1.26 mm, Root Mean Square Error: 1.53 mm, Coefficient of Determination = 0.99) was further achieved in 3D reconstruction. (4) Conclusions: Superior accuracy, efficiency, and interpretability are demonstrated compared with two existing rule-based stereo vision methods (Method A: ROI Tracking and Geometric Validation Method and Method B: Rule-Based Segmentation with Adaptive Thresholding) that perform line icing identification and 3D reconstruction, highlighting the framework’s advantages under limited data conditions. The interpretability of the framework is ensured through rule-based operations and stepwise visual outputs, allowing each processing result, from segmentation to three-dimensional reconstruction, to be directly understood and verified by operators and engineers. This transparency facilitates practical deployment and informed decision making in real world grid monitoring systems. Full article

Monitoring muscle fatigue is essential for ensuring safety and maximizing the effectiveness of resistance training. Conventional methods such as electromyography (EMG), inertial measurement units (IMU), and ratings of perceived exertion (RPE) involve complex procedures and have limited applicability, particularly in unsupervised or robotic exercise environments. This study proposes a machine learning-based approach to directly predict RPE from force–time data collected during repeated isokinetic bench press sets. Thirty-two male participants (64 limb datasets) performed seven sets at a standardized 7RM load, with load cell data and RPE scores recorded. Biomechanical features representing magnitude, variability, energy, and temporal dynamics were extracted, along with engineered features reflecting relative changes and inter-set variations. The findings indicate that RPE is more closely related to relative fatigue progression than to absolute biomechanical output. Incorporating engineered features substantially improved predictive performance, with the Random Forest model achieving the highest accuracy and more than 93% of predictions falling within ±1 RPE unit of the reported values. The proposed approach can be seamlessly integrated into intelligent resistance machines, enabling automated load adjustment and providing substantial potential for applications in both athletic training and rehabilitation contexts. Full article

Accurate prediction of the ultimate bearing capacity (UBC) of single piles is essential for safe and economical foundation design, as it directly impacts construction safety and resource efficiency. This study aims to develop a hybrid prediction framework integrating Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) to optimize a Backpropagation Neural Network (BPNN). GA performs global exploration to generate diverse initial solutions, while PSO accelerates convergence through adaptive parameter updates, balancing exploration and exploitation. The primary objective of this study is to enhance the accuracy and reliability of UBC prediction, which is crucial for informed decision-making in geotechnical engineering. A dataset consisting of 282 high-strain dynamic load tests was employed to assess the performance of the proposed GA-PSO-BPNN model in comparison with CNN, XGBoost, and traditional dynamic formulas (Hiley, Danish, and Winkler). The GA-PSO-BPNN achieved an R² of 0.951 and an RMSE of 660.13, outperforming other AI models and traditional approaches. Furthermore, SHAP (SHapley Additive exPlanations) analysis was conducted to evaluate the relative importance of input variables, where SHAP values were used to explain the contribution of each feature to the model’s predictions. The findings indicate that the GA-PSO-BPNN model provides a robust, cost-efficient, and interpretable approach for UBC prediction, which aligns with current sustainability goals by optimizing resource usage in foundation design. This model shows significant potential for practical use across various geotechnical settings, contributing to safer, more sustainable infrastructure projects. Full article

Rockburst disasters have become increasingly prevalent as distinct forms of subsurface geotechnical engineering advanced to the deep earth. Confronted with such a threatening subsurface geopressure disaster that poses a risk to personnel and equipment safety, the microseismic monitoring technology has been employed to track signals generated from rock fracture and collapse in the field. To guide the prevention and control of the hazard, the investigation conducted an effective microseismic data mining method. Through deep feature engineering and interpretable intelligence, a practical and available short-term prediction approach for the rockburst intensity class was developed. On the basis of rockburst case database collected from various underground geotechnical engineering, the neural network-based feature extraction method was conducted in the process of model training. The optimized model was obtained by combining the K-fold cross-validation approach with the structural parameter search methodology. The evaluation among the considered artificial intelligence models on the testing dataset was conducted and compared. Through analyses, the interpretable coupling intelligent model combining convolutional and recurrent neural networks for rockburst prediction were demonstrated with the most robust performance by evaluation metrics. Among them, the proposed adaptive feature extraction method leads the benchmark method by 6% for both accuracy and precision; meanwhile, the proposed metric generalization loss rate (GLR) for accuracy and precision in the validation–testing process reached 1.5% and 0.2%. Furthermore, the Shapley additive explanations (SHAP) approach was employed to verify the model interpretability by deciphering the model prediction from the perspective of the fined impact of input features. Therefore, the investigation demonstrates that the proposed method can predict rockburst intensity with robust generalization and feature extraction capabilities, which possess substantial engineering significance and academic worth. Full article