Huxiao Shi

This study focuses on the thermal runaway (TR) risk of lithium-ion batteries (LIBs) and explores data-driven multi-sensor early warning and risk-oriented prognostics based on the intrinsic thermal behavior of batteries. A framework is proposed to support health information extraction using multi-sensor monitoring data, where data-driven approaches are adopted to address multicollinearity among parameters and explore their synergistic effects. The identified health-related features help characterize abnormal behavior and model health index propagation under TR evolution, which support the design of warning points and estimation of remaining time before TR (time-to-TR). The framework is validated through a designed experiment, where the Accelerating Rate Calorimeter (ARC) is employed to create adiabatic conditions for LIBs. The experiment helps minimize external impacts during TR evolution and validate the framework according to the intrinsic characteristics of batteries related to TR risks. The results from Leave-One-Sample-Out cross-validation preliminarily demonstrate the application potential of identified feature behavior patterns in early warning and risk-oriented prognostics. The integration of these functions can enhance the current TR risk management solutions, transforming monitoring data into decision support information for proactive risk mitigation.

Thermal runaway (TR) of lithium-ion batteries (LIBs) represents a critical safety challenge in EV applications. This study explores the potential of data-driven safety management strategies for mitigating TR risks in EVs. To minimize the impact of external environmental factors on the degradation of LIBs, experiments were conducted using an accelerating rate calorimeter (ARC). The intrinsic thermal behavior of six nickel–cobalt–manganese (NCM) cells at different states of health (SOH) and operating temperatures has been captured in created adiabatic conditions. Multiple sensors were deployed to monitor the temperature and electrochemical and environmental parameters throughout the degradation process until TR occurred. The results show that both the thermal and electrochemical stability of LIBs have been affected, exhibiting consistent thermal patterns and early electrochemical instability. Furthermore, even under adiabatic conditions, the degradation of LIBs show synergistic effects with environmental parameters such as chamber temperature and pressure. Correlation analysis further revealed the coupling relationships between the monitored parameters. Through calculating their correlation coefficients, the results indicate advantages of combining thermal, electrochemical, and environmental parameters as being to characterize the degradation of LIBs and enhance the identification of TR precursors. These findings stress the importance of considering the battery-environment system as a whole in safety management of EVs. They also provide insights into the development of data-driven safety management strategies, highlighting the potential for achievement and integration of anomaly detection, diagnosis, and prognostics functions in current EV management frameworks.

Physical fatigue in repetitive production lines contributes to musculoskeletal disorders and absenteeism. This study investigates a pharmaceutical packaging environment where workers frequently perform repetitive tasks. Biometric data—pulse rate, internal temperature, electrodermal activity, and movement—were collected using smartwatches, alongside demographic (age, experience) and occupational factors (task load, line, shift, timing) Principal Component Analysis was applied to reduce dimensionality and extract key features. A fuzzy logic-based labeling method, adapted from prior controlled studies, was used to assign fatigue levels (binary and four-class) in a non-intrusive and objective way. These labeled datasets trained various machine learning models to classify physical fatigue states. The results demonstrate that incorporating demographic and occupational context (external features) alongside biometric data significantly enhances classification performance. In the binary classification task, the F1 score increased from 0.8848 (biometric data only) to 0.9375 with the addition of external features. Similarly, in the four-level classification, the F1 score improved from 0.8200 to 0.8793 when external features were combined with biometric inputs. Feature importance analysis identified motion-related metrics as the most influential predictors, while confusion matrix results showed a clear reduction in false negatives for critical fatigue states. This work introduces a scalable, human-centered system for early physical fatigue detection in industrial settings, supporting safety, performance, and well-being in line with Industry 5.0 principles.

Physical fatigue is a significant concern in repetitive production line operations, often contributing to musculoskeletal disorders (MSDs) and high absenteeism rates. This study focuses on a pharmaceutical packaging line where workers frequently develop MSDs due to the repetitive nature of their tasks. To address this issue, biometric data from smartwatches, including pulse rate, internal temperature, electrodermal activity, and movement patterns, were collected alongside demographic factors such as age and experience and occupational factors related to task demands, including physical load, and operational conditions such as production line location, day of the week, work shift, and timing within the shift. Principal Component Analysis was first applied to reduce the dataset's dimensionality, extracting the most relevant features. Subsequently, fuzzy logic was employed to label the data into two and four levels of fatigue based on prior research. The resulting features and labels were then used as inputs for machine learning classification models to predict fatigue states. Our findings demonstrate that integrating wearable sensor data significantly enhances classification performance. In binary classification, the Random Forest model achieved an F1 score of 0.935 with biometric data and 0.681 without it. For the four-level classification, incorporating biometric data improved the F1 score from 0.573 to 0.903, highlighting its importance in fatigue prediction. This study contributes by developing a generalized predictive fatigue model and establishing a foundation for a real-time fatigue alert system to enhance worker safety and productivity.