Wear of the clutch disc friction lining significantly influences the reliability and performance of torque transmission systems in automotive and industrial applications. Progressive degradation of the friction lining reduces torque transmission efficiency, resulting in clutch slippage, poor vehicle drivability, and an increased likelihood of unexpected mechanical failure. The absence of effective real-time monitoring mechanisms further limits the ability to detect critical wear conditions before system failure occurs. This study presents the development and experimental validation of an intelligent clutch disc wear monitoring and safety control framework designed to detect friction lining degradation and initiate protective vehicle responses. The proposed system employs an ultrasonic sensing technique to continuously measure friction lining thickness and estimate wear progression in real-time applications. A microcontroller-based multi-tier control architecture processes the measured data and correlates wear depth with predefined safety thresholds. When the lining thickness reaches a critical level of 3 mm, the system automatically activates a limp-home operational mode that limits vehicle speed to 40 km/h, enabling safe mobility to the nearest maintenance facility while preventing further damage to clutch components. When the wear approaches the critical shutdown threshold of 0.3 mm, an automated fuel interruption mechanism triggered to cut off fuel supply to the engine. The system additionally provides visual and audible warnings through the vehicle instrument cluster to alert the driver. Experimental validation on a prototype test rig and Proteus Visual System Modeling detects wear stages with 97% accuracy and successfully activated safety responses within maximum response time of 2.0 seconds (s). The proposed approach provides a practical real-time fail-safe solution that enhances vehicle safety, improves drivetrain reliability, and reduces the risk of sudden clutch-related failures.
To bridge the gap between physiological data and engineering implementation, this study addressed the limitation of indirect mapping of sitting posture by establishing a direct predictive link between physiological information from pressure distribution and optimal sitting posture. A novel predicting framework named Physics-Guided and Contrastive Learning Network (PGCLN) was proposed to predict sitting posture using 12 pressure distribution features and seven anthropometric data, and designed to overcome small-sample and high-dimensional regression problems. Crucially, Contact Pressure Distribution Index (CPDI) was firstly introduced as a new biomechanical constraint to ensure the model’s physical consistency. By integrating CPDI-based physical prior constraint with contrastive learning, the PGCLN can accurately predict the optimal sitting posture for diverse occupants with a R 2 of 0.9711 and RMSE of 0.7649, significantly outperforming baseline models. Furthermore, SHAP analysis reveals that Waist Average Pressure and Shoulder and Back Contact Area are the primary determinants for PGCLN. Overall, this work offers a robust solution for an on-vehicle deployment of real-time, personalized seat adaptive adjustment, providing both a theoretical foundation and a practical pathway for intelligent seating systems in human factors engineering.
With the rapid development of intelligent transportation and autonomous driving technologies, vehicle trajectory prediction, as a key task for ensuring traffic safety and efficiency, has become a crucial link in improving the decision-making performance of autonomous vehicles. To address the issue that traditional supervised learning is highly dependent on large amounts of labeled data, this paper proposes a vehicle trajectory prediction method based on a self-supervised learning mechanism, aiming to more fully explore the feature information of unlabeled data and enhance the model’s ability to fuse information in complex scenarios. The method is designed with a Global Channel-Spatial Fusion (GCSF) module to improve the extraction capability of multi-source feature information; it conducts multi-dimensional modeling by effectively integrating historical trajectory information, lane geometry information, and position information, enriches the representation ability of feature information, and achieves high-precision trajectory prediction. In the pre-training phase, it further incorporates Spatial Information (SI) enhancement to construct a multi-level self-supervised pre-training framework, realizing the feature enhancement of historical and future trajectory information for the pre-trained model and the establishment of a deep-level model. Experiments based on the Argoverse 2 dataset demonstrate that the proposed method outperforms existing mainstream methods in multiple prediction metrics; in particular, the minADE 1 and minFDE 1 metrics are improved by 1.3% and 3.0% respectively compared with the baseline models, which effectively enhances the generalization ability and robustness of the model and has important reference value for the intelligent decision-making of future autonomous driving systems.
In this study, the factors causing vehicle deviation are first classified into vehicle-intrinsic and external environmental factors using a fishbone diagram. Nine key parameters are selected: tire pressure P , vehicle speed V , distance from the center of mass to the front axle a , damping coefficient C , spring stiffness E , steering gear ratio I , camber angle α , toe angle β , and road adhesion coefficient σ . Subsequently, an orthogonal array with nine factors at eight levels each is constructed, and the vehicle deviation under different parameter combinations is simulated in CarSim. The relative importance of these parameters is initially ranked through range analysis. Based on the simulation outcomes, a judgment matrix for the analytic hierarchy process (AHP) is established to determine the weight of each parameter. The results show that the descending order of influence is β > V > σ > I > C > P > E > a > α , with corresponding weights of 36.48%, 18.42%, 13.86%, 7.98%, 7.98%, 5.59%, 3.31%, 3.24%, 3.14% respectively. This demonstrates that integrating the orthogonal experiment and range analysis with the AHP can provide objective data for constructing a judgment matrix with a satisfactory consistency ratio, thereby making the derived factor weights more reliable.
Energy management for hydrogen fuel cell heavy-duty trucks must balance hydrogen consumption, terminal state of charge (SOC), and component degradation under rapidly changing driving conditions. Predictive equivalent consumption minimization strategies can anticipate future power demand, but inaccurate predictions may distort equivalence factor adaptation and compromise charge sustainability. This study proposes a confidence-aware equivalent consumption minimization strategy (CA-ECMS) that integrates driving condition recognition, short-horizon speed prediction, an adaptive SOC reference, and online fusion of equivalence factors associated with current and predicted conditions. Prediction confidence and SOC tracking error jointly regulate the contribution of future driving information, retaining anticipatory control while limiting the influence of unreliable predictions. A vehicle-level model incorporating component degradation and operating cost was developed for evaluation. The recognition model achieved 94.78% accuracy, and the prediction model achieved a root mean square error of 1.241 km h −1 . Controller performance was evaluated using five repeated China Heavy-Duty Commercial Vehicle Test Cycle for Tractor-Trailer (CHTC-TT) cycles, three repeated Heavy Heavy-Duty Diesel Truck (HHDDT) cycles, and module-by-module ablation tests. Under CHTC-TT, CA-ECMS reduced operating cost, hydrogen cost, and fuel cell degradation cost by 9.31%, 6.14%, and 59.88%, respectively, relative to adaptive ECMS, while reducing terminal SOC error from 3.58% to 0.08%. Under HHDDT, CA-ECMS limited terminal SOC error to 0.40%, compared with 10.50%, 30.00%, and 25.90% for rule-based control, adaptive ECMS, and fuzzy dynamic switching, respectively. Ablation results confirmed the complementary roles of confidence regulation, the adaptive SOC reference, and SOC feedback. These results demonstrate that reliability-aware use of predicted driving information can improve operating cost and charge sustainability within an interpretable ECMS framework.
