Wuxi Vocational Institute of Commerce

Abstract This paper, addressing the requirement for strengthening engine bearings, investigates the effect of plating bath temperature on the microstructure and properties of electrodeposited Ni-Al2O3 nanocomposite coatings. The results show that the plating bath temperature has a “first improving then deteriorating” effect on the coating properties. When the plating bath temperature is 50°C, the coating surface is smooth, the Al 2 O 3 particles are evenly dispersed, and the grain refinement degree is high. At this temperature (50°C), the microhardness of the coating reaches a peak value of 712 HV, with a friction coefficient of 0.43 and a wear loss of 2.9 mg, indicating the optimal wear resistance.

ABSTRACT This research has introduced a hybrid model that integrates the long short‐term memory (LSTM) and extreme gradient boosting (XGBoost) models to assess students' mental health states, particularly to identify students' levels of stress, mood, and fatigue. The physiological measures measured were heart rate (HR), heart rate variability (HRV), electrodermal activity (EDA), and skin temperature. All measures were recorded using wearable sensors and underwent processing, such as normalization, noise filtering, and feature extraction, to ensure the signal quality was fit for analysis and interpretability. While the LSTM network can accurately represent the temporal dynamics present in the physiological sequences, the XGBoost model is critical in obtaining high accuracy through the classification of features' non‐linear interactions and decision boundary optimization. The experimental validation through the technique of fivefold cross‐validation shows that the hybrid model performs with high accuracy of 0.98 on average, F1‐score of 0.98, and consistently low false‐positive and false‐negative rates when compared to SVM, Random Forest, and single deep learning model methods that serve as baseline methods. The results assure the framework's reliability, consistency, and clarity in reasoning over different data conditions. This novel method provides a strong platform for the real‐time, data‐driven monitoring and early detection of psychological distress, thus allowing educators, mental‐health professionals, and caregivers to make timely interventions and improve the overall well‐being of students.

This paper addresses the average-tracking control problem for multi-agent systems subject to constant reference signals. By introducing auxiliary signals generated from the states and delayed states of agents, a novel privacy-preserving integral-type average-tracking algorithm is proposed. Leveraging the frequency-domain analysis approach, delay-dependent sufficient and necessary conditions for ensuring asymptotic average-tracking convergence are derived. Furthermore, the proposed algorithm is extended to tackle the average-tracking control problem with mismatched reference signals, and a corresponding delay-dependent sufficient condition is established to guarantee privacy-preserving average-tracking convergence. Numerical simulations are conducted to verify the effectiveness of the developed algorithms.

In the digital media era, identifying and managing public opinion risks has become essential for safeguarding business model innovation. Drawing on 303 survey responses and employing multiple regression and the Johnson–Neyman technique, this study developed a moderated mediation framework to examine how public opinion uncertainty shapes business model innovation through employees’ passion for inventing and passion for developing. The potential “chilling effect” and “peer effect” were also explored. Grounded in Conservation of Resources Theory, the study further explained employees’ coping strategies under uncertainty. The results revealed that public opinion uncertainty negatively affected business model originality, application, and lean through the two mediators, with no significant difference between the dual mediation paths. Unexpectedly, passion for inventing did not significantly mediate the link between public opinion uncertainty and business model application. The significant moderated mediation effects provide evidences to confirm “peer effect”, reflecting tendencies of conforming to external uncertainties. Together, these findings underscore the importance of fostering a supportive environment for business model innovation. Theoretical contributions and practical implications are also discussed.

Polyetheretherketone (PEEK) is a high-performance engineering plastic widely used in aerospace, automotive, and other industries due to its heat resistance and mechanical strength. However, its high friction coefficient and low thermal conductivity limit its use in heavy-load environments. Existing studies have extensively explored the individual effects of thermal processing or irradiation on PEEK. However, the synergistic mechanism between the initial microstructure formed by mold temperature and subsequent irradiation modification remains unclear. This paper investigates the coupled effects of injection molding temperature and electron beam irradiation on the tribology of carbon fiber-reinforced PEEK composites, with the aim of identifying process conditions that improve friction and wear performance under high load by controlling the crystal morphology and cross-linking network. Carbon fiber (CF) particles were mixed with PEEK particles at a 1:2 mass ratio, and specimens were prepared at injection molding temperatures of 150 °C, 175 °C, and 200 °C. Some specimens were irradiated with an electron beam dose of 200 kGy. The friction coefficient, wear rate, surface shape, and crystallinity of the material were obtained using friction and wear tests, white-light topography, SEM, and XRD. The results show that the injection molding temperature of the material influences the friction performance. Optimal performance is obtained at 175 °C with a friction coefficient of 0.12 and wear rate of 9.722 × 10−6 mm3/(N·m). After irradiation modification, the friction coefficient decreases to 0.10. This improvement is due to the moderate melt fluidity, adequate fiber infiltration, and dense crystallization at this temperature. In addition, cross-linking of chains occurs, and surface transfer films are created at this temperature. However, irradiation leads to a slight increase in wear rate to 1.013 × 10−5 mm3/(N·m), suggesting that chain segment fracture and embrittlement effects are enhanced at this dose. At 150 °C, there is weak interfacial bonding and microcrack development. At 200 °C, excessive thermal motion reduces crystallinity and adds residual stress, increasing wear sensitivity. Overall, while irradiation reduces the friction coefficient, the wear rate is affected by the initial microstructure at molding. At non-optimal temperatures, embrittlement tends to dominate the wear mode. This study uncovers the synergistic and competitive dynamics between the injection molding process and irradiation modification, offering an operational framework and a mechanistic foundation for applying CF/PEEK under heavy-load conditions. The present approach can be extended in future work to other reinforcement systems or variable-dose irradiation schemes to further optimize overall tribological performance.

In modern era, the growing demand for sustainable transportation across the globe has led to significant increase in New Energy Vehicle (NEV) power systems optimization to achieve higher energy efficiency, reduced fuel consumption and extended driving range. However, the existing Improved Particle Swarm Optimization-Dynamic Programming (IPSO-DP) based approach struggled with high computational cost, local convergence issues and restricted adaptability to diverse driving scenarios. This research proposed a Multi-Objective Genetic Algorithm-Adaptive Rule (MOGA-AR) based optimization framework that integrates both parameter optimization and intelligent energy management. This framework begins with system modelling and collection of data from standard driving cycles. Followed by Multi Objective Genetic Algorithm (MOGA) based optimization of crucial parameters involved in power distribution and efficiency. These optimized parameters are then processed by applying an Adaptive Rule Based Energy Management System (AR-EMS) that dynamically assigns power between engine and motor to obtain optimal performance. Results demonstrate that the proposed MOGA-AR showed improved in fuel consumption by $5.5(\mathrm{~L} / 100 \mathrm{~km})$ with enhanced system efficiency of $\mathbf{9 2. 7 \%}$ compared to existing IPSO-DP model.

The selective identification of CH4 in alkane gas mixtures remains challenging due to overlapping infrared absorption spectra among alkane species. This study introduces a novel algorithmic filter paradigm that fundamentally shifts from hardware-based to software-defined selectivity in Nondispersive Infrared (NDIR) sensing. Instead of relying on costly, fixed-wavelength optical filters, we employ a simplified four-source NDIR platform that deliberately captures composite spectral signals from mixed gases. A CNN-SVM hybrid model then serves as the algorithmic filter: the Convolutional Neural Network extracts discriminative features from overlapping spectra, while the Support Vector Machine performs robust classification. This integrated system achieved 89% accuracy in CH4 identification within complex alkane mixtures. By replacing expensive optical components with intelligent algorithms, this work demonstrates a cost-effective, flexible, and scalable approach.