To address the limited generalizability of electric-vehicle fault warning caused by large differences among vehicle models, restricted access to on-board private data and insufficient extraction of temporal features, the paper proposes a hybrid deep-learning fault-warning model based on grid-side charging-process data. First, model-independent voltage, current and other time-series data readily collected at charging piles are processed by the Transformer self-attention mechanism to capture global temporal dependencies and long-range correlations among key components such as batteries and motors. Scecond, a Bidirectional Long Short-Term Memory (BiLSTM) network models local temporal features in both directions to enhance the contextual representation of fault signatures. Finally, a Support Vector Machine (SVM) classifies the fused features to warn of fault levels during charging. Visualization of attention weights confirms that the model focuses effectively on fault-sensitive features such as voltage anomalies and abrupt temperature-gradient changes. The results show that the method enables unobtrusive "inspection while charging" fault warning using the charging process.

To address the issues that the insulation monitoring circuit of the On-Board Charger (OBC) cannot perform insulation monitoring before inverter activation and is prone to false alarms caused by capacitive loads, and an insulation monitoring circuit is developed by introducing a DC voltage component via a current mirror to monitor the insulation at the OBC inverter output. The parameter selection and design of critical electronic components in the circuit are analyzed. Simulation and experimental verifications are carried out by building simulation circuits and prototypes. The results show that the proposed scheme can complete self-check before OBC inverter output and effectively avoid false insulation monitoring alarms caused by capacitive loads.

Electronic nose technology holds immense application potential for odorants and air quality control within vehicles, owing to its significant advantages of high sensitivity, operational convenience and low cost. This paper focuses on the application of electronic nose technology in the identification and classification of gas components, with a particular emphasis on the working principles of electronic nose technology, the response performance of various gas sensors and pattern recognition algorithms. Additionally, the paper discusses the progress made in the use of electronic nose technology for Indoor Air Quality (IAQ) evaluation and the identification of odorants emitted by whole vehicles or interior materials. Finally, the paper provides an outlook on the future development direction and challenges of electronic nose technology in the field of vehicle odorant detection.

To establish a simulation model of the moving-iron electromagnetic actuator applied to automotive active tie rod mounts, a combined method of finite element electromagnetic simulation and bench test is adopted to conduct modeling simulation, performance calculation and test comparison analysis. A performance test platform for the electromagnetic actuator is built to obtain the test data of actuating force under different currents and frequencies. A simulation model of the actuator is established via electromagnetic simulation software to calculate the electromagnetic force output under corresponding working conditions, and the simulation results are compared with the test results for verification. The results show that the natural frequency of the electromagnetic actuator is about 30 Hz, and it outputs stably within the operating frequency range of 50~100 Hz. The actuating force amplitude presents a good linear relationship with the effective current value. The actuating force obtained by simulation is consistent with the excitation current in period, and the relative error between simulation and test results is controlled within 13%, which verifies the accuracy and reliability of the established model.

With the rapid development of the off-road passenger vehicle market and the diversification of user application scenarios, the traditional water-wading performance evaluation method, which relies solely on "maximum wading depth," has become inadequate for comprehensively reflecting users' actual needs. From the perspective of real-world user experience, the paper investigates and analyzes user encounters and core concerns in scenarios such as urban, off-road and emergency water crossings. A multidimensional testing framework is established, encompassing 5 key dimensions: static sealing, dynamic traversal capability, powertrain stability, electronic system reliability and post-wading recovery. Furthermore, an integrated evaluation system combining subjective assessments and objective data is developed. The results demonstrate that this method provides a more comprehensive and scientific evaluation of the water-wading performance of off-road passenger vehicles. It offers valuable references for automotive manufacturers in setting R&D targets and assists consumers in making informed vehicle selection decisions.

To achieve lightweight design for an electric light-duty cargo vehicle and enhance its overall reliability and endurance mileage, a finite element modeling of its frame is conducted. Static performance, modal performance and fatigue life analysis are performed to identify the weak spots in its strength under torsional conditions. Through sensitivity analysis, 19 key plate thicknesses and 2 crossbeam section widths are identified as design variables. An Optimal Latin Hypercube Design (OLHD) is employed to generate 260 training samples and 28 validation samples. A high-precision surrogate optimization model is constructed using a Radial Basis Function (RBF) network model. The Non-dominated Sorting Genetic Algorithm-II (NSGA-II) is utilized for multi-objective optimization, aiming to minimize the frame mass and the maximum deformation under torsional conditions. The validation results showed that after optimization, the total frame mass decreased from 574 kg to 533 kg, the maximum stress reduced by 19.73%, the safety factor increased to 1.58, the maximum deformation under torsional conditions decreased by 5.61%, the first-order natural frequency increased by 4.21%, the fatigue life under the weakest torsional condition improved by 3.96%, and the comprehensive safe driving mileage increased to 87.300×10⁴ km, meeting and exceeding the design requirements.

To address the diverse usage scenarios of light-duty trucks for overseas users, the study selects typical user usage scenarios in representative overseas markets and systematically investigates the aerodynamic characteristics of light-duty trucks with different cargo heights and body styles. A numerical model of the external flow field of a light-duty truck is established based on the Computational Fluid Dynamics (CFD) method, and simulations are carried out under the operating condition of 90 km/h. The effects of different body styles on the overall aerodynamic drag, surface pressure distribution, and rear wake vortex structures are comparatively analyzed. The results indicate that the height difference between the cab and the cargo body is a primary factor influencing pressure drag, and the installation of an air deflector is an important means of improving high-speed fuel economy. Finally, it is recommended that high-capacity drop-side cargo bodies be prioritized in regions with lower average vehicle speeds, while aerodynamically optimized enclosed van body configurations be adopted in European and Middle Eastern regions with well-developed highway networks.

The artificial intelligence autonomous vehicle identifies the vehicle environment based on communication, computer, network and control technology, and uses communication means to realize real-time and continuous control of the vehicle. However, the electronic module is prone to functional failure due to high temperature, and there are safety risks. In addition, after parking in the summer, the temperature of the passenger compartment rises sharply, and the internal electronic devices are in a high temperature state. Among them, the FCM is fixed on the front windshield and is exposed to direct sunlight, coupled with the influence of the black edge of the windshield, which is much higher than the surrounding ambient temperature. Therefore, taking FCM as the research object, a vehicle model is established to study the temperature and flow field changes in high-temperature environments, and the effects of different FCM cover designs on the temperature and flow field are compared. The results indicate that FCM is still much higher than the ambient temperature under the action of the air conditioning system. When the air conditioning is turned on after parking, the temperature of the FCM module continues to rise, and the front camera temperature increases most significantly, with a maximum temperature of 113 ℃ (Scheme 1), followed by the rain sensor, and a maximum temperature of 107 ℃ (Scheme 1). In addition, Scheme 3 has the most significant effect on reducing the temperature amplitude of the front camera, while Scheme 1 has the most significant effect on the rain sensor.

The traditional development of Child Restraint System (CRS) safety relies on simulation and physical test results, which suffers from high costs, low efficiency and obvious limitations. The paper constructes a simplified high-precision coupled model under standard working conditions to efficiently generate training datasets. By fusing the time-domain, frequency-domain and second-order waveform fitting features of crash pulses, an intelligent prediction model based on deep multilayer perceptron is adopted to rapidly predict 4 core safety indicators, namely the Head Injury Criterion (HIC), head acceleration, axial neck force and chest acceleration. Validation results on new vehicle models show that the prediction model achieves an average accuracy of 93.3%, which can support the rapid development of CRS safety and demonstrates excellent engineering applicability.

To address the high-voltage electrical safety risk of a hybrid SUV during 80 km/h rear impacts as specified by FMVSS 305, component-level investigations are conducted, and vehicle collision structure optimization is performed. At the component level, through designing two types of component tests, quasi-static extrusion and dynamic impact, the ultimate bearing capacity of Intelligent Power System (IPS) is obtained. At the level of vehicle collision structure optimization, by optimizing the rear impact force transmission path and improving the IPS collision mode, designing the rear longitudinal beam structure to bend upward makes IPS be subjected to planar extrusion. The simulated IPS collision force decreases by 64% from 137 kN to 49 kN, which is less than its ultimate bearing capacity.