A battery State of Health (SOH) estimation method based on Gated Recurrent Unit (GRU) neural network is proposed to address the issue of low accuracy in estimating the SOH of new energy vehicle power batteries. This method extracts multidimensional input features based on battery charging data, performs data cleaning and normalization on the features, and trains a GRU network to construct a battery SOH estimation model. The results indicate that the proposed method can achieve an average absolute error of 0.26% in estimating battery SOH, which is 1.04% lower than traditional calculation methods. This method can achieve a more accurate estimation of battery SOH and can be used for evaluating the aging status of electric vehicles.

Firstly, this paper reviews the definitions of the key states of lithium-ion batteries, including State of Charge (SOC), State of Power (SOP), State of Function (SOF), State of Energy (SOE), State of Health (SOH), Remaining Useful Life (RUL), State of Temperature (SOT) and State of Safety (SOS), and analyzes their coupling relationships. Then, it classifies and elaborates the methods for joint estimation of battery double states. In the future, multi-state joint estimation can further improve the estimation accuracy. Advanced sensor technologies, such as fiber-optic sensors, can more accurately measure the internal state quantities of batteries. At present, battery group state estimation is mostly focused on individual cells, and it is necessary to further explore the joint estimation at the battery module and group levels. Given the nonlinear characteristics of lithium-ion batteries, machine learning can achieve higher estimation accuracy with relatively low complexity. With the development of big data and cloud technologies, new-type battery state estimation will become a trend.

In order to improve the energy efficiency of pure eletric vehicles and a chieve precise and efficient vehicle control, explore the front axle disconnection device of a four-wheel drive pure electric vehicle equipped with dual permanent magnet synchronous motors, which realizes the dynamic switching between two-wheel drive and four-wheel drive modes by controlling the combination and separation of the front axle. The actual vehicle verification results show that this strategy effectively reduces the zero torque loss of the electric motor and minimizes the impact on drivability, while significantly improving economy and extending driving range.

In order to analyze the crucial role of the Steer-By-Wire (SBW) system in intelligent driving and its integrated application with the chassis control system, this paper focuses on the architecture and functions of the SBW system, including the fully redundant hardware architecture and variable steering ratio function. It also explores the vehicle application of the system, such as the calibration of the variable steering ratio and the matching of road-feel feedback. The paper also proposes an optimal basic road-feel feedback function scheme, as well as processes and methods for vehicle application suitable for the variable steering ratio and road-feel feedback of the SBW system, providing technical support for the development and engineering application of the SBW system.

To investigate the economic feasibility of hydrogen-powered heavy-duty trucks in both subsidized and non-subsidized markets, a hydrogen vehicle performance simulation model and a Total Cost of Ownership (TCO) model are established. Through comparative analysis of different powertrain configurations meeting dynamic performance requirements under user-specific operating conditions, as well as sensitivity studies on hydrogen pricing and energy consumption per 100 km, several critical findings are obtained as following. Powertrain configuration significantly impacts total vehicle cost, with higher fuel cell system power leading to increased overall costs. Hydrogen-powered heavy trucks require scenario-specific adaptations in both market types. While profitability is achievable in subsidized markets, the margin remains narrow. In non-subsidized markets, economic viability requires hydrogen prices below 21 RMB/kg. The study reveals substantial sensitivity to hydrogen consumption, with profitability thresholds established at <12 kg/100 km in subsidized markets and <10 kg/100 km in non-subsidized environments. Notably, when consumption falls below 9 kg/100 km in subsidized markets, economic performance becomes comparable to conventional diesel trucks. These findings provide theoretical foundations and technical references for advancing hydrogen vehicle commercialization, offering valuable insights for industry development.

To enhance the management capabilities for the State of Health (SOH) of power batteries and strengthen their contribution to carbon emission reduction, this paper conducts a detailed review centered on lithium-ion power batteries—a core component of electric vehicles. The review encompasses the industry overview, supportive policies, existing challenges, SOH management of in-vehicle power batteries, and future developments. The study demonstrates that SOH management of power batteries exhibits the following key trends: (1) Strengthening SOH management can effectively improve battery performance and lifespan, thereby reducing the carbon emissions of the entire vehicle; (2) Refined battery management technologies based on SOH optimization (e.g state estimation, optimal control) represent the core direction for future development; (3) Battery full-lifecycle management strategies incorporating cascade utilization can significantly enhance the overall carbon reduction capability of lithium-ion batteries.

The Noise Vibration Harshness (NVH) performance of vehicles is one of the key indicators of overall vehicle qualities. To enhance ride comfort and meet increasingly stringent NVH requirements, this paper reviews the application of Artificial Intelligence (AI) algorithms in NVH optimization, both domestically and internationally. It analyzes feasible approaches for improving NVH performance using AI-based methods and discusses future trends and challenges in AI-driven NVH optimization. The study aims to provide valuable insights for leveraging intelligent algorithms to address automotive performance enhancement.

Aiming at the reliability evaluation problem of small samples of long-life high-voltage relays, an analysis method of mean rank combined with least squares is proposed. Under the guidance of the basic principle of average rank method, the method of determining the fault rank of high voltage relay under random truncated multiple tests is studied. The least square method is used to estimate the reliability parameters, and the linear correlation coefficient and D-test method is used to test the fit. Under the condition that the fault data are subject to 2 distribution models at the same time, the total root-mean-square error method is introduced to optimize the distribution model, identify the optimal reliability model and conduct reliability evaluation.

The event-tracking data of intelligent cockpit contains rich information about driver and passenger actions. Analyzing and identifying specific action intents can benefit deeper insights into user needs. Considering the high cost, strong subjectivity, and repetitiveness of current methods that rely on manual tagging for action intent recognition, a new method based on Artificial Intelligence model for automated tagging and classification is proposed. By fine-tuning the Qwen2-14B model, this approach could rapidly identify action intents across multiple dimensions and granularities, enhance the efficiency of cloud data analysis and lay a theoretical foundation for real-time response to user needs on the vehicle side.

To enhance lateral active safety in intelligent connected vehicles, the identification and definition of unintended functional safety scenarios for the Electric Power Steering (EPS) system are integrated into system design and development process. By combining scenario domain analysis, equivalence partitioning, and boundary value analysis with the deconstruction of vehicle model variants and lateral motion scenarios related to EPS, more potential hazardous operational scenarios are expanded from known operational scenarios. Meanwhile, the Driver-In-the-Loop (DIL) system based on hardware-in-the-loop simulation is utilized. Relying on its advantages of “driver-vehicle-environment” closed-loop, more unknown risk scenarios are transformed into valid known scenarios. Subsequently, the existing safety technical requirements are optimized and the overall performance of the EPS system is further improved.