In the process of vehicle intelligence，in-vehicle sound field zoning control technology plays a crucial role in enhancing the acoustic experience within the cabin. In this paper，a comprehensive review of in-vehicle sound field zoning control algorithms and their application are provided. Firstly，the background and theoretical basis of the technology are introduced. Then，the development process，control principles，and characteristics of various sound field zoning control algorithms are thoroughly analyzed. Finally，based on the existing research progress，the potential advancements in sound field zoning control technology with regard to reproduction accuracy improvement，algorithm robustness，and sound field uniformity are explored，and a series of challenges limiting the widespread application of the technology in vehicles and the solutions are discussed. The review aims to provide reference for further research on in-vehicle sound field zoning control and to promote widespread application of the technology in the vehicle industry.

When driving on highways，it's necessary to reduce wind noise in the side window areas of a vehicle. Low-frequency noise control of automobile wind noise can be achieved through Active Noise Control （ANC）. Therefore，an Active Wind Noise Cancellation （AWNC） method for automobile wind noise is proposed in this paper. The suitable input signal of the side window area is selected as the reference signal，which shows good coherence with the target noise in the 100-500 Hz frequency range. Taking a full-scale clay model of the vehicle in a wind tunnel as the research object，the reference signals for wind noise are optimized through the Long Short-Term Memory （LSTM） method. The optimized reference signals are then processed using the FxLMS algorithm for AWNC simulation and validated through hardware dSPACE testing. The results show that the optimized reference signals not only reduce the number of sensors needed，thus saving cost，but also decrease the peak frequency band of wind noise by 5-15 dB.

High performance active suspension has significant advantages in improving driving experience，and robust control algorithm is an important guarantee for active suspension performance. To solve the problem that the typical robust control algorithms are difficult to achieve effective disturbance estimation and compensation，in this paper，a H₂/H_∞-H₂-IUDE algorithm is proposed to estimate and compensate the disturbance by using IUDE algorithm and introducing in H₂ state observer，which improves the robustness compared with H₂/H_∞ algorithm. Firstly，the model of half vehicle active suspension control systems is established，and the disturbance form is defined. Then，an IUDE algorithm for disturbance estimation and compensation decoupling is proposed，and a H₂ state observer is proposed to redesign H₂/H_∞ algorithm. Finally，simulation analysis is carried out for typical working conditions such as random road surface and speed bump road surface. The results show that，compared to the H₂/H_∞ algorithm，the proposed algorithm reduces the root mean square values of the vehicle body center vertical acceleration and pitch angle by 7.6% and 5.9%，respectively，under random road conditions，demonstrating a significant improvement in vehicle ride comfort. Meanwhile，the proposed H₂ observer can effectively estimate system states. The IUDE algorithm can accurately estimate disturbance，and can avoid the deterioration of suspension dynamic deflection caused by the non-decouple UDE method，which has outstanding characteristics of excellent disturbance estimation and flexible compensation.

In order to conduct more comprehensive safety analysis of electric cars in side pole collision scenarios，in the paper a locally refining scheme is used to build the finite element model of battery pack，which is applied to simulation at both the whole car and the battery pack levels. Based on accident statistics，the side pole collision responses of the car are examined by changing the impact positions，angles and collision speed，including the conditions defined in the national standards. Considering the high cost of the whole car simulation，a parameterized model of battery pack level is established by adjusting collision speed and mass compensation for large-scale side pole collision simulation. A fast prediction model based on the energy method is proposed for battery pack level collision safety，which can predict the deformation and mechanical failure risk in real time under different side pole impact conditions. The model is validated with an average prediction error of 3.22%.

In order to investigate the electrical response of proton exchange membrane fuel cell （PEMFC） stack under impact load，and to reveal the mechanical-electrical coupling mechanism of PEMFC stack，the mechanical-electrical coupling modeling method of the PEMFC stack under impact load is studied. A systematic investigation is undertaken to investigate the effect of impact velocity and direction on the electrical response of the PEMFC stack，based on the established mechanical-electrical coupling model of the PEMFC stack. The results show that the proposed method for modeling the mechanical-electrical coupling of the PEMFC stack can accurately simulate the inherent mechanical-electrical coupling characteristics within the PEMFC stack. The ohmic loss of the single cell inside the PEMFC stack increases as the shock load increases. Meanwhile，the impact load results in the formation of additional electrical contact between the gas diffusion layer （GDL） and the ribs of the bipolar plate，which causes a reduction in the average value of the current density on the surface of the GDL and deterioration in the distribution uniformity. This study has certain guiding significance for the modeling of PEMFC mechanical-electrical coupling and the study of electrical response under impact load.

Crashworthiness optimization is an effective way to achieve better passive safety protection performance of vehicles，but current optimization focuses on improving numerical response，while neglecting the control of a category response，namely，deformation modes. The deformation mode of key components is related to the effectiveness of vehicle force transmission path design. If an unsatisfactory deformation mode occurs in the optimization solution，the effectiveness of the optimization result cannot be guaranteed. Therefore，in this study a machine learning based deformation mode control optimization method is proposed to improve the crashworthiness index while ensuring that all samples in the optimization solution deform in ideal modes. Structural deformation is represented in the form of images，and deep learning auto encoder is used to extract deformation features and cluster them to identify different deformation modes. Then，machine learning prediction models based on Light Gradient Boosting Machine （LightGBM） are established for the identified deformation modes and numerical responses. Finally，the optimization is solved based on the machine learning prediction models. The proposed machine learning optimization method is validated using a full vehicle frontal collision case，and the results show that while improving the numerical crashworthiness responses，the deformation mode of the longitudinal beam is ensured to deform in an ideal mode. This study demonstrates the prospects of machine learning in improving the effectiveness of structural optimization.

With the development of intelligent vehicles and autonomous driving technologies，zero-gravity seat，with occupant comfort as core function，has been equipped in some vehicles. Compared to upright seating，reclined occupants face a higher risk of injury in collision，making the development of crash safety solutions imminent. In this paper，a review of the current research status and development trends regarding the crash safety of reclined occupants is conducted，focusing on injury mechanism，restraint systems，and research tools. The findings are summarized as follows： （1） Injury patterns for reclined occupants differ from those for upright occupants，and the injury mechanism at typical sites such as the lumbar spine and the iliac crest have not been fully clarified. （2） Traditional restraint systems with three-point seat belts as the core，even after improvement and optimization，is still difficult to provide effective overall protection for reclined occupants. Development of new protective means that can reasonably balance submarine and spinal injuries under the integrated active-passive safety system is a key issue in crash protection research for reclined occupants. （3） Crash dummies and human body models （HBMs），as the primary research and evaluation tools，need to improve their usability and bio-fidelity for reclined conditions.

Energy management determines the power distribution of the power system of fuel cell vehicles （FCVs） and affects the economy and durability of FCVs. As the operating conditions of vehicles are complex and variable，energy management can improve the output performance of FCV power system by integrating traffic information. In this paper，the optimization objectives of FCV energy management are summarized，and the traditional rule-based and optimization-based energy management strategies are analyzed. Then，focusing on the analysis and prediction of traffic information such as vehicle speed and traffic condition，prediction methods such as Markov method and artificial intelligence are reviewed，and the research progress of FCV energy management strategies by integrating traffic information is summarized. Finally，the research direction of development of FCV energy management by integrating traffic information is proposed.

To improve the lightweight level of electric cargo vehicles，a Cell To Frame （CTF） structure that integrates the frame and battery compartment is proposed in this paper. Firstly，a finite element model of the benchmark vehicle frame is established，and its static performance and free mode are calculated. The accuracy of the finite element model is verified through free mode experiments. Then，the fatigue life analysis of the frame is carried out using the nominal stress method in the time domain using the multi working condition combination fatigue load spectrum obtained from road sampling. Next，experimental design is conducted on the initial design of the CTF structure，which has been validated by finite element analysis，and a surrogate model is established. Finally，the global response search method is used for optimization design to obtain the optimal lightweight solution. The results show that after optimized design，the weight of the CTF structure is reduced by 139.95 kg compared to the traditional separation design of the frame and battery compartment，with a lightweight rate of 14.09%. At the same time，the mechanical properties and fatigue life of the CTF structure both meet the design requirements.

The goal of the structural design of a stamping die is to obtain the optimal structural configuration and the corresponding size parameters while considering both structural performance and die weight，which is difficult to achieve with a single topology optimization process. Therefore，a design method combining topology and size optimization for stamping die structure is proposed in this paper. The method avoids the complicated load mapping calculation step by adopting the node-to-node load mapping strategy，thus directly transferring the load distribution on the contact surface to the loading step in the static model. The relaxation coefficients of the structural performance in the topology optimization model are determined by the given performance evaluation index and the corresponding selection strategy so that the mechanical properties of the topology optimized dies are not weaker than those of the initial design while reducing the weight as much as possible. Finally，according to the optimal structural configuration obtained from the topology optimization，the corresponding structural parameters are determined by the multiple surrogate models-based size optimization method. The method is successfully applied to the optimal design of stamping dies for automotive structural components and its effectiveness is verified by comparing the results of the initial design，topology-optimized design，and topology size joint optimization design.