Table of Content

25 August 2023, Volume 45 Issue 8 Previous Issue    Next Issue

Select

Predictive Cruise and Lane-Changing Decision for Platoon Based on Cloud Control System Run Mei,Duanfeng Chu,Bolin Gao,Keqiang Li,Wei Cong,Chaoyi Chen 2023, 45 (8):  1299-1308.  doi: 10.19562/j.chinasae.qcgc.2023.08.001 Abstract ( 307 )   HTML ( 35 )   PDF (1638KB) ( 299 )   Save The predictive cruise and lane-changing decision method for platoon based on cloud control system is proposed in this paper to improve the safety， economy， efficiency and smoothness of platoon. This method obtains dynamic traffic information through roadside infrastructure and uploads it to the cloud platform， which uses the predictive model to estimate the future state of environmental vehicles. The penalty of different actions of the platoon is reflected in the objective function， by minimizing which the longitudinal acceleration and lateral lane-changing decision sequence are optimized synergistically， with the decision results sent to the vehicle for tracking and control. Sumo and Matlab are used to establish the simulation environment， and five sets of simulation conditions with different traffic flows are designed. The simulation results show that compared to the microscopic driving model （IDM+MOBIL）， the platoon with the proposed method can reduce the collision risk during cruise by 42.2% and the collision risk during lane change by 3.41%， with an average fuel saving rate of 1.22%， an increase of speed by 0.83%， and smoothness by 49.84%， better than the microscopic driving model in safety， economy， efficiency and smoothness. Figures and Tables | References | Related Articles | Metrics

Select

Car-Following Model for Connected Vehicles Based on Multiple Vehicles with State Change Features Xin Shi,Jian Zhu,Xiangmo Zhao,Fei Hui,Junyan Ma 2023, 45 (8):  1309-1319.  doi: 10.19562/j.chinasae.qcgc.2023.08.002 Abstract ( 145 )   HTML ( 15 )   PDF (3452KB) ( 151 )   Save For the unstable problem of traffic flow caused by the unidirectional and bidirectional abrupt change of speed of the preceding vehicle， a car following model for connected vehicles based on Multiple Vehicles with State Change Features （MVSCF） is proposed. Firstly， the acceleration difference change characteristics of multiple preceding vehicles and the optimized estimation of speed expectation are introduced in to improve the model of Multiple Vehicles Changes with Memory （MVCM）. Secondly， the critical stability conditions of MVSCF model are obtained by utilizing the micro perturbation method and the reductive perturbation method， respectively. Meanwhile， for the multiple preceding vehicles， the acceleration difference coefficient k， the preceding vehicle quantity q and the optimal speed weight ε are deduced in the circular road scenario， respectively. Finally， the traffic flow stability effect of the MVSCF model is simulated and analyzed in the straight road scenario under the influence of non-stationary change of the preceding vehicle speed. The simulation results show that when the speed of the preceding vehicle is influenced by either unidirectional or bidirectional abrupt change， the MVSCF model can better absorb the disturbance from the preceding vehicle， with the peak-to-valley difference of speed change and the fluctuation amplitude of acceleration reduced， which is conducive to improving the stability of traffic flow. Figures and Tables | References | Related Articles | Metrics

Select

Anti-disturbance and Anti-corner-cutting Control for Collaborative Path Tracking of Vehicle Platoon Yougang Bian,Tiantian Zhang,Heping Xie,Hongmao Qin,Zeyu Yang 2023, 45 (8):  1320-1332.  doi: 10.19562/j.chinasae.qcgc.2023.08.003 Abstract ( 88 )   HTML ( 2 )   PDF (11359KB) ( 98 )   Save The anti-disturbance and anti-corner-cutting collaborative path tracking control method for a vehicle platoon under the turning scenario is studied in this paper. Firstly, based on the predecessor-following topology scheme，a platoon turning anti-corner-cutting strategy is constructed by using circular-arc curve tracking path to replace the general straight-line tracking path, alleviating the overall tracking error of the vehicle platoon during turning. Secondly, a Kalman filter and a Luenberger observer are designed to address the problem of position noise and heading noise of the following vehicle or difficult measurement. Then, a collaborative path tracking controller is designed. By using the Lyapunov stability theory, sufficient conditions for system stability are derived for controller parameter design. Finally, the feasibility and effectiveness of the designed controller are validated through numerical simulation and real-vehicle experiments. Figures and Tables | References | Related Articles | Metrics

Select

Formation Containment Control for Multiple Unmanned Ground Vehicles Based on Hierarchical Constraints Qilin Wu,Yuming Lin,Zhengrong Cui,Xiaomin Zhao 2023, 45 (8):  1333-1342.  doi: 10.19562/j.chinasae.qcgc.2023.08.004 Abstract ( 97 )   HTML ( 5 )   PDF (2300KB) ( 89 )   Save An adaptive robust control method is proposed for the formation containment control of multiple unmanned ground vehicle system. The behavior constraints including formation， containment and collision avoidance are designed for the leader layer and the follower layer of the system， and the ideal driving force required to meet the constraints is obtained by the Udwadia-Kalaba equation. An adaptive robust control method based on fading adaptive law is proposed to estimate the uncertain parameters of the system so as to compensate for the influence of uncertainty. The Lyapunov function method is used to verify the stability of the designed control. Finally， the numerical simulation results show that the controlled system with time-varying uncertainty completes the formation containment task without any collision. Figures and Tables | References | Related Articles | Metrics

Select

Research on End-to-End Vehicle Motion Planning Method Based on Deep Learning Weiguo Liu,Zhiyu Xiang,Rui Liu,Guodong Li,Zixu Wang 2023, 45 (8):  1343-1352.  doi: 10.19562/j.chinasae.qcgc.2023.08.005 Abstract ( 173 )   HTML ( 10 )   PDF (4393KB) ( 160 )   Save In existing end-to-end deep learning-based autonomous driving frameworks， there is a common problem of low accuracy in planning and control prediction， often due to the single-source input data and inability to balance spatial and temporal information. To better reflect the impact of the historical interaction process between the ego vehicle， environment， and traffic participants on the current decision-making in virtual simulation testing， this paper designs a multi-level spatiotemporal attention long short-term memory network for vehicle motion planning in autonomous driving simulation environment. The algorithm extracts and represents deep abstract information of the autonomous driving environment and realizes end-to-end vehicle motion control in the simulation platform. Firstly， a convolutional module is used to extract spatial features of a single image at a specific moment using the historical continuous video frame sequence of RGB simulation data acquired by the forward-facing camera model as input. Secondly， the LSTM module is used to fuse the spatial information of the image across historical moment to obtain temporal contextual features. Additionally， to enhance the ability to extract spatiotemporal key information and accelerate network convergence， a spatiotemporal attention mechanism is applied in the fusion part of the multi-level spatiotemporal features. The proposed method is tested and validated on the Carla simulation platform. The experimental results show that the proposed method can more accurately simulate human driving decision-making behavior compared to the single spatiotemporal algorithm. Figures and Tables | References | Related Articles | Metrics

Select

Goal Supervised Attention Network for Vehicle Trajectory Prediction Jing Lian,Shuoxian Li,Yidi Liu,Dongfang Yang,Linhui Li 2023, 45 (8):  1353-1361.  doi: 10.19562/j.chinasae.qcgc.2023.08.006 Abstract ( 115 )   HTML ( 6 )   PDF (2595KB) ( 133 )   Save Effectively integrating lane information is significant for accurately predicting the future trajectory of vehicles. For the low efficiency problems existing in the fusion of lane information of the prediction model， a vehicle trajectory prediction method of Goal Supervised Attention （GSA） is proposed. Based on fusing the geometric and position information of the lane segment through the graph network， a lane goal prediction module is constructed in this paper starting from the attention model to directly supervise the model to fuse the lane goal features associated with vehicle motion into the vehicle’s motion characteristics while encoding changes in the surrounding lane topology over time. Through two Transformer networks with improved residual structure， low-level motion features are extracted and the correlation information of the lane goal at the time scale is fused sequentially to gradually update the vehicle motion features. An interaction fusion module based on a graph network is constructed to aggregate and propagate vehicle motion features globally. Experiments on the Argoverse and Changan vehicle trajectory prediction datasets show that the proposed GSA method can effectively improve the accuracy and quality of vehicle trajectory prediction in complex traffic scenarios. Figures and Tables | References | Related Articles | Metrics

Select

A Motion Planning Method for Autonomous Vehicles Considering Prediction Risk Ming Wang,Xiaolin Tang,Kai Yang,Guofa Li,Xiaosong Hu 2023, 45 (8):  1362-1372.  doi: 10.19562/j.chinasae.qcgc.2023.08.007 Abstract ( 149 )   HTML ( 15 )   PDF (4092KB) ( 263 )   Save In this paper， a motion planning method for autonomous vehicles considering prediction risk is proposed， which is based on the model predictive control algorithm while incorporating interactive prediction of the future trajectories of surrounding vehicles and the risks. Firstly， the interaction between the vehicles is modeled as a graph structure， which is then used to construct an interaction-aware motion prediction module. Then multiple prediction models with isomorphic and different parameters are trained and ensemble technology is used to obtain the uncertainty risk of the prediction network for the prediction results. The model predictive control algorithm is then applied to deal with the risk based on the obtained prediction algorithm uncertainty risk. By comprehensively considering the safety constraints， and vehicle physical property constraints in the optimization problem constraints， a motion planning method for autonomous driving considering the risk of prediction uncertainty is designed. Finally， the motion prediction capability of the established prediction model， the effectiveness of motion planning approach based on model predictive control， and the capability of motion planning to deal with prediction risks are verified based on real driving data set and SUMO simulation platform. The simulation results show that the motion planning method proposed in this paper is capable of sensing the uncertain risks posed by the prediction algorithm while acting to mitigate those risks when confronted with scenarios of high risk of prediction， such as the emergency acceleration and deceleration of nearby vehicles， which can increase the safety of road driving. Figures and Tables | References | Related Articles | Metrics

Select

Design Method of Motion Planning Reward Function Based on Utility Theory Wei Ran,Hui Chen,Jiaxin Yang,Nishimura Yosuke,Chaopeng Guo,Youyu Yin 2023, 45 (8):  1373-1382.  doi: 10.19562/j.chinasae.qcgc.2023.08.008 Abstract ( 50 )   HTML ( 5 )   PDF (2530KB) ( 65 )   Save Personalized and driver-preferred motion planning is of great importance in enhancing the acceptance of autonomous driving systems by drivers. This paper proposes a method for designing a motion planning reward function that considers driver preferences. Firstly， a two-layer structure model for quantifying driver trajectory preferences is proposed based on utility theory. The upper-layer utility evaluation model quantifies the driver's trade-off process between safety， comfort， and efficiency， while the lower-layer driver perception model quantifies the relationship between the driver's subjective feelings about safety， comfort， and efficiency and trajectory feature indicators. Then， two estimation methods for the trajectory preference model are proposed based on rating and pairwise comparison methods， respectively. Finally， the model estimation method is verified through a driver simulator evaluation test. Each participant in the experiment subjectively evaluates multiple trajectories using both rating and pairwise comparison approaches. Based on the evaluation results from the two evaluation methods and the computed trajectory features， the driver trajectory preference model is estimated using the two approaches. The results show that the proposed model can accurately describe the driver's preference evaluation process， with the estimation results based on comparison more accurate. Figures and Tables | References | Related Articles | Metrics

Select

A Method for Dynamically Calculating and Evaluating the Trustworthiness of Collaborative Perception of Intelligent Connected Vehicles Bing Zhu,Hongyi Jiang,Jian Zhao,Jiayi Han,Yanchen Liu 2023, 45 (8):  1383-1391.  doi: 10.19562/j.chinasae.qcgc.2023.08.009 Abstract ( 124 )   HTML ( 14 )   PDF (2464KB) ( 134 )   Save Collaborative perception technology enhances the perceptual performance of intelligent connected vehicles， but abnormal vehicles and malicious attack information in the collaborative network can affect the authenticity and effectiveness of collaborative perception results. To address this problem， an intelligent connected vehicle trustworthiness dynamic aggregation and evaluation method is proposed in this paper， based on occlusion state discrimination and detection effectiveness identification strategy， combined with detection results in the vehicle collaborative network. Simulation results show that the proposed collaborative perception trust evaluation method improves the reliability of detection results for collaborative perception vehicles， enhances the robustness of the intelligent connected vehicle collaborative perception process， and realizes dynamic identification of sudden malicious attacks of high-trust vehicles by the trust management model. Figures and Tables | References | Related Articles | Metrics

Select

Review on Power Battery Safety Warning Strategy in Electric Vehicles Da Li,Junjun Deng,Zhaosheng Zhang,Peng Liu,Zhenpo Wang 2023, 45 (8):  1392-1407.  doi: 10.19562/j.chinasae.qcgc.2023.08.010 Abstract ( 211 )   HTML ( 14 )   PDF (1940KB) ( 263 )   Save Battery safety has become an important issue restricting the development of electric vehicles. Accurate and timely battery safety warning can ensure the safety of occupants' life and property and improve the safety level of electric vehicles. A comprehensive review on the battery safety warning strategies in electric vehicles is conducted in this paper. Firstly， the definition of battery safety state is reviewed， and the framework of this review is proposed. Then， the battery safety characteristics and safety influencing factors analysis， battery-modeling methods， battery safety risk assessment/prediction methods are reviewed in detail. The advantages and disadvantages of different methods are summarized. Finally， the achievements and deficiencies of existing researches are summarized， and the development trend of battery safety warning technology in electric vehicle is proposed， including the new sensor technology， multi-factor integrated battery safety warning method and "terminal-side-cloud " battery safety warning system. This review provides a reference for further research on the safety warning strategy of electric vehicle battery. Figures and Tables | References | Related Articles | Metrics

Select

Research on Scenario Library Optimization Method Based on Scenario Dimension Reduction and Sampling Method Xianglei Zhu,Zhixin Wu,Yufei Zhang,Shuai Zhao,Keqiu Li,Bohua Sun 2023, 45 (8):  1408-1416.  doi: 10.19562/j.chinasae.qcgc.2023.08.011 Abstract ( 82 )   HTML ( 7 )   PDF (3138KB) ( 113 )   Save In this paper， scenario dimension reduction and sampling methods are used to optimize the scenario library. Firstly， scenario elements are classified， with their importance weights solved by the Analytic Hierarchy Process， based on which the scenario elements are discretized to construct the scenario space. Then， the risk degree of scenarios are calculated by the attributes of the scenario space itself and the occurrence probability of scenarios in the scenario space are calculated using the Natural Driving Database to construct the importance function. The critical scenarios are screened out from the artificially constructed scenario space through the guidance of the Natural Driving Database to form the testing scenario database. At the same time， to speed up the search process， the multi-starting optimization algorithm and the flood-filling algorithm are used for sampling search. Finally， the effectiveness of the critical scenarios is verified by the scenario risk assessment method. The results show that the scenario library optimization method proposed in this paper can screen out critical scenarios for automatic driving test， and improve the efficiency and practical significance of automatic driving testing. Figures and Tables | References | Related Articles | Metrics

Select

Research on Test Scenarios of Passenger Cars and Two-Wheelers at Intersections Based on CIDAS Accident Data Lin Hu,Gen Li,Fang Wang,Miao Lin,Ning Wu 2023, 45 (8):  1417-1427.  doi: 10.19562/j.chinasae.qcgc.2023.08.012 Abstract ( 128 )   HTML ( 7 )   PDF (3767KB) ( 139 )   Save The existing research on two-wheeler accident scenarios does not distinguish the accident location， so the extraction of two-wheeler accident scenarios at the intersection is far from enough. Therefore， this paper conducts a cluster analysis on 1 239 cases of intersection accidents involving passenger vehicles and two-wheelers from the CIDAS database， and extracts 10 typical two-wheeler accident scenarios at intersections. For the group of strongly correlated variables， the single-layer clustering and double-layer clustering methods are compared， and it is found that the double-layer clustering method has better performance in sample division and interpretation of results. The clustering results are analyzed from the perspective of scenario frequency and injury risk， and the correlation between velocity and scenario injury risk index is further explored. Through the analysis of accident causes， some characteristics scenarios are identified， such as failure to give way， two-wheeler running in the opposite direction， traffic light conflict （including jumping the red light and traffic light switching gap） and visual obstruction. The two-wheeler accident scenarios extracted in this paper can provide a reference basis for the test of intelligent vehicles and active safety systems. Figures and Tables | References | Related Articles | Metrics

Select

Testing and Analysis of the Robustness of Decision-Making and Planning Systems Based on Fault Injection Xinzheng Wu,Xingyu Xing,Lihao Liu,Yong Shen,Junyi Chen 2023, 45 (8):  1428-1437.  doi: 10.19562/j.chinasae.qcgc.2023.08.013 Abstract ( 108 )   HTML ( 2 )   PDF (4282KB) ( 119 )   Save Automated driving systems operate in complex and diverse environments. Considering the performance limitations of the sensors and the functional insufficiency of the perception algorithms under certain trigger conditions， it is inevitable that the upstream perception results of the autonomous driving system will be incorrect. Therefore， it is essential to test the robustness of decision-making and planning systems under conditions of erroneous upstream data to ensure the safety of automated driving. Firstly， in this paper， a data model based on a six-layer scenario ontology model and a fault model containing four types of uncertainty error patterns are proposed. Further， a generic fault injection framework named SOFIF is constructed to enable modification of upstream data. Finally， the robustness of two decision-making and planning systems under the error patterns of uncertainty existence is compared and analyzed based on Hardware-in-the-Loop （HiL） simulation testing， with the hazard rate proposed as the quantitative evaluation index. The hazard rate of the two tested systems is 0.89 and 0.64， respectively， indicating a large gap in the robustness of the two tested systems and further proving the effectiveness of SOFIF. Figures and Tables | References | Related Articles | Metrics

Select

Accelerating Technologies of Numerical Optimization for Motion Planning Designed by Nonlinear Model Predictive Control Feng Gao,Defu Feng,Qiuxia Hu 2023, 45 (8):  1438-1447.  doi: 10.19562/j.chinasae.qcgc.2023.08.014 Abstract ( 95 )   HTML ( 0 )   PDF (7033KB) ( 102 )   Save Nonlinear Model Predictive Control （NMPC） is an effective method for the motion planning of automated vehicles， but its high demand of computation resources for numerical optimization limits its practical application. This paper improves the solving speed of the numerical optimization of NMPC motion planning system by reducing the dimension of optimization variables and simplifying the non-convex constraints for obstacle avoidance. Given the high nonlinearity of vehicle dynamics， Lagrange interpolation is adopted to discretize the state function of vehicle dynamics and the objective function to ensure the accuracy with less discretization points. Furthermore， an adaptive strategy is designed to adjust the order of Lagrange polynomials based on the numerical analysis of the distribution characteristics of the discretization error to further reduce the dimension of optimization variables. Moreover， a hybrid strategy is presented to construct the constraints for obstacle avoidance by combing the elliptic and linear time-varying ones together to realize good balance between the difficulty of numerical optimization and the conservatism of optimized results while ensuring the driving safety. The acceleration effect and performance of the proposed method are validated by simulation and experimental tests under various scenarios with multi-obstacles. The results show that compared with traditional methods the accuracy and efficiency of discretization of the proposed method is improved by 74% and 60%， respectively. Figures and Tables | References | Related Articles | Metrics

Select

Heterogeneous Multi-object Trajectory Prediction Method Based on Hierarchical Graph Attention Qihui Hu,Yingfeng Cai,Hai Wang,Long Chen,Zhaozhi Dong,Qingchao Liu 2023, 45 (8):  1448-1456.  doi: 10.19562/j.chinasae.qcgc.2023.08.015 Abstract ( 111 )   HTML ( 7 )   PDF (2356KB) ( 152 )   Save Effectively predicting the future trajectories for surrounding multiple targets is critical to the success of autonomous vehicle decision-making and motion planning. Most existing studies consider pairwise interactions between individual vehicle behaviors， while ignoring the influence of different reaction patterns among heterogeneous traffic participants and other scene factors on prediction， which reduces the rationality of the predicted trajectories and affects the safety of motion control. In view of this， this paper proposes a heterogeneous multi-target trajectory prediction method HGATP based on hierarchical graph attention. Firstly， a category-target-lane three-level graph is innovatively constructed， and different types of targets are independently coded with categories using GRU and GCN respectively to capture the features of different categories. Secondly， to enhance the edge representation of the heterogeneous target interaction graph， the attention mechanism of hierarchical graph is constructed to separately capture the interaction between categories and categories and the interaction between targets and lanes so as to achieve efficient interaction and sharing of maps among heterogeneous multiple targets. Finally， a prediction network is constructed to predict the trajectories of multiple targets based on the target trajectory information and the lane information of the region. To evaluate the performance of the model， experiments are conducted on the INTERACTION and nuScenes datasets respectively. The experiments show that the proposed model reduces the average displacement error and final displacement error of single-target trajectory output on the nuScenes dataset by more than 20%， with the ADE loss effect of multi-target trajectory output on the INTERACTION dataset reduced by 2 m error compared with the baseline method， which improves the reasonableness of vehicle trajectory prediction under complex road structures. Figures and Tables | References | Related Articles | Metrics

Select

Visual SLAM Based on Jacobian Null-space Marginalization Tao Lu,Xin Jin,Yifei Liao,Shengjie Huang,Yilin Yang,Guotao Xie,Xiaohui Qin 2023, 45 (8):  1457-1467.  doi: 10.19562/j.chinasae.qcgc.2023.08.016 Abstract ( 56 )   HTML ( 2 )   PDF (5023KB) ( 68 )   Save The existing visual SLAM frameworks based on nonlinear optimization， in order to reduce the computational resource occupation and improve the system operation speed when solving large-scale linear equations， mostly use the Hession matrix sparsity and marginalization strategy in incremental equations to reduce the order of the problem. However， these methods still need a large amount of memory to explicitly construct the ultra-high dimensional Hessian matrix. Moreover， due to the sensitivity of the method to numerical changes， in order to reduce numerical errors， in actual deployment， they often rely on double precision floating point numbers to solve， which limits the application in low computing power platforms. To solve this problem， this paper proposes a visual SLAM method based on Jacobian domain null-space marginalization， which projects the landmark Jacobian matrix to its left null-space in the back-end optimization module， achieves the effect of reduction and improves the solution efficiency on the premise of avoiding the construction of Hessian matrix， and proves the equivalence of the two marginalization methods algebraically. From the perspective of numerical analysis， it is proved that the marginalization method proposed in this paper has better numerical stability and can support the single precision floating point solution， with further improvement of the efficiency. The open dataset and real vehicle test show that the method in this paper has better solution speed and accuracy than the general optimizer based on Schur complement marginalization. Figures and Tables | References | Related Articles | Metrics

Select

Research on Semantic Segmentation of Uneven Features of Unpaved Road Wenguang Wu,Shuangyue Tian,Zhiyong Zhang,Bin Zhang 2023, 45 (8):  1468-1478.  doi: 10.19562/j.chinasae.qcgc.2023.08.017 Abstract ( 80 )   HTML ( 3 )   PDF (5272KB) ( 87 )   Save The complexity of uneven feature parameters of unpaved roadincreases the difficulty of extracting effective information for path planning and decision control of autonomous vehicles. Accurate semantic segmentation method can help simplify road uneven parameter information， improve the accuracy and efficiency of feature recognition， thus improve the safety and comfort of autonomous driving of vehicles. Therefore， this paper proposes a semantic segmentation method for uneven features of unpaved road to classify uneven features of different dimensions and elevation differences. Firstly， the Gaussian function is introduced to establish the expression model of unpaved road， and the automatic labeling method of uneven features is proposed and the simulation data set is constructed， making up the gap of unpaved road point cloud data set. Then， a semantic segmentation model of unpaved road uneven features is built. Based on multi-level feature extraction structure of Pointnet++， the semantic segmentation of non-paved road uneven features is realized for the first time. Finally， the sand table model of unpaved road features is established and the proposed method is used for verification of the measured data. The results show that the proposed method can accurately classify the road uneven characteristics， and has good robustness in data of different point cloud data densities and road surface ranges. Figures and Tables | References | Related Articles | Metrics

Select

Intelligent Cockpit Perceptual Image Prediction Based on BP Neural Network Optimization Genetic Algorithm Guoqiang Chen,Zhengyi Shen,Li Sun,Mengfan Zhi,Tong Li 2023, 45 (8):  1479-1488.  doi: 10.19562/j.chinasae.qcgc.2023.08.018 Abstract ( 131 )   HTML ( 5 )   PDF (3127KB) ( 126 )   Save In order to reduce subjective interference and meet the diverse emotional needs of users， the design method of intelligent cockpit perceptual image prediction based on BP neural network optimization genetic algorithm is proposed. From the user's point of view， user emotional image is obtained and the intensity is divided. Factor analysis method is used to reduce dimension to obtain target images and cockpit samples of new energy vehicles. Cluster analysis method is applied to screen and obtain advantage samples and the modeling characteristic factors of intelligent cockpit central control are extracted by combining with morphological analysis method. Based on BP neural network， the mapping model of specific target image and modeling feature factors is constructed， and the functional relationship between the two is obtained， which is used as fitness function to carry out genetic algorithm analysis， optimize the optimal combination of modeling factors under the specific image， and complete the combination of evaluation method and optimization method. According to the combination of advantage factors， the design practice is carried out to verify the practicability of the method. The results show that the method can effectively meet the multidimensional emotional needs of users， and provide a new idea and reference for the diversification of intelligent cockpit modeling design. Figures and Tables | References | Related Articles | Metrics

Select

An Investigation on Intake Preheating Characteristics Based on Spray Wall Impinging Ignition for Diesel Engine Yixiao Zhang,Xiao Ma,Xinhui Lu,Zhi Wang,Weilin Zhuge,Shijin Shuai 2023, 45 (8):  1489-1498.  doi: 10.19562/j.chinasae.qcgc.2023.08.019 Abstract ( 80 )   HTML ( 8 )   PDF (4966KB) ( 70 )   Save For the cold start of heavy-duty diesel engine in low temperature environment， an intake preheating scheme using spray ignition by hot wall impinging combined with flame stabilization by recirculation is proposed. Based on the self-designed and built preheating experiment apparatus， the temperature rising and combustion characteristics under different inflow speed， fuel spray targeting and injection strategy are studied， and CFD numerical simulations are conducted. The experimental results show that ignition and temperature rise are strongly sensitive to spray targeting， and there is an optimal position of heating plate， with the mean temperature rising rate reaching 4.24 ℃/s at the inflow speed of 10 m/s. To balance the temperature rising rate， combustion efficiency and maintenance cost， the injection strategy with an injection period of 20~25 ms and injection pulse width of 1~3 ms should be adopted at high inflow speed. The fast droplets rebound and break up after impinging the heating plate， which falls in the Leidenfrost breakup mode. The simulation results show that a recirculation region with local flow speed of lower than 5 m/s is formed by the spoiler， which promotes evaporation and fuel-air mixing， and it is conducive to ignition and flame stabilization. For appropriate match between the injection mass with injection frequency， it is essentially to make the combustion duration suitable with injection period， so as to make full use of fuel and increase temperature rise and heat release rate. Figures and Tables | References | Related Articles | Metrics