Search

Connected and Autonomous Vehicles are predicted to drive in a platoon with the aid of communication technologies to increase traffic flow efficiency while improving driving comfort, safety, fuel consumption, and exhaust emissions. However, some vehicles in a group may face communication failures. Such potential risks may even worsen the efficiency and safety of traffic flow and increase fuel consumption and exhaust emissions. Therefore, there is a need to propose an alternative scheme to control traffic flow effectively through vehicle-based information without the aid of communication technologies. In this paper, a deterministic acceleration model was developed considering the sensor’s detection range to capture the underlying process of a car following the dynamics of autonomous vehicles. A delayed-feedback control was proposed based on the current and previous states of throttle angle to increase traffic flow stability and improve fuel consumption and exhaust emissions without the aid of communication technologies. Numerical simulations were carried out to study the impact of sensor detection range on micro-driving behavior and explore the effect of the proposed delayed-feedback control on the fuel consumption and exhaust emissions of autonomous vehicles in large-scale traffic flow. The numerical results certified that using delayed feedback with proper gains and delay time improved the total fuel consumption and exhaust emissions of autonomous vehicles.

This paper is concerned with the problem of robust constraint control for direct yaw moment control (DYC) system with sideslip angle. A two degree of freedom vehicle dynamics model is considered he...

The piecewise affine (PWA) model represents an attractive model structure for approximating nonlinear systems. In this paper, a procedure for obtaining the PWA model of the tire nonlinear cornering properties is introduced. In this approach, the highly nonlinear dynamic of the tire cornering properties is well approximated by a set of affine maps which relate inputs and outputs. These maps are defined in disjunctive regions in the regression space, itself composed of system inputs and outputs. The tire cornering properties tests are firstly carried out through a high-performance flat-plate test bench, thus the experimental data which can accurately reflect the tire cornering properties is obtained. On this basis, the PWA identification of the tire cornering properties is composed of the data clustering, the parameter estimation of the affine submodels and the calculation of the hyperplane coefficient matrices, which are respectively achieved by means of fuzzy c-means clustering, weighted least-squares and support vector machines. Finally, to verify the PWA model accuracy in approximating the tire nonlinear cornering properties, the comparison between the simulation results of the PWA identification model and the experimental data is conducted and the comparison results are analyzed.

The deep learning object detection algorithms have become one of the powerful tools for road vehicle detection in autonomous driving. However, the limitation of the number of high-quality labeled training samples makes the single-object detection algorithms unable to achieve satisfactory accuracy in road vehicle detection. In this paper, by comparing the pros and cons of various object detection algorithms, two different algorithms with a different emphasis are selected for a weighted ensemble. Besides, a new ensemble method named the Soft-Weighted-Average method is proposed. The proposed method is attenuated by the confidence, and it “punishes” the detection result of the corresponding relationship by the confidence attenuation, instead of by deleting the output of a certain model. The proposed method can further reduce the vehicle misdetection of the target detection algorithm, obtaining a better detection result. Lastly, the ensemble method can achieve an average accuracy of 94.75% for simple targets, which makes it the third-ranked method in the KITTI evaluation system.

The antilock braking system (ABS) is a representative technology to improve the safety of hard braking in automobiles. The slip rate control has been a challenging issue due to the complicated characteristics of tires and the strong nonlinearity of the system. In this paper, a novel adaptive finite-time controller for ABS is developed to improve braking performance. Different from the current control strategies for ABS, the extended finite-time stability theory and state constraint are comprehensively considered in the proposed control strategy. The extended finite-time stability theory is applied to deal with the system uncertainties, by which the convergence of slip rate tracking error is achieved. And the asymmetric tan-type barrier Lyapunov function (BLF) is used to ensure that the wheel slip ratio is within a smaller and more stable area. Finally, according to the simulation and experiment, compared with the existing BLF controller, a faster convergence rate, better robustness and anti-disturbance performance of ABS can be achieved with the proposed strategy.

Fast and accurate prediction of pedestrian trajectory around vehicles can reduce or even prevent most traffic accidents and improve the safety of traffic participants. This involves the real-time interaction and fusion of various information, such as the vehicle’s motion characteristics, the pedestrian’s historical motion trajectory, and the motion relationship between people and cars. However, most of the existing algorithms use RNN as the skeleton to process the information prediction trajectory, which is weak in extracting the internal relationship between different information, and the running time of the algorithm is long. To solve these problems, we propose a Transformer based deep learning algorithm (CVTF) to complete the first-person perspective pedestrian trajectory prediction task. We have the following innovations about this model: 1: We use the stamp coding method for vehicle speed and pedestrian information to ensure we can learn the characteristics of different information sources. 2: Transformer structure is used, and its attention mechanism is improved (Maybe-self attention), which improves the running speed of the model and reduces the memory consumption. 3: Combined with Conditional Variational Autoencoder (CVAE), hidden variables are introduced to improve the prediction accuracy. Experiments on three pedestrian trajectory prediction benchmarks show that our model achieves the most advanced performance.

Accurate localization is a crucial step for intelligent vehicles (IVs). And vision-based localization methods are promising due to its good accuracy and low cost. However, vision-based methods are usually not robust enough due to the errors of matching similar road scenarios. In this paper, we proposed a visual map-based localization method, called multi-view site matching (MVSM). We proposed using two camera views (i.e., downward-view and front-view) to construct visual map. The visual map consists of a serial of nodes. Each node encodes the features of the road, the 2D structure, and the poses of the vehicle. Based on the constructed visual map, we proposed a multi-scale method for accurate vehicle localization. In coarse localization, we adopt a topological model to obtain a set of candidate nodes from visual map. Furthermore, holistic features from front view are matched within the candidates such that the best matched node is determined for image-level localization. In metric localization, the best matched is first verified with the local features from downward view. And the vehicle pose is finally computed by utilizing the 2D structure from the verified nodes in the map. In the experiment, the proposed MVSM method has been tested with actual field data covering different pavement types in different seasons. The proposed MVSM method can achieve less than 0.20m mean localization errors. Compared to existing vision-based methods, the proposed method utilizes two views to enhance image-level localization and 2D pavement structure to improve metric localization so as to greatly improve the overall localization performance.

Multi-degree-of-freedom (MDOF) magnetic bearings have been widely investigated and designed for various applications. However, a new design magnetic bearing cannot be directly used without optimization due to the not relatively excellent performance. Besides, there may be a lack of consideration of the interaction of parameters in the design process. Hence, in this article, a three-degree-of-freedom hybrid magnetic bearing (THMB) is optimized as an example. First, a comprehensive sensitivity analysis is carried out to show the relationship between the parameters and optimization objectives in detail. Second, a cross-factor variance analysis is considered due to the possibility of parameter interaction. And then, a hierarchical multi-objective optimization structure is used with the Kriging model and the non-dominated Sorting Genetic Algorithm II (NSGA II). The simulation results verify the validity of the proposed method, and the prototype is under manufacture for further evaluation.

The use of object detection algorithms has become extremely important in autonomous vehicles. Object detection at high accuracy and a fast inference speed is essential for safe autonomous driving. Therefore, the balance between the effectiveness and efficiency of the object detector must be considered. This article proposes a one-stage object detection framework for improving the detection accuracy while supporting a true real-time operation based on the YOLOv4. The backbone network in the proposed framework is the CSPDarknet53_dcn(P). The last output layer in the CSPDarknet53 is replaced with deformable convolution to improve the detection accuracy. In order to perform feature fusion, a new feature fusion module PAN++ is designed and five scales detection layers are used to improve the detection accuracy of small objects. In addition, this article proposes an optimized network pruning algorithm to solve the problem that the real-time performance of the algorithm cannot be satisfied due to the limited computing resources of the vehicle-mounted computing platform. The method of sparse scaling factor is used to improve the existing channel pruning algorithm. Compared to the YOLOv4, the YOLOV4-5D improves the mean average precision by 4.23% on the BDD data sets and 1.68% on the KITTI data sets. Finally, by pruning the model, the inference speed of YOLOV4-5D is increased 31.3% and the memory is only 98.1 MB when the detection accuracy is almost unchanged. Nevertheless, the proposed algorithm is capable of real-time detection at faster than 66 frames/s (fps) and shows higher accuracy than the previous approaches with a similar fps.

This paper introduces a mechanic-electronic-hydraulic powertrain system (MEH-PS) composed of an electro-mechanical hybrid system and hydro-mechanical composite transmission according to current mainstream drive and transmission technologies. Firstly, the structural design concept of the system is introduced, and the power and transmission components are selected according to the actual working requirements of the tractor. Then, the principles of various drive modes and transmission modes of the powertrain system are explained, and the speed regulation characteristic curves of the hydro-mechanical transmission (HMT) are given; the speed characteristics, torque characteristics, power split characteristics, and efficiency characteristics of the powertrain system are analyzed. Finally, a tractor simulation and test model was developed to verify its performance under certain operating conditions. Simulation results show that: the tractor acceleration performance is improved, the speed range is wider, the power components and hydraulic components can also meet the requirements, the HMT in a wide range of speed to maintain the average efficiency of above 86%. The bench test results show that: the step-less speed regulation characteristics and efficiency characteristics of the powertrain system are basically consistent with the simulation results.

At present, most semantic segmentation models rely on the excellent feature extraction capabilities of a deep learning network structure. Although these models can achieve excellent performance on multiple datasets, ways of refining the target main body segmentation and overcoming the performance limitation of deep learning networks are still a research focus. We discovered a pan-class intrinsic relevance phenomenon among targets that can link the targets cross-class. This cross-class strategy is different from the latest semantic segmentation model via context where targets are divided into an intra-class and inter-class. This paper proposes a model for refining the target main body segmentation using multi-target pan-class intrinsic relevance. The main contributions of the proposed model can be summarized as follows: a) The multi-target pan-class intrinsic relevance prior knowledge establishment (RPK-Est) module builds the prior knowledge of the intrinsic relevance to lay the foundation for the following extraction of the pan-class intrinsic relevance feature. b) The multi-target pan-class intrinsic relevance feature extraction (RF-Ext) module is designed to extract the pan-class intrinsic relevance feature based on the proposed multi-target node graph and graph convolution network. c) The multi-target pan-class intrinsic relevance feature integration (RF-Int) module is proposed to integrate the intrinsic relevance features and semantic features by a generative adversarial learning strategy at the gradient level, which can make intrinsic relevance features play a role in semantic segmentation. The proposed model achieved outstanding performance in semantic segmentation testing on four authoritative datasets compared to other state-of-the-art models.

Following man-made rules in the traditional control method of autonomous driving causes limitations for intelligent vehicles under various traffic conditions that need to be overcome by incorporating machine learning-based method. The latter is inherently suitable for simple tasks of autonomous driving according to its limited characteristic under complex multi-lane traffic conditions. In this paper, a decision control method is proposed based on multi-task reinforcement learning to address the shortcomings of autonomous driving control under complex traffic conditions. Herein, the autonomous driving task is divided into several subtasks utilizing the proposed method to reduce the training time and improve traffic efficiency under complex multi-lane traffic condition. To ensure the efficiency and robustness of agent convergence to the optimal action space, an adaptive noise exploration method is designed for the subtasks with convex characteristics. Five-lane driving tasks scenarios embedded in Carla simulator have been conducted to verify the proposed method. The results of the simulation draw the conclusion that the proposed method increases the driving efficiency of intelligent vehicles under complex traffic conditions.

To improve the mode switching quality of the power-split hybrid electric vehicle (PS-HEV), a compound torque coordinated control strategy is proposed. Aiming at the problem of engine dynamic response lag, the engine real-time torque estimator is designed, and then the torque ripple at the output end of the power coupling mechanism is reduced through the basic motor torque compensation. On this basis, considering the existence of non-ideal communication networks in actual vehicle control systems, the tremendous impact of communication network time delay and interruption on the mode switching stability and vehicle fuel consumption has been deeply revealed. Then the compound coordinated control strategy including the BP-smith predictive controller, motor torque change rate limiting module, network transmission mechanism with fixed communication priority and fault-tolerant torque coordinated control module is put forward and verified by simulation and hardware-in-the-loop test. The results show that the compound coordinated control strategy could still guarantee the system stability, mode switching smoothness and vehicle fuel economy under the interference of stochastic communication delay and interruption.

In this article, an optimal control strategy for a bearingless permanent magnet synchronous machine (BPMSM) drive is proposed. The state feedback control (SFC) based on the grey wolf optimization (GWO) algorithm is applied. As for the BPMSM system, coupling and nonlinearity exist, which hinders the SFC. Hence, the linearization of the BPMSM mathematical model is implemented first. Second, the discretized state model with the augmented integrals of the displacement error and the angular speed error is obtained. Then, the weighting matrices $K_{d}$ are obtained by employing the GWO algorithm. Finally, simulations and experiments are carried out to verify the effectiveness of the proposed method. Comparisons between the controllers with and without the penalty term are conducted. Meanwhile, the proportional-integral (PI) controllers based on the genetic algorithm and the proposed one are compared as well. The results show the superiority of the proposed method reflecting in faster response and no overshoot compared with the PI controllers.

This article investigates the efficient robust design optimization of a five-phase permanent magnet (PM) hub motor for electric vehicles. Besides the requirement of high-performance, like high torque density, low torque ripple and efficiency, fault-tolerant operation capability are also considered in the design optimization. To ensure that the motor performance is not sensitive to the variations of manufacturing tolerances, robust design optimization is employed to the investigated motor. To improve the fault tolerant capability of the motor, the motor performances under fault operation are also considered in the optimization. A Fuzzy-based sequential Taguchi robust optimization method is proposed to improve the comprehensive performance and save computing time. The proposed method is efficient because it holds the advantages of Taguchi method, fuzzy theory, and sequential optimization strategy. The motor performance is improved significantly by using the proposed method. Experimental results verify the accuracy of the model used in this study.

The power-split hybrid electric vehicle has multiple working modes, which can be switched to different working mode according to different working conditions. The main switching process involved in the vehicle driving is the switch from the pure electric mode to the hybrid driving mode. This paper studies the mode switching process involved in the power-split hybrid electric vehicle driving process, and a nonlinear dynamic equation of the electromechanical coupling of the corresponding transmission system is established. Then the multi-scale method is employed to solve the dynamic equation, and the amplitude-frequency response curve is drawn. According to the curve, the effects of load, mechanical input excitation of the engine and motor electromagnetic excitation on the electromechanical coupling torsional vibration of the transmission system are studied. The engine and motor torque distribution schemes are obtained by analyzing the amplitude-frequency response curve of the torsional vibration characteristics of the system. The analysis results show that the vibration instability phenomenon of the transmission system can be avoided by establishing the nonlinear dynamic equation of the transmission system, analyzing the vibration characteristics of the vibration system, and optimizing the torque distribution of a PS-HEV at different working modes.

A novel four-phase 16/10 belt-driven starter generator segmented switched reluctance motor has been proposed in a previous work to reduce torque ripple and increase the fault tolerance ability. Based on the previous research, the segmented switched reluctance motor digital control system is designed and presented. The digital control system including a power converter, detection circuits, and protection circuits is introduced in detail. For detection circuits, the half-detection method is employed to decrease the cost of the system. In addition, based on MicroAutoBox DS1401, a rapid control prototype platform is established. With this software system, it is easy to transfer control models and realize real-time control directly. Then, the speed closed closed-loop control for the segmented switched reluctance motor is applied to verify the proposed system. It contains current chopper control at a low speed and angle position control at a high speed. The simulation results are given, including the flux, current, torque, and efficiency range over the entire speed range of the segmented switched reluctance motor. Finally, the experimental results are presented to verify the simulation results and the effectiveness of the system. It can be found that the simulation and experimental results are consistent and acceptable, which means that the proposed digital system can operate naturally and accurately under speed closed loop control. Hence, the proposed digital system has high compatibility and practicability.

Tire cornering characteristics have significant influence on vehicle lateral dynamics control. Unlike traditional tire mechanics models which are established based on the research experience or the mechanics mechanism, in this study, a novel experimental data-driven modeling approach is presented to model the tire cornering characteristics based on piecewise affine (PWA) identification method. In this approach, the highly nonlinear dynamic of the tire cornering characteristics is well approximated by several affine submodels acting on different regions. To obtain the experimental data which can accurately reflect the tire cornering characteristics, the tire tests are firstly carried out through a high-performance flat-plate test bench. On this basis, the PWA identification of the tire cornering characteristics is composed of the data clustering, the parameter estimation of the affine submodels and the calculation of the hyperplane coefficient matrices. The simulation results of the PWA identification model are finally compared with the experimental data to illustrate that the identified model has high accuracy in approximating the tire nonlinear cornering characteristics under wide range driving conditions.

The fuel economy of hybrid electric vehicles is very closely associated with the energy management strategy (EMS). In this paper, a practicality-oriented adaptive EMS for a parallel hybrid electric bus is presented, which combines the adaptive neuro-fuzzy inference system (ANFIS) and equivalent consumption minimization strategy (ECMS). Considering the regular and fixed route of the city bus, the optimal control trajectories can be attained by the dynamic programming in advance. Using the rolling optimization method, a group of optimal equivalent factors is extracted from aforementioned control trajectories and used as the training samples. Then, a trained ANFIS model that produces the optimal equivalent factor online is constructed, showcasing striking superiority in self-learning and inference. By applying the derived equivalent factor in the framework of the ECMS, an adaptive energy management controller is available to achieve desirable power distribution online. Finally, the simulation and hardware in the loop (HIL) tests are used to validate the effectiveness and feasibility of the controller. The results demonstrate that, compared with other strategies, the fuel economy with the proposed strategy can be effectively improved.

In order to make full use of the driver’s long-term driving experience in the process of perception, interaction and vehicle control of road traffic information, a driving behavior rule extraction algorithm based on artificial neural network interface (ANNI) and its integration is proposed. Firstly, based on the cognitive learning theory, the cognitive driving behavior model is established, and then the cognitive driving behavior is described and analyzed. Next, based on ANNI, the model and the rule extraction algorithm (ANNI-REA) are designed to explain not only the driving behavior but also the non-sequence. Rules have high fidelity and safety during driving without discretizing continuous input variables. The experimental results on the UCI standard data set and on the self-built driving behavior data set, show that the method is about 0.4% more accurate and about 10% less complex than the common C4.5-REA, Neuro-Rule and REFNE. Further, simulation experiments verify the correctness of the extracted driving rules and the effectiveness of the extraction based on cognitive driving behavior rules. In general, the several driving rules extracted fully reflect the execution mechanism of sequential activity of driving comprehensive cognition, which is of great significance for the traffic of mixed traffic flow under the network of vehicles and future research on unmanned driving.

In order to improve the mode switching stability of a power-split hybrid electric vehicle (HEV), a torque coordinated control strategy based on disturbance observation and compensation is proposed. Aiming at the problem of engine torque disturbances caused by engine modeling error, torque control error, working environment interference and other factors, and vehicle load torque interference caused by changes in vehicle driving conditions, an improved linear extended state observer (ILESO) is designed at first. According to the deviation control principle, the state variable regulation mechanism using the same error term in the traditional linear extended state observer (TLESO) is revised, and improved by adding the corresponding deviation between the state variable and its observed value separately. Then the Lyapunov stability of the error system for the ILESO is proved gradually. On this basis, a torque redistribution algorithm of two motors based on disturbances compensation is put forward. After that, simulation verification and road adaptability analysis are carried out subsequently. The results show that the coordinated control strategy based on ILESO, compared with the TLESO, has higher observation accuracy, and makes the HEV have better vehicle speed tracking stability and mode switching smoothness when the vehicle is subject to the same external disturbance, as well as excellent adaptability under a wide range of road conditions.

This paper presents a novel algorithm to deal with dynamic multiobjective optimization problems, in which the objective functions change over time. The algorithm adopts the decomposition framework to decompose the multiobjective optimization problems into a number of scalar optimization subproblems. For each subproblem, its respective solutions obtained in several former consecutive environments can form a moving trajectory over time. A shift vector guided prediction model is proposed, which samples three intermediately previous solutions of each subproblem to construct two shift vectors. The shift vectors use the weighted summation to generate a new shift vector as the forthcoming motion of the target solution. Then a new location in the later environment is estimated based on the current location and the newly generated shift vector. When detecting an environmental change, the multiobjective evolutionary algorithm based on decomposition will update the population using the predicted solutions by the proposed model. Empirical results demonstrate that our proposed algorithm is effective in tracking dynamic optimal solutions and shows great superiority comparing with state-of-the-art methods.

The traditional salient object detection models can be divided into several classes based on the low-level features of images and contrast between the pixels. This paper proposes an adversarial learning model (ALM) that includes the generative model and discriminative model. The ALM uses the original image as an input of the generative model to extract the high-level features and forms an initial salient map. Then, the discriminative model is utilized to compare differences in the features between the initial salient map and the ground truth, and the obtained differences are sent to the convolutional layers of the generative model to adjust the parameters for the generative model updating. Due to the serial-iterative adjustment, the salient map of the generative model becomes more similar to the ground truth. Lastly, the ALM forms the salient map fused with the super-pixels by enhancing the color and texture features, so the final salient map is obtained. The ALM is not limited to the color and texture features; on the contrary, it fuses multiple features and achieves good results in the salient target extraction. The experimental results show that ALM performs better than the other ten state-of-the-art models on three different datasets. Thus, the proposed ALM is widely applicable to the salient target extraction.

Crowd counting has played a substantial role in intelligent surveillance. This work presents a multi-scale multi-task convolutional neural network (MSMT-CNN) to estimate accurate density maps, thus can count the crowd through summing up all values in the estimated density maps. The ground truth density maps used for training are generated by a novel adaptive human-shaped kernel. In addition to resolving the scale problem with the multi-scale strategy, the multi-task learning strategy is added so as to make the estimated density maps more accurate. A weighted loss function is proposed to enhance the activations in dense regions and suppress the background noise. Experimental results on two benchmarking datasets reveal the strong ability of MSMT-CNN. Compared with existing crowd counting methods, the root mean squared error is decreased by 39.8 on the UCF_CC_50 dataset, and the mean absolute error is decreased by 2.3 on the World Expo’10 dataset. Furthermore, the evaluations in practical bus videos verify the practicability of our MSMT-CNN.

State-of-health (SoH) is one of the critical battery states that must be estimated and monitored by the on-board battery management system in electric vehicles. In this paper, the capacity degradation for the lithium iron phosphate (LiFePO 4 ) battery is detected based on the fast-dynamic behavior of the charge current during the constant-voltage (CV) period. Firstly, the time constant of the fast-dynamic CV charge current, i.e., Teq,1 of the simplified $2^{\mathrm{n}\mathrm{d}}-$order resistor-inductor (RL) network based equivalent circuit model (ECM) developed by the authors, is selected as a characteristic parameter correlating with the battery capacity fade, and the reference regression function between Teq,1 and the battery SoH is established. Furthermore, for the incomplete CV charge process, the reference regression function can be estimated by constructing the linear prediction model and the subsequent extrapolation. At last, the aging data from four LiFePO 4 batteries are employed to evaluate the performance of the proposed method. The results show that the proposed method yields a satisfactory SoH estimation accuracy, and is robust to the incomplete CV charge process.

Accurate estimation of the actual battery capacity is crucial for a reliable battery management system. In this paper, the battery capacity is estimated based on the battery surface temperature change under the constant-current scenario. Firstly, the change of the battery surface temperature, which is equivalent to the area under the differential thermal voltammetry curve, over a specific voltage range is introduced as a direct feature of interest to reflect the actual battery capacity. Then, the temperature variation curve transformation is utilized to reduce the influence of the initial battery inconsistency. Lastly, the proposed method is validated based on eight groups of battery aging data from the Oxford battery degradation dataset. With the proposed method, the established reference correlation based on one battery can be applied to other batteries with a satisfying accuracy.

The physical modeling-based approaches tend to be over-simplistic and cannot forecast the complex dynamical phenomena, thus leading to non-negligible errors. It is not easy to measure some parameters precisely, and they are usually approximated roughly. However, this approximation reduces the modeling accuracy of the physical model, which is a common problem in complex systems research. It is well-known that neural networks are capable of encoding dynamic information. The vehicle can be accurately modeled by collecting data during its motion. However, purely data-driven approaches have low interpretability and cannot be used in commercial applications. In this work, we present a new hybrid modeling architecture. Based on the physical model, the deep learning method is introduced to expand the incomplete dynamics described by differential equations. Compared with the physical modeling-based and purely data-driven approaches, the proposed technique has lower modeling error and higher interpretability. We evaluate the performance of the hybrid model based on the collected data. The test results show that the proposed architecture successfully captures the vehicle dynamics and reduces the error caused by multi-step prediction compared to the data-driven models. The results also show that the proposed method has value for significant research and practical application.

Based on the existing theory of EHB braking system, a new dual-source redundant braking system (DSRB) is proposed in this paper. The proposed DSRB is improved on the classic ESP system structure with two sets of motor hydraulic pumps, four throttle valves and two balance valves used to replace the failed oil inlet and outlet valves added in it. Then, the requirements of redundancy, reliability of intelligent vehicle braking system can be met by the system. The wheel cylinder pressure of DSRB system is accurately regulated by PID control algorithm. Finally, the co-simulation based on AMEsim/Simulink were implemented to verify the accuracy and reliability of the braking efficiency of the DSRB. Results show that the designed DSRB has fault tolerance even in the case of partial failure, that is, inlet and outlet valve failure and complete failure, that is, inlet and outlet valve and hydraulic motor failure at the same time. And good braking efficiency, boosting speed and pressure regulation accuracy are still available.

High nonlinearities of switched reluctance motor (SRM) caused by its double salient structure limit its industrial application in electric vehicles (EVs). In this article, an algorithm called maximum-correntropy-criterion-based least-squares support vector regression (MCC-LSSVR) is applied to the nonlinear modeling of a segmented-rotor SRM (SSRM). First, the mathematical model of SSRM is established. Finite element analysis (FEA) is carried out to obtain the static flux linkage and torque. Then, the intelligent algorithm MCC-LSSVR using an adaptive weight to avoid the interference of outliers is introduced. It is verified and applied to SSRM modeling. The results show that MCC-LSSVR exhibits a better performance than other intelligent algorithms. Finally, simulation and experimental validation under various modes are given to verify the accuracy and effectiveness of the MCC-LSSVR model. It is shown that the simulation and experimental results are in good agreement.

Nowadays, the deep learning for object detection has become more popular and is widely adopted in many fields. This paper focuses on the research of LiDAR and camera sensor fusion technology for vehicle detection to ensure extremely high detection accuracy. The proposed network architecture takes full advantage of the deep information of both the LiDAR point cloud and RGB image in object detection. First, the LiDAR point cloud and RGB image are fed into the system. Then a high-resolution feature map is used to generate a reliable 3D object proposal for both the LiDAR point cloud and RGB image. Finally, 3D box regression is performed to predict the extent and orientation of vehicles in 3D space. Experiments on the challenging KITTI benchmark show that the proposed approach obtains ideal detection results and the detection time of each frame is about 0.12 s. This approach could establish a basis for further research in autonomous vehicles.

Advantages of planetary gear powertrain (PGT) for electric vehicles (EVs) are the high degree of efficiency, various reduction ratio, stress distribution by the planet gear and compaction in designing driving system. However there is noise in running at high rotational speed, so the transient torsional vibration suppression of the PGT for EVs become extremely essential and urgent. This study presents a 4 + N degree of freedom (DOF) nonlinear torsional system that essentially describes a PGT of EVs example, and further study on influence of novel TSB modification on transient vibration of planetary gear powertrain for an electric vehicle. In particular, the vibration of the PGT during the speed-up process, as excited by dynamic torque of motor generator (MG), time-varying mesh stiffness of front and back gear teeth, and also teeth backlashes, are investigated using a nonlinear torsional transient model. Then a full PGT model during the speed-up process is proposed and numerically solved to obtain the transient vibration acceleration. Dynamic response results of the PGT are also successfully compared and analyzed under different teeth backlashes. Finally, an improved genetic algorithm is applied to construct optimal relationship between the transient vibration and the TSB modification, and further the optimum three-dimensional TSB modification of sun-gear is finally obtained. The simulation and experiment results indicated that the proposed novel TSB modification method effectively suppressed the PGT transient vibration and vehicle jerk, at the same time, improved the ride comfort during the high-speed driving mode.

This paper presents a comprehensive dynamic efficiency model for the overall powertrain efficiency that considers the internal combustion engine and electric motor generators in depth as well as a planetary coupling transmission system of PHEVs example. In particular, the dynamic forces of planetary coupling transmission system with an effect on the dynamic transmission efficiency are taken into consideration. Then a dynamic efficiency optimization strategy is proposed to improve the fuel economy, and an improved dynamic efficiency optimization strategy, consisting in adding to the dynamic efficiency optimization strategy a penalty coefficient, is applied to reach the trade-off between energy consumption and fatigue life of planetary coupling transmission system. Eventually, the dynamic efficiency optimization strategy and improved dynamic efficiency optimization strategy are validated by hardware-in-the-loop experiments. The main contribution of this study is to explore a novel way to optimize the comprehensive dynamic efficiency of whole powertrain, and also improve ride comfort by avoiding planetary coupling transmission system working in the inefficient resonance region.

The license plate robust recognition algorithm in complex road scene has both theoretical and practical values. The existing license plate recognition algorithm can achieve better recognition results under ideal road scenes such as moderate light intensity, good shooting angle, and clear license plate target, but in complex road scenes such as fast speed, blurred aging of license plates, and low illumination such as rainy days, the effectiveness of the license plate recognition algorithm still needs to be improved. Based on the realistic requirements of license plate recognition algorithm and in-depth analysis of the principle of deep convolution network, we designed a deep convolution network for Chinese characters, letters, and numbers in the license plate to automatically learn the essential features of the image to make up for the limitation of the artificial feature recognition of the traditional license plate recognition algorithm. At the same time, according to the convolution kernel, downsampling, and nonlinear operation of the deep convolution network, the nonlinear abstraction ability of the license plate character feature is improved. The experimental results show that the proposed method can quickly and accurately identify the license plate character in complex road scenes. The recognition accuracy is better than the existing license plate recognition algorithm, which improves the accuracy of license plate recognition and achieves an ideal license plate recognition effect.

This paper investigates the fault-tolerant path following control problem of autonomous ground electric vehicles with in-wheel motors through hierarchical control strategy. The sliding mode observer with boundary layer is designed to estimate the vehicle state, and the time-delay estimation method is used to compute the actuator fault. Considering the actuator fault, the fault-tolerant path following control strategy is proposed, in which the upper layer controller is developed to achieve path following control and guarantee vehicle stability simultaneously by sliding mode control method, and the lower layer controller is presented to achieve the control efforts of upper layer controller by adaptive orientated tire force allocation method. The simulations are implemented in the CarSim-Simulink co-simulation platform, and the simulation results have verified the effectiveness of proposed fault-tolerant path following control method.