Search Results

In this research, the interior noise of a passenger car was measured, and the sound quality metrics including sound pressure level, loudness, sharpness, and roughness were calculated. An artificial neural network was designed to successfully apply on automotive interior noise as well as numerous different fields of technology which aim to overcome difficulties of experimentations and save cost, time and workforce. Sound pressure level, loudness, sharpness, and roughness were estimated by using the artificial neural network designed by using the experiment values. The predicted values and experiment results are compared. The comparison results show that the realized artificial intelligence model is an appropriate model to estimate the sound quality of the automotive interior noise. The reliability value is calculated as 0.9995 by using statistical analysis.

The current global chassis control (GCC) frequently makes use of decoupled control methods which depend on driving condition partition and simple rule-based vertical force distribution, and are insufficient to obtain optimal vehicle dynamics performance. Therefore, a novel hierarchical global chassis control system for a distributed electric vehicle (DEV), which is equipped with four wheel driving/steering and active suspension systems, is developed in this paper. The control system consists of three layers: in the upper layer, the desired forces/moments based on vehicular driving demands are determined; in the middle layer, a coordinated control method of longitudinal/lateral/vertical tire forces are proposed; in the lower layer, the driving/steering/suspension control is conducted to realize each distributed tire force.

This paper proposes a new method of predicting the sound absorption performance of polymer wool using artificial neural networks (ANN) model. Some important parameters of the proposed model have been adjusted to best fit the non-linear relationship between the input data and output data. What's more, the commonly used multiple non-linear regression model is built to compare with ANN model in this study. Measurements of the sound absorption coefficient of polymer wool based on transfer function method are also performed to determine the sound absorption performance according to GB/T18696. 2-2002 and ISO10534- 2: 1998 (E) standards. It is founded that predictions of the new model are in good agreement with the experiment results.

A twist beam rear suspension system is modeled, analyzed and optimized in this paper. An ADAMS model is established based on the REC (Rigid-Elastic Coupling) Theory, which is verified by FEM (Finite Element Method) approach, the effects of the geometric parameters on the twist beam suspension performance are investigated. In order to increase the calculation efficiency and improve the simulation accuracy, a neural network model and NSGA II (Non-dominated Sorting Genetic Algorithm II) are adopted to conduct a multi-objective optimization on a twist beam rear suspension system.

In the face of energy and environmental problems, how to improve the economy of fuel cell vehicles (FCV) effectively and develop intelligent algorithms with higher hydrogen-saving potential are the focus and difficulties of current research. Based on the Toyota Mirai FCV, this paper focuses on the short-term speed prediction algorithm based on the back propagation neural network (BP-NN) and carries out the research on the short-term speed prediction algorithm based on BP-NN. The definition of NN and the basic structure of the neural model are introduced briefly, and the training process of BP-NN is expounded in detail through formula derivation. On this basis, the speed prediction model based on BP-NN is proposed. After that, the parameters of the vehicle speed prediction model, the characteristic parameters of the working condition, and the input and output neurons are selected to determine the topology of the vehicle speed prediction model.

As a novel assist actuator of brake system, the electromechanical brake (EMB) booster has played a significant role in the battery electric vehicles and automatic driving vehicles. It has advantages of independent to vacuum source, active braking, and tuning pedal feeling compared with conventional vacuum brake booster. In this article, a novel EMB booster system is proposed, which is consisted of a permanent magnet synchronous motor (PMSM), a two-stage reduction by gears and ball screw, a servo body, and a reaction disk. Together with the hydraulic control unit, it has two working modes: active braking for automatic drive and passive braking for driver intervention. The structure and work principle of the electric brake booster system is first introduced. The precise control from pedal force to hydraulic pressure is the key for such a power-assisted brake actuator. We translate the control problem of force feedback control to position tracking control.

To reduce the interference and conflict of human-machine cooperative control, lighten the operation workload of drivers, and improve the friendliness and acceptability of intelligent vehicles, a personalized human-machine cooperative lane-change trajectory tracking control method was proposed. First, a lane-changing driving data acquisition test was carried out to collect different driving behaviors of different drivers and form the data pool for the machine learning method. Two typical driving behaviors from an aggressive driver and a moderate driver are selected to be studied. Then, a control structure combined by feedforward and feedback control based on Long Short Term Memory (LSTM) and model-based optimum control was introduced. LSTM is a machine learning method that has the ability of memory. It is used to capture the lane-changing behaviors of each driver to achieve personalization. For each driver, a specific personalized controller is trained using his driving data.

With more and more countries proposing timetables for stopping selling of fuel vehicles, China has also issued a “dual-slope” policy. As electric vehicles are the most promising new energy vehicle, which is worth researching. The integration and control of the motor and gearbox have gradually become a hot research topic due to low cost with better performance. This paper takes an electric vehicle equipped with permanent magnet synchronous motor and two-gear automatic transmission without synchronizer and clutch as the research object.

The motor errors of the four-wheel independent driving electric vehicles was studied, and classified as steady errors and dynamic errors. In the paper, the forward compensation control and the PID control strategy were respectively applied to compensate for the errors. The electric vehicles straight-line running stability caused by the motor errors was discussed, the PID control method based on BP neural net work was presented to co-ordinate torque of the wheels. The result of the simulation on the 7 degrees of freedom vehicle model showed that control method improved the straight-line running ability of the vehicle.

A life-cycle assessment (LCA) has been developed to help compare the economic, environmental and energy (EEE) impacts of converting coal to automotive fuels in China. This model was used to evaluate the total economic cost to the customer, the effect on the local and global environments, and the energy efficiencies for each fuel option. It provides a total accounting for each step in the life cycle process including the mining and transportation of coal, the conversion of coal to fuel, fuel distribution, all materials and manufacturing processes used to produce a vehicle, and vehicle operation over the life of the vehicle. The seven fuel scenarios evaluated in this study include methanol from coal, byproduct methanol from coal, methanol from methane, methanol from coke oven gas, gasoline from coal, electricity from coal, and petroleum to gasoline and diesel. The LCA results for all fuels were compared to gasoline as a baseline case.

Vehicle lane keeping system is becoming a new research focus of drive assistant system except adaptive cruise control system. As we all known, vehicle lateral dynamics show strong nonlinear and time-varying with the variety of longitudinal velocity, especially tire’s mechanics characteristic will change from linear characteristic under low speed to strong nonlinear under high speed. For this reason, the traditional PID controller and even self-tuning PID controller, which need to know a precise vehicle lateral dynamics model to adjust the control parameter, are too difficult to get enough accuracy and the ideal control quality. Based on neural network’s ability of self-learning, adaptive and approximate to any nonlinear function, an adaptive PID control algorithm with BP neural network self-tuning online was proposed for vehicle lane keeping.

Coordinated EGR-VNT control based on the intake air mass observer is presented in this paper to deal with the transient AFR control of turbocharged diesel engine. The air mass model embedded in the observer is a Takagi-Sugeno fuzzy neural network trained with transient simulation results. It can predict the charged fresh air mass entering the cylinder. In a high load region, when EGR is not effective, the coordinated EGR-VNT control will also bring benefits to the transient air-fuel-ratio control. The simulation results of TDI engine model verify that the transient control strategy will allow a better control of the intake air mass, and thus improve air-fuel-ratio control and reduce NOx emission in transients.

Adaptive cruise control system with lane change assistance (LCACC) is a novel advanced driver assistance system (ADAS), which enables dual-target tracking, safe lane change, and longitudinal ride comfort. To design the personalized LCACC system, one of the most important prerequisites is to identify the driver’s individualities. This paper presents a real-time driver behavior characteristics identification strategy for LCACC system. Firstly, a driver behavior data acquisition system was established based on the driver-in-the-loop simulator, and the behavior data of different types of drivers were collected under the typical test condition. Then, the driver behavior characteristics factor Ks we proposed, which combined the longitudinal and lateral control behaviors, was used to identify the driver behavior characteristics. And an individual safe inter-vehicle distances field (ISIDF) was established according to the identification results.

A new lateral stability control method, which is based on vehicle sideslip angle and tire cornering stiffness estimation, is proposed to improve the lateral stability of the four-in-wheel-motor-driven electric vehicle (FIWMD-EV) in this paper. Through the lateral tire force information, vehicle sideslip angle can be estimated by the extended kalman filter (EKF). Using the estimated vehicle sideslip angle, tire cornering stiffness can be also estimated by forgetting factor recursive least squares (FFRLS). Furthermore, combining with the vehicle dynamics model, an adaptive control target model is proposed with the information on vehicle sideslip angle and tire cornering stiffness. The new lateral stability control system uses the direct yaw moment control (DYC) based on dynamic sliding mode is proposed. The performance and effectiveness of the proposed vehicle state estimation and lateral stability control system are verified by CarSim and Simulink cosimulation.

The primary noise sources of electric vehicles differ from that of traditional vehicles due to the fundamental differences in their powertrain architecture. In this work, some exterior noise test methods for electric vehicles are briefly introduced first, which include a pass-by noise measurement method during acceleration on the proving ground as well as a similar measurement in a semi-anechoic room. The obtained results based on those two methods from a production electric vehicle are compared and analyzed. Then the mechanism of the source, path, and contribution is illustrated, and a model of path-source-contribution for electric vehicles is established. The model validation is subsequently carried out by correlating the calculated outcomes with the measured results under real operating conditions. Finally, by using the model, contribution analyses are carried out to identify the primary exterior noise sources.

Compared with conventional vehicles, electric vehicles (EVs) offer the benefits of replacing petroleum consumption and reducing air pollutions. However, there have been controversies over greenhouse gas (GHG) emissions of EVs from the life-cycle perspective in China’s coal-dominated power generation context. Besides, it is in doubt whether the cost-effectiveness of EVs in China exceeds other fuel-efficient vehicles considering the high prices. In this study, we compared the life-cycle GHG emissions of existing vehicle models in the market. Afterwards, a cost model is established to compare the total costs of vehicles. Finally, the cost-effectiveness of different vehicle types are compared. It is concluded that the GHG emission intensity of EVs is lower than reference and hybrid vehicles currently and is expected to decrease with the improvement of the power grid.

Since road electric vehicles typically require a significantly variable and random load power demand in response to traffic conditions, such as frequent sequences of acceleration and deceleration and uphill followed by downhill runs. In this context, the energy management system of electric vehicle must ensure an effective power distribution between battery and supercapacitor to satisfy load demand. In this paper, the power management control strategy of hybrid energy storage system is developed by introducing terrain information to optimize system efficiency and battery lifetime. In this presented research, we aim at developing a power management control strategy considering the influence of the terrain information on system efficiency and battery lifetime.

Direct yaw moment control can maintain the vehicle stability in critical situation. For four-wheel independently driven (4WD) electric vehicle with in-wheel motors (IWMs), direct yaw moment control (DYC) can be easily achieved. A fairly accurate calculation of the required yaw moment can improve vehicle stability. A novel sliding mode control (SMC) technique is employed for the motion control so as to track the desired vehicle motion, which is it for different working circumstances compared to the well-used traditional DYC. Through the weighted least square algorithm, the lower controller is used to determine the torque properly allocated to each wheel according to the desired yaw moment. Several actuator constraints are considered in the control strategy. In addition, a nonlinear tire model is utilized to improve the accuracy of tire lateral force estimation. Then, simulations are carried out and the values of vehicle states are compared.

As a typical parameter of the road-vehicle interface, the road friction potential acts an important factor that governs the vehicle motion states under certain maneuvering input, which makes the prior knowledge of maximum road friction capacity crucial to the vehicle stability control systems. Since the direct measure of the road friction potential is expensive for vehicle active safety system, the evaluation of this variable by cost effective method is becoming a hot issue all these years. A ‘wheel slip based’ maximum road friction coefficient estimation method based on a modified Dugoff tire model for distributed drive electric vehicles is proposed in this paper. It aims to evaluate the road friction potential with vehicle and wheel dynamics analyzing by using standard sensors equipped on production vehicle, and fully take the advantage of distributed EV that the wheel drive torque and rolling speed can be obtained accurately.

Intelligent driving, aimed for collision avoidance and self-navigation, is mainly based on environmental sensing via radar, lidar and/or camera. While each of the sensors has its own unique pros and cons, camera is especially good at object detection, recognition and tracking. However, unpredictable environmental illumination can potentially cause misdetection or false detection. To investigate the influence of illumination conditions on detection algorithms, we reproduced various illumination intensities in a photo-realistic virtual world, which leverages recent progress in computer graphics, and verified vehicle detection effect there. In the virtual world, the environmental illumination is controlled precisely from low to high to simulate different illumination conditions in the driving scenarios (with relative luminous intensity from 0.01 to 400). Sedan cars with different colors are modelled in the virtual world and used for detection task.