Zhang Weigong

Neurofuzzy velocity tracking control with reinforcement learning

A control method of neurofuzzy controller with reinforcement learning is proposed to implement velocity tracking control of a vehicle manipulated by a robot driver. In neurofuzzy velocity tracking control, a neural network adjusts a fuzzy controller by fine-tuning the membership. The learning algorithm of the neural network is reinforcement learning, which is based on evaluating the system performance and giving credit for successful actions. After the designed controller is trained fully, the preliminary experiment is implemented to track the desired velocity. Experimental results show that the errors of velocity tracking meet the national standard. The maximum error usually appears at switch points of driving stages where displacement variety of acceleration pedal or brake pedal operated by the robot driver is larger. The error will reduce when displacement variety of the pedals becomes small except the near region of switch points. The robot driver embodies driving behavior of a skilled driver as operating the pedals, especially in the alternative switch process of the two pedals.

4WS vehicles lateral control via a modified exponent reaching law

Lateral control for Four-Wheel-Steering (4WS) vehicles on Automated Highway is investigated. Based on the previously studied look-down reference system with front and rear sensors, lateral dynamics model of 4WS vehicle is analyzed and model parameters uncertainties and external disturbance are considered. A sliding mode controller is designed based on a modified exponent reaching law, which integrates some states into the switch term to eliminate the chattering, and then the controller is applied to the lateral control for a 4WS vehicle. Simulations are conducted to evaluate the performance achieved by the proposed controller under different velocities and road adhesion factors, and effectiveness of the proposed approach is verified by the results.

Fuzzy-neural-network-based speed control method and experiment verification for electromagnetic direct drive robot driver

Vehicle test has a great significance for the development of new vehicle products. It is necessary for a new type of vehicle stereotypes to conduct a lot of vehicle test. Some vehicle test, such as emission durability test, vehicle performance test, vehicle noise test, high and low temperature environment test, vehicle road test, vehicle bench test, is more suitable for the operation by robot. Robot driver is an intelligent robot that can realize automatic driving under harsh environment in vehicle test instead of a human driver without any modification. Because of the vehicle is not required to be modified, and the vehicle robot driver can be directly installed in the different vehicle cab. The drive way of the vehicle robot driver includes the hydraulic drive, the pneumatic drive and the servo electric drive. The hydraulic drive is steady, but it needs an oil cylinder. It is not easy for the pneumatic drive to accurate positioning and the real-time property. As a driving device of the robot driver, the servo electric drive needs a mechanism of rotary motion into linear motion. Electromagnetic linear motor can solve the shortcomings of three other drive styles. It can improve the transmission efficiency and transmission accuracy, and make the transmission mechanism simple. A control approach of speed in an electromagnetic direct drive robot driver based on fuzzy neural network is proposed in this paper, in order to realize the accurate speed tracking of different driving test cycle conditions. The electromagnetic direct drive robot driver adopts an electromagnetic linear actuator as the driving device in this paper. The throttle mechanical leg, the brake mechanical leg, the clutch mechanical leg and the shift manipulator are directly driven through the electromagnetic linear actuator. The control system structure and the coordinated motion control model of the electromagnetic direct drive robot driver are given. On the basis of this, the speed control model based on fuzzy neural network of the electromagnetic direct drive robot driver is designed. The shift manipulator displacement, the throttle mechanical leg displacement, the clutch mechanical leg displacement and the brake mechanical leg are the input variables of the fuzzy neural network model, and the vehicle speed of the test vehicle is the output variable of the fuzzy neural network model. The number of the input variable membership functions is three, and the type of the input variable membership functions is gbellmf. The fuzzy neural network training algorithm adapts the hybrid learning algorithm combing with back propagation algorithm and least square method. The proposed control method of the electromagnetic direct drive robot driver is experimentally proved and compared with other control methods and with human driver performances. Actual vehicle test results and error comparison analysis show that the vehicle speed tracking accuracy of robot driver using the proposed approach is higher than that of robot driver using PID control method and human driver. Besides, the proposed method has good adaptability under all kinds of driving test cycle, which can ensure the accuracy and effectiveness of vehicle test.

Comprehensive warning decision-making method of the operational bus based on typical dangerous working conditions

Frequent occurrence of traffic accidents, especially large bus accidents with many casualties has become a focus of scientific study. In view of this, a comprehensive warning decision-making method is proposed, based on typical dangerous working conditions of the operational bus. Through the study of active safety technology, the data of typical dangerous working conditions of large buses is obtained. After the collection and procession of relevant driving parameters from vehicle sensors, the comprehensive early warning decision-making matrix is built. Thus, the early warning function is achieved by predicting whether the bus is in dangerous condition. The effect and feasibility of the method have been validated by tests and simulations. The results demonstrate that typical dangerous working conditions can be recognized accurately and the false alarm rate is less than 10% through the proposed method.

Research on Key Technologies of Vehicle Traffic Accidents Rescue

The new category of vehicle traffic accidents based on vehicle recovery is proposed in this paper to immediately dispose the accidents. Then, the vehicle recovery equipment and the integrated vehicle rescue equipment are designed as the key technologies of vehicle traffic accident rescue. The principle of vehicle recovery equipment and the main feature of the integrated vehicle rescue equipment are described. In order to utilize these equipments better, the operation standard and the training system are introduced.

Dynamic Comprehensive Evaluation of Property Insurance Companies' Business Performance

Under the framework of a comprehensive evaluation of business performance, the paper builds comprehensive evaluation index system from aspects of profitability, solvency, operating capability and growth capability, and determines the weight of the evaluation indicators by using ANP. Then it gives a dynamic comprehensive assessment method for property insurance companies’ business performance based on gain level in spiriting and applies it. The empirical study shows that the method is effective, and can objectively assess the comprehensive business performance. It provides a basis for comparison of property insurance companies.

Generation and Modeling of Asymmetric Hysteresis Damping Characteristics for a Symmetric Magnetorheological Damper

Asymmetric hysteresis damping characteristics are essential for vehicle suspension design with symmetric magnetorheological (MR) dampers. For this purpose, an asymmetric damping force generation (ADFG) algorithm is proposed by limiting the driving current to a higher value corresponding to extension and a lower value for compression, and the subsequent transient in damping force response is suppressed by a smooth modulator based on the arctan function. To describe the asymmetric hysteresis damping characteristics, an asymmetric hysteresis force-velocity (f-v) model is derived upon integrating the velocity and force offsets into the proposed symmetric synthesis, also, the model parameters are identified with least square algorithm and experimental data under various operation conditions. Excellent correlations between the model and experimental results verify the effectiveness of the algorithm and model.