Changwei Zheng

Improved LMBP algorithm in the analysis and application of simulation data

Based on the analysis of features and reasoning course of LMBP(Levenberg-Marquardt) algorithm, we propose the way of variable learning rate to improve the convergence speed. Using some literature data of reference standard database and program MATLAB simulation experiment, it shows that this improved the feasibility and effectiveness LMBP algorithm. Improving LMBP algorithm offers important reference value for combat simulation equipment for the analysis of the data characteristics and summary conclusions.

Research of Driver's Visual Perception Modeling and Simulation

Driving behavior research is the hot spot in the field of transportation nowadays owning to the stern traffic safety. The visual perception model based on bounded rationality has incorporated the attention distribution and concentration, driving fatigue, driving experience and visual information retrieve which provides a vivid simulation of real drivers visual perception procedure and it lays the foundation for the study of drivers decision and manipulation behavior.

The research of presentation decomposition and allocation of task in MAS based on And/Or graph

Multi-agent systems have been proposed as a promising technology for addressing many problems in distributed information management, Internet and so on. Decomposing and allocating asks in MAS has proved to be a NP-hard question. The approach based on And/Or graph solving this question has been proposed and verified by simulation which offers a new way for tasks planning in MAS.

Research and application of virtual instrument for tank integrated simulator based-on LabWindows

Tank situation display system is a basic component of the tank integrated simulator. This paper describes the design process of virtual instrument for tank integrated simulator based on LabWindows. The hardware architecture and diagrams of system are introduced first. The software module architecture and design development process are given later. The research of several key issues is focused on, such as signal collection, communication in TCP model, control of operation load system as well as parameters tests in automatic condition. And finally practical interface images of tank virtual instruments which give a powerful technical support for detection and maintenance are achieved so that met the demands for training purpose.

Research of Driving Manipulation Modeling and Simulation

In the modeling and simulation of driving behavior, the driving manipulation converts the decision to the specific actions and outputs to the physical model of vehicle so that the manipulation is the important content of driving research. Divided the driving manipulation modeling into resources matching and task planning. It matches the operating resources by comparing the resource matrix. Introduced the description and solving algorithm of hierarchical task network. It takes startup vehicle in gear two as example to explain the application of hierarchical task network which provides the foundation for improving the fidelity and reliability of driving behavior modeling and simulation.

Research of Aiming Error and Its Application in CGF Tank Firing Model

Based on the effecting factors of aiming error on firing precision in the gunner shooting procedure, it builds the aiming error model and shooting reaction delay model which compose the CGF tank aiming model with high precision. It makes the aiming action more realistic in CGF tank model which improves the fidelity and validity of system and it is conducive to enhance the efficiency of gunner’s shooting and tactical training system.

Research of differenced driving behavior modeling and simulation

Nowadays differenced driving behavior has realized by adding noise dada in the driver model which can not embody the essential difference between drivers. This paper analyzes the reasons of differenced driving behavior, uses the exploratory method to analyze the effects of drivers personality, intelligence and physiology on driving behavior and cooperates the affecting parameters in the driver model. It validates the improvement of enhanced model by simulation which provides the foundation for driving behavior modeling and simulation with high fidelity.