针对飞行模拟器人感系统的高度非线性和易受干扰性,提出一种基于PIDNN(Proportional Integral Differential Neural Network)的控制方案.首先对飞行模拟器人感系统的模型进行分析研究,对它所受到的外界干扰作理论分析,整理出系统的数学模型,再利用PIDNN控制器优良的在线训练、学习和调整功能对该模型进行仿真控制.与传统PID(Propor.tional Integral Differential)控制器相比,PIDNN结构简单、自适应性强、收敛速度快、不会陷入局部极小.仿真结果表明:PIDNN控制系统响应速度快、稳态精度高、具有良好的动静态特性和鲁棒性,满足实时控制的要求.
A control scheme based on proportional integral differential neural network (PIDNN) was proposed to control the highly nonlinear and vulnerable simulative aircraft and sensing system. Firstly, the models of the human perceive system for the simulative aircraft was analyzed and studied, the system formula was ratiocinated consequently, and its disturbance from outside environment was analyzed theoretically. Then its superior function of PIDNN controller for its on-line training, learning and regulating ability were used to control the system in simulation environment. Comprising the all-ready used traditional proportional integral differential (PID) controllers, PIDNN has simpler structure, stronger adaptability and faster tracing ability without singularity. The simulation experiment result shows that the PIDNN has properties of quick response and nice steady accuracy, and has a well static and dynamic and robust character, so it can meet the need of real-time control.