无刷直流电机的模糊神经网络控制设计

在无刷直流电机(BLDCM)的控制上,传统PID等控制方法存在或多或少的不足.在模糊PID控制的基础上提出了一种模糊神经网络PI控制器的设计方法.该方法结合了模糊逻辑与神经网络,使得模糊控制器模拟了人的控制功能,不仅对环境变化有较强的适应能力,还拥有自学习能力.相比模糊PID控制,其具有计算量小、稳定性强等特点.对BLDCM进行建模与分析;在BLDCM数学模型的基础上,分别设计模糊PID控制器和模糊神经网络PI控制器;对设计的控制器进行仿真验证并分析.实验结果表明,模糊神经网络PI控制具有跟踪性能好、超调小、响应快、脉动小等优点,其动静态特性均优于模糊PID控制.

Design of BLDCM Control System Based on Fuzzy Neural Networks

In the control of brushless DC motor (BLDCM),there are more or less deficiencies in traditional PID control methods.Based on the fuzzy PID control,a design method of fuzzy neural network PI controller is proposed.This method combines fuzzy logic and neural networks,which makes the fuzzy controller simulate the human control function,not only has the strong adaptability to the environment change,but also has the self-learning ability.Compared with fuzzy PID control,it has the characteristics of small computation and strong stability.BLDCM is modeled and analyzed,on the basis of BLDCM mathematical model,fuzzy PID controller and fuzzy neural network PI controller are designed respectively,then the designed controller is simulated and verified.The experimental results show that the fuzzy neural network PI control has the advantages of good tracking performance,small overshoot,fast response and small pulsation,and its dynamic and static characteristics are superior to fuzzy PID control.