基于模糊神经网络的执行器故障诊断

Actuator fault diagnosis based on fuzzy neural network

针对神经网络在故障诊断中的局限性,提出了一种将模糊理论与BP神经网络结合的故障诊断方法,使其应用到执行器故障诊断中。通过和BP神经网络学习算法对执行器故障诊断的结果比较来证明模糊神经网络算法的优越性。首先介绍执行器常见故障;其次对故障征兆进行模糊化预处理,获得了神经网络训练样本,最后应用Matlab软件进行了系统仿真。仿真结果表明:该方法收敛速度快、诊断精度高、自适应性强,能够有效地诊断执行器故障。

To explore the deficiency of the traditional neural network in fault diagnosis, a combination of fuzzy theory and neural network based on BP algorithm was proposed, and used in the fault diagnosis of actuator. Through the comparison of the algorithm of fuzzy neural network and BP neural network learning algorithm of actuator fault diagnosis results, prove the superiority of the fuzzy neural network algorithm.Through the establishment of the common failure knowledge base, fuzzy theory was used to process the fault information and to obtain the neural network training samples. With the simulation by Mat_lab software, The result shows that the method can effectively overcome the deficiency of BP algorithm, and provides efficient way for the fault diagnosis of actuator.