基于小波网络的水下机器人执行器故障诊断

Actuator Fault Diagnosis of Autonomous Underwater Vehicle Based on Wavelet Neural Network

针对水下机器人系统的不确定性使得对其进行建模比较困难的特点,提出采用一种改进的小波网络进行水下机器人运动建模。该网络通过学习,调节小波函数的伸缩和平移以及网络连接权,既能逼近函数的整体轮廓,亦能捕捉函数变化细节,使得函数的逼近效果较好。通过比较模型的输出(运动状态估计值)与实际测量值来产生残差,分析残差提取故障判断准则,从而进行执行器故障诊断。仿真试验验证了该方法的有效性。

Aiming at the character that the uncertainties of the complex system of Autonomous Underwater Vehicle （AUV） bring to model the system difficult, an improved wavelet neural network （WNN） was proposed to construct the motion model of AUV. By studying to adjust the scale factors and shift factors of wavelet and weights of WNN, the WNN has the ability not only to approach the whole figure of a function but also to catch detail changes of the function, which makes the approaching effect preferabe. Residuals were achieved by comparing the output of neural network with the real state value. Fault detection rules were distilled from the residuals to execute actuator fault diagnosis. Simulate experiment validates the validity of the method presented.