基于神经网络的水下机器人推进器故障诊断

Research on Thruster Fault Diagnosis of Underwater Vehicles Based on NN

为提高水下机器人系统的总体可靠性,开展了推进器故障诊断研究。在三层BP神经网络的基础上,提出了一种改进的递归神经网络并推导了网络的训练算法。利用直航、转艏等试验对网络进行训练,将训练好的网络用于水下机器人运动建模,对比模型的输出与实际传感器测量值来获取残差,通过分析残差特性来提取故障诊断判据,进而进行推进器故障诊断。将提出的方法应用到仿真试验和海上试验中,得出了相应的试验结果。通过对试验结果的分析研究,验证了方法的有效性与可行性,同时也表明该方法在工程应用方面具有一定的参考意义。

Study of thruster fault diagnosis of underwater vehicles （UVs） is undertaken to improve its whole system reliability. Based on the BP neural network, an improved recurrent neural network （RNN） is presented and the network training algorithm is deduced. The RNN is trained by voyage head and yaw turning experiments, and the well trained network is applied to the model for UVs. Compared the model＇s outputs with the sensors＇ outputs, the residuals can be obtained. Fault detection rules are distilled from the residuals to execute thruster fault diagnosis. The method is applied to the simulation and trials experiments, and plenty of results are got. Based on the analysis of experiments＇ results, the validity and feasibility of the methods can be verified and some reference in engineering application can be demonstrated by the results.