Fault Feature Enhancement for AUV With Weak Thruster Fault Based on Improved Stochastic Resonance System

Fault features are weak and their strength is close to external disturbances for weak thruster fault in an AUV. There are great difficulties to distinguish fault features and external disturbances. This paper investigates a method to enhance fault features and suppress external disturbances. The typical stochastic resonance based fault feature enhancement method has not achieved satisfactory performance for weak thruster fault in an AUV, artificial fish swarm algorithm is applied to optimize the parameters of the stochastic resonance. In this process, a new optimization evaluation index is developed, and the structural parameters of the stochastic resonance system are optimized simultaneously with two evaluation indexes. Experiment data from Beaver-II AUV are used to demonstrate the performance of the fault feature enhancement method developed in this paper.