Autonomous underwater vehicle propeller fault diagnosis method based on improved isometric feature mapping algorithm ISOMAP

Abstract

The invention belongs to the technical field of fault diagnosis of autonomous underwater vehicles, and specifically relates to an autonomous underwater vehicle propeller fault diagnosis method based on an improved isometric feature mapping algorithm ISOMAP. The method includes steps: performing fusion on a state quantity and a control quantity in an operation process of an AUV based on an improvedD-S evidence theory data fusion algorithm, performing feature extraction on fusion data based on the isometric feature mapping algorithm, performing fault detection on extracted feature points basedon an artificial immune algorithm, and performing fault degree identification on detected fault points based on an improved support vector domain algorithm. According to the method, the absence of faults of an AUV propeller can be determined, the fault diagnosis of the AUV propeller can be comprehensively realized from fault feature extraction, fault detection, and fault degree identification, thesevere degree of the faults of the AUV propeller is determined, the precision of fault diagnosis is improved, and the method is especially applicable to state monitoring of the AUV propeller.

Description

technical field [0001] The invention relates to the technical field of underwater robot fault diagnosis, in particular to an underwater robot propeller fault diagnosis method based on an improved isometric feature mapping algorithm ISOMAP. Background technique [0002] Autonomous underwater robot AUV works unmanned and untethered in a complex marine environment, and safety is one of the important research contents in the process of AUV research and practical application. The thruster is one of the main fault sources of AUV, and the research on the condition monitoring technology of AUV thruster has important research significance and practical value for improving the safety of AUV. However, the AUV thruster fault diagnosis algorithm has problems such as incomplete feature extraction, weak regularity between detection results, and large identification errors in fault feature extraction, detection, and identification. [0003] Under the same thruster fault, the distribution a...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problems of using the traditional isometric feature mapping algorithm ISOMAP to extract fault features of AUVs, the feature extraction results are unstable, the feature extraction ability for weak faults is poor, and it is impossible to detect faults and identify fault degrees. The present invention proposes a D-S The AUV thruster fault diagnosis method combines evidence theory with ISOMAP algorithm, artificial immunity, and improved support vector domain SVDD. Firstly, a new signal processing method is used to reduce the variation range between data, while keeping the original signal variation as much as possible. The trend remains unchanged, and then use the D-S evidence theory for data fusion to obtain the one-dimensional equivalent signal under the fault level, and then use ISOMAP to extract the features of the equivalent signal; after the feature extraction is completed, based on the obtained feature points, use manual The immune algorithm detects the thruster fault, and completes the unknown fault identification of the AUV thruster based on the improved support vector domain. The above-mentioned process constitutes the whole process of the fault diagnosis of the AUV thruster involved in the present invention

Images