Hydraulic system fault diagnosis method and system based on multi-task support vector machine

Abstract

The invention provides a hydraulic system fault diagnosis method and system based on a multi-task support vector machine, and the method comprises the steps: firstly collecting various types of signals of a hydraulic system in a fault state, segmenting the signals into segments with a certain length, then respectively screening out signal segments which are greatly related to each type of faults in a stable state, using a principal component analysis method, carrying out dimension reduction processing on the data with the cumulative variance contribution rate as an index, finally, building a multi-task support vector machine provided by the invention as a diagnosis model, and carrying out fault diagnosis by using the trained model. According to the method, under the conditions that multiple types of faults coexist and the fault degrees are different, multi-task classification is adopted instead of converting the composite faults into new types, the problems that the number of labels explodes and each type of samples is too few are avoided, meanwhile, signals with high correlation are screened out, the number of features is reduced, and the composite faults can be efficiently and accurately recognized.

Description

technical field [0001] The invention relates to the field of hydraulic system fault diagnosis, in particular to a hydraulic system fault diagnosis method and system based on a multi-task support vector machine, especially a composite fault diagnosis method for a hydraulic system based on a multi-task support vector machine. Background technique [0002] Hydraulic systems are widely used in aerospace, robotics, construction machinery and other fields due to their advantages of high power density and low vibration and shock. In a complex hydraulic system, fault diagnosis plays an important role. Timely determination of the fault type and fault degree can bring great convenience to the maintenance of the hydraulic system, save a lot of time and cost, and improve the reliability and safety of the hydraulic system sex. There are three types of commonly used fault diagnosis methods: model-based methods, knowledge-based methods and data-driven methods. The model-based method requ...

AI Technical Summary

Problems solved by technology

However, when the types of faults increase, and each type of fault has multiple fault levels, the number of labels will increase sharply, which will bring difficulties to classification

Images