A fault diagnosis system and method for a multi-vibration source system

Abstract

The invention discloses a fault diagnosis system and method of a multi-vibration source system, and relates to the technical field of mechanical fault diagnosis. Aiming at the composite vibration signal in the multi-vibration source system, the invention adopts the blind source separation method to realize the separation of the composite vibration signal, obtains the vibration signal of the independent vibration source, and generates a separated signal data set in a normal state. Use the separated signal data set to train the adversarial generation network, identify the vibration signal of the independent vibration source by the discriminant network, and judge whether the independent vibration source is in an abnormal state, so as to realize the location of the fault source without the sample and achieve the fault detection. Positioning and abnormal early warning functions. The method has strong applicability and can make full use of the normal and steady state working vibration signals of different independent vibration sources to train the model in the absence of fault samples, and perform timely positioning and abnormal early warning when faults occur.

Description

technical field [0001] The invention relates to an electric locomotive bogie frame assembling equipment, in particular to a fault diagnosis system and method for a multi-vibration source system. Background technique [0002] High-speed trains are an important tool for improving transportation capacity and belt industry development in my country. The vibration signal monitoring and fault diagnosis of the rotating parts of the bogie have important engineering value to ensure safety and sustainability. The bogie has a complex structure, a large number of vibration sources, and dense space, so the number of sensors is limited, and it is difficult to obtain comprehensive monitoring information with traditional monitoring strategies for single components. At the same time, due to the huge number of trains and conservative maintenance strategies, the monitoring data has the characteristics of huge amount of normal operation data and scarce fault operation data, which makes the arti...

AI Technical Summary

Problems solved by technology

However, in the diagnosis of bogie rotating parts, a large amount of data has a single mode, and the fault samples are scarce and the modes are incomplete, which brings great challenges to the training of the model.

At present, for the problem of fault diagnosis with few samples, solutions such as supplementary generation of samples, model simplification, and meta-learning have been proposed, but there are still problems such as weak generalization ability and low diagnostic accuracy.

Images