Fault diagnosis method and device based on device working condition

Abstract

The invention relates to a fault diagnosis method and device based on device working condition. The method comprises the steps that feature extraction is conducted on diagnosis data of unknown samples of a device; whether the fault of the device can be recognized directly or not is judged according to features of the diagnosis data; if the fault is recognized directly, fault diagnosis recognition is conducted on the device directly; if not, working condition recognition and classification are conducted according to behavior parameters of the device; optical diagnosis algorithms corresponding to all the working conditions of the device are obtained through a Q-matrix by the adoption of the working condition classification result and the features of the diagnosis data, wherein the Q-matrix represents the corresponding relation between different working condition types and the optical diagnosis algorithms.

Description

technical field [0001] The invention relates to the field of equipment fault diagnosis, in particular to a fault diagnosis method and device based on equipment working conditions. Background technique [0002] Equipment fault diagnosis is a technology to understand and grasp the status of equipment, detect faults early, and predict the development trend of faults. With the development of production and science and technology, the working intensity of equipment is increasing, and the degree of production automation is getting higher and higher. At the same time, the equipment is more complex and the relationship between various parts is closer. A small failure may lead to catastrophic damage to the entire equipment and even the entire "equipment chain", which not only causes huge economic losses, but also endangers personal safety. Therefore, equipment fault diagnosis technology plays an increasingly important role. It can diagnose equipment faults in time to reduce maintena...

AI Technical Summary

Problems solved by technology

For example: support vector machine (SVM) has obvious advantages in small sample, nonlinear and high-dimensional pattern recognition, and can obtain the global optimal solution, but the training algorithm is slow, the algorithm is complex, and the calculation amount in the detection stage is large; fuzzy C-means aggregation Class (FCM) calculation speed is fast, no prior knowledge is required, but the anti-noise ability is not strong, and the global optimal solution may not be obtained; BP neural network has strong learning, parallel processing and good fault tolerance capabilities, and may obtain local optimal solutions , but requires a large number of training samples and a long training time

Images