Dual-model fault diagnosis method based on dynamic weighing

Abstract

The invention discloses a dual-model fault diagnosis method based on dynamic weighing. The method comprises the steps that sensor vibration signals and fault recording texts collected by a motor driveend under the normal state and various fault states are selected; then,the sensor vibration signals and the fault recording texts are learned,then,a dynamic weighing combination algorithm is adoptedfor giving a weight to a model,sub-model SVM multi-classification voting results are combined,and a final classification result is obtained. Joint diagnosis for bearing fault data and bearing fault texts can be achieved. Non-balanced processing and valuable information extraction and classification are performed on equipment operation data,manual recording experience knowledges are effectively combined for text data mining,compared with a single diagnosis model,the method can remarkably improve the fault diagnosis precision,a better performance evaluation index is obtained,and the good theoretic and application value is obtained.

Description

technical field [0001] The invention relates to the technical field of fault diagnosis of bearing equipment, in particular to a dual-model fault diagnosis method based on dynamic weighting. Background technique [0002] In recent years, with the advancement of science and technology and the development of modern production, the technological revolution centered on manufacturing has become the key to the competition among major powers. All countries attach great importance to the development of the manufacturing industry: Germany proposed the "Industry 4.0" strategy, known as the fourth industrial revolution centered on intelligent manufacturing; the United States proposed the "National Strategic Plan for Advanced Manufacturing" to develop the manufacturing industry in various ways ; At the same time, the United Kingdom proposed "high-value manufacturing strategy", France proposed "new industrial France", Japan proposed "industrial revival plan" and so on. As a global manufa...

AI Technical Summary

Problems solved by technology

However, both of them still have the following deficiencies: data-driven fault diagnosis methods have problems such as inability to integrate empirical knowledge, data imbalance, and large-scale training set training convergence time is too long, making it impossible to obtain relatively high accuracy by relying on data-driven models alone. Good diagnostic effect; the text-driven fault diagnosis method has many problems such as unstable calculation results, large differences, sensitive to data, and prone to overfitting, which makes it difficult to achieve the ideal accuracy rate only by using the text-driven model

Images