Transmission system fault diagnosis method based on multi-information fusion

Abstract

The invention relates to a transmission system fault diagnosis method based on multi-information fusion. The method comprises the following steps: acquiring multiple groups of original signals of a transmission system in normal and fault states; preprocessing the acquired signals; respectively extracting first feature vectors, and performing normalization processing and feature fusion to serve astraining samples; constructing a support vector machine model, and training by using the training sample; collecting all signals of the transmission system in real time to be preprocessed, extractingand normalizing a second feature vector, conducting diagnosis through the trained support vector machine diagnosis model after feature fusion, and outputting a fault detection result. Multiple signalsare collected for feature extraction and feature fusion, the problem of low accuracy caused by diagnosis of single features can be effectively solved, the obtained diagnosis result better conforms tothe real running state of a motor, and the fault diagnosis rate of the transmission system is effectively increased.

Description

technical field [0001] The invention relates to the technical field of fault diagnosis, in particular to a transmission system fault diagnosis method based on multi-information fusion. Background technique [0002] The fault diagnosis technology of the transmission system is based on mathematical modeling, collects data through data acquisition and data mining, and then uses signal processing technology to extract fault features, and then performs fault diagnosis through the characteristics and development trends of the data. [0003] The existing technical solutions mainly include expert system and fuzzy theory, etc.; the expert system is a program system with a lot of expertise and experience. First, it needs to collect a lot of knowledge and data in advance to form its own independent knowledge base system. The logical relationship established by the database system is used for reasoning and judgment, and finally the logical relationship is programmed to simulate the deci...

AI Technical Summary

Problems solved by technology

[0004] The current fault diagnosis method only combines a certain fault feature set or a certain pattern recognition algorithm, and can only find the optimal fault classification method from a single perspective, which is bound to be one-sided and thus affects the reliability of transmission system fault diagnosis. The accuracy of fault diagnosis is low

[0005] In fault diagnosis, due to the increasing size and complexity of transmission structures such as fans, pumps, compressors, and gear plus motors, single or single-domain features have a certain degree of contingency, making it impossible to include all fault features of the transmission system , so there are often cases of missed detection or misjudgment in fault diagnosis

Images