Construction method of fuzzy automaton based on machine fault diagnosis

Abstract

The invention provides a construction method of a fuzzy automaton based on machine fault diagnosis, which comprises the following steps of establishing an internal network model of the fuzzy automaton, including an input module, a preprocessing model, a feature extraction model, a fuzzy matching model and an output module which are sequentially connected; distributing the fault information data todifferent neurons in a preprocessing model, and obtaining the output of each neuron by using a multi-input fuzzy inference method; distributing the output signals of the preprocessing model to different neurons in the feature extraction model, and performing fault feature extraction by using a function transformation method; distributing the fault feature signals outputted by the feature extraction model to different neurons in the fuzzy matching model, and calculating a similarity vector of a diagnosed fault fuzzy number vector and a known fault class by using a similarity calculation method; and enabling the fuzzy matching model to diagnose a fault through a vector norm method. The method is wide in application range, a fault sample is tested, and the correct diagnosis rate reaches 92.69%.

Description

technical field [0001] The invention relates to the technical field of machine fault diagnosis and knowledge mining, in particular to a method for constructing a fuzzy automaton based on machine fault diagnosis. Background technique [0002] With the rapid development of computer network technology, the vigorous development of the industrial age and the explosive application of machinery, while improving people's work speed and efficiency, fault diagnosis of important parts of machines has become a key issue. More and more large-scale advanced machinery and equipment can be seen everywhere in the means of transportation for people's daily travel, living tools at home, and advanced medical equipment in hospitals, especially in processing factories and construction sites. The fault diagnosis of the machine is conducive to the healthy operation of the machine, and the early and timely detection of faults can reduce unnecessary economic losses and casualties. Feature extraction...

AI Technical Summary

Problems solved by technology

[0009] Aiming at the technical problems of poor autonomy and poor detection accuracy in the existing fault diagnosis methods, the present invention proposes a construction method of fuzzy automata based on machine fault diagnosis, which has rapidity and accuracy compared with traditional algorithms, and is beneficial to Machine faults can be detected in time, and high fault types and identification accuracy can be achieved

Images