Scraper conveyor chain fluttering fault diagnosis method

Abstract

The invention discloses a scraper conveyor chain fluttering fault diagnosis method. According to the method, whether a scraper conveyor has a chain fluttering fault at a bending section thereof is diagnosed through correlation classification of a sound signal recognition model based on a deep convolutional neural network (CNN) and a support vector machine (SVM). The model is mainly composed of a related input sample, related sound signal features and a classifier, wherein the related input sample is a spectrogram during operation of fully-mechanized coal mining face equipment after principal component analysis (PCA) and whitening treatment, and the related sound signal features are sound signal features extracted by a deep convolutional neural network (CNN), and the classifier is a support vector machine (SVM) with the sound signal features as input. Whether a scraper conveyor has a chain fluttering fault at a bending section thereof is diagnosed by classifying sound signals through the classifier. The method has the advantages of simple steps, reasonable design, easy implementation, and good use effect which is proved by experiments.

Description

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine

Login to view more

AI Technical Summary

Problems solved by technology

However, there is no good detection method for the

Images