Method for intelligently diagnosing rotating machine fault feature based on deep CNN model

Abstract

The invention discloses a method for intelligently diagnosing a rotating machine fault feature based on a deep CNN model. The method comprises: (1) acquiring rotating machine fault vibration signal data, segmenting the data and performing de-trend item preprocessing; (2) performing short-time Fourier time-frequency transform analysis on the signal data to obtain the time-frequency representation of each vibration signal, and displaying the time-frequency representation with a pseudo-color map; (3) reducing the image resolution by an interpolation method and superimposing respective images to form a training sample and a test sample as inputs of the CNN; (4) constructing the deep CNN model including an input layer, two convolution layers, two pooling layers, a fully connected layer, and a softmax classification layer and an output layer; and (5) introducing the training sample into the model for training, obtaining a convolution feature, a pooling feature and a neural network structuralparameter, and diagnosing unknown fault signals according to the constructed deep CNN. The method has better accuracy and stability than an existing time-domain or frequency-domain method.

Description

technical field [0001] The invention belongs to the technical field of vibration fault diagnosis of rotating machinery, and relates to an intelligent diagnosis method for fault characteristics of rotating machinery based on a deep convolutional neural network structure. Background technique [0002] Vibration signals of rotating machinery can be collected in a timely manner through vibration sensors and other equipment to accurately reflect the working status of mechanical equipment. How to extract effective information that can accurately reflect the characteristics of mechanical faults from massive vibration signals, and determine the fault type and working status are the main research contents of mechanical fault diagnosis. The working environment of rotating mechanical equipment with fault characteristics is usually very complex, with many vibration sources and strong background noise. The mechanical vibration signals measured on site are usually multi-component, non-sta...

AI Technical Summary

Problems solved by technology

Since time-domain features cannot reflect information such as frequency and frequency spectrum, and frequency-domain methods can only reflect local feature information in vibration signals, and cannot reflect time-varying feature information, therefore, directly using a single time-domain or frequency-domain method cannot Accurate, effective and complete expression of useful information in vibration signals

Images