Robotized coal machine fault audio frequency recognition and diagnosis method

Abstract

The invention discloses a robotized coal machine fault audio recognition and diagnosis method, which comprises the following steps: preprocessing collected coal mine equipment sound information to obtain preprocessed sound information with a plurality of short-time sound frames; obtaining a spectrogram containing a plurality of spectrogram frames and corresponding to the preprocessed sound information; and inputting the spectrogram into the trained hybrid neural network model, and outputting a fault diagnosis result, wherein the hybrid neural network model comprises an ALEXTet network model, an LSTM network model and a Softmax classification layer. According to the invention, the abnormal sound of coal mine equipment is recognized through a hybrid neural network model, wherein an ALEXTet network model simplifies a traditional CNN convolutional layer and reduces the algorithm complexity; and a LSTM network model is adopted to circularly collect the image sequence, learn and memorize the sequence correlation information, and the single image information and the sequence correlation information are combined to carry out discrimination, so that the accuracy and robustness of abnormal sound recognition of the underground coal mine equipment are improved.

Description

technical field [0001] The invention relates to the field of coal mine equipment detection, in particular to a fault audio recognition and diagnosis method of a robotized coal machine. Background technique [0002] Existing inspection methods of coal mine equipment mainly include manual inspection and equipment monitoring. Manual inspection mainly uses coal mine safety supervision technicians to carry relevant spot inspection equipment or sensors to check the operation status of equipment in the inspection line. Equipment monitoring is based on different monitoring equipment. It can be divided into gas drainage monitoring system, transportation lane monitoring system, power supply monitoring system, mine pressure monitoring system and so on. However, the shortcomings of the two inspection methods are obvious: the labor intensity of manual inspection is high, and there is great uncertainty in the detection results due to the difference in the level of inspection personnel; in...

AI Technical Summary

Problems solved by technology

However, the shortcomings of the two inspection methods are obvious: the labor intensity of manual inspection is high, and there is great uncertainty in the detection results due to the difference in the level of inspection personnel; in addition, due to the complexity of the monitoring system, large network area, and various types of monitoring equipment, Causes high input costs and difficulty in continuous follow-up of daily inspections in management and maintenance

[0003] Large-scale coal mine equipment will emit sound when it is running, and the sound will change with the change of operating state. Manual inspection can judge the state of the equipment based on these sounds, but this is very dependent on the personal experience of the inspection personnel, and only by Manual inspection cannot guarantee real-time detection of equipment, and cannot find faults in time. Once abnormal faults occur in equipment, especially large-scale equipment, the losses may be huge

Images