Underground carry-scraper fault diagnosis method based on PSO-BP neural network

Abstract

The invention provides an underground carry-scraper fault diagnosis method based on a PSO-BP neural network, and belongs to the technical field of underground carry-scraper fault diagnosis. According to the method, firstly, original data of mine equipment operation are extracted from a database and classified and transferred according to the model of the equipment, after the obtained data are preprocessed, feature parameters of faults are mined by adopting a Relief algorithm, and a BP neural network model optimized by a particle swarm optimization (PSO) is constructed for fault diagnosis. Compared with the traditional manual screening, the invention has the advantages that the fault features are screened and filtered through the Relief algorithm, a large amount of analysis time can be saved, a more accurate analysis result can be provided; in addition, the optimized PSO-BP neural network overcomes the defect that only the BP neural network is used to converge to a local optimal solution, and the fault diagnosis accuracy of the mine equipment is improved.

Description

technical field [0001] The invention relates to the technical field of fault diagnosis of an underground scraper, in particular to a fault diagnosis method for an underground scraper based on a PSO-BP neural network. Background technique [0002] The normal operation of large underground equipment plays a very important role in the production and operation of mining enterprises, and underground scrapers are a type of typical underground mining equipment widely used, and their operating conditions and management levels directly affect the production efficiency and safety of mining enterprises . [0003] Nowadays, with the development of mining equipment in the direction of large-scale, digital, and intelligent, the structure of the underground scraper is becoming more and more complex. Once the machine fails, it is difficult for professional maintenance personnel to troubleshoot and repair the fault in time, which not only damages the equipment, stops production and causes h...

AI Technical Summary

Problems solved by technology

[0004] The traditional fault diagnosis technology based on analytical model cannot timely feedback the fault type and fault degree. With the development of artificial intelligence and big data technology, more and more people apply big data information, machine learning and deep learning technologies to fault diagnosis , to improve the rapid fault detection, diagnosis and maintenance capabilities of equipment

BP neural network theory is relatively mature and suitable for the field of fault diagnosis, but its defect is that when using error backpropagation to adjust the weight of network connections, it is easy to fall into the local optimal solution problem. The BP neural network optimized by particle swarm optimization (PSO) The optimal weight and threshold of the network can be searched in a large space, which improves the performance of the BP neural network to a certain extent and improves the accuracy of diagnosis

Images