An ipso-bp neural network based wire rope broken wire damage recognition method

Abstract

An IPSO-BP neural network wire rope broken wire damage identification method, a BP neural network identification method based on an improved particle swarm optimization algorithm (IPSO), is proposed, by collecting wire rope broken wire damage signals, extracting defect signal features, and using damage signal The peak value, peak-to-peak value, wave width, area under the waveform and wave energy form the eigenvector as the input of the neural network, and the number of broken wires as the output of the network. Values ​​and thresholds are optimized to achieve precise location and rapid identification of wire rope broken wire damage. The invention can improve the generalization ability of the steel wire rope defect recognition neural network, realize the prediction, prevention and pre-control of the safety hazards of the steel wire rope, and provide a reliable technical means for the damage detection of the load-bearing steel wire rope.

Description

technical field [0001] The invention belongs to the technical field of sensor detection, and relates to signal intelligent detection and identification, and artificial neural network technology. Background technique [0002] As a load-bearing component in hoisting, hoisting and traction systems, steel wire ropes are widely used in metallurgy, mining, coal, construction, ports, oil drilling, as well as in the machinery industry, aerial travel aerial ropeways, cable-stayed bridges, and elevator industries. During use, due to the influence of wear, corrosion, fatigue, impact and other factors, the steel wire rope will inevitably produce various damages, resulting in a reduction in the bearing capacity, and even a sudden fracture resulting in death, casualties and major accidents. Therefore, intelligent diagnosis, safety detection and quantitative identification of steel wire ropes have become urgent problems to be solved, and it is of great significance to realize online detect...

AI Technical Summary

Problems solved by technology

[0003] The traditional quantitative identification methods for wire rope broken wire damage mostly use the over-threshold decision-making method based on statistical pattern recognition. The selection of the threshold value depends on human experience, which may easily cause missed detection

Images