基于小波网络的矿井提升机钢丝绳磨损程度趋势预测研究

Study on Trend Estimate of the Mine Hoist Based on the Wavelet Neural Network

提升机是煤矿生产的重要设备,开展故障预报是减少提升机突发故障、提高预知维修的重要手段之一。通过对矿井提升机关键特征参数的时间序列预报,即可实现故障预报。小波网络比一般神经网络具有更多的自由度,从而使其具有更灵活有效的函数逼近能力。小波冲经元的良好局部特性和多分辨率学习实现了与信号的良好巨配,使得小波网络的更强的自适应能力,更快的收敛速度和更高的预报精度。因此本文采用小波网络对提升机钢丝绳损度、空动时间、衬垫磨损寿命、闸瓦间隙△、残压Pc、制动盘偏摆度δ进行故障预测。对保证矿井提升帆字全和高效运行具有重要意义。

Developing fault forecast is one of important means to reduce the catastrophic failure and increase the foreknowledge of maintenance in mine hoist, as which is the important equipments that the coal mine produce. By forecasting time series of key characteristic parameter of mine hoist, fault forecast are realized. With more degree of freedom in relation to the general neural network, Wavelet neural network is in possession of more vivid and more valid ability in function approximation. With the good partial characteristic and distinguish rate study Wavelet neural network realizes the signal with good matching, and then Wavelet neural network had stronger self adaptation ability, more sooner convergence rate and higher forecast accuracy. Then the fault forecast in mine hoist to steel wire rope wears away degree, get empty to move time, brake shoe wear away life, brake shoe clearance, remnant presses and brake disk deflection degree adopt Wavelet neural network in this paper, which have the important meaning to guarantee the mine hoist circulate efficiently s^ety.