采煤机截割部齿轮故障预测模型设计及试验
Design and Test of Fault Prediction Models for Gears in the Cutting Section of Coal Mining Machines
岳继敏1
作者信息
- 1. 晋能控股煤业集团同发东周窑煤业有限公司,山西 左云 037103
- 折叠
摘要
井下采煤机结构复杂、工况环境差,容易出现各类故障,且处置难度较大.针对MG1000/2500-WD型采煤机截割部齿轮故障诊断需求,结合卷积神经网络的故障特征提取原理,设计了DCNN故障预测模型,并实施了数据训练及模型测试.测试结果表明:预测模型的故障甄别准确率达到98.17％,故障训练值与标准值的准确率达到99.13％,故障预测具有较高的可靠性,实现了预期的研究目的.
Abstract
Underground coal mining machine has complex structure and poor working environment,which is prone to various kinds of faults and difficult to dispose of.To meet the demand for fault diagnosis of the cut-off gear of MG 1000/2500-WD coal mining machine,a DCNN fault prediction model is designed by combining the fault feature extraction principle of convolutional neural network,and the data training and model testing are implemented.The test results show that the fault screening accuracy of the prediction model reaches 98.17％,and the accuracy of the fault training value and the standard value reaches 99.13％,and the fault prediction has a high reliability,which achieves the expected research purpose.
关键词
采煤机/截割部/齿轮/故障诊断/故障预测模型/卷积神经网络Key words
coal mining machine/cut-off section/gear/fault diagnosis/fault prediction model/convolutional neural network引用本文复制引用
出版年
2024
NETL
NSTL
维普
万方数据