摘要
为了提高煤矿主扇风机故障诊断的准确性,将网格搜索法和支持向量机(SVM)应用到主扇风机的故障诊断中。首先,建立主扇风机运行故障的知识库,并将采集到的主扇风机振动信号进行小波消澡和归一化;然后,设计了网格搜索参数优化SVM的主扇风机故障诊断模型。最后,通过工程现场提取的数据进行实验验证,并与遗传算法和粒子群算法寻优的时间和诊断结果准确率进行比较。实验结果表明,网格搜索法SVM参数优化非常适合于煤矿主扇风机的故障系统中。
In order to improve the accuracy of fault diagnosis of mine main fan,grid search method and support vector machine(SVM) are applied to fault diagnosis of the main fan. First,the establishment of operational failure of the main fan knowledge,and the collected main fan vibration signals are used to wavelet de bath and normalization; then designed a grid search parameter optimization of SVM main fan failure neural network; Finally,verify the data extracted by the project site. The experimental results show that this method can effectively diagnose the main fan.
出处
《煤炭技术》
CAS
北大核心
2015年第1期295-297,共3页
Coal Technology
