摘要
为了对采煤机故障进行准确诊断研究,本文提出了一种基于优化支持向量机的采煤机故障诊断新方法,首先采用主成分分析法(PCA)对采煤机故障特征参数进行特征提取,其次应用特征数据进行基于支持向量机(SVM)的采煤机故障诊断模型训练,再次采用交叉验证方法对SVM模型参数进行优化,建立最优SVM采煤机故障诊断模型,最后通过对比实验,验证了基于优化SVM采煤机故障诊断模型的可行性和优越性。
In order to research on breakdown diagnosis of coal excavator, this paper proposed an optimal support vectormachine （SVM） model for it. Firstly the principal component analysis （PCA） was adopted to extract the breakdowncharacteristic parameters of coal excavator. Secondly the breakdown characteristic data was applied to the breakdowndiagnosis model training based on SVM using the cross validation method to optimize the parameters of SVM, andestablishing the optimal SVM model for coal excavator breakdown diagnosis. At last, with comparing experiment, theexperimental result showed that the optimized SVM breakdown diagnosis model of coal excavator was feasible andadvantageous.
出处
《山东农业大学学报（自然科学版）》
CSCD
2015年第1期132-135,共4页
Journal of Shandong Agricultural University：Natural Science Edition
基金
河北省社会科学基金年度项目(HB13GL041)
河北省重点发展学科计算机应用技术(冀教高HB201406)
关键词
采煤机
支持向量机
主成分分析
交叉验证
故障诊断
Coal excavator
Support Vector Machine
Principal Component Analysis
cross validation
breakdown diagnosis
