首页|期刊简介|投稿指南|分类索引|刊文选读|订阅指南|证明资料|样刊邮寄查询|常见问题解答|联系我们
韩松,徐林森. 基于主成分分析和支持向量机分类模型的滚动轴承故障诊断[J]. 科学技术与工程, 2021, 21(8): 3153-3158.
Han song.Research on Fault Diagnosis of Rolling Bearing Based on Classification Model of PCA and SVMHAN Song1,2,XU Lin-sen1,3[J].Science Technology and Engineering,2021,21(8):3153-3158.
基于主成分分析和支持向量机分类模型的滚动轴承故障诊断
Research on Fault Diagnosis of Rolling Bearing Based on Classification Model of PCA and SVMHAN Song1,2,XU Lin-sen1,3
投稿时间:2020-05-30  修订日期:2020-11-29
DOI:
中文关键词:  故障诊断  滚动轴承  误差分析  PCA  SVM
英文关键词:fault diagnosis  rolling bearing  error analysis  PCA  SVM
基金项目:江苏省科技计划项目(产业前瞻与共性关键技术)(BE2017067)
     
作者单位
韩松 中国科学院
徐林森 中国科学院
摘要点击次数: 202
全文下载次数: 65
中文摘要:
      本文提出了一种基于主成分分析(Principal Component Analysis,PCA)和支持向量机(Support Vector Machine,SVM)模型的滚动轴承故障诊断研究。首先,通过不同公式计算标准差比较法和拉依达准则对数据进行误差分析。其次,利用MATLAB软件中的pca函数对数据进行主成分分析,将8个原始变量降维成3个综合变量。最后,分别从降维前和降维后的输入属性数据中随机选取70%的数据作为训练集来建立SVM分类模型和PCA-SVM分类模型,而把剩余的30%作为测试集来对模型的性能进行仿真测试。MATLAB仿真测试的结果表明,PCA-SVM模型的分类效果更好,其预测正确率对于绝大多数故障诊断来说是可以接受的,即这种方法是可以作为一种故障诊断的评价标准的。
英文摘要:
      Machine learning demonstrates its absolute advantage in equipment fault diagnosis with its excellent learning ability. Therefore, a fault diagnosis study of rolling bearing based on Principal Component Analysis (PCA) and Support Vector Machine (SVM) model is proposed. First, the error analysis of the data is performed by calculating the standard deviation comparison method with different formulas and the Pauta Criterion. Secondly, using the pca function in MATLAB software to perform principal component analysis on the data, the eight original variables are reduced to three integrated variables. Finally, 70% of the data from the input attribute data before and after the dimension reduction are randomly selected as the training set to establish the SVM classification model and the PCA-SVM classification model, and the remaining 30% is used as the test set to the model. Performance is tested by simulation. The results of MATLAB simulation test show that the SVM model established by data without principal component analysis has better classification effect, and its prediction accuracy is acceptable for most fault diagnosis, that is, this method can be used as a kind of the evaluation criteria for fault diagnosis.
查看全文  查看/发表评论  下载PDF阅读器
关闭
你是第37537087位访问者
版权所有:科学技术与工程编辑部
主管:中国科学技术协会    主办:中国技术经济学会
Tel:(010)62118920 E-mail:stae@vip.163.com
京ICP备05035734号-4
技术支持:本系统由北京勤云科技发展有限公司设计

京公网安备 11010802029091号