作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程

• 开发研究与工程应用 • 上一篇    下一篇

基于ICA-ELM的工业过程故障分类

严文武,潘丰   

  1. (江南大学轻工过程先进控制教育部重点实验室,江苏 无锡 214122)
  • 收稿日期:2014-09-30 出版日期:2015-10-15 发布日期:2015-10-15
  • 作者简介:严文武(1989-),男,硕士研究生,主研方向:控制理论与控制工程;潘丰,教授、博士生导师。
  • 基金资助:
    国家自然科学基金资助项目(61273131);江苏省产学研联合创新基金资助项目(BY2013015-39)。

Industry Process Fault Classification Based on ICA-ELM

YAN Wenwu,PAN Feng   

  1. (Key Laboratory of Advanced Control for Light Industry Process,Ministry of Education,Jiangnan University,Wuxi 214122,China)
  • Received:2014-09-30 Online:2015-10-15 Published:2015-10-15

摘要: 基于独立成分分析(ICA)的多变量统计过程监控主要用于故障检测,不能有效地进行故障分类。为此,结合极限学习机(ELM),提出一种ICA-ELM的故障分类方法。利用ICA提取故障特征,通过ELM学习算法训练神经网络,从而实现故障分类。采用TE过程数据进行验证,实验结果表 明,与概率神经网络和支持向量机相比,ICA-ELM算法的故障分类准确率更高,训练速度更快。

关键词: 独立成分分析, 极限学习机, 故障分类, 概率神经网络, 支持向量机, TE过程

Abstract: The process monitoring method with multivariate statistics based on Independent Component Analysis(ICA) is mainly used for fault detection,but it is not effective for fault classification.For this reason,combining with Extreme Learning Machine(ELM),a method called ICA-ELM for fault classification is proposed.ICA-ELM extracts the fault features with ICA,and then trains the networks with ELM,so as to realize fault classification.ICA-ELM is tested with Tennessee Eastman (TE) process data and compared with Probabilistic Neural Network(PNN) and Support Vector Machine(SVM).Experimental result shows that the accuracy of ICA-ELM is higher,training speed of ICA-ELM is faster.

Key words: Independent Component Analysis(ICA), Extreme Learning Machine(ELM), fault classification, Probabilistic Neural Network(PNN), Support Vector Machine(SVM), Tennessee Eastman(TE) process

中图分类号: