化工学报 ›› 2017, Vol. 68 ›› Issue (6): 2447-2454.DOI: 10.11949/j.issn.0438-1157.20161252

• 过程系统工程 • 上一篇    下一篇

基于重构的半监督ELM及其在故障诊断中的应用

易维淋, 田学民, 张汉元   

  1. 中国石油大学(华东)信息与控制工程学院, 山东 青岛 266580
  • 收稿日期:2016-09-06 修回日期:2017-02-06 出版日期:2017-06-05 发布日期:2017-06-05
  • 通讯作者: 田学民
  • 基金资助:

    国家自然科学基金项目(61273160)

Reconstruction based semi-supervised ELM and its application in fault diagnosis

YI Weilin, TIAN Xuemin, ZHANG Hanyuan   

  1. College of Information and Control Engineering, China University of Petroleum, Qingdao 266580, Shandong, China
  • Received:2016-09-06 Revised:2017-02-06 Online:2017-06-05 Published:2017-06-05
  • Contact: 10.11949/j.issn.0438-1157.20161252
  • Supported by:

    supported by the National Natural Science Foundation of China (61273160)

摘要:

工业过程中获取带标签的故障数据困难,而无标签故障数据却大量存在,如何有效地利用数据信息进行故障诊断是故障诊断领域的重要内容。为更充分地挖掘和利用数据信息,提出一种新的半监督学习方法:基于重构的半监督极限学习机(RSELM)。相比于传统的半监督极限学习机(ELM)方法,RSELM采用自动编码ELM(ELM-AE)获得的输出权重替代随机的隐含层输入权重,能更有效地提取数据特征;考虑到数据均可由其近邻数据来线性重构,故可构建近邻数自适应选择的重构图,并同时利用数据的标签信息优化连接权重,以更优地反映数据结构信息;通过建立新的含局部保持的目标函数,可有效地训练分类器。标准数据集和TE过程上的仿真实验验证了所提算法的有效性。

关键词: 半监督极限学习机, 重构, ELM-AE, 故障诊断

Abstract:

It is difficult to obtain labeled fault data while there are a multitude of unlabeled data available in industrial process, so how to utilize data information effectively is an important focal point in the field of fault diagnosis. A new semi-supervised learning method, reconstruction-based semi-supervised extreme learning machine (RSELM), was proposed for more sufficient data mining and information usage. Compared to traditional semi-supervised ELM, RSELM replaced random input weight in hidden layer with output weight, which was obtained by ELM auto-encoder (ELM-AE), such that data feature was extracterd more effectively. Since data could be reconstructed linearly by its neighbors, a self-adaptive reconstruction graph of neighboring data in combination with connection weight of optimal labeled data better reflected data structure information. A novel objective function preserving local structure information was further built to train classifier effectively. Simulation experiment on standard datasets and TE process demonstrated effectiveness of the proposed algorithm.

Key words: semi-supervised ELM, reconstruction, ELM-AE, fault diagnosis

中图分类号: