[an error occurred while processing this directive]

Journal of Systems Engineering and Electronics ›› 2021, Vol. 32 ›› Issue (1): 209-219.doi: 10.23919/JSEE.2021.000018

• • 上一篇    下一篇

  

  • 收稿日期:2020-02-25 出版日期:2021-02-25 发布日期:2021-02-25

Constrained voting extreme learning machine and its application

Mengcan MIN(), Xiaofang CHEN*(), Yongfang XIE()   

  1. 1 School of Automation, Central South University, Changsha 410083, China
  • Received:2020-02-25 Online:2021-02-25 Published:2021-02-25
  • Contact: Xiaofang CHEN E-mail:mengcanmin@csu.edu.cn;xiaofangchen@csu.edu.cn;yfxie@csu.edu.cn
  • About author:|MIN Mengcan was born in 1996. She received her B.E. degree in School of Computer and Information Engineering from Henan University, Kaifeng, China, in 2018. She is currently a postgraduate student at School of Automation, Central South University, Changsha, China. Her research interests include machine learning, knowledge automation, and modeling and control of complex industrial process. E-mail: mengcanmin@csu.edu.cn||CHEN Xiaofang was born in 1975. He received his M.S. degree in control science and engineering and Ph.D. degree in control science and engineering from Central South University, Changsha, China, in 2000 and 2004, respectively. He was with the Baosteel Research Institute and the China North Industries Group, China. Since 2018, he has been a professor with the School of Automation, Central South University. His current research interests include modeling and optimal control of complex industrial process, control and optimization, intelligent control system, and knowledge driven automation.E-mail: xiaofangchen@csu.edu.cn||XIE Yongfang was born in 1972. He received his B.S., M.S. and Ph.D. degrees in control science and engineering from Central South University, Changsha, China, in 1993, 1996 and 1999, respectively. From 1999 to 2003, he did collaborative research in the International Institute of Information Science in Tokyo, Japan and PToPA Institute as a visiting scholar. From 2007 to 2009, he was a visiting scholar at University of Duisburg-Essen, Germany. Currently, he is a full professor in Central South University. His research interests include modeling and control of complex industrial process, decentralized robust control and fault diagnosis. E-mail: yfxie@csu.edu.cn
  • Supported by:
    This work was supported by the National Natural Science Foundation of China (61773405; 61751312), and the Major Scientific and Technological Innovation Projects of Shandong Province (2019JZZY020123).

Abstract:

Extreme learning machine (ELM) has been proved to be an effective pattern classification and regression learning mechanism by researchers. However, its good performance is based on a large number of hidden layer nodes. With the increase of the nodes in the hidden layers, the computation cost is greatly increased. In this paper, we propose a novel algorithm, named constrained voting extreme learning machine (CV-ELM). Compared with the traditional ELM, the CV-ELM determines the input weight and bias based on the differences of between-class samples. At the same time, to improve the accuracy of the proposed method, the voting selection is introduced. The proposed method is evaluated on public benchmark datasets. The experimental results show that the proposed algorithm is superior to the original ELM algorithm. Further, we apply the CV-ELM to the classification of superheat degree (SD) state in the aluminum electrolysis industry, and the recognition accuracy rate reaches 87.4%, and the experimental results demonstrate that the proposed method is more robust than the existing state-of-the-art identification methods.

Key words: extreme learning machine (ELM), majority voting, ensemble method, sample based learning, superheat degree (SD)