Unsupervised fault detection in refrigeration showcase with single class data using autoencoders

被引：0
作者：
Santana A. [1 ]
Kawamura Y. [1 ]
Murakami K. [1 ]
Iizaka T. [1 ]
Matsui T. [1 ]
Fukuyama Y. [2 ]
机构：
[1] Fuji Electric, Co. Ltd., 1, Hino, Fujimachi, Tokyo
[2] Meiji University, 4-21-1, Nakano, Nakano-ku, Tokyo
来源：
IEEJ Transactions on Electronics, Information and Systems | 2019年 / 139卷 / 10期
关键词：
Artificial neural networks; Classification algorithms; Fault detection; Machine learning;
D O I：
10.1541/ieejeiss.139.1191
中图分类号：
学科分类号：
摘要：
Refrigeration showcases are commonly utilized equipment in super markets and convenience stores to maintain the temperature and quality of products. Being also susceptible to fault events, the detection of symptoms of unusual operation is still difficult as only samples of normal behavior are usually available. This paper introduces a new use of autoencoders for this one class classification problem with only normal data. An unsupervised approach to cumulatively flag abnormal events is proposed based on ensembled autoencoders and compared with a deep learning counterpart, one-class support vector machine, and the multivariate statistical model standardly employed for fault analysis by the showcase industry manufacturer. Results showed the robustness of the method in flagging out-of-control samples, even when trained with raw sensor data without prior preprocessing. © 2019 The Institute of Electrical Engineers of Japan.
引用
收藏
页码：1191 / 1200
页数：9
相关论文
共 36 条
  • [1] Murakami K., Matusi T., Kawamura Y., Daitou T., Sakai K., Hayashi S., Azumaya N., Nasu T., Development of the online MSPC system for batch processes, Proceedings of the Society Meeting of Electronics, Information and Systems of IEEJ, pp. 1438-1443, (2015)
  • [2] Kano M., Nakagawa Y., Data-based process monitoring, process control, and quality improvement: Recent developments and applications in steel industry, Computers & Chemical Engineering, 32, 1, pp. 12-24, (2008)
  • [3] Dudzic M., Zhang Y., On-line industrial implementation of process monitoring/control applications using multivariate statistical technologies: Challenges and opportunities, Dynamics and Control of Process Systems, pp. 269-279, (2004)
  • [4] Vanhatalo E., Multivariate process monitoring of an experimental blast furnace, Quality and Reliability Engineering International, 26, pp. 495-508, (2009)
  • [5] Gamero F.I., Colomer J., Melendez J., Warren P., Predicting aerodynamic instabilities in a blast furnace, Engineering Applications of Artificial Intelligence, 19, pp. 103-111, (2006)
  • [6] Santana A., Fukuyama Y., Murakami K., Matsui T., Machine learning application for refrigeration showcase fault discrimination, Proceedings of 2016 IEEE Region 10 Conference (TENCON), pp. 10-13, (2016)
  • [7] Zhiqiang G., Song Z., Gao F., Review of recent research on data-based process monitoring, Industrial & Engineering Chemistry Research, 52, 10, pp. 3543-3562, (2013)
  • [8] Arian D., Surjandari I., Review on some multivariate statistical process control methods for process monitoring, International Conference on Industrial Engineering and Operations Management, pp. 754-759, (2016)
  • [9] Wang L., Zhao X., Pei J., Tang G., Transformer fault diagnosis using continuous sparse autoencoder, SpringerPlus, 5, 1, (2016)
  • [10] Chopra P., Yadav S.K., Fault detection and classification by unsupervised feature extraction and dimensionality reduction, Complex & Intelligent Systems, 1, 1-4, pp. 25-33, (2015)
1234