SCI和EI收录∣中国化工学会会刊

中国化学工程学报 ›› 2022, Vol. 50 ›› Issue (10): 398-411.DOI: 10.1016/j.cjche.2022.10.001

• Process Systems Engineering and Process Safety • 上一篇    下一篇

Adaptive multiscale convolutional neural network model for chemical process fault diagnosis

Ruoshi Qin1, Jinsong Zhao1,2   

  1. 1 State Key Laboratory of Chemical Engineering, Department of Chemical Engineering, Tsinghua University, Beijing 100084, China;
    2 Beijing Key Laboratory of Industrial Big Data System and Application, Tsinghua University, Beijing 100084, China
  • 收稿日期:2022-07-01 修回日期:2022-09-14 出版日期:2022-10-28 发布日期:2023-01-04
  • 通讯作者: Jinsong Zhao,E-mail:jinsongzhao@tsinghua.edu.cn
  • 基金资助:
    The authors gratefully acknowledge support from the National Science and Technology Innovation 2030 Major Project of the Ministry of Science and Technology of China (2018AAA0101605) and the National Natural Science Foundation of China (21878171).

Adaptive multiscale convolutional neural network model for chemical process fault diagnosis

Ruoshi Qin1, Jinsong Zhao1,2   

  1. 1 State Key Laboratory of Chemical Engineering, Department of Chemical Engineering, Tsinghua University, Beijing 100084, China;
    2 Beijing Key Laboratory of Industrial Big Data System and Application, Tsinghua University, Beijing 100084, China
  • Received:2022-07-01 Revised:2022-09-14 Online:2022-10-28 Published:2023-01-04
  • Contact: Jinsong Zhao,E-mail:jinsongzhao@tsinghua.edu.cn
  • Supported by:
    The authors gratefully acknowledge support from the National Science and Technology Innovation 2030 Major Project of the Ministry of Science and Technology of China (2018AAA0101605) and the National Natural Science Foundation of China (21878171).

摘要: Intelligent fault recognition techniques are essential to ensure the long-term reliability of manufacturing. Due to the variations in material, equipment and environment, the process variables monitored by sensors contain diverse data characteristics at different time scales or in multiple operating modes. Despite much progress in statistical learning and deep learning for fault recognition, most models are constrained by abundant diagnostic expertise, inefficient multiscale feature extraction and unruly multimode condition. To overcome the above issues, a novel fault diagnosis model called adaptive multiscale convolutional neural network (AMCNN) is developed in this paper. A new multiscale convolutional learning structure is designed to automatically mine multiple-scale features from time-series data, embedding the adaptive attention module to adjust the selection of relevant fault pattern information. The triplet loss optimization is adopted to increase the discrimination capability of the model under the multimode condition. The benchmarks CSTR simulation and Tennessee Eastman process are utilized to verify and illustrate the feasibility and efficiency of the proposed method. Compared with other common models, AMCNN shows its outstanding fault diagnosis performance and great generalization ability.

关键词: Neural networks, Multiscale, Adaptive attention module, Triplet loss optimization, Fault diagnosis, Chemical processes

Abstract: Intelligent fault recognition techniques are essential to ensure the long-term reliability of manufacturing. Due to the variations in material, equipment and environment, the process variables monitored by sensors contain diverse data characteristics at different time scales or in multiple operating modes. Despite much progress in statistical learning and deep learning for fault recognition, most models are constrained by abundant diagnostic expertise, inefficient multiscale feature extraction and unruly multimode condition. To overcome the above issues, a novel fault diagnosis model called adaptive multiscale convolutional neural network (AMCNN) is developed in this paper. A new multiscale convolutional learning structure is designed to automatically mine multiple-scale features from time-series data, embedding the adaptive attention module to adjust the selection of relevant fault pattern information. The triplet loss optimization is adopted to increase the discrimination capability of the model under the multimode condition. The benchmarks CSTR simulation and Tennessee Eastman process are utilized to verify and illustrate the feasibility and efficiency of the proposed method. Compared with other common models, AMCNN shows its outstanding fault diagnosis performance and great generalization ability.

Key words: Neural networks, Multiscale, Adaptive attention module, Triplet loss optimization, Fault diagnosis, Chemical processes