Fault detection of batch image-based convolutional autoencoder

被引：0
|
作者：
Zhang H.-L. [1 ,2 ,3 ,4 ]
Wang P. [1 ,2 ,3 ,4 ]
Gao X.-J. [1 ,2 ,3 ,4 ]
Qi Y.-S. [5 ]
Gao H.-H. [1 ,2 ,3 ,4 ]
机构：
[1] Faculty of Information Technology, Beijing University of Technology, Beijing
[2] Engineering Research Center of Digital Community of Ministry of Education, Beijing
[3] Beijing Laboratory for Urban Mass Transit, Beijing
[4] Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing
[5] School of Electric Power, Inner Mongolia University of Technology, Hohhot
来源：
Gao, Xue-Jin (gaoxuejin@bjut.edu.cn) | 1600年 / Northeast University卷 / 36期
关键词：
Batch image; Batch process; Convolutional autoencoder; Fault detection; Multi-phase; One-class support vector machine;
D O I：
10.13195/j.kzyjc.2019.1342
中图分类号：
学科分类号：
摘要：
Aiming at nonlinearity, multi phases and 3D data matrixes in batch processes, a fault detection method using a batch image-based convolutional autoencoder is proposed. Process data of each batch is considered as a grayscale image and is input to the convolutional autoencoder (CAE) directly for representation learning. Data variation in each batch can be regarded as the texture change of the image. Information loss caused by 3D data unfolding to 2D is avoided. Meanwhile, variable correlation is effectively extracted using global modeling with no need to phase division. Convolution operation extracts local conjunction features, and using a autoencoder is an efficient way for unsupervised learning. Then the one-class support vector methold (OCSVM) is used to constructe monitoring statistic and calculate control limit for fault detection. By applying the proposed method on the Pensim simulation and recombinant human granulocyte colony-stimulating factor (rhG-CSF) fermentation process, the effectiveness is demonstrated. Copyright ©2021 Control and Decision.
引用
收藏
页码：1361 / 1367
页数：6
相关论文
共 31 条
  • [1] Chi R H, Hou Z S, Huang B., Optimal iterative learning control of batch processes: From model-based to data-driven, Acta Automatica Sinica, 43, 6, pp. 917-932, (2017)
  • [2] Liu Q, Zhuo J, Lang Z Q, Et al., Perspectives on data-driven operation monitoring and self-optimization of industrial processes, Acta Automatica Sinica, 44, 11, pp. 1944-1956, (2018)
  • [3] Ge Z Q., Review on data-driven modeling and monitoring for plant-wide industrial processes, Chemometrics and Intelligent Laboratory Systems, 171, pp. 16-25, (2017)
  • [4] Ding S X., Data-driven design of monitoring and diagnosis systems for dynamic processes: A review of subspace technique based schemes and some recent results, Journal of Process Control, 24, 2, pp. 431-449, (2014)
  • [5] Chai T Y., Industrial process control systems: Research status and development direction, Scientia Sinica (Information), 46, 8, pp. 1003-1015, (2016)
  • [6] Yang C M, Hou J., Fed-batch fermentation penicillin process fault diagnosis and detection based on support vector machine, Neurocomputing, 190, pp. 117-123, (2016)
  • [7] Wang J, Hu Y, Shi H B., Fault detection for batch processes based on gaussian mixture model, Acta Automatica Sinica, 41, 5, pp. 899-905, (2015)
  • [8] Xiong W L, Guo X G., A process on-line monitoring method based on multi-mode identificatio, Control and Decision, 33, 3, pp. 403-412, (2018)
  • [9] Rendall R, Chiang L H, Reis M S., Data-driven methods for batch data analysis - A critical overview and mapping on the complexity scale, Computers & Chemical Engineering, 124, pp. 1-13, (2019)
  • [10] Qin S J., Survey on data-driven industrial process monitoring and diagnosis, Annual Reviews in Control, 36, 2, pp. 220-234, (2012)
1234