One-dimensional convolutional auto-encoder-based feature learning for fault diagnosis of multivariate processes. (March 2020)

• Record Type: Journal Article
• Authors: Chen, Shumei; Yu, Jianbo; Wang, Shijin
• Is Part Of: Journal of process control. Volume 87(2020)
• Page Start: 54
• Page End: 67
• Publication Date: 2020-03
• Subjects: Multivariate process -- Fault diagnosis -- Convolutional auto-encoder -- Feature learning -- Tennessee Eastman Process -- Fed-batch fermentation penicillin process; Process control -- Periodicals; Fabrication -- Contrôle -- Périodiques; Process control; Periodicals; Electronic journals; 660.281
• DOI: 10.1016/j.jprocont.2020.01.004
• Languages: English
• ISSNs: 0959-1524

Abstract

Highlights: A new DNN (1D-CAE) is proposed to learn features from process signals. 1D-CAE integrates convolution convolutional kernel and auto-encoder. 1D-CAE-based feature learning is effective for process fault diagnosis. DNN provides an effective way for process control due to powerful feature learning. Abstract: Noise and high-dimension of process signals decrease effectiveness of those regular fault detection and diagnosis models in multivariate processes. Deep learning technique shows very excellent performance in high-level feature learning from image and visual data. However, the large labeled data are required for deep neural networks (DNNs) with supervised learning like convolutional neural network (CNN), which increases the time cost of model construction significantly. A new DNN model, one-dimensional convolutional auto-encoder (1D-CAE) is proposed for fault detection and diagnosis of multivariate processes in this paper. 1D-CAE is utilized to learn hierarchical feature representations through noise reduction of high-dimensional process signals. Auto-encoder integrated with convolutional kernels and pooling units allows feature extraction to be particularly effective, which is of great importance for fault detection and diagnosis in multivariate processes. The comparison between 1D-CAE and other typical DNNs illustrates effectiveness of 1D-CAE for fault detection and diagnosis on Tennessee Eastman Process and Fed-batch fermentation penicillin process. The proposed method provides an effective platform for deep-learning-based process fault detection and diagnosis of multivariate processes. Graphical abstract: Image, graphical abstract