One-dimensional convolutional neural network-based active feature extraction for fault detection and diagnosis of industrial processes and its understanding via visualization

Feature extraction from process signals enables process monitoring models to be effective in industrial processes. Deep learning presents extensive possibilities for extracting abstract features from image and visual data. However, the main inputs of conventional deep neural networks are large images. To overcome this, a one-dimension convolution neural network-based model optimized by a reinforcement-learning-based neural architecture search, is proposed for multivariate processes control. The experimental results illustrate its predominance for detecting and recognizing process faults. Feature and network visualization are also implemented to explore the reasons for its outstanding performance. This research extends the applications of convolutional neural network based on one-dimension process signals in complex multivariate process control. (c) 2021 ISA. Published by Elsevier Ltd. All rights reserved.

Automated summary

This study proposes a one-dimensional convolutional neural network model optimized by reinforcement learning-based neural architecture search for multivariate process control, which shows excellent performance in detecting and recognizing process faults.