Supervised convolutional autoencoder-based fault-relevant feature learning for fault diagnosis in industrial processes

Background: Convolutional autoencoder (CAE) is an unsupervised feature learning method and shows excellent performance in multivariate fault diagnosis. However, CAE cannot guarantee that the extracted feature is always related to the fault type due to its unsupervised self-reconstruction in the pretraining phase.Methods: To solve this problem, a new feature learning method, supervised convolutional autoencoder (SCAE) is proposed to pretrain the network and learn representative feature containing internal spatial information and fault information. In the SCAE, process sample and corresponding label are reconstructed by multilayer encoding-decoding the raw sample. Meanwhile, to prevent label information overfitting the network, a minimum difference transformation function is introduced into the loss function.Findings: The obtained fault-relevant features can be obviously distinguished between different fault types. The trained pretraining network provides more appropriate predefined parameters for fine-tuning to improve the classification performance. The effectiveness of the proposed method is evaluated by the continuous stirred tank reactor (CSTR) process and the Tennessee Eastman (TE) process.(c) 2021 Taiwan Institute of Chemical Engineers. Published by Elsevier B.V. All rights reserved.

Automated summary

A new feature learning method, SCAE, addresses the issue of CAE's inability to ensure that extracted features are related to fault types, by pretraining the network to learn internal spatial information and fault information. The fault-relevant features obtained by SCAE can clearly distinguish between different fault types, providing more appropriate predefined parameters for fine-tuning to enhance classification performance.