Fault detection and classification using artificial neural networks. Issue 18 (2018)

• Record Type: Journal Article
• Authors: Heo, Seongmin; Lee, Jay H.
• Is Part Of: IFAC-PapersOnLine. Volume 51:Issue 18(2018)
• Page Start: 470
• Page End: 475
• Publication Date: 2018
• Subjects: artificial neural network -- deep learning -- fault detection -- fault classification; Automatic control -- Periodicals; 629.805
• DOI: 10.1016/j.ifacol.2018.09.380
• Languages: English
• ISSNs: 2405-8963

Abstract

Abstract: Process monitoring is considered to be one of the most important problems in process systems engineering, which can be benefited significantly from deep learning techniques. In this paper, deep neural networks are applied to the problem of fault detection and classification to illustrate their capability. First, the fault detection and classification problems are formulated as neural network based classification problems. Then, neural networks are trained to perform fault detection, and the effects of two hyperparameters (number of hidden layers and number of neurons in the last hidden layer) and data augmentation on the performance of neural networks are examined. Fault classification problem is also tackled using neural networks with data augmentation. Finally, the results obtained from deep neural networks are compared with other data-driven methods to illustrate the advantages of deep neural networks.