Browse by author
Lookup NU author(s): Dr Jie ZhangORCiD
Full text for this publication is not currently held within this repository. Alternative links are provided below where available.
With industrial production processes becoming more and more sophisticated, traditional fault diagnosis systemsmay be insufficient to meet current industrial diagnostic performance requirements. In order to improve fault diagnosisperformance, this paper proposes an enhanced neural network based fault diagnosis system by integrating Andrews plot and Autoencoder. Features are first extracted from on-line measurements by Andrews plot and the high-dimensionalfeatures are compressed by autoencoder to an appropriate dimension, which are then fed to a neural network for faultclassification. Application to a simulated CSTR process demonstrates that the proposed method can give more reliableand earlier diagnosis than the traditional neural network based fault diagnosis method.
Author(s): Wang S, Zhang J
Publication type: Conference Proceedings (inc. Abstract)
Publication status: Published
Conference Name: 18th IEEE International Conference on Industrial Informatics (INDIN2020)
Year of Conference: 2020
Pages: 787-792
Print publication date: 20/07/2020
Online publication date: 20/07/2020
Acceptance date: 16/06/2020
Publisher: IEEE
Library holdings: Search Newcastle University Library for this item
ISBN: 9781728149639
