Enhanced Data-Driven Fault Diagnosis of Chemical Process via Information Fusion in Multiple Neural Networks and Andrews Plot

Wang, S; Zhang, J

doi:10.23919/ICAC50006.2021.9594242

Enhanced Data-Driven Fault Diagnosis of Chemical Process via Information Fusion in Multiple Neural Networks and Andrews Plot

Lookup NU author(s): Dr Shengkai Wang, Dr Jie Zhang ORCiD

Downloads

Full text for this publication is not currently held within this repository. Alternative links are provided below where available.

Abstract

An enhanced data-driven fault diagnosis system combining multiple neural networks and using Andrews plot for information pre-processing is presented in this paper. The system first extract features from on-line measurements by Andrews plot approach and the normalized features are used as the neural network inputs. To overcome the non-robustness of a single neural network, multiple neural networks are combined using information fusion for enhanced fault diagnosis performance. The proposed method is applied to a simulated CSTR process and the results show that the proposed method gives more robust and faster diagnosis than the conventional neural network based fault diagnosis method.