Title: Online fault detection strategy applied to a binary component distillation

Authors: Yahya Chetouani

Addresses: Département Génie Chimique, Université de Rouen, Rue Lavoisier, 76821, Mont Saint Aignan Cedex, France

Abstract: This paper deals with an early fault detection method in order to improve the safety and continuity of production. It consists of the design of a residual generator, which is based on a multi-layer perceptron artificial neural network to reveal any drift. Three statistical criteria are used for the validation of the experimental data. This study shows another technique for reduction of neural models into account the physical knowledge of the process. A distillation column is presented in order to illustrate the reliability of the prediction and model reduction. Satisfactory agreement between identified and experimental data is found and results show that the neural model successfully predicts the process behaviour. Then, the proposed FD method, which is based on the standardised residuals, is developed and tested on a real incident. The study shows that it detects the change presence, and pinpoints the moment it occurred.

Keywords: reliability; anomaly detection; normal behaviour; modelling; artificial neural networks; ANNs; online fault detection; distillation column; production safety; production continuity; residual generator design; process behaviour.

DOI: 10.1504/IJESMS.2015.068647

International Journal of Engineering Systems Modelling and Simulation, 2015 Vol.7 No.2, pp.136 - 145

Accepted: 17 Sep 2013
Published online: 18 Mar 2015 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article