Title: Constrained neural classifier training method for flaw detection in industrial pipes using particle swarm optimisation

Authors: Gilvan Farias Da Silva; Edmar E.P. De Souza; Eduardo F. De Simas Filho; Paulo C.M.A. Farias; Maria C.S. Albuquerque; Ivan Costa Da Silva; Cláudia T.T. Farias

Addresses: Digital Systems Laboratory, Electrical Engineering Program, Federal University of Bahia, Salvador, BA, Brazil ' Digital Systems Laboratory, Electrical Engineering Program, Federal University of Bahia, Salvador, BA, Brazil ' Digital Systems Laboratory, Electrical Engineering Program, Federal University of Bahia, Salvador, BA, Brazil ' Digital Systems Laboratory, Electrical Engineering Program, Federal University of Bahia, Salvador, BA, Brazil ' Federal Institute of Bahia, Salvador, BA, Brazil ' Federal Institute of Bahia, Salvador, BA, Brazil ' Federal Institute of Bahia, Salvador, BA, Brazil

Abstract: A novel method for constrained training of multi-class artificial neural network classifiers is proposed in this work. The traditional training procedure is usually based on mean square error minimisation and thus, all classes of interest are considered as having the same relevance for system performance. This is not always the case for real-world applications in which the class relevance may be unbalanced. In this paper, cost functions designed to introduce classification performance constraints for specific classes are presented and particle swarm optimisation is used as global optimisation method. The proposed method is applied to a non-destructive evaluation decision support problem using pulsed eddy currents signals. Experimental results obtained from thermally insulated industrial pipes indicate the efficiency of the proposed method in comparison to neural networks trained from the traditional back-propagation algorithm.

Keywords: artificial neural networks; ANN; particle swarm optimisation; PSO; pulsed-eddy current evaluation; signal processing.

DOI: 10.1504/IJICA.2022.124239

International Journal of Innovative Computing and Applications, 2022 Vol.13 No.3, pp.150 - 160

Received: 11 Apr 2020
Accepted: 21 Apr 2020
Published online: 19 Jul 2022 *

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