Title: Modelling and identification of an irrigation station using hybrid possibilistic c-means and fuzzy particle swarm optimisation

Authors: Jaouher Chrouta; Abderrahmen Zaafouri; Mohamed Jemli

Addresses: DGE, University of Tunis, 5 Av Taha Hussein, Tunis, Tunisia ' DGE, University of Tunis, 5 Av Taha Hussein, Tunis, Tunisia ' DGE, University of Tunis, 5 Av Taha Hussein, Tunis, Tunisia

Abstract: Data-driven design of accurate and reliable Takagi-Sugeno (T-S) fuzzy systems has drawn the attention of several researchers in recent decades, according to an excellent ability for describing non-linear systems. In literature, several fuzzy clustering algorithms have been proposed to identify the parameters involved in the Takagi-Sugeno fuzzy model. Possibilistic C-Means (PCM) is one of the most used clustering methods because it is efficient, straightforward, easy to implement and exhibits robustness to noise. However, PCM is sensitive to initialisation and is easily trapped in local optima. Contrariwise, the PSO algorithm has strong global searching ability, and it doesn't easily get into the local minimum to overcome the drawbacks of PCM algorithm. In this paper, a hybrid fuzzy clustering method based on PCM and fuzzy PSO (FPSO) is proposed which makes use of the merits of both algorithms. Experimental results applied to an irrigation station show that the hybrid algorithm (PCM-FPSO) is efficient and can reveal encouraging results.

Keywords: irrigation stations; fuzzy clustering; particle swarm optimisation; fuzzy PSO; Takagi-Sugeno fuzzy systems; modelling; identification; possibilistic c-means; PCM; c-means clustering; nonlinear systems.

DOI: 10.1504/IJCAT.2017.082265

International Journal of Computer Applications in Technology, 2017 Vol.55 No.1, pp.30 - 38

Received: 06 Jun 2015
Accepted: 11 Oct 2015

Published online: 14 Feb 2017 *

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