Title: Adaptive fuzzy control strategy for greenhouse micro-climate

Authors: Mouna Boughamsa; Messaoud Ramdani

Addresses: Department of Electronics, Badji Mokhtar-Annaba University, P.O. Box 12, Sidi Amar, Annaba, 23000, Algeria ' Laboratory of Automatic and Signals of Annaba (LASA), Department of Electronics, Badji Mokhtar-Annaba University, P.O. Box 12, Sidi Amar, Annaba, 23000, Algeria

Abstract: This paper describes a model predictive controller design to regulate the greenhouse micro-climate, where the controller outputs are computed to optimise the future behaviour of the greenhouse's environment, concerning the setpoint accuracy of the internal temperature and humidity described by Takagi-Sugeno (T-S) model. Modelling procedure is based on two steps. First, the identification of the antecedent part where local linear models are valid using the well-known fuzzy C-means clustering algorithm. Then, recursive least squares (RLS) algorithm is used for consequent part parameters adaptation. An adaptive T-S fuzzy model is considered within the control scheme for prediction of the future greenhouse behaviour. The main way of controlling the greenhouse micro-climate is to use heating and ventilation to regulate both internal temperature and humidity. The simulation results show that the proposed approach maintains successfully both temperature and humidity within the greenhouse around the desired set points in the presence of disturbances. The simulation results are compared between MPC controller based on T-S fuzzy model and MPC based on a single linear model.

Keywords: adaptive fuzzy modelling; greenhouse; predictive control; adaptive metric FCM; Kalman filter.

DOI: 10.1504/IJAAC.2018.088604

International Journal of Automation and Control, 2018 Vol.12 No.1, pp.108 - 125

Received: 02 Aug 2016
Accepted: 14 Oct 2016

Published online: 30 Oct 2017 *

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