Self-tuning Fuzzy Logic Control of Greenhouse Temperature using Real-coded Genetic Algorithm

Abstract

The greenhouse temperature model is built based on the balance of the energy. A new real-coded genetic algorithm (GA) for self-tuning fuzzy logic control (FLC) of greenhouse temperature is proposed, in which, an arithmetical crossover operator, a ranking-based reproduction operator and a non-uniform mutation operator are adopted. The Gaussian input membership functions for the error and the change-in-error of the temperature of FLC is optimized by GA in terms of the root-mean-square error (RMSE) with setpoint and input energy. Compared with the basic fuzzy control, the tuned FLC gives better performance in terms of improving control precision and saving energy