System Identification Using Gray-Based Adaptive Heterogeneous Multi-Swarm PSO Algorithm: Application to an Irrigation Station

In this paper, a modified methodology to find an optimal T-S fuzzy model based on an extended heterogeneous Multi-swarm PSO (MsPSO) algorithm is developed in order to enhance search ability of the classical MsPSO algorithm. However, this simple MsPSO algorithm search behavior is not always optimal to find the potential solution to a special problem, and it may trap the individuals into local regions leading to premature convergence. To overcome this drawback, two parameter automation strategies (inertia weight and acceleration coefficients) are introduced based on gray relational analysis in MsPSO to guarantee a highly accurate model. The performance of the proposed algorithm is evaluated by adopting standard tests and indicators which are reported in the specialized literature. The numerical results demonstrate that the proposed algorithm is significantly better than the original MsPSO algorithm and the rest of compared algorithms according to mean and standard deviation (std) tests. Next, to further validate the generalization ability of the Improved OptiFel approach, the proposed algorithm is secondly applied on the BoxJenkins Gas Furnace system. Then, the improved OptiFel method is applied to an irrigation station process in order to provide an optimal T-S fuzzy model. Compared to the other existing methods, we achieve the result that the improved OptiFel can generate good fuzzy model with high accuracy and strong generalization ability.