A meta-inspired algorithm-based fuzzy model for wind speed prediction using chaotic time series and phase space reconstruction

This study proposes a phase space reconstruction-based fuzzy identification method to improve the prediction accuracy of chaotic time series. First, the delay time and embedding dimension are determined using mutual information and the Cao method, respectively, to reconstruct the phase space. Second, the particle swarm optimization algorithm is applied to optimize the membership function parameters of the T-S fuzzy model, enabling a more rational partition of the premise space. Finally, the conclusion parameters of the fuzzy model are identified via the recursive least squares method. Experimental validation using two benchmark chaotic time series and a real-world wind speed series demonstrates that the proposed model achieves high prediction accuracy. The results confirm the effectiveness and practical applicability of the method for modeling and forecasting chaotic systems.