Identification of Wiener-Hammerstein Cascaded System Using Hybrid Backtracking Search Algorithm with Wavelet Mutation

In this paper, a nonlinear three-stage cascaded Wiener-Hammerstein (W-H) system with polynomial nonlinearities of the different order has been identified efficiently. A hybrid Backtracking Search Algorithm with Wavelet Mutation (BSA-WM) has been applied for the identification of the parameters associated with the overall system. The original Backtracking Search Algorithm has been modified with wavelet-based mutation strategy to incorporate a perfect balance between the exploration of the new search region and the exploitation of the already searched regions in the optimization process that enhances the overall accuracy of identification. The statistical inferences of the estimated parameters and the objective function have been reported to justify the effectiveness of the employed identification approach.