IIR system identification using differential evolution with wavelet mutation

Abstract

In this paper an improved version of Differential Evolution (DE) technique called Differential Evolution with Wavelet Mutation (DEWM) is applied to the infinite impulse response (IIR) system identification problem. Instead of fixed value of scaling factor in standard DE, an iteration dependent scaling factor governed by the wavelet function during the mutation process is adopted in the proposed technique. This modification in the mutation process ensures not only the faster searching in the multidimensional search space but also the solution produced is very close to the global optimal solution. Apart from this, the proposed technique DEWM has alleviated from inherent drawbacks of premature convergence and stagnation, unlike Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). The simulation results obtained for some well known benchmark examples justify the efficacy of the proposed system identification approach using DEWM over GA, PSO and DE in terms of convergence speed, plant coefficients and mean square error (MSE) values produced for both the same order and reduced order models of adaptive IIR filters.