Quantum genetic algorithm and its application to designing fuzzy neural controller

Aiming at the BP algorithm convergence difficulty for fuzzy neural controller with many parameters, a quantum genetic algorithm is proposed to optimize the parameters of a normalized fuzzy neural controller. In the proposed method, Chromosomes are comprised of qubits, and updated by quantum rotation gates, mutated by quantum non-gates. The probability amplitudes of each qubit are regarded as two coordinate genes, each chromosome contains two gene chains, and each gene chain represents an optimization solution, which can accelerate the convergence process and increase the successful probability. First, the parameters of the normalized fuzzy neural controller are encoded into an individual, and the initial colony is composed of some random individuals, then the global searching is performed by the proposed algorithm. Finally, the designed controller is employed to control an inverted pendulum system, and the simulation results verified the effectiveness of the proposed algorithm.