An optimized method for electric power system harmonic measurement based on back-propagation neural network and modified genetic algorithm

In this paper, according to the respective performance of genetic algorithm and neural network, the authors proposed a new method, based on the model of multilayered feed forward neural network (MLFNN), and it is used to simultaneously measure amplitude and phase angle of harmonic, i.e., genetic algorithm and back-propagation neural network (GABPNN). In this algorithm, the new coding scheme of the global optimization of the weight distribution of neural network fusing with genetic algorithm is designed; fitness function, crossover and mutation are improved. The training method and training samples in the neural network are presented using 3rd harmonic as an example. And simulation experiments are performed using Matlab. The simulation results shows that the proposed method has higher precision and flexibility in real time harmonic measurement and the proposed method has no restrict limitation to the samples number. The off-line trained GABPNN may suit for the occasion where the harmonic source is constant.