Application of BP neural network intelligent PID controller based on GA in electrode regulator systems of electric arc furnace

Aimed at the characteristics of strong nonlinearity, uncertainty, time-variance and, strong coupling etc for AC electric arc furnace (EAF), and the traditional PID can not achieve desired control effect. The paper proposes a PID control algorithm based on optimized BP neural network using genetic algorithm, which is applied in electrode regulator systems of electric arc furnace to design the optimized controller. The algorithm optimizes the initial weights of BP neural network by using genetic algorithm firstly, and then adjusts the PID parameters by using BP neural network. The simulation indicates that the algorithm is feasible, and unit with intelligent PID controller has better accuracy and dynamic characteristics.