Optimal design for 2-DOF PID controller based on Maximum Entropy Estimation of Distribution Algorithm

Estimation of Distribution Algorithms (EDAs) is new kinds of colony evolution algorithms. It produces its new generation by constructing probability distribution model through counting excellent information of individuals of present colony EDAs first, and then sampling the model. To solve the NP-Hard question as EDAs searching optimum network structure, a new Maximum Entropy Estimation of Distribution Algorithm (MEEDA) is proposed; and the paper puts forward the MEEDA to optimize two degree of freedom PID controller parameters. The simulation results show that the optimal 2-DOF PID controller has simultaneously both the characteristics of command tracking and disturbance rejection, so we can see the simulation verifies the effectiveness of the EDA algorithm.