Decentralized H∞ control for roller kiln temperature based on off-policy Q-learning
Roller kiln sintering process is the key to the preparation of cathode materials,and controling kiln temperature precisely is extremely important to reducing energy consumption,improving materials performance and heightening unity of products.However,unknown internal system dynamics,severe energy exchange between different temperature regions and frequent disturbance in the roller kiln make it very difficult to control kiln temperature accurately.A novel decentralized H∞ control method of roller kiln temperature is proposed.First,a bounded function is constructed to describe the maxium effects caused by temperature coupling to the control performance of regions in the roller kiln,the minimax problems of different regions can be established based on bounded function above,thus,the large-scale H∞control problem of the whole roller kiln is turned to the small-scale H∞ control problem of regions.The target roller kiln temperature H∞ control policy can be obtained by solving minimax problems above,so the control method is competeley decentralized.Then,the off-policy Q-learning algorithm is used to learn the roller kiln temperature decentralizedH control policy.Simulation result shows that the proposed control method can not only control roller kiln temperature to reach the set point precisely,but also overcome the negative effects caused by disturbance.
roller kilntemperature controlreinforcement learningoff-policy Q-learningH∞ controldecentralized control
NETL
NSTL
万方数据
