A Self-optimal Fuzzy Logic Controller Based on Association Rules Mining to Ball Mill Pulverizing System

Ball mill pulverizing system is one of the major assistant systems in a thermal power plant and it is a multi-variable and strong coupling system with nonlinearity, large delay and time-varying. To control it work stably and efficiently, a self-optimal fuzzy logic controller based on association rule mining is proposed in the paper. In the controller, the self-optimizing algorithm can adjust the controller set value to keep the ball mill pulverizing system working at the optimum point all alone, and the fuzzy logic rules are derived by the association rules mining algorithm, which uses the antecedent ergodicity and the single consequent link methods. Moreover, the consequent strength measure is presented in the paper to estimate the mined rules. Simulations results verify that the controller can control the ball mill pulverizing system effectively and has higher control quality.