Parameter optimization in complex industrial process control based on improved fuzzy-GA

In the modern complex industrial process, the control system generally has characteristics of large inertia, nonlinearity and time-varying, and its control requirements are diverse and uncertain, so it is difficult to smoothly turn the control parameters. To solve the problem, a fuzzy evaluating approach is used to improve the SGA (simple genetic algorithms), and a fuzzy fitness function is designed to divide those control requirements into many evaluating factors with different weights. The fitness of the individual reflects the fuzzy evaluating degree of control result, and shows the approximate degree of control result in an ideal situation. In the paper, we use the fuzzy-GA to optimize the control parameters of temperature controller in tower type fermenter. Experiments and simulations show that control indexes have been improved and this approach can successfully solve parameter optimization problem in complex industrial process.