基于遗传算法的压缩空气调压系统变论域模糊PID控制

Variable Domain Fuzzy PID Control for Compressed Air Pressure Regulating System Based on Genetic Algorithm

摘要: 面对压缩空气这样复杂的系统，使用传统的PID控制难以满足控制要求，模糊控制作为一种智能控制方式，将其与PID控制相结合可以提高控制的鲁棒性。本文采用变论域的方法对模糊控制进行改进，在模糊控制规则不变的情况下，根据偏差的变化改变基本论域的大小，从而提高控制的精度。由于模糊PID控制中的模糊控制规则的建立过于依赖经验，具有较强的不确定性，利用遗传算法对模糊控制规则进行优化，通过增加区域筛选操作对算法进行了改进，进而避免算法陷入局部最优而无法获得全局最优解。引入欧几里得距离对模糊控制规则进行分区，通过对区域筛选找出最优解区域。本文选择误差绝对值时间积分性能指标作为目标函数，利用MATLAB建立压缩空气调压系统模型，通过对控制系统进行仿真验证控制方式的可行性。仿真结果表明：与传统PID控制和模糊PID控制相比，基于遗传算法的变论域模糊PID控制对系统的跟随性能指标和抗扰性能指标都有所改善。

Abstract: For the complicated system like compressed air regulating system, it is difficult to satisfy the control requirements by using traditional PID control. Fuzzy control as an intelligent control method can be combined with PID control to improve the robustness of the control. This paper adopts the method of variable domain to improve fuzzy control, which can improve the accuracy of control by changing the size of the basic domain according to the change of error while the fuzzy control rules remain unchanged. Since the establishment of fuzzy control rules in fuzzy PID control relies too much on experience and has strong uncertainty, the genetic algorithm is used to optimize the fuzzy control rules. In order to avoid the algorithm falling into the local optimum and failing to obtain the global optimum solution, we add the region screening operation to improve the algorithm by introducing Euclidean distance to partition the fuzzy control rules by screening the region to find the region where the optimum solution is located. In this paper, the absolute value of the error time integral performance index is selected as the objective function, and the compressed air regulating system is modeled by MATLAB, and the feasibility of the control method is verified by simulation of the control system. The simulation results show that compared with the traditional PID control and fuzzy PID control, the variable domain fuzzy PID control based on genetic algorithm has improved the following performance index and the anti-disturbance performance index of the system.