电子设计工程
電子設計工程
전자설계공정
ELECTRONIC DESIGN ENGINEERING
2012年
4期
63-66
,共4页
粒子群优化算法%神经网络%比例一积分一微分控制器%参数优化
粒子群優化算法%神經網絡%比例一積分一微分控製器%參數優化
입자군우화산법%신경망락%비례일적분일미분공제기%삼수우화
Particle Swarm Optimization algorithm neural networks PID controller parameter optimization
针对传统PID控制系统参数整定过程存在的在线整定困难和控制品质不理想等问题,结合BP神经网络自学习和自适应能力强等特点,提出采用BP神经网络优化PID控制器参数。其次,为了加快BP神经网络学习收敛速度,防止其陷入局部极小点,提出采用粒子群优化算法来优化BP神经网络的连接权值矩阵。最后,给出了PSO—BP算法整定优化PID控制器参数的详细步骤和流程图。并通过一个PID控制系统的仿真实例来验证本文所提算法的有效性。仿真结果证明了本文所提方法在控制品质方面优于其它三种常规整定方法。
針對傳統PID控製繫統參數整定過程存在的在線整定睏難和控製品質不理想等問題,結閤BP神經網絡自學習和自適應能力彊等特點,提齣採用BP神經網絡優化PID控製器參數。其次,為瞭加快BP神經網絡學習收斂速度,防止其陷入跼部極小點,提齣採用粒子群優化算法來優化BP神經網絡的連接權值矩陣。最後,給齣瞭PSO—BP算法整定優化PID控製器參數的詳細步驟和流程圖。併通過一箇PID控製繫統的倣真實例來驗證本文所提算法的有效性。倣真結果證明瞭本文所提方法在控製品質方麵優于其它三種常規整定方法。
침대전통PID공제계통삼수정정과정존재적재선정정곤난화공제품질불이상등문제,결합BP신경망락자학습화자괄응능력강등특점,제출채용BP신경망락우화PID공제기삼수。기차,위료가쾌BP신경망락학습수렴속도,방지기함입국부겁소점,제출채용입자군우화산법래우화BP신경망락적련접권치구진。최후,급출료PSO—BP산법정정우화PID공제기삼수적상세보취화류정도。병통과일개PID공제계통적방진실례래험증본문소제산법적유효성。방진결과증명료본문소제방법재공제품질방면우우기타삼충상규정정방법。
Due to the strong self-learning and self-adaptive ability of BP neural networks, it can be used to solve the problems that existing in traditional PID controller parameters tuning methods. In order to accelerate the convergence speed of BP neural network and prevent it from falling into local minimum point, the particle swarm optimization algorithm is proposed to optimize the connection weight matrix of BP neural networks. At last, detailed steps and flow chart of the proposed method are given and the simulation results demonstrated that the control quality of the proposed method is superior to the conventional methods.