基于SAPSO-FNN的电动式加载系统控制研究
|
摘要
针对电动式加载系统中减速器带来的非线性等问题,提出了一种基于模拟退火的粒子群算法来优化模糊神经网络PID控制器初始参数的设计方法。该方法采用基于Mamdani模型的模糊神经网络,通过在线BP学习算法对PID控制器参数进行自整定,并结合基于模拟退火的粒子群算法离线调整模糊神经网络初始值。通过仿真与实验,将所设计算法与增量式PID控制器、粒子群-模糊神经网络PID控制器进行对比,证明了所设计的控制器具有良好的稳定性、有效性和快速性。
Aiming at the nonlinearity caused by the use of reducer in electric loading system, a method based on simulated annealing particle swarm optimization algorithm to optimize the initial parameters of fuzzy neural network PID controller is presented. In the method, the fuzzy neural network based on Mamdani model has used to self-tune the PID controller parameters through online BP learning algorithm, and the initial value of fuzzy neural network is adjusted offline with particle swarm optimization algorithm based on simulated annealing. Through simulation and experiment, the comparison among the designed algorithm, the incremental PID controller and particle swarm-fuzzy neural network PID controller proves that the controller designed has good stability, validity and rapidity.
Aiming at the nonlinearity caused by the use of reducer in electric loading system, a method based on simulated annealing particle swarm optimization algorithm to optimize the initial parameters of fuzzy neural network PID controller is presented. In the method, the fuzzy neural network based on Mamdani model has used to self-tune the PID controller parameters through online BP learning algorithm, and the initial value of fuzzy neural network is adjusted offline with particle swarm optimization algorithm based on simulated annealing. Through simulation and experiment, the comparison among the designed algorithm, the incremental PID controller and particle swarm-fuzzy neural network PID controller proves that the controller designed has good stability, validity and rapidity.
引文
[1] 张学成,聂建辉.双导程直线接触偏置蜗杆传动Ⅰ——原理分析[J].北京工业大学学报,2011,37(02):161-166.
[2] 方强.被动式力矩伺服控制系统设计方法及应用研究[D].哈尔滨:哈尔滨工业大学,2006.
[3] 陈峥,齐蓉,林辉.电动加载系统的模糊自适应PID控制研究[J].测控技术,2008(01):60-62.
[4] 张彩云.基于改进PSO算法的模糊神经网络研究[D].哈尔滨:哈尔滨理工大学,2014.
[5] 白国振,俞洁皓.基于改进模糊神经网络的PID参数自整定[J].计算机应用研究,2016,33(11):3358-3363.
[6] 张浩,王永泉,陈花玲,等.基于LabVIEW的运动控制卡对SINAMICSS120控制实现[J].机械研究与应用,2013,26(05):171-173.
[7] 白国振,邱磊,周媛,等.气动加载系统的粒子群-滑模观测器控制[J].控制工程,2017,24(11):2324-2331.
[8] 王瑞东,赵晓蓓.舵机电动力加载系统的研究[J].科学技术与工程,2007(22):5915-5917.
[9] 何春梅,叶有培.一般输入的折线模糊神经网络对模糊函数的通用逼近[J].模式识别与人工智能,2009,22(03):481-487.
[10] 刘金琨.先进PID控制MATLAB仿真[M].2版.北京:电子工业出版社,2004:1-10.
[11] Faa-Jeng Lin,Chih-Hong Lin.A Permanent-magnet Synchronous Motor Servo Drive Using Self-constructing Fuzzy Neural Network Controller[J].IEEE Transactions on Energy Conversion,2004,19(01):66-72.
[12] 孙海蓉.模糊神经网络的研究及其应用[D].北京:华北电力大学,2006.
[13] Eberhart R,Kennedy J.A New Optimizer Using Particle Swarm Theory[C] //IEEE.Proceedings of the Sixth International Symposium on Micro Machine and Human Science.New York:IEEE,1995:39-43.
[14] Clerc M,Kennedy J.The Particle Swarm-explosion,Stability,and Convergence in Multidimensional Complex Space[J].IEEE Transactions on Evolutionary Computation,2002,6 (01):58-73.
[15] Mirjalili S A,Hashim S Z M,Sardroudi H M.Training Feedforward Neural Networks Using Hybrid Particle Swarm Optimization and Gravitational Search Algorithm[J].Applied Mathematics and Computation,2012,218(22):11125-11137.
[2] 方强.被动式力矩伺服控制系统设计方法及应用研究[D].哈尔滨:哈尔滨工业大学,2006.
[3] 陈峥,齐蓉,林辉.电动加载系统的模糊自适应PID控制研究[J].测控技术,2008(01):60-62.
[4] 张彩云.基于改进PSO算法的模糊神经网络研究[D].哈尔滨:哈尔滨理工大学,2014.
[5] 白国振,俞洁皓.基于改进模糊神经网络的PID参数自整定[J].计算机应用研究,2016,33(11):3358-3363.
[6] 张浩,王永泉,陈花玲,等.基于LabVIEW的运动控制卡对SINAMICSS120控制实现[J].机械研究与应用,2013,26(05):171-173.
[7] 白国振,邱磊,周媛,等.气动加载系统的粒子群-滑模观测器控制[J].控制工程,2017,24(11):2324-2331.
[8] 王瑞东,赵晓蓓.舵机电动力加载系统的研究[J].科学技术与工程,2007(22):5915-5917.
[9] 何春梅,叶有培.一般输入的折线模糊神经网络对模糊函数的通用逼近[J].模式识别与人工智能,2009,22(03):481-487.
[10] 刘金琨.先进PID控制MATLAB仿真[M].2版.北京:电子工业出版社,2004:1-10.
[11] Faa-Jeng Lin,Chih-Hong Lin.A Permanent-magnet Synchronous Motor Servo Drive Using Self-constructing Fuzzy Neural Network Controller[J].IEEE Transactions on Energy Conversion,2004,19(01):66-72.
[12] 孙海蓉.模糊神经网络的研究及其应用[D].北京:华北电力大学,2006.
[13] Eberhart R,Kennedy J.A New Optimizer Using Particle Swarm Theory[C] //IEEE.Proceedings of the Sixth International Symposium on Micro Machine and Human Science.New York:IEEE,1995:39-43.
[14] Clerc M,Kennedy J.The Particle Swarm-explosion,Stability,and Convergence in Multidimensional Complex Space[J].IEEE Transactions on Evolutionary Computation,2002,6 (01):58-73.
[15] Mirjalili S A,Hashim S Z M,Sardroudi H M.Training Feedforward Neural Networks Using Hybrid Particle Swarm Optimization and Gravitational Search Algorithm[J].Applied Mathematics and Computation,2012,218(22):11125-11137.