基于自构建小波神经网络的内模控制Internal Model Control Based on Self-constructing Wavelet Neural Network
赵彬宏,王建鹏,王元元
摘要(Abstract)：
针对非线性被控过程,提出了一种自构建小波神经网络内模控制方法,自构建神经网络算法包括结构学习和参数学习。结构学习过程中,采用相似性度量法来确定是否需要增加新的小波基以满足辨识需求,根据小波基对网络输出的影响程度判断是否需要删除该小波基,参数学习采用自适应调节步长的梯度下降法以提高学习速率。将该神经网络与内模控制相结合,使得辨识被控过程内部模型和控制器模型的神经网络能够动态决定小波基的个数,进而改善了控制系统的动态性能和鲁棒性,仿真结果表明了所提方法的有效性。
关键词(KeyWords)： 自构建;小波神经网络;相似性度量;梯度下降法
基金项目(Foundation): 山西省重点研发计划(201703D111027)
作者(Author): 赵彬宏,王建鹏,王元元
参考文献(References)：
- [1]夏光,陈无畏,赵林峰,等.平衡重式叉车底盘小波网络动态逆内模控制[J].机械工程学报,2015,51(18):126-135.
- [2]HE Y,ZHENG S,FANG J.Start-up current adaptive control for sensorless high-speed brushless DC motors based on inverse system method and internal mode controller[J].Chinese Journal of Aeronautics,2017,30(1):358-367.
- [3]张新良,朱琳,郭晓迪.一种频率依赖性迟滞的神经网络内模控制[J].测控技术,2016,35(9):52-54.
- [4]HSU C.Adaptive growing-and-pruning neural network control for a linear piezoelectric ceramic motor[J].Engineering Applications of Artificial Intelligence,2008,21(8):1153-1163.
- [5]LIN C,XU Y.A self-adaptive neural fuzzy network with group-based symbiotic evolution and its prediction applications[J].Fuzzy Sets and Systems,2006,157(8):1036-1056
- [6]HASSEN M,MOHAMED C,NABIL D.Variable structure neural networks for adaptive control of nonlinear systems using the stochastic approximation[J].Simulation Modelling Practice and Theory,2006,14(7):1000-1009.
- [7]CHENG K.Auto-structuring fuzzy neural system for intelligent control[J].Journal of the Franklin Institute,2009,346(3):267-288.
- [8]赵志诚,王元元,刘志远.一种自构建神经网络的内模控制方法[J].控制工程,2014,21(1):111-115.
- [9]曾令梦,高强,侯远龙.基于自构建神经网络的舰载火箭炮内模控制[J].火炮发射与控制学报,2017,38(4):40-44.
- [10]LEE C,LIN C,CHEN H.A self-constructing fuzzy CMAC model and its applications[J].Information Sciences,2007,177(1):264-280.