Adaptive Control of Nonlinear Systems Based on Quasi-ARX Multilayer Learning Network Models
-
摘要: 建立了准ARX多层学习网络预测模型,并用于非线性系统自适应控制问题.该模型的内核部分为一个改进的神经模糊网络(NFNs):一部分为三层非线性网络结构,采用自联想网络进行离线训练;另一部分为三层NFNs,采取在线调整.据此对参数进行分类,给出相应调整算法. 然后,基于模型宏观结构的优势给出控制器设计方案.仿真分析给出该建模方法的有效性.Abstract: A quasi-ARX multilayer learning network prediction model was established and applied to the adaptive control of nonlinear systems. The kernel of the model is an improved neuro-fuzzy network: one part is a 3-layer nonlinear network with an off-line training self-associative network, the other part is a 3-layer neuro-fuzzy network adjusted online. Accordingly, the parameters were classified and the corresponding estimation algorithms were given. Then, the controller design scheme was proposed based on the advantages of the macrostructure of the model. Simulation analysis verifies the effectiveness of the proposed model.
-
Key words:
- quasi-ARX model /
- multilayer learning network /
- adaptive control
-
[1] NO L J P, KERSCHEN G. Nonlinear system identification in structural dynamics: 10 more years of progress[J].Mechanical Systems and Signal Processing,2017,〖STHZ〗 83: 2-35. [2] 芦泽阳, 李树江, 王向东. 采用RBF网络的喷雾机喷杆自适应动态面跟踪控制[J]. 应用数学和力学, 2019,40(7): 801-809.(LU Zeyang, LI Shujiang, WANG Xiangdong. Adaptive RBF-network dynamic surface tracking control of sprayer boom systems[J]. Applied Mathematics and Mechanics,2019,40(7): 801-809.(in Chinese)) [3] SUTRISNO I, JAMI’IN M A, HU J, et al. A self-organizing quasi-linear ARX RBFN model for nonlinear dynamical systems identification[J]. SICE Journal of Control, Measurement, and System Integration,2016,9(2): 70-77. [4] LJUNG L. System Identification: Theory for the User [M]. 2nd ed. Englewood Cliffs, NJ: Prentice-Hall, 1999. [5] HU J, KUMAMARU K, HIRASAWA K. A quasi-ARMAX approach to modelling of non-linear systems[J]. International Journal of Control,2001,74(18): 1754-1766. [6] NARENDRA K S, PARTHASARATHY K. Identification and control of dynamical systems using neural networks[J]. IEEE Transactions on Neural Networks,1990,1(1): 4-27. [7] YOUNG P C, MCKENNA P, BRUUN J. Identification of non-linear stochastic systems by state dependent parameter estimation[J]. International Journal of Control,2001,74(18): 1837-1857. [8] WANG L, CHENG Y, HU J L. Stabilizing switching control for nonlinear system based on quasi-ARX RBFN model[J]. IEEJ Transactions on Electrical and Electronic Engineering,2012,7(4): 390-396. [9] JANOT A, YOUNG P C, GAUTIER M. Identification and control of electro-mechanical systems using state-dependent parameter estimation[J]. International Journal of Control,2017,〖STHZ〗 90(4): 643-660. [10] XU W, PENG H, ZENG X, et al. Deep belief network-based AR model for nonlinear time series forecasting[J]. Applied Soft Computing,2019,77: 605-621. [11] HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science,2006,313(5786): 504-507. [12] WANG L, CHENG Y, HU J, et al. Nonlinear system identification using quasi-ARX RBFN models with a parameter-classified scheme[J]. Complexity,2017,2017: 1-12. [13] SRIVASTAVA N, HINTON G, KRIZHEVSKY A, et al. Dropout: a simple way to prevent neural networks from overfitting[J]. Journal of Machine Learning Research,2014,15(1): 1929-1958. [14] KUREMOTO T, KIMURA S, KOBAYASHI K, et al. Time series forecasting using a deep belief network with restricted Boltzmann machines[J]. Neurocomputing,2014,137: 47-56. [15] SCHMIDHUBER J. Deep learning in neural networks: an overview[J]. Neural Networks,2015,61: 85-117. [16] LI D, KANG T, HU J, et al. Quasi-linear recurrent neural network based identification and predictive control[C]//2018 International Joint Conference on Neural Networks (IJCNN) . 2018: 1-6. [17] HU J, HIRASAWA K, KUMAMARU K. Adaptive predictor for control of nonlinear systems based on neurofuzzy models[C]//1999 European Control Conference (ECC) . Karlsruhe, Germany, 1999.
点击查看大图
计量
- 文章访问数: 902
- HTML全文浏览量: 146
- PDF下载量: 512
- 被引次数: 0