Improved Cerebellar Model Neural Network and Its Application in Time Series Prediction

QIAO Junfei; DONG Jingjiao; LI Wenjing

doi:10.11936/bjutxb2019120017

Journal of Beijing University of Technology > 2021 > 47(6): 598-606. > DOI: 10.11936/bjutxb2019120017

QIAO Junfei, DONG Jingjiao, LI Wenjing. Improved Cerebellar Model Neural Network and Its Application in Time Series Prediction[J]. Journal of Beijing University of Technology, 2021, 47(6): 598-606. DOI: 10.11936/bjutxb2019120017

Citation:

PDF (3619 KB)

Improved Cerebellar Model Neural Network and Its Application in Time Series Prediction

Beijing Key Laboratory of Computational Intelligence and Intelligent System, Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China

More Information

Received Date: December 19, 2019
Available Online: August 03, 2022
Published Date: June 09, 2021

Graphical Abstract

Abstract

Abstract

To tackle the key problem of the conflict between generalization ability and storage space capacity in the cerebellar model neural network (CMNN), an improved cerebellar model neural network-fuzzy membership cerebellar model neural network (FM-CMNN) was proposed to solve the time series prediction problem of nonlinear dynamic systems. First, FM-CMNN, while retaining the address mapping mode of the original CMNN input variables, the bell fuzzy membership function was introduced into the CMNN storage space, so as to improve the generalization ability of the network without increasing the quantization series. Then, the gradient descent algorithm was used to update the weights of the network to improve the approximation strength of the network. Finally, the reliability of the network was verified by the nonlinear time series prediction benchmark experiment and the water quality parameter prediction experiment in sewage treatment.

FullText(HTML)

References (22)

References

[1]	ALBUS J S. A new approach to manipulator control: the cerebellar model articulation controller (CMAC)[J]. Transactions of the ASME Journal of Dynamic Systems, 1975, 97(3): 220-227. http://scitation.aip.org/getabs/servlet/GetabsServlet?prog=normal&id=JDSMAA000097000003000220000001&idtype=cvips&gifs=Yes
[2]	GROMOV V A, SHULGA A N. Chaotic time series prediction with employment of ant colony optimization[J]. Expert Systems with Applications, 2012, 39(9): 8474-8478. doi: 10.1016/j.eswa.2012.01.171
[3]	LI H, ZHANG Z Y. The application of immune genetic algorithm in main steam temperature of PID control of BP network[J]. Physics Procedia, 2012, 24(1): 80-86. http://www.sciencedirect.com/science/article/pii/S1875389212000569
[4]	孙增圻, 邓志东. 类似CMAC的模糊神经网络及其在控制中的应用[J]. 清华大学学报(自然科学版), 1996, 36(5): 17-23. https://www.cnki.com.cn/Article/CJFDTOTAL-QHXB199605003.htm SUN Z Q, DENG Z D. CMAC-like fuzzy neural network and its application to controls[J]. Journal of Tsinghua University (Science and Technology), 1996, 36(5): 17-23. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-QHXB199605003.htm
[5]	邓志东, 孙增圻, 张再兴. 一种模糊CMAC神经网络[J]. 自动化学报, 1995, 21(3): 288-294. https://www.cnki.com.cn/Article/CJFDTOTAL-MOTO503.004.htm DENG Z D, SUN Z Q, ZHANG Z X. A fuzzy CMAC neural network[J]. Acta Automatica Sinica, 1995, 21(3): 288-294. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-MOTO503.004.htm
[6]	WANG Y, HU S S. Robust adaptive tracking control for nonlinear systems based on self-organizing fuzzy CMAC neural networks[J]. Acta Automation Sinica, 2002, 28(6): 984-989. http://www.oalib.com/paper/1515824
[7]	王琳, 郭晨, 李晖. 基于GA学习的模糊小脑模型控制器[J]. 大连海事大学学报, 2000, 26(1): 65-69. doi: 10.3969/j.issn.1006-7736.2000.01.016 WANG L, GUO C, LI H. A fuzzified CMAC controller based on genetic algorithm learning[J]. Journal of Dalian Maritime University, 2000, 26(1): 65-69. (in Chinese) doi: 10.3969/j.issn.1006-7736.2000.01.016
[8]	GUO C, WANG L, LI H, et al. A genetic algorithms learning based fuzzified CMAC controller[C]//Proceedings of the 3rd World Congress on Intelligent Control and Automation. Piscataway: IEEE, 2000: 915-918.
[9]	周旭东, 王国栋. 模糊小脑模型神经网络[J]. 自动化学报, 1998, 24(2): 173-178. https://www.cnki.com.cn/Article/CJFDTOTAL-MOTO802.004.htm ZHOU X D, WANG G D. Fuzzy cerebellar model neural network[J]. Acta Automatica Sinica, 1998, 24(2): 173-178. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-MOTO802.004.htm
[10]	周旭东, 王国栋, 夏吾勇. 自适应遗传算法优化模糊小脑模型[J]. 东北大学学报(自然科学版), 1997, 18(6): 617-620. https://www.cnki.com.cn/Article/CJFDTOTAL-DBDX706.009.htm ZHOU X D, WANG G D, XIA W Y. Adaptive genetic algorithm to optimize the fuzzy cerebellar model[J]. Journal of Northeastern University(Natural Science), 1997, 18(6): 617-620. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-DBDX706.009.htm
[11]	TANG B, LIU G P, GUI W H. Improvement of state feedback controller design for networked control systems[J]. IEEE Transactions on Circuits and Systems Ⅱ: Express Briefs, 2008, 55(5): 464-468. doi: 10.1109/TCSII.2007.914893
[12]	杨波, 程龙. 提高电动加载系统输出平滑的CMAC复合控制[J]. 北京航空航天大学学报, 2013, 39(6): 723-727. https://www.cnki.com.cn/Article/CJFDTOTAL-BJHK201306004.htm YANG B, CHENG L. Improving the output smoothing of the electric loading system based on the CMAC+PD compound control strategy[J]. Journal of Beijing University of Aeronautics and Astronautics, 2013, 39(6): 723-727. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-BJHK201306004.htm
[13]	于士贤, 付兴建. 基于改进CMAC的高阶柔性直线系统跟踪控制[J]. 北京信息科技大学学报(自然科学版), 2018, 33(1): 18-22. https://www.cnki.com.cn/Article/CJFDTOTAL-BJGY201801004.htm YU S X, FU X J. Tracking control based on improved CMAC for high-order flexible linear system[J]. Journal of Beijing Information Science & Technology University, 2018, 33(1): 18-22. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-BJGY201801004.htm
[14]	WANG J, ZHANG C, JING Y. Hybrid CMAC-PID controller in heating ventilating and air-conditioning system[C]//Proceedings of the International Conference on Mechatronics and Automation. Piscataway: IEEE, 2007: 3706-3711.
[15]	LIN C M, CHEN T Y, YEUNG D S. Adaptive filter design using recurrent cerebellar model articulation controller[J]. IEEE Transactions on Neural Networks, 2010, 21(7): 1149-1157. doi: 10.1109/TNN.2010.2050700
[16]	OENTARYO R J, PASQUIER M, QUEK C. RFCMAC: a novel reduced localized neuro-fuzzy system approach to knowledge extraction[J]. Expert Systems with Applications, 2011, 38(10): 12066-12084. doi: 10.1016/j.eswa.2011.02.058
[17]	SU S F, TAO T, HUNG T H. Credit assigned CMAC and its application to online learning robust controllers[J]. IEEE Transactions on Systems man and Cybernetics B-Cybernetics, 2003, 33(3): 202-213. http://europepmc.org/abstract/MED/18238171
[18]	王丽梅, 孙伟. 基于模糊CMAC神经网络的XY平台交叉耦合控制[J]. 沈阳工业大学学报, 2015, 37(2): 121-125. https://www.cnki.com.cn/Article/CJFDTOTAL-SYGY201502001.htm WANG L M, SUN W. Cross-coupled control for XY table based on fuzzy-CMAC neural network[J]. Journal of Shenyang University of Technology, 2015, 37(2): 121-125. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-SYGY201502001.htm
[19]	MACNAB C J B. Preventing overlearning in CMAC by using a short-term memory[J]. International Journal of Fuzzy Systems, 2017, 19(6): 2020-2032. doi: 10.1007/s40815-016-0275-9
[20]	HIDALGO D, MELIN P, CASTILLO O. An optimization method for designing type-2 fuzzy inference systems based on the footprint of uncertainty using genetic algorithms[J]. Expert Systems with Applications, 2012, 39(4): 4590-4598. doi: 10.1016/j.eswa.2011.10.003
[21]	ALMEIDA P M, SIMOES M G. Parametric CMAC networks: fundamentals and application of the a fast convergences neural structure[J]. IEEE Transactions on Industrial Applications, 2003, 39(5): 1551-1557. doi: 10.1109/TIA.2003.816543
[22]	乔俊飞, 鞠岩, 韩红桂. 基于自组织随机权神经网络的BOD软测量[J]. 北京工业大学学报, 2016, 42(10): 1451-1460. doi: 10.11936/bjutxb2016040021 QIAO J F, JU Y, HAN H G. BOD soft-sensing based on SONNRW[J]. Journal of Beijing University of Technology, 2016, 42(10): 1451-1460. (in Chinese) doi: 10.11936/bjutxb2016040021

[1]	ZHANG Jianyu, DAI Yang. Application of Improvement Strategy of Bat Algorithm in Remaining Useful Life Prediction of Rolling Bearings[J]. Journal of Beijing University of Technology, 2023, 49(9): 959-969. DOI: 10.11936/bjutxb2021110017
[2]	ZHANG Jianyu, DAI Yang. Application of Improvement Strategy of Bat Algorithm in Remaining Useful Life Prediction of Rolling Bearings[J]. Journal of Beijing University of Technology, 2023, 49(9): 959-969. DOI: 10.11936/bjutxb2021110017
[3]	LI Wenjing, WANG Xiaoxiao. Time Series Prediction Method Based on Simplified LSTM Neural Network[J]. Journal of Beijing University of Technology, 2021, 47(5): 480-488. DOI: 10.11936/bjutxb2020120032
[4]	GUO Wen, LI Pengfei, BAO Yan, ZHANG Mingju, GAO Yang, WANG Guoquan, LI Rui, DUAN Xianfeng. High-accuracy GPS Monitoring of Riverbed Deformation Due to Shield Tunneling[J]. Journal of Beijing University of Technology, 2020, 46(5): 490-499. DOI: 10.11936/bjutxb2019030019
[5]	NIE Yao, WU Jianjun. An Online Time Series Prediction Method and Its Application[J]. Journal of Beijing University of Technology, 2017, 43(3): 386-393. DOI: 10.11936/bjutxb2015100045
[6]	SONG Yi-min, ZHAI Ya-pu, SUN Tao, LI Jin-he, ZHANG Jia-teng. Interval Analysis Based Accuracy Design of a 3-DOF Rotational Parallel Mechanism( Invited Paper)[J]. Journal of Beijing University of Technology, 2015, 41(11): 1620-1626,1755. DOI: 10.11936/bjutxb2015050096
[7]	QIN Xia, LEI Lei, YAO Xiao-li. Methods to Improve the Generalization of BP Neural Network Applied in Air Pollution Forecasting[J]. Journal of Beijing University of Technology, 2007, 33(8): 849-852.
[8]	XIA Ya-qin, CHEN Wei-sheng, LI Jun-zhi, QIN Fei. Some Advance in Earthquake Prediction[J]. Journal of Beijing University of Technology, 2006, 32(1): 11-14.
[9]	RUAN Xiao-gang, SUN Hai-jun. Research on Encode Influencing Protein Secondary Structure Prediction[J]. Journal of Beijing University of Technology, 2005, 31(3): 229-235.
[10]	Zeng Xiangjiang. The High-accuracy Continuous-wave YAG Laser Power[J]. Journal of Beijing University of Technology, 1998, 24(1): 87-92.

Cited By

Cited by

Periodical cited type(2)

1.	杨彦霞，王普，高学金，高慧慧，齐泽洋. 基于混合双层自组织径向基函数神经网络的优化学习算法. 北京工业大学学报. 2024(01): 38-49 . 本站查看
2.	姜海燕，李竹韵，陈艳. 基于改进小脑模型的sEMG下肢关节力矩预测. 仪器仪表学报. 2022(11): 172-180 .

Other cited types(2)

Get Citation

PDF

XML

Article views (263) PDF downloads (79) Cited by(4)

Turn off MathJax

Article Contents

Abstract

References

Improved Cerebellar Model Neural Network and Its Application in Time Series Prediction