基于TSA的非线性神经网络预测控制

doi:10.3969/j.issn.0255-8297.2018.05.014

应用科学学报 ›› 2018, Vol. 36 ›› Issue (5): 870-878.doi: 10.3969/j.issn.0255-8297.2018.05.014

• 控制与系统 • 上一篇

基于TSA的非线性神经网络预测控制

姜雪莹¹, 施惠元^1,2, 苏成利¹, 李平^1,2

1. 辽宁石油化工大学信息与控制工程学院, 辽宁抚顺 113001;
2. 西北工业大学自动化学院, 西安 710072

收稿日期:2017-07-28 修回日期:2018-03-13 出版日期:2018-09-30 发布日期:2018-09-30
通信作者: 施惠元,博士生,研究方向:工业先进过程控制、智能优化和预测控制的研究与应用等,E-mail:shy723915@126.com E-mail:shy723915@126.com
基金资助:
国家自然科学基金（No.61673199）；辽宁省自然科学基金（No.2013020024，No.20180550905）；辽宁省高校人才培养计划项目（No.LJQ2015061）资助

Nonlinear Neural Network Predictive Control Based on Tree and Seed Algorithm

JIANG Xue-ying¹, SHI Hui-yuan^1,2, SU Cheng-li¹, LI Ping^1,2

1. School of Information and Control Engineering, Liaoning Shihua University, Fushun 113001, Liaoning Province, China;
2. School of Automation, Northwestern Polytechnical University, Xi'an 710072, China

Received:2017-07-28 Revised:2018-03-13 Online:2018-09-30 Published:2018-09-30

摘要/Abstract

摘要： 针对现有非线性预测控制方法在线递推控制律时求解非线性方程的困难，提出一种基于树和种子算法（tree and seed algorithm，TSA）的非线性神经网络预测控制算法.该算法采用径向基函数（radical basis function，RBF）神经网络建立非线性系统的过程模型，并将该模型作为预测模型，可以有效逼近系统的过程特性.在此基础上，通过该模型递推非线性系统的预测输出值，并设计具有约束的二次型性能指标.利用TSA优化该性能指标，不断在线搜索非线性预测控制系统的最优控制律，避免采用直接递推的方式求解复杂非线性优化问题，减轻了系统的计算负担.生化发酵过程仿真对比结果表明，该算法具有很强的跟踪和抗干扰能力.

关键词: 径向基函数, 预测控制, 树和种子算法, 非线性优化, 生化发酵

Abstract: Because present nonlinear predictive control methods are difficult to solve the nonlinear equation online, a nonlinear neural network predictive control scheme based on tree and seed algorithm(TSA)is proposed in this paper. In this scheme, a process model of the nonlinear system is firstly built up based on radical basis function(RBF)neural networks, and regarded as a predictive model to approximate the process performance of system. Then the predictive output is derived by this model and the quadratic performance index under constrains is designed. And the optimal control law of the nonlinear predictive control system can be online searched with TSA under the performance index. Thus, the proposed scheme can avoid the direct derivation of the control law in complex nonlinear optimization problems and reduce the computational burden. Simulation results of biochemical fermentation process show that the proposed control scheme performs excellent tracking and anti-disturbance abilities.

Key words: predictive control, biochemical fermentation, nonlinear optimization, radical basis function (RBF), tree and seed algorithm (TSA)

中图分类号:

P751.1

姜雪莹, 施惠元, 苏成利, 李平. 基于TSA的非线性神经网络预测控制[J]. 应用科学学报, 2018, 36(5): 870-878.

JIANG Xue-ying, SHI Hui-yuan, SU Cheng-li, LI Ping. Nonlinear Neural Network Predictive Control Based on Tree and Seed Algorithm[J]. Journal of Applied Sciences, 2018, 36(5): 870-878.

参考文献

[1] Muske K R, Badgwell T A. Disturbance modeling for offset-free linear model predictive control[J]. Journal of Process Control, 2002, 12(5):617-632.
[2] Maeder U, Borrelli F, Manfred M. Linear offset-free model predictive control[J]. Automatica, 2009, 45(10):2214-2222.
[3] Shi H Y, Su C L, Cao J T, Song Y L, Li N B. Incremental multivariable predictive functional control and its application in a gas fractionation unit[J]. Journal of Central South University, 2015, 22(12):4653-4668.
[4] Tatjewski P. Advanced control of industrial processes[M]. London:Springer, 2007.
[5] 黄骅,何德峰,俞立. 基于多面体描述系统的鲁棒非线性预测控制[J]. 自动化学报,2012, 38(12):1906-1912. Huang H, He D F, Yu L. Robust nonlinear predictive control based on ploytopic description systems[J]. Acta Automatica Sinica, 2012, 38(12):1906-1912. (in Chinese)
[6] He D, Wang L, Yu L. Multi-objective nonlinear predictive control of process systems:a dualmode tracking control approach[J]. Journal of Process Control, 2015, 25:142-151.
[7] Shi H Y, Su C L, Cao J T, Li P, Liang J P, Zhong G C. Nonlinear adaptive predictive functional control based on the Takagi-Sugeno model for average cracking outlet temperature of the ethylene cracking furnace[J]. Industrial Engineering Chemistry Research, 2015, 54(6):1849-1860.
[8] Rankovi V, Radulovi J, Grujovi N, Divac D. Neural network model predictive control of nonlinear systems using genetic algorithms[J]. International Journal of Computers Communications & Control, 2014, 7(3):540-549.
[9] Araújo R D B, Coelho A A R. Filtered predictive control design using multi-objective optimization based on genetic algorithm for handling offset in chemical processes[J]. Chemical Engineering Research & Design, 2017, 117:265-273.
[10] Lee S M, Kim H, Myung H. Cooperative particle swarm optimization-based model predictive control for multi-robot formation[J]. Journal of Institute of Control, 2013, 19(5):429-434.
[11] Xu F, Chen H, Gong X, Mei Q. Fast nonlinear model predictive control on FPGA using particle swarm optimization[J]. IEEE Transactions on Industrial Electronics, 2015, 63(1):310-321.
[12] Karaboga D, Basturk B. A powerful and efficient algorithm for numerical function optimization:artificial bee colony (ABC) algorithm[J]. Journal of Global Optimization, 2007, 39(3):459-471.
[13] Afshar M H. Partially constrained ant colony optimization algorithm for the solution of constrained optimization problems:application to storm water network design[J]. Advances in Water Resources, 2007, 30(4):954-965.
[14] Li Y, Shen J, Lee K Y, Liu X. Offset-free fuzzy model predictive control of a boiler-turbine system based on genetic algorithm[J]. Simulation Modelling Practice & Theory, 2012, 26:77-95.
[15] 苏成利,吴云,刘晓琴. 一种基于PSO的自适应神经网络预测控制[J]. 控制工程,2009, 16(4):454-457. Su C L, Wu Y, Liu X Q. Adaptive neural network predictive control based on PSO algorithm[J]. Control Engineering, 2009, 16(4):454-457.(in Chinese)
[16] Sahed O A, Kara K, Benyoucef A, Hadjili M. An efficient artificial bee colony algorithm with application to nonlinear predictive control[J]. International Journal of General Systems, 2016, 45(4):1-25.
[17] 王娟,刘明治. 蚁群算法滚动优化的LS-SVM预测控制研究[J]. 控制与决策,2009, 24(7):1087-1091. Wang J, Liu M Z. Study of LS-SVM predictive control using ant colony algorithm rolling optimization[J]. Control and Decision, 2009, 24(7):1087-1091.(in Chinese)
[18] Kiran M S. TSA:tree-seed algorithm for continuous optimization[J]. Expert Systems with Applications, 2015, 42(19):6686-6698.
[19] 王令群,郑应平,潘石柱. 基于RBF神经网络预测模型的VLSI生产线智能控制算法[J]. 控制与决策,2006, 21(3):336-338. Wang L Q, Zheng Y P, Pan S Z. Intelligent control algorithm for VLSI manufacturing line based on RBF neural network predictive model[J]. Control and Decision, 2006, 21(3):336-338. (in Chinese)
[20] Henson M A, Seborg D E. An internal model control strategy for nonlinear systems[J]. Aiche Journal, 1991, 37(7):1065-1081.
[21] 王俊龙. 基于支持向量机建模的非线性预测控制研究[D]. 北京:北京交通大学,2014.
[22] 蓝玉龙. 计算机性能和成本研究[J]. 沿海企业与科技,2003(3):39-41. Lan Y L. Computer performance and cost research[J]. Coastal Enterprises and Science & Technology, 2003(3):39-41.(in Chinese)

基于TSA的非线性神经网络预测控制

Nonlinear Neural Network Predictive Control Based on Tree and Seed Algorithm

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 13

编辑推荐

Metrics

本文评价

[1]	魏巍, 全海燕. 基于单形进化的径向基网络训练算法[J]. 应用科学学报, 2019, 37(4): 459-468.
[2]	王德明, 隋修武, 张杨, 万凯新, 石峰. 基于DMA与改进GPC算法的超细缝合线直径控制技术[J]. 应用科学学报, 2019, 37(3): 349-358.
[3]	姜雪莹, 苏成利, 施惠元, 李平, 刘思雨. 采用多变量RBF神经网络的非线性内部迭代预测控制[J]. 应用科学学报, 2018, 36(4): 698-710.
[4]	王建宏1，许莺1，熊朝华1，徐波2. 故障条件下子空间预测控制的对偶分解[J]. 应用科学学报, 2014, 32(6): 652-660.
[5]	田中大，高宪文，李琨. 网络控制系统的自适应预测控制[J]. 应用科学学报, 2013, 31(3): 303-308.
[6]	王建宏，王道波. 子空间预测控制中的椭球优化及其应用[J]. 应用科学学报, 2010, 28(4): 424-429.
[7]	宫新保, 周希朗. 基于免疫聚类和遗传算法的RBF网络设计方法[J]. 应用科学学报, 2004, 22(1): 81-84.
[8]	邹涛, 闫志恒, 李少远. 基于PC机平台的多变量预测控制软件开发[J]. 应用科学学报, 2003, 21(3): 296-301.
[9]	唐斌, 胡光锐. 基于免疫神经网络的雷达天线扫描方式的识别[J]. 应用科学学报, 2003, 21(1): 36-38.
[10]	杨涛, 王学雷, 邵惠鹤. 基于在线训练RBF神经网络的混沌系统辨识研究[J]. 应用科学学报, 2002, 20(2): 160-164.
[11]	李一波, 黄小原. 基于RBFNN和GA的重叠峰分辨新技术[J]. 应用科学学报, 2002, 20(1): 99-103.
[12]	陈增强, 袁著祉. PI型有约束后移限位预测控制器[J]. 应用科学学报, 1998, 16(2): 229-233.
[13]	陈增强, 袁著祉. PI型扩展预测自适应控制器及其在造纸过程中的应用研究[J]. 应用科学学报, 1996, 14(4): 447-452.