基于ELM的水泥立磨生料细度ADP控制

doi:10.16182/j.issn1004731x.joss.201611017

系统仿真学报 ›› 2016, Vol. 28 ›› Issue (11): 2764-2770.doi: 10.16182/j.issn1004731x.joss.201611017

基于ELM的水泥立磨生料细度ADP控制

林小峰, 孔伟凯

广西大学,广西南宁 530004

收稿日期:2015-04-08 修回日期:2015-10-18 出版日期:2016-11-08 发布日期:2020-08-13
作者简介:林小峰(1955-), 男, 广西陆川, 学士, 教授,研究方向为复杂系统优化与智能控制; 孔伟凯(1989-), 男, 河北衡水, 硕士生, 研究方向为智能控制。
基金资助:
国家自然科学基金(61364007)

Adaptive Dynamic Programming in Raw Meal Fineness Control of Vertical Mill Grinding Process Based on Extreme Learning Machine

Lin Xiaofeng, Kong Weikai

Guangxi University, Nanning 530004, China

Received:2015-04-08 Revised:2015-10-18 Online:2016-11-08 Published:2020-08-13

摘要/Abstract

摘要： 水泥生产中的立磨粉磨过程具有非线性、强耦合、大滞后等特点,对其进行精确的建模和实现生料细度的控制比较困难。提出一种基于极限学习机(ELM, extreme learning machine)的自适应动态规划(ADP, adaptive dynamic programming)优化控制算法。采用极限学习机建立立磨生料粉磨过程的生料细度预测模型,将其作为ADP算法中的模型网络,并以在线序列极限学习机实现ADP的执行网络和评价网络。结果表明：在仿真意义上,所提算法能够对生料细度进行有效地控制,对立磨稳定生产,降低该生产过程的能耗具有一定理论指导意义。

关键词: 水泥立磨, 生料, 自适应动态规划, 极限学习机

Abstract: The grinding process of vertical mill raw meal in cement industry features nonlinear, strong coupling and long time-delay, which is difficult to model precisely and implement stable control for raw meal fineness. Against the problem, a production index prediction model of vertical mill raw meal grinding process was established using Extreme Learning Machine (ELM). Adaptive dynamic programming (ADP) was used to control the raw meal fineness, whose action and critic networks were implemented by online sequential extreme learning machine. In the meaning of simulation, the results show that the proposed method is valid and helpful to reduce the energy consumption.

Key words: vertical mill, raw meal, Adaptive Dynamic Programming (ADP), Extreme Learning Machine (ELM)

中图分类号:

TP183

林小峰, 孔伟凯. 基于ELM的水泥立磨生料细度ADP控制[J]. 系统仿真学报, 2016, 28(11): 2764-2770.

Lin Xiaofeng, Kong Weikai. Adaptive Dynamic Programming in Raw Meal Fineness Control of Vertical Mill Grinding Process Based on Extreme Learning Machine[J]. Journal of System Simulation, 2016, 28(11): 2764-2770.

参考文献 13

[1]	肖争鸣, 李坚利. 水泥工艺技术 [M]. 北京: 化学工业出版社, 2006. Xiao Z M , Li L J. (Xiao Zhengming, Li Jianli. Cement technology [M]. Beijing, China: Chemical Industry Press, 2006.)
[2]	颜文俊, 秦伟. 水泥立磨流程的建模和控制优化[J]. 控制工程, 2012, 19(6): 929-934.(Yan W J, Qin W.Modeling and Control Optimization in Cement Vertical Roller Mill Process[J]. Control Engineering of China, 2012, 19(6): 929-934.)
[3]	Bellmanr Dreyfuss.Applied dynamic programming Princeton [M]. NJ, USA: Princeton Univ Press, 1962: 25-50.
[4]	Wang F Y, Zhang H G, Liu D R.Adaptive dynamic programming: an introduction[J]. IEEE Computational Intelligence Magazine (S1556-603X), 2009, 8(3): 39-47.
[5]	孙常宝. 立式辊磨机原料磨系统工艺的控制[J]. 散装水泥, 2007 (2): 57-59.(Sun B C.Process Control of Raw Mill System of Vertical Roller Mill[J]. Bulk Cement, 2007 (2): 57-59.)
[6]	宁艳艳, 苑明哲, 王卓. 水泥生料立磨压差的广义预测PID控制[J]. 信息与控制, 2012, 41(3): 378-390.(Ning Y Y, Yuan M Z, Wang Z.Generalized Predictive PID Controller of Differential Pressure in Vertical Roller Mill for Cement-Raw Grinding[J]. Information and Control, 2012, 41(3): 378-383, 390.)
[7]	Huang G B.An Insight into Extreme Learning Machines: Random Neurons, Random Features and Kernels[J]. Cognitive Computation (S1866-9964), 2014(6): 376-390.
[8]	Huang G B, Zhou H, Ding X, et al.Extreme Learning Machine for Regression and Multiclass Classification[J]. IEEE Transactions on Systems, Man, and Cybernetics- Part B: Cybernetics (S2168-2267), 2012, 42(2): 513-529.
[9]	Huang G B, Zhu Q Y, Siew C K.Extreme learning machine: Theory and applications[J]. Neurocomputing (S0925-2312), 2006, 70: 489-501.
[10]	Wang D, Liu D R, Wei Q L, et al.Optimal control of unknown nonaffine nonlinear discrete-time systems based on adaptive dynamic programming[J]. Automatica (S0005-1098), 2012, 48(8): 1825-1832.
[11]	Zhang H G, Zhang X, Luo Y H, et al.An Overview of Research on Adaptive Dynamic Programming[J]. Automatica (S0005-1098), 2013, 39(4): 303-311.
[12]	Werbos P J.ADP: The Key Direction for Future Research in Intelligent Control and Understanding Brain Intelligent[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics (S2168-2267), 2008, 38(4): 898-900.
[13]	Liang N Y, Huang G B, P Saratchandran. A Fast and Accurate On-line Sequential Learning Algorithm for Feedforward Networks[J]. IEEE Transactions on Neural Networks (S1941-0093), 2006, 17(6): 1411-1423.

基于ELM的水泥立磨生料细度ADP控制

Adaptive Dynamic Programming in Raw Meal Fineness Control of Vertical Mill Grinding Process Based on Extreme Learning Machine

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献 13

相关文章 12

编辑推荐

Metrics

本文评价

[1]	党建武, 谭凌. 改进果蝇算法优化加权极限学习机的入侵检测[J]. 系统仿真学报, 2021, 33(2): 331-338.
[2]	魏铭琦, 张天瑞, 高秀秀, 王淑梅. 基于DA-RKELM算法的光伏发电功率预测方法[J]. 系统仿真学报, 2020, 32(10): 2041-2051.
[3]	张小平, 饶盛华, 张铸, 赵轩. 基于混沌果蝇算法的SRM多目标协同优化研究[J]. 系统仿真学报, 2018, 30(7): 2640-2647.
[4]	熊印国. 相对变换KPCA的变压器油击穿电压预测建模[J]. 系统仿真学报, 2018, 30(5): 1657-1664.
[5]	孙玉坤, 李曼曼, 黄永红. 基于改进在线核极限学习机的蓄电池SOC预测[J]. 系统仿真学报, 2018, 30(3): 969-975.
[6]	王田田, 王艳, 纪志成. 基于改进极限学习机的滚动轴承故障诊断[J]. 系统仿真学报, 2018, 30(11): 4413-4420.
[7]	王浩, 王艳, 纪志成. 基于改进极限学习机的风电功率预测仿真研究[J]. 系统仿真学报, 2018, 30(11): 4437-4447.
[8]	徐继亚, 王艳, 纪志成. 基于鲸鱼算法优化WKELM的滚动轴承故障诊断[J]. 系统仿真学报, 2017, 29(9): 2189-2197.
[9]	宋绍剑, 王志浩, 林小峰. 基于SOC的锂动力电池组双向主动均衡控制[J]. 系统仿真学报, 2017, 29(3): 609-617.
[10]	汪鑫, 王艳, 纪志成. 基于改进ELM的永磁同步电机故障诊断算法[J]. 系统仿真学报, 2017, 29(3): 646-653.
[11]	逄珊, 杨欣毅, 林学森. 一种基于量子粒子群优化的极限学习机[J]. 系统仿真学报, 2017, 29(10): 2447-2458.
[12]	李新利, 李楠, 孙愉佳, 卢钢, 闫勇, 刘石. 火焰自由基成像和极限学习机在NOx排放预测中的研究[J]. 系统仿真学报, 2016, 28(5): 1179-1185.