基于改进PDF技术的间歇过程NFM模型

doi:10.11949/j.issn.0438-1157.20151922

化工学报 ›› 2016, Vol. 67 ›› Issue (3): 998-1007.DOI: 10.11949/j.issn.0438-1157.20151922

基于改进PDF技术的间歇过程NFM模型

付钊, 贾立

上海大学机电工程与自动化学院自动化系, 上海市电站自动化重点实验室, 上海 200072

收稿日期:2015-12-17 修回日期:2015-12-19 出版日期:2016-03-05 发布日期:2016-01-12
通讯作者: 贾立
基金资助:
国家自然科学基金项目(61374044);上海市科委国际合作项目(12510709400);上海市教委创新重点项目(14ZZ088);2013年度上海市人才发展基金项目。

Improved PDF technology based NFM for batch process

FU Zhao, JIA Li

Shanghai Key Laboratory of Power Station Automation Technology, Department of Automation, School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200072, China

Received:2015-12-17 Revised:2015-12-19 Online:2016-03-05 Published:2016-01-12
Contact: 67
Supported by:
supported by the National Natural Science Foundation of China (61374044), the Shanghai Science Technology Commission (12510709400), the Shanghai Municipal Education Commission (14ZZ088) and the Shanghai Talent Development Plan 2013.

摘要/Abstract

摘要：

间歇过程是一类具有典型复杂非线性特性的生产过程,可以利用模糊神经网络(NFM)建立其输入输出的非线性映射关系。在前期的研究中曾提出过基于概率密度函数(PDF)技术的模型训练方法,成功解决了传统的基于MSE准则训练方法模型泛化能力弱的问题,但又产生了概率密度难以估计及目标PDF未知时模型性能不稳定的问题。针对这两个问题,引入了新的概率密度窗宽估计方法,并提出了在目标PDF未知时采用PDF预估器及其收缩策略的算法。仿真实验表明:该方法能够保证足够的概率密度估计精度和模型预测性能。

关键词: 间歇过程, 神经模糊模型, 概率密度函数, 收缩策略, 算法, 预测

Abstract:

Batch process is an typical nolinear production process and can be simulated by a neuro-fuzzy model (NFM). In the previous research, a new model training method called PDF technology was proposed to successfully conquer the weak generalization ability which caused by the MSE rule based model training. But the density function is hard to estimate and the trained model are not stable when the target PDF can not given. To solve these problems, a new window width estimation method is introduced and also a contraction strategy with a PDF predictor is proposed when the target can not be given. Simulation results demonstrate that the proposed methods can get a more accurate density estimation and a more excellent model prediction ability.

Key words: batch process, neuro-fuzzy model, probability density function, contraction strategy, algorithm, prediction

中图分类号:

TP273

付钊, 贾立. 基于改进PDF技术的间歇过程NFM模型[J]. 化工学报, 2016, 67(3): 998-1007.

FU Zhao, JIA Li. Improved PDF technology based NFM for batch process[J]. CIESC Journal, 2016, 67(3): 998-1007.

参考文献 21

[1]	陆宁云, 王福利, 高福荣, 等. 间歇过程的统计建模与在线监测[J]. 自动化学报, 2006, 32 (3): 400-410. LU N Y, WANG F L, GAO F R, et al. Statistical modeling and online monitoring for batch processes[J]. Acta Automatic Sinica, 2006, 32 (3): 400-410.
[2]	杨志才.化工生产过程中的间歇过程——原理、工艺及设备[M]. 北京: 化学工业出版社, 2001: 5-12. YANG Z C. Batch Process in Chemical Engineering— Principle, Technology and Equipment[M]. Beijing: Chemical Industry Press, 2001: 5-12.
[3]	侯忠生. 数据驱动控制理论及方法的回顾和展望[J]. 自动化学报, 2009, 35 (6): 651-654. HOU Z S. On data-driven control theory: the state of the art and perspective[J]. Acta Automatic Sinica, 2009, 35 (6): 651-654.
[4]	丛爽. 神经网络、模糊系统及其在运动控制中的应用[M]. 合肥: 中国科学技术大学出版社, 2001: 30-42. CONG S. Neural Network, Fuzzy System and Its Application in Motion Control[M]. Hefei: University of Science & Technology China Press, 2001: 30-42
[5]	HAYASHI Y, NAKAI M. Automated exaction of fuzzy IF-THEN rules using neural networks[J]. Transactions of the Institute of Electric Engineers of Japan, 1990, 110 (3): 198-206.
[6]	YU Z, LI S, DU H. Adaptive neural output feedback control for stochastic nonlinear systems with unknown control directions[J]. Neural Computing & Applications, 2014, 25 (7/8): 1979-1992.
[7]	丛爽. 几种模糊神经网络系统关系的对比研究[J]. 信息与控制, 2001, (6): 486-491. CONG S. Comparative research on relationships between several fuzzy-neural network systems[J]. Information and Control, 2001, (6): 486-491.
[8]	Karny M. Toward fully probabilistic control design[J]. Automatica, 1996, (32): 1719-1722.
[9]	陈海永, 王宏. 基于LMI的参数随机变化系统的概率密度函数控制[J]. 自动化学报, 2007, (11): 1216-1219. CHEN H Y, WANG H. PDF control of stochastic parameter system using linear matrix inequalities[J]. Acta Automatica Sinica, 2007, (11): 1216-1219.
[10]	贾立, 曹鲁明, 邱铭森. 基于建模误差PDF形状的间歇过程数据驱动模型[J]. 仪器仪表学报, 2012, (7): 1505-1512. JIA L, CAO L M, CHIU M S. Modeling error PDF shape based data-driven model for batch processes[J]. Chinese Journal of Scientific Instrument, 2012, (7): 1505-1512.
[11]	DING J L, CHAI T Y. Offline modeling for product quality prediction of mineral processing using modeling error PDF shaping and entropy minimization[J]. IEEE Transactions on Neural Networks, 2011, 22 (3): 408-419.
[12]	JIA L, CHIU M S. Research on fuzzy neural model with global convergence for batch process[J]. Information and Control, 2009, 38 (6): 683-691.
[13]	BOWMAN A W, AZZALINI A. Applied Smoothing Techniques for Data Analysis[M]. New York: Oxford University Press, 1997.
[14]	贾立. 神经模糊系统研究及其在建模与控制中的应用[D]. 上海: 华东理工大学, 2002: 10-32. JIA L. Research on neuro-fuzzy system and its application in modeling and control[D]. Shanghai: East China University of Science and Technology, 2002: 10-32.
[15]	贾立, 程大帅, 曹鲁明, 等. 基于数据的间歇过程时变神经模糊模型研究[J]. 计算机与应用化学, 2011, 28 (7): 915-918. JIA L, CHENG D S, CAO L M, et al. Research on data-based time-varying neuro-fuzzy model for batch processes[J].Computers and Applied Chemistry, 2011, 28 (7): 915-918.
[16]	王建平, 胡益, 侍洪波. 基于高阶偏最小二乘的间歇过程建模[J]. 化工学报, 2014, 65 (9): 3527-3534. WANG J P, HU Y, SHI H B. Modeling of batch process based on higher order partial least squares[J]. CIESC Journal, 2014, 65 (9): 3527-3534.
[17]	史洪岩, 苑明哲, 王天然, 等. 间歇过程动态优化方法综述[J]. 信息与控制, 2012, (1): 75-82. SHI H Y, YUANG M Z, WANG T R, et al. A survey on dynamic optimization methods of batch processes[J]. Information and Control, 2012, (1): 75-82.
[18]	朱朝艳, 王建波, 王学志, 等. 改进遗传算法的研究现状分析[J]. 吉林水利, 2010, (7): 1-4. ZHU C Y, WANG J B, WANG X Z, et al. The status quo of improved genetic algorithm[J]. Jilin Water Resources, 2010, (7): 1-4.
[19]	王梦寒, 杨海, 李雁召. 前馈神经网络与遗传算法相结合解决曲轴中心缩孔[J]. 化工学报, 2013, 64 (10): 3673-3678. WANG M H, YANG H, LI Y Z. Elimination of voids in crankshaft through a hybrid of back propagation neural network and genetic algorithm[J]. CIESC Journal, 2013, 64 (10): 3673-3678.
[20]	张炤, 张素, 章琛曦, 等. 基于支持向量机的概率密度估计方法[J]. 系统仿真学报. 2005, 10: 2355-2357. ZHANG Z, ZHANG S, ZHANG C X, et al. Density estimation based on support vector machines[J]. Journal of System Simulation. 2005, 10: 2355-2357.
[21]	XIONG Z H, ZHANG J, WANG X, XU Y M. Run-to-run iterative optimization control of batch processes based on recurrent neural network[J]. Advances in Neural Networks, 2004, 3174: 97-103.

基于改进PDF技术的间歇过程NFM模型

Improved PDF technology based NFM for batch process

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献 21

相关文章 15

编辑推荐

Metrics

本文评价

[1]	曹跃, 余冲, 李智, 杨明磊. 工业数据驱动的加氢裂化装置多工况切换过渡状态检测[J]. 化工学报, 2023, 74(9): 3841-3854.
[2]	尹刚, 李伊惠, 何飞, 曹文琦, 王民, 颜非亚, 向禹, 卢剑, 罗斌, 卢润廷. 基于KPCA和SVM的铝电解槽漏槽事故预警方法[J]. 化工学报, 2023, 74(8): 3419-3428.
[3]	诸程瑛, 王振雷. 基于改进深度强化学习的乙烯裂解炉操作优化[J]. 化工学报, 2023, 74(8): 3429-3437.
[4]	闫琳琦, 王振雷. 基于STA-BiLSTM-LightGBM组合模型的多步预测软测量建模[J]. 化工学报, 2023, 74(8): 3407-3418.
[5]	郭雨莹, 敬加强, 黄婉妮, 张平, 孙杰, 朱宇, 冯君炫, 陆洪江. 稠油管道水润滑减阻及压降预测模型修正[J]. 化工学报, 2023, 74(7): 2898-2907.
[6]	周继鹏, 何文军, 李涛. 异形催化剂上乙烯催化氧化失活动力学反应工程计算[J]. 化工学报, 2023, 74(6): 2416-2426.
[7]	李艳辉, 丁邵明, 白周央, 张一楠, 于智红, 邢利梅, 高鹏飞, 王永贞. 非常规服役超临界锅炉的微纳尺度腐蚀动力学模型建立及应用[J]. 化工学报, 2023, 74(6): 2436-2446.
[8]	于源, 陈薇薇, 付俊杰, 刘家祥, 焦志伟. 几何相似涡流空气分级机环形区流场变化规律研究及预测[J]. 化工学报, 2023, 74(6): 2363-2373.
[9]	高学金, 姚玉卓, 韩华云, 齐咏生. 基于注意力动态卷积自编码器的发酵过程故障监测[J]. 化工学报, 2023, 74(6): 2503-2521.
[10]	郑书闽, 郭鹏程, 颜建国, 王帅, 李文博, 周淇. 微小通道内过冷流动沸腾阻力特性实验及预测研究[J]. 化工学报, 2023, 74(4): 1549-1560.
[11]	吴心远, 刘奇磊, 曹博渊, 张磊, 都健. Group2vec：基于无监督机器学习的基团向量表示及其物性预测应用[J]. 化工学报, 2023, 74(3): 1187-1194.
[12]	张生安, 刘桂莲. 高效太阳能电解水制氢系统及其性能的多目标优化[J]. 化工学报, 2023, 74(3): 1260-1274.
[13]	张中秋, 李宏光, 石逸林. 基于人工预测调控策略的复杂化工过程多任务学习方法[J]. 化工学报, 2023, 74(3): 1195-1204.
[14]	顾学荣, 刘硕士, 杨思宇. 基于并行EGO和代理模型辅助的多参数优化方法研究[J]. 化工学报, 2023, 74(3): 1205-1215.
[15]	史克年, 郑景元, 钱宇, 杨思宇. 基于马尔可夫链的蒸汽动力系统两阶段随机规划[J]. 化工学报, 2023, 74(2): 807-817.