基于主元提取的鲁棒极限学习机研究及其化工建模应用

doi:10.11949/j.issn.0438-1157.20181355

化工学报 ›› 2019, Vol. 70 ›› Issue (2): 475-480.DOI: 10.11949/j.issn.0438-1157.20181355

基于主元提取的鲁棒极限学习机研究及其化工建模应用

张晓晗^1,²(),汪平江^1,²,顾祥柏^1,³,徐圆^1,²,贺彦林^1,²(),朱群雄^1,²()

1. 北京化工大学信息科学与技术学院，北京100029
2. 智能过程系统工程教育部工程研究中心，北京100029
3. 中石化炼化工程(集团)股份有限公司，北京100101

收稿日期:2018-11-16 修回日期:2018-11-26 出版日期:2019-02-05 发布日期:2019-02-05
通讯作者: 贺彦林,朱群雄
作者简介:<named-content content-type="corresp-name">张晓晗</named-content>（1995—），女，博士研究生，<email>xiao.han_zhang@qq.com</email>|贺彦林（1987—），男，博士，副教授，<email>heyl@mail.buct.edu.cn</email>|朱群雄（1960—），男，博士，教授，<email>zhuqx@mail.buct.edu.cn</email>
基金资助:
国家自然科学基金青年项目(61703027);国家自然科学基金重点项目(61533003);中央高校基本科研业务费专项资金(JD1808, XK1802-4)

Research on principal components extraction based robust extreme learning machine(PCE-RELM) and its application to modeling chemical processes

Xiaohan ZHANG^1,²(),Pingjiang WANG^1,²,Xiangbai GU^1,³,Yuan XU^1,²,Yanlin HE^1,²(),Qunxiong ZHU^1,²()

1. College of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China
2. Engineering Research Center of Ministry of Education, Beijing 100029, China
3. Sinopec Engineering Group Co., Ltd., Beijing 100101, China

Received:2018-11-16 Revised:2018-11-26 Online:2019-02-05 Published:2019-02-05
Contact: Yanlin HE,Qunxiong ZHU

摘要/Abstract

摘要：

化工生产过程日益复杂，传统极限学习机(extreme learning machine, ELM)无法有效地对化工过程数据建模。针对该问题，提出一种基于主元提取(principal components extraction, PCE)的鲁棒极限学习机(PCE-RELM)。通过对ELM隐含层进行主元分析，提取数据的主元特征，去除变量间的线性相关性，简化研究问题。可以减小隐含层节点数对模型精度的影响，实现对ELM隐含层节点数的快速随机选取，同时使ELM具有鲁棒性。为验证提出方法的有效性，将PCE-RELM模型应用于精对苯二甲酸(purified terephthalic acid,PTA)生产过程建模。仿真结果显示，相比传统的ELM，PCE-RELM模型具有设计简单、鲁棒性好、精度高等优势，可以对化工过程控制、分析起到指导作用。

关键词: 极限学习机, 神经网络, 主元分析, 过程建模, 化工生产, 过程控制

Abstract:

The chemical production processes are increasingly complex and the traditional extreme learning machine (ELM) cannot effectively model the chemical processes data. To tackle this problem, a novel PCE-RELM model based on principal components extraction (PCE) is proposed. Through principal component analysis of the ELM hidden layer, the principal component features of the data are extracted, the linear correlation between variables is removed, and the research problem is simplified. The influence of the number of hidden layer nodes on the accuracy of the model can be reduced, the number of hidden layer nodes in the ELM can be quickly and randomly selected, and the ELM model becomes robust. To verify the effectiveness of the proposed method, the PCE-RELM model was applied to modeling the purified terephthalic acid (PTA) production process. The simulation results show that, compared with the traditional ELM, the PCE-RELM model has the advantages of simple design, good robustness and high accuracy, which can guide the chemical process control and analysis.

Key words: extreme learning machine, neural network, principal components analysis, processes modeling, chemical production, process control

中图分类号:

TP 29

张晓晗, 汪平江, 顾祥柏, 徐圆, 贺彦林, 朱群雄. 基于主元提取的鲁棒极限学习机研究及其化工建模应用[J]. 化工学报, 2019, 70(2): 475-480.

Xiaohan ZHANG, Pingjiang WANG, Xiangbai GU, Yuan XU, Yanlin HE, Qunxiong ZHU. Research on principal components extraction based robust extreme learning machine(PCE-RELM) and its application to modeling chemical processes[J]. CIESC Journal, 2019, 70(2): 475-480.

图/表 6

参考文献 30

1	LiP, ChenS C. Hierarchical gaussian processes model for multi-task learning[J]. Pattern Recognition, 2018, 74: 134-144.
2	ZhangY W, DuW Y, FanY P, et al. Comprehensive correlation analysis of industrial process[J]. IEEE Transactions on Industrial Electronics, 2017, 64(12): 9461-9468.
3	ZhangX H, ZhuQ X, HeY L, et al. A novel robust ensemble model integrated extreme learning machine with multi-activation functions for energy modeling and analysis: application to petrochemical industry[J]. Energy, 2018, 162: 593-602.
4	ZhangX H, ZhuQ X, JiangZ Y, et al. A novel ensemble model using PLSR integrated with multiple activation functions based ELM: Applications to soft sensor development[J]. Chemometrics and Intelligent Laboratory Systems, 2018, 183: 147-157.
5	SajjiaM. Shirazian S, Kelly C B,et al. ANN analysis of a roller compaction process in the pharmaceutical industry[J]. Chemical Engineering & Technology, 2017, 40(3): 487-492.
6	BrosigF, MeierP, BeckerS, et al. Quantitative evaluation of model-driven performance analysis and simulation of component-based architectures[J]. IEEE Transactions on Software Engineering, 2015, 41(2): 157-175.
7	NeriA, CagnoE, Di SebastianoG, et al. Industrial sustainability: modelling drivers and mechanisms with barriers[J]. Journal of Cleaner Production, 2018, 194: 452-472.
8	MarínB, GallardoC, QuirogaD, et al. Testing of model-driven development applications[J]. Software Quality Journal, 2017, 25(2): 407-435.
9	HeY L, GengZ Q, ZhuQ X. Data driven soft sensor development for complex chemical processes using extreme learning machine[J]. Chemical Engineering Research and Design, 2017, 102: 1-11.
10	ZhangX H, ZhuQ X, HeY L, et al. Energy modeling using an effective latent variable based functional link learning machine[J]. Energy, 2018, 162: 883-891.
11	DingS F, SuC Y, YuJ Z. An optimizing BP neural network algorithm based on genetic algorithm[J]. Artificial Intelligence Review, 2011, 36(2): 153-162.
12	刘菲菲, 彭荻, 贺彦林, 等. 基于极限学习机的过程神经网络研究及化工应用[J]. 上海交通大学学报, 2014, 48(7): 977-981.
	LiuF F, PengD, HeY L, et al. Research and chemical application of extreme learning based process neural network[J]. Journal of Shanghai Jiao Tong University, 2014, 48(7): 977-981.
13	BehnasrM, Jazayeri-RadH. Robust data-driven soft sensor based on iteratively weighted least squares support vector regression optimized by the cuckoo optimization algorithm[J]. Journal of Natural Gas Science & Engineering, 2015, 22: 35-41.
14	ChenX, QiaoL S, CaiY L, et al. Combination computing of support vector machine, support vector regression and molecular docking for potential cytochrome P450 1A2 inhibitors[J]. Chinese Journal of Chemical Physics, 2016, 29(5): 629-634.
15	耿志强, 武开英, 韩永明. 基于层次分析的FLNN神经网络研究及应用[J]. 化工学报, 2016, 67(3): 805-811.
	GengZ Q, WuK Y, HanY M. Research and application of FLNN neural network based on AHP[J]. CIESC Journal, 2016, 67(3): 805-811.
16	CaoW S, LiuQ, WangY Q, et al. Modelling and simulation of VMD desalination process by ANN[J]. Computers & Chemical Engineering, 2016, 84: 96-103.
17	JiangN, XuJ, ZhangS. Neural network control of networked redundant manipulator system with weight initialization method[J]. Neurocomputing, 2018, 307: 117-129.
18	HuangG B, ZhuQ Y, SiewC K. Extreme learning machine: theory and applications[J]. Neurocomputing, 2006, 70(1/2/3): 489-501.
19	GengZ, DongJ, ChenJ, et al. A new self-organizing extreme learning machine soft sensor model and its applications in complicated chemical processes[J]. Engineering Applications of Artificial Intelligence, 2017, 62: 38-50.
20	HeY L, GengZ Q, XuY, et al. A robust hybrid model integrating enhanced inputs based extreme learning machine with PLSR (PLSR-EIELM) and its application to intelligent measurement[J]. ISA Transactions, 2015, 58: 533-542.
21	XuY, YeL L, ZhuQ X. A new DROS-extreme learning machine with differential Vector-KPCA approach for real-time fault recognition of nonlinear processes[J]. Journal of Dynamic Systems, Measurement, and Control, 2015, 137(5): 051011.
22	WoldS, EsbensenK, GeladiP. Principal component analysis[J]. Chemometrics and Intelligent Laboratory Systems, 1987, 2(1/2/3): 37-52.
23	AbdiH, WilliamsL J. Principal component analysis[J]. Wiley Interdisciplinary Reviews Computational Statistics, 2010, 2(4): 433-459.
24	ZhuQ X, WangX, HeY L, et al. An improved extreme learning machine integrated with nonlinear principal components and its application to modeling complex chemical processes[J]. Applied Thermal Engineering, 2018, 130: 745-753.
25	ArtoniF, DelormeA, MakeigS. Applying dimension reduction to EEG data by principal component analysis reduces the quality of its subsequent independent component decomposition[J]. NeuroImage, 2018, 175: 176-187.
26	ShenH B, LamH L. Sustainability evaluation for biomass supply chain synthesis: novel principal component analysis (PCA) aided optimisation approach[J]. Journal of Cleaner Production, 2018, 189: 941-961.
27	HuangG B, ZhuQ Y, SiewC K. Extreme learning machine: a new learning scheme of feedforward neural networks[C]//IEEE International Joint Conference on Neural Networks, 2004. Proceedings. IEEE Xplore, 2004: 985-990.
28	HuangG B, ZhouH, DingX, et al. Extreme learning machine for regression and multiclass classification[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2012, 42(2): 513-529.
29	LiuH, MiX, LiY. An experimental investigation of three new hybrid wind speed forecasting models using multi-decomposing strategy and ELM algorithm[J]. Renewable Energy, 2018, 123: 694-705.
30	ImtiazH, SarwateA D. Differentially private distributed principal component analysis[C]//2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2018: 2206-2210.

输入变量编号	变量名称
1	蒸汽流量
2	水回流
3	进料量
4	乙酸正丁酯侧回流
5	乙酸正丁酯主回流
6	回流罐液位
7	进料温度
8	回流温度
9	顶塔温度
10	顶塔产量
11	第三十五层塔板上方温度
12	进料成分(乙酸含量)
13	高灵敏板附近的塔板温度
14	低灵敏板附近的塔板温度
15	第三十五层塔板与第四十层塔板之间的温度
16	第四十四层塔板与第五十层塔板之间的温度
17	第五十三层塔板与第五十八层塔板之间的温度

输入变量编号	变量名称
1	蒸汽流量
2	水回流
3	进料量
4	乙酸正丁酯侧回流
5	乙酸正丁酯主回流
6	回流罐液位
7	进料温度
8	回流温度
9	顶塔温度
10	顶塔产量
11	第三十五层塔板上方温度
12	进料成分(乙酸含量)
13	高灵敏板附近的塔板温度
14	低灵敏板附近的塔板温度
15	第三十五层塔板与第四十层塔板之间的温度
16	第四十四层塔板与第五十层塔板之间的温度
17	第五十三层塔板与第五十八层塔板之间的温度

隐含层节点数	PCE-RELM	ELM
10	0.010067	0.008021
30	0.010250	0.006363
50	0.010186	0.006707
100	0.010212	0.027203
300	0.010275	0.021646
500	0.010337	0.019315
1000	0.010252	0.016531
10000	0.010318	0.015991

隐含层节点数	PCE-RELM	ELM
10	0.010067	0.008021
30	0.010250	0.006363
50	0.010186	0.006707
100	0.010212	0.027203
300	0.010275	0.021646
500	0.010337	0.019315
1000	0.010252	0.016531
10000	0.010318	0.015991

[1]	康飞, 吕伟光, 巨锋, 孙峙. 废锂离子电池放电路径与评价研究[J]. 化工学报, 2023, 74(9): 3903-3911.
[2]	温凯杰, 郭力, 夏诏杰, 陈建华. 一种耦合CFD与深度学习的气固快速模拟方法[J]. 化工学报, 2023, 74(9): 3775-3785.
[3]	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.
[4]	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.
[5]	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.
[6]	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.
[7]	徐野, 黄文君, 米俊芃, 申川川, 金建祥. 多源信息融合的离心式压缩机喘振诊断方法[J]. 化工学报, 2023, 74(7): 2979-2987.
[8]	王光, 单发顺, 钱禹丞, 焦建芳. 基于集成学习传递熵的化工过程微小故障检测方法[J]. 化工学报, 2023, 74(7): 2967-2978.
[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]	黄磊, 孔令学, 白进, 李怀柱, 郭振兴, 白宗庆, 李平, 李文. 油页岩添加对准东高钠煤灰熔融行为影响的研究[J]. 化工学报, 2023, 74(5): 2123-2135.
[11]	苏晓丹, 朱干宇, 李会泉, 郑光明, 孟子衡, 李防, 杨云瑞, 习本军, 崔玉. 湿法磷酸半水工艺考察与石膏结晶过程研究[J]. 化工学报, 2023, 74(4): 1805-1817.
[12]	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.
[13]	贠程, 王倩琳, 陈锋, 张鑫, 窦站, 颜廷俊. 基于社团结构的化工过程风险演化路径深度挖掘[J]. 化工学报, 2023, 74(4): 1639-1650.
[14]	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.
[15]	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.

基于主元提取的鲁棒极限学习机研究及其化工建模应用

Research on principal components extraction based robust extreme learning machine(PCE-RELM) and its application to modeling chemical processes

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 6

参考文献 30

相关文章 15

编辑推荐

Metrics

本文评价