基于多尺度核JYMKPLS迁移模型的间歇过程产品质量的在线预测方法

doi:10.11949/0438-1157.20200995

化工学报 ›› 2021, Vol. 72 ›› Issue (4): 2178-2189.DOI: 10.11949/0438-1157.20200995

基于多尺度核JYMKPLS迁移模型的间歇过程产品质量的在线预测方法

褚菲^1,²(),彭闯²,贾润达³,陈韬⁴,陆宁云⁵

^1.地下空间智能控制教育部工程研究中心，江苏徐州 221116
^2.中国矿业大学信息与控制工程学院，江苏徐州 221116
^3.东北大学信息科学与工程学院，辽宁沈阳 110819
^4.萨里大学化学与工艺工程系，英国吉尔福德
^5.南京航空航天大学自动化学院，江苏南京 210016

收稿日期:2020-07-23 修回日期:2020-09-17 出版日期:2021-04-05 发布日期:2021-04-05
通讯作者: 褚菲
作者简介:褚菲（1984—），男，博士，副教授，chufeizhufei@sina.com
基金资助:
国家自然科学基金项目(61973304);江苏省六大人才高峰项目(DZXX-045);江苏省科技计划项目(BK20191339);徐州市科技创新计划项目(KC19055);矿冶过程自动控制技术国家重点实验室开放课题(BGRIMM-KZSKL-2019-10);国家煤加工与洁净化工程技术研究中心开放课题(2018NERCCPP-B03);前沿课题专项项目(2019XKQYMS64)

Online prediction method of batch process product quality based on multi-scale kernel JYMKPLS transfer model

CHU Fei^1,²(),PENG Chuang²,JIA Runda³,CHEN Tao⁴,LU Ningyun⁵

^1.Engineering Research Center of Ministry of Education for Intelligent Control of Underground Space，Xuzhou 221116, Jiangsu, China
^2.College of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, Jiangsu, China
^3.Industrial Artificial Intelligence and Optimization Institute, Northeastern University, Shenyang 110819, Liaoning, China
^4.Department of Chemical and Process Engineering, University of Surrey, Guildford, United Kingdom
^5.College of Automation, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, Jiangsu, China

Received:2020-07-23 Revised:2020-09-17 Online:2021-04-05 Published:2021-04-05
Contact: CHU Fei

摘要/Abstract

摘要：

针对过程数据不足，且具有强非线性和多尺度特性的新间歇过程，结合迁移学习方法与多尺度核学习方法的优势，提出了一种基于多尺度核JYMKPLS（Joint-Y multi-scale kernel partial least squares）迁移模型的间歇过程产品质量在线预测方法。该方法首先通过迁移学习利用相似源域的旧过程数据提高新间歇过程建模效率和质量预测的精度。然后，针对间歇过程数据的非线性和多尺度特性问题，引入了多尺度核函数以更好地拟合数据变化的趋势，从而提高模型的预测精度。此外，提出模型在线更新和数据剔除，通过在线持续改善迁移模型对新间歇过程的匹配程度，以消除相似过程间的差异性给迁移学习带来的不利影响，从而不断地提升预测精度。最后，通过仿真验证了所提方法的有效性，结果表明，与传统的数据驱动建模方法相比，本文所提方法能够有效提高建模效率和预测精度。

关键词: 间歇式, 模型, 预测, 多尺度核, 迁移学习

Abstract:

In view of the shortage of process data and the strong nonlinear and multi-scale characteristics of the new batch process, a product quality prediction method based on multi-scale kernel JYMKPLS (Joint-Y multi-scale kernel partial least squares) transfer learning is proposed, which combines the advantages of transfer learning and multi-scale kernel learning. First, the new batch process modeling efficiency and quality prediction accuracy are improved by using the old process data in the similar source domain through transfer learning. Then, in order to solve the problem of non-linear and multi-scale characteristics of the data, multi-scale kernel method is used to better fit the data features, so as to improve the prediction accuracy of the model. In addition, the online update and data elimination of the model are proposed to continuously improve the matching degree of the transfer model to the new batch process, so as to eliminate the adverse effects of the differences between similar processes on the transfer learning, so as to continuously improve the prediction accuracy. Finally, the effectiveness of the proposed method is verified by simulation. The results show that, compared with traditional data-driven modeling methods, the method proposed in this paper can effectively improve modeling efficiency and prediction accuracy.

Key words: batchwise, model, prediction, multi-scale kernel, transfer learning

中图分类号:

TP 274

褚菲, 彭闯, 贾润达, 陈韬, 陆宁云. 基于多尺度核JYMKPLS迁移模型的间歇过程产品质量的在线预测方法[J]. 化工学报, 2021, 72(4): 2178-2189.

CHU Fei, PENG Chuang, JIA Runda, CHEN Tao, LU Ningyun. Online prediction method of batch process product quality based on multi-scale kernel JYMKPLS transfer model[J]. CIESC Journal, 2021, 72(4): 2178-2189.

图/表 12

图1 两个相似过程数据

Fig.1 Two similar process datasets

图2 JYMKPLS模型结构

Fig.2 The structure of JYMKPLS model

图3 相似过程数据的批次展开

Fig.3 Batch-unfolding of similar process data

图4 基于JYMKPLS过程迁移模型的批次过程质量预测及更新流程

Fig.4 Batch process quality prediction and update process based on JYMKPLS process transfer model

表1 过程A和B的工作条件

Table 1 Working conditions for batch processes A and B

输入变量	过程A的数值范围	过程B的数值范围
培养量/L	105~109	108~113
二氧化碳浓度/(mmol/L)	0.52~0.56	0.62~0.65
pH	4.3~5.2	4.1~4.6
通风率/(L/h)	5~6	6~7
搅拌功率/W	32~41	35~44
喂料温度/K	295.8~297.3	296.3~298.2
pH设定点	5.0~5.2	5.1~5.3

图5 基于KPLS和MKPLS的青霉素最终浓度预测结果

Fig.5 The prediction result of the final concentration of penicillin in each batch based on KPLS and MKPLS

表2 两种预测方法的评价指标对比

Table 2 The evaluation index comparison of two prediction methods

方法	RMSE	MPRE
KPLS	0.0081	0.0058
MKPLS	0.0079	0.0057

图6 带有模型更新的KPLS模型和MKPLS模型的RMSE

Fig.6 RMSE of KPLS model and MKPLS model with model updates

图7 基于KPLS、JYKPLS和JYMKPLS的青霉素最终浓度预测结果

Fig.7 Prediction results of final penicillin concentration for each batch based on KPLS, JYKPLS and JYMKPLS

表3 三种预测方法的评价指标对比

Table 3 The evaluation index comparison of three prediction methods

方法	RMSE	MPRE
KPLS	0.0081	0.0058
JYKPLS	0.0065	0.0044
JYMKPLS	0.0063	0.0042

表4 三种预测方法的平均均方根误差对比

Table 4 Comparison of mean RMSE of three prediction methods

方法	平均RMSE
KPLS	0.0070
JYKPLS	0.0048
JYMKPLS	0.0036

图8 带有模型更新的三种模型的RMSE

Fig.8 RMSE of the three models with model updates

参考文献 35

1	Jia R D, Mao Z Z, Wang F L, et al. Self-tuning final product quality control of batch processes using kernel latent variable model[J]. Chemical Engineering Research and Design, 2015, 94: 119-130.
2	Jiang Q C, Yan S F, Yan X F, et al. Data-driven two-dimensional deep correlated representation learning for nonlinear batch process monitoring[J]. IEEE Transactions on Industrial Informatics, 2020, 16(4): 2839-2848.
3	Zhang S M, Zhao C H. Slow-feature-analysis-based batch process monitoring with comprehensive interpretation of operation condition deviation and dynamic anomaly[J]. IEEE Transactions on Industrial Electronics, 2019, 66(5): 3773-3783.
4	Tulsyan A, Garvin C, Undey C. Industrial batch process monitoring with limited data[J]. Journal of Process Control, 2019, 77: 114-133.
5	Chu F, Cheng X, Jia R D, et al. Final quality prediction method for new batch processes based on improved JYKPLS process transfer model[J]. Chemometrics and Intelligent Laboratory Systems, 2018, 183: 1-10.
6	Shokry A, Vicente P, Escudero G, et al. Data-driven soft-sensors for online monitoring of batch processes with different initial conditions[J]. Computers & Chemical Engineering, 2018, 118: 159-179.
7	赵春晖, 王福利, 姚远, 等. 基于时段的间歇过程统计建模、在线监测及质量预报[J]. 自动化学报, 2010, 36(3): 366-374.
	Zhao C H, Wang F L, Yao Y, et al. Phase-based statistical modeling, online monitoring and quality prediction for batch processes[J]. Acta Automatica Sinica, 2010, 36(3): 366-374.
8	Li X, Wu F, Zhang R D, et al. Nonlinear multivariate quality prediction based on OSC-SVM-PLS[J]. Industrial & Engineering Chemistry Research, 2019, 58(19): 8154-8161.
9	Luo L J, Bao S Y, Mao J F, et al. Quality prediction and quality-relevant monitoring with multilinear PLS for batch processes[J]. Chemometrics and Intelligent Laboratory Systems, 2016, 150: 9-22.
10	Yao L, Ge Z Q. Locally weighted prediction methods for latent factor analysis with supervised and semisupervised process data[J]. IEEE Transactions on Automation Science and Engineering, 2017, 14(1): 126-138.
11	Yao L, Ge Z Q. Deep learning of semisupervised process data with hierarchical extreme learning machine and soft sensor application[J]. IEEE Transactions on Industrial Electronics, 2018, 65(2): 1490-1498.
12	Xiong W L, Shi X D. Soft sensor modeling with a selective updating strategy for Gaussian process regression based on probabilistic principle component analysis[J]. Journal of the Franklin Institute, 2018, 355(12): 5336-5349.
13	Yuan X F, Ge Z Q, Song Z H. Locally weighted kernel principal component regression model for soft sensing of nonlinear time-variant processes[J]. Industrial & Engineering Chemistry Research, 2014, 53(35): 13736-13749.
14	Mei C L, Su Y, Liu G H, et al. Dynamic soft sensor development based on Gaussian mixture regression for fermentation processes[J]. Chinese Journal of Chemical Engineering, 2017, 25(1): 116-122.
15	Wang K, Gopaluni R B, Chen J, et al. Deep learning of complex batch process data and its application on quality prediction[J]. IEEE Transactions on Industrial Informatics, 2020, 16(12): 7233-7242.
16	Jin H P, Chen X G, Yang J W, et al. Online local learning based adaptive soft sensor and its application to an industrial fed-batch chlortetracycline fermentation process[J]. Chemometrics and Intelligent Laboratory Systems, 2015, 143: 58-78.
17	Souza F A A, Araújo R, Mendes J. Review of soft sensor methods for regression applications[J]. Chemometrics and Intelligent Laboratory Systems, 2016, 152: 69-79.
18	Yao L, Ge Z Q. Big data quality prediction in the process industry: a distributed parallel modeling framework[J]. Journal of Process Control, 2018, 68: 1-13.
19	Bidar B, Sadeghi J, Shahraki F, et al. Data-driven soft sensor approach for online quality prediction using state dependent parameter models[J]. Chemometrics and Intelligent Laboratory Systems, 2017, 162: 130-141.
20	Lu J D, Yao Y, Gao F R. Model migration for development of a new process model[J]. Industrial & Engineering Chemistry Research, 2009, 48(21): 9603-9610.
21	Zhu J L, Gao F R. Similar batch process monitoring with orthogonal subspace alignment[J]. IEEE Transactions on Industrial Electronics, 2018, 65(10): 8173-8183.
22	Weiss K, Khoshgoftaar T M, Wang D D. A survey of transfer learning[J]. Journal of Big Data, 2016, 3(1): 1-40.
23	Tsung F, Zhang K, Cheng L W, et al. Statistical transfer learning: a review and some extensions to statistical process control[J]. Quality Engineering, 2018, 30(1): 115-128.
24	Shen S, Sadoughi M, Li M, et al. Deep convolutional neural networks with ensemble learning and transfer learning for capacity estimation of lithium-ion batteries[J]. Applied Energy, 2020, 260: 114296.
25	Shao S Y, McAleer S, Yan R Q, et al. Highly accurate machine fault diagnosis using deep transfer learning[J]. IEEE Transactions on Industrial Informatics, 2019, 15(4): 2446-2455.
26	Liu Y, Yang C, Liu K X, et al. Domain adaptation transfer learning soft sensor for product quality prediction[J]. Chemometrics and Intelligent Laboratory Systems, 2019, 192: 103813.
27	Jaeckle C M, MacGregor J F. Product transfer between plants using historical process data[J]. AIChE Journal, 2000, 46(10): 1989-1997.
28	García Muñoz S, MacGregor J F, Kourti T. Product transfer between sites using Joint-Y PLS[J]. Chemometrics and Intelligent Laboratory Systems, 2005, 79(1/2): 101-114.
29	汪洪桥, 孙富春, 蔡艳宁, 等. 多核学习方法[J]. 自动化学报, 2010, 36(8): 1037-1050.
	Wang H Q, Sun F C, Cai Y N, et al. On multiple kernel learning methods[J]. Acta Automatica Sinica, 2010, 36(8): 1037-1050.
30	Zhou S S, Liu H W, Ye F. Variant of Gaussian kernel and parameter setting method for nonlinear SVM[J]. Neurocomputing, 2009, 72(13/14/15): 2931-2937.
31	Bao J, Chen Y Y, Yu L, et al. A multi-scale kernel learning method and its application in image classification[J]. Neurocomputing, 2017, 257: 16-23.
32	Liu R N, Wang F, Yang B Y, et al. Multiscale kernel based residual convolutional neural network for motor fault diagnosis under nonstationary conditions[J]. IEEE Transactions on Industrial Informatics, 2020, 16(6): 3797-3806.
33	Sun G Y, Rong X Q, Zhang A Z, et al. Multi-scale mahalanobis kernel-based support vector machine for classification of high-resolution remote sensing images[J]. Cognitive Computation, 2019. DOI: 10.1007/s12559-019-09631-5. DOI
34	贾润达, 毛志忠, 王福利. 基于KPLS模型的间歇过程产品质量控制[J]. 化工学报, 2013, 64(4): 1332-1339.
	Jia R D, Mao Z Z, Wang F L. KPLS model based product quality control for batch processes[J]. CIESC Journal, 2013, 64(4): 1332-1339.
35	Iosifidis A, Tefas A, Pitas I. Minimum class variance extreme learning machine for human action recognition[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2013, 23(11): 1968-1979.

[1]	宋嘉豪, 王文. 斯特林发动机与高温热管耦合运行特性研究[J]. 化工学报, 2023, 74(S1): 287-294.
[2]	连梦雅, 谈莹莹, 王林, 陈枫, 曹艺飞. 地下水预热新风一体化热泵空调系统制热性能研究[J]. 化工学报, 2023, 74(S1): 311-319.
[3]	金正浩, 封立杰, 李舒宏. 氨水溶液交叉型再吸收式热泵的能量及分析[J]. 化工学报, 2023, 74(S1): 53-63.
[4]	李科, 文键, 忻碧平. 耦合蒸气冷却屏的真空多层绝热结构对液氢储罐自增压过程的影响机制研究[J]. 化工学报, 2023, 74(9): 3786-3796.
[5]	王浩, 王振雷. 基于自适应谱方法的裂解炉烧焦模型化简策略[J]. 化工学报, 2023, 74(9): 3855-3864.
[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]	李锦潼, 邱顺, 孙文寿. 煤浆法烟气脱硫中草酸和紫外线强化煤砷浸出过程[J]. 化工学报, 2023, 74(8): 3522-3532.
[8]	于旭东, 李琪, 陈念粗, 杜理, 任思颖, 曾英. 三元体系KCl + CaCl₂ + H₂O 298.2、323.2及348.2 K相平衡研究及计算[J]. 化工学报, 2023, 74(8): 3256-3265.
[9]	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.
[10]	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.
[11]	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.
[12]	刘春雨, 周桓宇, 马跃, 岳长涛. CaO调质含油污泥干燥特性及数学模型[J]. 化工学报, 2023, 74(7): 3018-3027.
[13]	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.
[14]	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.
[15]	刘起超, 周云龙, 陈聪. 起伏振动垂直上升管气液两相流截面含气率分析与计算[J]. 化工学报, 2023, 74(6): 2391-2403.

基于多尺度核JYMKPLS迁移模型的间歇过程产品质量的在线预测方法

Online prediction method of batch process product quality based on multi-scale kernel JYMKPLS transfer model

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 35

相关文章 15

编辑推荐

Metrics

本文评价