基于集成学习的多产品化工过程软测量建模方法

doi:10.11949/j.issn.0438-1157.20171286

化工学报 ›› 2018, Vol. 69 ›› Issue (6): 2551-2559.DOI: 10.11949/j.issn.0438-1157.20171286

基于集成学习的多产品化工过程软测量建模方法

邵伟明^1,2, 田学民³, 宋执环^1,2

1. 工业控制技术国家重点实验室, 浙江杭州 310027;
2. 浙江大学控制科学与工程学院, 浙江杭州 310027;
3. 中国石油大学信息与控制工程学院, 山东青岛 266580

收稿日期:2017-09-25 修回日期:2018-01-04 出版日期:2018-06-05 发布日期:2018-06-05
通讯作者: 宋执环
基金资助:
国家重点研发计划重点专项项目（2017YFB0304203）；国家自然科学基金项目（61703367）。

Ensemble learning-based soft sensor method for multi-product chemical processes

SHAO Weiming^1,2, TIAN Xuemin³, SONG Zhihuan^1,2

1. State Key Laboratory of Industrial Control Technology, Hangzhou 310027, Zhejiang, China;
2. College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, Zhejiang, China;
3. College of Information and Control Engineering, China University of Petroleum, Qingdao 266580, Shandong, China

Received:2017-09-25 Revised:2018-01-04 Online:2018-06-05 Published:2018-06-05
Supported by:
supported by the National Key Research and Development Program of China (2017YFB0304203) and the National Natural Science Foundation of China (61703367).

摘要/Abstract

摘要：

化工过程通常具有非线性、时变以及多产品等特性。针对上述特点，在集成学习框架下建立自适应软测量模型。首先，面向具有多个产品的化工对象，借助k近邻法，以统计假设检验理论为依据，提出一种自适应局部化方法，获得多样性程度高的局部模型集合。然后，根据未知样本量化局部模型的泛化能力，通过选择性集成方法获得主导变量的估计值。此外，为了对主导变量估计值的精度进行评估，基于局部模型泛化误差，给出一种通用性高的模型性能评价方法。在仿真的盘尼西林生产过程上的运行结果验证了所提方法的有效性。

关键词: 化工过程, 多产品, 软测量, 集成学习, 模型性能评价

Abstract:

To handle characteristics of nonlinearity, time-variation and multi-product of chemical processes, a self-adaptive soft sensing method was developed under ensemble learning framework. Initially, a self-adaptive localization technique was proposed to construct ensemble of high diversified local models by statistical hypothesis testing theory and k-nearest neighbor method. Subsequently, based on generalization capabilities of quantified local models with online query sample, primary process variables were estimated through selective ensemble learning. Furthermore, in order to measure estimation accuracy of primary process variables, a highly universal method of model performance assessment was presented by using local model's generalization error. Simulation study on a penicillin fermentation process demonstrated effectiveness of the proposed method.

Key words: chemical processes, multi-product, soft sensor, ensemble learning, model performance assessment

中图分类号:

TP301.6

邵伟明, 田学民, 宋执环. 基于集成学习的多产品化工过程软测量建模方法[J]. 化工学报, 2018, 69(6): 2551-2559.

SHAO Weiming, TIAN Xuemin, SONG Zhihuan. Ensemble learning-based soft sensor method for multi-product chemical processes[J]. CIESC Journal, 2018, 69(6): 2551-2559.

参考文献 30

[1]	KADLEC P, GABRYS B, STRANDT S. Data-driven soft sensors in process industry[J]. Computers and Chemical Engineering, 2009, 33(4):795-814.
[2]	KANO M, FUJIWARA K. Virtual sensing technology in process industries:trends and challenges revealed by recent industrial application[J]. Journal of Chemical Engineering of Japan, 2013, 46(1):1-17.
[3]	邵伟明, 田学民, 王平. 基于递推PLS核算法的软测量在线学习方法[J]. 化工学报, 2012, 63(9):2887-2891. SHAO W M, TIAN X M, WANG P. Online learning soft sensor method based on recursive kernel algorithm for PLS[J]. CIESC Journal, 2012, 63(9):2887-2891.
[4]	曹鹏飞, 罗雄麟. 化工过程软测量建模方法研究进[J]. 化工学报, 2013, 64(3):788-800. CAO P F, LUO X L. Modeling of soft sensor for chemical process[J]. CIESC Journal, 2013, 64(3):788-800.
[5]	KADLEC P, GRBI? R, GABRYS B. Review of adaptation mechanisms for data-driven soft sensors[J]. Computers and Chemical Engineering, 2011, 35(1):1-24.
[6]	袁晓锋, 葛志强, 宋执环. 基于时间差分和局部加权偏最小二乘法的过程自适应软测量建模[J]. 化工学报, 2016, 67(3):724-728. YUAN X F, GE Z Q, SONG Z H. Adaptive soft sensor based on time difference model and locally weighted partial least squares regression[J]. CIESC Journal, 2016, 67(3):724-728.
[7]	李春义, 袁起民, 陈小博, 等. 两段提升管催化裂解多产丙烯研究[J]. 中国石油大学学报(自然科学版), 2007, 31(1):118-121. LI C Y, YUAN Q M, CHEN X B, et al. Maximizing yield of propylene by two-stage riser catalytic pyrolysis of heavy oil[J]. Journal of China University of Petroleum (Natural Science Edition), 2007, 31(1):118-121.
[8]	SHAO W M, TIAN X M. Adaptive soft sensor for quality prediction of chemical processes based on selective ensemble of local partial least squares models[J]. Chemical Engineering Research & Design, 2015, 95:113-132.
[9]	KANO M, OGAWA M. The state of the art in chemical process control in Japan:good practice and questionnaire survey[J]. Journal of Process Control, 2010, 20(9):969-982.
[10]	钟伟民, 李杰, 程辉, 等. 基于FCM聚类的气化炉温度多模型软测量建模[J]. 化工学报, 2012, 63(12):3951-3955. ZHONG W M, LI J, CHENG H, et al. A soft sensor multi-modeling for furnace temperature of gasifier based FCM clustering[J]. CIESC Journal, 2012, 63(12):3951-3955.
[11]	LIU Y, LI C, GAO Z. A novel unified correlation model using ensemble support vector regression for prediction of flooding velocity in randomly packed towers[J]. Journal of Industrial and Engineering Chemistry, 2014, 20(3):1109-1118.
[12]	LI X L, SU H Y, CHU J. Multiple model soft sensor based on affinity propagation, gaussian process and Bayesian committee machine[J]. Chinese Journal of Chemical Engineering, 2009, 17(1):95-99.
[13]	李琨, 韩莹, 黄海礁. 基于自动谱聚类与多极端学习机模型的油井油液含水率软测量[J]. 化工学报, 2016, 67(7):2925-2933. LI K, HAN Y, HUANG H J. Soft sensor method for moisture content of well oil based on automatic spectral clustering and multiple extreme learning[J]. CIESC Journal, 2016, 67(7):2925-2933.
[14]	JIN X, WANG S, HUANG B, et al. Multiple model based LPV soft sensor development with irregular/missing process output measurement[J]. Control Engineering Practice, 2012, 20(2):165-172.
[15]	KADLEC P, GABRYS B. Local learning-based adaptive soft sensor for catalyst activation prediction[J]. AIChE Journal, 2011, 57(5):1288-1301.
[16]	SHAO W M, TIAN X M, WANG P. Soft sensor development for nonlinear and time-varying processes based on supervised ensemble learning with improved process state partition[J]. Asia-Pacific Journal of Chemical Engineering, 2015, 10(2):282-296.
[17]	NI W, TAN S K, NG W J, et al. Localized, adaptive recursive partial least squares regression for dynamic system modeling[J]. Industrial & Engineering Chemistry Research, 2012, 51(23):8025-8039.
[18]	JIN H P, CHEN X G, WANG L, et al. Adaptive soft sensor development based on online ensemble Gaussian process regression for nonlinear time-varying batch processes[J]. Industrial & Engineering Chemistry Research, 2015, 54 (30):7320-7345.
[19]	JIN H P, CHEN X G, WANG L, et al. Dual learning-based online ensemble regression approach for adaptive soft sensor modeling of nonlinear time-varying processes[J]. Chemometrics and Intelligent Laboratory Systems, 2016, 151:228-244.
[20]	LIU J L, CHEN D S, SHEN J F. Development of self-validating soft sensors using fast moving window partial least squares[J]. Industrial & Engineering Chemistry Research, 2010, 49(22):11530-11546.
[21]	KANEKO H, ARAKAWA M, FUNATSU K. Applicability domains and accuracy of prediction of soft sensor models[J]. AIChE Journal, 2011, 57(6):1506-1513.
[22]	KANEKO H, FUNATSU K. Applicability domain of soft sensor models based on one-class support vector machine[J]. AIChE Journal, 2013, 59(6):2046-2050.
[23]	KANEKO H, FUNATSU K. Estimation of predictive accuracy of soft sensor models based on data density[J]. Chemometrics and Intelligent Laboratory Systems, 2013, 128(15):111-117.
[24]	GE Z Q, CHEN T, SONG Z H. Quality prediction for polypropylene production process based on CLGPR model[J]. Control Engineering Practice, 2011, 19(5):423-432.
[25]	YUAN X F, GE Z Q, SONG Z H. Locally weighted kernel principal component regression model for soft sensing of nonlinear and time-varying processes[J]. Industrial & Engineering Chemistry Research, 2014, 53(35):19736-13749.
[26]	YU J. Multiway Gaussian mixture model based adaptice kernel partialleast squares regression method for soft sensor estimation and quality prediction of nonlinear multi-phase batch processes[J]. Industrial & Engineering Chemistry Research, 2012, 51(40):13227-13237.
[27]	LINDGREN F, GELADI F, WOLD S. The kernel algorithm for PLS[J]. Journal of Chemometrics, 1993, 7(1):45-59.
[28]	QIN S. Recursive PLS algorithms for adaptive data modeling[J]. Computers & Chemical Engineering, 1998, 44(4/5):503-514.
[29]	GE Z Q, SONG Z H. A comparative study of just-in-time-learning based methods for online soft sensor modeling[J]. Chemometrics and Intelligent Laboratory Systems, 2010, 104(2):306-317.
[30]	SUYKENS J A K, VAN GESTEL T, DE BRABANTER J, et al. Least Squares Support Vector Machines[M]. Singapore:World Scientific, 2002:98-100.

基于集成学习的多产品化工过程软测量建模方法

Ensemble learning-based soft sensor method for multi-product chemical processes

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献 30

相关文章 15

编辑推荐

Metrics

本文评价

[1]	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.
[2]	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.
[3]	邵伟明, 韩文学, 宋伟, 杨勇, 陈灿, 赵东亚. 基于分布式贝叶斯隐马尔可夫回归的动态软测量建模方法[J]. 化工学报, 2023, 74(6): 2495-2502.
[4]	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.
[5]	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.
[6]	罗顺桦, 王振雷, 王昕. 基于二子空间协同训练算法的半监督软测量建模[J]. 化工学报, 2022, 73(3): 1270-1279.
[7]	刘聪, 谢莉, 杨慧中. 基于改进DPC的青霉素发酵过程多模型软测量建模[J]. 化工学报, 2021, 72(3): 1606-1615.
[8]	陈忠圣, 朱梅玉, 贺彦林, 徐圆, 朱群雄. 基于分位数回归CGAN的虚拟样本生成方法及其过程建模应用[J]. 化工学报, 2021, 72(3): 1529-1538.
[9]	薛峰, 李欣铜, 周琨, 魏志强, 葛晓霞, 葛志强, 宋凯. 基于GLSAFIS的氟化工过程操作单元可靠性监测[J]. 化工学报, 2021, 72(11): 5696-5706.
[10]	冯思琦, 罗雄麟. 模式切换类经济预测控制切换时间在线估计[J]. 化工学报, 2020, 71(S2): 225-240.
[11]	李东, 黄道平, 刘乙奇. 基于协同训练的半监督异构自适应软测量建模方法的研究[J]. 化工学报, 2020, 71(5): 2128-2138.
[12]	杜宇浩, 阎高伟, 李荣, 王芳. 基于局部线性嵌入的测地线流式核多工况软测量建模方法[J]. 化工学报, 2020, 71(3): 1278-1287.
[13]	杨逸俊,王振雷,王昕. 基于最近邻与神经网络融合模型的软测量建模方法[J]. 化工学报, 2020, 71(12): 5696-5705.
[14]	王雅欣,徐宝昌,徐朝农,董秀娟,许立伟. 基于工厂数据的注意力LSTM网络辨识方法[J]. 化工学报, 2020, 71(12): 5664-5671.
[15]	代学志,熊伟丽. 基于核极限学习机的快速主动学习方法及其软测量应用[J]. 化工学报, 2020, 71(11): 5226-5236.