选择性集成LTDGPR模型的自适应软测量建模方法

doi:10.11949/j.issn.0438-1157.20161570

化工学报 ›› 2017, Vol. 68 ›› Issue (3): 984-991.DOI: 10.11949/j.issn.0438-1157.20161570

选择性集成LTDGPR模型的自适应软测量建模方法

熊伟丽^1,2, 李妍君¹

1 江南大学物联网工程学院自动化研究所, 江苏无锡 214122;
2 轻工过程先进控制教育部重点实验室, 江苏无锡 214122

收稿日期:2016-11-09 修回日期:2016-11-17 出版日期:2017-03-05 发布日期:2017-03-05
通讯作者: 熊伟丽,weili_xiong@jiangnan.edu.cn
基金资助:
国家自然科学基金项目（21206053，21276111）；江苏省“六大人才高峰”项目（2013-DZXX-043）。

Adaptive soft sensor based on selective ensemble of LTDGPR models

XIONG Weili^1,2, LI Yanjun¹

1 Institute of Automation, School of Internet of Things Engineering, Jiangnan University, Wuxi 214122, Jiangsu, China;
2 Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Jiangnan University, Wuxi 214122, Jiangsu, China

Received:2016-11-09 Revised:2016-11-17 Online:2017-03-05 Published:2017-03-05
Contact: 10.11949/j.issn.0438-1157.20161570
Supported by:
supported by the National Natural Science Foundation of China (21206053,21276111) and the Six Talent Peaks Project in Jiangsu Province (2013-DZXX-043).

摘要/Abstract

摘要：

随着时间的增加，传统时间差（TD）模型会出现性能显著下降的问题。为了提高TD模型的可靠性和预测精度，同时考虑过程的时滞特征，基于一种选择性集成策略，提出一种局部时间差高斯过程回归（LTDGPR）模型的自适应软测量建模方法。首先，提取出数据库中的时滞动态信息，对建模数据进行重构；然后，采取局部化策略对差分后的重构样本进行统计划分，得到LTDGPR模型集。对于新来的输入样本，选择部分泛化能力强的LTDGPR模型进行集成，估计出含一定时间差的主导变量动态偏移值；最后，基于TD模型思想对当前时刻主导变量值进行在线预测。通过脱丁烷塔过程的数据建模仿真研究，验证了所提方法的有效性和精度。

关键词: 选择性集成, 时间差模型, 参数识别, 动态建模, 化学过程

Abstract:

Traditional time difference (TD) model may deteriorate as time increases. In order to enhance reliability and prediction accuracy of TD model, an adaptive soft sensor was proposed on the basis of a selective ensemble of local time difference Gaussian process regression (LTDGPR) models and consideration of process time-delay characteristics. First, data for modelling was reconstructed by time delay and dynamic information extracted from database. Then, an adaptive localization step was used to statistically classify the reconstructed time-difference dataset and to establish an LTDGPR model set. For new input samples, prediction of dynamic drift for primary variables at certain time lapse was achieved through selective ensemble of LTDGPR models which had strong generalization capability. Finally, spontaneous online prediction of primary variable was achieved on the basis of TD model theory. Simulation results of a real debutanizer process indicated the effectiveness and accuracy of the proposed soft sensor.

Key words: selective ensemble, TD model, parameter identification, dynamic modelling, chemical processes

中图分类号:

TP391.9

熊伟丽, 李妍君. 选择性集成LTDGPR模型的自适应软测量建模方法[J]. 化工学报, 2017, 68(3): 984-991.

XIONG Weili, LI Yanjun. Adaptive soft sensor based on selective ensemble of LTDGPR models[J]. CIESC Journal, 2017, 68(3): 984-991.

参考文献 31

[1]	KADLEC P, GABRYS B, STRANDT S. Data-driven soft sensors in the process industry[J]. Computers & Chemical Engineering, 2009, 33(4):795-814.
[2]	FORTUNA L, GRAZIANI S, RIZZO A, et al. Soft Sensors for Monitoring and Control of Industrial Processes[M]. Berlin:Springer Science & Business Media, 2007:15-39.
[3]	KHATIBISEPEHR S, HUANG B, KHARE S. Design of inferential sensors in the process industry:a review of Bayesian methods[J]. Journal of Process Control, 2013, 23(10):1575-1596.
[4]	YUAN X, GE Z, YE L, et al. Supervised neighborhood preserving embedding for feature extraction and its application for soft sensor modeling[J]. Journal of Chemometrics, 2016, 30(8):430-441.
[5]	熊伟丽, 李妍君, 姚乐, 等. 一种动态校正的AGMM-GPR多模型软测量建模方法[J]. 大连理工大学学报, 2016, 56(1):77-85. XIONG W L, LI Y J, YAO L, et al. A dynamically corrected AGMM-GPR multi-model soft sensor modeling method[J]. Journal of Dalian University of Technology, 2016, 56(1):77-85.
[6]	张伟, 熊伟丽, 徐保国. 基于实时学习的高斯过程回归多模型融合建模[J]. 信息与控制, 2015, 44(4):487-492. ZHANG W, XIONG W L, XU B G. Multi-model combination modeling based on just-in-time learning using Gaussian process regression[J]. Information and Control, 2015, 44(4):487-492.
[7]	YUAN X F, YE L J, BAO L, et al. Nonlinear feature extraction for soft sensor modeling based on weighted probabilistic PCA[J]. Chemometrics and Intelligent Laboratory Systems, 2015, 147(2015):167-175.
[8]	KADLEC P, GABRYS B. Local learning-based adaptive soft sensor for catalyst activation prediction[J]. AIChE Journal, 2011, 57(5):1288-1301.
[9]	KOMULAINEN T, SOURANDER M, JÄMSÄ-JOUNELA S L. An online application of dynamic PLS to a dearomatization process[J]. Computers & Chemical Engineering, 2004, 28(12):2611-2619.
[10]	ZHANG J, JIN Q B, XU Y M. Inferential estimation of polymer melt index using sequentially trained bootstrap aggregated neural networks[J]. Chemical Engineering and Technology, 2006, 29(4):442-448.
[11]	阮宏镁, 田学民, 王平. 基于联合互信息的动态软测量方法[J]. 化工学报, 2014, 65(11):4497-4502. RUAN H M, TIAN X M, WANG P. Dynamic soft sensor method based on joint mutual information[J]. CIESC Journal, 2014, 65(11):4497-4502.
[12]	RAHMAN M M, IMTIAZ S A, HAWBOLDT K. A hybrid input variable selection method for building soft sensor from correlated process variables[J]. Chemometrics and Intelligent Laboratory Systems, 2016, 157(2016):67-77.
[13]	KIM S, KANO M, HASEBE S, et al. Long-term industrial applications of inferential control based on just-in-time soft-sensors:economical impact and challenges[J]. Industrial & Engineering Chemistry Research, 2013, 52(35):12346-12356.
[14]	KADLEC P, GRBIC R, GABRYS B. Review of adaptation mechanisms for data-driven soft sensors[J]. Computers & Chemical Engineering, 2011, 35(1):1-24.
[15]	KANEKO H, OKADA T, FUNATSU K. Selective use of adaptive soft sensors based on process state[J]. Industrial & Engineering Chemistry Research, 2014, 53(41):15962-15968.
[16]	ZHANG W, LI Y, XIONG W, et al. Adaptive soft sensor for online prediction based on enhanced moving window GPR[C]//Control, Automation and Information Sciences (ICCAIS), 2015 International Conference on. IEEE, 2015:291-296.
[17]	XU O G, LIU J F, FU Y F, et al. Dual updating strategy for moving-window partial least-squares based on model performance assessment[J]. Industrial & Engineering Chemistry Research, 2015, 54(19):5273-5284.
[18]	DAYAL B S, MACGREGOR J F. Recursive exponentially weighted PLS and its applications to adaptive control and prediction[J]. Journal of Process Control, 1997, 7(3):169-179.
[19]	MATIAS T, SOUZA F, ARAUJO R, et al. On-line sequential extreme learning machine based on recursive partial least squares[J]. Journal of Process Control, 2015, 27:15-21.
[20]	LIU Y Q, HUANG D P, LI Y. Development of interval soft sensors using enhanced just-in-time learning and inductive confidence predictor[J]. Industrial & Engineering Chemistry research, 2012, 51(8):3356-3367.
[21]	FUJIWARA K, KANO M, HASEBE S, et al. Soft-sensor development using correlation-based just-in-time modeling[J]. AIChE Journal, 2009, 55(7):1754-1765.
[22]	KANEKO H, FUNATSU K. Moving window and just-in-time soft sensor model based on time differences considering a small number of measurements[J]. Industrial & Engineering Chemistry Research, 2015, 54(2):700-704.
[23]	KANEKO H, FUNATSU K. Classification of the degradation of soft sensor models and discussion on adaptive models[J]. AIChE Journal, 2013, 59(7):2339-2347.
[24]	袁小锋, 葛志强, 宋执环. 基于时间差分和局部加权偏最小二乘算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.
[25]	WANG L, JIN H, CHEN X, et al. Soft sensor development based on the hierarchical ensemble of Gaussian process regression models for nonlinear and non-Gaussian chemical processes[J]. Industrial & Engineering Chemistry Research, 2016, 55(28):7704-7719.
[26]	YANG K, JIN H, CHEN X, et al. Soft sensor development for online quality prediction of industrial batch rubber mixing process using ensemble just-in-time Gaussian process regression models[J]. Chemometrics and Intelligent Laboratory Systems, 2016, 155(2016):170-182.
[27]	JIN H, CHEN X, 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(2016):228-244.
[28]	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(2015):113-132.
[29]	JIN H, CHEN X,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.
[30]	LIN Y, CUNNINGHAM G A. A new approach to fuzzy-neural system modeling[J]. IEEE Transactions on Fuzzy Systems, 1995, 3(2):190-198.
[31]	RASMUSSEN C E, WILLIAMS C K I. Gaussian Processes for Machine Learning[M]. Cambridge:The MIT Press, 2006:8-29.

选择性集成LTDGPR模型的自适应软测量建模方法

Adaptive soft sensor based on selective ensemble of LTDGPR models

PDF (PC)

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献 31

相关文章 15

编辑推荐

Metrics

本文评价

[1]	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.
[2]	胡月, 马守骏, 蹇锡高, 翁志焕. 新型聚芳醚腈固化邻苯二甲腈树脂的研究[J]. 化工学报, 2023, 74(2): 871-882.
[3]	王琨, 侍洪波, 谭帅, 宋冰, 陶阳. 局部时差约束邻域保持嵌入算法在故障检测中的应用[J]. 化工学报, 2022, 73(7): 3109-3119.
[4]	周乐, 沈程凯, 吴超, 侯北平, 宋执环. 深度融合特征提取网络及其在化工过程软测量中的应用[J]. 化工学报, 2022, 73(7): 3156-3165.
[5]	李淼, 赵虹, 姜标, 陈思远, 闫龙. 煤制乙炔关键中间体BaC₂合成的热力学分析[J]. 化工学报, 2022, 73(5): 1908-1919.
[6]	高欢, 丁国良, 周发贤, 庄大伟. R410A制冷剂在润滑油中的动态析出特性的研究[J]. 化工学报, 2022, 73(3): 1054-1062.
[7]	刘恒源, 王海辉, 徐建鸿. 电催化氮还原合成氨电化学系统研究进展[J]. 化工学报, 2022, 73(1): 32-45.
[8]	袁壮, 凌逸群, 杨哲, 李传坤. 基于TA-ConvBiLSTM的化工过程关键工艺参数预测[J]. 化工学报, 2022, 73(1): 342-351.
[9]	郭林新, 马养民, 强涛涛, 任龙芳. 植物单宁的结构改性研究进展[J]. 化工学报, 2021, 72(5): 2448-2464.
[10]	石珊珊, 魏爱博, 张小斌. 液氮超声空化CFD模拟及实验研究[J]. 化工学报, 2021, 72(4): 1930-1938.
[11]	徐斌. 基于改进差分进化算法的质子交换膜燃料电池模型参数优化识别[J]. 化工学报, 2021, 72(3): 1512-1520.
[12]	王晓慧, 王延江, 邓晓刚, 张政. 基于加权深度支持向量数据描述的工业过程故障检测[J]. 化工学报, 2021, 72(11): 5707-5716.
[13]	孟繁鑫, 孙佳宁, 周月, 高赞军, 程定斌. 飞机环控系统空气循环机仿真建模及试验校核[J]. 化工学报, 2020, 71(S1): 328-334.
[14]	尹林子, 关羽吟, 蒋朝辉, 许雪梅. 基于k-means++的高炉铁水硅含量数据优选方法[J]. 化工学报, 2020, 71(8): 3661-3670.
[15]	周红标, 张钰, 柏小颖, 刘保连, 赵环宇. 基于自适应模糊神经网络的非线性系统模型预测控制[J]. 化工学报, 2020, 71(7): 3201-3212.