基于深度集成支持向量机的工业过程软测量方法

doi:10.11949/j.issn.0438-1157.20171050

化工学报 ›› 2018, Vol. 69 ›› Issue (3): 1121-1128.DOI: 10.11949/j.issn.0438-1157.20171050

基于深度集成支持向量机的工业过程软测量方法

马建, 邓晓刚, 王磊

中国石油大学(华东)信息与控制工程学院, 山东青岛 266580

收稿日期:2017-08-02 修回日期:2017-10-19 出版日期:2018-03-05 发布日期:2018-03-05
通讯作者: 邓晓刚
基金资助:
国家自然科学基金项目（61403418，21606256）；山东省自然科学基金项目（ZR2014FL016，ZR2016FQ21，ZR2016BQ14）；青岛市应用基础研究计划项目（16-5-1-10-jch）；中央高校基本科研业务费专项资金（17CX02054）。

Industrial process soft sensor method based on deep learning ensemble support vector machine

MA Jian, DENG Xiaogang, WANG Lei

College of Information and Control Engineering, China University of Petroleum, Qingdao 266580, Shandong, China

Received:2017-08-02 Revised:2017-10-19 Online:2018-03-05 Published:2018-03-05
Supported by:
supported by the National Natural Science Foundation of China (61403418, 21606256), the Natural Science Foundation of Shandong Province(ZR2014FL016, ZR2016FQ21, ZR2016BQ14), the Application and Fundamental Research Project of Qingdao (16-5-1-10-jch) and the Fundamental Research Funds for the Central Universities (17CX02054).

摘要/Abstract

摘要：

基于支持向量机（SVM）的软测量建模方法已经在工业过程控制领域得到广泛应用，然而传统支持向量机直接针对原始测量变量建立模型，未能充分挖掘数据的内在特征信息以提高预测精度。针对该问题，本文提出一种基于深度集成支持向量机（DESVM）的软测量建模方法。该方法首先利用深度置信网络（DBN）来对数据进行深层次的信息挖掘，提取出数据的内在特征，然后引入基于Bagging算法的集成学习策略，构建基于深度数据特征的集成支持向量机模型，以提升软测量预测模型的泛化能力。最后通过数值系统和真实工业数据对方法进行应用分析，结果表明本文提出的方法能够有效提升支持向量机软测量模型的预测精度，能够更好地预测过程质量指标的变化。

关键词: 支持向量机, 软测量, 深度置信网络, 集成学习, 预测

Abstract:

The soft sensor modeling method based on support vector machine (SVM) has been widely used in the field of industrial process control. However, the traditional support vector machine directly models the original measurement variables without fully extracting the intrinsic data information to improve the prediction accuracy. Aiming at this problem, a soft sensor modeling method based on deep ensemble support vector machine (DESVM) is proposed in this paper. Firstly, this method uses the deep belief network (DBN) to carry on the deep information mining, and extracts the intrinsic data characteristic. Then the ensemble learning strategy based on the Bagging algorithm is introduced to construct the ensemble support vector machine model based on the deep data characteristic, which can enhance generalization ability of soft measurement prediction model. Finally, the applications on a numerical system and real industrial data are used to validate the proposed method. The results show that the proposed method can effectively improve the prediction accuracy of the soft vector model of support vector machine and can predict the change of process quality index better.

Key words: support vector machine, soft sensor, deep belief network, ensemble learning, prediction

中图分类号:

TP277

马建, 邓晓刚, 王磊. 基于深度集成支持向量机的工业过程软测量方法[J]. 化工学报, 2018, 69(3): 1121-1128.

MA Jian, DENG Xiaogang, WANG Lei. Industrial process soft sensor method based on deep learning ensemble support vector machine[J]. CIESC Journal, 2018, 69(3): 1121-1128.

参考文献 30

[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]	BAKIROV R, GABRYS B, FAY D. Multiple adaptive mechanisms for data-driven soft sensors[J]. Computers & Chemical Engineering, 2016, 96:42-54
[3]	曹鹏飞, 罗雄麟. 化工过程软测量建模方法研究进展[J]. 化工学报, 2013, 64(3):788-800. CAO P F, LUO X L. Advances in soft process modeling of chemical processes[J]. CIESC Journal, 2013, 64(3):788-800.
[4]	徐文艳, 王豪. 基于机理建模的聚醋酸乙烯浓度软测量技术[J]. 化工自动化及仪表, 2010, 37(7):70-71. XU W Y, WANG H. Soft sensor technology based on mechanism modeling of polyvinyl acetate concentration[J]. Control and Instruments in Chemical Industry, 2010, 37(7):70-71.
[5]	HAIMI H, MULAS M, CORONA F, et al. Data-derived soft-sensors for biological wastewater treatment plants:an overview[J]. Environmental Modelling &Software, 2013, 47(3):88-107.
[6]	王改堂, 李平, 苏成利. 基于多K最近邻回归算法的软测量模型[J]. 信息与控制, 2011, 40(5):639-645. WANG G T, LI P, SU C L. Soft sensor model based on multi-K nearest neighbor regression algorithm[J]. Information and Control, 2011, 40(5):639-645.
[7]	SHAO W, TIAN X, WANG P, et al. Online soft sensor design using local partial least squares models with adaptive process state partition[J]. Chemometrics and Intelligent Laboratory Systems, 2015, 144:108-121
[8]	韩红桂, 陈治远, 乔俊飞, 等. 基于区间二型模糊神经网络的出水氨氮软测量[J]. 化工学报, 2017, 68(3):1032-1040. HAN H G, CHEN Z Y, QIAO J F, et al. Soft sensor of effluent ammonia nitrogen based on interval-type fuzzy neural network[J]. CIESC Journal, 2017, 68(3):1032-1040.
[9]	田学民, 王强, 邓晓刚. 一种引入动量项的小波神经网络软测量建模方法[J]. 化工学报, 2011, 62(8):2238-2242. TIAN X M, WANG Q, DENG X G. A soft sensor modeling method based on wavelet neural network with impulsive terms[J]. CIESC Journal, 2011, 62(8):2238-2242.
[10]	LIU G, ZHOU D, XU H, et al. Model optimization of SVM for a fermentation soft sensor[J]. Expert Systems with Applications, 2010, 37(4):2708-2713.
[11]	ZHANG Y, LIANG Y. Research on soft sensor based on support vector regression for particle size of grinding and classification process[C]//IEEE Chinese Control and Decision Conference. 2016:6708-6713.
[12]	赵超, 李俊, 戴坤成, 等. 基于自适应加权最小二乘支持向量机的青霉素发酵过程软测量建模[J]. 南京理工大学学报(自然科学版), 2017, 41(1):100-107. ZHAO C, LI J, DAI K C, et al. Soft sensor modeling of penicillin fermentation process based on adaptive weighted least squares support vector machine[J]. Journal of Nanjing University of Science and Technology (Natural Science Edition), 2017, 41(1):100-107.
[13]	王平, 田华阁, 田学民, 等. 一种基于增量式SVR学习的在线自适应建模方法[J]. 化工学报, 2010, 61(8):2040-2045. WANG P, TIAN H G, TIAN X M, et al. An online adaptive modeling method based on incremental SVR learning[J]. CIESC Journal, 2010, 61(8):2040-2045.
[14]	CHENG Z, LIU X. Optimal online soft sensor for product quality monitoring in propylene polymerization process[J]. Neurocomputing, 2015, 149:1216-1224
[15]	阎威武, 朱宏栋, 邵惠鹤. 基于最小二乘支持向量机的软测量建模[J]. 系统仿真学报, 2003, 15(10):1494-1496. YAN W W, ZHU H D, SHAO H H. Soft sensor modeling based on least squares support vector machine[J]. Journal of System Simulation, 2003, 15(10):1494-1496.
[16]	LI Q, XING L, LIU W, et al. Adaptive soft sensor based on a moving window just-in-time learning LS-SVM for distillation processes[J]. IFAC-PapersOnLine, 2015, 48(28):51-56
[17]	汪世杰, 王振雷, 王昕. 基于JIT-MOSVR的软测量方法及应用[J]. 化工学报, 2017, 68(3):947-955. WANG S J, WANG Z L, WANG X. Soft sensor method based on JIT-MOSVR and its application[J]. CIESC Journal, 2017, 68(3):947-955.
[18]	LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521(7553):436-444.
[19]	王宇红, 狄克松, 张姗, 等. 基于DBN-ELM的聚丙烯熔融指数的软测量[J]. 化工学报, 2016, 67(12):5163-5168. WANG Y H, DI K S, ZHANG S, et al. Soft measurement of polypropylene melt index based on DBN-ELM[J]. CIESC Journal, 2016, 67(12):5163-5168.
[20]	刘瑞兰, 毛佳敏. 基于深度置信网络的4-CBA软测量建模[J]. 计算机工程与应用, 2017, 53(6):227-230. LIU R L, MAO J M. Prediction of 4-CBA soft sensor based on deep belief network[J]. Journal of Computer Engineering and Applications, 2017, 53(6):227-230.
[21]	YAN W, TANG D, LIN Y. A data-driven soft sensor modeling method based on deep learning and its application[J]. IEEE Transactions on Industrial Electronics, 2017, 64(5):4237-4245.
[22]	SHANG C, YANG F, HUANG D, et al. Data-driven soft sensor development based on deep learning technique[J]. Journal of Process Control, 2014, 24(3):223-233.
[23]	LU M, KANG Y, HAN X, et al. Soft sensor modeling of mill level based on deep belief network[C]//The 26th Chinese Control and Decision Conference.2014:189-193.
[24]	CORTES C, VAPNIK V. Support-vector networks[J]. Machine Learning, 1995, 20(3):273-297.
[25]	LIU W, WANG Z, LIU X, et al. A survey of deep neural network architectures and their applications[J]. Neurocomputing, 2017, 234:11-26.
[26]	KHATAMI A, KHOSRAVI A, NGUYEN T, et al. Medical image analysis using wavelet transform and deep belief networks[J]. Expert Systems with Applications, 2017, 86:190-198.
[27]	田旺兰, 李加升. 改进运用深度置信网络的语音端点检测方法[J]. 计算机工程与应用, 2014, 50(20):207-210. TIAN W L, LI J S. Improved voice endpoint detection method using deep belief network[J]. Computer Engineering and Applications, 2014, 50(20):207-210.
[28]	ASUNCION A U, LIU Q, IHLER A T, et al. Learning with blocks:composite likelihood and contrastive divergence[J]. Journal of Machine Learning Research, 2010, 9:33-40.
[29]	BREIMAN L. Bagging predictors[J]. Machine Learning, 1996, 24(2):123-140.
[30]	孙茂伟, 杨慧中. 基于改进Bagging算法的高斯过程集成软测量建模[J]. 化工学报, 2016, 67(4):1386-1391. SUN M W, YANG H Z. Ensemble soft sensor modeling of Gaussian process based on improved Bagging algorithm[J]. CIESC Journal, 2016, 67(4):1386-1391.

基于深度集成支持向量机的工业过程软测量方法

Industrial process soft sensor method based on deep learning ensemble support vector machine

PDF (PC)

可视化

被引次数

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]	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.
[2]	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.
[3]	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.
[4]	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.
[5]	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.
[6]	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.
[7]	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.
[8]	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.
[9]	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.
[10]	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.
[11]	陈家辉, 杨鑫泽, 陈顾中, 宋震, 漆志文. 以离子液体密度为例的分子性质预测模型建模方法探讨[J]. 化工学报, 2023, 74(2): 630-641.
[12]	杨静, 林振康, 汤君, 樊铖, 孙克宁. 电池系统的故障特征以及多故障的诊断与识别[J]. 化工学报, 2022, 73(8): 3394-3405.
[13]	周新杰, 王建林, 艾兴聪, 随恩光, 王汝童. 基于IDPC-RVM的多模态间歇过程质量变量在线预测[J]. 化工学报, 2022, 73(7): 3120-3130.
[14]	吴子睿, 孙瑞, 石凌峰, 田华, 王轩, 舒歌群. CO₂混合工质的气液相平衡的混合规则对比与预测研究[J]. 化工学报, 2022, 73(4): 1483-1492.
[15]	任嘉辉, 刘豫, 刘朝, 刘浪, 李莹. 基于分子指纹和拓扑指数的工质临界温度理论预测[J]. 化工学报, 2022, 73(4): 1493-1500.