基于DBN-ELM的聚丙烯熔融指数的软测量

doi:10.11949/j.issn.0438-1157.20161280

化工学报 ›› 2016, Vol. 67 ›› Issue (12): 5163-5168.DOI: 10.11949/j.issn.0438-1157.20161280

基于DBN-ELM的聚丙烯熔融指数的软测量

王宇红¹, 狄克松¹, 张姗¹, 尚超², 黄德先²

1 中国石油大学(华东)信息与控制工程学院, 山东青岛 266580;
2 清华大学自动化系, 北京 100084

收稿日期:2016-09-12 修回日期:2016-09-22 出版日期:2016-12-05 发布日期:2016-12-05
通讯作者: 王宇红(1970-),男,博士,教授。Wang@upc.edu.cn
基金资助:
山东省自然科学基金项目（2013ZRE28089）。

Melt index prediction of polypropylene based on DBN-ELM

WANG Yuhong¹, DI Kesong¹, ZHANG Shan¹, SHANG Chao², HUANG Dexian²

1 College of Information and Control Engineering, China University of Petroleum, Qingdao 266580, Shandong, China;
2 Department of Automation, Tsinghua University, Beijing 100084, China

Received:2016-09-12 Revised:2016-09-22 Online:2016-12-05 Published:2016-12-05
Supported by:
supported by the Natural Science Foundation of Shandong Province(2013ZRE28089).

摘要/Abstract

摘要：

针对聚丙烯熔融指数软测量中预测精度不高的缺点，将基于深度置信网络-极限学习机（DBN-ELM）的软测量方法应用到熔融指数的软测量中。与传统深度置信网络（DBN）不同的是，该方法将极限学习机（ELM）算法运用到深度置信网络的训练中。首先用深度置信网络对原始数据进行数值分析来提取特征，然后将提取的特征输入到极限学习机中进行训练，得到软测量模型。实验验证表明，与支持向量机和单纯的深度置信网络模型相比，该方法具有更高的测量精度。

关键词: 深度置信网络, 算法, 极限学习机, 数值分析, 特征提取, 实验验证

Abstract:

To solve the issue of low accuracy of the traditional soft sensor methods of polypropylene melt index, an approach based on deep belief network and extreme learning machine（DBN-ELM）was used to the melt index prediction of polypropylene. Traditional deep belief network(DBN) applied the deep learning to the learning process of the deep neural networks. Different from traditional deep belief network, this approach applied the extreme learning machine algorithm(ELM) to the learning process of DBN to improve the DBN model. Firstly, deep belief network was employed to extract effective features from vibration data by numerical analysis. Then, the effective features were put into the extreme learning machine to proceed model training to obtain the soft sensor model. The experimental validation showed that the method was more accuracy than the traditional method.

Key words: deep belief network, algorithm, extreme learning machine, numerical analysis, feature extraction, experimental validation

中图分类号:

TP273

王宇红, 狄克松, 张姗, 尚超, 黄德先. 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 Yuhong, DI Kesong, ZHANG Shan, SHANG Chao, HUANG Dexian. Melt index prediction of polypropylene based on DBN-ELM[J]. CIESC Journal, 2016, 67(12): 5163-5168.

参考文献 21

[1]	YI H S, AND J H K, HAN C, et al. Plantwide optimal grade transition for an industrial high-density polyethylene plant[J]. Industrial & Engineering Chemistry Research, 2003, 42(1):91-98.
[2]	AND F T, BIEGLER L T, SALDÍVARGUERRA E. Optimal grade transitions in the high-impact polystyrene polymerization process[J]. Industrial & Engineering Chemistry Research, 2006, 45(18):6175-6189.
[3]	SHARMIN R, SUNDARARAJ U, SHAH S, et al. Inferential sensors for estimation of polymer quality parameters:industrial application of a PLS-based soft sensor for a LDPE plant[J]. Chemical Engineering Science, 2006, 61(19):6372-6384.
[4]	WEI Y J, JIANG Y H, YAN F, et al. Three-stage decomposition modeling for quality of gas-phase polyethylene process based on adaptive hinging hyperplanes and impulse response template[J]. Ind. Eng. Chem. Res., 2013, 52(16):5747-5756.
[5]	马勇, 黄德先, 金以慧.基于支持向量机的软测量建模方法[J].信息与控制, 2004, 33(4):417-421. MA Y, HUANG D X, JIN Y H. Soft-sensor modeling method based on support vector machine[J]. Information and Control, 2004, 33(4):417-421.
[6]	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.
[7]	康岩, 卢慕超, 阎高伟.基于DBN-ELM的球磨机料位软测量方法研究[J].仪表技术与传感器, 2015,(4):73-75. KANG Y, LU M C, YAN G W. Soft sensor for ball mill fill level based on DBN-ELM model[J]. Instrument Technique and Sensor, 2015,(4):73-75.
[8]	王平, 田华阁, 田学民. Spheripol-Ⅱ双环管聚丙烯装置动态建模[J]. 计算机与应用化学, 2008, 25(7):827-831. WANG P, TIAN H G, TIAN X M. Dynamic modeling of Spheripol-Ⅱ propylene polymerization in dual-loop reactor[J]. Computers and Applied Chemistry, 2008, 25(7):827-831.
[9]	田华阁, 田学民, 邓晓刚. 基于Kalman-OLS的聚丙烯熔融指数软测量[J]. 控制工程, 2010,(S1):83-86. TIAN H G, TIAN X M, DENG X G. Polypropylene melt index soft sensor based on Kalman-Orthogonal least squares[J]. Control Engineering of China, 2010,(S1):83-86.
[10]	潘泽林, 夏陆岳, 周猛飞, 等. KPCA-SNNs的聚丙烯熔融指数软测量[J]. 计算机与应用化学, 2014, 31(2):203-206. PAN Z L, XIA L Y, ZHOU M F, et al. Soft sensor of polypropylene melt index based on KPCA-SNNs[J]. Computers and Applied Chemistry, 2014, 31(2):203-206.
[11]	LIU X, ZHAO C. Melt index prediction based on fuzzy neural networks and PSO algorithm with online correction strategy-s[J]. AIChE Journal, 2012, 58(4):1194-1202.
[12]	ZHANG M, LIU X.A soft sensor based on adaptive fuzzy neural network and support vector regression for industrial melt index prediction[J]. Chemometrics and Intelligent Laboratory Systems, 2013, 126(15):83-90.
[13]	LI J, LIU X, JIANG H, et al. Melt index prediction by adaptively aggregated RBF neural networks trained with novel ACO algorithm[J]. Journal of Applied Polymer Science, 2012, 125(2):829-1656.
[14]	蒋华琴, 刘兴高.免疫PSO_WLSSVM最优聚丙烯熔融指数预报[J]. 化工学报, 2012, 63(3):866-872. JIANG H Q, LIU X G. Optimal melt index prediction based on ICPSO_WLSSVM algorithm for industrial propylene polymerization[J]. CIESC Journal, 2012, 63(3):866-872.
[15]	HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786):504-507.
[16]	LANGKVIST M, KARLSSON L, LOUTFI A.A review of unsupervised feature learning and deep learning for time series modeling[J]. Pattern Recognition Letters, 2014, 42(1):11-24.
[17]	HINTON G E, OSINDERO S, TEH Y W. A fast learning algorithm for deep belief nets[J].Neural Computation, 2006, 18(7):1527-1554.
[18]	张春霞, 姬楠楠, 王冠伟.受限波尔兹曼机[J]. 工程数学学报, 2015,(2):159-173. ZHANG C X, JI N N, WANG G W. Restricted Boltzmann machines[J]. Chinese Journal of Engineering Mathematics, 2015,(2):159-173.
[19]	HUANG G B, ZHOU H, DING X, et al. Extreme learning maching for regression and multiclass classification[J]. IEEE, Transactions on System, Man, and Cybernetics, 2012, 42(2):513-529.
[20]	赵志勇, 李元香, 喻飞, 等.基于极限学习的深度学习算法[J]. 计算机工程与设计, 2015,(4):1022-1026. ZHAO Z Y, LI Y X, YU F, et al. Improved deep learning algorithm based on extreme learning machine[J]. Computer Engineering and Design, 2015,(4):1022-1026.
[21]	HUANG G B, ZHOU H, DING X, et al. Extreme learning machine for regression and multiclass classification.[J]. IEEE Transactions on Systems Man & Cybernetics Part B Cybernetics A Publication of the IEEE Systems Man & Cybernetics Society, 2012, 42(42):513-529.

基于DBN-ELM的聚丙烯熔融指数的软测量

Melt index prediction of polypropylene based on DBN-ELM

PDF (PC)

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献 21

相关文章 15

编辑推荐

Metrics

本文评价

[1]	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.
[2]	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.
[3]	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.
[4]	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.
[5]	周继鹏, 何文军, 李涛. 异形催化剂上乙烯催化氧化失活动力学反应工程计算[J]. 化工学报, 2023, 74(6): 2416-2426.
[6]	邵远哲, 赵忠盖, 刘飞. 基于共同趋势模型的非平稳过程质量相关故障检测方法[J]. 化工学报, 2023, 74(6): 2522-2537.
[7]	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.
[8]	李正涛, 袁志杰, 贺高红, 姜晓滨. 疏水界面上的NaCl液滴蒸发过程内环流调控机制研究[J]. 化工学报, 2023, 74(5): 1904-1913.
[9]	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.
[10]	许文烜, 江锦波, 彭新, 门日秀, 刘畅, 彭旭东. 宽速域三种典型型槽油气密封泄漏与成膜特性对比研究[J]. 化工学报, 2023, 74(4): 1660-1679.
[11]	罗来明, 张劲, 郭志斌, 王海宁, 卢善富, 相艳. 1~5 kW高温聚合物电解质膜燃料电池堆的理论模拟与组装测试[J]. 化工学报, 2023, 74(4): 1724-1734.
[12]	张生安, 刘桂莲. 高效太阳能电解水制氢系统及其性能的多目标优化[J]. 化工学报, 2023, 74(3): 1260-1274.
[13]	顾学荣, 刘硕士, 杨思宇. 基于并行EGO和代理模型辅助的多参数优化方法研究[J]. 化工学报, 2023, 74(3): 1205-1215.
[14]	袁海鸥, 叶方俊, 张硕, 罗祎青, 袁希钢. 考虑中间换热器的能量集成精馏序列合成[J]. 化工学报, 2023, 74(2): 796-806.
[15]	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.