基于Ms-LWPLS的化工过程网络化性能分级评估方法

doi:10.11949/j.issn.0438-1157.20181369

化工学报 ›› 2019, Vol. 70 ›› Issue (S1): 141-149.DOI: 10.11949/j.issn.0438-1157.20181369

基于Ms-LWPLS的化工过程网络化性能分级评估方法

曹晨鑫¹(),杜玉鹏¹,王昕²(),王振雷¹()

1. 华东理工大学化工过程先进控制和优化技术教育部重点实验室，上海 200237
2. 上海交通大学电工电子实验教学中心，上海 200240

收稿日期:2018-11-18 修回日期:2018-12-25 出版日期:2019-03-31 发布日期:2019-03-31
通讯作者: 王昕,王振雷
作者简介:<named-content content-type="corresp-name">曹晨鑫</named-content>（1994—），男，硕士研究生，<email>296883892@qq.com</email>|王昕（1972—），男，博士，副教授，<email>wangxin26@sjtu.edu.cn</email>|王振雷（1975—），男，博士，教授，<email>wangzhen_1@ecust.edu.cn</email>
基金资助:
国家自然科学基金项目(61673268);国家自然科学基金重点项目(61533003);国家自然科学基金重大项目(61590922);中央高校基本科研业务费专项资金(222201814043)

Networked grading performance assessment method of chemical process based on Ms-LWPLS

Chenxin CAO¹(),Yupeng DU¹,Xin WANG²(),Zhenlei WANG¹()

1. Key Laboratory of Advanced Control and Optimization for Chemical Processes, East China University of Science and Technology, Shanghai 200237, China
2. Electrical and Electronic Experimental Teaching Center, Shanghai Jiao Tong University, Shanghai 200240, China

Received:2018-11-18 Revised:2018-12-25 Online:2019-03-31 Published:2019-03-31
Contact: Xin WANG,Zhenlei WANG

摘要/Abstract

摘要：

针对化工过程输入输出数据间非线性关系问题，提出一种基于多数据空间局部加权潜结构映射(multi-space locally weighted projection to latent structures，Ms-LWPLS)的网络化性能分级评估方法。该方法将历史数据分成不同性能等级的集合，利用Ms-LWPLS方法提取不同性能等级训练数据的过程变化，获得训练数据与性能等级标签之间的非线性映射结构，实现输入数据与性能等级之间的网络化“离线建模”。得到模型后，以数据滑动时间窗为评估单元，将滑动窗口数据输入到训练好的神经网络模型中，根据网络输出划分过程当前性能等级，并构造过渡性能系数，将稳态性能等级和过渡性能等级进行识别和区分。最后，将该方法应用到乙烯裂解过程在线性能评估中，说明此性能评估方法的有效性和准确性。

关键词: 多数据空间, 局部加权潜结构映射, 非线性, 神经网络, 过渡, 稳态, 在线评估

Abstract:

A networked performance assessment method based on multi-space locally weighted projection to latent structures (Ms-LWPLS) is proposed to solve the nonlinear relationship between input and output data of chemical process. This method divides the historical training datasets into different sets of performance grades, extracting the process changes of different performance grade of training datasets by Ms-LWPLS method. This method obtains the latent structures accurately by matching the training datasets and performance grade labels through the non-linear networked structure. The“off-line modeling”is achieved by the trained neural network. With the model obtained, the sliding window is used as the assessment unit, working as the input data into the trained neural network model. The current performance grade is identified according to the network output and the transition performance coefficient is constructed. The steady-state performance grades and the transition performance grades are recognized and distinguished. Finally, the method is applied to the online performance assessment of ethylene cracking process, which shows the effectiveness and accuracy of the performance assessment method proposed.

Key words: multi-space, locally weighted projection to latent structures, nonlinearity, neural network, transition, steady state, online assessment

中图分类号:

TP 273

曹晨鑫, 杜玉鹏, 王昕, 王振雷. 基于Ms-LWPLS的化工过程网络化性能分级评估方法[J]. 化工学报, 2019, 70(S1): 141-149.

Chenxin CAO, Yupeng DU, Xin WANG, Zhenlei WANG. Networked grading performance assessment method of chemical process based on Ms-LWPLS[J]. CIESC Journal, 2019, 70(S1): 141-149.

图/表 10

图1 性能等级数据离线建模过程

Fig.1 Offline modeling process of performance grade data

图2 不经过滑动时间窗的数据采样点各通道输出情况

Fig. 2 Sample curves of channel outputs without sliding data window

图3 乙烯裂解炉工艺图

Fig.3 Ethylene cracking furnace process diagram

表1 乙烯裂解炉过程变量

Table 1 Ethylene cracking furnace process variables

No.	变量	描述	单位
1	$ρ N A P$	裂解原料密度	kg·m^-3
2	C_NP	正链烷浓度	%
3	C_IP	异构烷烃浓度	%
4	C_OLE	烯烃浓度	%
5	C_NAP	环烷烃浓度	%
6	C_BTX	芳烃浓度	%
7	F_feed	原料流量	t·h^-1
8	F_DS	稀释蒸汽量	t·h^-1
9	F_Bfuel	底部燃料流量	m³·h^-1
10	F_Sfuel	侧壁燃料流量	m³·h^-1
11	C_o₂	排烟氧含量	%
12	T_g₁	排烟温度1	℃
13	T_g₂	排烟温度2	℃
14	F_ss	高压蒸汽流量	kg·h^-1
15	T_ss	高压蒸汽温度	℃
16	COT	裂解出口温度	℃
17	T_HK	初镏点温度	℃
18	T_KK	终镏点温度	℃

表1 乙烯裂解炉过程变量

Table 1 Ethylene cracking furnace process variables

No.	变量	描述	单位
1	$ρ N A P$	裂解原料密度	kg·m^-3
2	C_NP	正链烷浓度	%
3	C_IP	异构烷烃浓度	%
4	C_OLE	烯烃浓度	%
5	C_NAP	环烷烃浓度	%
6	C_BTX	芳烃浓度	%
7	F_feed	原料流量	t·h^-1
8	F_DS	稀释蒸汽量	t·h^-1
9	F_Bfuel	底部燃料流量	m³·h^-1
10	F_Sfuel	侧壁燃料流量	m³·h^-1
11	C_o₂	排烟氧含量	%
12	T_g₁	排烟温度1	℃
13	T_g₂	排烟温度2	℃
14	F_ss	高压蒸汽流量	kg·h^-1
15	T_ss	高压蒸汽温度	℃
16	COT	裂解出口温度	℃
17	T_HK	初镏点温度	℃
18	T_KK	终镏点温度	℃

图4 基于PLS-NN的在线评估结果

Fig.4 PLS-NN-based online assessment results

图5 基于Ms-LWPLS-NN的在线评估结果

Fig.5 Ms-LWPLS-NN-based online assessment results

图6 基于PLS-NN的在线评估过渡性能系数

Fig.6 Performance transition coefficient based on PLS-NN online assessment method

图7 基于Ms-LWPLS-NN的在线评估过渡性能系数

Fig.7 Performance transition coefficient based on Ms-LWPLS-NN online assessment method

表2 在线评估结果与实际情况对比

Table 2 Comparison of online assessment result and actual condition

性能等级	实际情况	PLS-NN	Ms-LWPLS-NN
最优	1—442	1—100 133—454	1—451
过渡	443—486	455—493	452—492
一般	487—994	494—1023	493—1026
过渡	995—1033	1023—1038	1027—1045
较差	1034—1250	1039—1101 1122—1250	1046—1250
过渡	—	101—132 1102—1121	—
准确率	—	90.73%	94.18%

图8 基于Ms-LWPLS-NN的在线分级性能评估等级分布

Fig.8 Performance grade distribution based on Ms-LWPLS-NN online grading assessment method

参考文献 31

1	HarrisT J. Assessment of control loop performance [J]. Canadian Journal of Chemical Engineering, 1989, 67(5): 856-861.
2	HarrisT J, BoudreauF, MacgregorJ F. Performance assessment of multivariable feedback controllers [J]. Automatica, 1996, 32(11): 1505-1518.
3	HuangB, KwokE K, ShahS L. Good, bad or optimal? Performance assessment of multivariable processes [J]. Automatica, 1997, 33(6): 1175-1183.
4	HuangB, ShahS L. Practical issues in multivariable feedback control performance assessment [J]. Journal of Process Control, 1997, 8(5): 421-430.
5	HuangB, DingS X, ThornhillN. Practical solutions to multivariate feedback control performance assessment problem: reduced a-priori knowledge of interactor matrix [J]. Journal of Process Control, 2005, 15(5): 573-583.
6	HuangB, DingS X, ThornhillN. Alternative solutions to multi-variate control performance assessment problems [J]. Journal of Process Control, 2006, 16(5): 457-471.
7	YuJ, QinS J. Statistical MIMO controller performance monitoring(Ⅰ): Data-driven covariance benchmark [J]. Journal of Process Control, 2008, 18(3): 277-296.
8	YuJ, QinS J. Statistical MIMO controller performance monitoring(Ⅱ): Performance diagnosis [J]. Journal of Process Control, 2008, 18(3): 297-319.
9	QinS J. Survey on data-driven industrial process monitoring and diagnosis [J]. Annual Reviews in Control, 2012, 36(2): 220-234.
10	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.
	ZhaoC H, WangF L, YaoY, et al. Phase-based statistical modeling, online monitoring and quality prediction for batch processes [J]. Acta Automatica Sinica, 2010, 36(3): 366-374.
11	YanL, WangF, ChangY. Online fuzzy assessment of operating performance and cause identification of nonoptimal grades for industrial processes [J]. Industrial & Engineering Chemistry Research, 2013, 52(50): 18022-18030.
12	LiuY, ChangY, WangF. Online process operating performance assessment and nonoptimal cause identification for industrial processes [J]. Journal of Process Control, 2014, 24(10): 1548-1555.
13	LiuY, WangF, ChangY. Operating optimality assessment based on optimality related variations and nonoptimal cause identification for industrial processes[J]. Journal of Process Control, 2016, 39: 11-20.
14	ZhaoC, GaoF, NiuD, et al. A two-step basis vector extraction strategy for multiset variable correlation analysis [J]. Chemometrics & Intelligent Laboratory Systems, 2011, 107(1): 147-154.
15	LiuY, ChangY, WangF. Online process operating performance assessment and nonoptimal cause identification for industrial processes [J]. Journal of Process Control, 2014, 24(10): 1548-1555.
16	LiG, QinS J, ZhouD. Geometric properties of partial least squares for process monitoring[J]. Automatica, 2010, 46(1): 204-210.
17	ZhouD H, LiG, QinS J. Total projection to latent structures for process monitoring [J]. AIChE Journal, 2010, 56(1): 168-178.
18	赵小强, 薛永飞. 基于核 T-PLS 的化工过程故障检测算法[J]. 化工学报, 2013, 64(12): 4608-4614.
	ZhaoX Q, XueY F. Fault detection algorithm for chemical process based on kernel T-PLS[J]. CIESC Journal, 2013, 64(12): 4608-4614.
19	LiuY, ChangY, WangF. Nonlinear dynamic quality-related process monitoring based on dynamic total kernel PLS [C]//Intelligent Control and Automation. IEEE, 2015: 1360-1365.
20	KanekoH, FunatsuK. Ensemble locally weighted partial least squares as a just-in-time modeling method [J]. AIChE Journal, 2016, 62(3): 717-725.
21	HazamaK, KanoM. Covariance-based locally weighted partial least squares for high-performance adaptive modeling [J]. Chemometrics & Intelligent Laboratory Systems, 2015, 146: 55-62.
22	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.
	YuanX F, GeZ Q, SongZ H. Adaptive soft sensor based on time difference model and locally weighted partial least squares regression [J]. CIESC Journal, 2016, 67(3): 724-728.
23	WangG, YinS, KaynakO. An LWPR-based data-driven fault detection approach for nonlinear process monitoring [J]. IEEE Transactions on Industrial Informatics, 2014, 10(4): 2016-2023.
24	YinS, XieX, SunW. A nonlinear process monitoring approach with locally weighted learning of available data [J]. IEEE Transactions on Industrial Electronics, 2017, 64(2): 1507-1516.
25	UchimaruT, KanoM. Sparse sample regression based just-in-time modeling (SSR-JIT): beyond locally weighted approach [J]. IFAC Papers OnLine, 2016, 49(7): 502-507.
26	LiuJ, TaoL, JieZ. Window-based step-wise sequential phase partition for nonlinear batch process monitoring [J]. Industrial & Engineering Chemistry Research, 2016, 55(34): 9229-9243.
27	刘学彦, 王昕, 王振雷. 带遗忘因子的线性回归性能评估算法及应用[J]. 控制工程, 2014, 21(6): 867-872.
	LiuX Y, WangX, WangZ L. Performance assessment algorithm of improved linear regression with forgetting factor (ILR) and its application [J]. Control Engineering of China, 2014, 21(6): 867-872.
28	张壤文, 田学民. 带变遗忘因子的自适应子空间预测控制器设计[J]. 化工学报, 2016, 67(3): 858-864.
	ZhangR W, TianX M. Design of adaptive subspace predictive controller with variable forgetting factor [J]. CIESC Journal, 2016, 67(3): 858-864.
29	KerezsiJ. Computer simulation of an industrial ethane-cracking furnace operation [C]//International Youth Conference on Energy. IEEE, 2013: 1-5.
30	李平, 李奇安. 乙烯裂解炉先进控制系统开发与应用 [J]. 化工学报, 2011, 62(8): 2216-2220.
	LiP, LiQ A. Development and application of advanced process control system for ethylene cracking heaters [J]. CIESC Journal, 2011, 62(8): 2216-2220.
31	江伟, 王昕, 王振雷. 基于 LTSA 和 MICA 与 PCA 联合指标的过程监控方法及应用[J]. 化工学报, 2015, 66(12): 4895-4903.
	JiangW, WangX, WangZ L. LTSA and combined index based MICA and PCA process monitoring and application [J]. CIESC Journal, 2015, 66(12): 4895-4903.

[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]	温凯杰, 郭力, 夏诏杰, 陈建华. 一种耦合CFD与深度学习的气固快速模拟方法[J]. 化工学报, 2023, 74(9): 3775-3785.
[3]	范孝雄, 郝丽芳, 范垂钢, 李松庚. LaMnO₃/生物炭催化剂低温NH₃-SCR催化脱硝性能研究[J]. 化工学报, 2023, 74(9): 3821-3830.
[4]	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.
[5]	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.
[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]	徐野, 黄文君, 米俊芃, 申川川, 金建祥. 多源信息融合的离心式压缩机喘振诊断方法[J]. 化工学报, 2023, 74(7): 2979-2987.
[8]	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.
[9]	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.
[10]	黄磊, 孔令学, 白进, 李怀柱, 郭振兴, 白宗庆, 李平, 李文. 油页岩添加对准东高钠煤灰熔融行为影响的研究[J]. 化工学报, 2023, 74(5): 2123-2135.
[11]	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.
[12]	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.
[13]	张江淮, 赵众. 碳三加氢装置鲁棒最小协方差约束控制及应用[J]. 化工学报, 2023, 74(3): 1216-1227.
[14]	吴选军, 王超, 曹子健, 蔡卫权. 数据与物理信息混合驱动的固定床吸附穿透深度学习模型[J]. 化工学报, 2023, 74(3): 1145-1160.
[15]	王雅琳, 潘雨晴, 刘晨亮. 基于GSA-LSTM动态结构特征提取的间歇过程监测方法[J]. 化工学报, 2022, 73(9): 3994-4002.

基于Ms-LWPLS的化工过程网络化性能分级评估方法

Networked grading performance assessment method of chemical process based on Ms-LWPLS

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 31

相关文章 15

编辑推荐

Metrics

本文评价