基于双层机器学习的动态精馏过程故障检测与分离

doi:10.12034/j.issn.1009-606X.216293

过程工程学报 ›› 2017, Vol. 17 ›› Issue (2): 351-356.DOI: 10.12034/j.issn.1009-606X.216293

基于双层机器学习的动态精馏过程故障检测与分离

毛海涛，田文德^*，梁慧婷

青岛科技大学化工学院，山东青岛 266042

收稿日期:2016-09-06 修回日期:2016-10-21 出版日期:2017-04-20 发布日期:2017-04-19
通讯作者: 田文德 tianwd@qust.edu.cn
基金资助:
国家自然科学基金项目;山东省自然科学基金;国家级大学生创新创业训练计划项目

Fault Detection and Isolation of Dynamic Distillation Process Using Two-tier Machine Learning

MAO Hai-tao, TIAN Wen-de^*, LIANG Hui-ting

College of Chemical Engineering, Qingdao University of Science & Technology, Qingdao, Shandong 266042, China

Received:2016-09-06 Revised:2016-10-21 Online:2017-04-20 Published:2017-04-19
Contact: TIAN Wen-de tianwd@qust.edu.cn

摘要/Abstract

摘要： 提出了基于双层机器学习的动态精馏过程故障检测和分离的方法，检测的阈值为正常工况训练的网络输出值与样本的残差. 通过对比网络预测值和实测值的偏差检测故障，检测到故障时，启动另一网络对动态过程自适应拟合异常工况数据. 网络的预测值与实测值的偏差小于阈值时，拟合成功. 通过对两个网络进行结构解析找到造成输出变量异常波动的输入变量. 将该方法运用到脱丙烷精馏塔中，检测出过程中的故障，并分离出与故障源相关的变量，表明该方法准确、有效.

关键词: 机器学习, 动态精馏过程, 故障检测与分离, 网络结构解析

Abstract: A new method using two-tier machine learning is proposed to detect and isolate fault in dynamic distillation process. The residuals between output of network trained by normal condition data and samples are recognized as the threshold for detection. Fault detection is carried out by comparing the deviation between the prediction of one network and the measured value. Once the fault is detected, another network is activated to fit the dynamic distillation process adaptively. When the deviation between simulation output and the measured output of distillation column is less than the threshold, the fitting is considered satisfying. Then the input variables causing output variables’ abnormal fluctuation are found via the analysis of structure parameters of two networks. This method is applied to detect process’s fault and isolate variables relating with fault in the distillation tower simulation, and proved to be effective and veracious.

Key words: machine learning, dynamic distillation process, fault detection and isolation, analysis of network structure

毛海涛田文德梁慧婷. 基于双层机器学习的动态精馏过程故障检测与分离[J]. 过程工程学报, 2017, 17(2): 351-356.

MAO Hai-tao TIAN Wen-de LIANG Hui-ting. Fault Detection and Isolation of Dynamic Distillation Process Using Two-tier Machine Learning[J]. Chin. J. Process Eng., 2017, 17(2): 351-356.

参考文献

[1] Engelien H. K, Skogestad S.Selecting appropriate control variables for a heat-integrated distillation system with prefractionator. Computers & Chemical Engineering[J], 2004, 28(5): 683-691.
[2] Chetouani Y. Model selection and fault detection approach based on Bayes decision theory: Application to changes detection problem in a distillation column. Process Safety and Environmental Protection[J], 2014, 92(3): 215-233.
[3] Xie Lei , Zeng J S, Kruger U, et, al. Fault detection in dynamic systems using the Kullback–Leibler divergence. Control Engineering Practice[J], 2015, 43: 39-48.
[4] Bo C M, Qiao X, Zhang G M, et, al. An integrated method of independent component analysis and support vector machines for industry distillation process monitoring. Journal of Process Control[J], 2010, 20(10): 1133-1140.
[5] Motlaghi S, Jalali F, Ahmadabadi M.N. An expert system design for a crude oil distillation column with the neural networks model and the process optimization using genetic algorithm framework.Expert Systems with Applications[J], 2008, 35(4): 1540-1545.
[6] Liau C K, Yang C K, Tsaib M T. Expert system of a crude oil distillation unit for process optimization using neural networks. Expert Systems with Applications[J], 2004, 26(2): 247-255.
[7] Vanini Z.N, Khorasani K, Meskin N. Fault detection and isolation of a dual spool gas turbine engine using dynamic neural networks and multiple model approach. Information Sciences[J], 2014, 259: 234-251.
[8] Qu Y, Li Z M, Li E.Fault detection and diagnosis for non-Gaussian stochastic distribution systems with time delays via RBF neural networks. ISA Transactions[J], 2012, 51(6): 786-791.
[9] Tian W D, Sun S L, Guo Q J. Fault detection and diagnosis for distillation column using two-tier model. The Canadian Journal of Chemical Engineering[J] ,2013, 91: 1671-1685.
[10]Kamal H, Meisam P, Hosein M M. Fault diagnosis and classification based on wavelet transform and neural network. Progress in Nuclear Energy[J], 2011, 53(1): 41-47.
[11]Gorman C, Valova I.Optimizations of the Gravitationally Organized Related Mapping ANN through Genetic Algorithms. Procedia Computer Science[J], 2014, 36: 529-534.
[12] Leonard E B, Ted P. statistical inference for probabillstic function of finite state Markov chains. The Annals of Mathematical Statistics[J], 1966, 37(6): 1554-1563.

基于双层机器学习的动态精馏过程故障检测与分离

Fault Detection and Isolation of Dynamic Distillation Process Using Two-tier Machine Learning

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics