Monitoring and diagnosis of abnormal condition in ethylene production process based on SVM-BOXPLOT

doi:10.11949/j.issn.0438-1157.20170907

Abstract

Abstract:

As an important raw material for chemical production, the demands of ethylene greatly increase, but it consumes large energy. Since ethylene production and operation status is directly related to the level of energy efficiency, the economic benefits of enterprises are affected. It is great significance to realize the intelligent identification of ethylene production operating conditions for saving energy and reducing consumption. Therefore, a comprehensive method for the abnormity identification in ethylene production is presented by using the IPSO-optimized SVM-BOXPLOT method based on the key energy efficiency indicators, ethylene yield, propylene yield and comprehensive energy consumption. Specifically, the data dimensionality is reduced on the basis of the deep analysis of the ethylene production technology and the data analysis. Then the working conditions are classified by SVM for reducing the scope of abnormal recognition. Finally, the abnormal data is identified by BOXPLOT. Combined with the on-line monitoring system, the scheme is applied to the production of a petrochemical enterprise. The monitoring and diagnosis scheme for abnormal working conditions has higher model precision and faster convergence speed. The method not only realizes the monitoring and diagnosis of abnormal working conditions in ethylene production, but also meets the technological requirements of actual operating conditions, which ensures the real-time and accuracy of abnormal identification.

Key words: ethylene production, energy efficiency, chemical process safety, fault diagnosis, IPSO, SVM, BOXPLOT

摘要：

乙烯作为化工生产的重要原材料，需求量持续增加，但它也是高能耗产业，其生产运行状态直接关系到能效的高低，进而影响企业的经济效益。因此，乙烯生产运行工况的智能识别对节能降耗意义重大。针对直接影响乙烯生产过程能效水平的异常工况智能识别问题，以能够反映乙烯生产能效与能耗的关键指标——乙烯收率、丙烯收率及综合能耗为基础，使用IPSO优化SVM-BOXPLOT的方法对乙烯生产过程进行异常工况智能识别。通过机理分析与数据分析相结合的方法对监测数据降维，用SVM对生产数据进行工况分类，缩小异常识别范围，最后用BOXPLOT进行异常工况识别。将其与在线监测系统相结合应用于某石化企业生产中，所提出的异常工况监测与诊断方案模型精度更高，收敛速度更快，既实现了乙烯生产过程异常工况的监测与诊断，又满足了实际运行工况的工艺要求，保证了异常识别的实时性、准确性。

关键词: 乙烯生产, 能效, 化工安全, 故障诊断, 粒子群优化, 支持向量机, 箱线图

CLC Number:

TQ202

HUA Li, YU Haichen, SHAO Cheng, GONG Shixin. Monitoring and diagnosis of abnormal condition in ethylene production process based on SVM-BOXPLOT[J]. CIESC Journal, 2018, 69(3): 1053-1063.

华丽, 于海晨, 邵诚, 巩师鑫. 基于SVM-BOXPLOT的乙烯生产过程异常工况监测与诊断[J]. 化工学报, 2018, 69(3): 1053-1063.

References 31

[1]	张金元. 论节能减排技术在乙烯装置上的应用研究[J]. 化工管理, 2014, 32(5):260. ZHANG J Y. Study on the application of energy saving and emission reduction technology in ethylene plant[J]. Chemical Enterprise Management, 2014, 32(5):260.
[2]	许江, 宋邦勇, 杨利斌, 等. 乙烯装置规模大型化的研究与探讨[J]. 现代化工, 2011, 31(4):11-13. XU J, SONG B Y, YANG L B, et al. Research and discussion on enlargement of ethylene production equipment[J]. Modern Chemical Industry, 2011, 31(4):11-13.
[3]	姜振宇. 乙烯装置中TRICON系统问题分析及解决方案[J]. 化工管理, 2016, 20(5):191. JIANG Z Y. Problem analysis and solution of TRICON system in ethylene plant[J]. Chemical Enterprise Management, 2016, 20(5):191.
[4]	孙广民. 石化电气设备典型故障的诊断[J]. 化工管理, 2015, 12(6):111-112. SUN G M. Diagnosis of typical faults in petrochemical electrical equipment[J]. Chemical Enterprise Management, 2015, 12(6):111-112.
[5]	金祖荣. 石化行业电气设备状态监测与故障诊断[J]. 甘肃科技, 2010, 26(4):65-68. JIN Z R. Condition monitoring and fault diagnosis of electrical equipment in petrochemical industry[J]. Gansu Science and Technology, 2010, 26(4):65-68.
[6]	马斌良, 潘延君, 陆军, 等. 基于状态监测和故障诊断技术的脱乙烷塔回流泵故障检修[J]. 石油化工设备技术, 2013, 34(2):38-42. MA B L, PAN Y J, LU J, et al. Troubleshooting of reflux pump of ethane tower based on condition monitoring and fault diagnosis technology[J]. Petrochemical Equipment Technology, 2013, 34(2):38-42.
[7]	徐波有. 化工离心泵常见故障诊断及处理[J]. 中国设备工程, 2017, 32(16):77-78. XU B Y. Common fault diagnosis and treatment of chemical centrifugal pump[J]. China Plant Engineering. 2017, 32(16):77-78.
[8]	刘兰英. 模糊多级融合技术在化工故障诊断中的应用[J]. 互联网科技, 2016, 26(6):137-139. LIU L Y. Application of fuzzy multilevel fusion to chemical fault diagnosis[J]. Wireless Internet Technology, 2016, 26(6):137-139.
[9]	王秋杰. 浅析智能型定位器在乙烯项目中的应用[J]. 石油化工自动化, 2014, 50(1):69-71. WANG Q J. Analysis of the application of intelligent positioner in ethylene project[J]. Automation in Petro-Chemical Industry, 2014, 50(1):69-71.
[10]	王政, 孙锦程, 王迎春, 等. 基于复杂网络理论的符号有向图(SDG)化工故障诊断[J]. 化工进展, 2016, 35(5):1344-1352. WANG Z, SUN J C, WANG Y C, et al. Research on chemical process signed directed graph(SDG) fault diagnosis based on complex network[J]. Chemical Industry and Engineering Progress, 2016, 35(5):1344-1352.
[11]	王迎春. 基于复杂网络的化工过程SDG模型研究[D]. 青岛:青岛科技大学, 2015. WANG Y C. The research of chemical process SDG model based on complex network[D]. Qingdao:Qingdao University of Science & Technology, 2015.
[12]	张晓丹. 基于免疫克隆算法的LVQ神经网络研究及其在化工工业故障诊断过程中的应用[D]. 上海:华东理工大学, 2013. ZHANG X D. Research of ICALVQ neural network and its application in the fault diagnosis of chemical industry[D]. Shanghai:East China University of Science and Technology, 2013.
[13]	李召, 杨英华, 李智辉. 基于小波去噪结合CVA-ICA的故障检测方法的研究[J]. 仪表技术与传感器原理, 2014, 34(4):80-81. LI Z, YANG Y H, LI Z H. Fault detection based on wavelet de-noise and CVA-ICA[J]. Instrument Technology and Sensor, 2014, 34(4):80-81.
[14]	赵贺嘉. 状态检测技术在石化企业安全生产中的应用[D]. 大庆:东北石油大学, 2015. ZHAO H J. Condition monitoring technology in the application of the petrochemical enterprise safety in production[D]. Daqing:Northeast Petroleum University, 2015.
[15]	夏丽莎, 杨玉英, 方华京. 基于EasyEnsemble的化工过程故障诊断性能改进[J]. 控制理论与应用, 2017, 34(1):49-53. XIA L S, YANG Y Y, FANG H J. Fault diagnosis performance improvement for chemical process based on EasyEnsemble method[J]. Control Theory&Application, 2017, 34(1):49-53.
[16]	罗雄麟, 赵晓鹰, 吴博, 等. 乙烯精馏塔异常工况在线侦测与控制[J]. 化工学报, 2014, 65(11):4517-4523. LUO X L, ZHAO X Y, WU B, et al. Online detection and control of ethylene column abnormal condition[J]. CIESC Journal, 2014, 65(11):4517-4523.
[17]	马立玲, 徐发富, 王军政. 一种基于改进核Fisher的故障诊断方法[J]. 化工学报, 2017, 68(3):1041-1048. MA L L, XU F F, WANG Z J. A fault diagnosis method based on improved kernel Fisher[J]. CIESC Journal, 2017, 68(3):1041-1048.
[18]	刘莉, 王晶. 基于核Fisher包络分析的间歇过程故障诊断[D]. 北京:北京化工大学, 2015. LIU L, WANG J. Kernel Fisher envelop surface based fault diagnosis for batch process[D]. Beijing:Beijing University of Chemical Technology, 2015.
[19]	王振武, 孙佳俊, 尹成峰. 改进粒子群算法优化的支持向量机及其应用[J]. 哈尔滨工程大学学报, 2016, 37(12):1728-1733. WANG Z W, SUN J J, YIN C F. A support vector machine based on an improved particle swarm optimization algorithm and its application[J]. Journal of Harbin Engineering University, 2016, 37(12):1728-1733.
[20]	刘健, 刘忠, 熊鹰. 基于PSO算法的SVM参数优化方法研究[J]. 计算机科学与技术学报, 2013, 2(1):9-16. LIU J, LIU Z, XIONG Y. Method of parameters optimization in SVM based on PSO[J]. Transactions on Computer Science and Technology, 2013, 2(1):9-16.
[21]	胡旺, 李志蜀. 一种更简化而高效的粒子群优化算法[J]. 软件学报, 2007, 18(4):861-868. HU W, LI Z S. A simple and more effective partical swarm optimization algorithm[J]. Journal of Software, 2007, 18(4):861-868.
[22]	王振武, 孙佳骏, 尹成峰. 改进粒子群算法优化的支持向量机及其应用[J]. 哈尔滨工程大学学报, 2016, 37(12):1728-1733. WANG Z W, SUN J J, YIN C F. A support vector machine based on an improved partical swarm optimization algorization and its application[J]. Journal of Harbin Engineering University, 2016, 37(12):1728-1733.
[23]	奉国和. SVM分类核函数及参数选择比较[J]. 计算机工程与应用, 2011, 47(3):123-128. FENG G H. Parameter optimizing for support vector machines classification[J]. Computer Engineering and Applications, 2011, 47(3):123-128.
[24]	宋辰. 免疫文化算法研究及其在化工工业故诊断中的应用[D]. 上海:华东理工大学, 2013. SONG C. Immune culture algorithm and its application in the fault diagnosis of chemical industry[D]. Shanghai:East China University of Science and Technology, 2013.
[25]	李红英, 钟波. 支持向量分类机的核函数研究[D]. 重庆:重庆大学, 2009. LI H Y, ZHONG B. Research of kernels in support vector classifying machinne[D]. Chongqing:Chongqing University, 2009.
[26]	祝晓燕, 张金会, 付士鹏, 等. 基于改进PSO的SVM参数优化及其在风速预测中的应用[J]. 中国电力, 2013, 46(11):105-108. ZHU X Y, ZHANG J H, FU S P. Optimization of SVM parameters based on improved PSO and its application in wind speed prediction[J]. China Electric Power, 2013, 46(11):105-108.
[27]	张学成, 周斌, 孔瑞远, 等. 大型仪器利用情况调查数据异常值检测的数学方法比较[J]. 数学知识与实践, 2012, 42(11):50-52. ZHANG X C, ZHOU B, KONG R Y, et al. Comparison of outliner detection mathematical methods on the survey data from the use of large-scale instrument[J]. Mathematics in Practice and Theory, 2012, 42(11):50-52.
[28]	庄作钦. BOXPLOT——描述统计的一个简便工具[J]. 统计教育, 2013, 42(21):34-35. ZHUANG Z Q. BOXPLOT-a simple tool for describing statistics[J]. Statistical Education, 2013, 42(21):34-35.
[29]	彭红, 刘洋, 邓维维, 等. 股票数据流的相关性计算方法[J]. 华南理工大学学报(自然科学版), 2006, 34(1):86-89. PENG H, LIU Y, DENG W W, et al. Correlation calculation method of stock data flow[J]. Journal of South China University of Technology (Natural Science Edition), 2006, 34(1):86-89.
[30]	陈上珠, 陆传荣. 应用数理统计[M]. 沈阳:辽宁大学出版社, 2007. CHEN S Z, LU C R. Applied Mathematical Statistics[M]. Shenyang:Liaoning University Press, 2007.
[31]	陆兵焱, 陈友龙, 李映颖. 基于SPSS对试飞数据进行的相关性分析[J]. 科技信息, 2009, 32(15):405-487. LU B Y, CHEN Y L, LI Y Y. Correlation analysis of flight test data based on SPSS[J]. Science & Technology Information, 2009, 32(15):405-487.