Recent development of the application of big data technology in process industries

doi:10.16085/j.issn.1000-6613.2016.06.006

Abstract

Abstract: Recently,the big data technology has been applied in many field widely,such as finance,trade and medical healthy. But the applications in process industries are only in the beginning stages. In this paper,the characteristics,analyzing methods and applications of the data in process industries are introduced. The data obtained by the process industry have the characteristics of high dimension,strong nonlinearity,uneven sample distribution and low signal-to-noise ratio except from the characteristics of volume,variety,velocity and variability. The big data technology has emerged and developed to be available in analyzing data from the process industries. The analyzing methods based on the industrial data include dimension reduction analysis,cluster and classification analysis,correlation analysis and prediction analysis according to their functions. In this paper,the applications of the big data technology in process industries are summarized from three aspects including process optimization,process monitoring and fault diagnosis and prediction of product properties and yield. It is found that the big data will play a more important role if the production data in the process industries can be combined with the market data of raw material and product.

Key words: big data, process industry, data analysis, process systems

摘要： 近些年,大数据技术在金融、贸易和医疗健康等行业也得到了较好的应用,但大数据技术在过程工业中的应用还处于起步阶段。本文分别从过程工业大数据的特点、分析方法以及应用现状3个方面进行介绍,简述了过程工业数据除了具有一般大数据海量性、多样性、高速性和易变性的4V特点外,还具有高维度、强非线性、样本分布不均和低信噪比的特点。基于过程工业数据的分析方法,按照功能划分可以分为降维分析、聚类和分类分析、相关性分析和预测分析四大类。在此基础上,综述了近些年大数据技术在过程工业上的应用,分别从过程工业优化、过程监测与故障诊断以及产品性能和产率预测3个方面介绍了其在过程工业中的应用情况,并指出未来应该将企业内部的生产数据和原料与产品的市场数据等相结合进行分析和挖掘,这样能够更大程度地发挥大数据的价值。

关键词: 大数据, 过程工业, 数据分析, 过程系统

CLC Number:

TQ063

SU Xin, WU Yingya, PEI Huajian, LAN Xingying, GAO Jinsen. Recent development of the application of big data technology in process industries[J]. Chemical Industry and Engineering Progree, 2016, 35(06): 1652-1659.

苏鑫, 吴迎亚, 裴华健, 蓝兴英, 高金森. 大数据技术在过程工业中的应用研究进展[J]. 化工进展, 2016, 35(06): 1652-1659.

References

[1] 韩晶.大数据服务若干关键技术研究[D].北京:北京邮电大学,2013.
[2] CRASSO M,ZUNINO A,CAMPO M.Easy web service discovery:a query-by-example approach[J].Science of Computer Programming,2008,71(2):144-164.
[3] CHIRITA P A,NEJDL W.13th International Conference, SPIRE 2006, Glasgow, UK, October 11-13, 2006 [C].Berlin:Springer, 2006:86-97.
[4] O'DRISCOLL J,DAUGELAITE,SLEATOR R D.‘Big data',Hadoop and cloud computing in genomics[J].Journal of Biomedical Informatics,2013,46(5):774-781.
[5] HERODOTOU H,LIM H,LUO G,et al.5th Biennial Conference on Innovative Data Systems Research (CIDR), January 9-12, 2011[C].California:ACM Press,2011.
[6] 李杰,刘宗长.中国制造2025的核心竞争力——挖掘使用数据[J].博鳌观察,2015(4):52-55.
[7] 彭训文.工业4.0:从自动生产到智能制造[J].大飞机,2014(7):40-42.
[8] 王宁玲,付鹏,陈德刚,等.大数据分析方法在厂级负荷分配中的应用[J].中国电机工程学报,2015,35(1):68-73.
[9] 孔宪光,章雄,马洪波,等.面向复杂工业大数据的实时特征提取方法研究[J].西安电子科技大学学报,2016,43(5):78-83.
[10] HAND D J.Data mining:statistics and more?[J].The American Statistician,1998,52(2):112-118.
[11] HAND D J.Statistics and data mining:intersecting disciplines[J].ACM SIGKDD Explorations Newsletter,1999,1(1):16-19.
[12] HOPKINS B,EVELSON B,LEAVER S,et al.Expand your digital horizon with big data[R].Forrester,2011.
[13] 王建民.探索走出符合国情的工业大数据自主之路——工业大数据的范畴、关键问题与实践[J].中国设备工程,2015(9):36-37.
[14] 高婴劢.工业大数据价值挖掘路径[J].中国工业评论,2015(s1):21-27.
[15] 刘继伟.基于大数据的多尺度状态监测方法及应用[D].北京:华北电力大学,2013.
[16] DERMAN C.Adaptive control processes,a guided tour[J].Management Science,1961,7(4):450.
[17] 毕达天,邱长波,张晗.数据降维技术研究现状及其进展[J].情报理论与实践,2013,36(2):125-128.
[18] 谭璐.高维数据的降维理论及应用[D].长沙:国防科学技术大学,2005.
[19] JACKSON,E J.A user's guide to principal components[M].New York:Wiley-Interscience [Imprint];John Wiley & Sons,Incorporated,2005.
[20] 李荣雨.基于PCA的统计过程监控研究[D].杭州:浙江大学,2007.
[21] 成平,李国英.投影寻踪——一类新兴的统计方法[J].应用概率统计,1986,2(3):267-276.
[22] 曾群芳.基于拓扑结构保持的线性降维方法研究及其应用[D].广州:华南理工大学,2012.
[23] BRAND M.18th International Joint Conference on Artificial Intelligence, 2003[C].San Francisco:Morgan Kaufmann Publishers,2003:547-552.
[24] GRIFFITHS T L,KALISH M L.A multidimensional scaling approach to mental multiplication[J].Memory & Cognition,2002,30(1):97-106.
[25] ZHA H Y,ZHANG Z Y.Twentieth International Conference on Machine Learning. 2003[C].Menlo Park, California:AAAI Press,2003.
[26] SAUL L K,ROWEIS S T.Think globally,fit locally:unsupervised learning of nonlinear manifolds[J].Journal of Machine Learning Research,2003,4(2):119-155.
[27] GRIGOR'YAN A.Estimates of heat kernels on Riemannian manifolds[M]// DAVIES E B,SAFAROW Y. Spectral theory and geometry. Cambridge:Cambridge Universty Press,1999:140–225.
[28] 许丽利.聚类分析的算法及应用[D].长春:吉林大学,2010.
[29] 戴涛.聚类分析算法研究[D].北京:清华大学,2005.
[30] 郭军华.数据挖掘中聚类分析的研究[D].武汉:武汉理工大学,2003.
[31] 刘红岩,陈剑,陈国青.数据挖掘中的数据分类算法综述[J].清华大学学报(自然科学版),2002,42(6):727-730.
[32] QUINLAN J R.C4.5:Programs for machine learning[M].San Mateo:Califomia Morgan Kaufmann,1993.
[33] 栾丽华,吉根林.决策树分类技术研究[J]. 计算机工程,2004,30(9):94-96,105.
[34] RISSANEN J,AGRAWAL R,MEHTA M.International Conference on Very Large Data Bases[C].San Francisco:Morgan Kaufmann Publishers,1996.
[35] FRIEDMAN N,GEIGER D,GOLDSZMIDT M.Bayesian network classifiers[J].Machine Learning,1997,29(1):131-163.
[36] LIU B,HSU W,MA Y.The Fourth International Conference on Knowledge Discovery and Data Mining [C].Menlo Park, California:AAAI Press,1998.
[37] 李伟卫,李梅,张阳,等.基于分布式数据仓库的分类分析研究[J].计算机应用研究,2013,30(10):2936-2939,2943.
[38] 刘晓欣.互信息多元时间序列相关分析与变量选择[D].大连:大连理工大学,2013.
[39] 何宽,陈森发.基于一类因果关系图的综合评价方法及应用[J].控制与决策,2010,25(10):1513-1518.
[40] YAMAMOTO H,YAMAJI H,FUKUSAKI E,et al.Canonical correlation analysis for multivariate regression and its application to metabolic fingerprinting[J].Biochemical Engineering Journal,2008,40(2):199-204.
[41] SUNGUR Engin A.An introduction to copulas[J].Journal of the American Statistical Association,2000,95(449):334-335.
[42] TSENG F M,YU H C,TZENG G H.Applied hybrid grey model to forecast seasonal time series[J].Technological Forecasting and Social Change,2001,67(2):291-302.
[43] KWAK N,CHOI C H.Input feature selection by mutual information based on parzen window[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(12):1667-1671.
[44] 丁云,于静江,周春晖.原油蒸馏塔的质量估计和优化管理[J].石油炼制与化工,1994,25(5):23-28.
[45] 郭斌,孟令启,杜勇,等.基于GRNN神经网络的中厚板轧机厚度预测[J].中南大学学报(自然科学版),2011,42(4):960-965.
[46] 王文新,潘立登,李荣,等.常减压蒸馏装置双模型结构RBF神经网络建模与应用[J].北京化工大学学报,2004,31(5):23-28.
[47] 苏鑫,裴华健,吴迎亚,等.经遗传算法优化的BP神经网络预测催化裂化装置焦炭产率应用[J].化工进展,2016,35(2):389-396.
[48] 张健,陈丙珍,胡山鹰,等.复杂流程工业系统的优化操作[J].计算机与应用化学,2000,17(6):481-488.
[49] 柴天佑,丁进良,王宏,等.复杂工业过程运行的混合智能优化控制方法[J].自动化学报,2008,34(5):505-515.
[50] 牟盛静.石化工业过程建模与优化若干问题研究[D].杭州:浙江大学,2004.
[51] 殷瑞钰.新世纪炼钢科技进步回顾与“十二五”展望[J].炼钢,2012,28(5):1-7.
[52] 薛见新.炼钢连铸过程温度流优化的设计与分析[D].沈阳:东北大学,2010.
[53] 宋辉.聚类分析系统的设计与实现及在工业中的应用[D].天津:天津科技大学,2004.
[54] 王基铭.21世纪我国炼油工业面临的挑战和对策[J].石油炼制与化工,1999,30(5):3-6.
[55] 侯芙生.创新炼油技术推动21世纪我国炼油工业的发展[J].石油炼制与化工,2002,33(1):1-9.
[56] 徐春明,杨朝合.石油炼制工程[M].4版.北京:石油工业出版社,2009.
[57] 殷卫兵,罗雄麟,史伟.原油常减压蒸馏塔的流程模拟[J].化工自动化及仪表,2010,37(5):88-93.
[58] 梁志勇,孙甲,刘政,等.原油电脱盐脱水技术的研究现状及进展[J].石油和化工设备,2012,15(8):26-29.
[59] 郭超.决策树方法在提高电脱盐效果中的应用[J].计算机工程与设计,2010,31(10):2372-2375.
[60] 侯祥麟.中国炼油技术[M].2版.北京:中国石化出版社,2001.
[61] 许友好.我国催化裂化工艺技术进展[J].中国科学(化学),2014,44(1):13-24.
[62] 闫平祥,刘植昌,高金森,等.重油催化裂化工艺的新进展[J].当代化工,2004,33(3):136-140.
[63] 许友好,张久顺,龙军.生产清洁汽油组分的催化裂化新工艺MIP[J].石油炼制与化工,2001,32(8):1-5.
[64] 许友好,张久顺,马建国,等.生产清洁汽油组分并增产丙烯的催化裂化工艺[J].石油炼制与化工,2004(9);1-4.
[65] 伍星,陈进,李如强,等.基于数据挖掘的设备状态监测和故障诊断[J].振动与冲击,2004,23(4):72-76.
[66] FAYYAD U,STOLORZ P.Data mining and KDD:promise and challenges[J].Future Generation Computer Systems,1997,13(2):99-115.
[67] 周德泽.计算机智能监测控制系统的设计及应用[M].北京:清华大学出版社,2002.
[68] 郭明.基于数据驱动的流程工业性能监控与故障诊断研究[D].杭州:浙江大学,2004.
[69] 张殿伟,郭培民,赵沛.现代炼铁技术进展[J].钢铁钒钛,2006,27(2):26-32.
[70] 刘祥官,曾九孙,郝志忠,等.多模型集成的高炉炼铁智能控制专家系统[J].浙江大学学报(工学版),2007,41(10):1637-1642.
[71] LIAO S H.Expert system methodologies and applications—a decade review from 1995 to 2004[J].Expert Systems with Applications,2005,28(1):93-103.
[72] 周传典.高炉炼铁生产技术手册[M].北京:冶金工业出版社,2002.
[73] 刘祥官,刘芳.高炉过程优化与智能控制模型[J].高校应用数学学报A辑(中文版),2001,16(4):462-470.
[74] BETTINGER D,SCHURZ B,STOHL K,et al.Expert system control of blast furnaces-the next step[J].Steel Times International,2005,29(7):14.
[75] 任盛怡.基于数据挖掘的高炉异常炉况分析[D].重庆:重庆大学,2009.
[76] 何细藕.乙烯裂解炉技术进展[J].现代化工,2001,21(9):13-17.
[77] 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,2014.
[78] 于文秀.聚丙烯技术新进展[J].石油化工,2003,32(10):913-917.
[79] 赵文明.对我国聚丙烯技术及市场发展的认识和思考[J].化学工业,2009,27(12):10-16.
[80] 夏陆岳,潘海天,周猛飞,等.基于改进多尺度主元分析的丙烯聚合过程监测与故障诊断[J].化工学报,2011,62(8):2312- 2317.
[81] 李跃文.塑料注塑成型技术新进展[J].塑料工业,2011,39(4):6-9.
[82] 赵斐,陆宁云,杨毅.基于工况识别的注塑过程产品质量预测方法[J].化工学报,2013,64(7):2526-2534.
[83] 曹汉昌,郝希仁,张韩.催化裂化工艺计算与技术分析[M].北京:石油工业出版社,2000.
[84] 周小伟,袁俊,杨伯伦.应用BP神经网络的二次反应清洁汽油辛烷值预测[J].西安交通大学学报,2010,44(12):82-86.