人工神经网络在化工过程中的应用进展

doi:10.16085/j.issn.1000-6613.2016.12.004

摘要/Abstract

摘要： 人工神经网络作为人工智能的重要组成部分，以其超强的鲁棒性、容错性、可充分逼近任何复杂的非线性关系、并行处理、可学习和自适应等优点在改善化工过程传统生产技术诊断滞后、难以优化控制、物性估算误差较大以及不能处理非线性复杂情况等问题上有着广阔的发展空间。本文概述了人工神经网络的原理和发展历程，综述并分析了人工神经网络在故障诊断、过程控制和优化、质量控制、定量结构-活性/性质相关性分析、物性估算、专家系统以及聚类分析等化工过程中的应用原理以及研究进展和现状。最后指出卷积神经网络等深度学习算法的性能高、速度快，在化工过程中发展和应用深度学习算法将成为其发展方向和研究热点。

关键词: 神经网络, 模型, 化工过程, 生产, 原理

Abstract: Artificial neural networks were the important part of artificial intelligence,which had a broad space in improving the chemical process of traditional production techniques diagnosis of lag,difficult to optimize and control,large property estimation error and could not deal with complex nonlinear problems. Artificial neural networks have drawn much attention because of superior robustness,fault tolerance,approximation of complex nonlinear correlations,parallel processing and adaptive learning. Artificial neural networks have been applied to chemical processes in the following areas:fault diagnosis,process control and optimization,quality control,quantitative structure-activity/property correlation analysis,property estimation,expert system and clustering analysis. This paper summarized the theory and development history of artificial neural network,and conducted meta-analysis of the literature on the principles and the development of artificial neural networks in chemical processes. Finally,the paper pointed out that the deep learning algorithm had advantages of high-performance and high speed,and then discussed that the future study of neural networks in chemical process would be the direction and hot topic in the development and application of deep learning algorithm.

Key words: neural networks, model, chemical engineering process, production, principle

中图分类号:

TQ021.9

宋泓阳, 孙晓岩, 项曙光. 人工神经网络在化工过程中的应用进展[J]. 化工进展, 2016, 35(12): 3755-3762.

SONG Hongyang, SUN Xiaoyan, XIANG Shuguang. Progress on the application of artificial neural network in chemical industry[J]. Chemical Industry and Engineering Progree, 2016, 35(12): 3755-3762.

参考文献

[1] CROWTHER R H,PITRAK J E,PLYEN.Computer control at american oil[J].Chemical Engineering Process,1961,57(6):183-186.
[2] 王聃,方利国.神经网络在化工应用中的研究进展[J].广东化工,2007,34(10):52-55.
[3] 冉清,刘莹.人工神经网络及其在化工领域中的应用[J].广东化工,2001,29(2):32-34.
[4] HAGAN M T、,DEMUTH H B,DEALE M H.神经网络设计[M]戴葵等译.北京:机械工业出版社,2002:5-8.
[5] HINTON G E,SALAKHUTDINOV R R.Reducing the dimensionality of data with neural networks[J].Science,2006,313(5786):504-507.
[6] KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Image net classification with deep convolutional neural networks[C]//Advances in Neural Information Processing Systems,2012,25(2):1105-1114.
[7] ALESSANDRO L,GIANLUCA P,PIERRE B.Deep architectures and deep learning in chemoinformatics:the prediction of aqueous solubility for drug-like molecules[J].Journal of Chemical Information and Modeling,2013,53(7):1563-1575.
[8] 张文达,许悦雷,倪嘉成,等.基于多尺度分块卷积神经网络的图像目标识别算法[J].计算机应用,2016,36(4):1033-1038.
[9] SCHMIDHUBER J,MEIER U,CIRESAN D.Multi-column deep neural networks for image classification[C]//IEEE Conference on Computer Vision and Pattern Recognition,2012,157(10):3642-3649.
[10] 黄道,宋欣.神经网络在化工过程故障诊断中的应用[J].控制工程,2006,13(1):6-9.
[11] DOWNS J J,VOGEL E F.A plant-wide industrial process control problem[J].Computers&Chemical Engineering,1993,17(3):245-255.
[12] WATANABE K,HIROTA S,HOU L,et al.Diagnosis of multiple simultaneous fault via hierarchical artificial neural networks[J].AIChE Journal,1994,40(5):839-848.
[13] 谷雷.基于人工神经网络的化工过程故障诊断[D].沈阳:沈阳理工大学,2008:22-36.
[14] 谷雷,杨青,王大志.概率神经网络在化工过程故障检测中的应用[J].控制工程,2008,15(s1):128-130.
[15] 张卫华,吴重光,等.基于神经网络的化工过程故障诊断[J].计算机与应用化学,2010,27(7):987-991.
[16] 缪素云.基于人工神经网络的TE过程故障诊断与检测研究[D].哈尔滨:哈尔滨理工大学,2011:38-45.
[17] KUMAR A,SINGH A P.Transistor level fault diagnosis in digital circuits using artificial neural network[J].Measurement,2016,82:384-390.
[18] AIRIKKA P.Advanced control methods for industrial process control[J].Computing and Control Engineering Journal,2004,15(3),18-23.
[19] PIOVOSO M J.Industrial process control[J].IEEE Control Systems,2000,20(3):22-24.
[20] JAMES L,MCCLELLAND.Parallel distributed processing[M].The PDP Research Group:The MIT Press,1987:45-623.
[21] GOH C J,EDWARDS N J,ZOMAYA A Y.Feedback control of minimum time optimal control problems using neural networks[J].Optimal Control Applications&Methods,1993,14(1):1-16.
[22] 裴浩东.基于神经网络的稳态优化和控制研究[D].杭州:浙江大学,2001:1-8.
[23] CHEN Q,WEIGAND W A.Dynamic optimization of nonlinear processes by combining neural net model with UDMC[J].AIChE Journal,2004,40(9):1488-1497.
[24] 夏静.基于广义回归神经网络的工业过程优化建模[D].哈尔滨:哈尔滨理工大学,2009:1-27.
[25] 安爱民.基于预测控制的先进过程控制技术研究[D].兰州:兰州理工大学,2010:1-14.
[26] ARCOTUMAPATHY V,SIAHVASHI A,ADESINA A A.A new weighted optimal combination of ANNs for catalyst design and reactor operation:methane steam reforming studies[J].AIChE Journal,2012,58(8):2412-2427.
[27] CARTWRIGHT H,CURTEANU S.Neural networks applied in chemistry.Ⅱ.Neuro-evolutionary techniques in process modeling and optimization[J].Industrial&Engineering Chemistry Research,2013,52(36):12673-12688.
[28] AHMED D F.Artificial neural network control of chemical processes[J].Uotechnology.edu.iq,2014,32-a(1):176-196.
[29] 郭凯,郭奇,李大伟,等.模糊神经网络PID控制器设计及在常减压装置中的应用[J].自动化应用,2016(2):14-15.
[30] 任有志,杨亚威,等.BP神经网络PID控制器在聚合釜温控中的应用[J].现代化工,2016,36(2):165-167.
[31] TSEN Y D,SHI S J,WONG D S H,et al.Predictive control of quality in batch polymerization using hybrid ANN models[J].AIChE Journal,1996,42(2):455-465.
[32] 李圭贤,宋桂秋,张东,等.BP神经网络法在产品质量预测中的应用[J].东北大学学报(自然科学版),2001,22(6):682-684.
[33] 郑唯唯.过程质量控制智能化体系与方法研究[D].西安:西北工业大学管理学院,2006:28-77.
[34] 程红军.基于神经网络的多元质量控制与诊断技术研究[D].天津:天津大学,2008:49-61.
[35] 杨明莉.基于人工神经网络的软件质量预测模型研究[D].长春:吉林工商学院信息工程学院,2013:1-4.
[36] 朱鹏飞,夏陆岳,潘海天.基于软测量技术的间歇聚合过程质量控制[J].计算机与应用化学,2015,32(8):959-963.
[37] 李鹏霞,陈晶,周喜斌,等.定量结构-性质/活性关系在分析和环境化学中的进展及应用[J].分析科学学报,2011,27(2):241-245.
[38] 潘勇,蒋军成,曹洪印,等.基于神经网络的定量结构-性质相关性研究预测有机物燃烧特性[J].化工进展,2008,27(3):378-384.
[39] 何琴,李靖.人工神经网络用于氯代芳烃定量结构-活性关系研究[J].河北化工,2012,35(9):28-31.
[40] 何琴,黄保军.人工神经网络用于有机磷酸酯类定量结构活性关系研究[J].安徽农业科学,2012,40(4):2087-2089.
[41] DONG M,LI G,LI Y,LIU C.The research on slab thermal properties estimated by bp artificial neural networks[C]//ICECE'10 Proceedings of the 2010 International Conference on Electrical and Control Engineering,IEEE Computer Society,Washington D C, USA,2010:2425-2427.
[42] 董新法,方利国,陈砺.物性估算原理及计算机计算[M].北京:化学工业出版社,2006:25-30.
[43] 张向东,赵立群,张国义.人工神经网络法预测有机物基础物性[J].化工学报,1995,46(1):66-74.
[44] 陈海松,王福安,宋建池,等.纯物质汽化热的人工神经网络算法[J].高校化学工程报,1998,12(4):475-478.
[45] 旷戈,赵素英,赵之山,等.人工神经网络基团贡献法估算纯有机物的临界参数[J].计算机与应用化学,2001,18(4):396-399.
[46] 旷戈,邱挺,赵之山,等.基团贡献人工神经网络法估算有机物常压沸点[J].化学工程,2001,29(6):49-51.
[47] 贺益君,高华,陈钟秀.基于基团贡献神经网络集成法估算有机物常压凝固点[J].化工学报,2004,55(7):1124-1130.
[48] TATLIER M,CIGIZOGLU H K,ERDEM-SENATALAR A.Artificial neural network methods for the estimation of zeolite molar compositions that form from different reaction mixtures[J].Computers&Chemical Engineering,2005,30(1):137-146.
[49] 潘勇,蒋军成.人工神经网络基团贡献法预测有机物闪点[J].天然气化工,2007,32(2):67-71.
[50] 潘勇,蒋军成,王志荣.人工神经网络基团键贡献法预测烷烃闪点[J].化学工程,2007,35(4):38-41.
[51] GHARAGHEIZI F,ESLAMIMANESH A,MOHAMMADI A H,et al.Determination of critical properties and acentric factors of pure compounds using the artificial neural network group contribution algorithm[J].Journal of Chemical&Engineering Data,2011,56(5):2460-2476.
[52] MOOSAVI M,SOLTANI N.Prediction of hydrocarbon densities using an artificial neural network-group contribution method up to high temperatures and pressures[J].Thermochimica Acta,2013,556:89-96.
[53] KHAZAIEPOUL A,SOLEIMANI M,SALAHI S.Solubility prediction of disperse dyes in supercritical carbon dioxide and ethanol as co-solvent using neural network[J].Chinese Journal of Chemical Engineering,2015,24(4):491-498.
[54] 魏奇业,李谦.基于神经网络的精馏塔动态模拟[J].吉林化工学院学报,2004,21(1):10-15.
[55] 张煜东,吴乐南,韦耿.基于粒子群神经网络的细胞图像分割方法[J].电子测量与仪器学报,2009,23(7):56-62.
[56] 张煜东,吴乐南,韦耿.神经网络泛化增强技术研究[J].科学技术与工程,2009,9(17):4997-5002.
[57] 张煜东,吴乐南,吴含前.工程优化问题中神经网络与进化算法的比较[J].计算机工程与应用,2009,45(3):1-6.
[58] ZHANG Y D,WU L N,WEI G.A New classifier for Polarimetric SAR images[J].Progress in Electromagnetics Research,2009,94(4):83-104.
[59] AMODIO P,PELLEGRINI A,UBIALI E,et al.The EEG assessment of low-grade hepatic encephalopathy:comparison of an artificial neural network-expert system(ANNES) based evaluation with visual EEG readings and EEG spectral analysis[J].Clinical Neurophysiology,2006,117(10):2243-225.
[60] VENKAT V,CHAN K.A neural network methodology for process fault diagnosis[J].Industrial&Engineering Chemistry Research,1989,35(12):1993-2002.
[61] 张璟,李人厚.实时控制神经网络专家系统结构及推理算法[J].模式识别与人工智能,1995(2):171-178.
[62] LIAU C K,YANG C K,TSAI M T.Expert system of a crude oil distillation unit for process optimization using neural networks[J].Expert Systems with Applications,2004,26(2):247-255.
[63] 杜文莉,钱峰.基于神经网络的实时专家控制系统及其PTA工业应用[J].控制与决策,2005,20(6):694-697.
[64] 郑小霞,钱锋.模糊神经网络推理的实时故障诊断专家系统[J].计算机工程与应用,2006,42(3):226-229.
[65] 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[J].Expert Systems with Applications,2008,34(4):1540-1545.
[66] WANG Y Y,LI Q J,CHANG M,et al.Research on fault diagnosis expert system based on the neural network and the fault tree technology[J].Procedia Engineering,2012,31(16):1206-1210.
[67] 辛志斌.基于聚类分析的神经网络-模糊控制[D].太原:太原理工大学,2003:1-37.
[68] 钟旭.ART2神经网络与化学模式聚类分析的研究[D].杭州:浙江大学,2004:1-62.
[69] 周洋,余文武,董相娟,等.基于聚类分析和神经网络的高炉焦比预测模型[J].辽宁科技大学学报,2010,33(3):245-247.
[70] 胡曙.基于模糊与神经网络的聚类分析[D].昆明:昆明理工大学,2012:1-54.
[71] 杨红波,郑剑.基于改进聚类分析的神经网络集成方法应用研究[J].计算机工程与科学,2015,37(5):974-978.