基于互信息和IGSA优化ELM的重整芳烃收率软测量
|
摘要
芳烃收率是催化重整生产过程中一个重要的产品质量指标。针对芳烃收率难以在线测量的问题,提出一种基于互信息(MI)和改进引力搜索算法(IGSA)优化极限学习机(ELM)的芳烃收率软测量建模方法。首先利用MI技术对输入变量进行特征提取及降维处理,确定软测量模型的辅助变量;其次通过引入序列二次规划法(SQP)和混沌变异策略,构建一种具有良好全局寻优性能的改进引力搜索算法,并利用该算法优化极限学习机的隐层阈值及输入权值参数,优化目标同时兼顾模型输出均方根误差和输出矩阵条件数的最小化,建立起基于IGSA优化ELM的芳烃收率软测量模型;最后应用该模型对某炼化企业催化重整装置的芳烃收率进行预报研究,结果表明,该软测量模型具有较高的预测精度和可靠性能。
Aromatic hydrocarbon yield is considered as one of the important product quality indicator in catalytic reforming production process. Aiming at the difficulty of the aromatic hydrocarbon yield on-line measurement, a soft sensor modeling method of aromatic hydrocarbon yield is proposed based on mutual information-improved gravitational search algorithm(MI-IGSA) optimized extreme learning machine(ELM). Firstly, the MI method is used to extract the most relevant process feature quantities and perform dimension reduction processing, and the auxiliary variables of the soft sensor model are determined. Secondly, through introducing the successive quadratic programming(SQP) method and chaos mutation strategy, the IGSA with good global optimization performance is constructed. The IGSA algorithm is then applied to optimize the hidden layer threshold parameters and input weight parameters of ELM, and the optimization target considers the minimization of both the root mean squared error(RMSE) of the model output and the number of conditions of the hidden layer output matrix. Finally, the aromatic hydrocarbon yield soft sensor model is established based on the IGSA optimized ELM method. The proposed model was applied in the prediction study of the aromatic hydrocarbon yield of the catalytic reforming equipment in a certain refinery plant, the simulation results show that the proposed soft sensor model possesses promising prediction accuracy and reliability.
Aromatic hydrocarbon yield is considered as one of the important product quality indicator in catalytic reforming production process. Aiming at the difficulty of the aromatic hydrocarbon yield on-line measurement, a soft sensor modeling method of aromatic hydrocarbon yield is proposed based on mutual information-improved gravitational search algorithm(MI-IGSA) optimized extreme learning machine(ELM). Firstly, the MI method is used to extract the most relevant process feature quantities and perform dimension reduction processing, and the auxiliary variables of the soft sensor model are determined. Secondly, through introducing the successive quadratic programming(SQP) method and chaos mutation strategy, the IGSA with good global optimization performance is constructed. The IGSA algorithm is then applied to optimize the hidden layer threshold parameters and input weight parameters of ELM, and the optimization target considers the minimization of both the root mean squared error(RMSE) of the model output and the number of conditions of the hidden layer output matrix. Finally, the aromatic hydrocarbon yield soft sensor model is established based on the IGSA optimized ELM method. The proposed model was applied in the prediction study of the aromatic hydrocarbon yield of the catalytic reforming equipment in a certain refinery plant, the simulation results show that the proposed soft sensor model possesses promising prediction accuracy and reliability.
引文
[1] FRANCISCO A A,RUI A,JEROME M.Review of soft sensor methods for regression applications[J].Chemometrics and Intelligent Laboratory Systems,2016(152):69-79.
[2] 曹鹏飞,罗雄麟.化工过程软测量建模方法研究进展[J].化工学报,2013,64(3):788- 800.CAO P F,LUO X L.Research progress in soft sensing modeling methods for chemical processes[J].CIESC Journal,2013,64(3):788- 800.
[3] 赵朋程,刘彬,孙超,等.基于IQPSO优化ELM的熟料质量指标软测量研究[J].仪器仪表学报,2016,37(10):2243- 2250.ZHAO P CH,LIU B,SUN CH,et al.Soft measurement of clinker quality index based on IQPSO optimized ELM[J].Acta Instrument,2016,37(10):2243- 2250.
[4] 朱湘临,凌婧,王博,等.基于改进PSO-RBFNN的海洋蛋白酶发酵过程软测量[J].化工学报,2018,69(3):1221-1227.ZHU X L,LING J,WANG B,et al.Soft measurement of marine protease fermentation process based on improved PSO-RBFNN[J].CIESC Journal,2018,69(3):1221-1227.
[5] 刘思成,李悦,杨秀,等.芳烃抽提过程收率软测量技术应用[J].自动化与仪器仪表,2015,50(4):45- 47.LIU S CH,LI Y,YANG X,et al.Application of Soft measurement technology for aromatics extraction process[J].Automation & Instrumentation,2015,50(4):45- 47.
[6] 王玉乔,程光旭,汤杰国.基于KPCA的连续重整催化剂结焦碳含量软测量模型[J].高校化学工程学报,2009,23(5):852- 857.WANG Y Q,CHENG G X,TANG J G.Soft measurement model of coke carbon content in continuous reforming catalyst based on KPCA[J].Journal of Chemical Engineering of Chinese Universities,2009,23(5):852- 857.
[7] 邱禹,刘乙奇,吴箐,等.基于深层神经网络的多输出自适应软测量建模[J].化工学报,2018,69(7):3101-3113.QIU Y,LIU Y Q,WU W,et al.Multi-output adaptive soft sensor modeling based on deep neural network[J].CIESC Journal,2018,69(7):3101-3113.
[8] HUANG G B,ZHOU H,DING X,et al.Extreme learning machine:a survey[J].International Journal of Machine Learning and Cybernetics,2011,2(2):107-122.
[9] HUANG G,HUANG G B.Trends in extreme learning machines:A review[J].Neural Networks,2015(61):32- 48.
[10] 王宇红,狄克松,张姗,等.基于DBN-ELM的聚丙烯融指数的软测量[J].化工学报,2016,67(12):5163- 5168.WANG Y H,DI K S,ZHANG SH,et al.Soft measurement of polypropylene melting index based on DBN-ELM[J].CIESC Journal,2016,67(12):5163- 5168.
[11] 贺彦林,王晓.朱群雄.基于主成分分析-改进的极限学习机方法的精对苯二甲酸醋酸含量软测量[J].控制理论与应用,2015,32(1):80- 85.HE Y L,WANG X.ZHU Q X.Soft measurement of purified terephthalic acid content based on principal component analysis-improved extreme learning machine method[J].Control Theory and Applications,2015,32(1):80- 85.
[12] 刘浩然,赵翠香,李轩,等.一种基于改进遗传算法的神经网络优化算法研究[J].仪器仪表学报,2016,37(7):1573-1580.LIU H R,ZHAO C X,LI X,et al.A neural network optimization algorithm based on improved genetic algorithm[J].Chinese Journal of Scientific Instrument,2016,37(7):1573-1580.
[13] WANG M J,CHEN H L,LI H Z,et al.Grey wolf optimization evolving kernel extreme learning machine:Application to bankruptcy prediction[J].Engineering Applications of Artificial Intelligence,2017(63):54- 68.
[14] 毛羽,毛力,杨弘,等.改进人工蜂群优化的极限学习机[J].传感器与微系统,2018,37(4):116-120.MAO Y,MAO L,YANG H,et al.Extreme learning machines optimized by improved ABC[J].Transducer and Microsystem Technologies,2018,37(4):116-120.
[15] RASHEDI E,HOSSEI N.A comprehensive survey on gravitational search algorithm[J].Swarm and Evolutionary Computation,2018(41):141-158.
[16] KHARE A,SAROJ R.A review of particle swarm optimization and its applications in Solar photovoltaic system[J].Applied Soft Computing,2013,13(5):2997-3006.
[17] 黄海松,魏建安,康佩东.基于不平衡数据样本特性的新型过采样SVM分类算法[J].控制与决策,2018,33(9):1549-1558.HUANG H S,WEI J AN,KANG P D.A review over sampling SVM classification algorithm based on unbalanced data sample characteristics[J].Control and Decision,2018,33(9):1549-1558.
[2] 曹鹏飞,罗雄麟.化工过程软测量建模方法研究进展[J].化工学报,2013,64(3):788- 800.CAO P F,LUO X L.Research progress in soft sensing modeling methods for chemical processes[J].CIESC Journal,2013,64(3):788- 800.
[3] 赵朋程,刘彬,孙超,等.基于IQPSO优化ELM的熟料质量指标软测量研究[J].仪器仪表学报,2016,37(10):2243- 2250.ZHAO P CH,LIU B,SUN CH,et al.Soft measurement of clinker quality index based on IQPSO optimized ELM[J].Acta Instrument,2016,37(10):2243- 2250.
[4] 朱湘临,凌婧,王博,等.基于改进PSO-RBFNN的海洋蛋白酶发酵过程软测量[J].化工学报,2018,69(3):1221-1227.ZHU X L,LING J,WANG B,et al.Soft measurement of marine protease fermentation process based on improved PSO-RBFNN[J].CIESC Journal,2018,69(3):1221-1227.
[5] 刘思成,李悦,杨秀,等.芳烃抽提过程收率软测量技术应用[J].自动化与仪器仪表,2015,50(4):45- 47.LIU S CH,LI Y,YANG X,et al.Application of Soft measurement technology for aromatics extraction process[J].Automation & Instrumentation,2015,50(4):45- 47.
[6] 王玉乔,程光旭,汤杰国.基于KPCA的连续重整催化剂结焦碳含量软测量模型[J].高校化学工程学报,2009,23(5):852- 857.WANG Y Q,CHENG G X,TANG J G.Soft measurement model of coke carbon content in continuous reforming catalyst based on KPCA[J].Journal of Chemical Engineering of Chinese Universities,2009,23(5):852- 857.
[7] 邱禹,刘乙奇,吴箐,等.基于深层神经网络的多输出自适应软测量建模[J].化工学报,2018,69(7):3101-3113.QIU Y,LIU Y Q,WU W,et al.Multi-output adaptive soft sensor modeling based on deep neural network[J].CIESC Journal,2018,69(7):3101-3113.
[8] HUANG G B,ZHOU H,DING X,et al.Extreme learning machine:a survey[J].International Journal of Machine Learning and Cybernetics,2011,2(2):107-122.
[9] HUANG G,HUANG G B.Trends in extreme learning machines:A review[J].Neural Networks,2015(61):32- 48.
[10] 王宇红,狄克松,张姗,等.基于DBN-ELM的聚丙烯融指数的软测量[J].化工学报,2016,67(12):5163- 5168.WANG Y H,DI K S,ZHANG SH,et al.Soft measurement of polypropylene melting index based on DBN-ELM[J].CIESC Journal,2016,67(12):5163- 5168.
[11] 贺彦林,王晓.朱群雄.基于主成分分析-改进的极限学习机方法的精对苯二甲酸醋酸含量软测量[J].控制理论与应用,2015,32(1):80- 85.HE Y L,WANG X.ZHU Q X.Soft measurement of purified terephthalic acid content based on principal component analysis-improved extreme learning machine method[J].Control Theory and Applications,2015,32(1):80- 85.
[12] 刘浩然,赵翠香,李轩,等.一种基于改进遗传算法的神经网络优化算法研究[J].仪器仪表学报,2016,37(7):1573-1580.LIU H R,ZHAO C X,LI X,et al.A neural network optimization algorithm based on improved genetic algorithm[J].Chinese Journal of Scientific Instrument,2016,37(7):1573-1580.
[13] WANG M J,CHEN H L,LI H Z,et al.Grey wolf optimization evolving kernel extreme learning machine:Application to bankruptcy prediction[J].Engineering Applications of Artificial Intelligence,2017(63):54- 68.
[14] 毛羽,毛力,杨弘,等.改进人工蜂群优化的极限学习机[J].传感器与微系统,2018,37(4):116-120.MAO Y,MAO L,YANG H,et al.Extreme learning machines optimized by improved ABC[J].Transducer and Microsystem Technologies,2018,37(4):116-120.
[15] RASHEDI E,HOSSEI N.A comprehensive survey on gravitational search algorithm[J].Swarm and Evolutionary Computation,2018(41):141-158.
[16] KHARE A,SAROJ R.A review of particle swarm optimization and its applications in Solar photovoltaic system[J].Applied Soft Computing,2013,13(5):2997-3006.
[17] 黄海松,魏建安,康佩东.基于不平衡数据样本特性的新型过采样SVM分类算法[J].控制与决策,2018,33(9):1549-1558.HUANG H S,WEI J AN,KANG P D.A review over sampling SVM classification algorithm based on unbalanced data sample characteristics[J].Control and Decision,2018,33(9):1549-1558.