基于人工智能算法的催化裂化装置汽油收率预测模型的构建与分析
|
摘要
基于某石化企业的LIMS(Laboratory information management system)及DCS(Distributed control system)系统中的工业生产数据,结合工业经验中已知的影响催化裂化产品收率的重要因素,通过分析监控指标与实际汽油收率的相关性,筛选出与汽油收率的正负相关性较高的分析指标。在此基础上,基于梯度提升决策树GBDT算法构建了催化裂化汽油收率的预测模型,并预测了相应的汽油产率。结果表明:由GBDT算法构建的汽油收率预测模型预测结果的准确率为98.9%,R~2系数为0.236,平均绝对误差为0.531%;模型预测结果与实际汽油产率相比,误差率小于1%,表明构建的模型能精确预测催化裂化装置中汽油等产品收率,有助于在实际生产中优化催化裂化装置的操作条件,从而进一步提升催化裂化装置的经济性能。
Industrial data were collected from a petrochemical company's DCS(Distributed control system) and LIMS(Laboratory information management system) systems. Together with the essential factors affecting the product yield of catalytic cracking from industrial experience, indicators with high correlations were filtered out by analyzing their correlations with actual gasoline yield. Subsequently, a prediction model based on gradient-growth decision tree(GBDT algorithm) was constructed to predict the gasoline yield on the catalytic cracking unit. The results show that the accuracy of the GBDT gasoline yield prediction model is 98.9%, the R~2 value is 0.236, and the mean absolute error is 0.531%. Compared to actual gasoline yield, the error of prediction result is less than 1%, indicating that the presented model could predict the product yield such as gasoline on the catalytic cracking unit accurately. This will optimize the operation conditions of FCC, and further enhance the economic performance of FCC unit.
Industrial data were collected from a petrochemical company's DCS(Distributed control system) and LIMS(Laboratory information management system) systems. Together with the essential factors affecting the product yield of catalytic cracking from industrial experience, indicators with high correlations were filtered out by analyzing their correlations with actual gasoline yield. Subsequently, a prediction model based on gradient-growth decision tree(GBDT algorithm) was constructed to predict the gasoline yield on the catalytic cracking unit. The results show that the accuracy of the GBDT gasoline yield prediction model is 98.9%, the R~2 value is 0.236, and the mean absolute error is 0.531%. Compared to actual gasoline yield, the error of prediction result is less than 1%, indicating that the presented model could predict the product yield such as gasoline on the catalytic cracking unit accurately. This will optimize the operation conditions of FCC, and further enhance the economic performance of FCC unit.
引文
[1]SOUZA N L A,TKACH I,JR E M,et al.Vanadium poisoning of FCC catalysts:A quantitative analysis of impregnated and real equilibrium catalysts[J].Applied Catalysis A General,2018,560(12):206-214.
[2]SHAH M T,UTIKAR R P,PAREEK V K,et al.Computational fluid dynamic modelling of FCC riser:Areview[J].Chemical Engineering Research&Design,2016,111(7):403-448.
[3]SALVADO F C,TEIXEIRA-DIAS F,WALLEY S M,et al.A review on the strain rate dependency of the dynamic viscoplastic response of FCC metals[J].Progress in Materials Science,2017,88(7):186-231.
[4]卢春喜,范怡平,刘梦溪,等.催化裂化反应系统关键装备技术研究进展[J].石油学报(石油加工),2018,34(3):441-454.(LU Chunxi,FAN Yiping,LIUMengxi,et al.Advances in key equipment technologies of reaction system in RFCC unit[J].Acta Petrolei Sinica(Petroleum Processing Section),2018,34(3):441-454.)
[5]杨朝合,陈小博,李春义,等.催化裂化技术面临的挑战与机遇[J].中国石油大学学报:自然科学版,2017,41(6):171-177.(YANG Chaohe,CHEN Xiaobo,LIChunyi,et al.Challenges and opportunities of fluid catalytic cracking technology[J].Journal of China University of Petroleum(Edition of Natural Science),2017,41(6):171-177.)
[6]ALI A E,HADIS M,HAMID B,et al.Nine-lumped kinetic model for VGO catalytic cracking;using catalyst deactivation[J].Fuel,2018,231(21):118-125.
[7]SANI A G,EBRAHIM H A,AZARHOOSHM J.8-Lump kinetic model for fluid catalytic cracking with olefin detailed distribution study[J].Fuel,2018,225(15):322-335.
[8]熊凯,卢春喜.催化裂化(裂解)集总反应动力学模型研究进展[J].石油学报(石油加工),2015,31(2):293-306.(XIONG Kai,LU Chunxi.Research progresses of lump kinetic model of FCC and catalytic pyrolysis[J].Acta Petrolei Sinica(Petroleum Processing Section),2015,31(2):293-306.)
[9]ALARADI A A,ROHANI S.Identification and control of a riser-type FCC unit using neural networks[J].Computers&Chemical Engineering,2002,26(3):401-421.
[10]苏鑫,裴华健,吴迎亚,等.应用经遗传算法优化的BP神经网络预测催化裂化装置焦炭产率[J].化工进展,2016,35(2):389-396.(SU Xin,PEI Huajian,WUYingya,et al.Predicting coke yield of FCC unit using genetic algorithm optimized BP neural network[J].Chemical Industry and Engineering Progress,2016,35(2):389-396.)
[11]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.(ZHOU Xiaowei,YUAN Jun,YANGBolun.Prediction of octane number for clean gasoline obtained from secondary reactions based on BackPropagation neural network[J].Journal of Xi’an Jiaotong University,2010,44(12):82-86.)
[12]全石峰.云计算环境下大数据处理对电子商务发展的作用[J].电脑知识与技术,2013,19(20):4762-4770.(QUAN Shifeng.The effect of big data processing on the development of e-commerce in cloud computing environment[J].Computer Knowledge and Technology,2013,19(20):4762-4770.)
[13]赵云山,刘换换.大数据技术在电力行业的应用研究[J].电信科学,2014,30(1):57-62.(ZHAOYunshan,LIU Huanhuan.Research on application of big data technique in electricity power industry[J].Telecommunications Science,2014,30(1):57-62.)
[14]旷典,付尧明,房丽瑶.大数据挖掘分析在航空发动机状态监控与故障诊断中的应用[J].西安航空学院学报,2017,35(5):42-46.(KUANG Dian,FUYaoming,FANG Liyao.Application of big data mining analysis in aircraft engine condition monitoring and fault diagnosis[J].Journal of Xi’an Aeronautical University,2017,35(5):42-46.)
[15]THOMAS L.Big data in forensic science and medicine[J].Journal of Forensic and Legal Medicine,2017,57(7):1-6.
[16]苏鑫,吴迎亚,裴华健,等.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(6):1652-1659.(SU Xin,WU Yingya,PEI Huajian,et al.Recent development of the application of big data technology in process industries[J].Chemical Industry and Engineering Progress,2016,35(6):1652-1659.)
[17]ZAHEDI G,MOHAMMADZADEH S,MORADI G.Enhancing gasoline production in an industrial catalyticreforming unit using artificial neural networks[J].Energy&Fuels,2008,22(4):2671-2677.
[18]李鹏,郑晓军,明梁,等.大数据技术在催化裂化装置运行分析中的应用[J].化工进展,2016,35(3):665-670.(LI Peng,ZHENG Xiaojun,MING Liang,et al.Application of big data technology in operation analysis of catalytic cracking[J].Chemical Industry and Engineering Progress,2016,35(3):665-670.)
[19]陈露.基于数据挖掘的技术原油评价系统研究[D].西安:西安石油大学,2012.
[20]孔金生,张娓娓,王爱玲.催化裂化粗汽油干点的神经网络质量模型[J].湖南工业大学学报,2009,23(5):77-80.(KONG Jinsheng,ZHANG Weiwei,WANGAiling.Neural network quality model of FCC crude gasoline end-boiling-point[J].Journal of Hunan University of Technology,2009,23(5):77-80.)
[21]方伟刚.数据挖掘技术在催化裂化MIP工艺产品分布优化中的应用研究[D].上海:华东理工大学,2016.
[2]SHAH M T,UTIKAR R P,PAREEK V K,et al.Computational fluid dynamic modelling of FCC riser:Areview[J].Chemical Engineering Research&Design,2016,111(7):403-448.
[3]SALVADO F C,TEIXEIRA-DIAS F,WALLEY S M,et al.A review on the strain rate dependency of the dynamic viscoplastic response of FCC metals[J].Progress in Materials Science,2017,88(7):186-231.
[4]卢春喜,范怡平,刘梦溪,等.催化裂化反应系统关键装备技术研究进展[J].石油学报(石油加工),2018,34(3):441-454.(LU Chunxi,FAN Yiping,LIUMengxi,et al.Advances in key equipment technologies of reaction system in RFCC unit[J].Acta Petrolei Sinica(Petroleum Processing Section),2018,34(3):441-454.)
[5]杨朝合,陈小博,李春义,等.催化裂化技术面临的挑战与机遇[J].中国石油大学学报:自然科学版,2017,41(6):171-177.(YANG Chaohe,CHEN Xiaobo,LIChunyi,et al.Challenges and opportunities of fluid catalytic cracking technology[J].Journal of China University of Petroleum(Edition of Natural Science),2017,41(6):171-177.)
[6]ALI A E,HADIS M,HAMID B,et al.Nine-lumped kinetic model for VGO catalytic cracking;using catalyst deactivation[J].Fuel,2018,231(21):118-125.
[7]SANI A G,EBRAHIM H A,AZARHOOSHM J.8-Lump kinetic model for fluid catalytic cracking with olefin detailed distribution study[J].Fuel,2018,225(15):322-335.
[8]熊凯,卢春喜.催化裂化(裂解)集总反应动力学模型研究进展[J].石油学报(石油加工),2015,31(2):293-306.(XIONG Kai,LU Chunxi.Research progresses of lump kinetic model of FCC and catalytic pyrolysis[J].Acta Petrolei Sinica(Petroleum Processing Section),2015,31(2):293-306.)
[9]ALARADI A A,ROHANI S.Identification and control of a riser-type FCC unit using neural networks[J].Computers&Chemical Engineering,2002,26(3):401-421.
[10]苏鑫,裴华健,吴迎亚,等.应用经遗传算法优化的BP神经网络预测催化裂化装置焦炭产率[J].化工进展,2016,35(2):389-396.(SU Xin,PEI Huajian,WUYingya,et al.Predicting coke yield of FCC unit using genetic algorithm optimized BP neural network[J].Chemical Industry and Engineering Progress,2016,35(2):389-396.)
[11]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.(ZHOU Xiaowei,YUAN Jun,YANGBolun.Prediction of octane number for clean gasoline obtained from secondary reactions based on BackPropagation neural network[J].Journal of Xi’an Jiaotong University,2010,44(12):82-86.)
[12]全石峰.云计算环境下大数据处理对电子商务发展的作用[J].电脑知识与技术,2013,19(20):4762-4770.(QUAN Shifeng.The effect of big data processing on the development of e-commerce in cloud computing environment[J].Computer Knowledge and Technology,2013,19(20):4762-4770.)
[13]赵云山,刘换换.大数据技术在电力行业的应用研究[J].电信科学,2014,30(1):57-62.(ZHAOYunshan,LIU Huanhuan.Research on application of big data technique in electricity power industry[J].Telecommunications Science,2014,30(1):57-62.)
[14]旷典,付尧明,房丽瑶.大数据挖掘分析在航空发动机状态监控与故障诊断中的应用[J].西安航空学院学报,2017,35(5):42-46.(KUANG Dian,FUYaoming,FANG Liyao.Application of big data mining analysis in aircraft engine condition monitoring and fault diagnosis[J].Journal of Xi’an Aeronautical University,2017,35(5):42-46.)
[15]THOMAS L.Big data in forensic science and medicine[J].Journal of Forensic and Legal Medicine,2017,57(7):1-6.
[16]苏鑫,吴迎亚,裴华健,等.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(6):1652-1659.(SU Xin,WU Yingya,PEI Huajian,et al.Recent development of the application of big data technology in process industries[J].Chemical Industry and Engineering Progress,2016,35(6):1652-1659.)
[17]ZAHEDI G,MOHAMMADZADEH S,MORADI G.Enhancing gasoline production in an industrial catalyticreforming unit using artificial neural networks[J].Energy&Fuels,2008,22(4):2671-2677.
[18]李鹏,郑晓军,明梁,等.大数据技术在催化裂化装置运行分析中的应用[J].化工进展,2016,35(3):665-670.(LI Peng,ZHENG Xiaojun,MING Liang,et al.Application of big data technology in operation analysis of catalytic cracking[J].Chemical Industry and Engineering Progress,2016,35(3):665-670.)
[19]陈露.基于数据挖掘的技术原油评价系统研究[D].西安:西安石油大学,2012.
[20]孔金生,张娓娓,王爱玲.催化裂化粗汽油干点的神经网络质量模型[J].湖南工业大学学报,2009,23(5):77-80.(KONG Jinsheng,ZHANG Weiwei,WANGAiling.Neural network quality model of FCC crude gasoline end-boiling-point[J].Journal of Hunan University of Technology,2009,23(5):77-80.)
[21]方伟刚.数据挖掘技术在催化裂化MIP工艺产品分布优化中的应用研究[D].上海:华东理工大学,2016.