面向反应再生过程的量子粒子群多目标优化
|
摘要
针对催化裂化反应再生过程难以有效解决提升效率、降低损耗、减少排放的多目标优化问题,利用改进的多目标量子粒子群算法进行求解。建立轻油收率、焦炭产率和硫化物排量的多目标优化模型;引入拥挤熵排序更新外部档案,精确估计非支配解集分布性;构造自适应因子以动态调整吸引子,平衡算法的收敛性和多样性;再引入高斯变异进行分段式扰动,增强算法的局部搜索精度,最后求解该优化模型。对某厂催化裂化进行实验,得到轻质油吸收率76.22%,焦炭产率5.72%和硫化物排放量626 mg/m~3的结果,均优于其他比较算法,表明改进后的算法可以快速、准确地获得分布均匀的Pareto最优解,能有效解决反应再生过程多目标优化问题。
It is difficult to solve the multi-objective optimization problem of improving efficiency, reducing loss and reducing emissions for the catalytic cracking reaction regeneration process. The improved multi-objective quantum-based particle swarm optimization-crowding entropy sorting(MQPSO-CES) is used to solve the problem. A multi-objective optimization model is established to maximize the light oil absorption rate and synchronously minimize thecoke yield and sulfide emissions. Particularly, crowding entropy sorting is used to update the archive, whichaccurately estimates the distribution of the non-dominated solutions. Afterwards, an adaptive factor is introduced toself-adaptively and dynamically adjust the construction of the attractor, which can balance the convergence anddiversity of the proposed algorithm. In addition, with the application of a piecewise Gauss mutation operator, theprecision of the local search can be enhanced. Finally, the multi-objective model is resolved with the novelalgorithm. The results indicate that the improved algorithm can outperform other algorithms with convergent andwell-distributed approximate Pareto fronts when dealing with ZDT3-4 and DTLZ1-2 benchmark problems. Inaddition, the proposed algorithm can obtain 76.22% of light oil absorption rate, 5.72% of coke yield and 626 mg/m~3 of sulfide emissions in the reaction and generation process, illustrate its superiority compared with other algorithms.
It is difficult to solve the multi-objective optimization problem of improving efficiency, reducing loss and reducing emissions for the catalytic cracking reaction regeneration process. The improved multi-objective quantum-based particle swarm optimization-crowding entropy sorting(MQPSO-CES) is used to solve the problem. A multi-objective optimization model is established to maximize the light oil absorption rate and synchronously minimize thecoke yield and sulfide emissions. Particularly, crowding entropy sorting is used to update the archive, whichaccurately estimates the distribution of the non-dominated solutions. Afterwards, an adaptive factor is introduced toself-adaptively and dynamically adjust the construction of the attractor, which can balance the convergence anddiversity of the proposed algorithm. In addition, with the application of a piecewise Gauss mutation operator, theprecision of the local search can be enhanced. Finally, the multi-objective model is resolved with the novelalgorithm. The results indicate that the improved algorithm can outperform other algorithms with convergent andwell-distributed approximate Pareto fronts when dealing with ZDT3-4 and DTLZ1-2 benchmark problems. Inaddition, the proposed algorithm can obtain 76.22% of light oil absorption rate, 5.72% of coke yield and 626 mg/m~3 of sulfide emissions in the reaction and generation process, illustrate its superiority compared with other algorithms.
引文
[1]鲁波娜,张景远,王维,等. FCC反应过程的CFD模拟进展[J].化工学报, 2016, 67(8):3121-3132.Lu B N, Zhang J Y, Wang W, et al. CFD modeling of FCC reaction process:a review[J]. CIESC Journal, 2016, 67(8):3121-3132.
[2]刘蕾,赵众,陶兴文,等.催化裂化反应再生系统的建模与优化[J].石油化工自动化, 2009, 26(5):26-30.Liu L, Zhao Z, Tao X W, et al. The modeling and optimization for FCC reactor-regenerator system[J]. Automation in PetroChemical Industry, 2009, 26(5):26-30.
[3]谢朝钢,魏晓丽,龚剑洪,等.催化裂化反应机理研究进展及实践应用[J].石油学报(石油加工), 2017, 33(2):189-197.Xie C G, Wei X L, Gong J H, et al. Progress on chemistry of catalytic cracking reaction and its practice[J]. Acta Petroeli Sinica(Petroleum Processing Section), 2017, 33(2):189-197.
[4]刘梦溪,卢春喜,时铭显.催化裂化后反应系统快分的研究进展[J].化工学报, 2016, 67(8):3133-3145.Liu M X, Lu C X, Shi M X. Advances in quick separators of postriser system in FRCC unit[J]. CIESC Journal, 2016, 67(8):3133-3145.
[5]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):295-305.Xiong K, Lu C X. Research progresses of lump kinetic model of FCC and catalytic pyrolysis[J]. Acta Petroeli Sinica(Petroleum Processing Section), 2015, 31(2):295-305.
[6]吴飞跃,翁惠新,罗世贤. FDFCC工艺中重油提升管催化裂化反应动力学模型[J].石油学报, 2008, 24(5):540-546.Wu F Y, Weng H X, Luo S X. Kinetic model for heavy oil catalytic cracking in riser of FCC process[J]. Acta Petroeli Sinica,2008, 24(5):540-546.
[7]张忠洋,李泽钦,李宇龙,等. GA辅助BP神经网络预测催化裂化装置汽油产率[J].石油炼制与化工, 2014, 45(7):91-96.Zhang Z Y, Li Z Q, Li Y L, et al. Prediction of gasoline yield in FCC unit by GA aided BP neural network[J]. Petroleum Processing and Petrochemicals, 2014, 45(7):91-96.
[8] Yi J, Huang D, Li T F, et al. A novel framework for fault diagnosis using kernel partial least squares based on an optimal preference matrix[J]. IEEE Transaction on Industrial Electronics, 2017, 64(5):4315-4324.
[9] Yi J, Huang D, Fu S Y, et al. Optimized relative transformation matrix using bacterial foraging algorithm for process fault detection[J]. IEEE Transaction on Industrial Electronics, 2016, 63(4):2595-2605.
[10] Yi J, Bai J R, Zhou W, et al. Operating parameters optimization for the aluminum electrolysis process using an improved quantumbehaved particle swarm algorithm[J]. IEEE Transaction on Industrial Informatics, 2018, 14(8):3405-3415.
[11] Michalopoulos J, Papadokonstadakis S, Ararnpatzis G, et al.Modelling of an industrial fluid catalytic cracking unit using neural networks[J]. Institution of Chemical Engineers, 2001, 79(3):137-143.
[12] Lid T, Strand S. Real-time optimization of a cat cracker unit[J].Computers&Chemical Engineering, 1997, 21(1/2):887-892.
[13] Sankararao B, Gupta K S. Multi-objective optimization of an industrial fluidized-bed catalytic cracking unit using two jumping gene adaptations of simulated annealing[J]. Computers and Chemical Engineering, 2007, 31:1496-1515.
[14] Kasat B R, Gupta K S. Multi-objective optimization of an industrial fluidized-bed catalytic cracking unit using genetic algorithm with the jumping genes operator[J]. Computers and Chemical Engineering, 2003, 27:1785-1800.
[15] Chen C, Yang B, Yuan J, et al. Establishment and solution of eight-lump kinetic model for FCC gasoline secondary reaction using particle swarm optimization[J]. Fuel, 2007, 86:2325-2332.
[16] Wang Y, Wu L, Yuan X. Multi-objective self-adaptive differential evolution with elitist archive and crowding entropybased diversity measure[J]. Soft Computing, 2010, 14(3):193-209.
[17]肖晓伟,肖迪,林锦国,等.多目标优化问题的研究概述[J].计算机应用研究, 2011, 28(3):805-808.Xiao X W, Xiao D, Lin J G, et al. Overview on multi-objective optimization problem research[J]. Application Research of Computers, 2011, 28(3):805-808.
[18] Sun J, Feng B, Xu W. Particle swarm optimization with particles having quantum behavior[C]//Proc. of the IEEE Congress on Evolutionary Computation. Portland, USA:IEEE, 2004:325-331.
[19] Wang Y N, Wu L H, Yuan X. Multi-objective self-adaptive differential evolution with elitist archive and crowding entropybased diversity measure[J]. Soft Computing, 2010, 14(3):193-209.
[20] Coelho L D S. Gaussian quantum-behaved particle swarm optimization approaches for constrained engineering design problems[J]. Expert Systems with Applications, 2010, 37(2):1676-1683.
[21] Zitzler E, Laumanns M, Thiele L. SPEA2:improving the strength pareto evolutionary algorithm[C]//Evolutionary Methods for Design, Optimization and Control with Applications to Industrial Problems, 2002:95-100.
[22] Sierra M R, Coello C A C. Multi-objective particle swarm optimizer:a survey of the state-of-the-art[J]. International Journal of Computation Intelligence Research, 2006, 22(3):287-308.
[23] Deb K, Pratap A, Agarwal S, et al. A fast and elitist multiobjective genetic algorithm:NSGA-II[J]. IEEE Transactions on Evolutionary Computation, 2002, 6(2):182-197.
[24]华长春,王雅洁,李军朋,等.基于NSGA-Ⅱ算法的高炉生产配料多目标优化模型建立[J].化工学报, 2016, 67(3):1040-1047.Hua C C, Wang Y J, Li J P, et al. Multi-objective optimization model for blast furnace production and ingredients based on NSGA-II algorithm[J]. CIESC Journal, 2016, 67(3):1040-1047.
[25] Yi J, Huang D, Fu S Y, et al. Multi-objective bacterial foraging optimization algorithm based on parallel cell entropy for aluminum electrolysis production process[J]. IEEE Transaction on Industrial Electronics, 2016, 63(4):2488-2500.
[26]易军,黄迪,李太福,等.基于拥挤距离排序的铝电解多目标优化[J].仪器仪表学报, 2015, 36(11):2502-2509.Yi J, Huang D, Li T F, et al. Optimization of aluminum electrolysis production process based on crowding distance sorting[J]. Chinese Journal of Scientific Instrument, 2015, 36(11):2502-2509.
[27]施展,陈庆伟.基于QPSO和拥挤距离排序的多目标量子粒子群优化算法[J].控制与决策, 2011, 26(4):540-547.Shi Z, Chen Q W. Multi-objective quantum-behaved particle swarm optimization algorithm based on QPSO and crowding distance sorting[J]. Control and Decision, 2011, 26(4):540-547.
[28] Ding S F, Su C Y, Yu J Z. An optimizing BP neural network algorithm based on genetic algorithm[J]. Artificial Intelligence Review, 2011, 36(2):153-162.
[29]刘朝华,王慧娟,吴春笃,等.基于BP神经网络的脉冲放电等离子体氧化酸性橙Ⅱ影响因素分析[J].化工学报, 2012, 63(10):3190-3195.Liu C H, Wang H J, Wu C D, et al. Analysis of factors effecting acid orange 7 decoloration in pulsed discharge plasma system based on BP neural network mode[J]. CIESC Journal, 2012, 63(10):3190-3195.
[2]刘蕾,赵众,陶兴文,等.催化裂化反应再生系统的建模与优化[J].石油化工自动化, 2009, 26(5):26-30.Liu L, Zhao Z, Tao X W, et al. The modeling and optimization for FCC reactor-regenerator system[J]. Automation in PetroChemical Industry, 2009, 26(5):26-30.
[3]谢朝钢,魏晓丽,龚剑洪,等.催化裂化反应机理研究进展及实践应用[J].石油学报(石油加工), 2017, 33(2):189-197.Xie C G, Wei X L, Gong J H, et al. Progress on chemistry of catalytic cracking reaction and its practice[J]. Acta Petroeli Sinica(Petroleum Processing Section), 2017, 33(2):189-197.
[4]刘梦溪,卢春喜,时铭显.催化裂化后反应系统快分的研究进展[J].化工学报, 2016, 67(8):3133-3145.Liu M X, Lu C X, Shi M X. Advances in quick separators of postriser system in FRCC unit[J]. CIESC Journal, 2016, 67(8):3133-3145.
[5]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):295-305.Xiong K, Lu C X. Research progresses of lump kinetic model of FCC and catalytic pyrolysis[J]. Acta Petroeli Sinica(Petroleum Processing Section), 2015, 31(2):295-305.
[6]吴飞跃,翁惠新,罗世贤. FDFCC工艺中重油提升管催化裂化反应动力学模型[J].石油学报, 2008, 24(5):540-546.Wu F Y, Weng H X, Luo S X. Kinetic model for heavy oil catalytic cracking in riser of FCC process[J]. Acta Petroeli Sinica,2008, 24(5):540-546.
[7]张忠洋,李泽钦,李宇龙,等. GA辅助BP神经网络预测催化裂化装置汽油产率[J].石油炼制与化工, 2014, 45(7):91-96.Zhang Z Y, Li Z Q, Li Y L, et al. Prediction of gasoline yield in FCC unit by GA aided BP neural network[J]. Petroleum Processing and Petrochemicals, 2014, 45(7):91-96.
[8] Yi J, Huang D, Li T F, et al. A novel framework for fault diagnosis using kernel partial least squares based on an optimal preference matrix[J]. IEEE Transaction on Industrial Electronics, 2017, 64(5):4315-4324.
[9] Yi J, Huang D, Fu S Y, et al. Optimized relative transformation matrix using bacterial foraging algorithm for process fault detection[J]. IEEE Transaction on Industrial Electronics, 2016, 63(4):2595-2605.
[10] Yi J, Bai J R, Zhou W, et al. Operating parameters optimization for the aluminum electrolysis process using an improved quantumbehaved particle swarm algorithm[J]. IEEE Transaction on Industrial Informatics, 2018, 14(8):3405-3415.
[11] Michalopoulos J, Papadokonstadakis S, Ararnpatzis G, et al.Modelling of an industrial fluid catalytic cracking unit using neural networks[J]. Institution of Chemical Engineers, 2001, 79(3):137-143.
[12] Lid T, Strand S. Real-time optimization of a cat cracker unit[J].Computers&Chemical Engineering, 1997, 21(1/2):887-892.
[13] Sankararao B, Gupta K S. Multi-objective optimization of an industrial fluidized-bed catalytic cracking unit using two jumping gene adaptations of simulated annealing[J]. Computers and Chemical Engineering, 2007, 31:1496-1515.
[14] Kasat B R, Gupta K S. Multi-objective optimization of an industrial fluidized-bed catalytic cracking unit using genetic algorithm with the jumping genes operator[J]. Computers and Chemical Engineering, 2003, 27:1785-1800.
[15] Chen C, Yang B, Yuan J, et al. Establishment and solution of eight-lump kinetic model for FCC gasoline secondary reaction using particle swarm optimization[J]. Fuel, 2007, 86:2325-2332.
[16] Wang Y, Wu L, Yuan X. Multi-objective self-adaptive differential evolution with elitist archive and crowding entropybased diversity measure[J]. Soft Computing, 2010, 14(3):193-209.
[17]肖晓伟,肖迪,林锦国,等.多目标优化问题的研究概述[J].计算机应用研究, 2011, 28(3):805-808.Xiao X W, Xiao D, Lin J G, et al. Overview on multi-objective optimization problem research[J]. Application Research of Computers, 2011, 28(3):805-808.
[18] Sun J, Feng B, Xu W. Particle swarm optimization with particles having quantum behavior[C]//Proc. of the IEEE Congress on Evolutionary Computation. Portland, USA:IEEE, 2004:325-331.
[19] Wang Y N, Wu L H, Yuan X. Multi-objective self-adaptive differential evolution with elitist archive and crowding entropybased diversity measure[J]. Soft Computing, 2010, 14(3):193-209.
[20] Coelho L D S. Gaussian quantum-behaved particle swarm optimization approaches for constrained engineering design problems[J]. Expert Systems with Applications, 2010, 37(2):1676-1683.
[21] Zitzler E, Laumanns M, Thiele L. SPEA2:improving the strength pareto evolutionary algorithm[C]//Evolutionary Methods for Design, Optimization and Control with Applications to Industrial Problems, 2002:95-100.
[22] Sierra M R, Coello C A C. Multi-objective particle swarm optimizer:a survey of the state-of-the-art[J]. International Journal of Computation Intelligence Research, 2006, 22(3):287-308.
[23] Deb K, Pratap A, Agarwal S, et al. A fast and elitist multiobjective genetic algorithm:NSGA-II[J]. IEEE Transactions on Evolutionary Computation, 2002, 6(2):182-197.
[24]华长春,王雅洁,李军朋,等.基于NSGA-Ⅱ算法的高炉生产配料多目标优化模型建立[J].化工学报, 2016, 67(3):1040-1047.Hua C C, Wang Y J, Li J P, et al. Multi-objective optimization model for blast furnace production and ingredients based on NSGA-II algorithm[J]. CIESC Journal, 2016, 67(3):1040-1047.
[25] Yi J, Huang D, Fu S Y, et al. Multi-objective bacterial foraging optimization algorithm based on parallel cell entropy for aluminum electrolysis production process[J]. IEEE Transaction on Industrial Electronics, 2016, 63(4):2488-2500.
[26]易军,黄迪,李太福,等.基于拥挤距离排序的铝电解多目标优化[J].仪器仪表学报, 2015, 36(11):2502-2509.Yi J, Huang D, Li T F, et al. Optimization of aluminum electrolysis production process based on crowding distance sorting[J]. Chinese Journal of Scientific Instrument, 2015, 36(11):2502-2509.
[27]施展,陈庆伟.基于QPSO和拥挤距离排序的多目标量子粒子群优化算法[J].控制与决策, 2011, 26(4):540-547.Shi Z, Chen Q W. Multi-objective quantum-behaved particle swarm optimization algorithm based on QPSO and crowding distance sorting[J]. Control and Decision, 2011, 26(4):540-547.
[28] Ding S F, Su C Y, Yu J Z. An optimizing BP neural network algorithm based on genetic algorithm[J]. Artificial Intelligence Review, 2011, 36(2):153-162.
[29]刘朝华,王慧娟,吴春笃,等.基于BP神经网络的脉冲放电等离子体氧化酸性橙Ⅱ影响因素分析[J].化工学报, 2012, 63(10):3190-3195.Liu C H, Wang H J, Wu C D, et al. Analysis of factors effecting acid orange 7 decoloration in pulsed discharge plasma system based on BP neural network mode[J]. CIESC Journal, 2012, 63(10):3190-3195.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |