摘要
为了准确建立锅炉飞灰含碳量预测模型,首先提出了基于量子比特的Bloch球面坐标编码和迭代混沌映射的改进涡流搜索(I-VS)算法,然后对I-VS算法、涡流搜索(VS)算法、粒子群优化(PSO)算法、正余弦(SCA)算法和樽海鞘群(SSA)算法的性能进行比较。基于某热电厂300 MW循环流化床锅炉现场运行数据,采用I-VS算法优化并行感知机的极端学习机(PELM),得到飞灰含碳量的综合预测模型(即I-VS-PELM模型)。最后将I-VS-PELM模型的预测结果与PELM、PSO-PELM、SCA-PELM、SSA-PELM和VS-PELM模型的预测结果进行比较。结果表明:与其他模型相比,I-VS-PELM模型具有更高的预测精度和更好的泛化性能,能更准确地预测锅炉飞灰含碳量。
To accurately predict the carbon content in boiler fly ash, an improved vortex search(I-VS) algorithm was proposed based on Bloch coordinates and iterative chaos mapping, following which, a performance comparison was conducted among the original vortex search(VS) algorithm, I-VS algorithm, particle swarm optimization(PSO) algorithm, sine cosine algorithm(SCA) and salp swarm algorithm(SSA). Based on the operation data of a 300 MW circulating fluidized bed boiler, the I-VS algorithm was used to optimize the extreme learning machine with parallel layer perception(PELM) to form the I-VS-PELM model for prediction of carbon content in fly ash. The prediction results of I-VS-PELM were then compared with those of PELM, PSO-PELM, SCA-PELM, SSA-PELM and VS-PELM. Results show that, compared with other models, the I-VS-PELM model has not only higher prediction precision, but also better generalization ability, which could then be used to effectively predict the carbon content in boiler fly ash.
引文
[1]麻红波,余瑞锋,倪艳红,等.基于GSA-LSSVM的循环流化床锅炉飞灰含碳量预测[J].锅炉技术,2016,47(2):53-56,72.MA Hongbo,YU Ruifeng,NI Yanhong,et al.The prediction of the carbon content of fly ash of circulating fluidized bed boilers based on GSA-LSSVM[J].Boiler Technology,2016,47(2):53-56,72.
[2]王月兰,马增益,尤海辉,等.基于自适应神经模糊推理系统的煤粉锅炉飞灰含碳量建模[J].热力发电,2018,47(1):26-32.WANG Yuelan,MA Zengyi,YOU Haihui,et al.Modelling for unburned carbon content in fly ash from coal-fired boilers based on adaptive neuro-fuzzy inference system[J].Thermal Power Generation,2018,47(1):26-32.
[3]赵健,袁瀚,梅宁.燃煤锅炉飞灰含碳量的BP神经网络模型[J].热科学与技术,2016,15(6):499-504.ZHAO Jian,YUAN Han,MEI Ning.BP neural network model of fly ash carbon content of coal-fired boiler[J].Journal of Thermal Science and Technology,2016,15(6):499-504.
[4]张正友,钱家俊,冯旭刚.基于蚁群神经网络的飞灰含碳量测量方法[J].计测技术,2017,37(1):18-20.ZHANG Zhengyou,QIAN Jiajun,FENG Xugang.Prediction method of unburned carbon content in fly ash based on ant colony algorithm[J].Metrology&Measurement Technology,2017,37(1):18-20.
[5]TAVARES L D,SALDANHA R R,VIEIRA D AG.Extreme learning machine with parallel layer perceptrons[J].Neurocomputing,2015,166:164-171.
[6]DOGAN B,?LMEZ T.A new metaheuristic for numerical function optimization:vortex search algorithm[J].Information Sciences,2015,293:125-145.
[7]POLI R,KENNEDY J,BLACKWELL T.Particle swarm optimization:an overview[J].Swarm Intelligence,2007,1(1):33-57.
[8]MIRJALILI S.SCA:a sine cosine algorithm for solving optimization problems[J].Knowledge-Based Systems,2016,96:120-133.
[9]MIRJALILI S,GANDOMI A H,MIRJALILI S Z,et al.Salp swarm algorithm:a bio-inspired optimizer for engineering design problems[J].Advances in Engineering Software,2017,114:163-191.
[10]TOGAN V,DALOGLU A T.An improved genetic algorithm with initial population strategy and self-adaptive member grouping[J].Computers&Structures,2008,86(11/12):1204-1218.
[11]LI Panchi.A quantum-behaved evolutionary algorithm based on the Bloch spherical search[J].Communications in Nonlinear Science and Numerical Simulation,2014,19(4):763-771.
[12]BOUSHAKI S I,KAMEL N,BENDJEGHABA O.A new quantum chaotic cuckoo search algorithm for data clustering[J].Expert Systems with Applications,2018,96:358-372.
[13]HE Di,HE Chen,JIANG Lingge,et al.Chaotic characteristics of a one-dimensional iterative map with infinite collapses[J].IEEE Transactions on Circuits and Systems I:Fundamental Theory and Applications,2001,48(7):900-906.
[14]林开平.人工神经网络的泛化性能与降水预报的应用研究[D].南京:南京信息工程大学,2007.
[15]李俭川,秦国军,温熙森,等.神经网络学习算法的过拟合问题及解决方法[J].振动、测试与诊断,2002,22(4):260-264.LI Jianchuan,QIN Guojun,WEN Xisen,et al.O-ver-fitting in neural network learning algorithms and its solving strategies[J].Journal of Vibration,Measurement&Diagnosis,2002,22(4):260-264.
[16]江学军,唐焕文.前馈神经网络泛化性能力的系统分析[J].系统工程理论与实践,2000,20(8):36-40.JIANG Xuejun,TANG Huanwen.System analysis for generalization of MFNN[J].Systems EngineeringTheory&Practice,2000,20(8):36-40.