基于深度信念网络的纳米流体热导率预测方法
|
摘要
纳米流体因具有较好的传热性能而被认为是未来极具发展前景的强化传热工质,为了提高纳米流体热导率预测的精确性,依据深度学习理论建立了基于DBN的纳米流体热导率预测模型.对模型进行训练和微调,可自动提取纳米流体热导率自身的发展规律,逐层激活纳米流体各影响因素的强相关性.将深度信念网络模型的仿真结果与基于BP神经网络、基于SVM纳米流体热导率预测模型的仿真结果及实验数据进行对比,结果表明:DBN预测模型克服了传统神经网络容易陷入局部最优、训练时间长及函数拟合度不高等缺点,具有预测精度高,预测速度快的优点.
Nanofluids are considered to be the most promising enhancement in the future because of their excellent heat transfer performance,and the research on the thermal conductivity of nanofluids is the basis of their application.In order to improve the accuracy of the thermal conductivity prediction of nanofluids,a prediction model for the thermal conductivity of nanofluids based on deep belief networks was proposed.In the model temperature,particle diameter,volume fraction,particle thermal conductivity,base fluid thermal conductivity for visual input layer,through the limited based on the depth of the boltzmann machine belief network model training,can automatically extract nano fluid thermal conductivity own law of development,can activate the strong correlation of various influencing factors of nanofluids step by step.Deep belief network model's simulation results and based on the BP neural network,based on the SVM nano fluid thermal conductivity model for prediction of comparing the simulation results and experimental data,the results show that DBN model overcomes the traditional neural network easy to fall into local optimum,long training time and function fitting degree not higher shortcomings,has high forecast precision,predict the advantages of fast speed,so it is of high significance in engineering application.
Nanofluids are considered to be the most promising enhancement in the future because of their excellent heat transfer performance,and the research on the thermal conductivity of nanofluids is the basis of their application.In order to improve the accuracy of the thermal conductivity prediction of nanofluids,a prediction model for the thermal conductivity of nanofluids based on deep belief networks was proposed.In the model temperature,particle diameter,volume fraction,particle thermal conductivity,base fluid thermal conductivity for visual input layer,through the limited based on the depth of the boltzmann machine belief network model training,can automatically extract nano fluid thermal conductivity own law of development,can activate the strong correlation of various influencing factors of nanofluids step by step.Deep belief network model's simulation results and based on the BP neural network,based on the SVM nano fluid thermal conductivity model for prediction of comparing the simulation results and experimental data,the results show that DBN model overcomes the traditional neural network easy to fall into local optimum,long training time and function fitting degree not higher shortcomings,has high forecast precision,predict the advantages of fast speed,so it is of high significance in engineering application.
引文
[1] S.U.S.Choi.Enhancing thermal conductivity of fluids with nano-particles[J].Asme Fed,1995,231(1):99-105.
[2] S.U.S.Choi,Z.G.Zhang,W.Yu,et al.Anomalous thermal conductivity enhancement in nanotube suspensions[J].Applied Physics Letters,2001,79(14):2252-2254.
[3] B.X.Wang,L.P.Zhou,X.F.Peng.A fractal model for predicting the effective thermal conductivity of liquid with suspension of nanoparticles[J].International Journal of Heat&Mass Transfer,2003,46(14):2665-2672.
[4]孙斌,曲艺.Al-水纳米流体冲击射流流动换热特性研究[J].东北电力大学学报,2017,37(4):67-73.
[5] S.Lee,S.U.S.Choi.Measuring thermal conductivity of fluids containing oxide nanoparticles[J].Transaction of the ASME,1999,121(5):280-289.
[6] J.A.Eastman,S.U.S.Choi,S.Li,et al.Anomalously increased effective thermal conductivities of ethylene glycol-based nanofluids containingcopper nanoparticles[J].Applied Physics Letters,2001,78(6):718-720.
[7] Y.M.Xuan,Q.Li.Heat transfer enhancement of nanofluids[J].Journal of Engineering Thermophysics,2000,21(1):58-64.
[8] S.Lee,S.U.S.Choi.Application of metallic nanoparticle suspensions in advanced cooling systems[J].American Society Mechanical EngineersPressure Vessels and Piping Division,1997,120(6):342-350.
[9] S.Bi,L.Shi,L.Zhang.Application of nanoparticles in domestic refrigerators[J].Applied Thermal Engineering,2008,28(14):1834-1843.
[10] J.C.Maxwell-Garnett.Colours in metal glasses and metal films[J].Philosophical Transactions of the Royal Society A Mathematical Physical&Engineering Sciences,1904,203(1):385-420.
[11] D. A. G. Bruggeman. Berechnung verschiedener physikalischer konstanten von heterogenen substanzen. I. dielektrizittskonstanten undleitfhigkeiten der mischkrper aus isotropen substanzen[J].Annalen Der Physik,1935,421(2):160-178.
[12] R.L.Hamilton,O.K.Crosser.Thermal conductivity of heterogeneous two-component systems[J].Industrial&Engineering Chemistry Funda-mentals,1962,1(3):27-40.
[13] D.J.Jeffrey.Conduction through a random suspension of spheres[J].Proceedings of the Royal Society of London,1973,335(1602):355-367.
[14] M.H.Esfe,S.Saedodin,N.Sina,et al.Designing an artificial neural network to predict thermal conductivity and dynamic viscosity of ferromag-netic nanofluid[J].International Communications in Heat&Mass Transfer,2015,68(11):50-57.
[15] E.Ahmadloo,S.Azizi.Prediction of thermal conductivity of various nanofluids using artificial neural network[J].International Communicationsin Heat&Mass Transfer,2016,74(5):69-75.
[16] M.H.Esfe,M.Afrand,W.M.Yan,et al.Applicability of artificial neural network and nonlinear regression to predict thermal conductivity model-ing of Al2O3-water nanofluids using experimental data[J].International Communications in Heat&Mass Transfer,2015,66(8):246-249.
[17] H.Kurt,M.Kayfeci.Prediction of thermal conductivity of ethylene glycol–water solutions by using artificial neural networks[J].Applied En-ergy,2009,86(10):2244-2248.
[18] X.H.Yang,N.Y.Zhong.Forecasting of hospital outpatient based on deep belief network[J].Computer Science,2016,43(11):26-30.
[19] L.Chen,J.Zhang,N.Wang,et al.Deep belief networks based popularity prediction for online video services[J].Computer Engineering&Ap-plications,2017,53(9):162-189.
[20] M.A.An-Xiang,C. S. Zhang,B. Zhang,et al.Load prediction approach for cloud application based on deep belief networks[J]. Journal ofNortheastern University,2017,38(2):209-213.
[21] Y.Wang,D.I.Kesong,Z.Shan,et al.Melt index prediction of polypropylene based on DBN-ELM[J]. Ciesc Journal,2016,67(12):5163-5168.
[22] G.E.Hinton,R.R.Salakhutdinov.Reducing the dimensionality of data with neural networks[J].Science,2006,313(504):504-512.
[23] L.Deng,D.Yu.Deep learning:methods and applications[J].Foundations&Trends in Signal Processing,2014,7(3):197-387.
[24] A.Fischer,C.Igel.Training restricted boltzmann machines:an introduction[J].Pattern Recognition,2014,47(1):25-39.
[25] R.Sarikaya,G.E.Hinton,A.Deoras.Application of deep belief networks for natural language understanding[J].IEEE/ACM Transactions onAudio Speech&Language Processing,2014,22(4):778-784.
[26] G.E.Hinton.Training products of experts by minimizing contrastive divergence[J].Neural Computation,2002,14(8):1771-1800.
[27] A.Aminian.Predicting the effective thermal conductivity of nanofluids for intensification of heat transfer using artificial neural network[J].Powder Technology,2016,301(11):288-309.
[2] S.U.S.Choi,Z.G.Zhang,W.Yu,et al.Anomalous thermal conductivity enhancement in nanotube suspensions[J].Applied Physics Letters,2001,79(14):2252-2254.
[3] B.X.Wang,L.P.Zhou,X.F.Peng.A fractal model for predicting the effective thermal conductivity of liquid with suspension of nanoparticles[J].International Journal of Heat&Mass Transfer,2003,46(14):2665-2672.
[4]孙斌,曲艺.Al-水纳米流体冲击射流流动换热特性研究[J].东北电力大学学报,2017,37(4):67-73.
[5] S.Lee,S.U.S.Choi.Measuring thermal conductivity of fluids containing oxide nanoparticles[J].Transaction of the ASME,1999,121(5):280-289.
[6] J.A.Eastman,S.U.S.Choi,S.Li,et al.Anomalously increased effective thermal conductivities of ethylene glycol-based nanofluids containingcopper nanoparticles[J].Applied Physics Letters,2001,78(6):718-720.
[7] Y.M.Xuan,Q.Li.Heat transfer enhancement of nanofluids[J].Journal of Engineering Thermophysics,2000,21(1):58-64.
[8] S.Lee,S.U.S.Choi.Application of metallic nanoparticle suspensions in advanced cooling systems[J].American Society Mechanical EngineersPressure Vessels and Piping Division,1997,120(6):342-350.
[9] S.Bi,L.Shi,L.Zhang.Application of nanoparticles in domestic refrigerators[J].Applied Thermal Engineering,2008,28(14):1834-1843.
[10] J.C.Maxwell-Garnett.Colours in metal glasses and metal films[J].Philosophical Transactions of the Royal Society A Mathematical Physical&Engineering Sciences,1904,203(1):385-420.
[11] D. A. G. Bruggeman. Berechnung verschiedener physikalischer konstanten von heterogenen substanzen. I. dielektrizittskonstanten undleitfhigkeiten der mischkrper aus isotropen substanzen[J].Annalen Der Physik,1935,421(2):160-178.
[12] R.L.Hamilton,O.K.Crosser.Thermal conductivity of heterogeneous two-component systems[J].Industrial&Engineering Chemistry Funda-mentals,1962,1(3):27-40.
[13] D.J.Jeffrey.Conduction through a random suspension of spheres[J].Proceedings of the Royal Society of London,1973,335(1602):355-367.
[14] M.H.Esfe,S.Saedodin,N.Sina,et al.Designing an artificial neural network to predict thermal conductivity and dynamic viscosity of ferromag-netic nanofluid[J].International Communications in Heat&Mass Transfer,2015,68(11):50-57.
[15] E.Ahmadloo,S.Azizi.Prediction of thermal conductivity of various nanofluids using artificial neural network[J].International Communicationsin Heat&Mass Transfer,2016,74(5):69-75.
[16] M.H.Esfe,M.Afrand,W.M.Yan,et al.Applicability of artificial neural network and nonlinear regression to predict thermal conductivity model-ing of Al2O3-water nanofluids using experimental data[J].International Communications in Heat&Mass Transfer,2015,66(8):246-249.
[17] H.Kurt,M.Kayfeci.Prediction of thermal conductivity of ethylene glycol–water solutions by using artificial neural networks[J].Applied En-ergy,2009,86(10):2244-2248.
[18] X.H.Yang,N.Y.Zhong.Forecasting of hospital outpatient based on deep belief network[J].Computer Science,2016,43(11):26-30.
[19] L.Chen,J.Zhang,N.Wang,et al.Deep belief networks based popularity prediction for online video services[J].Computer Engineering&Ap-plications,2017,53(9):162-189.
[20] M.A.An-Xiang,C. S. Zhang,B. Zhang,et al.Load prediction approach for cloud application based on deep belief networks[J]. Journal ofNortheastern University,2017,38(2):209-213.
[21] Y.Wang,D.I.Kesong,Z.Shan,et al.Melt index prediction of polypropylene based on DBN-ELM[J]. Ciesc Journal,2016,67(12):5163-5168.
[22] G.E.Hinton,R.R.Salakhutdinov.Reducing the dimensionality of data with neural networks[J].Science,2006,313(504):504-512.
[23] L.Deng,D.Yu.Deep learning:methods and applications[J].Foundations&Trends in Signal Processing,2014,7(3):197-387.
[24] A.Fischer,C.Igel.Training restricted boltzmann machines:an introduction[J].Pattern Recognition,2014,47(1):25-39.
[25] R.Sarikaya,G.E.Hinton,A.Deoras.Application of deep belief networks for natural language understanding[J].IEEE/ACM Transactions onAudio Speech&Language Processing,2014,22(4):778-784.
[26] G.E.Hinton.Training products of experts by minimizing contrastive divergence[J].Neural Computation,2002,14(8):1771-1800.
[27] A.Aminian.Predicting the effective thermal conductivity of nanofluids for intensification of heat transfer using artificial neural network[J].Powder Technology,2016,301(11):288-309.