基于剪接系统的遗传算法RBF网络建模方法

A splicing system based genetic algorithm is proposed to optimize dynamical radial basis function （RBF） neural network, which is used to extract valuable process information from input output data. The novel RBF network training technique includes the network structure into the set of function centers by compromising between the conflicting requirements of reducing prediction error and simultaneously decreasing model complexity. The effectiveness of the proposed method is illustrated through the development of dynamic models as a benchmark discrete example and a continuous stirred tank reactor by comparing with several different RBF network training methods.     

CONDENSING HEAT TRANSFER IN AN ADVANCED TWO-PHASE CLOSED THERMOSYPHON

1 INTRODUCTIONClosed thermosyphon has been developed to enhance heat transfer and recover wasteheat in various process industries [1,2].Stimulated by this success,a new type oftwo-phase closed thermosyphon was designed by inserting respectively two inner tubesinto the thermosyphon,one in the boiling section and the other in the condensing sec-tion.The two-phase flow boiling heat transfer coefficient was calculated successfully onthe basis of Chen's dual-mechanism [3].A boiling heat transfer model for thetwo-phase closed thermosyphon with an inner tube in the boiling section was pro-     

循环流化床的沸腾传热

A model is proposed to predict boiling heat transfer coefficient in a three-phase circulating fluidized bed (CFB), which is a new type of evaporation boiling means for enhancing heat transfer and preventing fouling. To verify the model, experiments are conducted in a stainless steel column with 39 mm ID and 2.0 m height, in which the heat transfer coefficient is measured for different superficial velocities, steam pressures, particle concentrations and materials of particle. As the steam pressure and particle concentrations increase, the heat transfer coefficient in the bed increases. The heat transfer coefficient increases with the liquid velocity but it exhibits a local minimum.The heat transfer coefficient is correlated with cluster renewed model and two-mechanism method. The prediction of the model is in good agreement with experimental data.     

用人工神经网络方法预测鼓泡塔气含率

A new correlation for the prediction of gas hod up in bubble columns was proposed based on an extensive experimental database set up from the literature published over last 30 years .The updated estimation method relying on artificial neural network,dimensional analysis and phenomenological approaches was used and the model prediction agreed with the experimental data with average relative error less than 10%.     

添加剂强化沸腾传热的综合评价及预测

A model of evaluation and prediction of enhancement of boiling heat transfer with additives has been proposed according to fuzzy fundamentals. Correlative appraisement of boiling heat transfer augmentation was done with the model based on 39 additives which were tested by the authors and other researchers. The results show that the evaluation of 35 additives is consistent with experiments, which means that the accuracy of the model is 89.7 percent. In addition, the prediction of the ability of boiling heat transfer enhancement with sodium oleate, polyethylene glycol and Tween-40 is also in good agreement with correspondent experiments.     

三甘醇水溶液池沸腾传热

Boiling of water/triethyleneglycol (TEG) binary solution has a wide-ranging application in the gas processing engineering. Design, operation and optimization of the involved boilers require accurate prediction of boiling heat transfer coefficient between surface and solution. In this investigation, nucleate pool boiling heat transfer coef-ficient has been experimentally measured on a horizontal rod heater in water/TEG binary solutions in a wide range of concentrations and heat fluxes under ambient condition. The present experimental data are correlated using major existing correlations. In addition a correlation is presented for prediction of pool boiling heat transfer for the system in which the vapour pressure of one component is negligible. This model is based on the mass transfer rate equation for prediction of the concentration at the bubble vapor/liquid interface. Based on this prediction, the temperature of the interface and accordingly, the boiling heat transfer coefficient could be straightforwardly calculated from the known concentration at the interface. It is shown that this simple model has sufficient accuracy and is acceptable below the medium concentrations of TEG when the vapor equilibrium concentration of TEG is almost zero. The presented model excludes any tuning parameter and requires very few physical properties to apply.     

CONVECTIVE HEAT TRANSFER CHARACTERISTICS OF GAS IMPINGEMENT ON SMALL HEATED DEVICE IN LIQUID COOLANT BATH

Heat transfer characteristics of a small heated device have been investigated in a liquid bath with gas jetimpingement as function of gas flow rate,coolant temperature,liquid phsicochemical properties,heat flux,heat source size,ambient pressure and the distance between jet and heated wall.The experimental results show that the agitation of liquid caused by gas jet bubbles increases greatly therate of heat transfer,and the evaporation of coolant near the wall,which was due to the concentration differencebetween gas-liquid interface and bulk gas phase,gives additional enhancement of heat transfer.The rate ofevaporation related to the bubble growth was mathematically formulated.By using the simultaneous heat and mass transfer model,the convective heat transfer coefficient and masstransfer coefficient can be deduced from the experimental results.In addition,the local heat transfer coefficient and the distribution of evaporation heat flux on the smallheated surface are investigated mathematically and experimentally.     

A MODEL FOR BED-TO-SURFACE HEAT TRANSFER IN CIRCULATING FLUIDIZED BEDS

Experiments on bed-to-surface heat transfer in the axial and radial directions were carried out in a cold flowmodel of the circulating fluidized bed of 244mm i.d.and with FCC catalysts(d_p=83.4μm)as the fluidized particles.A simplified gas-solid flow model comprising of the cluster-particulate phases upflowing cocurrentlywas proposed.By taking into account the alternative contacts of cluster and particulate phases with the immersedsurface,a composite heat transfer model was developed.The model gave good predictions as compared withthe experimental results of this work and those of others.     

Experimental and CFD Heat Transfer Studies of Al2Oa-Water Nanofluid in a Coiled Agitated Vessel Equipped with Propeller

This paper presents the heat transfer characteristics of A1203-water nanofluid in a coiled agitated vessel with propeller agitator. The experimental study was conducted using 0.10%, 0.20% and 0.30% volume concentra tion of A1203-water nanofluids. The results showed considerable enhancement of convective heat transfer using the nanofluids. The empirical correlations developed for Nusselt number in terms of Reynolds number, Prandtl number, viscosity ratio and volume concentration fit with the experimental data within ±10%. The heat transfer characteris tics were also simulated using computational fluid dynamics using FLUENT software with the standard ke model and multiple reference frame were adopted. The computational fluid dynamics （CFD） predicted Nusselt number agrees well with the experimental value and the discrepancy is found to be less than ＋8%.     

APPLICATION OF “VAPOR-PHASE RESISTANCE METHOD” TO THE STUDY ON CONDENSATION IN HORIZONTAL TUBES

A physical model and a mathematical model were established in order to describe and improve the“vapor-phase resistance method” of Bell and Ghaly.Considering the effect of ripples at the interface onvapor-phase resistance,a correction factor v_ι was proposed.Another factor (θ/π)β which correctsthe influence of the liquid pool along the bottom of the horizontal tube on the liquid-phase heat transfercoefficient was derived and the relationship of θ and β was correlated.The heat transfer coefficient pre-dicted by Bell's method are approximately 10—15% lower than the experimental values if the effect ofripples on vapor-phase resistance has not been taken into account.The comparison of the predicted valuesof h_c from the modified vapor-phase resistance method with the experimental data showed a deviation of±10%.     

基于粗糙集和RBF神经网络的风电场短期风速预测模型

结合粗糙集提出了一种RBF神经网络短期风速预测模型。采用粗糙集对预测模型的输入特征空间进行约简,找出对未来预测的风速具有主要影响的因素,以此作为RBF神经网络预测模型的输入变量;在RBF神经网络训练的过程中,采用在线滚动优化策略,将最新的样本加入训练集,从而使预测模型能够跟踪风速的最新变化。将提出的方法用于某风电场的1 h短期风速预测,仿真实验结果表明该方法具有结构简单、预测精度高的优点。     

新型重力热管的研究

提出了一种具有内插物的新型重力热管,该热管避免了流体的逆流流动.实验观察和传热性能的实验研究表明,其操作稳定,传热性能良好,具有较高的临界热通量.在分析以乙醇、水为介质的实验数据基础上,给出了该热管的设计计算方法及改进的环隙并流冷凝传热模型.     

两相热虹吸循环蒸发侧传热模型比较

两相热虹吸换热器在工业领域应用广泛,其制冷剂内侧的传热过程是热虹吸管设计的基础。然而由于沸腾传热和两相流动的复杂性,基于实验的经验传热模型各自差异很大且适用范围有限,给热虹吸管建模时传热模型选取带来了一定的困难。建立了稳态两相热虹吸循环分布式参数模型,利用5篇文献中4种工质共424个热虹吸管传热实验数据点,对热虹吸管中常用的7种传热模型进行比较评价,为模型选取提供参考。结果发现:Kandlikar流动沸腾模型和Rahmatollah拟合的热虹吸管传热模型模拟精度最好,推荐使用;Cooper池沸腾也有较好的精度,说明核态沸腾在热虹吸管传热中占主导地位; Gungor and Winterton、Liu and Winterton等常用的流动沸腾模型模拟精度差别不大,误差尚可接受;Imura池沸腾模型不适用于热虹吸管传热模拟。     

Melt index prediction by RBF neural network with an ICO‐VSA hybrid optimization algorithm

Melt index (MI) is considered as one of the most significant parameter to determine the quality and the grade of the practical polypropylene polymerization products. A novel ICO‐VSA‐RNN (RBF neural network with ICO‐VSA algorithm) MI prediction model is proposed based on radial basis function (RBF) neural network and improved chaos optimization (ICO), and variable‐scale analysis (VSA), where the ICO is first added and then combined with the VSA to overcome the defects of ICO and VSA, then the parameters of the RBF neural network are optimized with them. At last, the RBF neural network model for MI prediction model is developed. Further researches on the optimal RBF neural network model of MI prediction are carried out with the data from a real industrial plant, and the prediction results show that the performance of this prediction model is much better than the RBF neural network model without optimization. © 2012 Wiley Periodicals, Inc. J Appl Polym Sci, 2012     

基于滴膜共存理论热虹吸管冷凝段传热模型

引入滴膜共存冷凝传热理论分析管内存在滴状冷凝的热虹吸管冷凝段传热,将热虹吸管冷凝段传热表示为滴状区和膜状区传热之和建立传热模型。滴状区,以Rose冷凝传热模型计算单个液滴的传热,基于随机分形理论建立了液滴的空间和尺度分布函数,进而求解整个滴状区的热通量。膜状区,根据Nusselt竖壁层流膜状凝结理论进行热通量的计算。通过沟流级别计算滴状区和膜状区的面积比率,从而建立滴膜共存冷凝传热模型。传热模型计算结果与实验结果较为吻合,能够反应热管冷凝段传热本质。     

基于BP神经网络方法的热管中冷器热工性能分析

基于BP神经网络建立了热管中冷器的传热性能和阻力性能预测模型,采用基于Levenberg Marquardt的trainlm训练算法,对热管中冷器的传热性能和阻力性能进行了预测,经试验数据的验证,预测值与试验值吻合较好,传热性能网络预测最大相对误差为8.0%,平均相对误差为3.5%,阻力性能网络预测最大相对误差为13....     

A new algorithm for developing dynamic radial basis function neural network models based on genetic algorithms

A new method for extracting valuable process information from input–output data is presented in this paper. The proposed methodology produces dynamical radial basis function (RBF) neural network models based on a specially designed genetic algorithm (GA), which is used to auto-configure the structure of the networks and obtain the model parameters. The new RBF network training technique formulates a complete optimization problem, which includes the network structure into the set of free variables that are used to minimize the prediction error. This is a different approach compared with the local search methods employed by other structure selection mechanisms, which are often trapped to local minima. Another advantage of the proposed method is that only one run of the algorithm is required to obtain the optimal network structure, in contrast to the standard RBF training techniques, where the produced model is selected by trial and error. The effectiveness of the method is illustrated through the development of dynamical models for two sets of data: simulated data from a Continuous Stirred Tank Reactor (CSTR) and true data collected from a Kamyr digester, which is a rather complicated reactor used in the pulp and paper industry.     

碳纳米管悬浮液强化小型重力型热管换热特性

对水基多壁碳纳米管悬浮液强化小型重力型热管换热特性进行了实验研究。碳纳米管悬浮液质量分数为0. 1%～3%，热管运行压力为7. 45、12. 38和19. 97 kPa。实验结果发现，用质量分数为2. 0%的碳纳米管悬浮液替代去离子水后，热管蒸发段换热性能大幅度提高，临界热通量最大提高了120%。热管运行压力对蒸发段沸腾传热系数有明显影响，压力越小，碳纳米管悬浮液对沸腾换热特性的强化作用越显著。壁面热通量对蒸发段沸腾换热特性也有明显影响，低热通量时碳纳米管悬浮液的强化换热作用不明显，到高热通量时，其强化换热作用显著。     

基于径向基函数网络的MH/Ni电池建模及容量预测

引　言近年来 ,随着汽车的迅速发展和大量普及 ,它所造成的尾气污染问题也日益突出 .电动车的发展可以有效地解决燃油汽车的污染排放问题 .MH/Ni电池是一种无污染的“绿色能源” ,它具有高比能量、高比功率、长寿命及安全性好等特点 ,是电动车用动力型电池的首选 .在动力型电池     

潜油电泵智能节电装置的研制

在进入高含水期的油田开发中,潜油电泵得到广泛应用,而如何提高其采油系统效率,降低电泵采油井耗电量,成为油田节能减排工作的重点。本文设计了一种新型智能潜油电泵有载调压变压器,给出了结构组成及工作流程,进行了室内外的现场实验,结果表明,该装置可以有效地选择最佳电压,节电效果显著。