Decision support system based on a hybrid genetic algorithm–Kohonen map for combined mode conduction–radiation heat transfer in a porous medium: A comparative assessment of three variations of the Kohonen map

A hybrid genetic algorithm (GA)–Kohonen map, with its three variants, is explored for the first time for the decision-making system in a porous ceramic matrix (PCM)-based burner through determination of the regime of operation. Four different attributes of PCMs such as convective coupling (P₂), extinction coefficient (β), downstream porosity (ϕ₂), and scattering albedo (ω) are selected for determining the regime of operation of a PCM-based burner. Changes in any of these attributes of a PCM lead to significant changes in the temperature profiles of the gas and solid phases. Temperature profiles of the gas and solid phases are computed by developing a numerical model. Various samples corresponding to different regimes are generated and used in a hybrid GA–Kohonen map. The best architectural details such as the neuron number and training epochs are obtained from GA as output. The best Kohonen map is trained with the input data, and regimes of operation for new temperature profiles are predicted. A supervised Kohonen map is able to provide the highest average class prediction of more than 40%. All the variants are assessed under two different types of neuron grids: hexagonal and rectangular. Comparative assessments of the three different variants of Kohonen maps, in terms of CPU time and average class prediction, are carried out.     

有限体积法在电站锅炉炉膛辐射换热计算中的应用

辐射换热是大型锅炉炉膛内的主要换热形式,准确的计算炉膛内的辐射换热量对大型锅炉设计和优化有重要意义。本文将有限体积法推广用于求解和分析大型电站锅炉炉膛内的辐射换热。给出了有限体积法对辐射传递方程进行离散和求解的基本过程。评估了有限体积法求解大型电站锅炉炉膛辐射换热的可靠性。将有限体积法用于分析某电厂600MW锅炉炉膛内的辐射换热,结果表明有限体积法可以有效的求解大型电站锅炉炉膛内的复杂辐射换热过程。     

炉内辐射换热过程的有限体积法

简要分析了含吸收散射性介质的三维空腔内辐射传递方程的有限体积法求解过程,应用该方法对四角切圆炉膛内的辐射换热过程进行模拟计算,得出了炉膛内温度分布,并将计算结果与实测值进行了比较。通过数值计算表明：有限体积法计算速度快,对不规则边界适应性强,具有很高的工程可用性。     

Modeling of convection heat transfer of supercritical carbon dioxide in a vertical tube at low Reynolds numbers using artificial neural network

Today, many researches have been directed on heat transfer of supercritical fluids; however, since the analysis of heat transfer in these fluids founded by a mathematical model based on the effective parameters is complicated, so in this paper, a group method of data handling (GMDH) type artificial neural network are used for calculating local heat transfer coefficient h_x of supercritical carbon dioxide in a vertical tube with 2 mm diameter at low Reynolds numbers (Re < 2500) by empirical results obtained by Jiang et al. [1].At first, we considered h_x as target parameter and G, Re, Bo^?, x⁺ and q_w as input parameters. Then, we divided empirical data into train and test sections in order to accomplish modeling. We instructed GMDH type neural network by 80% of the empirical data. 20% of primary data which had been considered for testing the appropriateness of the modeling were entered into the GMDH network. Results were compared by two statistical criterions (R² and RMSE) with empirical ones. The results obtained by using GMDH type neural network are in excellent agreement with the experimental results.     

Discussion on the Network Method for Calculating Radiant Interchange Within an Enclosure

ＤｉｓｃｕｓｓｉｏｎｏｎｔｈｅＮｅｔｗｏｒｋＭｅｔｈｏｄｆｏｒＣａｌｃｕｌａｔｉｎｇＲａｄｉａｎｔＩｎｔｅｒｃｈａｎｇｅＷｉｔｈｉｎａｎＥｎｃｌｏｓｕｒｅ￥Ｈ．Ｊ．Ｋａｎｇ；Ｗ．Ｑ．Ｔａｏ（ＳｃｈｏｏｌｏｆＥｎｅｒｇｙａｎｄＰｏｗｅｒＥｎｇｉｎｅｅｒ...     

Simultaneous Estimation of Properties in a Combined Mode Conduction–Radiation Heat Transfer in a Porous Medium

Simultaneous estimation of thermophysical and optical properties such as the thermal conductivity, the scattering albedo, and the emissivity of a 1‐D planar porous matrix involving combined mode conduction and radiation heat transfer with heat generation is reported. Coupled energy equations for the gas and solid phase account for the nonlocal thermal equilibrium between the two phases. Performances of the genetic algorithm (GA) and the global search algorithm (GSA) in simultaneous estimation of three properties are analyzed. Both the GA and the GSA utilize a priori knowledge of the axial gas temperature distribution, and the magnitudes of the convective and the radiative heat fluxes at the outer surface of the porous matrix. With volumetric radiative information needed in the solid‐phase energy equation computed using the discrete transfer method, the two energy equations are simultaneously solved using the finite volume method. GSA provides better estimation, and computationally, it is much faster than the GA.     

Development of a finite element radiation model applied to two‐dimensional participating media

A finite element method (FEM) for radiative heat transfer has been developed and it is applied to 2D problems with unstructured meshes. The present work provides a solution for temperature distribution in a rectangular enclosure with black or gray walls containing an absorbing, emitting, isotropically scattering medium. Compared with the results available from Monte Carlo simulation and finite volume method (FVM), the present FEM can predict the radiative heat transfer accurately. © 2005 Wiley Periodicals, Inc. Heat Trans Asian Res, 34(6): 386–395, 2005; Published online in Wiley InterScience ( www.interscience.wiley.com ). DOI 10.1002/htj.20076     

A novel application of artificial neural network for wind speed estimation

Providing accurate multi-steps wind speed estimation models has increasing significance, because of the important technical and economic impacts of wind speed on power grid security and environment benefits. In this study, the combined strategies for wind speed forecasting are proposed based on an intelligent data processing system using artificial neural network (ANN). Generalized regression neural network and Elman neural network are employed to form two hybrid models. The approach employs one of ANN to model the samples achieving data denoising and assimilation and apply the other to predict wind speed using the pre-processed samples. The proposed method is demonstrated in terms of the predicting improvements of the hybrid models compared with single ANN and the typical forecasting method. To give sufficient cases for the study, four observation sites with monthly average wind speed of four given years in Western China were used to test the models. Multiple evaluation methods demonstrated that the proposed method provides a promising alternative technique in monthly average wind speed estimation.     

Compact modeling approach using genetic algorithms for accurate thermal simulation

In this paper, we propose a technique that uses thermal measurement results for improved accuracy in thermal simulation of electronic apparatus. Because the modeling of the electronic components in such apparatus has hitherto been very poor, the thermal simulation results cannot achieve the required accuracy. To solve this problem, we first represent a component as a set of cubic blocks with equivalent thermal conductivity and contact thermal resistance values, and then identify these values by using the thermal measurement results for the component. We regard the identification of parameters as an optimization problem that involves minimizing the difference between the predicted and measured results. To solve the problem, we combine genetic algorithms and a thermal simulation tool. Our technique was successfully applied to the construction of an accurate thermal model, which we validated by using thermal measurement results. © 2000 Scripta Technica, Heat Trans Asian Res, 30(1): 28–39, 2001     

Transient coupled heat transfer in multilayer composite with one specular boundary coated

By the ray tracing?node method, the transient coupled radiative and conductive heat transfer in absorbing, scattering multilayer composite is investigated with one surface of the composite being opaque and specular, and the others being semitransparent and specular. The effect of Fresnel’s reflective law and Snell’s refractive law on coupled heat transfer are analyzed. By using ray tracing method in combination with Hottel and Sarofim’s zonal method and spectral band model, the radiative intensity transfer model have been put forward. The difficulty for integration to solve radiative transfer coefficients (RTCs) is overcame by arranging critical angles according to their magnitudes. The RTCs are used to calculated radiative heat source term, and the transient energy equation is discretized by control volume method. The study shows that, for intensive scattering medium, if the refractive indexes are arranged decreasingly from the inner part of the composite to both side directions respectively, then, the total reflection phenomenon in the composite is advantageous for the scattered energy to be absorbed by the layer with the biggest refractive index, so at transient beginning a maximum temperature peak may appear in the layer with the biggest refractive index.     

用于制冷机组性能分析的神经网络模型

本文建立了制冷机组性能神经网络模型，并用测试数据进行了训练。结果表明，人工神经网络方法是分析制冷机组性能的一种有效途径。     

基于人工蜂群算法的大体积混凝土温度场参数反演

针对传统混凝土热学参数反分析计算量大、计算效率不高等特点,将人工蜂群算法引入到混凝土温度场计算中,提出基于该算法的反分析法,通过室内二期通水冷却试验,对通水冷却过程中大体积混凝土试件的导温系数及表面散热系数进行反演分析,并利用反演参数结果进行温度场反馈分析。结果表明,人工蜂群算法在温度场参数反演中具有很好的适用性,有效地提高了温度场参数反演的效率。     

一种二维Stefan反问题的数值求解算法

针对因相变引起边界位置移动的二维Stefan反问题,提出了基于有限体积法(FVM)结合Powell法的求解算法。首先假设待定边界位置的初始猜测值,采用Stefan正问题的无量纲化焓法模型,通过FVM对Stefan正问题进行计算,得到各测温点处对应的温度估计值,计算测量值和估计值的方差,然后采用Powell算法,通过方向置换准则判断搜索正确边界问题的方向向量。通过数值仿真实验对提出的算法进行了验证,讨论了测量误差、测点位置、初值、测量时刻数目以及测点数量对反演精度的影响,并与共轭梯度法(CGM)的反演结果进行了对比。数值实验结果表明,该算法能够精确地识别各种不规则的边界形状,并且对误差和初值等影响因素不敏感,具有良好的稳定性。