基于RBF神经网络的水平光管内R407C流动沸腾换热预测  

Prediction of Flow Boiling Heat Transfer of R407C inside Horizontal Smooth Tubes Based on RBF Neural Network

作　　者：文旭林[1,2] 王辉涛[1,2] 王华[1,2] 毕贵红[3] 黄峻伟[1,2] 刘军云[1,2] 陈晓萍[1,2] 

机构地区：[1]昆明理工大学冶金节能减排教育部工程研究中心,云南昆明650093 [2]云南省复杂有色金属资源清洁利用国家重点实验室(培育基地),云南昆明650093 [3]昆明理工大学电力工程学院,云南昆明650500

出　　处：《昆明理工大学学报（自然科学版）》2012年第4期57-62,共6页Journal of Kunming University of Science and Technology(Natural Science)

基　　金：国家自然科学基金-云南联合基金(U0937604);国家自然科学基金(51066002);云南省重大产业技术开发专项项目(2008CD001);云南省科技强省计划项目(2008KA002)

摘　　要：基于RBF神经网络建立了水平光管内混合工质R407C流动沸腾换热的预测模型,以质流密度(G),热通量(q),干度(x),饱和温度(Tsat)和光管内径(D)作为网络输入,流动沸腾换热系数(h)作为网络输出,神经网络模型通过训练学习,对水平光管内R407C的流动沸腾换热系数进行预测,经实验数据验证,预测结果与实验结果吻合较好,网络预测的平均误差为-0.9%,绝对误差为5.5%,均方根误差为10.9%,并且网络预测结果与四个传统关联式的计算结果相比有了明显的改善.由此说明该模型适用于水平光管内R407C的流动沸腾换热预测,对采用R407C制冷系统管式蒸发器的优化设计具有一定的指导意义.A prediction model for flow boiling heat transfer of refrigerant mixture R407C inside horizontal smooth tubes is proposed based on RBF neural network. The main factors strongly affecting flow boiling such as mass flux （G） , heat flux （q）, quality （x）, saturation temperature （Tsat） and tube inner diameter （D） are used as the inputs of the model, and the flow boiling heat transfer coefficient （h） as the output. The prediction results are in good agreement with the experimental results. For the network model of heat transfer, the average deviation is - 0.9%, the absolute average deviation is 5.5% and the root - mean - square deviation is 10.9%. The prediction accuracy of flow boiling heat transfer coefficient is significantly improved compared with four frequently used conventional correlations. The simulation results reveal that the modeling method based on RBF neural net-work is feasible to calculate the flow boiling heat transfer coefficient, and it may provide some guidelines for the optimization design of tube evaporators for R407C.

关 键 词：混合工质 沸腾换热 RBF神经网络 预测模型 误差 

分 类 号：TK124[动力工程及工程热物理—工程热物理]