扭带式换热器水热关联的机器学习辅助建模  

Machine learning assisted modeling of thermohydraulic correlations for heat exchangers with twisted tape inserts

作　　者：Jyoti Prakash Panda Bipin Kumar Anil Kumar Patil Manoj Kumar Ravi Kumar 

机构地区：[1]Department of Mechanical Engineering,DIT University,Dehradun,Uttarakhand,India

出　　处：《Acta Mechanica Sinica》2023年第1期148-157,共10页力学学报（英文版）

摘　　要：本文介绍了机器学习(ML)算法在带扭带插件的换热器传热关联(如努塞尔数和摩擦系数)建模中的应用.采用换热器在不同雷诺数(Re)、扭转比(t)、穿孔率(p)和不同扭带数(n)下的实验数据进行相关建模.在数据驱动的代理建模中使用了三种机器学习算法:多项式回归(PR)、随机森林(RF)和人工神经网络(ANN).为了保证模型的通用性,对ML模型的超参数进行了优化,分析了不同ML算法的性能参数(如R 2和MAE).结果表明,在不同的测试数据集上,人工神经网络对传热系数的预测优于PR和RF的预测.基于本文分析内容,对未来数据驱动的传热关联建模工作和类似研究提出了建议.This article presents the application of machine learning(ML)algorithms in modeling the heat transfer correlations(e.g.,Nusselt number and friction factor)for a heat exchanger with twisted tape inserts.The experimental data for the heat exchanger at different Reynolds numbers(Re),twist ratio(t),percentage of perforation(p),and a varied number of twisted tapes(n)were used for the correlation modeling.Three ML algorithms:polynomial regression(PR),random forest(RF),and artificial neural network(ANN)were used in the data-driven surrogate modeling.The hyperparameters of the ML models were carefully optimized to ensure generalizability.The performance parameters(e.g.,R 2 and mean absolute error(MAE))of different ML algorithms were analyzed.It was observed that the ANN predictions of heat transfer coefficients outperform the predictions of PR and RF across different test datasets.Based on our analysis we make recommendations for future data-driven modeling efforts of heat transfer correlations and similar studies.

关 键 词：机器学习 数据驱动 测试数据集 辅助建模 多项式回归 超参数 穿孔率 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]