Work

Thermal performance analysis of a heat exchanger with a novel turbulator insert by using machine learning method

Year: 2025

Type: article

Abstract: A novel turbulence promoter comprising a V-shaped perforated rectangular winglet vortex generator integrated with a circular ring is introduced. The investigation delves into the heat transfer enhancement and pressure loss associated with its insertion within a tube, utilizing the artificial neural network approach, particularly the Multi-Layer Perceptron (MLP), for regression analysis. The outcomes are embodied in the Nusselt number ratio ( ), friction coefficient ratio ( ), and thermal enhancement factor (TEF). The findings underscore that the proposed turbulence promoter adeptly generates mixing vortices in the fluid flow, thereby enhancing heat transfer, with a maximum heat transfer enhancement of 3.9 times, and the optimal TEF value is 1.4. To evaluate the performance of the predictions, various metrics are employed, including the Regression Coefficient (R 2 ), Mean Squared Error, Mean Absolute Error, and Root Mean Squared Error, for each output variable. Furthermore, the MLP model emerges as a highly efficient tool for estimating the , , and TEF of the targeted heat exchanger, where the R 2 value of is 0.9821, is 0.9967, and TEF is 0.9370.

Source: Case Studies in Thermal Engineering

DOI: 10.1016/j.csite.2025.106412

Authors: Jiangbo Wang, Chenzhe Li, Liangcai Zeng, Ting Fu, Kai Liu

Institutions: Wuhan University of Science and Technology, Wuhan Technical University

Language: English

Topic: Heat Transfer Mechanisms

Subfield: Mechanical Engineering

Field: Engineering

Domain: Physical Sciences

SDG: Affordable and clean energy

Open Access status: gold

Estimated APC paid: $1,620