Developing a machine learning model for heat pipes considering different input features

doi:10.1016/j.ijthermalsci.2024.109398

Developing a machine learning model for heat pipes considering different input features

2025-02-01

1

PRE

AI

DOI：10.1016/j.ijthermalsci.2024.109398

Original

Original request for help

Save

Abstract

En 中文

Using heat pipes (HPs) is an effective method for heat dissipation to overcome the challenge about the rising power density of the permanent magnet synchronous motor (PMSM). Using machine learning models to evaluate the performance of HPs has attracted much attention. There are many key input features that can affect the performance of machine learning models, which impacts, whereas, have not been understood, and how to select such features still remains unclear. In this work, the impact of thirteen key input features is investigated by using the Shapely value. Results showed that, when only predicting the effective thermal conductivity (Keff), heat flux (Q), ratio of HP length to diameter (F), ratio of evaporator length to HP length (e), ratio of condenser length to HP length (c), ratio of HP length to cross area (I), effective length of HP (Leff), inclination angle (B), and Nusselt number (Nu) should be considered when using the Artificial Neural Network (ANN) model. Based on such input features, the mean absolute percentage error (MAPE) and coefficient of determination (R2) are 5.68 % and 0.9580, respectively. When predicting critical heat flux (Qcr) and (Keff), the model accuracy is lower, with 6.81 % of MAPE and 0.9377 of R2. The identified key input features can also provide insights on how to improve the HP design and how to renovate the development of physical models.

Keywords:

Motor cooling

Heat pipe

Performance modeling

Machine learning

Developing a machine learning model for heat pipes considering different input features

Abstract

Journal

Organization