Synergizing ANSYS Simulations and Machine Learning for Transient Thermal Analysis in Aluminium Alloys

Abstract

Time-dependent thermal analysis plays a pivotal role in the manufacturing industry as it greatly influences the overall performance of the final product. This study delves into transient thermal analysis of an aluminum alloy concerning both temperature and time. Employing ANSYS, a finite element-based software, an axisymmetric model is constructed. This model encompasses a mold made of sand and a pattern filled with aluminum alloy. The analysis focuses on temperatures ranging from 650 to 1050°C, examining the temperature changes in the mold and pattern after 1500 seconds, primarily due to the convection process. Parameters like heat flux and directional heat flux are also determined. Subsequently, machine learning models are utilized to interpret the data acquired from ANSYS, enabling the extension of the results to a broader temperature range of 1150 to 1550°C. This study is instrumental in facilitating the effective design of transient thermal analysis for various alloys at different temperatures.