Advances in Sciences and Technology (Apr 2024)

Analyzing the Impact of Population Size in AI-Based Reconstruction of the Thermal Parameter in Heat Conduction Modeling

  • Elzbieta Gawronska,
  • Maria Anna Zych,
  • Robert Dyja,
  • Michal Kowalkowski

DOI
https://doi.org/10.12913/22998624/185298
Journal volume & issue
Vol. 18, no. 2
pp. 349 – 364

Abstract

Read online

The research shows how to use swarming algorithms to rebuild the heat transfer coefficient, especially in regard to the continuous border condition. The authors utilized their application software to do numerical computations, employing classical variants of swarm algorithms. The numerical calculations employed a functional determining error to assess the accuracy of the estimated result. The functional minimization was conducted with the swarm algorithms (especially ABC and ACO). The geometry analyzed in this study consisted of a square shape referred to as the cast, enclosed within another square shape known as the casting mold. These two squares were separated by a layer facilitating heat conduction, characterized by the coefficient κ. The coefficient of the thermally conductive layer was recalibrated utilizing swarm methods within the range of 900 - 1500 [W/m^2K] and subsequently compared to a predetermined reference value. A finite element mesh consisting of 576 nodes was used for the calculations. The study involved simulations with populations of 5, 10, 15, and 20 individuals. Furthermore, each scenario also took into account noise of 0%, 2%, and 5% of the reference values. Results make evident the reconstructed value of the κ coefficient, cooling curves, and temperatures for the ABC and ACO algorithms are physically correct. The consequences indicate a notable level of satisfaction and strong concurrence with the anticipated of the κ parameter values. The results from the numerical simulations demonstrate considerable promise for applying artificial intelligence algorithms in optimizing production processes, analyzing data, and facilitating data-driven decision-making.

Keywords