Browsing by Author "Krastev B."

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Deep Learning-Driven Insights into Hardness and Electrical Conductivity of Low-Alloyed Copper Alloys
    (2025-12-01) Kolev M.; Javorova J.; Simeonova T.; Hadjitodorov Y.; Krastev B.
    Understanding the intricate relationship between composition, processing conditions, and material properties is essential for optimizing Cu-based alloys. Machine learning offers a powerful tool for decoding these complex interactions, enabling more efficient alloy design. This work introduces a comprehensive machine learning framework aimed at accurately predicting key properties such as hardness and electrical conductivity of low-alloyed Cu-based alloys. By integrating various input parameters, including chemical composition and thermo-mechanical processing parameters, the study develops and validates multiple machine learning models, including Multi-Layer Perceptron with Production-Aware Deep Architecture (MLP-PADA), Deep Feedforward Network with Multi-Regularization Framework (DFF-MRF), Feedforward Network with Self-Adaptive Optimization (FFN-SAO), and Feedforward Network with Materials Mapping (FFN-TMM). On a held-out test set, DFF-MRF achieved the best generalization (R2_test = 0.9066; RMSE_test = 5.3644), followed by MLP-PADA (R2_test = 0.8953; RMSE_test = 5.7080) and FFN-TMM (R2_test = 0.8914; RMSE_test = 5.8126), with FFN-SAO slightly lower (R2_test = 0.8709). Additionally, a computational performance analysis was conducted to evaluate inference time, memory usage, energy consumption, and batch scalability across all models. Feature importance analysis was conducted, revealing that aging temperature, Cr, and aging duration were the most influential factors for hardness. In contrast, aging duration, aging temperature, solution treatment temperature, and Cu played key roles in electrical conductivity. The results demonstrate the effectiveness of these advanced machine learning models in predicting critical material properties, offering insightful advancements for materials science research. This study introduces the first controlled, statistically validated, multi-model benchmark that integrates composition and thermo-mechanical processing with deployment-grade profiling for property prediction of low-alloyed Cu alloys.
  • No Thumbnail Available
    Item
    INVESTIGATION OF THE POSSIBILITY OF DETERMINING THE THERMAL CONDUCTIVITY COEFFICIENT OF A356 FOAM BY MATHEMATICAL MODELING AND IDENTIFICATION PROCEDURE
    (2022-01-01) Georgiev G.E.; Velikov A.; Krastev B.; Popov S.; Stanev S.; Yordanova R.; Manolov V.
    A method for determining the thermal conductivity coefficient of a foam material of A356 aluminum alloy has been proposed. The foam material has been produced by decomposition of titanium hydride introduced into the melt and subsequent cooling and crystallization. During the process, the measurement of temperature dependences on time has been performed at two selected points of the foam casting. The problem of heat transfer and crystallization of the casting and mold is solved by means of mathematical model proposed. The experimental data and the corresponding solutions of the mathematical model have been used for the realization of an identification procedure for determining the coefficient of thermal conductivity of the foam material and the coefficient of heat transfer at the casting-mold boundary. Through the represented methodology new data for important thermophysical characteristic are obtained.