Data-Driven ANN-Based Predictive Modeling of Mechanical Properties of 5Cr-0.5Mo Steel: Impact of Composition and Service Temperature

• DOI: 10.3390/cryst15030213
• Publication Date: 2025-02-24T11:47:17Z
• Authors: Muhammad Ishtiaq; Saurabh Tiwari; Molakatala Nagamani; Sung-Gyu Kang; Nagireddy Gari Su...
• Keywords: Predictive modelling

The mechanical properties of steel are intricately connected to their composition and service temperature. Predicting these across different work temperatures using traditional statistical methods, algorithms, equations is highly challenging due complex interdependencies. To address this, we developed an artificial-neural-network (ANN) model elucidate the relationships between composition, temperature, 5Cr-0.5Mo steels. Our demonstrated high accuracy, with minimal percentage errors in predicting YS, UTS, El (%)—3.5%, 0.97%, 1.9%, respectively. ANN predictions realistic closely match experimental results. We propose easy-to-use model’s GUI predict achieve desired at any findings offer valuable insights for researchers designers, aiding developing components optimized properties. This technique expected significantly enhance planning practical experiments improve material performance overall.