Predictive modeling of electrical conductivity and hardness in copper-based alloys for futuristic applications using machine learning

What is it about?

This paper explores the performance of machine learning models in predicting electrical conductivity and hardness of copper-based alloys. These properties are important in aerospace, automotive, defense, and electronics industry. Instead of relying only on time-consuming and costly experiments, this research shows that models trained using a dataset of 1,481 copper alloy samples with measured properties give good results. The different algorithms were tested and it was found that random forest regression was best at predicting hardness, while XGBoost regression performed best for electrical conductivity. The results show that tree-based models are particularly effective for this type of material prediction. By providing accurate forecasts of alloy properties, the study demonstrates how machine learning can speed up the design and optimization of new copper-based alloys for advanced applications such as energy systems, biomedical devices, high-temperature components, and space technology.

Featured Image

Why is it important?

This study is important because it shows how machine learning models can save time and cost in developing new copper-based alloys by predicting their key properties without needing physical experiments. Since copper alloys are essential in many advanced technologies such as in designing aerospace engines and automotive parts to electronics, biomedical devices, and space applications, being able to design alloys with the right combination of hardness and electrical conductivity quickly is a huge asset. The predictive models act as useful tools which help researchers focus on the most promising alloy compositions, accelerating innovation and making it easier to create materials tailored for futuristic applications.