Prediction of Hardness of Cast Iron Using Intelligent Tools

The objective of this research paper is to introduce a machine learning and artificial intelligence-based approach for predicting the hardness of cast iron. The hardness of cast iron is a significant factor in determining its strength and performance for different applications. The hardness is primarily tested using experimental methods and is majorly done using testing materials. It is observed that the Brinell Hardness testing method can be time-consuming. In this paper, the authors have made an attempt to use an Artificial Intelligence and Machine Learning (AI/ML) approach that can provide an efficient and accurate analysis of Brinell hardness test data, allowing for improved measurement and prediction of material hardness values. By processing large amounts of data and identifying complex patterns, AI/ML algorithms can enhance the accuracy and reliability of Brinell Hardness measurements, making them valuable tools for materials science research. The model is trained using diverse data sources, including experimental data, published results, and foundry data. Subsequently, the trained model is employed to accurately predict the Brinell Hardness Number (BHN) of cast iron. The model's predictions are verified against experimental methods to validate the accuracy of the proposed approach. This method offers an effective and efficient means of predicting the BHN of cast iron by optimizing its process parameters, making it useful for a variety of applications.