Abstract
This study proposes a novel modelling approach that integrates mutual information (MI)-based parameter screening with random forest (RF) modelling to achieve an accurate quantitative prediction of surface hardness and impact energy in two martensitic stainless steels (1Cr13 and 2Cr13). Preliminary analyses indicated that the magnetic parameters derived from Barkhausen noise (MBN), and the incremental permeability (IP) measurements showed limited linear correlations with the target properties (surface hardness and impact energy). To address this challenge, an MI feature screening method has been developed to identify both the linear and non-linear parameter dependencies that are critical for predicting target mechanical properties. The selected features were then fed into an RF model, which outperformed traditional multiple linear regression in handling the complex, non-monotonic relationships between magnetic signatures and mechanical performance. A key advantage of the proposed MI-RF framework lies in its robustness to small sample sizes, where it achieved high prediction accuracy (e.g., R(2) > 0.97 for hardness, and R(2) > 0.86 for impact energy) using limited experimental data. By leveraging MI's ability to capture multivariate dependencies and RF's ensemble learning power, it effectively mitigates overfitting and improves generalisation. In addition to demonstrating a promising tool for the non-destructive evaluation of martensitic steels, this study also provides a transferable paradigm for the quantitative assessment of other mechanical properties by magnetic feature fusion.