Triboinformatics Modeling of Dry Sliding Wear of High Manganese Hadfield Steel alloys

Abstract

The present research article describes a study on the wear resistance of high manganese Hadfield steel produced through a clean metallurgical process during dry sliding wear conditions; solidified ingots are subjected to heat treatments, such as annealing, ice water quenching, and age hardening for 2 h at 550 °C, 600 °C, 650 °C, and 700 °C. Samples are prepared as per the standards for mechanical and tribological tests. The peak hardness of 292.87 HV is observed for alloy 4 aged at 600 °C. The ultimate tensile strength of 434.18 MPa is observed for alloy 3 aged at 600 °C. The minimum specific wear rate of 1.5649E-05 mm3/N-m is witnessed for the as-cast sample of alloy 4 at 50 N load and 1.885 m/s speed. Wear tracks are analyzed through SEM, and microstructures are retrieved from OM, SEM, and TEM. The XRD patterns revealed the developed steel is austenitic in nature. Furthermore, to validate the wear rate, a total of 8 machine learning models/ensembles are developed and trained as it is obvious to associate tribological and material features with ML models. With an efficiency of 94%, Decision Tree Regressor outperformed all other constructed models using R2 values as the performance assessment criterion.