A machine learning model for multi-class classification of quenched and partitioned steel microstructure type by the k-nearest neighbor algorithm

The paper proposed a machine learning model for multiclass classification of quenched and partitioned (Q & P) steel microstructure type. In this work, we implemented the k-nearest neighbor (k-NN) algorithm to train the classifier. A Q & P steel microstructure-type database has been compiled from the previous research data comprising the information of 348 steel samples. The feature space was described by the steel composition, lower critical temperature (Ac1), upper critical temperature (Ac3), martensitic-start temperature (Ms), etc., and the Q & P heat treatment parameters. At the same time, the target or dependent variable was recorded as the microstructure type, for example, martensite-retained austenite {M, RA}, martensite-bainite-retained austenite {M, B, RA} etc. The proposed classifier could achieve an overall performance of 97.7% and 77.7%, measured as f1-Score in the training and testing dataset, respectively. The martensite-retained austenite {M, RA} type was found to be the most confusing class. The model explored the effect of compositional parameters and heat treatment variables on the evolution of microstructure. The re-engineering through model study for targeted martensite-retained austenite microstructure type has depicted a steel composition and heat treatment window, which has been validated by experimental development of steel microstructure. The optical and SEM micrographs, along with hardness, strongly corroborated the model analysis from a re-engineering perspective.