Research On The Quantitative Metallographic Analysis Of GCR15 Microstructure Using Mask R-CNN

Quantitative metallographic analysis plays an important role in predicting the mechanical and physical properties of materials.This research presents a way to identify the carbide particles present within the GCr15 bearing steel,SEM image.One very important property of metallographic quantitative analysis is its ability to provide us with first-hand data which is very significant in establishing a reasonable mathematical model.By knowing and understanding the microstructure,we can predict the material’s behaviour,control the properties of the material produced and compare it to other materials having similar or different microstructures.GCr15 is a type of bearing steel which is classified as a quality alloy;high carbon,chromium and manganese.It is used in the manufacturing of rolling bearings as well as rolling rings.For this reason,the microstructure analysis and performance of bearing steel are crucial in helping us understand the functioning of bearings and their associated equipment.To further comprehend the microstructure of this metal,this research did not only detect the carbide particles(blobs)within the microstructure of this steel alloy but also quantified them.The metallographic images of GCr15 were obtained by a JSM-6700 scanning electron microscope and this made it easier to work on.The quantitation of the proportion of carbide particles present in the GCr15 bearing steel microstructure was done using the method of Mask Region-Based Convolution Neural Networks(Mask R-CNN).The approach was able to locate the carbide particles,using bounding box indicators based on the concept,Region of Interest(ROI),as used in Mask R-CNN,after that,I proceeded to mask the carbide particles within the ROIs.It resulted in accurately locating and masking over 90% of our target particles and calculated the area and perimeter of the blobs present within the microstructure of the GCr15 using NumPy.