High-Precision Instance Segmentation Detection of Micrometer-Scale Primary Carbonitrides in Nickel-Based Superalloys for Industrial Applications.

In industrial production, the identification and characterization of micron-sized second phases, such as carbonitrides in alloys, hold significant importance for optimizing alloy compositions and processes. However, conventional methods based on threshold segmentation suffer from drawbacks, including low accuracy, inefficiency, and subjectivity. Addressing these limitations, this study introduced a carbonitride instance segmentation model tailored for various nickel-based superalloys. The model enhanced the YOLOv8n network structure by integrating the SPDConv module and the P2 small target detection layer, thereby augmenting feature fusion capability and small target detection performance. Experimental findings demonstrated notable improvements: the mAP50 (Box) value increased from 0.676 to 0.828, and the mAP50 (Mask) value from 0.471 to 0.644 for the enhanced YOLOv8n model. The proposed model for carbonitride detection surpassed traditional threshold segmentation methods, meeting requirements for precise, rapid, and batch-automated detection in industrial settings. Furthermore, to assess the carbonitride distribution homogeneity, a method for quantifying dispersion uniformity was proposed and integrated into a data processing framework for seamless automation from prediction to analysis. [ABSTRACT FROM AUTHOR]