An effective detection model based on YOLO for pore defects in additive manufacturing

Microscopic imaging serves as a crucial method for assessing the quality of selective laser melting (SLM). Traditional approaches rely on manual inspection, which limits their efficiency and reproducibility. To address the demand for defect detection and analysis, this paper proposes a synergistic method for analyzing pore defects in microscopic images, integrating image segmentation with polynomial fitting. We designed a high-performance image segmentation model. Its capabilities are enhanced through an adaptive curved learning rate adjustment strategy, an attention-based feature extraction module, and a lightweight feature fusion network. Additionally, the model automatically calculates and quantifies the pixel proportion of pore defects within micrographs. Experiments conducted on a constructed SLM pore defect microscopic image dataset demonstrated excellent performance, enabling effective calibration and quantification of defect information. Chebyshev polynomials are employed to fit the nonlinear relationship between key process parameters and porosity. Based on these results, we conducted an in-depth analysis of how different process parameters influence pore defect formation, revealing the intrinsic correlation between process parameters and defects. This study provides an effective automated detection and analysis tool for SLM quality assessment and analysis.