research on ai-driven modeling and real-time control for enhancing additive manufacturing process quality

This research addresses the significant challenge of high defect rates in additivemanufacturing (am) processes, which primarily stem from unstable material deposition,concentrated thermal stress, and inadequate interlayer bonding. the study aims to enhance the geometric accuracy, mechanical properties, and overall quality of fabricated components.to achieve this, a high-resolution visual sensing system is integrated to capture key process data, such as melt pool dynamics and thermal distribution, in real-time. advanced image processing algorithms, including feature extraction and state recognition techniques, are employed to analyze this data. furthermore, an intelligent control strategy, potentially leveraging machine learning or adaptive models, is implemented to dynamically adjust critical process parameters like laser power and scanning speed. this approach establishes a fully integrated 'perception-decision-control' closed-loop system. experimental results demonstrate that the proposed system significantly improves manufacturing quality, enabling micron-level error control and high repeatability. it also proves highly effective in suppressing typical defects, including warping and cracks, thereby advancing the reliabilityof am for precision applications.