CNN architecture-based hybrid fusion model for in-situ monitoring to fabricate metal matrix composite by laser melt injection

Laser melt injection (LMI) provides a new route for fabricating multi-material components with tailored physical performance and distributed functional properties. However, the widespread industrial adoption of metal matrix composite (MMC) fabricated by LMI is still hampered by repeatability and reliability compared to monolithic alloys. This study presents promising results that aim to bridge the knowledge gap by determining a novel method to correlate visual and infrared images with the quality of MMC. A CNN architecture-based hybrid fusion model integrating molten pool and spatter features is proposed based on process understanding for quality monitoring of MMCs fabricated by LMI. The laser energy density and powder feed rate are intentionally tuned to fabricate WC reinforced MMC with four different ceramic particle states. Five models are established based on the single-sensor data, data-level fusion, feature-level fusion, and multi-level hybrid fusion respectively and compared in quality identification performance by four quantitative metrics and two visualization models. The results show that the three multi-sensor fusion models can significantly improve the classification accuracy compared to the single sensor-based model. Compared with data-level fusion and feature-level fusion, the proposed multi-level hybrid fusion model can integrate the advantages of the two fusion models and exhibits the best classification performance by multiple feature extraction channels with complementary and redundant data. The InceptionV3-based hybrid fusion model achieves the highest overall accuracy of 97.44% among the four state-of-the-art CNN architectures.