Enhanced Defect Detection in Additive Manufacturing Through In-Situ Vibration and Acoustic Data Fusion

Abstract

Additive manufacturing (AM) is transforming modern production methods by enabling the fabrication of complex structures with high precision and customization. However, the layer-by-layer construction inherent in AM introduces unique challenges, particularly the risk of internal defects that compromise structural integrity. Conventional post-processing inspection techniques are often inadequate for real-time defect detection, necessitating the development of effective in-situ monitoring solutions. This paper proposes an innovative approach combining vibration and acoustic emission data collected during fabrication to detect defects in real-time. Using advanced signal processing and data fusion techniques, we analyze how the synergy between these two modalities can enhance the sensitivity and accuracy of defect detection. The proposed method is validated through experimental trials on metal additive manufacturing systems, demonstrating superior performance over single-sensor monitoring strategies. The findings highlight the significant potential of multi-modal sensor fusion for ensuring the reliability and safety of additively manufactured components.