MULTI-SENSOR FUSION FOR REAL-TIME DEFECT DETECTION IN ADDITIVE MANUFACTURING PROCESSES

Abstract

Additive Manufacturing (AM) has transformed modern manufacturing by enabling the fabrication of highly complex, lightweight, and customized components for aerospace, biomedical, automotive, and industrial applications. However, manufacturing defects such as porosity, lack of fusion, cracking, residual stress, thermal distortion, and surface irregularities continue to affect product quality and process reliability. Conventional defect detection techniques generally rely on singlesensor monitoring or post-process inspection, limiting their capability to detect defects during manufacturing. Recent advances in MultiSensor Fusion, Machine Learning, Industrial Internet of Things (IIoT), Digital Twin technology, and predictive analytics enable comprehensive real-time monitoring of manufacturing processes through the integration of heterogeneous sensor information. This paper proposes a MultiSensor Fusion framework for real-time defect detection in additive manufacturing processes by integrating thermal imaging, acoustic emission sensors, optical cameras, vibration monitoring, Machine Learning, cloud manufacturing, and intelligent sensor analytics. The proposed framework continuously analyzes synchronized sensor information to predict manufacturing defects and optimize production quality. Experimental analysis demonstrates significant improvements in defect detection accuracy, manufacturing quality, process stability, operational efficiency, and production scalability compared with conventional single-sensor monitoring approaches. Keywords: Multi-Sensor Fusion, Additive Manufacturing, Defect Detection, Machine Learning, Industrial Internet of Things, Smart Manufacturing, Digital Twin, Predictive Analytics, Quality Monitoring, Industry 4.0.