REAL-TIME MELT POOL MONITORING AND DEFECT PREDICTION USING INTELLIGENT SENSOR ANALYTICS

Abstract

Metal additive manufacturing has become an essential technology for advanced industrial production due to its ability to manufacture complex components with improved design flexibility and reduced material waste. However, controlling melt pool dynamics and preventing defect formation remain critical challenges affecting manufacturing quality and reliability. This paper proposes a real-time melt pool monitoring and defect prediction framework using intelligent sensor analytics by integrating Industrial Internet of Things (IIoT), thermal imaging, optical sensing, machine learning, Digital Twin technology, multi-sensor data fusion, and predictive analytics. The proposed methodology continuously captures melt pool characteristics, analyzes process variations, predicts defect formation, and supports adaptive process control for improved manufacturing quality. Experimental evaluation demonstrates improvements in defect prediction accuracy, process stability, monitoring efficiency, surface quality, and production reliability. The proposed framework provides a scalable and intelligent solution for real-time quality assurance in Industry 4.0-enabled metal additive manufacturing environments. Keywords— Melt Pool Monitoring, Defect Prediction, Intelligent Sensor Analytics, Additive Manufacturing, Machine Learning, IIoT, Digital Twin, Smart Manufacturing.