Machine learning and sensor-based approach for defect detection in MEX additive manufacturing process- A Review

Defect detection in the material extrusion process is of prime importance to enhance the production of high-quality parts with more complex designs and reduction of defects. This paper presents a comprehensive review of machine learning and sensor-based approaches for defect detection in the material extrusion process (MEX) additive manufacturing process. The literature review provides insight into various machine learning and deep learning models that can be used in conjunction with sensorisation to monitor the health of the printer as well as the printing process. The study highlights the significance of defect detection in the material extrusion process and explores the potential of machine learning and sensor-based methods in identifying defects and improving the quality of the final products. The review also highlights the advantages and limitations of these techniques and identifies the areas for future research. The organisation and synthesis of information in this review provide valuable insights into the current state of research on defect detection in the MEX process, specifically focusing on the utilisation of sensors, machine learning, and artificial intelligence. By organising and presenting this information, this review paper aims to facilitate a deeper understanding of the challenges, advancements, and potential future directions in the field of defect detection in MEX. These insights contribute to the ongoing efforts to enhance the quality and reliability of 3D-printed products.