Artificial intelligence for process monitoring of automated fibre placement: Real-time defect detection and classification

Automated Fibre Placement (AFP) has seen rising interest within the composites manufacturing industry, due to its ability to produce complex parts with high precision and speed. However, like any process, AFP is susceptible to defects. Historically, the detection of defects during AFP manufacturing has been a challenging part of the process, requiring time-consuming manual inspection to maintain quality control. Traditional inspection is also conducted post-layup, leading to significant material wastage and poor sustainability characteristics, as defective parts are often discarded and non-recyclable. Recognising a shift towards industry 4.0, this work presents a proof-of-concept level, real time inspection system which utilises artificial intelligence, specifically convolutional neural networks (CNNs) trained on laser profilometry data, to automate the inspection process. The proposed system
was evaluated on a lab-scale AFP machine and is capable of accurately detecting and classifying defects rapidly after they are laid up. The results of this study therefore demonstrate the potential application of AI for real time inspection during composites manufacturing. Such systems not only address the limitations of traditional quality control methods, but also open avenues for enhancing production efficiency, reducing costs/wastage, and aiding the consistent delivery of high-quality composite components.