Résumé:
This final year project investigates the use of artificial intelligence (AI) to enhance the inspection
process of printed circuit boards (PCBA) at Bomare Company. Utilizing a convolutional neural network
(CNN), we developed an AI model capable of accurately distinguishing defective from non-defective
PCBA. Trained on a large dataset of images, the model demonstrated excellent performance in terms of
accuracy, recall, and AUC score. We also discussed in detail the integration of the model into the
production process, highlighting the importance of collaboration among various teams, operator training,
and continuous performance monitoring of the model. The potential of AI to improve efficiency, quality,
and reduce production costs was underscored, making this technology a viable solution for PCBA
inspection in the manufacturing industry.
