Article’s

In the realm of electrical circuits, ensuring the integrity and functionality of components is crucial for maintaining system reliability. This paper proposes a novel approach for the automated detection of missing components in electrical circuits leveraging the power of YOLOv12. The YOLOv12 architecture is well-suited for object detection tasks, making it an ideal candidate for identifying and localizing missing components within complex circuit layouts. The proposed system employs a two-stage approach, where the first stage involves region proposal generation, and the second stage focuses on refining and classifying these proposals. The YOLOv12 model is trained on a dataset composed of diverse circuit layouts, encompassing various types of components and their normal configurations. The network learns to differentiate between normal and anomalous circuit patterns, with an emphasis on identifying regions where components are missing. To enhance the robustness of the detection system, data augmentation techniques are employed during the training phase, allowing the model to generalize well to different circuit layouts and variations in component placements. The trained YOLOv12 model demonstrates its ability to accurately locate missing components, even in the presence of noise, variations in lighting, and different circuit board orientations. Experimental results showcase the effectiveness of the proposed approach, achieving high accuracy and precision in detecting missing components across a range of test scenarios. The system’s performance is evaluated on both synthetic datasets and real-world electrical circuits, demonstrating its applicability in practical scenarios. The proposed YOLOv12-based approach holds promise for integration into real-time monitoring systems, contributing to the overall reliability and safety of electrical systems. Keywords: YOLOv12, electrical circuits, missing components, object detection, PCB inspection, automation, deep learning, anomaly detection, computer vision, fault diagnosis.