Ensuring product detection and product counting on the assembly line using deep learning (YOLOv11)

This study used the YOLO (You Only Look Once) algorithm and the Ultralytics library for product counting and inspection on the suspension system assembly line. Suspension systems, which connect a vehicle to its wheels and manage its interaction with the road, are crucial for vehicle control and passenger comfort. Key components, such as the Z-rod, tie rod, swing arm, and tie rod end, play a vital role in the production process. Accurate product counting on the assembly line is essential to detect any shortages or surpluses. Relying on operator discretion for product detection can lead to customer complaints and financial losses. To address this, the YOLO algorithm was employed to perform faster, more accurate product counting and inspection. YOLO, a deep learning-based object detection method, was implemented using the Ultralytics YOLOv11 model. Suspension part images were labeled with bounding boxes and class labels for training. During the training process, hyperparameters were optimized to improve accuracy. After training, the model was tested on new data, successfully detecting and counting products. In conclusion, using YOLO and Ultralytics significantly improved the assembly line's product counting and inspection processes, eliminating operator errors and enabling faster, more precise counting. This deep learningapproach enhanced production efficiency, ensuring product quality and reliability.