AI Vision System Slashes Spare Part Identification Time for Small Manufacturers
Researchers developed an AI-powered image recognition system that automatically identifies mechanical parts from customer photos, cutting out manual expert work. For manufacturing SMEs, this means faster service delivery and lower operational costs—critical advantages in industries where spare part delays directly cost customers money.
Originaltitel: AI-Driven Real-Time Spare Part Identification in Manufacturing SMEs Using YOLO Models
<p>In the competitive landscape of various industries, small and medium-sized enterprises (SMEs) face significant challenges in maintaining efficient customer service, particularly when it comes to identifying and ordering spare parts. The current process is often based on 3D diagrams, CAD images, or customer-provided photos is manual, time-consuming, and dependent on individual experts, leading to inefficiencies, longer lead times, and risks of knowledge loss. This study investigates the use of deep learning-based image recognition to automate spare part identification and improve service efficiency. We develop and evaluate a YOLO-based detection system trained on diverse real-world images to handle variations in lighting, angles, and backgrounds. The system demonstrates robust performance and achieves high accuracy in identifying parts from customer-provided images in both two-class (up to 100%) and three-class (up to 80%) experiments. Comparative results show that lightweight YOLO variants, particularly YOLOv8n, provide the best trade-off between accuracy and speed, making them suitable for real-time SME applications. This research highlights the potential of integrating AI-driven part detection into customer service workflows, reducing lead times, enhancing accuracy, and offering a scalable, low-cost solution for manufacturing SMEs</p>