🤖 AI Summary
Manufacturing SMEs face critical bottlenecks in visual assembly quality control—including scarce real-image acquisition, high annotation costs, and insufficient training data. To address these challenges, this paper proposes a CAD model–driven fully synthetic data framework. It establishes an end-to-end virtual generation pipeline integrating parametric CAD modeling, physics-based rendering, and YOLO-family object detection, enabling efficient simulation-to-reality transfer learning. This work represents the first systematic deployment of a purely synthetic data approach to industrial inspection of planetary gear assemblies. Experiments demonstrate a 99.5% mAP@0.5:0.95 on synthetic data; after domain adaptation, detection accuracy remains at 93% on real-world images. The framework significantly reduces dependence on manual annotation and physical image collection, validating its feasibility for lightweight, reusable, and low-cost industrial deployment.
📝 Abstract
Quality control of assembly processes is essential in manufacturing to ensure not only the quality of individual components but also their proper integration into the final product. To assist in this matter, automated assembly control using computer vision methods has been widely implemented. However, the costs associated with image acquisition, annotation, and training of computer vision algorithms pose challenges for integration, especially for small- and medium-sized enterprises (SMEs), which often lack the resources for extensive training, data collection, and manual image annotation. Synthetic data offers the potential to reduce manual data collection and labeling. Nevertheless, its practical application in the context of assembly quality remains limited. In this work, we present a novel approach for easily integrable and data-efficient visual assembly control. Our approach leverages simulated scene generation based on computer-aided design (CAD) data and object detection algorithms. The results demonstrate a time-saving pipeline for generating image data in manufacturing environments, achieving a mean Average Precision (mAP@0.5:0.95) up to 99,5% for correctly identifying instances of synthetic planetary gear system components within our simulated training data, and up to 93% when transferred to real-world camera-captured testing data. This research highlights the effectiveness of synthetic data generation within an adaptable pipeline and underscores its potential to support SMEs in implementing resource-efficient visual assembly control solutions.