Classification of Spot-welded Joints in Laser Thermography Data using Convolutional Neural Networks
This addresses quality inspection in industrial spot welding, but it is incremental as it applies existing CNNs to a specific domain with tailored data filters.
The paper tackles the problem of classifying spot welding quality from laser thermography images by proposing data preparation methods based on physics and using convolutional neural networks, achieving over 95% accuracy.
Spot welding is a crucial process step in various industries. However, classification of spot welding quality is still a tedious process due to the complexity and sensitivity of the test material, which drain conventional approaches to its limits. In this paper, we propose an approach for quality inspection of spot weldings using images from laser thermography data.We propose data preparation approaches based on the underlying physics of spot welded joints, heated with pulsed laser thermography by analyzing the intensity over time and derive dedicated data filters to generate training datasets. Subsequently, we utilize convolutional neural networks to classify weld quality and compare the performance of different models against each other. We achieve competitive results in terms of classifying the different welding quality classes compared to traditional approaches, reaching an accuracy of more than 95 percent. Finally, we explore the effect of different augmentation methods.