Classification of Spot-welded Joints in Laser Thermography Data using Convolutional Neural Networks

TL;DR

This paper presents a CNN-based method for classifying spot weld quality from laser thermography images, achieving over 95% accuracy and improving upon traditional techniques by leveraging physics-informed data preparation and augmentation.

Contribution

It introduces a physics-based data filtering approach and compares various CNN models for improved weld quality classification from thermography data.

Findings

Achieved over 95% classification accuracy.

Demonstrated the effectiveness of physics-informed data filtering.

Explored the impact of different data augmentation methods.

Abstract

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.