Quality Assurance of Weld Seams Using Laser Triangulation Imaging and Deep Neural Networks

TL;DR

This paper introduces a deep learning-based optical inspection system using laser triangulation imaging for weld seam quality assurance, suitable for Industry 4.0, achieving high accuracy and robustness with low-cost hardware.

Contribution

It presents a novel, flexible inspection system that combines laser triangulation images and deep neural networks for accurate weld seam classification in manufacturing.

Findings

Achieved classification accuracy up to 96.88%.

System is robust to environmental variations.

Enables fast, cost-effective inspection integrated into production lines.

Abstract

In this paper, a novel optical inspection system is presented that is directly suitable for Industry 4.0 and the implementation on IoT-devices controlling the manufacturing process. The proposed system is capable of distinguishing between erroneous and faultless weld seams, without explicitly defining measurement criteria . The developed system uses a deep neural network based classifier for the class prediction. A weld seam dataset was acquired and labelled by an expert committee. Thereby, the visual impression and assessment of the experts is learnt accurately. In the scope of this paper laser triangulation images are used. Due to their special characteristics, the images must be pre-processed to enable the use of a deep neural network. Furthermore, two different approaches are investigated to enable an inspection of differently sized weld seams. Both approaches yield very high classification accuracies of up to 96.88\%, which is competitive to current state of the art optical inspection systems. Moreover, the proposed system enables a higher flexibility and an increased robustness towards systematic errors and environmental conditions due to its ability to generalize. A further benefit of the proposed system is the fast decision process enabling the usage directly within the manufacturing line. Furthermore, standard hardware is used throughout the whole presented work, keeping the roll-out costs for the proposed system as low as possible.