Improved Image-Based Welding Status Recognition with Dimensionality Reduction and Shallow Learning

• Published in: Experimental mechanics 2022-07, Vol.62 (6), p.985-998
• Main Authors: Ferreira, G.R.B., Ayala, H.V.H.
• Format: Article
• Language: English
• Subjects: Accuracy; Automatic welding; Benchmarks; Biomedical Engineering and Bioengineering; Characterization and Evaluation of Materials; Classification; Control; Deep learning; Disk drives; Dynamical Systems; Engineering; Feature extraction; Gas tungsten arc welding; Image acquisition; Lasers; Machine learning; Object recognition; Optical Devices; Optics; Optimization; Photonics; Prediction models; Principal components analysis; Real time; Reduction; Research Paper; Solid Mechanics; Vibration; Welding machines; Workflow
• ISSN: 0014-4851; 1741-2765
• DOI: 10.1007/s11340-022-00850-w

Background The recent advances in the manufacturing industry, mainly fueled by the fourth industrial revolution, and the shortage of skilled welders are boosting research towards intelligent automatic welding. In this context, vision sensing and machine learning have been widely applied to the development of welding status recognition (WSR) systems. However, researchers have mainly focused on developing accurate models putting aside the analysis on computational performance, which is a relevant aspect of the development of real-time WSR systems. Objective This work aims at devising improved modeling paradigms, considering optimization towards both accuracy and computational performance, for real-time WSR in gas tungsten arc welding. Methods Shallow learning paradigms are compared with a benchmark deep learning model regarding classification as well as computational performance. For that purpose, metrics that account for the time a model takes to make a prediction and the hard disk space occupied by the model are proposed. The dataset used in this paper comprehends molten pool images acquired for defective and non-defective welding conditions. A dimensionality reduction technique was used to extract features from the data efficiently. For the model creation, a randomized hyperparameter search strategy was adopted. Results The modeling workflow adopted resulted in an efficient and lightweight model suitable for being deployed as a diagnostic tool. Results have shown that shallow learning jointly with principal component analysis improved both the accuracy and hardware consumption. Specifically, compared to the benchmark deep learning model, the developed classifier presented size 84.82% smaller, and related accuracy improved by 17.32%. Conclusion The proposed approach has shown to be an efficient way of achieving a compromise between classification and computational performance when developing a predictive model to serve as an online tool for vision-sensing-based WSR.