Acoustic based classification of transfer modes in gas metal arc welding
- Publication Type:
- Conference Proceeding
- Annual Conference of the Australian Acoustical Society 2021: Making Waves, AAS 2021, 2021, pp. 51-57
- Issue Date:
Copyright Clearance Process
- Recently Added
- In Progress
- Open Access
This item is open access.
Gas Metal Arc Welding (GMAW) is a welding process which involves forming an electric arc between a consumable wire electrode and a metal work piece while protecting the arc from contaminants using a shielding gas. In this form of welding, there are several varying ways in which the molten droplets can be transferred from the end of the welding wire into the weld pool known as transfer modes. Identifying these transfer modes is crucial in monitoring and controlling the welding process, especially in automated applications such as industry 4.0 manufacturing lines. Currently in industry, these transfer modes can be identified by expert welders by using the sound signal that is generated throughout the welding process. However, there has been limited research on using the acoustic signal to detect these transfer modes in automated welding applications.This paper explores a new method of automatic GMAW transfer mode detection using machine learning techniques to analyse the acoustic signal generated during the welding process. Several time and frequency domain features are extracted from the acoustic signal and used to train a support vector machine classifier to accurately classify the transfer modes. In addition to this, a new feature selection algorithm is proposed to improve the prediction accuracy of the support vector machine classifier and a final prediction rate of 94% was achieved. This high prediction rate demonstrates the feasibility and promising accuracy of using the acoustic signal as a basis for transfer mode classification in future smart welding technology with real-time adaptive feedback control.
Please use this identifier to cite or link to this item: