Use this URL to cite or link to this record in EThOS: https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.817888
Title: Vision-based monitoring system for high quality TIG welding
Author: Bacioiu, Daniel
ISNI:       0000 0004 9358 7065
Awarding Body: University of Birmingham
Current Institution: University of Birmingham
Date of Award: 2019
Availability of Full Text:
Access from EThOS:
Access from Institution:
Abstract:
The current study evaluates an automatic system for real-time arc welding quality assessment and defect detection. The system research focuses on the identification of defects that may arise during the welding process by analysing the occurrence of any changes in the visible spectrum of the weld pool and the surrounding area. Currently, the state-of-the-art is very simplistic, involving an operator observing the process continuously. The operator assessment is subjective, and the criteria of acceptance based solely on operator observations can change over time due to the fatigue leading to incorrect classification. Variations in the weld pool are the initial result of the chosen welding parameters and torch position and at the same time the very first indication of the resulting weld quality. The system investigated in this research study consists of a camera used to record the welding process and a processing unit which analyse the frames giving an indication of the quality expected. The categorisation is achieved by employing artificial neural networks and correlating the weld pool appearance with the resulting quality. Six categories denote the resulting quality of a weld for stainless steel and aluminium. The models use images to learn the correlation between the aspect of the weld pool and the surrounding area and the state of the weld as denoted by the six categories, similar to a welder categorisation. Therefore the models learn the probability distribution of images’ aspect over the categories considered.
Supervisor: Not available Sponsor: EPSRC
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID: uk.bl.ethos.817888  DOI: Not available
Keywords: TS Manufactures
Share: