Driven by technological advancements, machine vision has become a fundamental technology within computer-integrated manufacturing. Consequently, this PhD study explores the potential of applying machine vision to advance quality assurance and quality control of manufacturing processes, supporting the digital transformation. The study centres on two industrial research projects: CeJacket and INTERLASE.

In the context of the CeJacket project, the application of machine vision is studied within the domain of post-weld treatment and quality inspection. By utilising 3D scanning, the goal is to enhance robotised high-frequency mechanical impact (HFMI) treatment. The outcome of the study is experimentally validated, demonstrating significant improvements in reproducibility, work environment, and the overall quality assurance of the process.

Related to the INTERLASE project, the PhD study presents several machine vision-based solutions to optimise laser processing. These include innovative methods such as in situ calibration of galvanometric scanner systems and in-line monitoring methods to identify variations in surface quality and part alignment. The developed methods are experimentally demonstrated, showing enhancements in processing accuracy and stability.

In summation, the outcomes of this research demonstrate the potential of machine vision to optimise manufacturing processes and deliver effective and robust solutions for quality assurance and quality control.