AI-Powered, Real-Time Quality Inspection in Mission-Critical Materials Processing Operations
Mike Mohseni, PhD, Founder and President, AutoMetrics Manufacturing Technologies Inc
In mission-critical manufacturing operations such as welding, defects can potentially lead to disasters, therefore, quality inspection is a critical part of these operations. The manufacturing industry adopts various solutions to ensure quality, and intensive post-process inspection is the most used approach. Process automation using robotic systems is another approach that enhances the execution and ultimately quality of the welding process. Nevertheless, due to significant variabilities in manufacturing processes and the high number of influencing process parameters, most quality inspection operations related to weld quality remain manual and post-process. AI and machine learning can enhance reliability and enable automated inspection during welding operations. There is a growing interest in automated defect detection and geometrical inspections using machine learning and vision software solutions in food and electronics packaging industries. Nevertheless, the adoption of these powerful tools in materials processing operations such as welding is lagging. The complexity of the process and high changeover rates in manufacturing lines that use welding tend to be main hurdles.
We review new approaches in real-time analytics and computer vision powered by machine learning, and how these tools can enable automated inspection in welding operations and provide manufacturing operations with actionable insight regarding process quality in real-time. Considering the established nature of the manufacturing sector, the adoption of such advanced technologies in manufacturing lines requires special attention. We present a case study related to the adoption of automated inspection at a metal fabrication plant and discuss how the intrinsic nature of machine learning in conjunction with advanced IoT infrastructure can facilitate seamless integration causing minimal interruptions in manufacturing operations at both installation and deployment stages.
Mike Mohseni completed a Ph.D. in composites manufacturing at The University of British Columbia. His work on defect control in aerospace composites manufacturing is being used by the industry to reduce costs and increase production efficiency. Inspired by his education, professional experience as a Simulation and Machine Learning engineer, and projects such as manufacturing workflow optimization with software, Mike founded AutoMetrics, to develop and commercialize automated quality management systems with machine learning and AI.