PathPartner Technology, a product R&D organization, announced a collaboration with Intel Corporation to deliver an Artificial Intelligence (AI) technology-based arc welding defect detection solution to the manufacturing industry. PathPartner leverages its deep expertise in building state-of-the-art AI and Machine Vision software on Intel® edge processors to help manufacturers successfully adopt the defect detection technology and expand it to address broader Industry 4.0 use-cases.
This very low latency automated defect detection solution is for robotic gas metal arc welding (GMAW) in heavy equipment manufacturing. The camera-based solution runs on the edge, detects weld porosity defects using a proven AI algorithm, and can be used to stop the robotic arm immediately in case an anomaly is identified. This allows manufacturers to find weld defects and reduce delays in the production process, optimize costs, and increase overall productivity.
Automated Arc Welding Defect Detection uses a deep neural network based inferencing engine to detect welding defects in a way not possible with the human eye and is tested to deliver an accuracy of 97%. It is powered by scalable Intel® Core™ i7 processors and uses Intel® Movidius™ VPUs and the Intel® Distribution of OpenVINO™ toolkit to detect arc welding defects with very low latency and high accuracy.
“AI and machine vision technologies are transforming traditional manufacturing processes in ways we could never imagine before. PathPartner is extremely excited to collaborate with Intel and be at the forefront of this transformation,” said Raman Narayan, Country Head, USA at PathPartner. “With our extensive experience in building custom AI-based solutions coupled with the compute horsepower of Intel edge processors, we are committed towards helping our customers successfully deploy machine vision on their smart factory floors and bring unprecedented efficiencies in their manufacturing processes.”
The technology is available for a free evaluation on the AWS marketplace. All that is needed to get started is an input stream from the welding setup that should be tested. System integrators and manufactures can quickly evaluate the technology without worrying about hardware dependencies, software installations, and other dependencies.
