Intel has developed an AI solution for John Deere to automatically spot common defects in the automated welding process at its manufacturing facilities.
According to the tractor and agro-equipment manufacturer, Intel’s computer vision could help solve a costly and age-old problem plaguing John Deere’s manufacturing welding process.
John Deere currently uses Gas Metal Arc Welding (GMAW) process to weld mild- to high-strength steel to create machines and products.
Hundreds of robotic arms consume millions of weld wire pounds annually at Deere’s 52 factories that are located across the globe. With this volume of welding, there is bound to be welding issues.
One common welding challenge felt across the industry is porosity, in which cavities in the weld metal are caused by trapped gas bubbles as the weld cools. This weakens the weld strength.
GMAW defect detection is a manual process and it requires highly skilled technicians. Past attempts to deal with weld porosity issues during the welding process haven’t always been successful.
If these flaws are found later in the manufacturing process, they require re-work or even scrapping of full assemblies, which can be disruptive and expensive to manufacturers.
To remedy this, Intel and Deere have combined expertise to develop an integrated, end-to-end system of hardware and software that can generate insights in real time.
The AI ‘defect detection at the edge’ solution is powered by Intel Core i7 processors and uses Intel Movidius VPUs and the Intel Distribution of OpenVINO toolkit.
These are implemented with an industrial-grade ADLINK Machine Vision Platform and a MeltTools welding camera.
When using a neural network-based inference engine, the solution logs defects in real time and automatically stops the welding process.
This allows Deere to correct the issue in real time and produce quality products.
According to Christine Boles, Intel’s IoT Group vice president, the Intel solution isn’t just limited to welding; it comes with the potential of revolutionizing Deere’s other Industry 4.0 goals.
Image and content: John Deere/Intel