Multispectral Automated Roller and Ball Bearing Inspection System Using Machine Learning

To address the Department of the Air Force (DAF) need for a nondestructive inspection (NDI) system for silicon nitride ceramic bearings that is significantly faster and more cost-effective than current systems, Intellisense Systems, Inc. (Intellisense) proposes to advance the developments of its Multispectral Automated Roller and Ball Bearing Inspection System Using Machine Learning (MARBIL), which uses an innovative multispectral imaging approach to detect all potential flaws in the bearing, including surface and interior flaws, without requiring any liquid penetrant, in combination with machine learning (ML) algorithms to rapidly distinguish faulty bearings from acceptable ones. Specifically, MARBIL can detect surface defects as small as 15 µm and voids as small as 50 µm, depending on the specifics of the bearing under test. MARBIL can accommodate multiple sizes of rolling elements, both roller and ball designs (including tapered and crowned rollers), and bearings of different materials, including various ceramics and metal. This allows a single MARBIL unit to inspect all possible bearings at a production facility, reducing costs by up to 54% over five years relative to facilities that utilize manual inspection with liquid penetrant. MARBIL’s parallelization approach for imaging and image processing reduces the total inspection time to <8 s, allowing every bearing to be inspected and thus improving the quality of bearings delivered to the Air Force. During Phase II, Intellisense will refine the prototype for integrability in bearing production facilities, validate the inspection methodology developed in Phase I for conditions replicating those found in practice with physical testing, and show feasible build processes and stable quality assurance processes. By the conclusion of Phase II, Intellisense plans to demonstrate the MARBIL system at a bearing supplier’s production facility. Intellisense will then begin transitioning the technology to interested original equipment manufacturers and bearing suppliers during Phase III.