Abstract
Gears are a vital component in many complex mechanical systems. In automotive systems, and in particular vehicle transmissions, we rely on them to function properly on different types of challenging environments and conditions. However, when a gear is manufactured with a defect, the gear’s integrity can become compromised and lead to catastrophic failure. The current inspection process used by an automotive gear manufacturer in Guelph, Ontario, requires human operators to visually inspect all gear produced. Yet, due to the quantity of gears manufactured, the diverse array of defects that can arise, the time requirements for inspection, and the reliance on the operator’s inspection ability, the system suffers from poor scalability, and defects can be missed during inspection. In this work, we propose a machine vision system for automating the inspection process for gears with damaged teeth defects. The implemented inspection system uses a faster R-CNN network to identify the defects, and combines domain knowledge to reduce the manual inspection of non-defective gears by 66%.
Highlights
Gears play an important role in automotive transmission systems, where they are used to transfer power from the vehicles motor through to the various wheels
At an automotive gear manufacturer located in Guelph, Ontario, the current quality control inspection process requires human operators to manually inspect all gear for the presence of defects
The damaged teeth defect has a distinct profile on the gear, which usually appears as a laceration or lesion on the surface, and can be recognized by human operators through visual inspection
Summary
Gears play an important role in automotive transmission systems, where they are used to transfer power from the vehicles motor through to the various wheels. The types of gears used in these transmissions are typically mass-produced, with different kinds of gears used in different vehicles, and all manufactured using different dyes and tooling processes Due to these conditions, it is possible for a manufactured gear to either directly or indirectly be produced with a defect(s). As the defects are infrequent and have diverse profiles, and as the gears themselves have different shapes and material characteristics (e.g., reflective surfaces), inspection can be a challenging and time-consuming process All of these factors contribute to the quantity of parts that can be inspected daily, and as such, an automated system that can improve the inspection accuracy and speed is required to further optimize the quality control process
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
