AI for Airplane Engine Inspection

This project aims to develop an AI-powered visual inspection system using image data from P&WC’s existing Computer Vision Inspection System (CVIS) to enhance aircraft engine assembly issue detection. By leveraging deep learning techniques, the proposed solution will address current limitations in accuracy and consistency, targeting a 100% visual detection rate for anomalies such as: part at wrong orientation, missing or extra component, and not-tospec installation. The model will be trained on historical CVIS images, validated against expert annotations, and integrated into a streamlined inspection workflow with human-in-the-loop capabilities for continuous improvement. This initiative will replace a less reliable visual inspection system currently used, reduce time and energy resources expended when out-of-spec parts are shipped by or require off-site repair, and establish a scalable foundation for future smart inspection technologies within aerospace manufacturing and maintenance environments.

Faculty Supervisor:

Ameera Al-Karkhi;Ethan Shen

Student:

Partner:

Pratt & Whitney Canada

Discipline:

Engineering

Sector:

Manufacturing; Mining; Professional, scientific and technical services

University:

Sheridan College Institute of Technology and Advanced Learning

Program: