Date of Award

Spring 5-2022

Document Type


Degree Name

Master of Science (MS)


Mechanical & Aerospace Engineering


Aerospace Engineering

Committee Director

Shizhi Qian

Committee Member

Xiaoyu Zhang

Committee Member

Yan Peng


Current analysis of manufacturing defects in the production of rims and tires via x-ray inspection at an industry partner’s manufacturing plant requires that a quality control specialist visually inspect radiographic images for defects of varying sizes. For each sample, twelve radiographs are taken within 35 seconds. Some defects are very small in size and difficult to see (e.g., pinholes) whereas others are large and easily identifiable. Implementing this quality control practice across all products in its human-effort driven state is not feasible given the time constraint present for analysis.

This study aims to identify and develop an object detector capable of conducting defect detection in real-time across all manufactured products to remove the human-in-the-loop from the quality control cycle and leverage subject matter expertise at scale.

A survey of existing literature on object detectors in a defect detection setting was conducted to aid in the selection process of the detector algorithm. Of focus were studies related to the inspection of radiographs in real-time. Additional consideration was given to studies where the performance of small object detection was characterized. Following the literature review, defect detection models were trained and assessed for performance. The object detector utilized in this study is YOLOv3 with a Darknet-53 network.