Tuning domain randomization for 3D-rendered synthetic training data for defect detection in aircraft engine borescope inspection

Visual surface defect detection in complex industrial inspection scenarios remains predominantly manual. Deep learning–based vision systems promise to automate this task but require large quantities of representative, annotated defect images, which are often unavailable due to the rarity and diversity of relevant defects. We address this challenge with a modular synthetic data generation pipeline leveraging physically based 3D rendering, which enables systematic domain randomization throughout the entire rendering chain. The pipeline comprises dedicated modules for scene composition, geometry-based defect generation, procedural material modeling, rendering, and automatic pixel-wise annotation, allowing users to expose and tune key parameters such as defect size, position, and penetration depth, object materials, camera poses, and lighting. We first provide a structured analysis of all process steps that influence image appearance in defect synthesis and then instantiate the pipeline for a case study on aircraft engine borescope inspection, targeting missing-material defects on high-pressure compressor blades. Using a two-stage experimental design, we employ a Plackett–Burman screening over 22 candidate factors followed by a one-factor-at-a-time optimization of the most influential parameters. Our results show that the material model, defect positioning, defect size, and penetration depth randomization dominate detection performance. Training an object detector solely on synthetic images generated with the optimized configuration yields a maximum of 0.89 mAP@0.5IoU on a real-world borescope validation set, with performance saturating at ∼500 rendered training images. These findings demonstrate that carefully structured domain randomization in a physically based rendering pipeline can provide practically useful synthetic training data for industrial defect detection.

Subjects

deep learning

defect detection

domain randomization

industrial quality control

machine learning

rendering

synthetic training data

visual inspection

DDC Class

629.1: Aviation

Funding(s)

Automatische Datenauswertung für die Inspektion von Luftfahrszeugtriebwerken mit einer in ein Endoskop integrierten MEMS-3D-Kamera

Lizenz

https://creativecommons.org/licenses/by/4.0/

Publication version

publishedVersion

Name

043008_1.pdf

Type

Main Article

Size

17.49 MB

Format

Adobe PDF

Options

Tuning domain randomization for 3D-rendered synthetic training data for defect detection in aircraft engine borescope inspection