Deep learning enabled intelligent robotic system for aeroengine blade surface inspection – Scientific Reports

Subjects

Abstract

Aeroengine blades (AEBs) are critical components of aircraft engines that require consistent monitoring and inspection to ensure airworthiness and operational safety. The aerospace industry relies heavily on maintenance, repair, and overhaul (MRO) procedures, where surface inspection of AEBs plays a pivotal role. Traditional manual or borescope-based inspection methods are time consuming, labor intensive, and susceptible to human error. In this work, a deep learning enabled intelligent robotic system is proposed for the autonomous inspection of AEBs, addressing key MRO requirements. Two distinct datasets were collected, one for aeroengine blade localization and another for surface defect detection. A robust deep learning model is trained separately on each dataset to perform their respective tasks with high accuracy. The trained models were integrated into an intelligent robotic system to automate the inspection workflow. In real time operation, a container filled with aeroengine blades is placed in front of the intelligent system, which autonomously localizes each blade, picks it up, places it in an image acquisition box, detects any surface defects, and returns the blade to its original position. The system provides real time feedback and accelerates decision making processes. Experimental results demonstrate that the proposed approach significantly reduces inspection time and enhances defect detection accuracy compared to conventional methods. By seamlessly combining vision based deep learning with robotic automation, the system offers a reliable solution for controlled industrial inspection environments for modern aerospace MRO processes, overcoming the limitations associated with manual inspection techniques. Experimental results demonstrate that the proposed approach achieves an mAP of 88.2% and reduces inspection cycle time to approximately 4 seconds per blade, significantly improving efficiency compared to conventional methods.