Beihang University Develops Innovative Robot for Aircraft Wing Maintenance

During the assembly of aircraft, excess materials such as nuts, rivets, and aluminum shavings often remain trapped within the wings. These remnants pose a significant risk, potentially disrupting the operation of critical aircraft components and leading to serious flight incidents. To address this pressing issue, researchers at Beihang University have introduced a novel solution in their study titled “Detection and Removal of Excess Materials in Aircraft Wings Using Continuum Robot End-Effectors.”

The study focuses on enhancing the efficiency of removing excess materials, which has traditionally relied on manual operations. The confined spaces within aircraft wings make manual access challenging, and conventional robotic systems often fail to navigate such narrow environments effectively. This has resulted in low efficiency during removal tasks.

The researchers employed a continuum robot equipped with a specialized removal end-effector and a stereo camera. They began by analyzing the size and weight characteristics of the materials commonly found in aircraft wings. Based on this analysis, they designed a unique negative pressure end-effector capable of removing small items like nuts and rivets, as well as a two-finger gripper intended for extracting larger volumes of aluminum shavings.

To tackle the inadequate lighting conditions often present inside aircraft wings, the team incorporated supplementary lighting devices. This enhancement is crucial for accurate detection and removal operations. For object classification and detection, the You Only Look Once (YOLO) v5 algorithm was utilized, along with the creation of two training datasets tailored for different types of wings.

Given the limited texture features within the aircraft wings, the researchers implemented an image-matching technique that leverages the YOLO v5 detection results. This method circumvents the performance instability commonly associated with traditional feature point matching systems. Experimental results demonstrated impressive outcomes, with detection accuracy for each type of excess material exceeding 90%. Additionally, the visual localization error was maintained at under 2 mm for four distinct types of excess objects.

The efficacy of the two end-effectors was confirmed through experimental verification, showcasing their capability to effectively remove excess materials from aircraft wings. The research paper, authored by Xiujie Cao, Jingjun Yu, Siqi Tang, Junhao Sui, and Xu Pei, presents a significant advancement in aircraft maintenance technology.

For those interested, the full text of the paper is available at: https://doi.org/10.1007/s11465-024-0806-2. This innovative approach not only enhances the safety and reliability of aircraft operations but also showcases the potential of robotics in the aerospace industry.