AIoT for Aircraft Final Assembly: An Intelligent and Collaborative Framework

Abstract

Aircraft final assembly line (AFAL) involves thousands of processes that must be completed before delivery. However, the heavy reliance on manual labor in most assembly processes affects the quality and prolongs the delivery time. While the advent of artificial intelligence of things (AIoT) technologies has introduced advancements in certain AFAL scenarios, systematically enhancing the intelligence level of the AFAL and promoting the widespread deployment of artificial intelligence (AI) technologies remain significant challenges. To address these challenges, we propose the intelligent and collaborative aircraft assembly (ICAA) framework, which integrates AI technologies within a cloud-edge-terminal architecture. The ICAA framework is designed to support AI-enabled applications in the AFAL, with the goal of improving assembly efficiency at both individual and multiple process levels. We analyze specific demands across various assembly scenarios and introduce corresponding AI technologies to meet these demands. The three-tier ICAA framework consists of the assembly field, edge data platform, and assembly cloud platform, facilitating the collection of heterogeneous terminal data and the deployment of AI technologies. The framework enhances assembly efficiency by reducing reliance on manual labor for individual processes and fostering collaboration across multiple processes. We provide detailed descriptions of how AI functions at each level of the framework. Furthermore, we apply the ICAA framework to a real AFAL, focusing explicitly on the flight control system testing process. This practical implementation demonstrates the effectiveness of the framework in improving assembly efficiency and promoting the adoption of AIoT technologies.