Research on key technologies of flexible automated helicopter assembly production lines for aerospace manufacturing
Abstract
Helicopter assembly is characterized by complex structures, stringent accuracy requirements, and low-volume multi-variant production, posing significant challenges to conventional assembly lines in terms of efficiency, flexibility, and quality control. To address these issues, this paper proposes a Digital Twin-driven Flexible Automated Helicopter Assembly Line (DFA-HAL) for aerospace manufacturing. The proposed framework integrates laser–vision fusion adaptive positioning, multi-robot collaborative assembly, dynamic production scheduling, and intelligent quality monitoring into a unified cyber-physical system. An adaptive positioning method is developed to compensate for geometric deviations in real time, while a multi-robot collaboration strategy and an improved NSGA-II algorithm are employed to enhance assembly efficiency and scheduling flexibility. Furthermore, a cloud–edge–end quality monitoring framework based on a CNN-LSTM model is established for real-time quality prediction and closed-loop control. Experimental results demonstrate that the proposed method reduces positioning error to 0.15 mm, shortens changeover time by 51.7%, and decreases makespan by 44.9% under production disturbances. The results verify the effectiveness of the proposed approach in improving flexibility, productivity, and assembly quality in aerospace manufacturing.