Towards perceptive assembly: Real-time full-field deformation twin perception method for large components under parametric load

Abstract

Enhancing information perception capabilities during the manufacturing and assembly of large-scale components is pivotal for advancing intelligent systems, particularly in the aerospace industry. This paper presents a perceptive assembly approach utilizing a full-field deformation twin perception method based on parametric loads, enabling real-time and accurate reconstruction of deformation fields in large components through a binocular vision system. This method centers around parametric load definitions, proposing the PPOD (Parametric Proper Orthogonal Decomposition) technique for deformation reconstruction, followed by an in-depth analysis of the factors contributing to perception errors. To meet the demands of online deployment, a comprehensive framework is established, deeply integrating measurement instruments, measurement data, and physical models to enhance measurement efficiency and perception robustness. Extensive simulations and experimental results demonstrate that this approach reduces perception errors by over 70% compared to traditional methods, achieving real-time, high-precision, and robust monitoring of deformation in large components. This perceptive assembly framework holds significant promise as a foundational infrastructure for real-time state perception in the intelligent manufacturing of large-scale components.