Surrogate Model-Based Control Considering Uncertainties for Composite Fuselage Assembly

Abstract

Shape control of composite parts is vital for large-scale production and integration of composite materials in the aerospace industry. The current industry practice of shape control uses passive manual metrology. This has three major limitations: (i) low efficiency: it requires multiple trials and a longer time to achieve the desired shape during the assembly process; (ii) nonoptimal: it is challenging to reach optimal deviation reduction; and (iii) experience-dependent: highly skilled engineers are required during the assembly process. This paper describes an automated shape control system that can adjust composite parts to an optimal configuration in a manner that is highly effective and efficient. The objective is accomplished by (i) building a finite element analysis (FEA) platform, validated by experimental data; (ii) developing a surrogate model with consideration of actuator uncertainty, part uncertainty, modeling uncertainty, and unquantified uncertainty to achieve predictive performance and embedding the model into a feed-forward control algorithm; and (iii) conducting multivariable optimization to determine the optimal actions of actuators. We show that the surrogate model considering uncertainties (SMU) achieves satisfactory prediction performance and that the automated optimal shape control system can significantly reduce the assembly time with improved dimensional quality.