A Comparative Regression Analysis between Principal Component and Partial Least Squares Methods for Flight Load Calculation

Featured Application This study investigates and compares various multivariate regression methods, including principal component regression (PCR) and partial least squares regression (PLSR), for flight load analysis and demonstrates their high learning efficiency and strong generalization capabilities, making them highly suitable for this purpose. This study investigates and compares various multivariate regression methods, including principal component regression (PCR) and partial least squares regression (PLSR), for flight load analysis and demonstrates their high learning efficiency and strong generalization capabilities, making them highly suitable for this purpose. The flight load data of a civil aircraft use altitude, Mach number and load factors as input parameters, which are used as sample data to establish regression models for predicting wing loads under different flight conditions. The accuracy of all regressions are confirmed through evaluation, with PLSR being the most efficient. In the comparison of computational times, it was found that the computational efficiency of regression methods was significantly superior to traditional panel methods. The flight load calculation shows that PCR and PLSR can significantly improve analysis efficiency and provide new insights into efficient flight load analysis.