Bagging-GPR method for ship RCS extrapolation in frequency domain

Abstract

Objective To solve the difficulty of obtaining a radar cross section (RCS) using traditional simulation and measurement methods under high frequency, this study proposes a hybrid method which combines bootstrap aggregation (Bagging) and spectral mixture covariance function-based Gaussian process regression (GPR) model to predict the RCS of ships in the high frequency band efficiently and accurately according to the data in the low frequency band.MethodsFirst, according to the monostatic RCS data of ships in the low frequency band, the training subset is obtained by resampling. The spectral mixture covariance function-based GPR model is then used to extrapolate the RCS data of each subset in the frequency domain. Finally, the extrapolation results of each subset are mixed by the Bagging method to further improve the extrapolation accuracy and robustness of GPR. The proposed method is then tested on the simulation data and measured data respectively. ResultsThe predicted value of the Bagging-GPR hybrid method is basically consistent with the simulated value and measured value, and the root mean square error is very small.ConclusionsThe Bagging-GPR hybrid method has high RCS extrapolation accuracy and good robustness in the frequency domain, providing a new technical means for quickly obtaining the high-frequency RCS characteristics of targets.

Keywords

• radar cross section
• ships
• gaussian process regression
• bootstrap aggregating
• extrapolation.