Angle Measurement Based on Second Harmonic Generation Using Artificial Neural Network

Abstract This article proposed an angle measurement method based on second harmonic generation (SHG) using artificial neural network (ANN). The comprises three sequential parts: SHG spectrum collection, data preprocessing, and training. First, the referenced angles spectrums are collected by autocollimator SHG-based sensor, respectively, for mapping is learned trained ANN after completing training process, which solves inverse problem of obtaining from spectrum. Then, feasibility verified in multiple-peak Maker fringe single-peak phase-matching areas, with overall range exceeding 20,000 arcseconds. predicted compared to evaluate performance all angular ranges. Particularly, a sub-arcsecond level accuracy resolution achieved area.