Adaptive extraction of rotating Doppler shift based on random forest regression

Rotational Doppler effect (RDE) has played an important role in target rotational speed measurement since its discovery and has attracted widespread attention. Addressing the issues of complex rotational speed extraction processes and limited means of rotational speed information extraction in traditional RDE-based measurements, this study introduces a novel method for intelligent extraction of rotational speed information based on a random forest machine learning model. An intelligent extraction scheme for target rotational speed information is established, achieving adaptive and high-precision extraction of target rotational speed information under the RDE regime. Experiments show that the trained model achieves a processing accuracy of over 95 % for actual measurement data, effectively improving the efficiency and precision of target rotational speed information extraction, and has broad application prospects in metrology.