Double-line spectroscopic binaries (SB2s) are a vital class of spectroscopic binaries for studying star formation and evolution. Searching for SB2s has been a hot topic in astronomy. Although considerable efforts have been made with fruitful outcomes, limitations in automation and accuracy still persist. In this study, we developed a convolutional neural network (CNN) model to search for SB2 candidates in LAMOST medium-resolution survey (MRS) DR9 v1.0 by detecting double peaks in the cross-correlation function (CCF). We first generated a large number of spectra of single stars and binaries using the iSpec spectral synthesis software (Blanco-Cuaresma+ 2014A&A...569A.111B & Blanco-Cuaresma 2019MNRAS.486.2075B). The CCFs of these synthesized spectra were then calculated to form our training set. To efficiently detect the peaks of the CCFs, we applied a Softmax function-based noise reduction method. After testing and validation, the model achieved an accuracy of 97.76% in the testing set and was validated for more than 90% of the sample in several published SB2 catalogs. Finally, by applying the model to examine approximately 1.59 million LAMOST-MRS DR9 spectra, we identified 728 candidate SB2s, including 281 newly discovered ones.

Cone search capability for table J/ApJS/266/18/table6 (Details of a total of 728 SB2 candidates eventually obtained)

Cone search capability for table J/ApJS/266/18/table4 (Information of 2139 SB2 candidate spectra)

Cone search capability for table J/ApJS/266/18/table5 (Information on the complete table of a total of 36470 SB2 candidates)