This paper constructs a fault diagnosis model for antenna drive reducer bearings based on the integration of Successive Variational Mode Decomposition (SVMD) and a Convolutional-Long Short-Term Memory Neural Network (CNN-LSTM). The model employs SVMD to decompose bearing vibration signals into multiple intrinsic mode components, forming the dataset. It utilizes CNN to extract local spatial features of the signals and combines the temporal characteristics of LSTM to achieve deep analysis of fault features. Experimental results demonstrate that the proposed model achieves a classification accuracy of 97.63%, outperforming standalone CNN and CNN-LSTM models by 5.94% and 2.42% respectively in accuracy. This model provides a novel solution for fault diagnosis in antenna drive reducer bearings.