Aiming at the difficulty of extracting features and classifying 3D point clouds due to their irregularity and disorder, this paper proposes a 3D point cloud classification method that integrates deep learning and ensemble learning. Firstly, the deep learning model PointCloudTransformer is trained to extract point cloud features and to construct a set of base classifiers. Subsequently, we design a base classifier selection model for ensemble learning that takes the diversity and average overall accuracy of the base classifiers as the optimization objectives and proposes a binary multi-objective beluga optimization algorithm to optimize the base classifier model and obtain the ensemble pruning scheme set. Finally, the majority voting method is used to ensemble the classification results of each base classifier combination on the test set to obtain the optimal base classifier combination, and an ensemble learning model of point cloud classification based on multi-objective optimization ensemble pruning is obtained. Experimental results on the ModelNet40 point cloud classification dataset demonstrate that the method in this paper achieves higher ensemble accuracy with a smaller ensemble scale and can accurately classify multi-class 3D point clouds.