Particle identification is a critical component of space environment detection. In this study, we propose a CNN-LSTM based multi-class automatic particle classification network, which employs 1-D CNN to extract more discriminative local features of waveforms produced by particle detector, and utilizes the ability of LSTM to capture long-range dependencies for extracting global features with stronger generalization capability. The proposed network can effectively classify the waveforms from multi-type with multi-energy charged particles, achieving an accuracy of 91.72% in simultaneously classifying H, B, C, O, and Al ions across three distinct energy levels. Furthermore, the proposed network achieves an accuracy of 73.60% in classifying particles with unseen energy levels during training, significantly surpassing the accuracy of previous methods. Extensive analysis experiments demonstrate the robustness and effectiveness of the proposed network.