Addressing the challenge of low identification accuracy in traditional load identification methods based on the truncated singular value decomposition (TSVD) method, especially when the external load frequency approaches or reaches the natural frequency of the structure, we propose the LSTM-CNN load identification model. This model combines the feature extraction capabilities of the convolutional neural network (CNN) with the long-term memory function of the long short-term memory network (LSTM). The load identification method based on the LSTM-CNN model is then applied to research load time domain waveform identification on the GARTEUR aircraft model. For model training and load identification, we collect response data and excitation data from the structure. The identification results are compared with the TSVD method, LSTM method, and DCNN method. The findings demonstrate that the load identification method based on the LSTM-CNN model proves effective for sinusoidal load identification problems, especially under the natural frequency excitation of the structure. The method exhibits high identification accuracy and robust noise resistance capabilities.