The fault diagnosis for hydraulic system of automatic grabbing beam faces the problems of low accuracy and difficulty in deep feature extraction.A diagnosis model integrating long short-term memory convolutional neural network (LSTM-CNN) feature extraction network and particle swarm optimization K-nearest neighbors (PSO-KNN) was proposed.Taking the pressure information of key nodes in hydraulic system of automatic grabbing beam as inputs,LSTM was adopted for 1D feature extraction and combined with 2D feature extracted by CNN.The optimized KNN model was then utilized for fault classification based on the extracted features.The AMESim automatic grabbing beam model based on real data was built for simulation,to verify the effectiveness and progressiveness of the proposed model.The results demonstrate that the proposed model achieves a diagnostic accuracy of 97.92% and it can effectively identify common faults in hydraulic system of automatic grabbing beam.