Aiming at the difficulty of manual feature extraction and the poor performance of shallow fault diagnosis models, a deep fault diagnosis model based on one-dimensional convolutional neural network (1D-CNN) and residual connection was proposed.A bearing vibration signal was input into the network, then the feature can be automatically extracted by one-dimensional convolution layers with residual connection.The residual connection can not only extract deep features and input it into the deep network layer, but also preserve the features extracted from the shallow layer.Compared with the 1D-CNN network without residual connection, it can obtain more abundant feature information.A Softmax layer was designed to classify the fault type of the vibration signal and output the result.By designing different diagnosis models, the validity of the 1D-CNN network with residual connection in the bearing fault diagnosis was verified, and finally it is proved that the residual connection can effectively improve the fault diagnosis results.