Aiming at the typical non-stationary and non-linear characteristics of rolling bearing vibration signals,a multi-scale convolutional neural network method for bearing fault diagnosis based on wavelet transform and one-dimensional convolutional neural network was proposed.The signal was decomposed into multi scale components with wavelet transform,and then each scale component was reconstructed.The reconstructed signal was subjected to the Fourier transform to obtain the frequency spectrum representation,which was used as the input of the one-dimensional convolutional neural network.Finally,one-dimensional convolution neural network was used to learn the features of the input data and recognize the bearing fault.The performance of the model was verified by using 10 state data sets of rolling bearing.The results show that this method can avoid manual feature extraction and obtain a promising 99.94% diagnostic accuracy.