Bearings are vital components of a rotary machine. Real-time fault diagnosis of bearings has great significance in the maintenance of equipment. Current vibration-based fault diagnosis methods rely on the usage of long time series data to reduce the influence of noise but often suffer from imbalances in datasets, significantly affecting diagnosis accuracy. In this paper, a fault diagnosis method based on Intertemporal Return Plot and data augmentation is proposed. The Intertemporal Return Plot is employed to transform one-dimensional time series data into two-dimensional images. The Wasserstein Generative Adversarial Network is employed to generate synthetic images for data argumentation. This approach helps reduce the influence of data imbalance, thereby improving the accuracy and convergence speed of the fault diagnosis. Comparisons with existing well-known methods are performed to demonstrate the effectiveness of the proposed method. The results show that the proposed method achieves a high accuracy of fault diagnosis for short time series data. An inverse transformation is also proposed to convert the images to time series data.

The rolling bearing is a critical part of rotating machinery and its condition determines the performance of industrial equipment; it is necessary to detect rolling bearing faults as early as possible. The traditional methods of fault diagnosis are not efficient and are time-consuming. With the help of deep learning, the convolution neural network (CNN) plays a huge role in the data-driven methods of bearing fault diagnosis. However, the vibration signal is non-stationary, contains high noise, and is one-dimensional, which is difficult to analyze directly by the CNN model. Considering the multi-domain learning as an advantage of deep learning, this paper proposes a novel rolling bearing fault diagnosis approach using an improved one-dimensional (1D) and two-dimensional (2D) convolution neural network (CNN) of two-domain information learning. The constructed fault diagnosis model combining 1D and 2D CNN extracts the fault features from the two-domain information of bearing fault samples. The padding and dropout technology are utilized to fully extract features from the raw data and reduce over-fitting. To prove the validity of the proposed method, this paper performs two tests with two bearing datasets, the Case Western Reserve University (CWRU) bearing dataset and the Dalian University of Technology (DUT) vibration laboratory dataset. The experimental results show that our proposed method achieves high recognition accuracy of rolling bearing fault states via two-domain learning of monitoring data, and there is no manual experience necessary. Vibration data under strong noise were also used to test the method, and the results show the superiority and robustness of the proposed method.