Feature extraction is crucial in intelligent fault diagnosis of rotating machinery. It is easier for convolutional neural networks(CNNs) to visually recognize and learn fault features by converting the complicated one-dimensional (1D) vibrational signals into two-dimensional (2D) images with simple textures. However, the existing representation methods for encoding 1D signals as images have two main problems, including complicated computation and low separability. Meanwhile, the existing 2D-CNN fault diagnosis methods taking 2D images as the only inputs still suffer from the inevitable information loss because of the conversion process. Considering the above issues, this paper proposes a new 1D-to-2D conversion method called Embedding Gramian Representation (EGR), which is easy to calculate and shows good separability. In EGR, 1D signals are projected in the embedding space and the intrinsic periodicity of vibrational signals is captured enabling the faulty characteristics contained in raw signals to be uncovered. The bridge connection is designed to improve the feature learning interaction between the two branches. Widely used open domain gearbox dataset and bearing dataset are used to verify the effectiveness and efficiency of the proposed methods. EGR-Net is compared with traditional and state-of-the-art approaches, and the results show that the proposed method can deliver enhanced performance. Introduction Bearings and gearboxes are critical components of rotating machines[1]. These machines often operate under varying speeds, loads, material conditions, maintenance procedures, and environments. Thus, performing effective fault diagnosis for the equipment through vibrational signal analysis is challenging and has received significant attention[2]. Intelligent fault diagnosis based on deep learning (DL) has demonstrated improved performance on fault classification. Many DL models such as CNNs [3][4], generative adversarial networks(GANs) [5], Deep Belief Networks (DBNs) [6], and transformers [7] are applied in fault diagnosis with promising results. Among those DL-based methods, the CNN model is developed to imitate the concept of visual human object recognition. CNN's feature extraction performance has been verified in many applications, such as image recognition [8] and video analysis [9].