The fault diagnosis of rolling bearings is of utmost importance in industrial applications to ensure mechanical systems' reliability, safety, and economic viability. However, conventional data-driven fault diagnosis techniques mainly depend on a pre-existing dataset with complete failure modes and knowledge to serve as the training data, which may not be available or accessible in some crucial industrial scenarios. This can limit the practicality of these methodologies in real-world industrial applications. This paper addresses this issue by developing a novel digital twin-enabled domain adversarial graph network (DT-DAGN). The main contributions of this paper are as follows: 1) the development of a comprehensive and accurate digital twin model for rolling bearings that includes a dynamic simulation of the bearing's operational status using only its structural parameters and failure severity/size to obtain the system's vibration response, and 2) the development of a novel graph convolutional network-based transfer learning framework to transfer knowledge from simulated datasets to measured datasets, enabling effective fault diagnostics of bearings with limited knowledge. A series of experiments are applied to validate the efficacy of the developed methodology.

Convolutional neural networks (CNN) have developed rapidly in recent years, which has greatly promoted the advancement of intelligent fault diagnosis. Most currently available CNN-based diagnostic models are developed under the presumption that the acquired mechanical signals are invulnerable to noise. However, transmission systems usually operate under fluctuating conditions (e.g., variable speed and strong noise scenarios), making the fault-related pulse information in the mechanical signal easily swamped by noise. Therefore, it is challenging for these existing approaches to achieve satisfactory results in industrial scenarios. To deal with this problem, an online knowledge distillation-based multiscale threshold denoising network (OKD-MTDN) is developed in this research work. The main innovations and contributions of this research work include: 1) introducing a novel convolutional module, called the Multiscale Convolutional Module (MCM), alongside a Global Attention Module (GAM), for extracting a range of discriminative features generated from mechanical signals; 2) designing a multi-dilated threshold denoising module (MTDM) to expand the receptive field and filter out interference features; 3) establishing an online knowledge distillation (OKD) algorithm to improve the generalization capability of OKD-MTDN. The hF-MS planetary gearbox dataset and the real-running high-speed rail dataset is utilized to verify the effectiveness of the proposed method. Experimental results show that the developed OKD-MTDN can achieve satisfactory results in various nonstationary scenarios.

Convolutional neural network (CNN)-based intelligent fault diagnosis approaches have showcased remarkable performance in the assessment of machine safety. The data monitored from mechanical systems in industries is primarily characterized by class imbalance. Nevertheless, most of the current CNN-based models are designed under the assumption of balanced sample distributions, which do not align with the prevalent conditions observed in real industrial scenarios. To tackle this challenge, a state-of-the-art multiattention-based feature aggregation convolutional network (MFACN) is developed in this study. The key contributions of this study are outlined as follows: 1) this study designs an attention-based multiscale module (AMM) and a multiscale feature aggregation module (MFAM) to facilitate comprehensive learning across multiple levels; 2) a robust CNN model based on AMM and MFAM is established. The constructed model can explore abundant information from mechanical signals; and 3) a dual focal loss (DFL) function is introduced to enhance diagnostic results under conditions of data imbalance. To assess the applicability of the proposed MFACN in machine health state identification, two experiments were conducted using the bearing dataset and the planetary gearbox dataset. The experimental results unequivocally show that MFACN surpasses seven other state-of-the-art approaches, especially when dealing with imbalanced datasets.