Effective fault diagnosis is essential to ensure the safe and reliable operation of equipment. In recent years, several transfer learning-based methods for diagnosing faults under variable working conditions have been developed. However, these models are designed to completely match the feature distributions between different domains, which is difficult to accomplish because each domain has unique characteristics. To solve this problem, we propose a framework based on the maximum classifier discrepancy with marginal probability distribution adaptation that focuses on task-specific decision boundaries. Specifically, this method captures ambiguous target samples through the predicted discrepancy between two classifiers for the target samples. Furthermore, marginal probability distribution adaptation facilitates the capture of target samples located far from the source domain, and these target samples are brought closer to the source domain through adversarial training. Experimental results indicate that the proposed method demonstrates higher performance and generalization ability than existing fault diagnosis methods.

The speed of rotating parts is often affected by different working conditions in mechanical equipment, which results in more complications in the feature mapping relationship. However, existing methods that address the large fluctuation problem in rotational speed have been formulated merely to improve test accuracy and do not consider the effects of irregular fluctuation frequency on the fault samples located at the class boundary. Thus, to distinguish the health conditions under frequent or irregular fluctuation speeds, this paper explores an enhanced sparse filtering (SF) algorithm based on maximum classifier discrepancy to diagnose the fault conditions caused by speed fluctuation. It considers the superiority of the task-specific decision boundary and adversarial training for the fault diagnosis network. Unlike traditional SF methods, the proposed framework introduces the Wasserstein distance to reduce the domain discrepancy between the source domain and the target domain and then uses the probability output discrepancy of the classifier to locate the fuzzy fault samples on the class boundary. This paper conducts theoretical analysis and experimental comparison and verifies the performance advantages of the framework through bearing and gear experiments under large speed fluctuation conditions. The proposed model also shows an excellent performance even when the speed fluctuates frequently.

Domain adaptation (DA)-based methods for fault diagnosis (FD) of rotating machinery have achieved impressive results in recent years. Most methods hold the assumption that the source domain (SD) and target domain (TD) share the same label space, which is not always satisfied in actual situations. A more practical scenario called partial domain adaptation (PDA) needs to be given more attention, where the transferable knowledge learned from a larger SD is applied to a smaller but relevant TD. A PDA method called class-weighted alignment-based transfer network (CWATN) is proposed in this article to adapt this scenario. A novel weighting method is designed to adapt the data distributions of shared classes. Except for weighted class-level alignment, global-level feature adaptation is also considered to learn more general transferable knowledge. Moreover, a domain discrepancy learning block is plugged in the shared classifier as a residual block, which could enforce the network to learn and measure the discrepancy between SD and TD explicitly, thus improving the result of DA. Three case studies are implemented to verify the superiority of CWATN. Results demonstrate that the proposed method could obtain better diagnostic performance than the selected competitive methods in the PDA scenario.

Domain adaptation-based models for fault classification under variable working conditions have become a research focus in recent years. Previous domain adaptation approaches generally assume identical label spaces in the source and target domains, however, such an assumption may be no longer legitimate in a more realistic situation that requires adaptation from a larger and more diverse source domain to a smaller target domain with less number of fault classes. To address the above deficiencies, we propose a partial transfer fault diagnosis model based on a weighted subdomain adaptation network (WSAN) in this paper. Our method pays more attention to the local data distribution while aligning the global distribution. An auxiliary classifier is introduced to obtain the class-level weights of the source samples, so the network can avoid negative transfer caused by unique fault classes in the source domain. Furthermore, a weighted local maximum mean discrepancy (WLMMD) is proposed to capture the fine-grained transferable information and obtain sample-level weights. Finally, relevant distributions of domain-specific layer activations across different domains are aligned. Experimental results show that our method could assign appropriate weights to each source sample and realize efficient partial transfer fault diagnosis.

As a practical tool for big data processing, deep learning not only has drawn extensive attentions in the inherent law and representation level of sample data, but also has been widely concerned in the field of mechanical intelligent fault diagnosis. In deep learning models, autoencoder (AE) and its derivative models can automatically extract useful features from big data, and many researchers have successfully applied them to the field of intelligent fault diagnosis. However, these studies always neglect two important points as follows: (1) the model training process will not be ideal when the original training dataset is insufficient; (2) the learning content of the network model is not clear. In order to surmount the above deficiencies, this paper proposes a novel framework named Data-enhanced Stacked Autoencoders (DESAE), which consists of a data enhancement module and a fault classification module. In the data enhancement module, SAE is adopted to generate simulated signals to strengthen the insufficient training data. In the fault classification module, the enhanced dataset is used to train another SAE model for fault type recognition. Meanwhile, two bearing datasets are employed to validate the efficiency of the proposed method. The experimental results show that the proposed method is superior to the method without enhanced data. In addition, the visual analysis of the learning characteristics in each layer of DESAE is presented, which is helpful to understand the working process of DESAE.

With the development of precision sensing instruments and data storage devices, the fusion of multi-sensor data in gearbox fault diagnosis has attracted much attention. However, existing methods have difficulty in capturing the local temporal dependencies of multi-sensor monitoring information, and the inescapable noise severely decreases the accuracy of multi-sensor information fusion diagnosis. To address these issues, this paper proposes a fault diagnosis method based on dynamic graph convolutional neural networks and hard threshold denoising. Firstly, considering that the relationships between monitoring data from different sensors change over time, a dynamic graph structure is adopted to model the temporal dependencies of multi-sensor data, and, further, a graph convolutional neural network is constructed to achieve the interaction and feature extraction of temporal information from multi-sensor data. Secondly, to avoid the influence of noise in practical engineering, a hard threshold denoising strategy is designed, and a learnable hard threshold denoising layer is embedded into the graph neural network. Experimental fault datasets from two typical gearbox fault test benches under environmental noise are used to verify the effectiveness of the proposed method in gearbox fault diagnosis. The experimental results show that the proposed DDGCN method achieves an average diagnostic accuracy of up to 99.7% under different levels of environmental noise, demonstrating good noise resistance.