Machinery typically operates under constantly changing working conditions in real-time production. Directly applying a diagnostic model, which has been trained solely on monitoring data from a single working condition, to a new unseen working condition poses a notably challenging task called single-source domain generalization (SSDG) fault diagnosis. Current research mainly aims to augment source-domain training samples but struggles to maintain health state information invariance for diverse augmented samples. Therefore, a targeted augmentation domain-mixed network (TADNet) is proposed in this paper for SSDG fault diagnosis of rotating machinery. The TADNet constructs a targeted augmentation chain, which generates samples in an augmented domain with different distributions from the source-domain samples through a chained generation structure, and ensures the semantic consistency of state features. Additionally, a domain random mixing strategy is established to synthesize a new mixed domain with diverse distributions, through probabilistically and randomly mixing the feature statistics of the samples from the source and augmented domains, for further augmentation of samples. The TADNet effectively balances the distribution diversity and semantic consistency of augmented samples in the course of model training. The superior diagnosis generalization ability of the proposed method to unseen working conditions is demonstrated on two rotating machinery datasets.

Difference mode decomposition (DMD) is proposed to accurately decompose the signal into health component, fault component and noise. However, DMD is only applicable to vibration signals containing a single fault and is extremely sensitive to interference from other components across all frequencies. In practical operating conditions, bearing damage typically manifests as complex compound faults with numerous intricate disturbances, which makes it challenging for DMD to accurately separate different fault components. To broaden the application prospects of DMD, this paper proposes a difference multi-modes decomposition (DMMD) method, aiming to achieve accurate diagnosis of complex compound-fault signals. Firstly, the center frequencies (CFs) and boundary frequencies (BFs) that indicate fault information are located by the spectral structure information analyzer (SSIA), and the modes containing fault information are selected via correlation kurtosis (CK). Secondly, The initial DMMD weight is set as the average of the difference between two normalized Fourier spectra to improve the efficiency and accuracy of the operation. Finally, Gaussian mixture model (GMM) is used to distinguish the rearranged optimal difference spectrum into three categories accurately and the optimal threshold can be obtained. Simulated and experimental results indicate the effectiveness and accuracy of the proposed method in practical application.

Unknown domain shift caused by the unavailability of target domain during training phase degrades the performance of intelligent fault diagnosis models in practical applications. Domain generalization (DG)-based methods have recently emerged to alleviate the influence of domain shift and improve the generalization ability of models toward invisible working conditions. However, most existing studies are conducted on multiple fully labeled source domains. Meanwhile, domain-specific information related to the variations of working conditions is often neglected during model training. Therefore, in order to realize reliable generalization fault diagnosis based on partially labeled source domains, this article proposes a contrast-assisted domain-specificity-removal network (CDSRN) to extract transferable features from domain-specificity-removal perspective. Concretely, a domain-specific feature removal branch is designed to disentangle domain-invariant features and domain-specific features, thus excavating generalized information only in domain-invariance dimension. Simultaneously, proxy-contrastive representation enhancement module is embedded to facilitate the fault class-discriminative and domain-discriminative feature learning, thereby assisting the model in further improvement of generalization capability. Experimental studies confirm the effectiveness and competitiveness of the proposed CDSRN in semi-supervised generalization fault diagnosis.

Machine learning models have been widely successful in the field of intelligent fault diagnosis. Most of the existing machine learning models are deployed in static environments and rely on precollected datasets for offline training, which makes it impossible to update the models further once they are established. However, in the open and dynamic environment in reality, there is always incoming data in the form of streams, including new categories of data that are constantly generated over time. In addition, the operating conditions of mechanical equipment are time-varying, which results in continuous stream data that are nonindependently and homogeneously distributed. In industrial applications, the diagnosis problem of nonindependent and identically distributed continuous streaming data is referred to as the cross-domain class incremental diagnosis problem. To address the cross-domain class incremental problem, a novel cross-domain class incremental broad network (CDCIBN) is proposed. Specifically, to solve the nonindependent identically distributed problem, a novel domain-adaptation learning loss function is first designed, which enables the conventional broad network to handle the category increment task well. Then, a cross-domain class incremental learning mechanism is designed, which learns new categories while retaining the knowledge of old categories well enough without replaying old category data. The effectiveness of the proposed method is evaluated through multiple mechanical failure increment cases. Experimental analysis demonstrates that the designed CDCIBN has significant advantages in the variable working condition class incremental application.

Aluminum electrolytic capacitors (AECs) are utilized as the key components in smart transformers (STs). The service status of the AEC is crucial for the maintenance of the ST. The capacitance ($C$) and the equivalent series resistance (ESR) are the key parameters to reflect the service status of AEC. Moreover, the values of$C$and ESR are negatively correlated. However, existing machine learning methods for identifying the parameters ($C$and ESR) of AEC do not consider the correlation between$C$and ESR. This reduces the accuracy of the parameter identification. This problem belongs to the exploring inter-target correlations in the field of multi-target regression. To address this issue, the low-rank double-scale convolutional neural network (LDCNN) is proposed to identify$C$and ESR. Specially, to preserve the feature structure, the fully connected layer in the traditional convolutional neural network is replaced by the tensor-train (TT) layer. And the low-rank constraint is implemented to the parameter of the TT layer to learn the correlation of$C$and ESR. The accuracy of the proposed LDCNN for the parameter identification is verified by simulation and experimental data, respectively. The validation results show that the accuracy of parameter identification can be effectively improved by learning the correlation between$C$and ESR.

Aluminum electrolytic capacitors (AECs) are utilized as the key components in power electronic transformers (PETs). The AEC degradation monitoring is crucial for the maintenance of PET. Degradation of AEC performance is often reflected by changes of capacitance (C) and equivalent series resistance (ESR). SinceCand ESR dominate the low- and mid-frequency impedance characteristics of the AEC, respectively, the features of the corresponding frequency bands of the respective signals need to be simultaneously extracted. However, the current studies on parameter identification of AECs have not focused on this issue. In this article, the double-scale convolutional autoencoder and extreme learning machine (DCAE-ELM) framework is proposed to identifyCand ESR based on AEC voltage. Specifically, DCAE extracts the low- and mid-frequency features of AEC voltages with large- and small-scale convolutional kernels, respectively. Then, ELM is employed to identifyCand ESR based on the features extracted by DCAE. Moreover, the mathematical mechanisms between the gradients and reconstructed data of DCAE with data concatenated in columns (cDCAE) and rows (rDCAE) are analyzed. Validation results of both simulation and experimental data have verified the data reconfiguration performance of rDCAE and the parameter identification capability of the proposed DCAE-ELM framework.

It is difficult to preserve diminishing weak structures and edges, and remove complex details simultaneously in the context of image smoothing. While most of existing methods only take either local or global features into consideration, the authors propose two methods taking advantage of both to achieve smoothing, both of which consist of two steps and share the same first step. In the first step, the authors use a scale‐aware approach to generate a guidance image by blurring the small‐scale components in the input image. Such approach, based on the rolling guidance framework with domain transform filter and bilateral filter, can prevent diminishing the corners of the main structures. Subsequently, the authors use the two proposed methods, with the guidance image as input, to remove blurry details. The first method introduces two data fidelity terms into L 0 gradient minimisation and removes high‐contrast details, which is a structure‐preserving method. The other method, an edge‐preserving method, uses an adaptive L 0 gradient minimisation technique, facilitating the preservation of the weak structures and edges. The smoothing factors in such technique are decide by the corresponding gradient of each pixel of the guidance image. The authors apply both methods to various image processing fields.

This paper proposes a wavelet-based statistical signal detection approach for monitoring and diagnosis of bearing compound faults at an early stage. The bearing vibration signal is decomposed by an orthonormal discrete wavelet transform to obtain its energy dispersions at multiple levels. We investigate the statistical properties of the decomposed signal energy under both the normal and faulty conditions, based on which a generalized likelihood ratio test is developed. An exponentially weighted moving average control chart is then constructed to detect faults at an early stage. Simulation studies and a real case study are conducted to demonstrate the effectiveness of the proposed method. Furthermore, the comparison studies show that the proposed method outperforms the empirical mode decomposition method and Hilbert envelope spectrum analysis method.

Shape matching has always been a key issue in the field of computer vision. To obtain high recognition accuracy with low time complexity and to reduce the influence of contour deformation due to noise in shape matching, a novel shape matching method based on common base triangle area (CBTA) is proposed. First, a CBTA descriptor of each contour point is defined based on the area functions of the triangles formed by its two neighbour points and other contour points. Then, the descriptor is locally smoothed to keep it more compact and robust to noise. Secondly, a match cost matrix is obtained by computing the CBTA descriptors of all the contour points on two shapes. Finally, the similarity between the two shapes is measured on the basis of the match cost matrix by a dynamic programming algorithm. The experimental results on MPEG‐7, Kimia and an articulation shape database indicate that this method is robust to contour deformation, and both the computational efficiency and the retrieval rate are essentially improved.