Domain Generalization (DG) has been explored to achieve machine fault diagnosis under previously unseen operating conditions. However, most DG methods assume access to training data collected across multiple conditions, an assumption that rarely holds in industrial practice, where fault data are typically available from only a single operating condition. To address this critical constraint, we propose an attention-throughout latent diffusion model for single-source domain generalization (ATLD-SSDG). The proposed framework learns discriminative fault representations from a single-condition source domain and generalizes robustly to multiple unseen target conditions. First, to effectively capture complementary fault information, vibration signals from three views are fused and projected into a latent space via a collaborative attention fusion mechanism. Next, a dedicated one-dimensional (1D) U-Net is constructed to address information loss in existing approaches and facilitate more effective conditional diffusion. Unlike existing methods that directly adopt computer vision diffusion architectures, the proposed 1D U-Net is specifically designed for vibration signals, preserving localized fault-related details and preventing information loss caused by time–frequency transformations. Moreover, by explicitly regulating self-attention and cross-attention within the diffusion model, the framework preserves fault-relevant characteristics while selectively substituting operating-condition-related factors, thereby enabling controllable and effective domain generalization. Extensive experiments demonstrate superior generalization performance and diagnostic accuracy of the proposed method over state-of-the-art DG methods. These results indicate that latent diffusion, when properly structured for 1D condition-monitoring signals, provides an effective mechanism for single-source domain generalization, helping to close an important gap in DG research for predictive maintenance.

Zero-shot fault diagnosis (ZSFD) faces significant challenges in aligning time-series signal features and contextual semantic information. Direct projection from feature space to semantic space may suffer from domain bias, while mutual projection approaches require complex tradeoffs among multiple objective functions. This article proposes a multiattribute cross-modal semantic alignment network (MCSANet) for ZSFD. An enhanced feature extractor incorporating a conditional fault severity encoding mechanism is employed to extract discriminative fault features across multiple attributes. The time-series features, and contextual semantic information are then aligned using a novel cross-modal embedding approach, eliminating the need for complex tradeoffs among multiple objective functions. The proposed method was validated on both self-designed and open-source bearing experiments. Experimental results demonstrate that MCSANet achieves robust diagnosis performance even under nonstationary operational conditions and limited distributional diversity in the training phase. Comparative experiments confirm that MCSANet outperforms current state-of-the-art approaches.

In modern industrial processes, class imbalance occurs when there is a significant disparity in the number of instances between different classes. Current approaches for handling this problem cannot work effectively due to the invalid instance replenishment strategy for rare categories and even exacerbate class imbalance issues. Therefore, this work presents a novel semi-supervised fault diagnosis (FD) method to address imbalances in FD data by leveraging extensive unlabeled samples. Inspired by adversarial discriminative domain adaptation learning, the proposed approach includes a distribution alignment model for extracting domain-invariant fault features from unlabeled data. Additionally, a soft threshold selection strategy is introduced to strategically select unlabeled fault samples, ensuring an abundance of samples for rare categories and enriching their distribution. Extensive experiments on the two industrial process datasets, including a real-world hot rolling of steel process and a well-established public Tennessee Eastman process, demonstrate the effectiveness of the proposed method in alleviating imbalances and utilizing unlabeled samples, establishing its superiority over existing methods. The code is publicly available onhttps://github.com/Ticuby/SFDM.

Health state prediction and fault time prediction are two key tasks in the fault prediction field. However, existing fault prediction techniques perform these tasks hierarchically and separately without considering the time-varying dynamics of the system operation process, which reduces the prediction efficiency and accuracy. Therefore, a Gaussian process regression prediction method based on the update strategy is proposed for the dual tasks of aeroengines. In this method, for new samples collected continuously, the predictive distributions are deduced and the model parameters are updated. Specifically, through variable selection and multivariable fusion technology, the most beneficial variables corresponding to the health state are used to construct a shared health index for health state and fault time prediction. The proposed health index can better characterize the health state. Then, by the update strategies including single-point and multipoint update strategies, a unified Gaussian process regression framework with newly collected samples information is obtained. Thereby, the health index and fault time prediction are realized synchronously. Experimental results on the commercial modular aero-propulsion system simulation dataset demonstrate that the proposed method outperforms state-of-the-art ones.

The scarcity of fault samples is a common scenario in the field of fault diagnosis. In the context of mechanical fault diagnosis, the emergence of new working conditions and fault modes renders the availability of samples of target (unseen) faults for model training unfeasible, thus limiting the performance of data-driven methods. Consequently, zero-sample learning and diagnosis of mechanical faults is a challenging task. In this regard, this article proposes a multiattribute learning model, inspired by the zero-shot learning paradigm, for zero-sample mechanical fault diagnosis. The key lies in the shared multiclass attribute classifiers. During the attribute learning process, a convolutional neural network is developed to construct multiclass attribute classifiers, which serve as a mapping between visual features and semantic features. These classifiers are transferred from readily available faults to enhance the capability of diagnosing unseen faults. By minimizing the difference among the fault attributes, the diagnosis of unseen faults is achieved, which includes fault location, size, working load, etc. Experiments on two real datasets verify the efficacy and the superiority of the proposed method.

Zero-sample fault diagnosis (ZSFD) achieves remarkable success and has attracted considerable attention. However, existing methods suffer from the limitations in fault attribute labeling and feature extraction, leading to poor generalization and robustness. To be specific, fault attribute labeling that depends on expert knowledge is time-consuming and laborious. Fault feature extraction is carried out in one projecting space, and the useful knowledge of target data is ignored, which results in nonoptimal ZSFD performance. To tackle the above problems, a novel ZSFD based on transfer learning is proposed. First, a shared knowledge dictionary that automatically learns from source data with labels is transferred into the target data, which reduces the dependence of ZSFD on fault description. Second, a novel multiclass space projection model is designed to obtain the discriminative fault features. Finally, the pseudolabel mechanism is introduced to excavate the interclass and intraclass information in the target domain. The experiment results on the Tennessee–Eastman process and a real hot roll of steel process show the effectiveness of our method as well as its superiority.

Principal component analysis (PCA) is one of the most successful unsupervised subspace learning methods and has been used in many practical applications. To deal with the outliers in real-world data, robust principal analysis models based on various measure are proposed. However, conventional PCA models can only transform features to unknown subspace for dimensionality reduction and cannot perform features’ selection task. In this article, we propose a novel robust PCA (RPCA) model to mitigate the impact of outliers and conduct feature selection, simultaneously. First, we adopt$\sigma $-norm as reconstruction error (RE), which plays an important role in robust reconstruction. Second, to conduct feature selection task, we apply$\ell _{2,0}$-norm constraint to subspace projection. Furthermore, an efficient iterative optimization algorithm is proposed to solve the objective function with nonconvex and nonsmooth constraint. Extensive experiments conducted on several real-world datasets demonstrate the effectiveness and superiority of the proposed feature selection model.

In recent years, the field of online learning has received considerable attention for addressing the challenges associated with evolving features in fault diagnosis. Existing methods often assume that the dynamics of the feature space are predictable. However, in reality, the change of features is unpredictable, and the appearance or disappearance of features can occur arbitrarily. This presents a significant challenge for learning algorithms to adapt and effectively learn from such data. In this paper, we propose a novel online learning method called Kernelized Online Perceptron-based Online Fault Detection (KOGD) to address the challenge of feature appearance or disappearance in industrial systems. Our proposed model treats each variant of features as a distinct feature set and utilizes multiple kernel gradient descent methods to process them individually. This approach enables the detection of both new and disappearing fault signatures. To improve computational efficiency, we introduce a support vector selection mechanism and a strategy to control the number of cores used in the model. This helps reduce the computational complexity associated with kernelization, making our method more scalable and practical. Additionally, we devise a method to optimize the update of the fault detection model by incorporating historical information from the deleted kernelized perceptrons into the newly selected kernelized perceptrons. This integration allows the model to leverage past knowledge and enhance its performance. Through experimental evaluation on the TEP dataset, the proposed method achieves an accuracy of 89.73 %. The experimental results highlight the effectiveness of the proposed method in handling the changing characteristics of industrial systems and achieving efficient fault detection in realtime.

This study investigates the sample value imbalance problem of process monitoring. A fault detection approach based on variable selection and support vector data description (SVDD) is developed for efficient process monitoring. First, Kullback–Leibler divergence serves as the variable selection algorithm, which highlights the most beneficial information about the concerned faults. The attained variables are segmented by block division to avoid faults information being covered in single space monitoring, so that the relevant variables and the most beneficial information are concentrated in the same block. Then, Kernel principal component analysis is applied in each block to address the challenge that variables may still be high-dimensional and nonlinear. After that, the monitoring result is given based on the proposed SVDD with a restructured radius index, which is more sensitive to the fault. As demonstrated from experimental results on the Tennessee Eastman process, this method is effective and outperforms counterparts with higher mean fault detection rate. Note to Practitioners—Recently, multivariate statistical process monitoring (MSPM) has attracted much attention. In general, MSPM incorporates all variables for the large-scale process. However, only a small number of variables are fault-dependent. Namely, the sample value imbalance problem is encountered in application. In this scenario, the monitoring performance degrades and the online computational complexity increases. To this end, a SVDD-based fault detection method, which considers the fault-related variables, is proposed for process monitoring. The proposed method is verified by the Tennessee Eastman process and it is more sensitive to the concerned fault.

Incremental learning-based fault diagnosis is effective to learn from continuous industrial data on an ongoing basis. However, in the case of nonstationary industrial processes, new data distribution often gradually shifts away from that of historical data, due to equipment aging and manufacturing strategies. Thus, conventional incremental methods with the identical independent distribution (i.i.d.) assumption may no longer promise satisfied diagnosis performance. This article concerns the conditional drift phenomenon, a relaxation of the i.i.d. assumption, in which the conditional distribution of industrial data changes within different time. From a mathematical point of view, we first give the problem formulation of conditional drift and introduce a target mapping strategy for drift adaptation, under the minimum risk criteria. Then, following this strategy, an incremental diagnosis model with adaptation ability is designed. Particularly, a transformation matrix keeps matching the distributions of historical and new data. Thus, our method can quickly adapt to the conditional drift and be more robust against evolving environment. The proposed method is applied for diagnosing faults in two industrial processes to demonstrate its effectiveness.