In practical engineering, the vibration-based fault diagnosis with few failure samples is gaining more and more attention from researchers, since it is generally hard to collect sufficient failure records of centrifugal pumps. In such circumstances, effective feature extraction becomes quite vital, since there may not be enough failure data to train an end-to-end classifier, like the deep neural network (DNN). Among the feature extraction, the entropy combined with signal decomposition algorithms is a powerful choice for fault diagnosis of rotating machinery, where the latter decomposes the non-stationary signal into multiple sequences and the former further measures their nonlinear characteristics. However, the existing entropy generally aims at processing the 1D sequence, which means that it cannot simultaneously extract the fault-related information from both the time and frequency domains. Once the sequence is not strictly stationary (hard to achieve in practices), the useful information will be inevitably lost due to the ignored domain, thus limiting its performance. To solve the above issue, a novel entropy method called time-frequency entropy (TfEn) is proposed to jointly measure the complexity and dynamic changes, by taking into account nonlinear behaviors of sequences from both dimensions of time and frequency, which can still fully extract the intrinsic fault features even if the sequence is not strictly stationary. Successively, in order to eliminate the redundant components and further improve the diagnostic accuracy, recursive feature elimination (RFE) is applied to select the optimal features, which has better interpretability and performance, with the help of the supervised embedding mechanism. To sum up, we propose a novel two-stage method to construct the fault representation for centrifugal pumps, which develops from the TfEn-based feature extraction and RFE-based feature selection. The experimental results using the real vibration data of centrifugal pumps show that, with extremely few failure samples, the proposed method respectively improves the average classification accuracy by 12.95% and 33.27%, compared with the mainstream entropy-based methods and the DNN-based ones, which reveals the advantage of our methodology.

With the rapid development of more-electric and all-electric aircraft, the role of power supply systems in aircraft is becoming increasingly prominent. However, due to the complex coupling within the power supply system, a fault in one component often leads to parameter abnormalities in multiple components within the system, which are termed associated faults. Compared with conventional faults, the diagnosis of associated faults is difficult because the fault source is hard to trace and the fault mode is difficult to identify accurately. To this end, this paper proposes a graph-matching approach for the associated fault diagnosis of power supply systems based on a deep residual shrinkage network. The core of the proposed approach involves supplementing the incomplete prior fault knowledge with monitoring data to obtain a complete cluster of associated fault graphs. The association graph model of the power supply system is first constructed based on a topology with characteristic signal propagation and the associated measurements of typical components. Furthermore, fault propagation paths are backtracked based on the Warshall algorithm, and abnormal components are set to update and enhance the association relationship, establishing a complete cluster of typical associated fault mode graphs and realizing the organic combination and structured storage of knowledge and data. Finally, a deep residual shrinkage network is used to diagnose the associated faults via graph matching between the current state graph and the historical graph cluster. The comparative experiments conducted on the simulation model of an aircraft power supply system demonstrate that the proposed method can achieve high-precision associated fault diagnosis, even under circumstances where there are an insufficient number of samples and missing parameters.

In recent years, multitask learning (MTL) has attracted the increasing focus in the field of mechanical fault diagnosis. Relevant research shows that the MTL-based fault diagnosis frameworks generally achieve more satisfactory performance than the single-task ones. The key to promoting the above MTL frameworks is how to assign the task weights to balance the model training among multiple tasks. However, this issue has not received sufficient attention. In these frameworks, the task weights are generally statically assigned by manual predefinition or simple grid search, which is thus unable to provide the real-time guidance for the model training. In this regard, this paper aims to integrate the multitask model parameters update and task weights assignment into a collaborative training procedure via a gradient-based approach. To this end, we propose a constrained bi-level gradient optimization (C-BLGO) algorithm. For each training epoch, C-BLGO can adaptively optimize the real-time task weights through the task-level and layer-level gradients calculated from the dynamically updated multitask model. In addition, C-BLGO can integrate prior task priorities to modify real-time task weights within constrained range, so as to make the task weights assignment more controllable and targeted. Subsequently, these assigned task weights further provide the real-time guidance for the update of the entire multitask model. The proposed framework makes the training dynamics well controlled and thus brings satisfactory performance gains. The experimental results on three public datasets and an electromechanical measurement system, demonstrate that our work can better improve the training stability and fault diagnosis accuracy compared to other mainstream MTL methods. Thanks to the model-independent characteristics, C-BLGO is scalable to various model architectures and thus is adapted to different fault diagnosis scenarios.

Accurately predicting the remaining useful life (RUL) of rotating machinery, such as bearings, is essential for ensuring equipment reliability and minimizing unexpected industrial failures. Traditional data-driven deep learning methods face challenges in practical settings due to inconsistent training and testing data distributions and limited generalization for long-term predictions.