Data-driven fault diagnosis techniques utilizing deep learning have achieved widespread success. However, their diagnostic capability and application possibility are significantly reduced in real-world scenarios where fault modes are not fully covered and labels are lacking. Owing to potential conflicts of interest and legal risks, industrial equipment fault data usually exist in the form of isolated islands, making it difficult to carry out large-scale centralized model training. This paper proposes open-set federated adversarial domain adaptation (OS-FADA) to achieve collaborative evolution of fault diagnosis capabilities among cross-domain data owners while protecting privacy. The OS-FADA is a general fault diagnosis framework that employs two-phase adversarial learning. First, faced with the data distribution shift caused by variable working conditions, a generative adversarial feature extractor training strategy is designed to achieve domain-invariant fault feature extraction by approximating the feature distributions of clients to a unified generated distribution. Second, considering the label distribution shift of unknown faults occurring in the target client, an adversarial learning method is proposed to establish decision boundaries between known and unknown faults. Ultimately, the co-evolution of fault diagnosis models between clients is achieved by combining two-phase adversarial learning and federated aggregation. Results from an industrial gearbox case demonstrate that our proposed method achieves over 20% diagnostic accuracy improvement and has excellent potential for cross-domain fault diagnosis tasks with unknown faults when the data silos problem cannot be ignored.

Rapid and comprehensive fighter optimisation is an important part of modern combat decision-making. However, due to the numerous influencing factors, it is difficult for decision-makers to consider comprehensively and specify the optimal decision, and it is highly subjective, which leads to different decision conclusions from person to person. Therefore, to solve the above deficiencies in fighter selection, this paper proposes a sequential decision-making framework that comprehensively considers the effectiveness, maintenance, support capability and health status of the fighter aircraft. Based on the multi-dimensional state, it provides comprehensive and credible auxiliary support for commanders. The sequential decision-making framework (called GRA-VIKOR-IFNs) uses the combination of equation and fuzzy multi-criteria decision-making (FMCDM) to evaluate the effectiveness, support capability and health in turn, to complete the step-by-step selection of fighter models, troops and sorties. The evaluation equation is for the effectiveness evaluation and a hybrid method using the extended grey correlation analysis (GRA) and VlseKriterijumska Optimizacija I Kompromisno Resenje (VIKOR) method based on intuitionistic fuzzy numbers (IFNs) is for the support capability and health evaluation. The proposed strategy is in line with the logic and demand of actual combat and training decision-making and takes into account the influence of uncertain factors. Finally, a comparison with some classical methods is carried out, such as the full consistency method (FUCOM), the technique for order of preference by similarity to ideal solution (TOPSIS) and so on. The GRA-VIKOR-IFNs method is consistent with the results of other methods and the result sort resolution is 0.0619 and at least 40% higher than other methods, which can lead the commanders to a more reliable and clear decision.

The precise remaining useful life (RUL) prediction of turbofan engines benefits maintenance decisions. The training data quantity and quality are crucial for effective prediction modeling and accuracy improvement. However, the performance degradation process of the same type of turbofan engine usually exhibits different trajectories because of engines’ differences in degradation degrees, degradation rates, and initial health states. In addition, the initial part of the trajectory is a stationary health stage, which contains very little information on degradation and is not helpful for modeling. Considering the differential degradation characteristics and the requirement for accurate prediction modeling of the same type of turbofan engines with individual differences, we specifically propose a personalized transfer learning framework for RUL prediction by answering three key questions: when, what, and how to transfer in prediction modeling. The framework tries to maximumly utilize multi-source-domain data (samples of the same type of engines that run to failure) to improve the training data quantity and quality. Firstly, a transfer time identification method based on a dual-baseline performance assessment and the Wasserstein distance is designed to eliminate the worthless part of a trajectory for transfer and prediction modeling. Then, the transferability of each sample in the multi-source domain is measured by an approach, named the time-lag ensemble distance measurement, and then the source domain is ranked and adaptively deconstructed into two parts according to transferability. Ultimately, a new training loss function considering the transferability of the weighted multi-source-domain data and a two-stage transfer learning scheme is introduced into an informer-based RUL prediction model, which has a great advantage for long-time-series prediction. The simulation data of 100 of the same type of turbofan engine with individual differences and five comparison experiments validate the effectiveness and accuracy of the proposed method.

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.

Gearboxes play an important role in ensuring the reliability and operational safety of mechanical systems. Fault diagnosis for gearboxes has been widely studied in academic and industrial fields. However, a single algorithm with inherent randomness is often difficult to achieve accurate diagnosis due to noise and environmental fluctuations. To solve this problem, this paper adopts an ensemble learning approach. Ensemble learning can effectively improve classification accuracy and generalization ability by combining multiple diagnostic algorithms. In this study, a novel convolutional neural network (CNN)-based selective ensemble learning method for gearbox fault diagnosis is presented. First, an improved CNN algorithm based on the idea of information reuse is proposed, which has a stronger feature extraction ability than traditional CNN. In addition, the bagging method was used to generate differentiated basic learners based on the improved CNN. However, using too many base learners in ensemble learning may degrade classification accuracy. Therefore, the spectral clustering method is employed to realize basic learner pruning based on the theory that selective elimination of low-performance learners during ensemble learning can improve classification accuracy. Finally, Dezert-Smarandache (DSmT) theory is used to integrate the selected individual learners, and the final fault diagnosis result is obtained. The effectiveness of the proposed method was verified based on datasets collected from a gearbox test rig. The comparative test results show that the accuracy of the proposed ensemble fault diagnosis method for a gearbox is 99.375%, which is better than other comparative methods.