Ensuring reliable machine operation is dependent on effective fault detection. Feature indicators construction is considered as the foundation for operational condition assessment among various detection methods. However, the nuclear circulating water pump (NCWP) experiences severe disturbances due to noise and changes in operating conditions. Additionally, the complex movement of the gears causes signal interference, which may result in the feature indicators failing. To address the above issues, this paper proposes a generalized features construction method (GFC) to realize unsupervised planetary gearbox fault detection. First, a feature relevance evaluation method is presented to filter intrinsic mode functions (IMFs) obtained through ensemble empirical mode decomposition (EEMD) for noise reduction. Second, feature indicators are constructed based on interpretable frequency information. Then, global and local features are evaluated respectively to realize fault detection and further detection of faults from the sun or planetary gears. Finally, the effectiveness of the proposed method is demonstrated through data obtained from the NCWP test bench.

Journal bearings are the key components of the nuclear circulating water pump (NCWP), and accurate remaining useful life (RUL) prediction is of great significance for improving the reliability, safety, and maintenance planning of NCWP. However, it is difficult to quantify the uncertainty of bearing RUL based on the current deep learning (DL) model, resulting in a lack of credibility and effective convincing for RUL predicted by the model. Meanwhile, all existing hybrid models are basically simple combinations, and they cannot solve the uncertainty quantification problem of RUL predicted by DL. Hence, the bearing RUL prediction method based on a dynamic interactive hybrid model is proposed. First, a degradation model based on a nonlinear enhanced generalized Wiener process (EGWP) is proposed, which combines gated neural networks and time-varying drift coefficients to describe the nonlinear degradation process of bearing. Then, a corrective gated recurrent unit (CGRU) network is designed to learn and predict real-time degradation increments, and the parameters of the degradation model are dynamically updated through the history and prediction of degradation increments. Finally, the bearing RUL prediction is given by the CGRU network, and the probability density function of RUL is given by the proposed hybrid model. The performance of the proposed method is evaluated using the PHM 2012 bearing dataset and the NCWP journal bearing dataset. The results show that our proposed method can effectively predict bearing RUL and its uncertainty.

Machinery remaining useful life (RUL) prediction has important guiding significance for prognostics and health management. In order to improve the prediction accuracy of the RUL prediction model under different working conditions, the transfer method on domain adaptation (DA) has achieved preliminary results. However, on the one hand, the existing DA methods mostly use a single vibration signal to predict RUL, resulting in low model robustness. On the other hand, DA methods force transfer without considering the degradation information specific to the target domain, resulting in negative transfer. To solve the above problems, a degradation prior assisted multisource information fusion domain adaptive method is proposed for cross-domain RUL prediction. In this method, the multisource information fusion is realized by introducing the convolution neural network with a multidimensional attention mechanism, and comprehensive degradation features are obtained. Then, the degradation prior information of the target domain is fused with the multisource degradation characteristics in a weak supervision way, so as to retain the unique degradation features of the target domain. Finally, the cross-domain RUL prediction is realized by improved long short-term memory neural network. The performance of the proposed method is verified by the commercial modular aero-propulsion system simulation dataset and nuclear circulating water pump bearing dataset. The results show that the proposed method has better accuracy and generalization ability than the existing methods.

Real-time and accurate prediction of remaining useful life (RUL) is important to safe operation and maintenance (O&M) planning of mechanical equipment. However, the uncertainty of online RUL prediction is difficult to predict with most current deep learning (DL)-based methods, making the prediction results difficult to convince. Furthermore, the offline-trained DL model is unable to adaptively update the network parameters online when acquiring new data, leading to a decrease in RUL prediction accuracy. To overcome these problems, an innovative approach based on the incremental contrast hybrid model is proposed for online RUL prediction with uncertainty quantification, which combines the contrastive learning transformer (CLformer) with the enhanced generalized Wiener process (EGWP) to describe trends in mechanical degradation. First, a CLformer is developed for online trend prediction, and an incremental contrastive learning strategy is designed for online adaptive updating of CLformer parameters to reduce prediction offset errors. Then, the degradation increments within the EGWP state-space equations are predicted online by the proposed CLformer network for online updating of EGWP parameters. Finally, online prediction of the machine RUL is provided by the CLformer, whereas the hybrid model provides the probability density function of RUL. The effectiveness of the proposed method is verified using two publicly available datasets and the journal-bearing dataset of the nuclear-circulating water pump. The results demonstrate the ability of the proposed method to dynamically update model parameters when new data are acquired online while giving the RUL prediction values and uncertainties.

Unsupervised anomaly detection methods, either reconstruction-based or prediction-based, determine anomalies based on residuals. Occasional mutations in a single variable can cause the residuals to exceed the limits. Indeed, such mutations are not variations in the operating mechanism of the system. Thus, system-level anomalies are challenging to characterize. Complex networks (or “graphs”) are well adapted for modeling and characterizing the laws of evolution of complex systems. However, most industrial scenarios are without graphs. Hence, a self-supervised variational graph autoencoders (SS-VGAE) method is proposed. First, the multisource sensor dynamic graph is constructed through detrended cross-correlation analysis. Second, target and self-supervised learning tasks are designed. The target task is to reconstruct the input graph structure to minimize the reconstruction loss. The self-supervised task is to learn the optimal center of the hypersphere in the latent space such that the mean features are gathered towards the center as much as possible. Multi-task joint optimization allows high and low- dimensional space features to be considered simultaneously, thereby improving the reliability of anomaly scores. Then, the distribution of anomaly scores is calculated and integrated into a system health indicator (HI). The system HI is more applicable to assist decision-making. Finally, the superiority of the proposed method, namely better detection accuracy and robustness, is demonstrated by nuclear PCTRAN simulation data and SKAB data. Last but not least, systematic anomalies are found to make the correlation between the variables stronger.

Deep learning (DL) has demonstrated splendid performance in fault diagnosis with sufficient samples and ideal operating environments. However, in practice, it is hard to acquire adequate fault samples from high-reliability equipment, thus inducing challenges in applying DL for intelligent diagnosis. Moreover, data distribution shift occurs due to working load variation or environment noise interference, severely degrading DL models’ performance. Aiming at the above problems, this paper proposes a method called Q networks calibrated ensemble (QCE). Specifically, two improved deep Q networks are employed to enhance the attention to critical feature samples and fault samples by quantifying feature distribution and utilizing fault prior knowledge. Afterward, the calibrated Choquet integral is adopted to achieve the models’ ensemble, further enhancing the generalization ability and robustness of the diagnosis results. The proposed method has been verified on the NCWP test bench. Results indicate the superiority and reliability of the QCE method. Besides, results when working load changes demonstrate the outstanding generalization ability of the proposed method for cross-domain fault diagnosis with class imbalance. Furthermore, Grad-CAM visualization verifies that the proposed method effectively learns fault features instead of noise.