The increasing complexity and interconnectivity of modern process industry systems, particularly in critical infrastructure such as circulating water pump systems in nuclear and chemical plants, pose significant challenges for ensuring operational security and system-level situational awareness. Conventional deep learning models, while effective in temporal pattern recognition, exhibit limited capability in capturing spatial dependencies across heterogeneous sensor networks, thereby restricting their ability to represent dynamic system behavior. To address these limitations, this paper presents a novel method titled graph attention-based deviation network (GADN4SA) for circulating water system situational awareness. The proposed method dynamically constructs task-aware sensor graphs based on signal correlations, integrates both structural and semantic representations, and leverages attention-guided mechanisms to model long-range spatial-temporal dependencies. In addition, a structured deviation scoring module is incorporated to enable interpretable anomaly quantification and attribution. Extensive experiments on both simulated and real-world datasets demonstrate that the proposed method consistently outperforms state-of-the-art baselines in terms of robustness, accuracy, and generalization, highlighting its effectiveness for deployment in safety-critical industrial environments.

Mining excavators, transport vehicles, and other construction machinery, as well as energy equipment like nuclear power plant units, operate in complex and harsh environments, where high reliability and continuous operation are crucial. However, existing health monitoring methods have difficulty adapting their thresholds, leading to false alarms and missed detections. Additionally, the prediction accuracy of current health prognostics methods is still not up to expectations, and their reliability is insufficient. To address these issues, a dynamic adaptive Transformer-based method is proposed. In the health monitoring module, a dual-stage attention mechanism is introduced, which includes spatial and temporal attention, aimed at capturing the spatiotemporal features in the multi-source data and optimizing anomaly detection through dynamic threshold adjustments. To further improve prediction accuracy, a multi-scale multi-head attention mechanism is used, and Monte Carlo Dropout is applied to estimate the uncertainty of the prediction results. Furthermore, a dynamic adaptive fine-tuning mechanism solves the issue of prediction bias, making the predictions more aligned with actual operational trends. Experimental validation demonstrates that the proposed method performs excellently in anomaly detection and trend prediction, offering high engineering application value.

Due to coupled nonlinearities and complex measurement noise, assess the condition of the rotor system remains a challenge, particularly in cases where historical run-to-failure data is lacking. To this end, we proposed a hierarchical physics-informed neural network (HPINN) to identify/discover the ordinary differential equations (ODEs) of a healthy/faulty rotor system from noise measurements and then assess the rotor condition based on the discovered ODEs. Specifically, the ODEs of a healthy rotor system are first stably identified from noisy measurement through HPINN guided by rotor dynamics. Based on the identified healthy ODEs, the extra fault terms in the ODEs of the faulty rotor system are then sparsely regressed from the predefined library embedded in HPINN, in which the phase compensation and alternating training strategy are developed to guarantee training convergence. Moreover, with the mathematical terms of discovered fault, the potential fault and the health indicator (HI) are diagnosed and constructed to assess the condition of the rotor system, respectively. Finally, the effectiveness of the proposed method is verified with simulation and test bench datasets, showing the potential for practical industrial applications.Note to Practitioners—This paper investigates the health assessment problem (condition monitoring and fault diagnosis) of the rotor system, a critical component in large rotating machinery. The proposed HPINN provides a hierarchical framework to firstly identify the ODEs of healthy rotor system and then discover the ODEs of faulty rotor system with limited monitoring data (3-5 seconds data collected from sensor commonly, depending on the rotating speeds). With the mathematical terms of discovered fault, the fault can be diagnosed and a health indicator (HI) can be constructed to assess the condition of rotor system in a fully interpretative way. This approach is applicable to large rotating machinery in safety-critical industries, such as circulating water pumps.

The advancement of large models has initiated a transformation in the field of time-series forecasting. Both the repurposing of existing large models and the development of large models tailored for time-series analysis have exhibited impressive performance. In industrial applications, challenges, such as limited data availability and constrained computational resources, render the first approach viable. However, it is important to note that this approach is still in its infancy and lacks both a thorough technical analysis and a unified effective framework. Meanwhile, as large models become a mainstream artificial intelligence paradigm, it is urgent to discuss typical industrial scenarios, such as how automated systems can transition from intelligent to collaborative operation and maintenance. In light of this premise, this article endeavors to advance a generalized technical framework for large model-driven time-series forecasting, under which existing methods can be subsumed. Then, within this overarching technical paradigm, the technical advancements facilitated by diverse methods will be systematically elucidated and analyzed, along with a comparative evaluation conducted across seven benchmark datasets. Concluding this analysis, the implementation pathway for the industrial automation system is delineated that integrates operator action commands to forecast post-action trends to assess action correctness in advance. Finally, the challenges and future directions of large model-based time-series forecasting are outlined.

Nuclear safety technology arouses the concern of nuclear power works when historical nuclear accidents have proven irreversible environmental damage and bodily injury. Significantly, nuclear evacuation technology is one of the critical parts to guarantee public lives, exacerbated by the spatial and temporal uncertainties associated with unfixed routes, radiation distribution, and crowdedness in traffic. At present, large-scale nuclear evacuation falls into three challenges: 1) round-trip, 2) unfixed routes, and 3) dynamic radiation field. This article proposes a multistage vehicle planning model for evacuation time and individual dose optimizations under real-world constraints such as vehicle limits, evacuee demand, and number of evacuation times. The critical contributions include three stages: 1) optimizing the number of vehicles and vehicle schemes for round-trip, guaranteeing the evacuation of all personnel efficiently; 2) the next pick-up point is selected to minimum distance and dose for unfixed routes; and 3) vehicle routing is conducted of emergency response, featuring a dynamic programming by nondominant sorting genetic algorithm II with minimum time and individual dose. Therefore, the proposed model can provide recommended schedules, consisting of the number of vehicles, associated arrival, departure trips, and the exposure dose. With the actual data of the nuclear power plant in China, the case demonstrates the model's efficiency by comparing it with conventional solutions.

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.

Existing domain adaptation methods strive to align all domains equally under a single domain shift dimension, which poses two problems. On the one hand, multiaspect domain transferring factors and homogenous alignment may lead to suboptimal results in more distant domains. On the other hand, such a global alignment ignores local discriminatory information, making class boundary samples susceptible to misclassification. Hence, the three-types-of-graph-relational guided domain adaptation (TGGDA) is proposed. First, thedomain graphis formed based on condition-dependent slow variables. The domain discriminator is redesigned to reconstruct the domain graph. Second,intrinsicandpenalty graphsare integrated to draw the same class but different domains sample closer and vice versa. The TGGDA is a system-assisted cross-domain diagnosis method that enables multidimensional domain information measurable, and the adjacency alignment allows for more accurate diagnostic results. Finally, experiments on gearbox fault diagnosis in circulating water pumps show that TGGDA can improve diagnosis accuracy.

Remaining useful life (RUL) prediction is crucial for ensuring machine operating safety and reducing maintenance costs in nuclear power plants. Existing RUL prediction methods generally use run-to-failure data or known degradation mechanisms to establish a static model for degradation process characterization. However, the inherent degradation mechanisms of machines are time-varying, and a static model may only cover part of the degradation, resulting in an inaccurate RUL result. Hence, we propose an optimized online RUL prediction considering time-varying degradation mechanisms. The degradation model type (discrete variables) and boundary/initial conditions (continuous variables) are first set as the main variables affecting the approximation of the time-varying degradation mechanism. The RUL prediction is then formulated as a feedback-decision process through interacting with the anomaly data stream, in which variables are jointly optimized with reinforcement learning by minimizing the approximation error. Based on the degradation model established with optimized variables, the RUL can finally be deduced. The proposed method is validated by a run-to-failure dataset collected in a nuclear circulating water pump test bench.

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.

Insufficient spatio-temporal feature extraction in normalizing flows (NFs) based anomaly detection (AD) method impedes their performance improvement. Moreover, it is worth noting that the multioperational nature of the process poses a challenge for most AD methods, including those based on NF, rendering them largely ineffective. Hence, this article introduces a new method called spatial-temporal graph conditionalized normalizing flows (STGNFs). First, multiscale dilation convolutional layers and mix-hopping graph convolutional layers are interleaved to form a spatio-temporal feature extractor. Second, spatio-temporal features are employed as conditional information for NF, while scheduling variables are factored in to adapt to operating conditions. Then, tracing the anomaly variables through the conditional density magnitude allows for interpretable AD results. Finally, experimental results on four datasets, including high-fidelity experimental bench data and real nuclear power plant data, demonstrate the performance of STGNF. STGNF enables the detection and precise localization of anomalies in various power modes, including nuclear plant shutdown and peaking, transcending the limitations of existing methods.

Domain adaptation can transfer cross-domain diagnosis knowledge by minimizing the divergence of labeled source and unlabeled target data. However, the model neglects to maximize physics prior knowledge during feature extraction and distribution alignment, resulting in a noninterpretable model even negative transfer. Hence, a physics-informed domain adaptation network, termed adaptive fault attention residual network (AFARN), is proposed. First, an adaptive fault attention mechanism is designed to refine features guided by bearing fault characteristics, suited to generating diagnosis-relevant features. Then, several metrics are applied to minimize the marginal and conditional distribution discrepancy of features, thus, generalizing the model from source to target domain. The AFARN utilizes the fault characteristics and label information simultaneously to train the model, which can enhance the distribution alignment of diagnosis-relevant features, thus, providing an interpretable knowledge transfer. Finally, experiments on public and circulating water pump datasets show that AFARN can enhance fault feature learning and diagnosis accuracy.