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.

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.

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.

Many optimization problems for heating, ventilation, and air conditioning (HVAC) control systems usually refer to multiple timescales. This paper studies a two-timescale decision problem for indoor temperature regulation by HVAC with the objective to improve user's comfort under limited energy consumption. A slow timescale is divided into several fast timescales, so the two timescales have inherent association. Using states of fast timescale to represent the state of its slow timescale properly is challenging, thereby the weighted mean type is proposed in this paper. We find that the realizability and consistency in two-timescale cannot be guaranteed in existing empirical models, which are the bases for physical application. Therefore, this paper proposes a method that building the fast timescale model first and then inducing the slow timescale model from the fast timescale model. In addition, such a problem in the high-order system is more complex, whose solution is also discussed in this paper. The results of case studies show that the induced model can guarantee the consistency and realizability and meet the user desired temperature for comfort. This paper was motivated by the multi-timescale problem that making a decision of controlling the indoor temperature for the user's comfort with energy constraint. Existing approaches to build a two-timescale model by experience would cause the inconsistent deviation. If the HVAC works in a closed environment system like a space station, besides crew comfort, the temperature for experiments in the space station should be accurate. Therefore, the deviation from the actual temperature and the desired temperature will cause adverse effects. In this paper, we mathematically derive the thermal state transfer equations and analyze some problems. Then, this paper suggests a new approach to build the two-timescale model for various conditions, in which the models of two timescales are consistent with each other. Preliminary experiments suggest that this approach is feasible and effective. In future research, we will jointly make optimization and decision of multiple appliances in home energy management (HEM) system.