Accurate estimation and prediction of the state-of-health (SOH) and remaining useful life (RUL) are fundamental to optimal maintenance strategies formulation for prognostics and health management (PHM) of degraded equipment. However, the performance assessment of health state prognostics and RUL prediction is strongly dependent on the errors and uncertainties in physical measurements, and heterogeneous degradation of equipment in time-varying operating conditions. The objective of this article is to provide a hybrid prognostic framework that integrates a two-phase clustering scheme and a particle filter (PF)-long short-term memory (LSTM) learning algorithm based on PF and LSTM networks for dynamic classification of SOH and long-term RUL prediction in the absence of future observations. The proposed generic hybrid PF-LSTM prognostic approach is demonstrated and compared with other adaptive learning and machine learning methods such as unscented particle filter (UPF) and radial basis function network (RBFN) on the degradation modeling and RUL prediction for lithium-ion batteries. The comparison results show that robust prediction performance can be obtained by the hybrid PF-LSTM prognostic approach with the accurate characterization of equipment degradation states based on the integrated subtractive-fuzzy clustering analysis. The more accuracy on prognostic estimations in probability density function (PDF) of prior and posterior distributions of battery capacity and RUL that are achieved by particle filtering can gain extensive insights to predictive maintenance action guide.

In the contemporary big data era, data-driven prognostic and health management (PHM) methodologies have emerged as indispensable tools for ensuring the secure and reliable operation of complex equipment systems. Central to these methodologies is the accurate prediction of remaining useful life (RUL), which serves as a pivotal cornerstone for effective maintenance and operational decision-making. While significant advancements in computer hardware and artificial intelligence (AI) algorithms have catalyzed substantial progress in AI-based RUL prediction, extant research frequently exhibits a narrow focus on specific algorithms, neglecting a comprehensive and comparative analysis of AI techniques across diverse equipment types and operational scenarios. This study endeavors to bridge this gap through the following contributions: (1) A rigorous analysis and systematic categorization of application scenarios for equipment RUL prediction, elucidating their distinct characteristics and requirements. (2) A comprehensive summary and comparative evaluation of several AI algorithms deemed suitable for RUL prediction, delineating their respective strengths and limitations. (3) An in-depth comparative analysis of the applicability of AI algorithms across varying application contexts, informed by a nuanced understanding of different application scenarios and AI algorithm research. (4) An insightful discussion on the current challenges confronting AI-based RUL prediction technology, coupled with a forward-looking examination of its future prospects. By furnishing a meticulous and holistic understanding of the traits of various AI algorithms and their contextual applicability, this study aspires to facilitate the attainment of optimal application outcomes in the realm of equipment RUL prediction.

The design of a nuclear power plant is proved to be safe enough in various hypothetical operation scenarios after strict safety assessment. One of the important tasks of operational risk management in a nuclear power plant is to evaluate whether any configuration change of the nuclear power plant can still achieve its expected safety and economic goals. This paper proposes a system reliability modeling and analysis method based on two-layers hierarchical GO-FLOW model. By flexibly adjusting the parameters of a GO-FLOW model, the model can adapt to the changes of success criteria and various configuration of the modeled system, thus avoiding the extra workload brought by re-modeling and improving the efficiency of risk management in nuclear power plants.

Large-scale, complex, and high-risk industrial systems such as nuclear power plants have developed detailed operating procedures. Under the expected conditions, the operators operate the system according to the operating procedures to avoid human error. However, under complex and unfamiliar conditions, once the guidance of operating procedures is lost, serious consequences may be caused. This paper proposes a No-Procedure guided Operation Supervision Technology (NoP-OST). The key idea is to identify the success paths by a forward-searching approach from source to sink functions. On this basis, the success paths are combined to generate various operation schemes to achieve the main objectives of the system. The paper illustrates the application of NoP-OST through the case of loss of the Residual Heat Removal System (RHRS) in a Pressurized Water Reactor (PWR) nuclear power plant. The research results show that the method proposed in this paper can provide a valuable operational reference for complex systems by making use of the available functions of the system.