Dynamic interactions among multiple agents in maintenance scenarios are common. Flexible maintenance strategies can enhance system reliability, reduce downtime, and minimize operational costs to achieve system health management in long-term operations. Therefore, investigating the complexity and interdependence of these agents in performing maintenance operations from the perspective of system maintenance decision-making is beneficial. In this paper, we propose the integration of multiagent-based modelling and simulation (MABMS) with a multistage evolutionary game (EG) model for the development of adaptive maintenance strategies. In the proposed method, MABMS is applied to describe the interactions among various agents. Stakeholders related to agents in MABMS are regarded as players in a game. Game theory can thus be adopted to model the strategic decision-making of stakeholders at different maintenance stages. We subsequently established a multistage EG to study the strategies of both competition and cooperation among agent-related stakeholders. Stakeholders at different stages optimize their strategies on the basis of feedback from agents and the results of relevant maintenance stages. Finally, by improving decision-making across different maintenance stages, a dynamic maintenance strategy is established to enhance system reliability and reduce downtime. The obtained results indicate that the proposed approach yields improvements in maintenance efficiency and decision-making adaptability.

"Intelligent Prediction in the Information Era" is a specialized general education course designed for undergraduates. This study focuses on the teaching needs and issues in the current teaching model of this course, conducting an in-depth investigation from three aspects: teaching content, teaching methods, and evaluation system. There search develops a set of teaching content that integrates and correlates intelligent prediction knowledge across multiple disciplines for undergraduates and proposes a new syllabus. Furthermore, it explores teaching methods that inspire students' active and innovative research thinking and designs assessment standards to guide students in actively exploring intelligent prediction techniques. There search findings provide significant reference value for the reform and innovation of teaching models and methods in undergraduate specialized general education courses.

Multiple unmanned aerial vehicle (multi-UAV) system is a type of dynamic spatiotemporal Internet of Things and susceptible to destruction from the external environment. Meanwhile, resilience theory has been introduced to describe the ability of unmanned aerial vehicles (UAVs) faced with disturbances. However, the existing methods do not fully reflect the dynamic spatiotemporal characteristics of multi-UAV systems. Therefore, we proposed a novel resilience metric that integrates mission coverage area and communication status to describe the dynamic spatiotemporal characteristics of multi-UAV systems. On the basis, a combination of importance measures for vulnerability, recoverability, and resilience is presented to support the analysis and identification of weaknesses for the system in whole process. Furthermore, a structure design method is given to improve system resilience by considering both importance measures and trajectory optimization methods simultaneously. Finally, a typical formation topology with six UAVs is simulated as a case study to verify the proposed approach.

In the design phase of Li-ion batteries for electric vehicles, battery manufacturers need to carry out cycle life tests on a large number of formulations to get the best one that meets customer demands. However, such tests take considerable time and money due to the long cycle life of power Li-ion batteries. Aiming at reducing the cost of cycle life tests, we propose a prediction method that can learn historical degradation data and extrapolate to predict the remaining degradation trend of the current formulation sample taking the initial stage of partial cycle life test results as input. Compared with existing methods, the proposed deep reinforcement learning based method is able to learn degradation trends with different formulations and predict long-term degradation trends. Based on the deep deterministic policy gradient algorithm, the proposed method builds a degradation trend prediction model. Meanwhile, an interactive environment is designed for the model to explore and learn in the training phase. The proposed method is verified with real test data from battery manufacturers under three different temperature conditions in the formulation design stage. The comparisons indicate that the proposed method is superior to traditional degradation trend prediction methods in both accuracy and stability.