Accurate bed temperature prediction is crucial in the circulating fluidized bed (CFB) combustion process, as it provides early warning of abnormal conditions, allowing timely intervention to prevent potential safety risks. However, the inherently complex multiphase flows and nonlinear chemical reactions in CFB systems make time series prediction of bed temperature a highly challenging task. Starting from the intrinsic spatial correlations and the temporal dependencies, this article proposes an adaptive learning-based bed temperature prediction method. The proposed model integrates dynamic correlation-guided Graph Convolutional Networks (GCN) and Long Short-Term Memory (LSTM) networks. Specifically, the GCN guided by prior knowledge adaptively learns complex topological structures to capture spatial dependencies. LSTM receives both raw input features and the spatial features extracted by GCN as parallel inputs, effectively capturing the temporal evolution of bed temperature. The proposed method is then applied to the task of bed temperature prediction in CFB. The experimental findings indicate that the proposed method consistently outperforms other comparative methods across different forecasting horizons, achieving a leading level of performance.

This article addresses adaptive event-triggered sampled-data (SD) fuzzy security control under spatially local averaged measurements (LAMs) for nonlinear delayed distributed parameter systems (DPSs) with denial of service (DoS) attacks and stochastic actuator failures. Firstly, a Takagi–Sugeno (T–S) fuzzy model of delayed partial differential equations (PDEs) is introduced to precisely characterize the dynamic behavior of nonlinear delayed DPS. Secondly, an adaptive event-triggered SD fuzzy security control strategy is designed under DoS attacks and stochastic actuator failures, which can be flexibly modified in accordance with the present sampling and the most recently transmitted signals, and is implemented utilizing a restricted number of sensors and actuators. Subsequently, by establishing a Lyapunov functional, sufficient conditions that guarantee the mean square exponential stability of closed-loop nonlinear delayed DPSs are obtained based on linear matrix inequalities (LMIs). Finally, two examples are provided and the presented controller are compared to demonstrate the applications and advantages of the proposed approach.

Controlling boiler–turbine systems (BTS) is challenging due to their complex nonlinearity and dynamic nature. To address these issues, we propose a novel dual event-triggered fuzzy model predictive control (DEFMPC) method. First, an event-triggered online update strategy is established for the fuzzy prediction model. To save computing resources and communication costs, a dual-channel event-triggered mechanism with a control efficiency evaluation index is then developed. This mechanism updates the prediction model and control input based on the control effect, ensuring efficient control interventions. The stability of the method is analyzed, and its superior performance is demonstrated through numerical simulations on the BTS, showcasing significant improvements in control accuracy and energy efficiency. The results highlight the potential of DEFMPC to enhance the performance and sustainability of thermal power generation systems.

Recently, many researchers have made successful progress in building the AI systems for MOBA-game-playing with deep reinforcement learning, such as on Dota 2 and Honor of Kings. Even though these AI systems have achieved or even exceeded human-level performance, they still suffer from the lack of policy diversity. In this paper, we propose a novel Macro-Goals Guided framework, called MGG, to learn diverse policies in MOBA games. MGG abstracts strategies as macro-goals from human demonstrations and trains a Meta-Controller to predict these macro-goals. To enhance policy diversity, MGG samples macro-goals from the Meta-Controller prediction and guides the training process towards these goals. Experimental results on the typical MOBA game Honor of Kings demonstrate that MGG can execute diverse policies in different matches and lineups, and also outperform the state-of-the-art methods over 102 heroes.