Chuan Zhou

Attitude stability during the reentry phase of hypersonic flight vehicle (HFV) relies heavily on aerodynamic control surfaces. Any failure in these components can severely compromise mission safety. However, the acquisition of fault data is prohibitively expensive, and the types of faults are diverse. Existing methods show suboptimal diagnostic performance under these conditions. This article proposes a contrastive learning-based approach for diagnosing faults in aerodynamic control surfaces. The diagnosis task is defined as a multi-class classification problem using multivariate state time series. To this end, a dilated attention temporal network (DAT-Net) is developed within the contrastive orthogonal-center framework (COC-Framework), forming the COC-DAT-Net. The proposed network combines dilated convolutions with attention mechanisms for feature extraction. It employs an orthogonal-center contrastive learning strategy to optimize the structure of the feature space. In addition, a dynamic sampling mechanism is introduced to improve the quality of sample pair construction. Simulation experiments demonstrate that the proposed method performs well in fault diagnosis of aerodynamic control surfaces. It achieves an average F1-Score of 94.04% and a silhouette score of 81.43%. These results confirm the effectiveness of COC-DAT-Net in multi-class and small-sample scenarios. The method provides methodological support for enhancing the safety of HFV reentry.

In this article, a novel robust consensus control protocol is proposed for multiple uncertain Euler–Lagrange systems with unknown external disturbances. First, the local adaptive control laws are derived under event‐triggered communication framework, and the robust consensus control problem is transformed into an equivalent optimal control problem with disturbance rejection. Event‐triggered mechanisms and distributed state estimators are designed by utilizing only triggered exchanging states, by which continuous monitoring neighbors' states is avoided and communication burdens are effectively reduced. Second, the Hamilton–Jacobi–Isaac equations are formulated based on zero‐sum differential game theory, and adaptive dynamic programming methods are employed to approximate the Nash‐equivalent solutions, by which the local robust optimal control laws are derived to eliminate the disturbance effects and improve the robustness of the proposed strategy. It is strictly proved that all signals in the closed‐loop systems are uniformly ultimately bounded and the cost functions are minimized. Finally, two practical examples are presented to validate the proposed strategy.

This article investigates the consensus tracking problem with predefined transient and steady performance requirements for a class of nonstrict‐feedback nonlinear multi‐agent systems (MASs) with input quantization under a directed graph. Based on prescribed performance error transformation methods and command filtered backstepping techniques, a novel observer‐based adaptive control protocol is proposed, where neural observers are designed to estimate unmeasurable states and radial basis function neural networks are constructed to compensate command filter errors. The proposed protocol can be applied to a more general class of nonlinear MASs with nonstrict‐feedback nonlinear dynamics and unmeasurable states information. It is strictly proved that all signals in the whole MAS are semi‐globally uniformly ultimately bounded and both the transient and steady performances of the consensus tracking errors satisfy prescribed performance requirements. Finally, three numerical examples are presented to validate the effectiveness of the proposed protocol.

Summary: In this article, a novel intermittent projected subgradient algorithm is presented to solve the randomized optimal consensus problem for heterogeneous multiagent systems with time‐varying communication topologies. The multiagent systems achieve the consensus meanwhile minimizing the global objective function via the proposed algorithm, where f_i(x) is the convex objective function of agent i itself. Due to the common Bernoulli distribution adopted in the existing random optimization algorithm without considering the different computing capability of each agent. An individual projection probability is assigned for each agent based on computing capabilities so that either making projection or taking average is chosen according to the above probability which can effectively avoid overload for some agents with lower computing capabilities and improve the reliability of the overall systems. A new sufficient step‐size condition is given to ensure all agents converge to the optimal solution with probability one. Finally, a numerical example is also given to validate the proposed method.

This paper deal with the event-triggered based consensus problem for heterogeneous multi-agent systems subject to communication delays. The consensus protocol is designed based on the two event-triggered schemes, one from the sensor to the controller and other from the controller to the actuator. Which can be further saved communication resources in multi-agent systems. Furthermore, under the proposed framework a new exponential stability criterion is derived which is proved by the Lyapunov function. The LMI (Linear Matrix Inequality) Toolbox in MATLAB is used to obtain the parameters. To illustrate the effectiveness of the proposed method a numerical example is given.