Shuai Mao

Fault diagnosis in induction motors is challenging when only a limited number of labeled infrared thermal images are available for training. Effective small-sample augmentation requires generated images to preserve class-related appearance patterns as well as visual realism. To address this challenge, a thermal-aware generative adversarial network (TA-GAN) is proposed for induction-motor fault diagnosis using pseudo-colour infrared images. An adaptive attention module combines feature intensity and Sobel-gradient information to emphasize component–state-related thermal patterns. A dual-branch critic jointly evaluates global and attention-weighted features, while an appearance-consistency loss constrains bright-region intensity, gradient structure, and spatial position during generation. The trained generator augments the limited real samples, and the combined dataset is used to train a lightweight classifier. Experiments on acquisition-batch-separated data partitions show improved classification performance over the evaluated real-only baselines under matched classifier-training budgets. The complete framework performs best among the evaluated component and individual-loss configurations. Generated-sample evaluation further indicates improved appearance similarity to real training images compared with a basic conditional GAN, while evaluation on a different motor provides additional evidence of transfer under the tested conditions. Image generation is performed offline, allowing the deployed system to retain the lightweight MobileNetV4 classifier architecture.

This article investigates reach–avoid games involving defenders equipped with capture radii, where both defenders and attackers have different speeds. The main challenge lies in using geometric methods to analyze different speed ratios, construct barriers, or defensive advantage angles, and divide the state space into defensive and offensive advantage regions. This article proposes optimal analytical strategies for players based on the corresponding payoff functions, depending on the attacker’s position within different winning regions under various speed ratios. In addition, we demonstrate the existence of a unique optimal target point within the offensive advantage region. Unlike numerical methods, which are limited by computational complexity and real-time application capabilities, the proposed method allows for the precise calculation of barriers and real-time updates in nonpoint capture scenarios. Finally, simulation results validate the effectiveness of the constructed barriers in multiplayer reach–avoid games.

Feedback signal delays present a common challenge in the online decision-making processes of various real-world systems, such as real-time economic dispatch in power systems. These delays, primarily induced by limited computational capabilities or unknown parameter changes, can significantly hinder the performance or even effectiveness of online decision-making strategies. This study investigates distributed optimization over time-varying unbalanced networks with delayed feedback signals. We propose discrete-time distributed online algorithms for both constrained and unconstrained optimization problems. Each node in the network has access only to its individual time-varying local objective function with a delayed time sequence. At each decision-making step, each node selects the appropriate local online behavior, which depends on the information from its neighbor nodes, towards the minimization of global cumulative cost function value. We demonstrate that sublinear regrets can be ensured as long as the time-varying unbalanced communication networks maintain $\mathcal {B}$ -strong connectivity. For a general convex or $\mu $ -strongly convex local objective function, the network regret and individual regret grow as $\mathcal {O}((\ln (T))^{2})$ and $\mathcal {O}(\sqrt {T})$ , respectively, and are intrinsically related to the feedback delays and step sizes. To validate the proposed algorithms, numerical studies are carried out on constrained distributed time-varying economic dispatch problems.

In cooperative multi-agent reinforcement learning (MARL), previous research has predominantly concentrated on augmenting cooperation through the optimization of global behavioral correlations between agents, with mutual information (MI) typically serving as a crucial metric for correlation quantification. The existing approaches aim to enhance the behavioral correlation among agents to foster better cooperation and goal alignment by leveraging MI. However, it has been demonstrated that the cooperative capabilities among agents cannot be enhanced merely by directly increasing their overall behavioral correlations, particularly in environments with multiple subtasks or scenarios requiring dynamic team structures. To tackle this challenge, a MARL algorithm named group-oriented mutual information collaboration (GoMIC) is designed, which dynamically partitions agents and employs MI within each partition as an enhanced reward. GoMIC mitigates excessive reliance of individual policies on team-related information and fosters agents to acquire policies across varying team compositions. Experimental evaluations across various tasks in multi-agent particle environment (MPE), level-based foraging (LBF), and StarCraft II demonstrate the superior performance of GoMIC over some existing approaches, indicating its potential to improve collaboration in multi-agent systems.

This manuscript considers distributed optimization problems in systems with cooperative-collaborative relationships, involving two groups of nodes, each with its own optimization problem, but with a coupled communication topology. For the signed graph representing the cooperation and collaboration between agents, this manuscript introduces DIG-JOR, a discrete-time distributed algorithm that consists of three key modules: an inexact consensus and gradient descent module, a group gradient-tracking module, and a dynamic Jacobi over-relaxation (JOR) inverse-tracking module. To support the convergence analysis of the distributed optimization algorithm, this manuscript proposes the Multi-Loop Small Gain Theorem. Under the assumption of strong convexity and with appropriately chosen step sizes, it is proved that the DIG-JOR algorithm converges to the optimal solutions of both groups at an R-linear rate. The theoretical results are validated through a simulation example.

In this paper, a unified influence networks model incorporating differential privacy mechanisms (DPMs), called the differentially private opinion dynamics (DPODs) model is proposed. In this model, each individual uses protected opinions rather than the private opinions of his/her neighbors to update his/her private opinions, where the protected opinion of an individual is a blend of private opinions and random noise following Laplace distribution. Building on stochastic analysis techniques and matrix theory, we show that the influence network under consideration converges under specific conditions governing individual sensitivities and interaction weights. In addition, the statistical properties related to convergence accuracy are established by utilizing the Markov inequality to estimate a lower bound on the probability of all individuals' final opinions converging to a neighborhood formed by their initial opinions' convex hull. We further conduct a differential privacy analysis to validate the efficacy of the proposed DPMs in safeguarding the private opinions of all individuals. Finally, two examples including one of the Karate-Club networks are provided to shed new light on the effectiveness of the theoretical results.

The implementation of distributed optimization, depending on the application, imposes escalating demands on communication and computational synchronization, with the general desire for the robust performance in the face of computationally slow agents and the avoidance of unnecessary communication. In this article, we propose a distributed algorithm with asynchronous computation and event-triggered communication (DAAET) that enables the nodes to flexibly determine their update and information transmission instants. DAAET achieves compatibility with nodes operating at varying computation frequencies and accomplishes a reduction in both wall time and communication costs. Meanwhile, this article proposes a model reconstruction technique to handle disconnectivity arising from the asynchronous implementation of the event-triggered mechanism. Theoretical analysis demonstrates the algorithm's linear convergence to the global optimum under relaxed conditions. The effectiveness and advantages of our approach are demonstrated through a set of examples, showcasing its potential for practical applications.

Energy storage systems (ESS) are pivotal component in the energy market, serving as both energy suppliers and consumers. ESS operators can reap benefits from energy arbitrage by optimizing operations of storage equipment. To further enhance ESS flexibility within the energy market and improve renewable energy utilization, a heterogeneous photovoltaic-ESS (PV-ESS) is proposed, which leverages the unique characteristics of battery energy storage (BES) and hydrogen energy storage (HES). For scheduling tasks of the heterogeneous PV-ESS, a practical cost function plays a crucial role in guiding operator’s strategies to maximize benefits. We develop a comprehensive cost function that takes into account degradation, capital, and operation/maintenance costs to reflect real-world scenarios. Moreover, while numerous methods excel in optimizing ESS energy arbitrage, they often rely on black-box models with opaque decision-making processes, limiting practical applicability. To overcome this limitation and enable explainable scheduling strategies, a prototype-based policy network with inherent interpretability is introduced. This network employs human-designed prototypes to guide decision-making by comparing similarities between prototypical situations and encountered situations, which allows for naturally explained scheduling strategies. Comparative results across four distinct cases demonstrate the effectiveness and practicality of our proposed pre-hoc interpretable optimization method when contrasted with black-box models.