Grid interconnection is a key strategy for strengthening power system resilience to extreme weather events by facilitating intersystem mutual assistance. Despite the overall reduction in risk exposure, significant residual risks remain that could still lead to catastrophic consequences. While insurance offers a means to transfer these risks, conventional standalone models struggle to balance insurer solvency with premium affordability and fail to incentivize participation from lower risk areas. Inspired by spatial risk diversification, this article proposes a novel coalitional insurance framework for weather-related risk management of interconnected transmission systems (ITS). The framework is built on a joint resilience assessment model that quantifies power outage risks in ITS, accounting for intersystem mutual assistance. To solve this model with guaranteed convergence and well-preserved privacy, a distributed optimization approach based on the Bregman alternating direction method of multipliers and iterative optimization is developed. Furthermore, specially designed exante premium and expost indemnity policies ensure equitable allocation and promote coalition participation. Numerical experiments on the IEEE RTS-96 system validate the effectiveness and superiority of the proposed coalitional insurance scheme.

Targeted adversarial attacks in black-box settings are pivotal for uncovering vulnerabilities in neural networks and guiding the development of robust defenses. However, conventional attack methods typically perturb the primary content, leading to a degradation in image quality and highlighting the need for more reasonable optimization strategies. In contrast, we propose a novel algorithm that restricts perturbations to the image boundary regions, thereby preserving content fidelity while enhancing attack effectiveness. Our approach employs an encoder–decoder generative network to craft targeted adversarial examples guided by optimized semantic perturbations derived from the boundaries. Moreover, the boundary signal is jointly optimized with the model parameters, enabling efficient, amortized optimization for multi-class targeted attacks. Extensive experiments demonstrate that the proposed boundary-guided method significantly improves the success rates of targeted black-box attacks and can be seamlessly integrated into existing noise-injection techniques to enhance overall performance.

Electrocardiogram (ECG) signals frequently encounter diverse types of noise, such as baseline wander (BW), electrode motion (EM) artifacts, muscle artifact (MA), and others. These noises often occur in combination during the actual data acquisition process, resulting in erroneous or perplexing interpretations for cardiologists. To suppress random mixed noise (RMN) in ECG with less distortion, we propose a Transformer-based Convolutional Denoising AutoEncoder model (TCDAE) in this study. The encoder of TCDAE is composed of three stacked gated convolutional layers and a Transformer encoder block with a point-wise multi-head self-attention module. To obtain minimal distortion in both time and frequency domains, we also propose a frequency weighted Huber loss function in training phase to better approximate the original signals. The TCDAE model is trained and tested on the QT Database (QTDB) and MIT-BIH Noise Stress Test Database (NSTDB), with the training data and testing data coming from different records. All the metrics perform the most robust in overall noise and separate noise intervals for RMN removal compared with the baseline methods. We also conduct generalization tests on the Icentia11k database where the TCDAE outperforms the state-of-the-art models, with a 55% reduction of the false positives in R peak detection after denoising. The TCDAE model approximates the short-term and long-term characteristics of ECG signals and has higher stability even under extreme RMN corruption. The memory consumption and inference speed of TCDAE are also feasible for its deployment in clinical applications.

For the fuel cell/battery UAV hybrid power system, an energy management strategy(EMS) based on fuzzy logic control(FLC) is proposed in this paper, which is optimized to reduce the system's hydrogen consumption, maintain the state of charge(SOC) of lithium battery, and stabilize the bus voltage. In order to verify the effectiveness of the EMS, a fuel cell UAV hardware experimental platform is built and a finite state machine(FSM) strategy is designed for comparison. Experimental comparison results verify the effectiveness of the proposed fuzzy logic control strategy in stabilizing the bus voltage, maintaining the SOC of the lithium battery, and improving the system fuel economy.

Energy Management Strategy (EMS) is a crucial part of More-Electric Aircraft (MEA) and aims at improving the efficiency of whole hybrid energy system. In this paper, fuzzy neural network trained by dynamic programming (FNDP) is proposed to solve the problem that dynamic programming (DP) cannot be used online. FNDP can obtain the optimal distribution scheme using DP and extract the rule from the data through fuzzy neural network (FNN). Compared to fuzzy control strategy based on power follow (PFF) in two different load profiles, it can be found that FNDP can attain a satisfied rule without manual setting and have a better performance than PFF.

In this paper, the hybrid power system of fuel cell Unmanned Aerial Vehicle (UAV) is established on the platform of Matlab/Simulink whose system architecture is fuel cell with lithium battery, and the overall scheme of the system is designed. In addition, the required power curves under two typical working conditions are obtained by establishing the aircraft dynamics model. An optimization energy management strategy based on dynamic programming is designed to achieve the least hydrogen consumption. For comparison, another two energy management strategies are designed under the same working condition. Finally, it is proved that dynamic programming has optimal fuel economy than the other two strategies. Moreover, each strategy has its own characteristics, which provides suggestions for selection of energy management strategies under different objectives.

In order to mitigate the environmental pollution problem, the fuel cell electric vehicle (FCEV), as one kind of renewable energy industry, is researched and developed. The performance of FCEV is deeply relied on the energy management strategy (EMS), an inappropriate EMS may cause the bad performance of FCEV. Strategies designed under specific work condition have poor adaptability to complex work conditions. What’s more, these strategies give little concern on the volatility of fuel cell’s output power, which will cause a loss of fuel cell’s life. Aiming at decreasing the hydrogen consumption of FCEV and the volatility of the output power of fuel cell, an optimized fuzzy logic control energy management strategy based on work condition recognition is proposed. In order to achieve a better performance, this strategy can recognize instant driving condition, and pick the corresponding parameters of fuzzy logic control system from the preset database of the parameters. The database is obtained by offline optimization with genetic algorithm. A simulation result based on the MATLAB/Simulink platform is obtained to demonstrate that this strategy has a better performance than a conventional fuzzy logic controller with fixed parameters under mixed work conditions.

In this paper, we deal with both velocity control and force control of a single-rod electro-hydraulic actuator subject to external disturbances and parameter uncertainties. In some implementations, both velocity control and force control are required. Impedance control and an extended disturbance observer are combined to solve this issue. Impedance control is applied to regulate the dynamic relationship between the velocity and output force of the actuator, which can help avoid impact and keep a proper contact force on the environment or workpieces. Parameters of impedance rules are regulated by a fuzzy algorithm. An extended disturbance observer is employed to account for external disturbances and parameter uncertainties to achieve an accurate velocity tracking. A detailed model of load force dynamics is presented for the development of the extended disturbance observer. The stability of the whole system is analyzed. Experimental results demonstrate that the proposed control strategy has not only a high velocity tracking performance, but also a good force adjustment performance, and that it should be widely applied in construction and assembly.