This study presents a data-driven framework that integrates machine-learning-based diagnosis with gradient-based optimization for lightning protection of transmission corridors. Six standardized features — ground resistance, insulator-string length, tower height, protection angle, ground inclination, and ground-flash density — are normalized to construct tower state vectors for model training and inference. The diagnostic model outputs risk scores and cause attributions, identifying ground-flash density as the dominant hazard (27.9%), followed by excessive ground inclination, increased tower height, and shortened insulator strings that elevate wrap-around strike risk. Using these diagnostic results, a gradient-based optimizer minimizes state deviations within engineering constraints to generate actionable protection measures, including arrester configuration and parameter adjustments. In a 220-kV case study covering 39 towers, 30 satisfied the standard and 9 were recommended for arrester installation; for the high-risk Tower #034, the trip-out rate decreased to 1.632 times/(100 km⋅a). The proposed approach improves objectivity and efficiency relative to manual practice. Future work will incorporate cost weighting to enhance practical deployment.

Coordinated secondary frequency regulation by flywheel energy storage arrays (FESAs) and thermal power units (TPUs) mitigates grid frequency oscillations caused by renewable integration. However, existing strategies often overlook stage-specific dynamics and multiobjective tradeoffs. To address this, a stage-aware, multiobjective, bilevel dynamic load allocation strategy is proposed based on grid assessment criteria. At the upper level, fuzzy adaptive control predicts TPU capacity, while field-based traction experiments establish precise physical power constraints for the FESA. An improved nondominated sorting genetic algorithm II (NSGA-II) with a comprehensive satisfaction model and smooth weights is developed to optimize power output across distinct regulation stages. At the lower level, a bidirectional coupling interface enables adaptive group selection, followed by an improved consensus algorithm based on the relative rate of change of state of charge (SOC) for rapid energy and state alignment. Validated with operational data from a 660-MW supercritical plant in Ningxia, China, results demonstrate superior robustness against 0.6 s network delays and 0.5 s unit failures. Compared to representative benchmarks, it increases regulation net profit by 21.83% and reduces energy losses by 19.8%, effectively balancing grid requirements with the operational safety and economic sustainability of storage-integrated plants.

In recent years, deep cross-modal hashing retrieval methods have attracted extensive attention due to their strong ability to learn efficient binary encodings. However, they still face two main challenges: 1) insufficient fusion of cross-modal information, leading to low semantic quality of the generated hash codes. 2) limited scalability for deployment in lightweight frameworks. To address these issues, this paper proposes a novel cross-modal hashing method based on knowledge distillation, termed Fine-Grained Feature Fusion Knowledge Distillation Hashing (F3KDH). Specifically, the teacher model incorporates the AFM that thoroughly fuses heterogeneous information, effectively capturing salient semantic cues in cross-modal data to enhance the weighting of important regions. Moreover, we employ a cross-modal knowledge distillation strategy to transfer the rich semantic knowledge captured by the teacher to a deliberately lightweight student model, enabling it to learn compact yet expressive hash representations while greatly reducing computational complexity. Experimental results on multiple benchmark datasets demonstrate that, compared to existing cross-modal hashing methods, our approach achieves significant model compression without sacrificing retrieval accuracy.

This paper presents a new variable stiffness actuator based on a second-order lever mechanism which has wide stiffness regulation range. By employing a novel symmetric structure design and improving the load capacity of the stiffness regulation module, the proposed actuator also shows well performance in load capacity, stiffness regulation response, and elastic hysteresis. On this basis, a variable stiffness actuated manipulator is developed. The experimental results demonstrate that the presented manipulator possesses abilities in fast stiffness tracking, shock-absorbing and explosive movement. It is also verified that the manipulator can withstand accidental impact, which illustrates the structure stability of the proposed design.

This paper presents a real-time kinematic control strategy to realize fast tracking of redundant robot manipulators in a time-varying environment. An obstacle avoidance method based on the law of conservation of energy is proposed to adjust the motion states of robot manipulators in real time. This method defines that the total energy for the end effector consists of an energy toward object (ETO) and an energy around obstacle (EAO), and that the total energy for each critical point on manipulator composes a relative kinematic energy (RKE) and an energy memory (EM). The total energies remain constant at each sampling period, and the conversions between the ETO and the EAO or between the RKE and the EM are recognized to obey a distance-related S-function. Such considerations ensure the smooth movement of the manipulator and avoid collisions with obstacles. In real-time planning, an unsupervised single neuron PID model is raised to adaptively increase the convergence ratio of moving object tracking via the online learning of the principal component analysis. Then, combined with the dynamic obstacle avoidance method based on conservation of energy, the kinematic control strategy is established for redundant manipulators to track a moving object rapidly in the presence of multiple dynamic obstacles. Theory analysis and various contrast experimental results show that the proposed kinematic control strategy is feasible and has fast convergence.