Search

The integrity of data-driven load frequency control (LFC) in power system is increasingly threatened by adversarial attack. Addressing this concern, this brief introduces a novel hybrid approach that integrates adversarial reinforcement learning and monotonic neural network (ARL-HMNN) for LFC in multi-area power system. To holistically counter unforeseen uncertainties and to withstand the prevalent adversarial attack, the proposed ARL-HMNN approach builds a stable neural network structure with monotonicity constraints, and optimizes this neural network for LFC with adversarial training and deep deterministic policy gradient algorithm. By enforcing the deviation-command monotonicity constraints, the HMNN is enabled to satisfy Lyapunov stability conditions for LFC, which significantly enhances the stability and robustness of the power system. To further enhance the robustness of LFC, the classic fast gradient sign method (FGSM) adversarial attack is applied during the reinforcement learning training process. Through the integration of adversarial training, our method improves the system’s resilience to FGSM attack under malicious threat from the communication network, while at the same time maintaining provable frequency stability. The superior performance of the developed approach is demonstrated by comparison to existing data-driven control methods on the IEEE 39-bus power system.

Objectives: Exploring the anisotropic mechanical behavior of cancellous bone is crucial for in-vivo bone biomechanical analysis. However, it is challenging to characterize anisotropic mechanical behaviors under low-resolution (LR) clinical CT images due to a lack of microstructural information. The data-driven method proposed in this article accurately characterizes the anisotropic mechanical properties of cancellous bone from LR clinical CT images. Methods: The trabecular bone cubes of sheep are used to obtain a high-resolution (HR) micro-CT and an LR clinical CT image dataset. First, an auto-encoder model is trained using HR image data. Microstructural features are extracted by the encoder. A fast super-resolution (FSR) model is trained to map LR bone cubes to the features extracted from corresponding HR samples. The pretrained FSR model is used to convert LR clinical CT images to encoded microstructural features. The features are later used to predict target histomorphological parameters, anisotropic elastic tensors, and fabric tensors based on a fully connected neural network. Results: The data-driven model accurately predicts the elastic tensor and fabric tensor of trabecular bones with LR CT images with 0.6 mm/pixel spatial resolution. It was verified that LR clinical CT images could generate microstructural information using a generative deep-learning model and an up-sampling operation. Significance: This study proves that clinical medical images of cancellous bone can be used for analysis of complex mechanical properties using a data-driven method, which is useful for real-time bone defect diagnosis and personalized bone prosthesis design in clinical application.

Practical operations of a power system need to comply with Grid Codes, which are usually grounded in linguistic stipulations that may be hard to quantify in conventional optimal power flow (OPF) models. In the lights of recent breakthrough in large language models (LLM), this letter proposes an OPF model with linguistic stipulations and a solution method by integrating the generative pre-trained transformer (GPT) based LLM agent in the primal-dual deep reinforcement learning (DRL) training loop. For the first time, conventionally unquantifiable linguistic stipulations expressed in natural language can be directly modeled as the objectives and constraints in the OPF problem. The GPT-agent is used to interpret satisfactions of linguistic stipulations as rewards and constraints. The non-differentiable rewards obtained by GPT-agent are optimized through interactions with environments in the DRL process. Once sufficiently trained, the DRL agent can solve the OPF model in real-time. The proposed method is demonstrated on the IEEE 118-bus system.

To detect cyber-attacks on individual smart meters, this letter proposes a novel data-driven method based on dimensional augmentation with recurrence plots (RPs) and visual geometry group network (VGGNet). Firstly, the real-time 1-dimensional time-series smart meter data is augmented to 2-dimensional image data using the RPs method, which provides visual-distinguishable features that can be more easily identified by the computer vision-based algorithms. Then, the genuine and contaminated smart meter data are distinguished using the VGGNet on the augmented 2-dimensional data. The proposed method is tested on a public user-level load dataset with 20 residential buildings and shows high accuracy and strong interpretability.

Utilizing renewable energy sources (RESs), such as wind and solar, to convert electrical energy into hydrogen energy for industrial users with different types of energy storage can enhance the integration of green electricity, thereby replacing fossil fuels like natural gas. In the energy management optimization of industrial electric‑hydrogen coupling system (EHCS) with high RESs integration, the traditional optimization methods cannot effectively address the nonlinear characteristics of equipment and stochastic RES generation, while the model-free reinforcement learning methods struggle to improve the training efficiency and may lead to constraint violation. To address this challenge, this paper proposes a short time scale energy management approach for EHCS based on physical models assisted deep reinforcement learning (DRL). Firstly, the energy management optimization model of the EHCS is developed based on the operation characteristics of the equipment within the system. Secondly, the energy management model of EHCS is formulated as a DRL framework. The DRL agent is efficiently trained with the assistance of the action transformation which takes into account the physical characteristics of the equipment during operation. Finally, a case study is conducted to verify the effectiveness of the proposed model for achieving high-efficiency agent training, reducing decision-making time for equipment scheduling, addressing the stochastic RES generation, and realizing the economic operation of EHCS with good performance based on the equipment characteristics.

Bone, renowned for its elegant hierarchical structure and unique mechanical properties, serves as a constant source of inspiration for the development of synthetic materials. However, achieving accurate replication of bone features in artificial materials with remarkable structural and mechanical similarity remains a significant challenge. In this study, we employed a cascade of continuous fabrication processes, including biomimetic mineralization of collagen, bidirectional freeze-casting, and pressure-driven fusion, to successfully fabricate a macroscopic bulk material known as artificial compact bone (ACB). The ACB material closely replicates the composition, hierarchical structures, and mechanical properties of natural bone. It demonstrates a lamellated alignment of mineralized collagen (MC) microfibrils, similar to those found in natural bone. Moreover, the ACB exhibits a similar high mineral content (70.9 %) and density (2.2 g/cm3) as natural cortical bone, leading to exceptional mechanical properties such as high stiffness, hardness, and flexural strength that are comparable to those of natural bone. Importantly, the ACB also demonstrates excellent mechanical properties in wet, outstanding biocompatibility, and osteogenic properties in vivo, rendering it suitable for a broad spectrum of biomedical applications, including orthopedic, stomatological, and craniofacial surgeries.

Acoustic metamaterials possessing subwavelength characteristics can be used for low-frequency noise and vibration control. Acoustic metamaterials with adjustable dynamic properties can further enhance their possible applications. This paper designs a kind of tunable acoustic metamaterials consisting of the frame structure, airbag, and balancing weight. And their dynamic characteristics can be manipulated by tuning gauge pressure and gas temperature in the airbag. The calculation results indicate that the tunable acoustic metamaterials can effectively suppress the wave propagation and vibration in the ultralow-frequency band gap (about 13Hz∼90Hz) during manipulation. The complete band gap is the overlapping frequency range of an out-of- and in-plane band gaps. Numerical analyses indicate that the formation of out-of-plane band gap is due to the coupling between the out-of-plane resonant mode of balancing weight and the anti-symmetric Lamb mode of the frame structure. In contrast, the formation of an in-plane band gap is due to the coupling between the in-plane resonant mode of balancing weight and the symmetric Lamb mode of the frame structure. Meanwhile, the manipulation mechanism of these band gaps stems from the fact that through tuning gauge pressure or gas temperature, the structural stiffness of the airbag (torsional stiffness, in-plane, and out-of-plane stiffness) and frame structure (in-plane and bending stiffness) can be significantly tuned so that the modes related to them can be manipulated. The tunable acoustic metamaterials can be used for active control of low-frequency vibration and noise. It is possible to provide guidelines for designing other acoustic metamaterials to suppress low-frequency vibration and noise.