Real-time Simulation Research Articles

Adversarial attacks on reinforcement learning agents for command and control

Given the recent impact of deep reinforcement learning in training agents to win complex games such as StarCraft and DoTA (Defense Of The Ancients)—there has been a surge in research for exploiting learning-based techniques for professional wargaming, battlefield simulation, and modeling. Real-time strategy games and simulators have become a valuable resource for operational planning and military research. However, recent work has shown that such learning-based approaches are highly susceptible to adversarial perturbations. In this paper, we investigate the robustness of an agent trained for a command and control task in an environment that is controlled by an active adversary. The C2 agent is trained on custom StarCraft II maps using the state-of-the-art RL algorithms—Asynchronous Advantage Actor Critic (A3C) and proximal policy optimization (PPO). We empirically show that an agent trained using these algorithms is highly susceptible to noise injected by the adversary and investigate the effects these perturbations have on the performance of the trained agent. Our work highlights the urgent need to develop more robust training algorithms especially for critical arenas like the battlefield.

Real-time energy management simulation for enhanced integration of renewable energy resources in DC microgrids

The presented work addresses the growing need for efficient and reliable DC microgrids integrating renewable energy sources. However, for the sake of practicality, implementing complex control strategies can increase system complexity. Thus, efficient methodologies are required to provide efficient energy management of microgrids while increasing the integration of renewable energy sources. The primary contribution of this work is to investigate the issues related to operating a DC microgrid with conventional control designed to power DC motors using readily available, non-advanced control strategies with the objective of achieving stable and reliable grid performance without resorting to complex control schemes. The proposed microgrid integrates a combination of uncontrollable renewable distributed generators (DGs) alongside controllable DGs and energy storage systems, including batteries and supercapacitors, connected via DC links. The Incremental Conductance (InCond) algorithm is employed for maximum power point tracking to maximize power output from the PV system. The energy management strategy prioritizes the solar system as the primary source, with the battery and supercapacitor acting as backup power sources to ensure overall system reliability and sustainability. The effectiveness of the microgrid under various operating conditions is evaluated through extensive simulations conducted using MATLAB. These simulations explore different power generation scenarios, including normal operation with varying load levels and operation under Standard Test Conditions (STC). Moreover, fault analysis of the DC microgrid is performed to examine system reliability. The system performance is evaluated using real-time simulation software (OPAL-RT) to validate the effectiveness of the approach under real-time conditions. This comprehensive approach demonstrates the efficacy of operating a DC microgrid with conventional controllers, ensuring grid stability and reliability across various operating conditions and fault scenarios while prioritizing the use of renewable energy sources. The results illustrated that system efficiency increases with load, but fault tolerance measures, can introduce trade-offs between reliability and peak efficiency.

Research and implementation of a large-bandwidth real-time radar jamming simulator.

The electromagnetic environment faced by modern radar is becoming increasingly complex. One effective means to improve the performance of radar systems is testing in an anti-jamming ability test chamber, where the increased complexity has also led to higher performance requirements for radar jamming simulators. Based on the requirements for modern radar system testing, this paper presents a study of a large-bandwidth real-time radar jamming simulator and describes its overall design architecture; the simulator covers the L-Ku and Ka frequency bands and the instantaneous bandwidth is ≥2GHz, which means that the system is able to simulate 11 interference patterns. Synchronous control of the system is realized in 1ms through use of the reflection memory interrupt mechanism, the synchronous pulse signal mechanism, synchronous timing design, and a real-time control software architecture. An overall design scheme for real-time simulation of a radar target jamming echo is given and baseband signal processing resources are saved through information preprocessing, a large-capacity high-speed storage board is designed to improve the data reading speed, a multiphase filtering structure is used to achieve high sampling rates and save hardware resources, and a high-speed parallel computing method is used to improve computing efficiency; the actual measured baseband signal processing time is less than 500ns. Finally, a measurement platform is built, and the main interference patterns are verified through experimental measurements.

Construction and application of static stability intelligent evaluator for large power grid from the perspective of knowledge graph

Abstract Relying on information technology such as artificial intelligence, knowledge analysis on a large amount of high-dimensional real-time measurement and simulation information, and deep excavation of stable operation situations in the power grid are the core of real time intelligent security defense of large power grid. In this paper, from the perspective of the knowledge graph, considering the stability state evaluation index and optimizing control strategy information of different operation scenarios of power grid comprehensively, using the integration mechanism of information system and knowledge graph, the functional framework of intelligent evaluator for static stability in power grid is proposed, and an evaluator including static evaluation and decision-making, and general intelligent algorithm is designed. Introducing knowledge graph automation engine technology, visual display of intelligent evaluator for large power grid static stability is realized. An application case in a real power grid is given to prove the effectiveness of the proposed method. The research work is helpful to regulate and control operators to grasp the operation situation and improve the efficiency of evaluation and decision-making of the power grid. It has positive exploration application value to improve the construction of intelligent active security defense systems online in large power grids.

Aeroelastic Real-Time Hybrid Simulation. II: Mitigation of Vortex-Induced Vibration of a Tall Building Structure

Aeroelastic Real-Time Hybrid Simulation. II: Mitigation of Vortex-Induced Vibration of a Tall Building Structure

Recommendation for the practice of total intravenous anesthesia.

This Recommendation was developed by the Japanese Society of Intravenous Anesthesia Recommendation Making Working Group (JSIVA-WG) to promote the safe and effective practice of total intravenous anesthesia (TIVA), tailored to the current situation in Japan. It presents a policy validated by the members of JSIVA-WG and a review committee for practical anesthesia management. Anesthesiologists should acquire and maintain the necessary knowledge and skills to be able to administer TIVA properly. A secure venous access is critically important for TIVA. To visualize and understand the pharmacokinetics of intravenous anesthetics, use of real-time pharmacokinetic simulations is strongly recommended. Syringe pumps are essential for the infusion of intravenous anesthetics, which should be prepared according to the rules of each individual anesthesia department, particularly with regard to dilution. Syringes should be clearly labeled with content and drug concentration. Whenmanaging TIVA, particularly with the use of muscle relaxants, monitoring processed electroencephalogram (EEG) is advisable. However, the depth of sedation/anesthesia must be assessed comprehensively using various parameters, rather than simply relying on a single EEG index. TIVA should be swiftly changed to an alternative method that includes inhalation anesthesia if necessary. Use of antagonists at emergence may be associated with re-sedation risk. Casual administration of antagonists and sending patients back to surgical wards without careful observation are not acceptable.

Discrete differential geometry-based model for nonlinear analysis of axisymmetric shells

In this paper, we propose a novel one-dimensional (1D) discrete differential geometry (DDG)-based numerical method for geometrically nonlinear mechanics analysis (e.g., buckling and snapping) of axisymmetric shell structures. Our numerical model leverages differential geometry principles to accurately capture the complex nonlinear deformation patterns exhibited by axisymmetric shells. By discretizing the axisymmetric shell into interconnected 1D elements along the meridional direction, the in-plane stretching and out-of-bending potentials are formulated based on the geometric principles of 1D nodes and edges under the Kirchhoff–Love hypothesis, and elastic force vector and associated Hessian matrix required by equations of motion are later derived based on symbolic calculation. Through extensive validation with available theoretical solutions and finite element method (FEM) simulations in literature, our model demonstrates high accuracy in predicting the nonlinear behavior of axisymmetric shells. Importantly, compared to the classical theoretical model and three-dimensional (3D) FEM simulation, our model is highly computationally efficient, making it suitable for large-scale real-time simulations of nonlinear problems of shell structures such as instability and snap-through phenomena. Moreover, our framework can easily incorporate complex loading conditions, e.g., boundary nonlinear contact and multi-physics actuation, which play an essential role in the use of engineering applications, such as soft robots and flexible devices. This study demonstrates that the simplicity and effectiveness of the 1D discrete differential geometry-based approach render it a powerful tool for engineers and researchers interested in nonlinear mechanics analysis of axisymmetric shells, with potential applications in various engineering fields.

Adaptive Control Strategies for Enhanced Integration of Solar Power in Smart Grids Using Reinforcement Learning

Integrating solar power into smart grids is challenging because of the variable nature of solar energy. This study focuses on implementing reinforcement learning (RL) using a Deep Q-Network algorithm to enhance the stability and efficiency of a grid. A custom environment was designed using OpenAI Gym, in which real-time simulation of grid operations was conducted using real-time data on solar power, weather, and other grid metrics. The trained RL agent exhibited high predictability in optimally distributing the load and managing the battery storage, with R-squared = 0.886, mean average error = 1,173,046.55 Wh, and root mean squared error = 2,075,515.10 Wh. The model effectively captured the seasonality and daily variations in solar power generation. Forecasting using the proposed model provides insights into future energy trends and uncertainties. The reward function will be further refined and scaled for more complex energy systems by incorporating additional variables and hybrid approaches. This study highlights the potential of RL-based adaptive control strategies for developing more efficient and resilient integration of renewable energy sources into smart grids.

Modeling Method for the Real-Time Simulation of Bridge-Based High-Switching-Frequency Power Electronic Converters

Modeling Method for the Real-Time Simulation of Bridge-Based High-Switching-Frequency Power Electronic Converters

Artificial neural network enabled photovoltaic-thermoelectric generator modelling and analysis

Photovoltaic-Thermoelectric Generator (PV-TEG) system has emerged as a promising approach to significantly enhance the efficiency of conventional PV cells. However, optimizing the performance of these hybrid systems presents a formidable challenge due to their complex structure and multitude of design parameters. This study tackles such challenge by developing a machine learning based Artificial Neural Network (ANN) model which comprises two sub-ANN models that can work independently for PV and TEG modules or in combination through a cyclic approach for the hybrid PV-TEG system. The model demonstrates remarkable versatility, allowing control over various parameters such as PV coating, device geometry, and environmental conditions. Compared to COMSOL simulations, the ANN model achieves over 97.6 % accuracy with a 6000-fold increase in simulation speed, enabling extensive parameter sweeps and insightful system analysis. Within 18 min, the model conducted a real-time simulation using 8712 weather data entries from Singapore in 2022 and predicted that the hybrid PV-TEG system would generate a total power of 265 kWh/m2, 6.4 % more than that of the standalone PV system with an average system temperature reduction of 7 K. The model's rapid processing capabilities and high accuracy are particularly beneficial for large-scale simulations and practical applications in renewable energy technology.

FPGA-Based Implicit–Explicit Real-Time Simulation Solver for Railway Wireless Power Transfer With Nonlinear Magnetic Coupling Components

FPGA-Based Implicit–Explicit Real-Time Simulation Solver for Railway Wireless Power Transfer With Nonlinear Magnetic Coupling Components

A Modified Algorithm for the L/C-based Switch Model of Power Converters in Real-Time Simulation Based on FPGA

A Modified Algorithm for the L/C-based Switch Model of Power Converters in Real-Time Simulation Based on FPGA

Positive sequence component based directional relaying for lines integrated with solar photovoltaic plant

Different fault current characteristics of converter interfaced solar photovoltaic plants as compared to the synchronous generator based sources impose challenges to the commonly used directional relaying methods. In this work, the issues with phasor based directional relay algorithms are analysed for the solar plant connected lines. A directional relaying method is proposed for such connectivity using the phase angle difference between positive sequence voltage and the line current measured at the local bus relay. Using PSCAD/EMTDC simulations the proposed method is tested for solar plant connected 39 bus system and validated using field data. The accuracy of the proposed method is also evaluated on a real-time simulation platform. Comparative analysis with the conventional directional relaying methods reveals the superiority of the proposed method.

A Reduced-Order Model of a Nuclear Power Plant with Thermal Power Dispatch

This paper presents reduced-order modeling of thermal power dispatch (TPD) from a pressurized water reactor (PWR) for providing heat to nearby heat consuming industrial processes that seek to take advantage of nuclear heat to reduce carbon emissions. The reactor model includes the neutronics of the reactor core, thermal–hydraulics of the primary coolant cycle, and a three-lump model of the steam generator (SG). The secondary coolant cycle is represented with quasi-steady state mass and energy balance equations. The secondary cycle consists of a steam extraction system, high-pressure and low-pressure turbines, moisture separator and reheater, high-pressure and low-pressure feedwater heaters, deaerator, feedwater and condensate pumps, and a condenser. The steam produced by the SG is distributed between the turbines and the extraction steam line (XSL) that delivers steam to nearby industrial processes, such as production of clean hydrogen. The reduced-order simulator is verified by comparing predictions with results from separate validated steady-state and transient full-scope PWR simulators for TPD levels between 0% and 70% of the rated reactor power. All simulators indicate that the flow rate of steam in the main steam line and turbine systems decrease with increasing TPD, which causes a reduction in PWR electric power generation. The results are analyzed to assess the impact of TPD on system efficiency and feedwater flow control. Due to the simplicity of the proposed reduced-order model, it can be scaled to represent a PWR of any size with a few parametric changes. In the future, the proposed reduced-order model will be integrated into a power system model in a digital real-time simulator (DRTS) and physical hardware-in-the-loop simulations.

Obstacle Avoidance Path Planning Strategy for Autonomous Vehicles Based on Genetic Algorithm

In order to enhance the driving ability of autonomous vehicles on structured roads and enable them to plan safe and comfortable paths, we propose an obstacle avoidance path strategy for autonomous vehicles based on genetic algorithm. The use of Frenet-Serret enhances the adaptability of the algorithm in complex environments. In order to improve the generation and optimisation of obstacle avoidance trajectory, we establish an anti-collision model. When the vehicle faces a potential collision with an obstacle, the genetic algorithm quickly iterates and selects the first nine genes to generate the rough solution and convex space of the path. Combined with convex space, the quadratic programming method will numerically optimise the generated rough solution to generate an accurate path that satisfies the constraints. In addition, in order to ensure the safety and comfort in the process of obstacle avoidance, based on the dynamic constraints of the vehicle, the speed planning is used to determine the speed curve. We simulate in various scenarios involving moving obstacles. The real-time simulation based on the HIL platform proves that the proposed path planning strategy is effective in various driving scenarios.

Discussion on the accuracy of methods for determining interface force between numerical and physical substructures in shaking table-based real-time hybrid simulation

Real-time hybrid simulation (RTHS) is a developing experimental technology that combines the advantages of numerical simulation and physical test. In RTHS, the interface force is a key physical quantity coupling the dynamic response of physical substructure and numerical substructure. An inaccurate force determination method can distort RTHS results and may cause incorrect estimations of the dynamic performance of structures. This article aims to systematically discuss the impact of possible error in determining the interface force during shaking table-based RTHS. The errors caused by two typical force determination methods, (1) using force sensors and (2) using strain gauges, are comprehensively investigated. These two force determination methods are typically used for (1) performance evaluation of nonlinear damping systems and (2) investigation of soil–structure interaction effects. Virtual hybrid simulation numerical models (in which both physical and numerical substructures are simulated numerically) representing the interface force determination processes are established. The impacts of error on the RTHS results are evaluate quantitatively. The reported findings can assist in developing a deeper understanding of the causes of errors during RTHS and enhance the experimental designs. This, in turn, leads to more accurate and reliable results in RTHS testing.

Enhanced Medical Education for Physically Disabled People through Integration of IoT and Digital Twin Technologies

This research presents an innovative approach to revolutionize IoT service development in medical education, specifically designed to empower individuals with physical disabilities. By integrating digital twin technology, we offer dynamic virtual representations of tangible assets, facilitating real-time simulation, monitoring, and feedback. A unique visual response algorithm has been developed to enhance the processing of visual vector data, resulting in a more efficient IoT service development process. Our method demonstrates superior performance over traditional techniques, particularly in achieving higher intrinsic variable merging values, which is critical for accurate and accessible visualization. The practical applications of this technology are highlighted through case studies that demonstrate how physically disabled students can benefit from interactive and immersive educational experiences. For instance, students can engage with the digital twins of medical equipment, allowing them to practice procedures and gain hands-on experience in a virtual environment without physical barriers. This approach not only improves accessibility but also personalizes learning experiences, adapting to the unique needs of each student. The research underscores the importance of inclusive design in developing IoT services, ensuring higher inclusivity rates and addressing diverse learning patterns. The findings suggest that the integration of IoT and digital twin technologies can significantly enhance medical education, making it more accessible, effective, and inclusive for physically disabled individuals. This study lays the groundwork for future advancements in this field, highlighting the potential for ongoing technological innovations to further transform medical education.

Electrochemical-mechanical coupled lithium growth in fiber-structured electrodes

Lithium plating (stripping) on the electrode surface and embedding inside the electrode occur simultaneously in lithium-ion batteries during fast (dis)charging, which involves both deposition and diffusion mechanisms. The paper presents a developed finite-element procedure that accommodates these two mechanisms, facilitating the modeling of the (dis)charging process in electrodes. The framework, which integrates interface electrochemical reaction kinetics, electrochemical-mechanical coupling, comprehensive constitutive models for silicon/graphite/lithium, and a surface growth re-meshing algorithm, is capable of real-time simulation of the surface deposition and coupled diffusion-deformation processes on the electrode substrate. We examined the effects of charging rate, diffusion rate and volumetric expansion on the stress of the plated lithium layer in a fiber-structured electrode. By accounting for creep in lithium metal and subsequent stress relaxation, we obtained time-dependent stress profiles in the plated lithium layer. As an application, we quantified electroplating stresses in both fiber-structured graphite and silicon electrodes. Taking the silicon electrode as a model case, we demonstrate that hollow fiber structural electrodes can also alleviate the stress in the surface lithium-plating layer. The numerical framework may be further applied to explorations for the optimization of electrode structures in advanced high performance lithium-ion batteries.

Enhanced pilot protection scheme for half-wavelength transmission line based on the conservation of traveling wave energy

The half-wavelength transmission system is a viable technology for long-distance and large-capacity power transmission. It can safely and efficiently transmit a large amount of clean energy to remote load centers. However, the traditional traveling wave protection methods have reliability and speed limitations for HWTL lines. To overcome these limitations, this paper proposes a novel and robust pilot protection scheme based on the conservation of traveling wave energy at the protection installation. The proposed scheme uses the constant equation relationship between fault-traveling waves, reflected waves and refracted waves at the measurement end to significantly improve the reliability and effectiveness of the protection mechanism. The blocking protection operation logic constructed by the inequality directional element is used to improve the rapidity of the pilot protection scheme. The theoretical analysis and real-time digital simulator (RTDS) digital-analog hybrid test demonstrate that the action equation of the proposed protection scheme is explicit to the operating value. The novel scheme exhibits enhanced resilience against high transition resistance and the impact of impulse corona while ensuring both reliability and rapidity.© 2017 Elsevier Inc. All rights reserved.

Machine Learning for Real-Time Building Outdoor Wind Environment Prediction Framework in Preliminary Design: Taking Xinjiekou Area of Nanjing, China as the Case

The incorporation of physical environmental performance as a primary consideration in building design can facilitate the harmonization of the built environment with the surrounding site and climate, enhance the building’s environmental adaptability and environmental friendliness, and contribute to the achievement of energy-saving and emission-reduction objectives through the integration of natural lighting and ventilation. General computational fluid dynamics (CFD) can help architects make accurate predictions and effectively control the building’s wind environment. However, CFD integration into the design workflow in the preliminary stages is frequently challenging due to program uncertainty, intricate parameter settings, and substantial computational expenses. This study offers a methodology and framework based on machine learning to overcome the complexity and computational cost barriers in simulating outdoor wind environments of buildings. In this framework, the machine learning model is trained using an automated CFD simulation system based on Butterfly and implemented within the Rhino and Grasshopper environment. This framework provides real-time simulation feedback within the design software and exhibits promising accuracy, with a Structural Similarity Index Measure (SSIM) ranging from 90–97% on a training dataset of 1200 unique urban geometries in Xinjiekou Area of Nanjing, China. Furthermore, we programmatically integrate various parts of the simulation and computation process to automate multiscenario CFD simulations and computations. This automation saves a significant amount of time in producing machine-learning training sets. Finally, we demonstrate the effectiveness and accuracy of the proposed working framework in the design process through a case study. Although our approach cannot replace CFD simulation computation in the later design stages, it can support architects in making design decisions in the preliminary stages with minimal effort and immediate performance feedback.