检索结果-内蒙古大学图书馆

IEEE/RSJ International conference on Intelligent Robots and Systems (IROS)

作者： Song, Chen Lau, Darwin Chinese Univ Hong Kong Dept Mech & Automat Engn Hong Kong Peoples R China

ISBN: (数字)9781665479271

ISBN: (纸本)9781665479271

In this paper, a computationally efficient model predictive control (MPC) is proposed for the trajectory tracking of cable-driven robots subject to state/input constraints. While MPC has been an effective tool in dealing with various constraints, the primary drawback is the high computational load caused by the non-convexity of the corresponding optimization problem. In order to avoid the non-convexity, the prediction model in the proposed reference acceleration MPC (RA-MPC) is simplified into a linear one by assuming the reference accelerations being taken in the future horizon steps. As a result, RA-MPC only optimizes for the instantaneous joint accelerations and the corresponding actuator commands for the current step, resulting in a convex quadratic program that can be efficiently solved. It is further shown that by properly selecting parameters, RA-MPC can be interpreted as 'soft-CTC' and 'soft-LQR', where the joint acceleration is allowed to deviate from the corresponding desired value, computed from a PD gain or an LQR gain. The effectiveness of the proposed RA-MPC are demonstrated in both simulation and hardware experiment using cable-driven robots.

关键词： Trajectory tracking Computational modeling simulation Predictive models Hardware Robustness Real-time systems

来源：评论

学校读者我要写书评

暂无评论

DEVELOPMENT OF A DATA-driven TURBULENCE MODEL FOR THERMAL STRATIFICATION ANALYSIS IN REACTOR SYSTEM 30

DEVELOPMENT OF A DATA-DRIVEN TURBULENCE MODEL FOR THERMAL ST...

引用

30th International conference on Nuclear Engineering, ICONE 2023

作者： Liu, Zijing Zhao, Pengcheng Florin, Badea Aurelian Yu, Tao Cheng, Xu Insititute of Applied Thermofluidics Karlsruhe Insititute of Technology Karlsruhe Germany Department of Nuclear Science and Technology University of South China Hengyang China

ISBN: (纸本)9784888982566

Thermal stratification in large pools or enclosures is a very important phenomenon that is critical to nuclear reactor safety, including the cold- and hot-pool mixing in pool-type reactors, reactor cavity cooling system behavior in high-temperature gas-cooled reactors, passive containment cooling in advanced light-water reactors, and thermal stratification in boiling-water reactor suppression pools. It is very important to accurately predict pool temperature and density distributions for both design optimization and safety analyses of these reactor systems. Currently, effective thermal stratification modeling is a multi-scale method, that couples 1-D system-level code and 3-D CFD code, and can provide detailed thermal stratification information while providing system-level information in other domains. However, coupling 2 codes operating at different spatial and temporal scales remains a challenging issue, and high-resolution CFD simulation is computationally intensive. This study developed a data-driven coarse-mesh turbulence model for thermal stratification to improve the efficiency and accuracy of reactor safety analysis. The 3-D fluid conservation equations are modeled with a data-driven turbulence model based on local flow features on a much coarser scale so that the corresponding mesh setup in the CFD code can be consistent with the 1-D system-level code. A machine learning framework has been introduced for the acceleration of RANS by training an deep neural network with a large amount of fine-mesh CFD-generated data to predict steady-state turbulent eddy viscosity. We choose OpenFOAM as the simulation framework, TensorFlow as machine learning framework, and use TensorFlow C API to realize the coupling of OpenFOAM/TensorFlow and the invocation of the data-driven turbulence model. The coupling is introduced by way of a surrogate model prediction task for the turbulence eddy viscosity for the SUPERCAVNA experimental facility problem. This demonstrates the feasib

关键词： Turbulence models

来源：评论

学校读者我要写书评

暂无评论

Fast Transmission of Massive Concurrent Alarm Messages in LoRaWAN 23

Fast Transmission of Massive Concurrent Alarm Messages in Lo...

引用

26th ACM International conference on Modelling, Analysis, and simulation of Wireless and Mobile Systems (MSWiM)

作者： Tamang, Dinesh Heusse, Martin Abrardo, Andrea Duda, Andrzej Univ Pisa Pisa Italy Univ Grenoble Alpes CNRS Grenoble INP LIG Grenoble France Univ Siena Siena Italy

ISBN: (纸本)9798400703669

In the context of the Factories at Major Accident Risk (FMAR), we consider a scenario consisting of multiple sensor nodes that detect dangerous conditions and raise alarms over a LoRaWAN network. Upon event detection, a large number of nodes try to transmit concurrent alarm messages and the reception of at least one message is sufficient for the central server to react. We propose a scheme in which nodes operate in a slotted-time mode after the detection of the triggering event and they can only transmit one packet in a randomly chosen slot. The choice of the transmission slot follows a specific probability distribution that maximizes the probability of successful reception of at least one packet subject to real-time latency constraints. We provide an optimization framework to find the optimal distribution for choosing a transmission slot. We validate the proposed scheme by simulations and provide numerical results to compare the performance for three different slot choice distributions: i) uniform, ii) the distribution used in the Sift protocol [8], and iii) the proposed optimal distribution. The results show that the proposed optimal distribution leads to much better probability of successful packet delivery than other distributions.

关键词： LoRaWAN Cyber-Physical Systems Industrial IoT Event-driven Transmissions Concurrent Transmissions Probability of Success

来源：评论

学校读者我要写书评

暂无评论

An Online Learning Approach for Data-driven Model Predictive Control in Building Energy Systems 35

An Online Learning Approach for Data-Driven Model Predictive...

引用

35th International conference on Efficiency, Cost, optimization, simulation and Environmental Impact of Energy Systems, ECOS 2022

作者： Stoffel, Phillip Berktold, Max Kümpel, Alexander Müller, Dirk Aachen Germany

ISBN: (纸本)9788774756989

Worldwide, buildings contribute to about 40 % of the global CO2 emissions. Efficient control algorithms like model predictive control (MPC) are a promising approach to reduce CO2 emissions in the building sector. Using MPC, the thermal building mass can be exploited to store energy and offer flexibility for the electric grid, which is essential for integrating more renewable energy sources. Currently, the bottleneck of applying MPC in the building sector on a wide scale is the vast modeling effort needed. For that reason, data-driven model generation, resulting in data-driven MPC, gains more and more popularity in scientific literature. To successfully employ data-driven MPC, the quality of the training data is crucial. In the best case, the training data cover all possible operation points and variations of disturbances like weather, internal gains, and user behavior. Ideally, the building is excited with various input combinations to learn the system dynamics accurately. However, prolonged excitation and extensive training can be costly and decrease user comfort, reducing acceptance of the approach. Therefore, a reduction of the needed commissioning time is desirable. In our work, we present a data-driven MPC based on artificial neural networks for an exemplary building energy system. Based on an initial controller training, we continuously employ online learning to improve the underlying process model. We systematically investigate the retraining and show how online learning can reduce the necessary amount of initial data to only three days. © Proceedings of ECOS 2022 - 35th International conference on Efficiency, Cost, optimization, simulation and Environmental Impact of Energy Systems.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

A Scaled Prediction Information Product Criterion for Bayesian optimization

A Scaled Prediction Information Product Criterion for Bayesi...

引用

Data-driven optimization of Complex Systems (DOCS), International conference on

作者： Tao Huang Yuwei Shi Yizhong Ma Chenglong Lin Department of Management Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (数字)9798350377842

ISBN: (纸本)9798350377859

Bayesian optimization (BO) is an efficient method for solving expensive black-box optimization problems, but the existing BO could be more efficient and have higher optimal accuracy to improve the greed characteristic of infill criteria in the optimization stage. Considering the greedy characteristics of the Bayesian infill criterion, a novel scaled prediction information product (SPIP) criterion is proposed. In the optimization process, the Gaussian process (GP) model provides the predicted information, and the SPIP criterion conducts the surrogate model management and sample updating, which guarantees the efficient BO process continues until terminated together. Experimental results of six benchmark functions and the aircraft wing design problem show that the proposed method can improve optimization efficiency and reduce the expensive simulation cost while enhancing optimization accuracy.

关键词： Costs Accuracy Atmospheric modeling Computational modeling Gaussian processes Predictive models Bayes methods Aircraft Complex systems optimization

来源：评论

学校读者我要写书评

暂无评论

Using simulation optimization to Improve Zero-shot Policy Transfer of Quadrotors

Using Simulation Optimization to Improve Zero-shot Policy Tr...

引用

IEEE/RSJ International conference on Intelligent Robots and Systems (IROS)

作者： Gronauer, Sven Kissel, Matthias Sacchetto, Luca Korte, Mathias Diepold, Klaus Tech Univ Munich Dept Elect & Comp Engn Arcisstr 21 D-80333 Munich Germany

ISBN: (数字)9781665479271

ISBN: (纸本)9781665479271

In this work, we propose a data-driven approach to optimize the parameters of a simulation such that control policies can be directly transferred from simulation to a realworld quadrotor. Our neural network-based policies take only onboard sensor data as input and run entirely on the embedded hardware. In real-world experiments, we compare lowlevel Pulse-Width Modulated control with higher-level control structures such as Attitude Rate and Attitude, which utilize Proportional-Integral-Derivative controllers to output motor commands. Our experiments show that low-level controllers trained with Reinforcement Learning require a more accurate simulation than higher-level control policies at the expense of being less robust towards parameter uncertainties.

关键词： Uncertain systems PI control Attitude control Computational modeling Reinforcement learning Pulse width modulation Robot sensing systems

来源：评论

学校读者我要写书评

暂无评论

AR/VR Digital Twin for simulation and Data Collection of Robotic Environments 25

AR/VR Digital Twin for Simulation and Data Collection of Rob...

引用

25th IEEE International conference on Autonomous Robot Systems and Competitions, ICARSC 2025

作者： Martins, João G. Nutonen, Karle Costa, Paulo Kuts, Vladimir Otto, Tauno Sousa, Armando Petry, Marcelo R. CRIIS - Centre for Robotics in Industry and Intelligent Systems INESC TEC - Institute for Systems and Computer Engineering Technology and Science Porto 4200-465 Portugal University of Porto (FEUP) Faculty of Engineering Porto 4200-465 Portugal ViruTech - Virumaa innovation center of digitalization and green technologies Taltech Virumaa College Kohtla-Jarve 30322 Estonia Taltech Department of Mechanical and Indusrial Tallinn 19086 Estonia

ISBN: (纸本)9798331538606

Digital twins enable real-time modeling, simulation, and monitoring of complex systems, driving advancements in automation, robotics, and industrial applications. This study presents a large-scale digital twin-testing facility for evaluating mobile robots and pilot robotic systems in a research laboratory environment. The platform integrates high-fidelity physical and environmental models, providing a controlled yet dynamic setting for analyzing robotic behavior. A key feature of the system is its comprehensive data collection framework, capturing critical parameters such as position, orientation, and velocity, which can be leveraged for machine learning, performance optimization, and decision-making. The facility also supports the simulation of discrete operational systems, using predictive modeling to bridge informational gaps when real-time data updates are unavailable. The digital twin was validated through a matrix manufacturing system simulation, with an Augmented Reality (AR) interface on the HoloLens 2 to overlay digital information onto mobile platform controllers, enhancing situational awareness. The main contributions include a digital twin framework for deploying data-driven robotic systems and three key AR/VR integration optimization methods. Demonstrated in a laboratory setting, the system is a versatile tool for research and industrial applications, fostering insights into robotic automation and digital twin scalability while reducing costs and risks associated with real-world testing. © 2025 IEEE.

关键词： Augmented Reality Digital Twin Industrial Metaverse Robotics Virtual Reality

来源：评论

学校读者我要写书评

暂无评论

modeling and Experimental Characterization of Propeller-driven Capsule Endoscope Robot for Gastrointestinal Minimally Invasive Diagnosis

Modeling and Experimental Characterization of Propeller-driv...

引用

4th IEEE International conference on Cyborg and Bionic Systems (CBS)

作者： Wang, Weihao Zhang, Yi Hu, Chengzlu Southern Univ Sci & Technol Shenzhen Key Lab Biomimet Robot & Intelligent Sys Dept Mech & Energy Engn Shenzhen 518055 Peoples R China Southern Univ Sci & Technol Guangdong Prov Key Lab Human Augmentat & Rehabil Shenzhen 518055 Peoples R China

ISBN: (纸本)9781665490283

Wireless capsule endoscopy robots are miniaturized robots that integrate camera, wireless communication, microcontroller, power supply, and other modules. In this paper, we study the modeling and experimental characterization of a propeller-driven capsule endoscopy robot (PCER). The profile of the propeller is challenging to design without detailed drawings because of the complex curved surfaces. The propeller design is achieved in the MIT open-source project OpenProp. The modeling of the propeller and the PCER shell are completed. We used the FLUENT fluid simulation toolkit to evaluate the hydrodynamic performance of the propeller and PCER shell. The thrust generated by the propeller is measured by experiment, and the resistance of PCER shell is measured by experiment following the fluid similarity law. The error between the simulation and the experiment results is within the allowable range, which proves that the hydrodynamic performance parameters of the micro-propeller and the PCER shell calculated by the simulation are reliable, and it provides a new method for the design and optimization of the PCER.

关键词： Shells (structures)

来源：评论

学校读者我要写书评

暂无评论

12th International conference on Evolutionary Multi-Criterion optimization, EMO 2023

12th International Conference on Evolutionary Multi-Criterio...

引用

12th International conference on Evolutionary Multi-Criterion optimization, EMO 2023

ISBN: (纸本)9783031272493

The proceedings contain 44 papers. The special focus in this conference is on Evolutionary Multi-Criterion optimization. The topics include: A Systematic Way of Structuring Real-World Multiobjective optimization Problems;IK-EMOViz: An Interactive Knowledge-Based Evolutionary Multi-objective optimization Framework;an Interactive Decision Tree-Based Evolutionary Multi-objective Algorithm;data-driven Evolutionary Multi-objective optimization Based on Multiple-Gradient Descent for Disconnected Pareto Fronts;Eliminating Non-dominated Sorting from NSGA-III;scalability of Multi-objective Evolutionary Algorithms for Solving Real-World Complex optimization Problems;Multi-objective Learning Using HV Maximization;sparse Adversarial Attack via Bi-objective optimization;preface;visual Exploration of the Effect of Constraint Handling in Multiobjective optimization;investigating Innovized Progress Operators with Different Machine Learning Methods;end-to-End Pareto Set Prediction with Graph Neural Networks for Multi-objective Facility Location;online Learning Hyper-Heuristics in Multi-Objective Evolutionary Algorithms;surrogate-assisted Multi-objective optimization via Genetic Programming Based Symbolic Regression;learning to Predict Pareto-Optimal Solutions from Pseudo-weights;a Relation Surrogate Model for Expensive Multiobjective Continuous and Combinatorial optimization;pareto Front Upconvert by Iterative Estimation modeling and Solution Sampling;an Improved Fuzzy Classifier-Based Evolutionary Algorithm for Expensive Multiobjective optimization Problems with Complicated Pareto Sets;approximation of a Pareto Set Segment Using a Linear Model with Sharing Variables;feature-Based Benchmarking of Distance-Based Multi/Many-objective Optimisation Problems: A Machine Learning Perspective;a Two-Stage Algorithm for Integer Multiobjective simulation optimization;partially Degenerate Multi-objective Test Problems;peak-A-Boo! Generating Multi-objective Multiple Peaks Benchmark Problems with

关键词：

来源：评论

学校读者我要写书评

暂无评论

Economic Planning and Comparative Analysis of Market-driven Multi-Microgrid System for Peer-to-Peer Energy Trading

引用

IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS 2022年第3期58卷 4025-4036页

作者： Ali, Liaqat Muyeen, S. M. Bizhani, Hamed Simoes, Marcelo G. Powerledger Perth WA 6000 Australia Qatar Univ Dept Elect Engn Doha 2713 Qatar Ferdowsi Univ Mashhad Sun Air Res Inst Mashhad *** Razavi Khorasan Iran Univ Vaasa Sch Technol & Innovat Vaasa 65200 Finland

This article focuses on the implementation of peer-to-peer (P2P) energy trading and planning of a grid-connected multi-microgrid system based on an advanced optimization approach. The proposed architecture is comprised of three microgrids (MGs) with combinations of distributed energy resources (DERs), including wind turbines, photovoltaic panels, and storage batteries, to meet the load requirement. A game theory technique, Nash equilibrium, is used to structure the proposed model for multiobjective optimization, where the main objectives are used to determine the correct sizing of DERs and optimum payoff values. Due to the variability of DERs, to maintain lower energy costs, the reliability index (I-R) and levelized cost of energy are the benchmarks considered for optimization. The proposed model is analyzed, and rigorous comparison is carried out for both peer-to-grid and P2P energy trading schemes, considering the Australian profiles for wind speed, solar irradiation, and residential load. The simulation model is built in MATLAB software, and the particle swarm optimization algorithm is exploited for the optimization. The results illustrate that P2P energy trading reduces the payoff value of the multiobjective function (MOF) to 36%. The robustness of MOF is validated and analyzed with different combinations of constant coefficients K-1 and K-2. In the end, the most economical and suitable models with DERs are proposed for each MG, and the results are verified with sensitivity analysis.

关键词： Costs Wind speed Mathematical models Load modeling optimization Australia Peer-to-peer computing Batteries game theory microgrids (MGs) particle swarm optimization (PSO) photovoltaic cells wind power generation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：