检索结果-内蒙古大学图书馆

NEAMS IRP challenge problem 1: Flexible modeling for heat transfer for low-to-high Prandtl number fluids for applications in advanced reactors

引用

NUCLEAR ENGINEERING AND DESIGN 2024年 428卷

作者： Bolotnov, Igor A. Iskhakov, Arsen S. Nguyen, Tri Tai, Cheng-Kai Wiser, Ralph Baglietto, Emilio Dinh, Nam Shaver, Dillon Merzari, Elia North Carolina State Univ Dept Nucl Engn Campus Box 7909 Raleigh NC 27695 USA MIT Dept Nucl Sci & Engn 77 Massachusetts Ave Cambridge MA 02139 USA Penn State Univ Dept Nucl Engn 206 Hallowell Bldg University Pk PA 16802 USA Argonne Natl Lab 9700 S Cass Ave Lemont IL 60439 USA

The adoption of liquid metals and molten salts as coolant fluids in advanced reactor designs has challenged traditional turbulence and heat transfer models because of different convective heat transfer characteristics from water. The challenge is exacerbated by the yet-to-be-understood mixed convection regime, which is crucial to passive heat removal. The NEAMS IRP Challenge Problem 1 (CP1) project aims to facilitate scale-flexible heat transfer models that can serve for broader applications in reactor thermal-hydraulic analysis. CP1 research activities include direct numerical simulation (DNS) and the development of advanced turbulence modeling techniques. The DNS efforts study the low- and high-Prandtl mixed convection in the identified canonical flow scenario, from which the fundamental understanding on the effect of buoyancy on turbulence and heat transfer is investigated. The CP1 modeling endeavors aim at advancement of the present engineering models and the employment of the data driven (DD) methods for the turbulence modeling. In the engineering model concentration, the performance of the current CFD models is assessed in the non-unitary Prandtl flows to gain physical understanding of their shortcomings. A framework for model error prediction and error propagation estimation is also established. A DD RANS framework is developed for the frozen prediction of Reynolds stress and turbulent heat flux based on the polynomial tensor representation of the respective quantities. The DD framework showed satisfactory performance over the k - tau model in the forced and mixed convection cases.

关键词： Mixed convection DNS Turbulence modeling Turbulent heat transfer data driven modeling

来源：评论

学校读者我要写书评

暂无评论

NSGA-II based short-term building energy management using optimal LSTM-MLP forecasts

引用

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS 2024年 159卷

作者： Cordeiro-Costas, Moises Labandeira-Perez, Hugo Villanueva, Daniel Perez-Orozco, Raquel Eguia-Oller, Pablo Univ Vigo CINTECX Rua Maxwell S-N Vigo 36310 Spain Univ Vigo Ind Engn Sch Rua Maxwell S-N Vigo 36310 Spain

To conduct analysis on the field of electricity management in buildings is crucial to contribute to the clean energy promotion, energy efficiency, and resilience against climate change. This manuscript proposes a methodology for modeling a predictive and calibrated energy management system (EMS) using a hybrid methodology that combines long short-term memory and multilayer perceptron models (LSTM-MLP) optimized by non -dominated sorting genetic algorithm II (NSGA-II). The proposed approach utilizes global forecast system (GFS) data to anticipate energy consumption fluctuations and optimize the use of distributed energy sources, such as photovoltaic (PV) production, based on knowledge of the electricity prices in the free market one day ahead. This energy trade-off in the building is conducted with NSGA-II, guaranteeing the exploration and the exploitation of energy in the building while minimizing energy costs and energy wastes. The research carried out demonstrates the effectiveness of the hybrid LSTM-MLP model and the advantages of NSGA-II in hyperparameter tuning and in energy balance for sustainable building practices. The methodology conducted is tested in an existing building, the Industrial Engineering School located on the Campus Lagoas-Marcosende of the Universidade de Vigo, Spain.

关键词： data driven modeling Deep learning (DL) Energy management system (EMS) Genetic algorithms Sustainable buildings

来源：评论

学校读者我要写书评

暂无评论

Learning stochastic dynamical system via flow map operator

引用

JOURNAL OF COMPUTATIONAL PHYSICS 2024年 508卷

作者： Chen, Yuan Xiu, Dongbin Ohio State Univ Dept Math Columbus OH 43210 USA

We present a numerical framework for learning unknown stochastic dynamical systems using measurement data. Termed stochastic flow map learning (sFML), the new framework is an extension of flow map learning (FML) that was developed for learning deterministic dynamical systems. For learning stochastic systems, we define a stochastic flow map that is a superposition of two sub -flow maps: a deterministic sub -map and a stochastic sub -map. The stochastic training data are used to construct the deterministic sub -map first, followed by the stochastic sub -map. The deterministic sub -map takes the form of residual network (ResNet), similar to the work of FML for deterministic systems. For the stochastic sub -map, we employ a generative model, particularly generative adversarial networks (GANs) in this paper. The final constructed stochastic flow map then defines a stochastic evolution model that is a weak approximation, in term of distribution, of the unknown stochastic system. A comprehensive set of numerical examples are presented to demonstrate the flexibility and effectiveness of the proposed sFML method for various types of stochastic systems.

关键词： data driven modeling Stochastic dynamical systems Deep neural networks Generative adversarial networks Stochastic differential equations

来源：评论

学校读者我要写书评

暂无评论

Investigating the Applicability of Physics-Based Machine Learning Algorithms to Meta-modeling of Complex Fluids

Investigating the Applicability of Physics-Based Machine Lea...

引用

作者： Mahmoudabadbozchelou, Mohammadamin Northeastern University

学位级别：Ph.D., Doctor of Philosophy

We present several types of physics-based machine learning frameworks, to model, describe, and predict the behavior of complex fluids. In the area of data-driven constitutive meta-modeling, we present Rheology-Informed Neural Networks (RhINNs) and Multi-Fidelity Neural Networks (MFNN), in which the physical intuition is included explicitly and implicitly, respectively. We used RhINNs as an alternative solver for systems of Ordinary Differential Equations (ODEs) in a direct approach, and to learn the model/material parameters using a series of limited experimental data in an inverse platform. MFNN is also used as a data-driven constitutive meta-modeling of complex fluids and compares its rheological predictions with simple Deep Neural Networks (DNNs) and experimental measurements. We will discuss the MFNN predictions of a set of flow curves for a multi-component colloidal and wormlike micelle solution concerning the mixture's temperature, salinity, and aging. Regarding complex fluid flow modeling, non-Newtonian physics-informed neural network (nn-PINNs) is introduced for solving systems of coupled PDEs. nn-PINNs are then employed to solve the constitutive models in conjunction with conservation of momentum while avoiding the mesh generation step, followed by validating for a number of different complex fluids with various constitutive models. These include a range of Generalized Newtonian Fluids empirical constitutive models and some phenomenological models with memory effects and thixotropic timescales and several flow protocols. In the end, we leverage advances in machine learning methodologies to construct rheology-informed graph neural networks (RhiGNets) that are capable of learning the hidden rheology of a complex fluid through a limited number of experiments. A multi-fidelity approach is then taken to combine limited additional experimental data with the RhiGNet predictions to develop “digital rheometers” that can be used in place of a physical instrument. We

关键词： Constitutive modeling data driven modeling Machine learning Rheology Rheology-informed neural networks

来源：评论

学校读者我要写书评

暂无评论

Enforcing exact physics in scientific machine learning: A data-driven exterior calculus on graphs

引用

JOURNAL OF COMPUTATIONAL PHYSICS 2022年 456卷 1页

作者： Trask, Nathaniel Huang, Andy Hu, Xiaozhe Sandia Natl Labs Ctr Comp Res Livermore CA 94550 USA Sandia Natl Labs Radiat & Elect Sci Livermore CA 94550 USA Tufts Univ Dept Math Medford MA 02155 USA

As traditional machine learning tools are increasingly applied to science and engineering applications, physics-informed methods have emerged as effective tools for endowing inferences with properties essential for physical realizability. While promising, these methods generally enforce physics weakly via penalization. To enforce physics strongly, we turn to the exterior calculus framework underpinning combinatorial Hodge theory and physics-compatible discretization of partial differential equations (PDEs). Historically, these two fields have remained largely distinct, as graphs are strictly topological objects lacking the metric information fundamental to PDE discretization. We present an approach where this missing metric information may be learned from data, using graphs as coarse-grained mesh surrogates that inherit desirable conservation and exact sequence structure from the combinatorial Hodge theory. The resulting data-driven exterior calculus (DDEC) may be used to extract structure-preserving surrogate models with mathematical guarantees of well-posedness. The approach admits a PDE-constrained optimization training strategy which guarantees machine-learned models enforce physics to machine precision, even for poorly trained models or small data regimes. We provide analysis of the method for a class of models designed to reproduce nonlinear perturbations of elliptic problems and provide examples of learning H(div)/ H(curl) systems representative of subsurface flows and electromagnetics. Published by Elsevier Inc.

关键词： Scientific machine learning data driven modeling Discrete exterior calculus de Rham complex PDE-constrained optimization Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Control oriented data driven linear parameter varying model for proton exchange membrane fuel cell systems

引用

APPLIED ENERGY 2020年 277卷 115540-115540页

作者： Deng, Zhihua Chen, Qihong Zhang, Liyan Zong, Yi Zhou, Keliang Fu, Zhichao Wuhan Univ Technol Sch Automat Wuhan 430070 Hubei Peoples R China Tech Univ Denmark Ctr Elect Power & Energy DK-4000 Roskilde Denmark CSIC Wuhan Inst Marine Elect Prop Wuhan 430064 Peoples R China

Proton exchange membrane fuel cell systems are widely used to drive vehicles. It is indispensable to establish accurate and simple control oriented model of the system. However, this control oriented model is difficult to build due to the characteristic of strongly nonlinear, coupled and time - varying in proton exchange membrane fuel cell systems. To solve this problem, nonlinear subspace identification method is proposed to discover linear parameter varying model for the proton exchange membrane fuel cell system. The modeling process can be divided into two stages. In the first stage, algebraic transformation method is proposed to transform the nonlinear model to linear parameter varying model. In the second stage, kernel method based subspace identification is presented to identify parameter matrices of the proton exchange membrane fuel cell system. The established model is demonstrated by a 50 kW on board proton exchange membrane fuel cell system under real driving condition. The results show that mean absolute percent error and root mean squared error are as low as 9.6941e - 06 and 0.0957, respectively. Therefore, the control oriented model perfectly agrees with real data. Compared with the prediction error method and recursive neural network nonlinear auto - regressive moving average model with exogenous method, modeling accuracy and speed of the proposed method are the best. Moreover, linear control theory can be employed to design controller based on the linear parameter varying model, which greatly simplifies controller design for proton exchange membrane fuel cell systems.

关键词： Proton exchange membrane fuel cell system data driven modeling Nonlinear subspace identification method Linear parameter varying system Kernel method

来源：评论

学校读者我要写书评

暂无评论

Copula-based Probabilistic Prediction of Grid Frequency Dynamics 25

Copula-based Probabilistic Prediction of Grid Frequency Dyna...

引用

Proceedings of the 16th ACM International Conference on Future and Sustainable Energy Systems

作者： Bolin Liu Maximilian Koblenz Oliver Grothe Institute of Operations Research Analytics and Statistics Karlsruhe Institute of Technology (KIT) Karlsruhe Germany Department of Services and Consulting Ludwigshafen University of Business and Society Ludwigshafen Germany

来源：评论

学校读者我要写书评

暂无评论

Predicting grid frequency short-term dynamics with Gaussian processes and sequence modeling 24

Predicting grid frequency short-term dynamics with Gaussian ...

引用

Proceedings of the 15th ACM International Conference on Future and Sustainable Energy Systems

作者： Bolin Liu Maximilian Coblenz Oliver Grothe Institute of Operations Research the Chair of Analytics and Statistics Karlsruhe Institute of Technology (KIT) Germany Department of Services and Consulting Ludwigshafen University of Business and Society Germany

ISBN: (纸本)9798400704802

modeling and predicting grid frequency is an important task in power system control. While the consideration of external techno-economic features could improve the modeling of the short-term dynamics of grid frequency, such features are often only recorded on an hourly basis and require careful treatment. We present a purely data-driven approach to modeling grid frequency as an alternative to prediction models incorporating physical characteristics of power systems. Using sequence models such as gated recurrent units and transformers, we extract the necessary information and relationships from the static frequency vector to predict the process parameters for the short-term dynamics of frequency following a Gaussian process. Both for the evaluation measures (e.g. MSE, MAE, RMSE) for point estimators and for the measures for probalistic evaluations (e.g. Negative Log Likelihood Score, CPRS and Energy Score), our prediction performance is comparable to state-of-the-art models and outperforms various purely data-driven models such as daily profiles and k-nearest-neighbour profiles. Moreover, synthetic time series generated by our models can successfully reproduce the main statistical characteristics of the grid frequency.

关键词： data driven modeling electric power system power-grid frequency

来源：评论

学校读者我要写书评

暂无评论

data-driven Online Energy Scheduling of a Microgrid Based on Deep Reinforcement Learning

引用

ENERGIES 2021年第8期14卷 2120-2120页

作者： Ji, Ying Wang, Jianhui Xu, Jiacan Li, Donglin Northeastern Univ Coll Informat Sci & Engn Shenyang 110819 Peoples R China

The proliferation of distributed renewable energy resources (RESs) poses major challenges to the operation of microgrids due to uncertainty. Traditional online scheduling approaches relying on accurate forecasts become difficult to implement due to the increase of uncertain RESs. Although several data-driven methods have been proposed recently to overcome the challenge, they generally suffer from a scalability issue due to the limited ability to optimize high-dimensional continuous control variables. To address these issues, we propose a data-driven online scheduling method for microgrid energy optimization based on continuous-control deep reinforcement learning (DRL). We formulate the online scheduling problem as a Markov decision process (MDP). The objective is to minimize the operating cost of the microgrid considering the uncertainty of RESs generation, load demand, and electricity prices. To learn the optimal scheduling strategy, a Gated Recurrent Unit (GRU)-based network is designed to extract temporal features of uncertainty and generate the optimal scheduling decisions in an end-to-end manner. To optimize the policy with high-dimensional and continuous actions, proximal policy optimization (PPO) is employed to train the neural network-based policy in a data-driven fashion. The proposed method does not require any forecasting information on the uncertainty or a prior knowledge of the physical model of the microgrid. Simulation results using realistic power system data of California Independent System Operator (CAISO) demonstrate the effectiveness of the proposed method.

关键词： microgrid energy management data driven modeling proximal policy optimization recurrent neural network

来源：评论

学校读者我要写书评

暂无评论

Reconstruction of observed mechanical motions with artificial intelligence tools

引用

NEW JOURNAL OF PHYSICS 2022年第7期24卷 073021页

作者： Jakovac, Antal Kurbucz, Marcell T. Posfay, Peter Wigner Res Ctr Phys Dept Computat Sci 29-33 Konkoly Thege Miklos St H-1121 Budapest Hungary Corvinus Univ Budapest Dept Stat 8 Fovam Sq H-1093 Budapest Hungary

The goal of this paper is to determine the laws of observed trajectories assuming that there is a mechanical system in the background and using these laws to continue the observed motion in a plausible way. The laws are represented by neural networks with a limited number of parameters. The training of the networks follows the extreme learning machine idea. We determine laws for different levels of embedding, thus we can represent not only the equation of motion but also the symmetries of different kinds. In the recursive numerical evolution of the system, we require the fulfillment of all the observed laws, within the determined numerical precision. In this way, we can successfully reconstruct both integrable and chaotic motions, as we demonstrate in the example of the gravity pendulum and the double pendulum.

关键词： data driven modeling mechanical motions artificial intelligence numerical determination of physical laws renormalization

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：