检索结果-内蒙古大学图书馆

Data-Driven vs Traditional Approaches to Power Transformer’s Top-Oil Temperature Estimation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Tembo, Francis Bragone, Federica Laneryd, Tor Barreau, Matthieu Morozovska, Kateryna Division of Decision and Control Systems Department of Intelligent Systems KTH Royal Institute of Technology Stockholm Sweden Division of Computational Science and Technology Department of Computer Science KTH Royal Institute of Technology Stockholm Sweden Hitachi Energy Research Västerås Sweden

Power transformers are subjected to electrical currents and temperature fluctuations that, if not properly controlled, can lead to major deterioration of their insulation system. Therefore, monitoring the temperature of a power transformer is fundamental to ensure a long-term operational life. Models presented in the IEC 60076-7 and IEEE standards, for example, monitor the temperature by calculating the top-oil and the hot-spot temperatures. However, these models are not very accurate and rely on the power transformers’ properties. This paper focuses on finding an alternative method to predict the top-oil temperatures given previous measurements. Given the large quantities of data available, machine learning methods for time series forecasting are analyzed and compared to the real measurements and the corresponding prediction of the IEC standard. The methods tested are Artificial Neural Networks (ANNs), Time-series Dense Encoder (TiDE), and Temporal Convolutional Networks (TCN) using different combinations of historical measurements. Each of these methods outperformed the IEC 60076-7 model and they are extended to estimate the temperature rise over ambient. To enhance prediction reliability, we explore the application of quantile regression to construct prediction intervals for the expected top-oil temperature ranges. The best-performing model successfully estimates conditional quantiles that provide sufficient coverage. Copyright © 2025, The Authors. All rights reserved.

关键词： Distribution transformers

Optimal Sensor Placement in Power Transformers Using Physics-Informed Neural Networks

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Sirui Bragone, Federica Barreau, Matthieu Laneryd, Tor Morozovska, Kateryna Division of Decision and Control Systems Department of Intelligent Systems KTH Royal Institute of Technology Stockholm Sweden Division of Computational Science and Technology Department of Computer Science KTH Royal Institute of Technology Stockholm Sweden Hitachi Energy Research Västerås Sweden

Our work aims at simulating and predicting the temperature conditions inside a power transformer using Physics-Informed Neural Networks (PINNs). The predictions obtained are then used to determine the optimal placement for temperature sensors inside the transformer under the constraint of a limited number of sensors, enabling efficient performance monitoring. The method consists of combining PINNs with Mixed Integer Optimization Programming to obtain the optimal temperature reconstruction inside the transformer. First, we extend our PINN model for thermal modelling of power transformers to solve the heat diffusion equation from 1D to 2D space. Finally, we construct an optimal sensor placement model inside the transformer that can be applied to problems in 1D and 2D. Copyright © 2025, The Authors. All rights reserved.

关键词： Integer programming

Intrinsic Motivation in Model-based Reinforcement Learning: A Brief Review

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Latyshev, Artem Panov, Aleksandr I. Moscow Institute of Physics and Technology Moscow Russia Moscow Institute of Physics and Technology Federal Research Center "Computer Science and Control" Russian Academy of Sciences AIRI Moscow Russia

The reinforcement learning research area contains a wide range of methods for solving the problems of intelligent agent control. Despite the progress that has been made, the task of creating a highly autonomous agent is still a significant challenge. One potential solution to this problem is intrinsic motivation, a concept derived from developmental psychology. This review considers the existing methods for determining intrinsic motivation based on the world model obtained by the agent. We propose a systematic approach to current research in this field, which consists of three categories of methods, distinguished by the way they utilize a world model in the agent’s components: complementary intrinsic reward, exploration policy, and intrinsically motivated goals. The proposed unified framework describes the architecture of agents using a world model and intrinsic motivation to improve learning. The potential for developing new techniques in this area of research is also examined. Copyright © 2023, The Authors. All rights reserved.

关键词： Autonomous agents

Deep-Learning-Based Identification of LPV Models for Nonlinear Systems

学校读者我要写书评

暂无评论

Deep-Learning-Based Identification of LPV Models for Nonline...

IEEE Conference on Decision and control

作者： Chris Verhoek Gerben I. Beintema Sofie Haesaert Maarten Schoukens Roland Tóth Control Systems Group Eindhoven University of Technology The Netherlands Institute for Computer Science and Control Budapest Hungary

ISBN: (数字)9781665467612

ISBN: (纸本)9781665467629

The Linear Parameter-Varying (LPV) framework provides a modeling and control design toolchain to address nonlinear (NL) system behavior via linear surrogate models. Despite major research effort on LPV data-driven modeling, a key shortcoming of the current identification theory is that often the scheduling variable is assumed to be a given measured signal in the data set. In case of identifying an LPV model of a NL system, the selection of the scheduling map, which describes the relation to the measurable scheduling signal, is put on the users’ shoulder, with only limited supporting tools available. This choice however greatly affects the usability and complexity of the resulting LPV model. This paper presents a deep-learning-based approach to provide joint estimation of a scheduling map and an LPV state-space model of a NL system from input-output data, and has consistency guarantees under general innovation-type noise conditions. Its efficiency is demonstrated on a realistic identification problem.

关键词： Data-driven modeling Technological innovation Current measurement Simulation Shoulder Estimation State-space methods

Deep-Learning-Based Identification of LPV Models for Nonlinear Systems

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Verhoek, Chris Beintema, Gerben I. Haesaert, Sofie Schoukens, Maarten Tóth, Roland The Control Systems Group Eindhoven University of Technology Netherlands The Institute for Computer Science and Control Budapest Hungary

The Linear Parameter-Varying (LPV) framework provides a modeling and control design toolchain to address nonlinear (NL) system behavior via linear surrogate models. Despite major research effort on LPV data-driven modeling, a key shortcoming of the current identification theory is that often the scheduling variable is assumed to be a given measured signal in the data set. In case of identifying an LPV model of a NL system, the selection of the scheduling map, which describes the relation to the measurable scheduling signal, is put on the users' shoulder, with only limited supporting tools available. This choice however greatly affects the usability and complexity of the resulting LPV model. This paper presents a deep-learning-based approach to provide joint estimation of a scheduling map and an LPV state-space model of a NL system from input-output data, and has consistency guarantees under general innovation-type noise conditions. Its efficiency is demonstrated on a realistic identification problem. © 2022, CC BY-NC-SA.

关键词： Nonlinear systems

Optimized Ensemble Algorithm for Predicting Metamaterial Antenna Parameters

学校读者我要写书评

暂无评论

computers, Materials & Continua 2022年第6期71卷 4989-5003页

作者： El-Sayed M.El-kenawy Abdelhameed Ibrahim Seyedali Mirjalili Yu-Dong Zhang Shaima Elnazer Rokaia M.Zaki Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Faculty of Artificial Intelligence Delta University for Science and TechnologyMansoura35712Egypt Computer Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt Centre for Artificial Intelligence Research and Optimization Torrens University AustraliaFortitude ValleyQLD 4006Australia Yonsei Frontier Lab Yonsei UniversitySeoul03722Korea School of Computing and Mathematical Sciences University of LeicesterLeicesterLE17RHUK Nile Higher Institute for Engineering and Technology MansouraEgypt Computer and Information Technology College Taif UniversityTaifSaudi Arabia Higher Institute of Engineering and Technology Kafrelsheikh Department of Electrical Engineering Shoubra Faculty of EngineeringBenha UniversityEgypt

Metamaterial Antenna is a subclass of antennas that makes use of metamaterial to improve *** antennas can overcome the bandwidth constraint associated with tiny *** learning is receiving a lot of interest in optimizing solutions in a variety of *** learning methods are already a significant component of ongoing research and are anticipated to play a critical role in today’s *** accuracy of the forecast is mostly determined by the model *** purpose of this article is to provide an optimal ensemble model for predicting the bandwidth and gain of the Metamaterial *** Vector Machines(SVM),Random Forest,K-Neighbors Regressor,and Decision Tree Regressor were utilized as the basic *** Adaptive Dynamic Polar Rose Guided Whale Optimization method,named AD-PRS-Guided WOA,was used to pick the optimal features from the *** suggested model is compared to models based on five variables and to the average ensemble *** findings indicate that the presented model using Random Forest results in a Root Mean Squared Error(RMSE)of(0.0102)for bandwidth and RMSE of(0.0891)for *** is superior to other models and can accurately predict antenna bandwidth and gain.

关键词： Metamaterial antenna machine learning ensemble model feature selection guided whale optimization support vector machines

Prediction of miRNA and Disease Association based on Graph Convolution Network using Latent Feature Vector by Positive Samples

学校读者我要写书评

暂无评论

Prediction of miRNA and Disease Association based on Graph C...

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Zhong, Jiancheng Kang, Jiedong Song, Xingran Xiao, Qiu Pan, Yi Hunan Normal University School of Information Science and Engineering Changsha China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen School of Computer Science and Control Engineering Guangdong China

ISBN: (纸本)9781665468190

The traditional approach of wet biological experiments tends to reveal whether there is an association between specific miRNA molecules and diseases, resulting in a lack of reliable negative samples of miRNA-disease associations in existing databases. To deal with the problem that many current computational methods treat unknown miRNA-disease associations in benchmark datasets as negative samples directly, we propose a graph convolutional neural network model, named DNMFGCN-MDA, based on feature extractions of positive samples. Firstly, by only using a dynamic matrix with positive samples, we extracted the potential feature vectors U and V of miRNAs and diseases in low-dimensional space. Then, we combined known miRNA-disease associations with potential feature vectors U and V to construct heterogeneous graph neural networks. Finally, we adopted graph convolutional neural networks to learn the structural features of the heterogeneous graph network and predicted the potential miRNA-disease associations by using linkage prediction. We use a 5-fold cross-validation experiment to evaluate the performance of our mode, and it turns out that our model has an average AUC of 95.23% and 96.07% on the HMDD v2.0 and HMDD v3.2 datasets, respectively, and achieves better-associated performance than that of the comparison method. © 2022 IEEE.

关键词： Forecasting

A One Stage Non-motorized Vehicle Detection Network

学校读者我要写书评

暂无评论

A One Stage Non-motorized Vehicle Detection Network

2022 International Conference on Cyber-Physical Social Intelligence, ICCSI 2022

作者： Fu, Xiaofeng Yuan, Xia Ye, Jialin Bo, Yuming School of Automation Nanjing University of Sicence and Technology Nanjing China Chengdu Southwest Information Control Research Institute Co. Ltd Chendu China School of Computer Science and Engineering Nanjing University of Sicence and Technology Nanjing China

ISBN: (数字)9781665498357

ISBN: (纸本)9781665498357

With the growth of non-motorized vehicles, low-carbon and environmentally friendly travel has gradually become the mainstream of people all over the world. The wide distribution and small proportion of non-motorized vehicles in the image make it difficult for traffic regulators to detection them, which increases the work of urban managers. Focusing on the task of non-motorized vehicle detection, we improve the YOLOv5s. The symmetric revolution module is used to construct the spatial attention mechanism, so as to improve the robustness of the network model. We design a spatial attention module to reduce the parameters. The proposed dimension decoupling module decouples the dimensions of the width and height of the feature map respectively, so that the network can adapt to the width and height of non-motorized vehicle targets. Through multi-scale receptive field fusion module, residual connection is used to improve the detection ability of the network to small targets. Finally, above modules are integrated into the YOLOv5s. Experiments on real road traffic images show that the proposed model has achieved good results in non-motorized vehicle detection. © 2022 IEEE.

关键词： Vehicles

Learning discretized neural networks under Ricci flow

学校读者我要写书评

暂无评论

The Journal of Machine Learning Research

The Journal of Machine Learning Research 2024年第1期25卷 18901-18944页

作者： Jun Chen Hanwen Chen Mengmeng Wang Guang Dai Ivor W. Tsang Yong Liu Institute of Cyber-Systems and Control Zhejiang University China and School of Computer Science and Technology Zhejiang Normal University China Institute of Cyber-Systems and Control Zhejiang University China SGIT AI Lab State Grid Corporation of China China Centre for Frontier Artificial Intelligence Research Agency for Science Technology and Research (A*STAR) Singapore and Institute of High Performance Computing Agency for Science Technology and Research (A*STAR) Singapore and College of Computing and Data Science Nanyang Technological University Singapore

In this paper, we study Discretized Neural Networks (DNNs) composed of low-precision weights and activations, which suffer from either infinite or zero gradients due to the nondifferentiable discrete function during training. Most training-based DNNs in such scenarios employ the standard Straight-Through Estimator (STE) to approximate the gradient w.r.t. discrete values. However, the use of STE introduces the problem of gradient mismatch, arising from perturbations in the approximated gradient. To address this problem, this paper reveals that this mismatch can be interpreted as a metric perturbation in a Riemannian manifold, viewed through the lens of duality theory. Building on information geometry, we construct the Linearly Nearly Euclidean (LNE) manifold for DNNs, providing a background for addressing perturbations. By introducing a partial differential equation on metrics, i.e., the Ricci flow, we establish the dynamical stability and convergence of the LNE metric with the L2-norm perturbation. In contrast to previous perturbation theories with convergence rates in fractional powers, the metric perturbation under the Ricci ow exhibits exponential decay in the LNE manifold. Experimental results across various datasets demonstrate that our method achieves superior and more stable performance for DNNs compared to other representative training-based methods.

关键词： discretized neural networks gradient perturbation information geometry ricci flow riemannian manifold