检索结果-内蒙古大学图书馆

A Client Selection Method Based on Loss Function Optimization for Federated Learning

Computer Modeling in engineering & Sciences 2023年第10期137卷 1047-1064页

作者： Yan Zeng Siyuan Teng Tian Xiang Jilin Zhang Yuankai Mu Yongjian Ren Jian Wan School of Computer Science and Technology Hangzhou Dianzi UniversityHangzhou310018China Key Laboratory of Complex System Modeling and Simulation Ministry of EducationHangzhou310018China Zhejiang Engineering Research Center of Data Security Governance Hangzhou310018China Intelligent Robotics Research Center Zhejiang LabHangzhou311100China HDU-ITMO Joint Institute Hangzhou Dianzi UniversityHangzhou310018China

Federated learning is a distributedmachine learningmethod that can solve the increasingly serious problemof data islands and user data privacy,as it allows training data to be kept locally and not shared with other *** trains a globalmodel by aggregating locally-computedmodels of clients rather than their ***,the divergence of local models caused by data heterogeneity of different clients may lead to slow convergence of the global *** this problem,we focus on the client selection with federated learning,which can affect the convergence performance of the global model with the selected local *** propose FedChoice,a client selection method based on loss function optimization,to select appropriate local models to improve the convergence of the global *** firstly sets selected probability for clients with the value of loss function,and the client with high loss will be set higher selected probability,which can make them more likely to participate in ***,it introduces a local control vector and a global control vector to predict the local gradient direction and global gradient direction,respectively,and calculates the gradient correction vector to correct the gradient direction to reduce the cumulative deviationof the local gradient causedby *** experiments to verify the validity of FedChoice on CIFAR-10,CINIC-10,MNIST,EMNITS,and FEMNIST datasets,and the results show that the convergence of FedChoice is significantly improved,compared with FedAvg,FedProx,and FedNova.

关键词： Federated learning model aggregation Non-IID

来源：评论

学校读者我要写书评

暂无评论

Sensorless control of SPMSM Based on Generalized Super-Twisting Observer and Non-Smooth controller

Sensorless Control of SPMSM Based on Generalized Super-Twist...

引用

Chinese control Conference (CCC)

作者： Dejin Chen Ke Yu Shihong Ding Xiangyu Wang Shihua Li School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China School of Electrical and Information Engineering Zhenjiang China

To enhance the estimation accuracy and dynamic performance of sensorless surface-mounted permanent magnet synchronous motor (SPMSM) drives, a sensorless control scheme based on generalized super-twisting observer (GSTO) and non-smooth controller is proposed. Firstly, a GSTO for back electromotive force (back-EMF) estimation is proposed. Compared with the conventional super-twisting observer, the GSTO has a faster convergence rate and stronger robustness due to the additional terms. Then a linear extended state observer (LESO) is adopted to estimate the position, speed, and lumped disturbance at the same time. Moreover, a non-smooth composite speed controller is designed by combining the disturbance feed-forward compensation. Compared with the conventional PI speed controller, the non-smooth controller has a shorter settling time and a better disturbance rejection ability. Finally, the effectiveness of the proposed method is verified by simulation results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Robust Optimization for Energy Chemical Processes under Uncertainties: A Review and Tutorial 4

Data-Driven Robust Optimization for Energy Chemical Processe...

引用

4th International Conference on Industrial Artificial Intelligence, IAI 2022

作者： Ning, Chao Li, Longyan Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Shanghai200240 China

ISBN: (数字)9781665451208

ISBN: (纸本)9781665451208

In recent years, data-driven robust optimization (DDRO) is becoming a popular and effective paradigm to address the challenging issue of uncertainty in energy chemical processes. This paper provides an overview of recent advances in the field of DDRO, with a primary focus on its methods and applications in process industries. Firstly, a brief introduction to various robust optimization model formulations and solution algorithms is presented. Secondly, research achievements of machine-learning enabled uncertainty sets, the corresponding DDRO, and variant techniques are summarized and analyzed in a systematic manner. Additionally, tutorial-like numerical examples are used to illustrate merits of DDRO compared with conventional robust optimization. Finally, fruitful applications of DDRO in energy chemical processes are encapsulated and categorized from domain perspectives. © 2022 IEEE.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Online Learning Distributionally Robust Energy Management of Ammonia-Based Multi-Energy Microgrid 4

Event-Triggered Online Learning Distributionally Robust Ener...

引用

4th International Conference on Industrial Artificial Intelligence, IAI 2022

作者： Li, Longyan Ning, Chao Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Department of Automation Shanghai200240 China

ISBN: (数字)9781665451208

ISBN: (纸本)9781665451208

This paper proposes a novel uncertainty-aware energy management framework for Multi-energy Microgrid (MEMG), which comprehensively comprises electricity, heat, natural gas, hydrogen, and ammonia. In particular, green ammonia is produced from hydrogen, which is derived from electrolysis powered by renewable energy. The proposed framework seamlessly integrates day-ahead optimal scheduling with data-driven model predictive control. To offer a just-in-time resilience to uncertainties of renewable energy and load, we further develop event-triggered online learning distributionally robust model predictive control (ET-OLDRMPC). Specifically, an event trigger mechanism is designed to enable the controller to intelligently switch between certainty-equivalence and distributionally robust schemes as per their respective advantageous regimes, thereby ensuring operation safety while mitigating unnecessary conservatism. For the distributionally robust scheme, we leverage a nonparametric Bayesian model to construct online ambiguity sets of uncertainty distributions, which encode statistical multimodality and local moment information. The effectiveness of the proposed framework is validated in a case study. © 2022 IEEE.

关键词： Ammonia

来源：评论

学校读者我要写书评

暂无评论

Research on the Evaluation of Dispersed Photovoltaics Hosting Capacity Utilizing Measured Data

Research on the Evaluation of Dispersed Photovoltaics Hostin...

引用

IEEE General Meeting Power& Energy Society

作者： Ruipeng Lu Wenping Qin Zhilong Zhu Penghui Qin Xiaoqing Han Peng Wang Shanxi Key Laboratory of Power System Operation and Control Key Laboratory of Cleaner Intelligent Control on Coal & Electricity Ministry of Education College of Electrical and Power Engineering Taiyuan University of Technology Taiyuan China

ISBN: (数字)9798350381832

ISBN: (纸本)9798350381849

To precisely evaluate the power system’s dispersed photovoltaics(PVs) hosting capacity, a method for assessing the maximum accessible capacity of distributed PVs using measured data has been suggested. Firstly, we extract the distributed PVs and bus power curves from the measured data and establish both distributed steady-state grid-following and grid-forming PVs power models. The shapelet method is employed to correct flawed daily load data. The simulated plant growth algorithm is integrated with the K-means clustering algorithm to identify time periods with similar load characteristics. The load decomposition method is utilised to reduce load time-series data into four load categories exhibiting typical industrial, commercial, agricultural, and domestic load characteristics. An enhanced ZIP load model is developed to examine the causes of load changes from a physical perspective. Furthermore, Using the improved dichotomy method, we rapidly analyse the hosting capacity of distributed PVs while adhering to operational safety constraints. We also compare the effects of two PVs types, namely grid-following PVs and grid-forming PVs, on system stability characteristics and hosting capacity. To culminate our study, we verify the simulation through application on an actual 10kV power distribution network.

关键词： Photovoltaic systems Power measurement Grid following Distributed databases Clustering algorithms Power system stability Data models Steady-state Load modeling Grid forming

来源：评论

学校读者我要写书评

暂无评论

Finite-time coordinated path-following control of leader-following multi-agent systems

引用

Frontiers of Information Technology & Electronic engineering 2022年第10期23卷 1511-1521页

作者： Weibin CHEN Yangyang CHEN Ya ZHANG School of Automation Southeast UniversityNanjing 210096China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of EducationSoutheast UniversityNanjing 210096China Robot Department Jiangsu Automation Research InstituteLianyungang 222061China

This paper presents applications of the continuous feedback method to achieve path-following and a formation moving along the desired orbits within a finite *** is assumed that the topology for the virtual leader and followers is *** additional condition of the so-called barrier function is designed to make all agents move within a limited area.A novel continuous finite-time path-following control law is first designed based on the barrier function and *** a novel continuous finite-time formation algorithm is designed by regarding the path-following errors as *** settling-time properties of the resulting system are studied in detail and simulations are presented to validate the proposed strategies.

关键词： Finite-time Coordinated path-following Multi-agent systems Barrier function

来源：评论

学校读者我要写书评

暂无评论

A Digital Twin Framework for Transient Stability Assessment Based on Knowledge Distillation

A Digital Twin Framework for Transient Stability Assessment ...

引用

Power and Electrical engineering (ACPEE), 5th Asia Conference on

作者： Junjie Cui Wenping Qin Zhilong Zhu Ruipeng Lu Penghui Qin Xianzhen Li Key Laboratory of Cleaner Intelligent Control on Coal & Electricity Ministry of Education Shanxi Key Laboratory of Power System Operation and Control College of Electrical and Power Engineering Taiyuan University of Technology Taiyuan China

ISBN: (数字)9798350309638

ISBN: (纸本)9798350309645

In the context of the digital transformation of power systems, various new sensors are capable of acquiring massive real-time data from the power grid, providing an opportunity for the development of digital twins in power systems. This paper proposes a transient stability assessment digital twin framework based on knowledge distillation. Addressing the challenges of high computational resource consumption and model deployment difficulties associated with existing high-precision complex models in transient stability assessment, the knowledge distillation method is introduced for model lightweighting. Simultaneously, the proposed continuous learning online updating strategy enables adaptive online updates for complex operating conditions and structures, enhancing the learning capability for online additions of diverse samples. Using Transformer as the transient stability assessment model, the effectiveness of the proposed approach was validated on the IEEE 39-bus system.

关键词： Training Adaptation models Computational modeling Power system stability Transformers Stability analysis Power grids

来源：评论

学校读者我要写书评

暂无评论

SoftNeRF: A Self-Modeling Soft Robot Plugin for Various Tasks

SoftNeRF: A Self-Modeling Soft Robot Plugin for Various Task...

引用

IEEE/RSJ International Conference on Intelligent Robots and systems (IROS)

作者： Jiwei Shan Yirui Li Qiyu Feng Ditao Li Lijun Han Hesheng Wang Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai China School of Mechanical Engineering Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Building a self-model for robots, enabling them to simulate their physical selves and predict future states without direct interaction with the physical world, is crucial for robot motion planning and control. Existing self-modeling methods primarily focus on rigid robots and typically require significant time, effort, and resources to gather training data. In this study, we introduce SoftNeRF, a self-supervised visual self-model designed for soft robots. We use a hybrid neural shape representation based on the Signed Distance Function (SDF) to capture both the geometry and complex nonlinear motion of soft robots. By leveraging differentiable rendering, our method learns a self-model from readily available RGB images, similar to how humans understand their physical state through reflection. To improve training efficiency and model accuracy, we propose an error-guided adaptive sampling strategy. SoftNeRF can serve as a plug-in for various downstream tasks, even when trained with data unrelated to those tasks. We demonstrate SoftNeRF’s ability to support shape prediction and motion planning for robots in both simulated and real-world environments. Furthermore, SoftNeRF excels in detecting and recovering from damage, thereby enhancing machine resilience. Code is available at: https://***/irmvlab/soft-nerf.

关键词： Training Visualization Adaptation models Accuracy Shape Training data Soft robotics Rendering (computer graphics) Sampling methods Planning

来源：评论

学校读者我要写书评

暂无评论

Quick identification of ABC trilayer graphene at nanoscale resolution via a near-field optical route

引用

Materials Futures 2023年第1期2卷 158-166页

作者： Peiyue Shen Xianliang Zhou Jiajun Chen Aolin Deng Bosai Lyu Zhichun Zhang Shuo Lou Saiqun Ma Binbin Wei Zhiwen Shi Key Laboratory of Artificial Structures and Quantum Control(Ministry of Education) Shenyang National Laboratory for Materials ScienceSchool of Physics and AstronomyShanghai Jiao Tong UniversityShanghai 200240People’s Republic of China Collaborative Innovation Center of Advanced Microstructures Nanjing UniversityNanjing 210093People’s Republic of China Institute of System Engineering Beijing 100191People’s Republic of China

ABC-stacked trilayer graphene has exhibited a variety of correlated phenomena owing to its relatively flat bands and gate-tunable ***,convenient methods are still lacking for identifying ABC graphene with nanometer-scale *** we demonstrate that the scanning near-field optical microscope working in ambient conditions can provide quick recognition of ABC trilayer graphene with no ambiguity and excellent resolution(∼20 nm).The recognition is based on the difference in their near-field infrared(IR)responses between the ABA and ABC *** show that in most frequencies,the response of the ABC trilayer is weaker than the ABA ***,near the graphene phonon frequency(∼1585 cm−1),ABC’s response increases dramatically when gated and exhibits a narrow and sharp Fano-shape resonant line,whereas the ABA trilayer is largely ***,the IR contrast between ABC and ABA becomes reversed and can even be striking(ABC/ABA∼3)near the graphene phonon *** observed near-field IR features can serve as a golden rule to quickly distinguish ABA and ABC trilayers with no ambiguity,which could largely advance the exploration of correlation physics in ABC-stacked trilayer graphene.

关键词： ABC trilayer graphene identification SNOM nanoscale Fano resonance

来源：评论

学校读者我要写书评

暂无评论

DDS-SLAM: Dense Semantic Neural SLAM for Deformable Endoscopic Scenes

DDS-SLAM: Dense Semantic Neural SLAM for Deformable Endoscop...

引用

IEEE/RSJ International Conference on Intelligent Robots and systems (IROS)

作者： Jiwei Shan Yirui Li Lujia Yang Qiyu Feng Lijun Han Hesheng Wang Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai China School of Mechanical Engineering Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Estimating camera motion and continuously reconstructing dense scenes in deformable environments presents a complex and open challenge. Many existing approaches tend to rely on assumptions about the scene’s topology or the nature of deformable motion. However, these assumptions do not hold true in medical endoscopy applications. To address these challenges, we introduce DDS-SLAM, a novel dense deformable semantic neural SLAM that achieves accurate camera tracking, continuous dense scene reconstruction, and high-quality image rendering in deformable scenes. First, we propose a novel hybrid neural scene representation method capable of capturing both natural and artificial deformations. Additionally, by leveraging the 2D semantic information of the scene, we introduce a semantic loss function based on semantic distance fields. This approach guides network optimization at a higher level, thereby enhancing system performance. Furthermore, we validate our method through a series of experiments conducted on several representative medical datasets, demonstrating its superiority over other state-of-the-art approaches. The code is available at: https://***/IRMVLab/DDS-SLAM.

关键词： Simultaneous localization and mapping Tracking system performance Semantics Cameras Rendering (computer graphics) Topology Image reconstruction Optimization Biomedical imaging

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：