检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhang, Heng He, Yun-Ling Liu, Dong Hang, Qin Yao, He-Min Xiang, Di Chongqing University of Posts and Telecommunications Chongqing400065 China Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of China Chengdu610213 China CNNC Engineering Research Center of Nuclear Energy Software and Digital Reactor Chengdu610213 China

The neutron diffusion equation plays a pivotal role in the analysis of nuclear reactors. Nevertheless, employing the Physics-Informed Neural Network (PINN) method for its solution entails certain limitations. Traditional PINN approaches often utilize fully connected network (FCN) architecture, which is susceptible to overfitting, training instability, and gradient vanishing issues as the network depth increases. These challenges result in accuracy bottlenecks in the solution. In response to these issues, the Residual-based Resample Physics-Informed Neural Network(R2-PINN) is proposed, which proposes an improved PINN architecture that replaces the FCN with a Convolutional Neural Network with a shortcut(S-CNN), incorporating skip connections to facilitate gradient propagation between network layers. Additionally, the incorporation of the Residual Adaptive Resampling (RAR) mechanism dynamically increases sampling points, enhancing the spatial representation capabilities and overall predictive accuracy of the model. The experimental results illustrate that our approach significantly improves the model’s convergence capability, achieving high-precision predictions of physical fields. In comparison to traditional FCN-based PINN methods, R2-PINN effectively overcomes the limitations inherent in current methods, providing more accurate and robust solutions for neutron diffusion equations. Copyright © 2024, The Authors. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Composite Structural Battery with Modified Carbon Fiber as Anode 23

Composite Structural Battery with Modified Carbon Fiber as A...

引用

23rd International Conference on Composite Materials, ICCM 2023

作者： Yin, Sha Hu, Zihan Zhou, Limin Department of Automotive Engineering School of Transportation Science and Engineering Beihang University Beijing100191 China School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen518055 China

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Multiuser Physical Layer Communication Without Known Channel

Deep Learning-based Multiuser Physical Layer Communication W...

引用

IEEE Conference on Wireless Communications and Networking

作者： Jiequ Ji Zehui Xiong Kun Zhu Tony Quek Department of Information System and Design Singapore University of Technology Design Singapore College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics China

ISBN: (数字)9798350303582

ISBN: (纸本)9798350303599

With the recent development of deep learning (DL), DL-based autoencoder techniques provide a novel paradigm for end-to-end physical layer optimization. In this paper, we address the dynamic interference in an end-to-end communication system with a multiuser Gaussian interference channel. In this context, the standard constellation is not optimal under high interference conditions. To address this issue, we propose an adaptive learning algorithm for learning and predicting dynamic interference. Note that existing DL-based autoencoders are unable to train end-to-end learning systems by deep learning without a known channel. Thus, we propose a generative adversarial network (GAN)-based training scheme to imitate the real channel. Simulation results show that compared with traditional PSK and QAM modulation schemes, our proposed adaptive learning-based auto encoder can achieve significantly lower block error rate (BLER) in presence of interference. Besides, the BLER performance of our proposed GAN-based training scheme is close to that of the optimal training scheme with known channel on different channel models.

关键词： Training Deep learning Adaptive learning Heuristic algorithms Simulation Modulation Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Decision Problems for Non-Affine Multi-Player systems

Hierarchical Decision Problems for Non-Affine Multi-Player S...

引用

2023 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2023

作者： Lin, Danyu Xue, Shan Liu, Derong Zhao, Bo School of Automation Guangdong University of Technology Guangzhou510006 China South China University of Technology School of Computer Science and Engineering Guangzhou510006 China Southern University of Science and Technology School of System Design and Intelligent Manufacturing Shenzhen518055 China Beijing Normal University School of Systems Science Beijing100875 China

ISBN: (纸本)9798350327182

Adaptive dynamic programming is used in this paper to solve the hierarchical decision problem for non-affine multi-player systems. A new affine system is formed by adding control dynamics to the original system. To solve the hierarchical decision problem of the original system, we modeled it as a Stackelberg game in the new system. Adaptive dynamic programming is used to approximate the value functions. The stability of the system is analyzed according to Lyapunov theory, which leads to the conclusion that both the system states and the weight errors are uniformly ultimately bounded. Finally, matlab simulation is used to verify the conclusion. © 2023 IEEE.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Robust Containment Control of Uncertain Multi-Agent systems Subject to Transmission Delays 42

Robust Containment Control of Uncertain Multi-Agent Systems ...

引用

42nd Chinese Control Conference, CCC 2023

作者： Bi, Cong Xu, Xiang College of Artificial Intelligence Nankai University Tianjin300350 China School of System Design and Intelligent Manufacturing Southern University of Science and Technology Guangdong Province Shenzhen China

ISBN: (纸本)9789887581543

This paper investigates the robust containment control problem of uncertain heterogeneous linear multi-agent systems with unbounded transmission delays under some mild assumptions. A novel distributed output feedback control strategy is proposed based on the distributed observer approach and the internal model principle. It is shown that under the proposed control strategy, the output of each follower converges to the convex hull spanned by the outputs of the leaders and the concerned time delayed system is analyzed by the Lyapunov-Krasovskii functional method. A simulation example is provided to show the effectiveness of the proposed controller. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Adaptive Containment Control of Heterogeneous Multi-Agent systems with Unknown Leaders and Communication Delays

Adaptive Containment Control of Heterogeneous Multi-Agent Sy...

引用

2023 IEEE International Conference on systems, Man, and Cybernetics, SMC 2023

作者： Bi, Cong Xu, Xiang The College of Artificial Intelligence Nankai University Tianjin300350 China The School of System Design and Intelligent Manufacturing Southern University of Science and Technology Guangdong Province Shenzhen China

ISBN: (纸本)9798350337020

This paper investigates the containment control problem of heterogeneous linear multi-agent systems with nonuniform bounded distributed communication delays under an assumption that only the neighboring agents of multiple leaders have access to the information on both the system matrices and the states of multiple leaders. Adaptive distributed observers under nonuniform distributed communication delays are proposed to estimate both the system matrices and the states of multiple leaders without the prior knowledge of communication delays. Then a novel distributed output feedback control strategy is proposed based on the adaptive distributed observer. It is shown that under the proposed control strategy, the output of each follower converges to the convex hull spanned by the outputs of the leaders. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Electrolytic Failure Modeling of Aluminum Electrolytic Capacitor by Finite Element Method

Electrolytic Failure Modeling of Aluminum Electrolytic Capac...

引用

Power Electronics and Application Symposium (PEAS), IEEE International

作者： Xinrui Chen Ran Yao Hui Li Wei Lai Yuan Min Cheng Yang Zeyu Duan Siyu Chen State Key Laboratory of Power Transmission Equipment Technology Chongqing University Chongqing China Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of China Chengdu China

The failure rate of aluminum electrolytic capacitor (AEC) is high in power electronic systems. Due to the complex structure of AEC, it is difficult to establish an actual model, so experiments are the common way to analyze the failure of AEC. Thus, this paper proposes a finite element method (FEM) for AEC considering electrolytic failure. Firstly, the mechanism of electrolytic failure and changes of characteristic parameters in the AEC are elucidated. Secondly, an equivalent finite element model is established to simulate and analyze the electrolytic failure of AEC. Finally, the effectiveness of the proposed AEC FEM method is verified through capacitor aging experiments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AN UNSUPERVISED LEARNING-BASED FRAMEWORK FOR EFFECTIVE REPRESENTATION EXTRACTION OF reactor ACCIDENTS

arXiv

引用

arXiv 2022年

作者： Li, Chengyuan Li, Meifu Qiu, Zhifang Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of China Chengdu Sichuan China

Compared to knowledge-based diagnostic systems, data-based methods tend to perform better in terms of speed and accuracy in diagnosing reactor accidents, and have significant advantages in terms of scalability of models. With the increasing use of high-precision system analysis programs in nuclear engineering, the number of high-fidelity computational data for accident simulation is exploding. Therefore, an algorithm that can achieve both automatic extraction of low-dimensional features from the data and guarantee the validity of the features is needed to improve the performance and confidence of the accident diagnosis system. This study proposes an autoencoder-based autonomous learning framework, namely Padded Auto-Encoder (PAE), which is able to automatically encode accident monitoring data that has been noise-added and with partially missing data into low-dimensional feature vectors via a Vision Transformer-based encoder, and to decode the feature vectors into noise-free and complete reconstructed monitoring data. Thus, the encoder part of the framework is able to automatically infer valid representations from partially missing and noisy monitoring data that reflect the complete and noise-free original data, and the representation vectors can be used for downstream tasks for accident diagnosis or else. In this paper, LOCA of HPR1000 was used as the study object, and the PAE was trained by an unsupervised method using cases with different break locations and sizes as the dataset. The encoder part of the pre-trained PAE was subsequently used as the feature extractor for the monitoring data, and several basic statistical learning algorithms for predicting the break locations and sizes. The results of the study show that the pre-trained diagnostic model with two stages has a better performance in break location and size diagnostic capability with an improvement of 41.62% and 80.86% in the metrics respectively, compared to the diagnostic model with end-to-end model st

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Corrosion Behavior of Alumina-Forming Austenitic Steel in Supercritical Carbon Dioxide Conditions: Effects of Nb Content and Temperature

SSRN

引用

SSRN 2023年

作者： Ma, Zhaodandan Cong, Shuo Chen, Huan Liu, Zhu Dong, Yuanyuan Tang, Rui Chen, Yong Guo, Xianglong Science and Technology on Reactor System Design Technology Laboratory Chengdu610041 China Science and Technology on Reactor Fuel and Materials Laboratory Chengdu610041 China Nuclear Power Institute of China Chengdu610041 China Shanghai Jiao Tong University Shanghai200030 China

The corrosion behavior of alumina-forming austenitic (AFA) stainless steels with different Nb additions in supercritical carbon dioxide environment at 500℃, 600℃ and 20 MPa were investigated. A novel structure with a double oxide was identified as outer Cr2O3 oxide film and inner Al2O3 oxide scale with discontinuous Fe-Cr spinel outermost in the steels with low Nb content and a transitional layer, consisting of Cr spinel and γ`-Ni3Al phase was distributed randomly below the oxide scale. The oxidation resistance was improved by decreasing diffusion of oxygen after adding 0.6wt.% Nb. However, the corrosion resistance ability degraded significantly at higher Nb level due to the accelerated diffusion rate of ions through the refined grain boundaries, which resulted in the formation of a continuous thick outer FeCr2O4 layer on the surface and an internal oxide zone. Fe2(Mo, Nb) Laves phase were discovered as well with high Nb addition, which promoted the production of cracks inside the oxide film. Fewer spinel and thinner oxide scales were found after exposure at 500℃. The specific mechanism was discussed. © 2023, The Authors. All rights reserved.

关键词： Alumina

来源：评论

学校读者我要写书评

暂无评论

Advances in Curved Layer Material Extrusion Additive Manufacturing: Machine, Mechanism, and Process Planning 24th

Advances in Curved Layer Material Extrusion Additive Manufac...

引用

24th IFToMM China International Conference on Mechanism and Machine science and Engineering, IFToMM CCMMS 2024

作者： Zhao, Donghua Xiong, Yi School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen 518055 China

ISBN: (纸本)9789819614660

Material Extrusion Additive Manufacturing (MEAM) is revolutionizing rapid prototyping to create complex structures and detailed surfaces. Traditional three-axis 3D printers are limited by planar slicing, restricting the ability to achieve solid freeform fabrication (SFF) due to confined print directions. In contrast, non-planar slicing, also known as curved layer slicing, allows printing in an unlimited range of directions. This innovation necessitates multi-axis 3D printers with more than three degrees of freedom (DOFs), enabling a more agile fabrication process. Despite these advancements, there is a notable gap in systematic research on the machine, mechanisms, and process planning involved in non-planar printing, particularly for printers that operate with collaborative modules (refers to a left-and-right hand system). Thus, this paper critically analyzes the topological configurations of current 3D printing equipment and investigates the application of Quotient Kinematics Machines (QKMs) for innovative machine design. Process planning is vital to achieving fine control and additive processes. Therefore, slicing and path planning strategies (both explicit and implicit) for non-planar printing are reviewed. Composite material MEAM is also discussed, including maximizing anisotropy in continuous-fiber-reinforced polymer (CFRP) parts and 4D planar printing for morphing structures. Moreover, this review addresses the challenges and opportunities surrounding the development of reconfigurable 3D printers, the importance of intelligent planning and in-situ MEAM, and the overarching need for integrated manufacturing, monitoring, and control. Ultimately, the paper highlights the transformative impact that advanced machine design, mechanism synthesis, and process planning strategies could have on MEAM, particularly in achieving versatile print orientations and advanced material deposition to push the boundaries of what can be manufactured. © The Author(s), under exclusive

关键词： Curved layer slicing Material extrusion additive manufacturing Mechanism Process planning

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：