检索结果-内蒙古大学图书馆

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

On the Accuracy and Efficiency of the reactor Operation Digital Twin for Parameter Identification and State Estimation

SSRN

引用

SSRN 2023年

作者： Hong, Lizhan Gong, Helin Ji, Hongjun Lu, Jialiang Li, Han Li, Qing Paris Elite Institute of Technology Shanghai Jiao Tong University Shanghai200240 China Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of China Chengdu610041 China

Accurate and efficient online parameter identification and state estimation are crucial to leveraging Digital Twin simulations for optimizing the operation of near-carbon-free nuclear energy systems. In previous works, we have developed the idea of reactor Operation Digital Twin (RODT). However, non-differentiabilities and discontinuities arise when employing some machine learning based surrogate forward models, challenging traditional gradient-based inverse methods and their variants. This study investigates deterministic and metaheuristic algorithms and further develops hybrid algorithms to address such issues. An efficient modular RODT software framework is presented incorporating these methods into its post-evaluation module for comprehensive comparison. Methods are rigorously assessed based on convergence profiles, stability with respect to noise, and computational performance. Numerical results demonstrate that the hybrid KNNLHS algorithm delivers the optimal balance of accuracy and efficiency for real-time online applications. Meanwhile, algorithms like FSA, DE and ADE exhibit slower yet highly accurate performance. This work advances RODT methodologies to harness machine learning and systems modelling for improved reactor monitoring, systematic diagnosis of off-normal events, lifetime management strategies, etc. The developed modular software and novel optimization methods presented offer pathways to realize the full potential of RODT for transforming energy engineering practices. © 2023, The Authors. All rights reserved.

关键词： State estimation

来源：评论

学校读者我要写书评

暂无评论

A Long-term Dependent and Trustworthy Approach to reactor Accident Prognosis based on Temporal Fusion Transformer

arXiv

引用

arXiv 2022年

作者： Li, Chengyuan Qiu, Zhifang Ma, Yugao Li, Meifu Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of China Chengdu610213 China

Prognosis of the reactor accident is a crucial way to ensure appropriate strategies are adopted to avoid radioactive releases. However, there is very limited research in the field of nuclear industry. In this paper, we propose a method for accident prognosis based on the Temporal Fusion Transformer (TFT) model with multi-headed self-attention and gating mechanisms. The method utilizes multiple covariates to improve prediction accuracy on the one hand, and quantile regression methods for uncertainty assessment on the other. The method proposed in this paper is applied to the prognosis after loss of coolant accidents (LOCAs) in HPR1000 reactor. Extensive experimental results show that the method surpasses novel deep learning-based prediction methods in terms of prediction accuracy and confidence. Furthermore, the interference experiments with different signal-to-noise ratios and the ablation experiments for static covariates further illustrate that the robustness comes from the ability to extract the features of static and historical covariates. In summary, this work for the first time applies the novel composite deep learning model TFT to the prognosis of key parameters after a reactor accident, and makes a positive contribution to the establishment of a more intelligent and staff-light maintenance method for reactor systems. Copyright © 2022, The Authors. All rights reserved.

关键词： Nuclear industry

来源：评论

学校读者我要写书评

暂无评论

Intra Fast Mode Decision Algorithm and Hardware design for AVS2

Intra Fast Mode Decision Algorithm and Hardware Design for A...

引用

2021 International Conference on Signal Processing and Machine Learning, CONF-SPML 2021

作者： Xie, Hao Liu, Kaiyang Zhao, Yang Zheng, Xiao Qing, Xianguo Nuclear Power Institute of China Science and Technology on Reactor System Design Technology Laboratory Chengdu China Peking University School of Software and Microelectronics Beijing China

ISBN: (纸本)9781665417341

AVS2 is a kind of video coding standard proposed by China, it adopts 33 intra prediction modes to improve coding performance, while the computational complexity has increased dramatically. In order to reduce the complexity of AVS2 intra mode decision and make the AVS2 hardware encoder meet real-time requirements, this paper proposes the AVS2 intra fast mode decision algorithm and hardware design. The experimental results show that the intra mode decision algorithm and hardware design proposed in this paper can meet the throughput requirement of 1920x1080@60fps at a clock frequency of 300MHz. By using Xilinx FPGA XC7K325T 900 on the Vivado HLS platform for synthesis, only 10% of the LUT, 5% of FF, 5% of BRAM, and 6% of DSP in FPGA resources are consumed to meet the design requirements. © 2021 IEEE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

MDDA: A Multi-scene Recognition Model with Multi-dimensional Domain Adaptation 4

MDDA: A Multi-scene Recognition Model with Multi-dimensional...

引用

4th IEEE International Conference on Electronics technology, ICET 2021

作者： Wan, Naijia Zhang, Changhua Chen, Qian Li, Hao Liu, Xiaobo Wei, Xuedong University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu China University of Electronic Science and Technology of China School of Mechanical and Electrical Engineering Chengdu China Science and Technology on Reactor System Design Technology Laboratory Chengdu China

ISBN: (纸本)9781728176734

Optical Character Recognition is widely used in scenarios from license plate recognition, chip detection to text translation. However, in some special scenarios, there are very few data for training or the target datasets are not marked. This paper mainly aims to establish a multi-scene text recognition model that can achieve accurate results even when the target test dataset is not marked. The model reduces the distance between domains at the feature level by using an adversarial loss and flipping the gradient. For the adversarial loss, each letter has a different domain discriminator to align the features at the character level. We also align the source domain features and target domain features in the background. Experimental results show that our model achieves good performance when the training dataset and test dataset have domain shift, and suggest possible scenarios for potential applications. © 2021 IEEE.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

In-situ Thermal Oxidation of Fusion PFM Tungsten Using Atmospheric Environmental TEM

引用

Microscopy and microanalysis : the official journal of Microscopy Society of America, Microbeam Analysis Society, Microscopical Society of Canada 2023年第1期29卷 1462-1463页

作者： Sainju, Rajat Togaru, Maanas Zhang, Lichun Jiang, Weilin Setyawan, Wahyu Atwani, Osman El Zhu, Yuanyuan Department of Materials Science and Engineering University of Connecticut Storrs CT United States Institute of Materials Science University of Connecticut Storrs CT United States Reactor Materials and Mechanical Design Group Nuclear Sciences Division Pacific Northwest National Laboratory Richland WA United States Materials Science and Technology Los Alamos National Lab Los Alamos NM United States

来源：评论

学校读者我要写书评

暂无评论

Numerical simulation of a UAV impacting engine fan blades

引用

Chinese Journal of Aeronautics 2021年第10期34卷 177-190页

作者： Jingyu YU Bingjin LI Jun LIU Naidan HOU Yingchun ZHANG Yafeng WANG Yulong LI School of Aeronautics Northwestern Poly technical UniversityXi'an 710072China Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of ChinaChengdu 610213China Shanghai Aircraft Airworthiness Certification Center of CAAC Shanghai 200335China China Aircraft Strength Research Institute Xi'an 710065China

A 3D digital model of a small Unmanned Aerial Vehicle(UAV)is obtained by using the method of scanning reverse modeling and joint mapping.A numerical simulation of a small UAV strikes on rotary engine blades,presented in this paper,was performed with a Transient Nonlinear Finite Element code PAM-CRASH software.A test of motor strike on plate was developed and the dynamic response of the plate were obtained to validate the numerical simulation method of a UAV strike on *** on this,dynamic damage response caused by UAV on the engine blades were *** is indicated that the impact process between the UAV and a single blade can be divided into two typical stages:cutting and *** mainly leads to the failure of the leading edge material,and impact mainly leads to the plastic deformation of the *** the same time,it is compared with the damage impacted by bird with the same *** the same mass of bird and UAV,the damage caused by UAV striking fan blade is more serious,and 1.345 kg UAV striking fan blade of typical civil aviation engine is enough to cause damage to flight safety.

关键词： Airworthiness Bird impact Engine fan blade Explicit dynamics UAV

来源：评论

学校读者我要写书评

暂无评论

Corrosion Mechanisms and Differences of Inconel 617 and Incoloy 800h Under High-Temperature Air Ingress Accident

SSRN

引用

SSRN 2024年

作者： Li, Haoxiang Yan, Dapeng Li, Guodong Tian, Changqing An, Jiayi Tan, Jiaqi Zheng, Wei Du, Bin Yin, Huaqiang Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of China Chengdu610213 China State Key Laboratory of Advanced Nuclear Energy Technology Nuclear Power Institute of China Chengdu China Institute of Nuclear and New Energy Technology Key Laboratory of Advanced Reactor Engineering and Safety of Ministry of Education Tsinghua University Beijing China Tsinghua University China

In the high-temperature operation of very high-temperature gas-cooled reactors (VHTRs), "microclimate reaction" are one of the key corrosion reactions of concern. This study investigates the corrosion behavior and mechanisms of the two mainstream high-temperature alloys, Incoloy 800H and Inconel 617, under minor air ingress accidents. The main focus is on comparing and analyzing the "microclimate reaction" corrosion behavior and mechanisms of the two alloys, as well as exploring changes in their mechanical properties. The results show that during the experiment, both alloys primarily underwent oxidation and "microclimate reaction". The double-layer oxide of Cr2 O3 -MnCr2 O4 /MnFe2 O4 and the SiO2 layer on the surface of Incoloy 800H provide good resistance to "microclimate reaction," whereas the single-layer Cr2 O3 oxide on Inconel 617 is not effective in preventing "microclimate reaction". The mechanical property test results indicate that the decarburization caused by "microclimate reaction" does not significantly affect the basic mechanical properties of the alloy. Research on "microclimate reactions" should primarily focus on preventing the oxidation layer from cracking and reducing the time during which the alloy matrix is unprotected by a protective oxide layer. © 2024, The Authors. All rights reserved.

关键词： Gas cooled reactors

来源：评论

学校读者我要写书评

暂无评论

Numerical Study on the Impact Characteristics of a Single Molten Lead Bismuth Droplet on Water

SSRN

引用

SSRN 2024年

作者： Lin, Yue Zhang, Dalin Chen, Yutong Zhang, Xisi Deng, Jian Du, Peng Tian, Wenxi Qiu, Suizheng Su, Guanghui Department of Nuclear Science and Technology State Key Lab. of Multiphase Flow in Power Engineering Shaanxi Key Lab. of Advanced Nuclear Energy and Technology Xi’an Jiaotong University No.28 Xianningxilu Beilinqu Shaanxi Xi’an710049 China Institute of Reactor Engineering Technology China Institute of Atomic Energy Beijing102413 China Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of China Sichuan Chengdu610213 China

As an important link in the possible occurrence of steam explosions, the interaction between molten materials and coolant is of great significance for safety analysis in severe accidents of nuclear reactors. This study is based on the two-dimensional multiphase and multi-component fluid dynamics code ACENA to model the process of single molten lead bismuth droplet impacting a water tank and obtain the velocity changes of the molten droplet as it moves through the water tank. Furthermore, a sensitivity analysis of relevant factors such as the heat transfer area fraction and drag coefficient of the droplet is carried out. To verify models in ACENA, the computation results are compared to experimental data. It is demonstrated that the overall trend of the velocity curve acquired by the ACENA code during the interaction between a molten lead bismuth droplet and water is consistent with the experimental results. The droplet falling velocity increases with the increase in droplet temperature when the temperature of water is the same, and the droplet falling velocity increases with the increase of water temperature at the same droplet temperature. The simulation results by ACENA code for MFCI are in good agreement with experiments which verifies the accuracy of relevant models in ACENA. It can provide an effective means for safety analysis of nuclear reactors in China. © 2024, The Authors. All rights reserved.

关键词： Drops

来源：评论

学校读者我要写书评

暂无评论

Identification Algorithm Framework and Structural model on Input Pattern of Metamorphic Relations 9

Identification Algorithm Framework and Structural model on I...

引用

9th International Conference on Dependable Systems and Their Applications, DSA 2022

作者： Yan, Shiyu Yang, Xiaohua Lu, Zhongjian Li, Meng Gong, Helin Liu, Jie Computer School University of South China Hunan Hengyang China Intelligent Equipment Software Evaluation Engineering Technology Research Center of Hunan Hengyang China Cnnc Key Laboratory on High Trusted Computing Hunan Hengyang China Nuclear Power Institute of China Science and Technology on Reactor System Design Technology Laboratory Chengdu China

ISBN: (数字)9781665488778

ISBN: (纸本)9781665488778

Metamorphic Relation (MR) plays a crucial role in Metamorphic Testing (MT), which can be regarded as the implication relation from the input pattern to the output pattern. Based on MR's properties, the identification of Metamorphic Relations (MRs) can be from its input pattern and output pattern, respectively. However, the finding of the effective input pattern is very first and important. Especially for complicated mathematical function includes more than two input variables, we systematically analyze the structural model of input pattern in MR, propose the concept of the class of basic input pattern, as well as prove that any one input pattern can be expressed as a combination of basic input patterns in scientific computing programs. Moreover, the structural model of input pattern in MR is established based on previous proof. Finally, we put forward an identification algorithm framework and analysis its complexity. The core contribution of our method is to decompose the input pattern identification problem in multi-dimensional space into a single one-dimensional. For this reason, the examples show that the complexity of the algorithm is reduced significantly. © 2022 IEEE.

关键词： Computational complexity

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：