检索结果-内蒙古大学图书馆

Pattern Recognition and Machine Learning (PRML), IEEE International Conference on

作者： Xiang Wei Yang Zhou Yaxin Bai Zihui Li Mingqi Hu Qiuming Liu State Grid Jiangxi Elettric Power co. Ltd Nanchang China Information and Communication Branch of State Grid Jiangxi Electric Power Co. Ltd. Nanchang China School of Software Engineering Jiangxi University of Science and Technology Nanchang China Advanced Copper Industry College Jiangxi University of Science and Technology Yingtan China

ISBN: (数字)9798350355925

ISBN: (纸本)9798350355932

Accurate short-term electricity load forecasting is essential to ensure the safe, reliable, and economically efficient operation of power systems. However, traditional forecasting methods are increasingly inadequate to meet the demand for ever more precise load predictions. In response to this issue, a CNN-BILSTM-Attention neural network method optimized based on an improved Sparrow Search Algorithm is proposed for short-term electricity load forecasting. Firstly, the Sin chaotic mapping strategy is utilized to initialize the Sparrow population, enhancing the diversity of population positions. Additionally, the cosine optimization algorithm is introduced into the formula for updating the joiner's position. This aims to address the decrease in global search capability in the later iterations of the Sparrow algorithm, thereby enhancing the accuracy of the Sparrow search algorithm; Next, the ISSA algorithm is employed to optimize the CNN-BILSTM-Attention neural network. This helps avoid overly random initialization of the CNN-BILSTM-Attention neural network's initial weight thresholds, thus enhancing the stability of prediction results; Finally, load forecasting is conducted and compared with other algorithmic models for analysis. Additionally, for the WOA-CNN-BILSTM-Attention model, RMSE decreases by 1.832%, with a corresponding MAE reduction of 1.073%. Similarly, for the PSO-CNN-BILSTM-Attention model, RMSE decreases by 1.804% and MAE by 1.026%. The results of the case study demonstrate that the proposed model can effectively enhance prediction accuracy and is valid for short-term load forecasting. By accurately predicting the power demand, the reasonable distribution and optimal dispatch of power can be realized, and the power grid fluctuations caused by the load mutation can be reduced, so as to ensure the quality of power supply.

关键词： Machine learning algorithms Accuracy Load forecasting Biological system modeling Neural networks power system stability Prediction algorithms Optimization Thermal stability Load modeling

来源：评论

学校读者我要写书评

暂无评论

software Quality Evaluation of Non-safety Digital I&C System in NPPs 5th

Software Quality Evaluation of Non-safety Digital I&C System...

引用

5th International Symposium on software Reliability, Industrial Safety, Cyber Security and Physical Protection of Nuclear power Plant, ISNPP 2020

作者： Ye, Wang-Ping State Key Laboratory of Nuclear Power Safety Monitoring Technology and Equipment I&C Equipment Qualification and Software V&V Laboratory China Nuclear Power Engineering Company Ltd. Shenzhen China

ISBN: (纸本)9789811634550

As an important process control system in nuclear power plants, non-safety digital I&C system has the characteristics of numerous internal and external interface, complex functions and low development integrity level. Users pay more and more attention to the quality in each phase of its life cycle, such as design, equipment manufacturing, commissioning and verification, delivery, operation and maintenance. This paper studies the software quality evaluation process, and proposes a set of applicable regulations and standards system and quality evaluation model. The contents and key elements of quality evaluation in three important phases of life cycle process are discussed in detail, and the V&V technical requirements and quality management requirements are integrated, which provides a reference for the implementation of new building nuclear power plants and modernization projectsPer. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Nuclear power plants

来源：评论

学校读者我要写书评

暂无评论

Development and Implementation of a Holistic Flexibility Market Architecture

Development and Implementation of a Holistic Flexibility Mar...

引用

2022 IEEE power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2022

作者： Kraft, Oliver Pohl, Oliver Hager, Ulf Heussen, Kai Muller, Nils Afzal, Zeeshan Ekstedt, Mathias Farahmand, Hossein Ivanko, Dmytro Singh, Ankit Leksawat, Sasiphong Kubis, Andreas TU Dortmund University Institute of Energy Systems Energy Efficiency and Energy Economics Dortmund Germany Technical University of Denmark Department of Electrical Engineering Kongens Lyngby Denmark KTH Royal Institute of Technology Division of Network and System Engineering Stockholm Sweden Norwegian University of Science and Technology Department of Electric Power Engineering Trondheim Norway PSI Software AG Electrical Energy Division Research and Development Department Dortmund Germany

ISBN: (纸本)9781665437752

The demand for increasing flexibility use in power systems is stressed by the changing grid utilization. Making use of largely untapped flexibility potential is possible through novel flexibility markets. Different approaches for these markets are being developed and vary considering their handling of transaction schemes and relation of participating entities. This paper delivers the conceptual development of a holistic system architecture for the realization of an interregional flexibility market, which targets a market based congestion management in the transmission and distribution system through trading between system operators and flexibility providers. The framework combines a market mechanism with the required supplements like appropriate control algorithms for emergency situations, cyber-physical system monitoring and cyber-security assessment. The resulting methods are being implemented and verified in a remote-power-hardware-in-the-loop setup coupling a real world low voltage grid with a geographically distant real time simulation using state of the art control system applications with an integration of the aforementioned architecture components. © 2022 IEEE.

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

Monopulse transmitarray antenna fed by aperture-coupled microstrip structure

引用

Frontiers of Information technology & Electronic engineering 2022年第3期23卷 502-510页

作者： Na KOU Shixing YU Zhao DING Zhengping ZHANG College of Big Data and Information Engineering Guizhou UniversityGuiyang 550025China Key Laboratory of Micro-Nano-Electronics and Software Technology ofGuizhou Province Guiyang 550025China Engineering Research Center of Power Semiconductor Device Reliability of the Ministry of Education Guiyang 550025China

An X-band monopulse antenna based on transmitarray with light-weight and low-cost features is designed,fabricated,and *** proposed antenna is composed of a transmitarray lens,a feed source which combines aperture-coupled microstrip antennas,and a sum-difference(SUM-DIFF)compar-atoi\According to simulation and measurement results of the transmitarray based monopulse antenna,gain of sum beam reaches 21.5 dBi.

关键词： antenna pulse transmit

来源：评论

学校读者我要写书评

暂无评论

One-Bit Reconfigurable Reflective Metasurface Based on Electromagnetically Wideband Element

SSRN

引用

SSRN 2023年

作者： Wu, Yuhan Yu, Shixing Kou, Na Ding, Zhao Zhang, Zhengping Key Laboratory of Micro-Nano-Electronics and Software Technology of Guizhou Province Engineering Research Center of Semiconductor Power Device Reliability the Ministry of Education College of Big Data and Information Engineering Guizhou University Guiyang550025 China

In this paper, a one-bit reconfigurable reflective metasurface is proposed by electromagnetically wideband elements is proposed. The element has a double-layer structure, the lower dielectric plate is driven by a electromagnetically push-pull solenoid to adjust the air layer thickness between top layer. The element has a wideband characteristic, the phase difference between 1bit and 0bit in 9.3GHz-16GHz is 180°±10°and the bandwidth of the unit reaches 53.6%. A 12x12 prototype was then designed, simulated and measured at 10GHz, 12.5GHz and 15GHz. The maximum gain is 18.4 dBi, 19.08 dBi, 18.8 dBi. The aperture efficiency is 13.51% at 12.5GHz. The 3dB bandwidth is 16%, and the main beam can scan range of ±40° at the centre frequency. © 2023, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Model-Driven Intelligent Management: Constructing a New Framework for Efficient engineering Safety Monitoring

Model-Driven Intelligent Management: Constructing a New Fram...

引用

Computer technology and Information Science (ISCTIS), International Symposium on

作者： Hong Li Fei Wang Shaoxun Deng Research and Development Department Guizhou Bit Software Co. Ltd. Guiyang China Power China Guiyang Engineering Co. Ltd. Institute of Engineering Safety Science Guiyang China School of Computer Science and Technology Guizhou University Guiyang China

ISBN: (数字)9798350354560

ISBN: (纸本)9798350354577

In the context of ensuring operational safety for reservoir dams and other vital infrastructures, engineering safety monitoring systems play an essential role, functioning as a core component in assessing and guaranteeing structural health. Traditional monitoring systems, however, have been constrained by their reliance on data architectures tailored to specific manufacturers' devices, limiting system scalability and maintainability. This paper introduces an innovative strategy aimed at eliminating differences among instruments, achieving an integrated process from data acquisition, processing, analysis to report *** study adopts JSON format to standardize instrument models, incorporating abstract design principles that define not only fundamental parameters and data fields but also specific computational logic to accommodate diverse monitoring needs. particularly for complex instruments like multipoint displacement meters, the system introduces the concept of virtual instrument types, realizing advanced functionality through combinations of basic instrument models. Furthermore, by employing predefined templates for data visualization, graphics, and analysis, the system can flexibly adapt to various monitoring *** approach has been successfully implemented in the engineering safety monitoring projects of China power Construction Group Guiyang Institute, covering over 82 dams, foundation pits, and other structures, processing more than 20 million monitoring records, significantly enhancing monitoring efficiency and data analysis quality. While the current system operates effectively with relational databases, future research aims to explore its potential within a Bson and NoSQL environment, further boosting scalability and flexibility.

关键词： Meters Dams Instruments Computational modeling Scalability Relational databases Reservoirs Safety Logic Monitoring

来源：评论

学校读者我要写书评

暂无评论

DeST 3.0:A new-generation building performance simulation platform

引用

Building Simulation 2022年第11期15卷 1849-1868页

作者： Da Yan Xin Zhou Jingjing An Xuyuan Kang Fan Bu Youming Chen Yiqun Pan Yan Gao Qunli Zhang Hui Zhou Kuining Qiu Jing Liu Yan Liu Honglian Li Lei Zhang Hong Dong Lixin Sun Song Pan Xiang Zhou Zhe Tian Wenjie Zhang Ruhong Wu Hongsan Sun Yu Huang Xiaohong Su Yongwei Zhang Rui Shen Diankun Chen Guangyuan Wei Yixing Chen Jinqing Peng Building Energy Research Center School of ArchitectureTsinghua UniversityBeijing 100084China School of Architecture Southeast UniversityNanjingJiangsu 210096China School of Environment and Energy Engineering Beijing University of Civil Engineering and ArchitectureBeijing 100044China College of Civil Engineering Hunan UniversityChangshaHunan 410082China School of Mechanical Engineering Tongji UniversityShanghai200092China Beijing Key Lab of Heating Gas SupplyVentilating and Air Conditioning EngineeringBeijing University of Civil Engineering and ArchitectureBeijing 100044China China State Construction Technology Center Beijing 101320China School of Architecture Harbin Institute of TechnologyHarbinHeilongjiang 150090China School of Architecture Xi'an University of Architecture and TechnologyXi'anShaanxi 710055China School of Architecture South China University of TechnologyGuangzhouGuangdong 510641China Institute of Building Environment and Energy China Academy of Building ResearchBeijing 100013China Beijing Key Laboratory of Green Built Environment and Energy Efficient Technology Beijing University of TechnologyBeijing 100124China Key Lab of Built Environment and Energy of Tianjin School of Environmental Science and EngineeringTianjin UniversityTianjin 300350China School of Energy and Power Engineering Nanjing University of Science and TechnologyNanjing 210094China School of Civil Engineering Guangzhou UniversityGuangzhou 510006China Faculty of Computing Harbin Institute of TechnologyHarbinHeilongjiang 150001China Beijing Glory PKPM Technology Co. Ltd.Beijing 100013China Beijing Tangent Software Co. LtdBeijing 100081China Shanghai Huadianyuan Information Technology Co. LtdShanghai200092China Luoyang Hongye Information Technology Co. Ltd.LuoyangHenan 471822China

Buildings contribute to almost 30%of total energy consumption *** building energy modeling programs is of great significance for lifecycle building performance assessment and *** in novel building technologies,the requirements of high-performance computation,and the demands for multi-objective models have brought new challenges for building energy modeling software and *** meet the increasing simulation demands,DeST 3.0,a new-generation building performance simulation platform,was developed and *** structure of DeST 3.0 incorporates four simulation engines,including building analysis and simulation(BAS)engine,HVAC system engine,combined plant simulation(CPS)engine,and energy system(ES)engine,connected by air loop and water loop balancing *** 3.0 offers numerous new simulation features,such as advanced simulation modules for building envelopes,occupant behavior and energy systems,cross-platform and compatible simulation kernel,FMI/FMU-based co-simulation functionalities,and high-performance parallel simulation *** 3.0 has been thoroughly evaluated and validated using code verification,inter-program comparison,and case-study *** 3.0 has been applied in various aspects throughout the building lifecycle,supporting building design,operation,retrofit analysis,code appliance,technology adaptability evaluation as well as research and *** new generation building simulation platform DeST 3.0 provides an efficient tool and comprehensive simulation platform for lifecycle building performance analysis and optimization.

关键词： DeST building performance simulation building energy modeling

来源：评论

学校读者我要写书评

暂无评论

Enhanced Physics-Informed Neural Networks Without Labeled Data for Weakly and Fully Coupled Transient Thermomechanical Analysis

SSRN

引用

SSRN 2024年

作者： Xu, Haihang Wang, Chong Jia, Haikun Liu, Zhenhai Wan, Mingxin Zhang, Zhaohuan Zheng, Yonggang State Key Laboratory of Structural Analysis Optimization and CAE Software for Industrial Equipment Department of Engineering Mechanics School of Mechanics and Aerospace Engineering Dalian University of Technology Dalian116024 China National Key Laboratory of Renewable Energy Grid-Integration China Electric Power Research Institute Beijing100192 China Economic & Technology Research Institute State Grid Shandong Electric Power Company Jinan250021 China

In this paper, a series of enhanced physics-informed neural networks (PINN) models without labeled data is proposed to solve the weakly and fully coupled thermomechanical problems. In these models, to better predict the thermal and mechanical responses, PINNs consisting of different deep neural networks (DNN) representing temperature, displacement, and stress are specifically constructed. Furthermore, to elevate the accuracy and avoid possible training failure, several advanced algorithms are developed to ensure the effectiveness of imposing boundary conditions, refining sampling distributions, and enhancing training strategy. A notable aspect of the enhanced PINNs is their independence from expensive, labeled data, relying solely on the temporal and spatial information embedded within the sampling points. The effectiveness and accuracy of the enhanced PINNs are validated through extensive numerical examples, including heat conduction and both weakly and fully coupled thermomechanical problems. The results demonstrate the significant potential of PINN methodologies in engineering areas involving complex thermomechanical processes. © 2024, The Authors. All rights reserved.

关键词： Heat conduction

来源：评论

学校读者我要写书评

暂无评论

Event-Driven High-resolution Load Data Compression via SAX

Event-Driven High-resolution Load Data Compression via SAX

引用

Frontiers of power and Energy (ACFPE), Asian Conference on

作者： Xueming Zhao Bowei Hu Zhigang Zhang Bo Liu Dongfeng Mi Hao Liu Chengdong Power Supply Branch State Grid Tianjin Electric Power Company Tianjin China School of Electrical and Information Engineering Tianjin University Tianjin China Software Department Tianjin Trans-Energy Technology Co. Ltd Tianjin China

With the continuous development of modern power system, more and more advanced metering devices have been deployed and popularized. A large amount of information is generated for power network analysis, load forecasting, state perception and other aspects, providing information support for the related technical development. However, the increasing volume of data also brings huge pressure to the data storage, transmission, analysis and so on. Therefore, how to achieve data compression while reducing the amount of data and retaining the characteristics of data information as much as possible has become a key concern. In this paper, a high-resolution power load data compression method based on symbolic aggregate approximation (SAX) is adopted. The obtained power load data is first divided into event segment and non-event segment. The non-event segment is processed by SAX, and the event segments are divided into long event segments and short event segments. The original data of the short event segment is retained, and the long event segment is also processed by SAX. The comparison testing demonstrates that our proposed method achieves better performance. The average reconstruction accuracy obtained by RMSE index is 99.78%, and the average compression ratio is 21.90, which is promising for future engineering applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Model-Free Adaptive Optimal Control for Fast and Safe Start-Up of Pumped Storage Hydropower Units

SSRN

引用

SSRN 2023年

作者： Liu, Dong Zhang, Jingjing Lu, Xueding Li, Chaoshun Malik, O.P. College of Energy and Power Engineering North China University of Water Resources and Electric Power Zhengzhou450045 China School of Civil and Hydraulic Engineering Huazhong University of Science and Technology Wuhan430074 China Department of Electrical and Software Engineering University of Calgary CalgaryABT2N 1N4 Canada Huazhong University of Science and Technology China

Pumped storage unit (PSU) is a special kind of hydropower unit, that undertakes the task of power generation, and also performs the function of energy storage. Due to its unique advantages, pumped storage power stations have been extensively developed in China in recent years and play an important role that is difficult to be performed by other energy sources. Although a large number of studies have been carried out on the control of PSUs, most of the control algorithms are based on object models, which results in the control performance depending on the model accuracy to a large extent, limiting the practical application of these algorithms. For this reason, this paper investigates the preliminary application of model-free adaptive control in PSUs. Firstly, a refined nonlinear model of PSU is established, secondly, the model-free adaptive controller of PSU and its parameter optimization strategy are designed, and finally, verification is carried out by simulation studies for four different start-up conditions, and a comprehensive comparison is made with control strategies such as proportional-integral-derivative (PID), fractional-order PID, and nonlinear generalized predictive control. The results show that the proposed method has a significant improvement in both speed and head control performance compared with other methods, which proves the effectiveness and superiority of the method. In addition, the proposed method reduces energy consumption in the regulation process, and the computational cost meets the real-time control requirements, which has a wide range of application prospects. © 2023, The Authors. All rights reserved.

关键词： Real time control

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：