检索结果-内蒙古大学图书馆

FISS GAN:A Generative Adversarial Network for Foggy Image Semantic Segmentation

IEEE/CAA Journal of Automatica Sinica 2021年第8期8卷 1428-1439页

作者： Kunhua Liu Zihao Ye Hongyan Guo Dongpu Cao Long Chen Fei-Yue Wang School of Computer Science and Engineering Sun Yat-sen UniversityGuangzhou 510006China State Key Laboratory of Automotive Simulation and Control and the Department of Control Science and Engineering Jilin University(Campus Nanling)Changchun 130025China Mechanical and Mechatronics Engineering Department at the University of Waterloo 200 University Avenue West WaterlooON N2L 3G1Canada State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190 Institute of Systems Engineering Macao University of Science and TechnologyMacao 999078China

Because pixel values of foggy images are irregularly higher than those of images captured in normal weather(clear images),it is difficult to extract and express their *** method has previously been developed to directly explore the relationship between foggy images and semantic segmentation *** investigated this relationship and propose a generative adversarial network(GAN)for foggy image semantic segmentation(FISS GAN),which contains two parts:an edge GAN and a semantic segmentation *** edge GAN is designed to generate edge information from foggy images to provide auxiliary information to the semantic segmentation *** semantic segmentation GAN is designed to extract and express the texture of foggy images and generate semantic segmentation *** on foggy cityscapes datasets and foggy driving datasets indicated that FISS GAN achieved state-of-the-art performance.

关键词： Edge GAN foggy images foggy image semantic segmentation GAN semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Repercussions of COVID-19 pandemic on solid waste generation and management strategies

引用

Frontiers of Environmental Science & Engineering 2021年第6期15卷 241-258页

作者： Yangyang Liang Qingbin Song Naiqi Wu Jinhui Li Yuan Zhong Wenlei Zeng Macao Institute of Systems Engineering Macao University of Science and TechnologyMacao 999078China Macao Environmental Research Institute Macao University of Science and TechnologyMacao 999078China State Key Joint Laboratory of Environment Simulation and Pollution Control School of EnvironmentTsinghua UniversityBeijing 100084China

It has been over ten months since the beginning of the 2019 coronavirus disease(COVID-2019),and its impact on solid waste management,especially medical waste,is becoming *** study systematically reviews the potential influences of the COVID-19 pandemic on medical waste,personal protection equipment waste and municipal solid waste(MSW),and discusses the corresponding measures and policies of solid waste management in typical *** results show that the generation of medical waste from the pandemic increased significantly,with 18%‒425%*** is estimated that the daily output of COVID-19 medical waste increased from 200 t/d on Feb.22 to over 29000 t/d at the end of September 2020 throughout the *** use of personal protective equipment will continue to grow in the long-term,while the blockade and isolation measures greatly reduced the volume of commercial waste,especially for tourist cities,and part of this waste was transferred to household ***’attitudes and behavior toward food waste have changed due to the COVID-19 *** response to the pandemic,international organizations and several countries have issued new policies and guidelines and adjusted their management strategies for medical waste and MSW *** pandemic has brought specific challenges to the disposal capacity of medical waste *** has also brought about the stagnation of policies related to the reduction of plastic products and waste *** study will provide some useful information for managers and governmental officials on effective solid waste management during and after the COVID-19 pandemic.

关键词： COVID-19 Medical waste Personal protective equipment Municipal solid waste Waste management

来源：评论

学校读者我要写书评

暂无评论

Analysis and suppression of low-frequency oscillation of photovoltaic cells with inertia control

Analysis and suppression of low-frequency oscillation of pho...

引用

China International Electrical and Energy Conference (CIEEC)

作者： Zhenyang Wang Gangui Yan Yue Zhao Jili Peng Dazhong Wang Shuang Ren Dept. Ministry of Education Key Laboratory of Modern Power System Simulation control and Green Power Technology Northeast Electric Power University Jilin China Dept. State Grid Hengyang Power Supply Branch State Grid Hunan Power Supply Hunan China

Aiming at the problem of low-frequency oscillation when photovoltaic power generation is connected to weak AC system, a linearization model of photovoltaic power generation is established, which ignores current inner loop and considers inertia control. The influence of various leading factors on low-frequency oscillation modes of photovoltaic power generation is analyzed. Finally, a low-frequency oscillation stabilizer (SSDC) is designed according to the phase compensation method to suppress the low-frequency oscillation of power system. The results show that the increase of input power of DC capacitor and the decrease of proportional control parameters of DC voltage loop and PLL will lead to the decrease of system damping and stability. Finally, the electromagnetic simulation model of weak AC system with photovoltaic power generation is built on PSCAD/EMTDC platform, which verifies the validity of eigenvalue analysis results and SSDC.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Multi-Model Fusion Approach for Transformer Fault Detection

A Multi-Model Fusion Approach for Transformer Fault Detectio...

引用

Information Technology,Big Data and Artificial Intelligence (ICIBA), International Conference on IEEE International Conference on

作者： Ke Zhou Wei Zhang Ligang Li Shaoming Pan Chengwei Huang Guangxi Power Grid Equipment Monitoring and Diagnosis Technology Innovation Center Guangxi Key Laboratory of Intelligent Control and Maintenance of Power Equipment Electric Power Research Institute of Guangxi Power Grid CO. LTD. Nanning State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences China Power Supply Bureau of Guangxi Hezhou Power Grid Co. Ltd.

ISBN: (数字)9798350363609

ISBN: (纸本)9798350363616

Addressing the weak generalization capability and suboptimal prediction performance of single mechanistic and data-driven models, this paper proposes a transformer fault detection method based on the fusion of mechanism and data models. Firstly, vibration and current data are collected on-site to train the SVM vibration model and the Adaboost current model. Secondly, current simulation data is obtained using laboratory simulation software. This simulation data, combined with the current data collected under the same conditions on-site, is used as input to train the GBDT error compensation model. Finally, these three models are used as inputs to the GRNN, completing the overall model design. This fusion of mechanistic and data-driven models not only addresses the parameter mismatch issue of the mechanistic model under complex working conditions but also deeply mines time-series data. Experimental results show that The mean squared error of the fusion model is 0.002 lower than that of the data model, and the coefficient of determination is improved by 5.07% compared to the mechanistic model, enhancing the overall predictive accuracy of the model.

关键词： Vibrations Support vector machines Training Accuracy Biological system modeling Fault detection Predictive models Transformers Prediction algorithms Data models

来源：评论

学校读者我要写书评

暂无评论

A Model Integrating Wavelet Convolution and Linear Attention Mechanism for Inventory Management in power Warehouses

A Model Integrating Wavelet Convolution and Linear Attention...

引用

Information Technology,Big Data and Artificial Intelligence (ICIBA), International Conference on IEEE International Conference on

作者： Tao Li Zhengli Zhang Ligang Li Guozheng Du State Grid Shandong Electric Power Company Material Company Jinan China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China

ISBN: (数字)9798350363609

ISBN: (纸本)9798350363616

Accurate inventory management in power warehouses is crucial for maintaining consistency between records and actual stock levels. However, the complex storage layout and the diversity of stored materials often lead to human errors during manual inventory checks, resulting in inefficiencies. To address these challenges, we collected 2,000 images from power warehouse environments and created a binary classification dataset containing images of correctly and incorrectly placed items. We propose a novel network, CWAMNet, specifically designed for visual inventory management in complex power warehouse environments. CWAMNet integrates wavelet convolution and a linear attention mechanism to overcome the limitations of traditional convolutional neural networks (CNNs) and standard attention mechanisms, achieving a balance between model capacity and computational efficiency.

关键词： Solid modeling Visualization Attention mechanisms Accuracy Convolution Computational modeling Inventory management Computational efficiency Convolutional neural networks Standards

来源：评论

学校读者我要写书评

暂无评论

Role of nitrogen cycling functional genes and their key influencing factors in eutrophic aquatic ecosystems

引用

Environmental Reviews 2025年 33卷

作者： Wang, Wenwen Li, Mengze Chen, Peng Yuan, Shengwu Wang, Kun Wang, Shuhang Jiang, Xia State Key Laboratory of Environmental Criteria and Risk Assessment National Engineering Laboratory for Lake Pollution Control and Ecological Restoration State Environment Protection Key Laboratory for Lake Pollution Control Chinese Research Academy of Environmental Science Beijing100012 China MOE Key Laboratory of Resources and Environmental Systems Optimization College of Environmental Science and Engineering North China Electric Power University Beijing102206 China Key Laboratory of Aquatic Botany and Watershed Ecology Wuhan Botanical Garden Chinese Academy of Sciences Wuhan430074 China

The nitrogen cycle, essential for the transformation and circulation of nitrogen, involves key processes such as nitrogen fixation, nitrification, denitrification, and ammonification. Microorganisms are crucial in these processes, influencing water quality through energy conversion and nitrogen cycling. Eutrophication, driven by human activities, increases exogenous nitrogen input, accelerating nitrogen cycling and loss, boosting greenhouse gas emissions, and impacting aquatic ecosystems. Functional genes in the nitrogen cycle, such as amoA (nitrification), nirS, nirK, nosZ (denitrification), and hzs and hzo (anaerobic ammonium oxidation), are indicators of nitrogen transformation in sediments. Environmental factors like temperature, dissolved oxygen (DO), organic matter content, nitrogen levels, pH, and salinity significantly influence these genes’ expression and regulation. For example, temperature changes can affect nitrifying and denitrifying bacteria activities, DO levels impact microbial growth and metabolism, and higher organic matter content stimulates the expression of nitrogen cycle genes. Understanding how these environmental factors affect nitrogen cycling genes is crucial for addressing eutrophication in aquatic ecosystems. This review focuses on the adaptability and responses of nitrogen-associated functional microorganisms and genes environmental changes, offering theoretical insights and practical guidance for sustainable ecosystem management. © 2025 The Authors.

关键词： Microorganisms

来源：评论

学校读者我要写书评

暂无评论

Initial-stage performance evolution of solid oxide fuel cells based on polarization analysis 17

Initial-stage performance evolution of solid oxide fuel cell...

引用

17th International Symposium on Solid Oxide Fuel Cells, SOFC 2021

作者： Wang, Yige Lyu, Zewei Han, Minfang Sun, Zaihong Sun, Kaihua Department of Energy and Power Engineering State Key Laboratory of Control and Simulation of Power Systems and Generation Equipment Tsinghua University Beijing100084 China Xuzhou Huatsing Jingkun Energy Co. Ltd. Jiangsu Province Xuzhou221005 China

ISBN: (纸本)9781607685395

The performance evolution of solid oxide fuel cells (SOFCs) is more pronounced and non-linear in the initial stage, determining the output level during subsequent long-term operation. In this study, an industrial-size (10×10 cm2) cell was tested under 0.1 A cm-2 for 96 hours. I-V-P curves and EIS data under different DC bias (0, 0.05, 0.10, 0.30, 0.50, 0.70 A cm-2) were periodically recorded every 24 hours to investigate the mechanism of initialstage performance evolution. The ohmic loss was identified as the main contributor to the total overpotential, especially under large current density. The cell performance increased during 4-24 h due to the enhancement of anode gas-phase diffusion/conversion processes, while the performance degraded significantly during 48- 96 h caused by the deterioration of anode charge transfer reaction. The EIS evolution trend under different DC bias was consistent, while the evolution degree was larger under smaller current density. © 2021 Electrochemical Society Inc.. All rights reserved.

关键词： Deterioration

来源：评论

学校读者我要写书评

暂无评论

power Load Forecasting Based on COA-Bi-LSTM Method 2

Power Load Forecasting Based on COA-Bi-LSTM Method

引用

2nd International Conference on Electrical Engineering and control Science, IC2ECS 2022

作者： Chen, Gang Zhang, Dian Xiang, Wei Guan, Zhenqi Huang, Jing Chongqing University of Posts and Telecommunications Chongqing Key Laboratory of Complex Systems and Bionic Control Nanan District Chongqing China Economic and Technology Research Institute State Grid Chongqing Electric Power Company Chongqing China

ISBN: (纸本)9798350399165

A power load forecasting method based on Coyote optimization Algorithm-Bidirectional Long short-Term Memory Neural Network (COA-Bi-LSTM) model was proposed in this study to solve the problem of inaccurate power load prediction. Aiming at the problem of artificial selection of neural network hyperparameters leading to inaccurate prediction, COA was used to iteratively optimize the three hyperparameters of Bi-LSTM: learning rate, iteration times and number of hidden units. Two groups of historical load data with different characteristics in January and August 2018 were selected and compared with the proposed method using BP neural network, LSTM and Bi-LSTM, respectively. The simulation results show that the optimized prediction effect is better. The Mean Absolute Percentage Error (MAPE) in the data prediction results in January is reduced by 45.46%, 28.57%, and 24.05% respectively. Meanwhile, the MAPE in the data prediction results in August are respectively reduced by 73.71%, 44.04%, 17.57%, verifying the effectiveness of the method. © 2022 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Ultra-Short-Term Multi-Step Prediction of Wind power Based on ModernTCN and Multi-Task Learning

Ultra-Short-Term Multi-Step Prediction of Wind Power Based o...

引用

IEEE International Conference on power and power and Renewable Energy (ICPRE)

作者： Mao Yang Xiangyu Li Zifen Han Yong Sun Xiqiang Chang Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Ministry of Education (Northeast Electric Power University) Jilin China State Grid Gansu Electric Power Company Gansu China State Grid Jilinsheng Economic And Technological Research Institute Jilin China State Grid Xinjiang Electric Power CO. LTD Xinjiang China

ISBN: (数字)9798350377460

ISBN: (纸本)9798350377477

The intermittent and fluctuating nature of wind energy makes it difficult to accurately predict wind power, leading to low penetration in the wind power grid. To address this problem, this paper designs ultra-short-term multi-step prediction of wind power based on ModernTCN and multi-task learning to improve the prediction accuracy. Firstly, ModernTCN's ability to have a large receptive field and capture cross-variate timing dependencies is exploited to obtain multivariate timing feature information and establish a multi-step mapping of input features to power. Then it is inputted into the MMoE multi-task learning method, and the prediction results are corrected to obtain the ultra-short-term prediction of wind power using multiple expert networks and gating units. The experimental results show that the method proposed in this paper can effectively improve the ultra-short-term prediction accuracy of wind power, and can provide a favourable reference for the scheduling centre to adjust the power generation plan in real-time response to the power demand.

关键词： Renewable energy sources Accuracy Wind energy Wind power generation Predictive models Multitasking Feature extraction Real-time systems Timing Wind forecasting

来源：评论

学校读者我要写书评

暂无评论

Active Thermal control of Grid-Forming Converters Based on DC-link Voltage Synchronization

Active Thermal Control of Grid-Forming Converters Based on D...

引用

IEEE International Conference on power and power and Renewable Energy (ICPRE)

作者： Mingqun Liu Guanming Zeng Xin He Liang Tu Peng He Yihua Zhu Electric Power Research Institute Yunnan Power Grid Co. Ltd. Kunming Yunnan State Key Laboratory of HVDC Electric Power Research Institute China Southern Power Grid National Energy Power Grid Technology R&D Centre Guangzhou China Guangdong Provincial Key Laboratory of Intelligent Operation and Control for New Energy Power System State Key Laboratory of HVDC Electric Power Research Institute China Southern Power Grid Guangzhou China CSG Key Laboratory for Power System Simulation Electric Power Research Institute China Southern Power Grid National Energy Power Grid Technology R&D Centre Guangzhou China

ISBN: (数字)9798350377460

ISBN: (纸本)9798350377477

Grid-forming control, as a key technology for building new power systems, enables inertia and damping characteristics of converters to actively support grid frequency and voltage. However, GFM-based converters are often required to generate short-circuit currents in excess of the rated value to support grid voltage recovery during transient faults, which poses a greater challenge to their electro-thermal stresses. At the same time, the over-issuance of short-circuit current will lead to the aggravation of junction temperature fluctuation, which will shorten the lifetime of the power devices and bring new challenges to their reliability. Based on the above problems, this paper firstly establishes a corresponding electrothermal coupling model for the GFM converter synchronized based on DC voltage. Subsequently, an active thermal control technique based on the adaptive adjustment of switching frequency is proposed, which can not only reduce the junction temperature of the power device under the same short-circuit current amplitude, but also further reduce the junction temperature fluctuation of the power device. Finally, the corresponding circuit as well as thermal circuit models are established by simulation software to verify the effectiveness of the strategy.

关键词： Adaptation models Fluctuations Switching frequency Short-circuit currents control systems Temperature control Junctions Transient analysis Voltage control Grid forming

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：