期刊:
IET Conference Proceedings,2025年2024(6):723-727 ISSN:2732-4494
作者机构:
[Yunfeng Li; Tao Wen; Yuhang Zhang; Hangyu Wei; Siyi Xia; Huirong Ye; Yuming Wang] School of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha, People's Republic of China
会议名称:
20th International Conference on AC and DC Power Transmission 2024 (ACDC 2024)
会议时间:
2024
会议地点:
Shanghai, China
会议论文集名称:
20th International Conference on AC and DC Power Transmission 2024 (ACDC 2024)
摘要:
In the modular multilevel converter (MMC) based high voltage direct current (HVDC) transmission system, the high-frequency negative damping effect of the MMC output impedance induces high frequency resonances. The existing active damping controls, such as the virtual series impedance, change the range of high-frequency negative damping effects, thereby suppressing the high-frequency resonances (HFRs). However, it can only be applied to the single operating condition of AC power grid because the single damping controller cannot effectively reshape the impedance characteristics of MMC in multiple HFR risk regions simultaneously. Therefore, a frequency divided active damping control (FDADC) is proposed to address the suppression requirements of multiple HFR risk regions. Based on the simplified model of the MMC in high-frequency band, the analytical calculation method and expressions for the parameters’ selection ranges of the frequency divided damping controller are presented. The parameters of damping controller suitable for multiple operating conditions of AC systems are given, and their effectiveness is verified through electromagnetic transient simulation models.
摘要:
Sand mining can meet market demand and promote local economic development, but it has an impact on riverbank stability and embankment safety, and currently there is still a lack of quantitative research on the safe distance in this regard. Therefore, this study used a seepage finite element analysis method and the Swedish arc sliding method to establish a calculation model for embankment seepage safety and anti-sliding stability based on hydrological surveys and topographic and geological survey data and applied them to a case study of the embankment from Yingtian to Leishi in the tail of the Xiangjiang River in Hunan province, China. The results show that high-intensity sand mining activities can cause serious river channel incision, destroy the balance of river scouring and silting, and easily cause bank slope reconstruction and steep slope collapse; sufficient mining ban areas and safe distance need to be retained to ensure the safety and stability of the embankment. The research methods and conclusions can provide a reference for river sand mining planning, river dredging, and embankment design.
作者机构:
[Runda Luo] Faculty of Information Science and Engineering, Ocean University of China, Shandong, China;[Shengtao Su] School of Electrical & Information Engineering, Changsha University of Science & Technology, Hunan, China
会议名称:
2025 IEEE 8th Information Technology and Mechatronics Engineering Conference (ITOEC)
会议时间:
14 March 2025
会议地点:
Chongqing, China
会议论文集名称:
2025 IEEE 8th Information Technology and Mechatronics Engineering Conference (ITOEC)
摘要:
With the increase of demand side flexible load and the development of new energy technology, the power transaction of distribution network is gradually improved. This paper considers the application of blockchain technology to demand-side electrical energy trading. First of all, the basic framework to meet the needs of various flexible loads and distributed energy trading is established, and then the content of blockchain trading technology is analyzed, and the distribution network intelligent trading based on blockchain technology is realized through the deployment of smart contracts that meet the main characteristics of distributed energy-grid-flexible loads, and finally through matching transactions. Finally, the transaction deployment that meets the main characteristics of the distribution network is realized.
摘要:
Deep learning-based dMRI super-resolution methods can effectively enhance image resolution by leveraging the learning capabilities of neural networks on large datasets. However, these methods tend to learn a fixed scale mapping between low-resolution (LR) and high-resolution (HR) images, overlooking the need for radiologists to scale the images at arbitrary resolutions. Moreover, the pixel-wise loss in the image domain tends to generate over-smoothed results, losing fine textures and edge information. To address these issues, we propose a novel continuous super-resolution method for dMRI, called CSR-dMRI, which utilizes an anatomical structure-assisted implicit neural representation learning approach. Specifically, the CSR-dMRI model consists of two components. The first is the latent feature extractor, which primarily extracts latent space feature maps from LR dMRI and anatomical images while learning structural prior information from the anatomical images. The second is the implicit function network, which utilizes voxel coordinates and latent feature vectors to generate voxel intensities at corresponding positions. Additionally, a frequency-domain-based loss is introduced to preserve the structural and texture information, further enhancing the image quality. Extensive experiments on the publicly available HCP dataset validate the effectiveness of our approach. Furthermore, our method demonstrates superior generalization capability and can be applied to arbitrary-scale super-resolution, including non-integer scale factors, expanding its applicability beyond conventional approaches.
作者机构:
[Yaqing Liu] College of Electrical Engineering, Changsha University of Science and Technology, Changsha, People's Republic of China
会议名称:
4th Energy Conversion and Economics Annual Forum (ECE Forum 2024)
会议时间:
2025
会议地点:
Beijing, China
会议论文集名称:
4th Energy Conversion and Economics Annual Forum (ECE Forum 2024)
摘要:
In recent years, high loss line power theft detection technology has achieved certain results, but in the actual line operation state, there may still exist small amount of power theft users. Since these users steal small amounts of electricity, they are easy to be ignored by inspectors, leading to misjudgment of the existing power theft detection technology, so it is necessary to consider the user's own metering data changes in the power theft detection technology. In this study, a Quantile Regression Neural Network (QRNN) power theft detection method for small amounts of power theft is proposed to take advantage of the fact that the power consumption of dedicated variable users is characterized by continuity. First, the cycle difference between normal users and power theft users is analyzed to refine the cycle fluctuation characteristics of user information; then, based on the refined user characteristics, the power sequence is reconstructed and the fitted value is obtained through the QRNN model, and a threshold is set adaptively based on the mean square error of the power sequence before and after the reconstruction, and the power theft identification is carried out by judging whether the error is more than the adaptive threshold. Finally, the proposed method is tested and verified by the collected actual power theft data, and the results show that the method has excellent performance.
作者机构:
[Chong Sun; Wei Wang] State Grid Hebei Marketing Service Center, Power Purchase Business Office, Shijiazhuang, People's Republic of China;[Hongming Yang; Sheng Xiang; Lei Liu] Changsha University of Science and Technology, School of Electrical and Information Engineering, Changsha, People's Republic of China;[Yidi Wu] State Grid Hebei Marketing Service Center, Central leadership, Shijiazhuang, People's Republic of China
会议名称:
4th Energy Conversion and Economics Annual Forum (ECE Forum 2024)
会议时间:
2025
会议地点:
Beijing, China
会议论文集名称:
4th Energy Conversion and Economics Annual Forum (ECE Forum 2024)
摘要:
The latest reform phase in the Chinese power market will result in a prolonged period of coexistence between the plan and the market. In this context, the operation of the electricity market gives rise to imbalanced costs because of discrepancies between the planned scale of priority power generation and consumption, inconsistencies in priority power generation and consumption curves, and deviations between forecasts of priority power purchases and actual power consumption. To accurately assess the scale of imbalanced power and the associated costs, this study analyses the formation mechanisms and characteristics of imbalanced costs in a coupled plan and market model, focusing on a power grid that incorporates large-scale foreign power and a complex structure of energy resources. This study presents an assessment model of imbalance costs comprising a typical day-power balance model and a time-period-specific imbalance power calculation model. The evaluation of typical scenarios illustrates that the proposed model can effectively and accurately quantify the scale of the power imbalance and costs within the power grid, thereby providing a robust foundation for power-grid enterprises to develop effective strategies.
期刊:
IET Conference Proceedings,2025年2024(6):700-705 ISSN:2732-4494
作者机构:
[Yunfeng Li; Jialin Zhang] National Key Laboratory of Power Grid Disaster Prevention and Reduction, Changsha University of Science and Technology, School of Electrical &Information Engineering, Changsha, People's Republic of China;[Dong Liu] National Key Laboratory of Advanced Power Transmission Technology, State Grid Smart Grid Research Institute CO. LTD, Beijing, People's Republic of China;[Yang Shi] State Grid Corporation of China, Beijing, People's Republic of China;[Yunfeng Li; Jialin Zhang] Information Engineering, Changsha, People's Republic of China
会议名称:
20th International Conference on AC and DC Power Transmission 2024 (ACDC 2024)
会议时间:
2024
会议地点:
Shanghai, China
会议论文集名称:
20th International Conference on AC and DC Power Transmission 2024 (ACDC 2024)
摘要:
This paper proposes a characteristic harmonics suppression strategy for the LCC-MMC based HVDC system using the MMC. Firstly, the topology of the LCC-MMC based HVDC system is introduced, in which the sending end converter station adopts the LCC-MMC hybrid converter valves despite of the structure of receiving end converter. Secondly, in the outer voltage loop of the MMC, high pass filters, band pass filters, and notch filters are used to extract the characteristic harmonics of the LCC converter for performance comparison, and they are reverse superimposed onto the reference current. In the inner current loop, a PIR control strategy is proposed to track and compensate for the characteristic harmonics without influence on the fundamental components. Finally, the LCC-MMC based HVDC system is constructed in MATLAB/Simulink to verify the effectiveness of the proposed characteristic harmonics suppression strategy.
作者机构:
[Zhuoyan Zhou; Jingjie Huang; Zirong Cheng] State Key Laboratory of Disaster Prevention & Reduction for Power Grid, Changsha University of Science and Technology, Changsha, China;[Yunqing Zhang] School of Electrical and Computer Engineering, The University of Sydney, Sydney, Australia
会议名称:
2025 4th International Conference on Smart Grid and Green Energy (ICSGGE)
会议时间:
28 February 2025
会议地点:
Sydney, Australia
会议论文集名称:
2025 4th International Conference on Smart Grid and Green Energy (ICSGGE)
摘要:
To enhance service quality, many service areas have introduced fast-charging stations for electric vehicles (EVs). However, these stations often demand substantial charging loads, primarily supplied by traditional energy sources, leading to increased carbon emissions and costs. Therefore, establishing a low-carbon, economical, and energy-efficient energy supply system for highway service area charging stations has become imperative. This involves optimizing the configuration of photovoltaic (PV) systems and energy storage to minimize carbon emissions while maximizing economic benefits and clean energy utilization.In constructing such a low-carbon, economical, and clean energy supply system for highway service area charging stations, this study proposes an integrated PV and energy storage optimization model that considers comprehensive energy efficiency. The model aims to achieve multiple objectives: minimizing carbon emissions, reducing annual operational and investment costs, and maximizing energy self-sufficiency. Constraints include the charging and discharging states of EVs. Given the discrete and discontinuous variables, along with multiple objectives in the established model, the Non-dominated Sorting Genetic Algorithm III (NSGA-III) is employed for optimization.Case studies demonstrate that, within a microgrid model of a highway service area charging station, the system meets EV charging and discharging demands and basic load requirements. This results in improved service levels, reduced carbon emissions, and enhanced power supply reliability. The proposed model is also applicable to other service area charging stations. Integrating a high proportion of renewable energy into the grid can effectively achieve clean, low-carbon, and economical energy supply.
作者:
Yuan Chen;Chongju Zhong;Pinyi Huang;Wangyang Cai;Lei Wang
作者机构:
[Wangyang Cai] School of Computer and Communication Engineering, Changsha University of Science and Technology;[Yuan Chen; Chongju Zhong; Pinyi Huang; Lei Wang] School of Computer Science and Engineering, Central South University
会议名称:
ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
会议时间:
06 April 2025
会议地点:
Hyderabad, India
会议论文集名称:
ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
摘要:
Micro-expression (ME) recognition holds great potential for revealing true human emotions. A significant barrier to effective ME recognition is the lack of sufficient annotated ME video data because MEs are subtle and involuntary facial expressions that are very hard to capture. To address this issue, data augmentation techniques, such as ME migration based on a driven video, have been employed to enrich training samples. Considering that MEs can be complex facial movements involving multiple action unit (AU) changes, we propose a novel ME generation approach that enables the creation of more realistic facial sequences by fusing MEs from multiple videos rather than just single driven video. To enhance the effectiveness of multi-sequence ME transfer, we adapt the thin plate spline motion model and improve traditional face alignment methods to better suit the model, facilitating multi-sequence driven ME generation. In our experiments, we conduct a downstream ME recognition task using models trained on our augmented ME sequences to demonstrate the effectiveness of our approach on the SAMM, SMIC, and CASME II datasets. The results confirm that our proposed approach outperforms state-of-the-art (SOTA) augmentation and generation methods in terms of F1 score and recognition accuracy.
作者机构:
[Xig, Jiaojiao; Li, Wenjun; Ma, Wanjun; Peng, Huan] Changsha Univ Sci & Technol, Hunan Prov Key Lab Intelligent Proc Big Data Tran, Changsha, Hunan, Peoples R China.;[Liang, Weijun] Univ South China, Affiliated Changsha Cent Hosp, Hengyang Med Sch, Changsha, Hunan, Peoples R China.
会议名称:
7th Chinese Conference on Pattern Recognition and Computer Vision
会议时间:
OCT 18-20, 2024
会议地点:
Urumqi, PEOPLES R CHINA
会议主办单位:
[Li, Wenjun;Xig, Jiaojiao;Peng, Huan;Ma, Wanjun] Changsha Univ Sci & Technol, Hunan Prov Key Lab Intelligent Proc Big Data Tran, Changsha, Hunan, Peoples R China.^[Liang, Weijun] Univ South China, Affiliated Changsha Cent Hosp, Hengyang Med Sch, Changsha, Hunan, Peoples R China.
会议论文集名称:
Lecture Notes in Computer Science
关键词:
Embedded Deep Learning;Rifampicin;Drug Resistance;Tuberculosis;CT Images;Diagnostic Application
摘要:
In the treatment of tuberculosis (TB), drug-resistant tuberculosis arises when Mycobacterium tuberculosis undergoes genetic mutations or acquires resistance through horizontal gene transfer. Identifying the treatment response of TB patients to Rifampicin, a principal medication for TB treatment, is essential for healthcare professionals to make timely and accurate diagnoses. Not only can this approach save on the costs and duration of TB treatment, but it also helps prevent the disease's spread and fatalities. Traditional methods for diagnosing Rifampicin-resistant TB involve molecular biology tests and drug susceptibility testing, which are time-consuming, expensive, and labor-intensive. To assist physicians in diagnosing the treatment response of TB patients to Rifampicin more rapidly and efficiently, this study introduces a computer-aided diagnostic algorithm based on Embedded Deep Learning (EDL). Initially, CT images from target patients at two imaging centers were collected. The classifier model used in this research combines image preprocessing techniques, three convolutional neural networks, and decision fusion technology to enhance the model's classification efficiency and reduce overfitting. Additionally, the Grad-CAM model was utilized for visualizing the areas of lesions. In the test sets from both centers, the Embedded Deep Learning Model (EDL Model) demonstrated superior performance over other models by combining hard voting or soft voting mechanisms, with an average accuracy improvement of 3.16-16.87%, AUC increase of 3.05-12.66%, and F1-score enhancement of 6.38-22.49%. The diagnostic tool developed in this research for assisting in the diagnosis of TB patients' response to Rifampicin treatment has significant clinical potential, particularly in settings lacking specialized radiological expertise.
关键词:
Polyps;Rough outline;Clarify;Edge information
摘要:
Colon polyp screening is critical for the prevention of colon cancer, and the use of colon polyp segmentation to assist physicians in identifying potential polyps can improve detection efficiency and reduce misdiagnosis and missed diagnoses. However, polyp segmentation encounters the following challenges: (1) the size and shape of polyps vary widely; (2) the edge between polyps and the surrounding normal area is not obvious. To address the above challenges, a novel colon polyp segmentation method like human observation (LHONet) is proposed. This approach aims to align the polyp segmentation network more closely with human cognitive processes. First, the rough outline of the colon polyp image is identified to roughly understand the size and shape of the polyp, and then the polyp edge is finely segmented. The network structure consists of three modules: the Rough Outline Generation (ROG) module is designed to generate the rough outline of colon polyps; the Edge Information Extraction (EIE) module extracts the edge information of the polyps more accurately by combining with the classical edge detection technique; and the Outline Feature Clarifying (OFC) module is devised to supplement the edge information into the rough outline to realize the accurate segmentation of polyps. The method was compared to other methods on five datasets: EndoScene, CVC-ClinicDB, KvasirSEG, CVC-ColonDB, and ETIS-LaribPolypDB, with mDice scores of 90.79, 94.46, 92.13, 82.00, 82.29%, respectively. The codes are available at https://github.com/heyeying/LHONet.
作者机构:
[Xin Peng; Jingjie Huang] State Key Laboratory of Disaster Prevention & Reduction for Power Grid, Changsha University of Science and Technology, Changsha, China;[Yuxia Hua; Cuo Zhang] School of Electrical and Computer Engineering, The University of Sydney, Sydney, Australia
会议名称:
2025 4th International Conference on Smart Grid and Green Energy (ICSGGE)
会议时间:
28 February 2025
会议地点:
Sydney, Australia
会议论文集名称:
2025 4th International Conference on Smart Grid and Green Energy (ICSGGE)
摘要:
This article provides a concise analysis of the current limitations in PV systems and suggests improving the feasibility of engineering applications through the integration of energy storage devices, thereby establishing a distributed photovoltaic storage system model. Utilizing historical load and photovoltaic data from a company in South China, the study employs optimization programming software to achieve operational economic optimization on a typical day. Furthermore, it explores the economic advantages of the distributed photovoltaic storage system over an extended time scale in practical engineering scenarios.
摘要:
The prevalence of spinal tuberculosis (ST) is particularly high in underdeveloped regions with inadequate medical conditions. This not only leads to misdiagnosis and delays in treatment progress but also contributes to the continued transmission of tuberculosis bacteria, posing a risk to other individuals. Currently, CT imaging is extensively utilized in computer-aided diagnosis (CAD). The main features of ST on CT images include bone destruction, osteosclerosis, sequestration formation, and intervertebral disc damage. However, manual diagnosis by doctors may result in subjective judgments and misdiagnosis. Therefore, an accurate and objective method is needed for diagnosing of spinal tuberculosis. In this paper, we put forward an assistive diagnostic approach for spinal tuberculosis that is based on deep learning. The approach uses the Mask R-CNN model. Moreover, we modify the original model network by incorporating the ResPath and cbam* to improve the performance metrics, namely [Formula: see text] and F1-score. Meanwhile, other deep learning models such as Faster-RCNN and SSD were also compared. Experimental results demonstrate that the enhanced model can effectively identify spinal tuberculosis lesions, with an [Formula: see text] of 0.9175, surpassing the original model’s 0.8340, and an F1-score of 0.9335, outperforming the original model’s 0.8657.
作者机构:
[PengFei Deng] State Grid Dongan Power Supply Company, State Grid Hunan Electric Power Co., Yongzhou, People's Republic of China;[Jie Rong; Jing Zhu] College of Electrical Engineering, Changsha University of Science and Technology, Changsha, People's Republic of China
会议名称:
4th Energy Conversion and Economics Annual Forum (ECE Forum 2024)
会议时间:
2025
会议地点:
Beijing, China
会议论文集名称:
4th Energy Conversion and Economics Annual Forum (ECE Forum 2024)
摘要:
The problem of heavy rainfall disasters due to heavy rainfall extremes, such as typhoons and torrential rains, has become frequent, and many cities still lack precautions against sudden extreme weather disasters brought about by climate change. The precautionary standards of some urban infrastructures have failed to keep up with historical climatic changes, such as facilities such as distribution substations and distribution rooms, which are more prone to failures in flooding disasters. Based on the principle of hydrodynamics and the basic assumption of active inundation caused by rainfall, inundation simulation calculations of flooding caused by rainfall in Nanning are carried out by using high-resolution geographic information data and GIS raster analysis technology based on the FloodArea model. Then the inundation range and water depth of different rainfall scenarios are simulated to determine the different disaster-causing levels of distribution network equipment in the study area.
作者:
Yibo Zhou;Yunfei Huang;Libin He;Zhikai Luo;Sheng Su
作者机构:
[Sheng Su] Changsha University of Science & Technology, Changsha, Hunan, People's Republic of China;[Yibo Zhou; Yunfei Huang; Libin He; Zhikai Luo] Dongguan Power Supply Bureau, Guangdong Power Grid Corporation, Dongguan, Guangdong, People's Republic of China
会议名称:
4th Energy Conversion and Economics Annual Forum (ECE Forum 2024)
会议时间:
2025
会议地点:
Beijing, China
会议论文集名称:
4th Energy Conversion and Economics Annual Forum (ECE Forum 2024)
摘要:
The low-voltage distribution substation area supplies many users through complex feeders, with leakage faults common in residential and industrial settings, posing serious safety risks. Neutral-to-ground wiring errors causing leakage faults are widespread and challenging to detect due to hidden fault locations and lack of visible insulation breakdown. These issues hinder RCD deployment and are a major cause of electric shocks and fires. This paper reviews the existing three-tier leakage protection and grounding framework, investigates the mechanisms of neutral-ground miswiring, and establishes a residual current model for substations. It also analyzes dangerous voltages in TT and TN-C-S grounding systems from these faults, assessing safety risks for users and proposing targeted countermeasures.
作者机构:
[Ren Yan] School of Electrical Engineering and Automation, Hefei University of Technology, Anhui, China;[Sichen Wu] School of Economics & Management, Changsha University of Science & Technology, Hunan, China;[Yue Dai] College of Science, Beijing University of Civil Engineering and Architecture, Beijing, China
会议名称:
2025 International Conference on Digital Analysis and Processing, Intelligent Computation (DAPIC)
会议时间:
26 February 2025
会议地点:
Incheon, Korea, Republic of
会议论文集名称:
2025 International Conference on Digital Analysis and Processing, Intelligent Computation (DAPIC)
摘要:
This article establishes a customer rating prediction model based on customer online business experience data, aiming to help mobile operators better understand market operations and improve network service quality. Firstly, in the data preprocessing stage, missing and outlier values were removed, and data features were unified through feature engineering, including normalization, removal of irrelevant features, feature replacement, and encoding. Subsequently, the main factors affecting customer ratings, such as the total GPRS traffic (KB) accounting for <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{8. 7 9 2} {\%}$</tex>, were analyzed using the random forest algorithm. Next, to prevent overfitting of the model, feature embedding selection is used to further screen features to enhance the model's expressive power. The dataset was divided in a <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$7: 3$</tex> ratio, and three ensemble learning models were established: random forest, BP neural network, and XGBoost. The model parameters were optimized, and the experimental results showed that the three optimized models improved on the mixed evaluation index MAPE-Accuracy5. However, due to the lower prediction accuracy than expected, a stacked model fusion method was ultimately adopted. By assigning different weights to the prediction results of the three models and combining their advantages, a final customer rating prediction model was established. The stacked fusion model generally scored above 0.7 on both the training and testing sets, outperforming other models. Through the methods described in this article, mobile operators can better understand customer needs, continuously improve service quality, create more value for customers, and continuously optimize service experience.
作者机构:
[Ye Zheli] Chansha University of Science & Technology, School of Electrical & information Engineering, Chansha, China;[Cheng Guangjie; Zhang Zhaoyun] Dongguan University of Technology, School of Electrical Engineering and Intelligentization, Dong Guang, China
会议名称:
2025 15th International Conference on Power, Energy, and Electrical Engineering (CPEEE)
会议时间:
15 February 2025
会议地点:
Fukuoka, Japan
会议论文集名称:
2025 15th International Conference on Power, Energy, and Electrical Engineering (CPEEE)
关键词:
Inverter;PR;PI
摘要:
At present, photovoltaic power generation has been appreciated by all countries, and the inverter, as an equipment to convert direct current into alternating current, is an important equipment to convert solar energy into electricity. Scholars at home and abroad for inverter control strategy do a lot of research, but with the increase of photovoltaic installed capacity and permeability, the accuracy of the inverter output voltage waveform put forward higher requirements, before many control strategy has been unable to meet the requirements, in order to reduce the inverter output voltage distortion rate, this study puts forward a quasi-PR(Proportional Resonant) control and PI(Proportional Integral) control combined double closed-loop control strategy, finally simulation verified the feasibility of the method.
作者机构:
[Zirong Cheng; Jingjie Huang; Zhuoyan Zhou] State Key Laboratory of Disaster Prevention & Reduction for Power Grid,, Changsha University of Science and Technology, Changsha, China;[Fan Huang] School of Electrical and Computer Engineering, The University of Sydney, Australia, Sydney, Australia
会议名称:
2025 4th International Conference on Smart Grid and Green Energy (ICSGGE)
会议时间:
28 February 2025
会议地点:
Sydney, Australia
会议论文集名称:
2025 4th International Conference on Smart Grid and Green Energy (ICSGGE)
关键词:
off-grid wind-solar hydrogen production system;capacity configuration;economic performance;wind-solar hydrogen;wind hydrogen
摘要:
To enhance the economic efficiency and operational stability of off-grid wind-solar hydrogen production systems, a novel capacity configuration method is proposed. This method optimizes system equipment capacity in an integrated wind-solar-hydrogen system with the objective of maximizing system revenue. A case study is conducted using data from a wind-solar hydrogen production project in a specific region, where three schemeswind energy, hydrogen production, wind-battery hydrogen production, and wind-solar-battery hydrogen production-are designed and compared. The analysis reveals that, under the given wind and solar conditions, the system achieves maximum benefit when the wind power to photovoltaic installation ratio is 2.75:1. Additionally, energy storage effectively mitigates fluctuations in new energy output. The study also examines the cost composition of the wind-solar hydrogen storage system and the impact of equipment costs on the unit hydrogen production cost. The findings show that the cost of wind turbine equipment significantly influences the unit hydrogen production cost. A 50% reduction in wind turbine costs corresponds to a $4.9 \mathrm{CNY} / \mathrm{kg}$ increase in hydrogen price.
摘要:
The complex nature of brain tumors, characterized by their individual shapes, sizes, and locations, as well as the presence of indistinct boundaries, presents a challenging task for precise automatic segmentation. While U-Net has been a top performer in medical image segmentation, it struggles with capturing multi-scale details, preserving information across layers, and focusing on critical features. To address these issues, a new 3D brain tumor segmentation network called GBA-Net is proposed, which introduces - 1) A multi-scale Gaussian boundary attention (GBA) module with the ability to automatically focus on boundary features, 2) Efficient inverted bottleneck convolution upsample (Up-IBC) and inverted bottleneck convolution downsample (Down-IBC) modules that enhance the richness of cross-scale information, 3) The high-low feature fusion (HLFF) module that mitigates information loss during the decoder’s restoration of full spatial resolution. The proposed GBA-Net achieves state-of-the-art performance on the 3D brain tumor dataset BraTS 2021. Cross-validation on the BraTS 2018 and BraTS 2019 datasets indicates that GBA-Net generalizes well on the external datasets.
作者:
Bo He;Chenhui Song;Bangkai Zhang;Shunyu Li;Sizhuo Huang
作者机构:
[Bo He; Chenhui Song; Bangkai Zhang; Shunyu Li; Sizhuo Huang] School of Electrical & Information Engineering, Changsha University of Science & Technology, Changsha, People's Republic of China
会议名称:
4th Energy Conversion and Economics Annual Forum (ECE Forum 2024)
会议时间:
2025
会议地点:
Beijing, China
会议论文集名称:
4th Energy Conversion and Economics Annual Forum (ECE Forum 2024)
摘要:
Integrated energy system (IES) is an important means to achieve the comprehensive utilization of heterogeneous energy and improve the efficiency of energy utilization. But its coupling relationship is complex, and the running model often has nonlinear characteristics, making it easy to fall into local optima when solving using traditional algorithms. This article proposes an IES optimization running method based on the bald eagle search algorithm (BES) to address this issue. Firstly, an IES structure considering electrical-thermal-gas coupling was constructed. Secondly, an IES optimal operation model was established, and a BES based optimization solution method for IES was proposed. Finally, the effectiveness of our method was verified based on a typical IES case study. The results of the case study showed that our method can effectively solve th e problem of traditional algorithms easily getting stuck in local optima.