检索结果-内蒙古大学图书馆

A novel scenario generation and forecasting method for multiple future states at source side based on combinatorial models

引用

ENERGY CONVERSION AND MANAGEMENT 2024年 310卷

作者： Wang, Shunjiang Li, Zihan Cui, Jia Xu, Kun Zhang, Ximing Huang, Jingbo Li, Chaoran State Grid Liaoning Elect Power Supply Co Ltd Shenyang 110006 Liaoning Peoples R China Shenyang Univ Technol Sch Elect Engn Shenyang 110870 Liaoning Peoples R China

This paper proposes a novel method for scenario generation and scenario forecasting considering windphotovoltaic-hydro-thermal power sources. With the rapid development and application prospects of energy internet and grid modernization, accurate source-side multiple output modeling and forecasting is essential to observe and estimate the multiple curves. It is becoming more and more important to optimize the operation efficiency of power grid. The traditional methods mainly focus on multi-scene generation of a single power source. Grid scheduling requirements that could not take into account multiple time correlations and multiple scenario forecasting. The paper proposes a scenario forecasting method considering scenario generation. Firstly, mutual Information (MI) and depth-first traversal (DFS) are combined to analyze the factors associated with power generation and build the MI-DFS-K2-Bayes network to generate multiple scenarios of wind- photovoltaichydro-thermal power. Secondly, the improved k-means algorithm is proposed to obtain the center curve of each power source. The algorithm improves the accuracy of the multivariate clustering center curve. It solves the problem that the initial clustering center and the number of clusters are difficult to select, and builds the multivariate running state. Finally, the upper and lower interval of point forecasting constrained by confidence parameters is proposed to make the running state scene match the point forecasting. The future state curves of each power source in short time scale are obtained. The future state scenario is implemented. Numerical examples demonstrate that the proposed method reduces the modeling error of wind- photovoltaic-hydro-thermal power curves by 0.13%-0.4%. The overall forecasting accuracy is significantly better than the state of the study.

关键词： Power source Scenario generation Scenario forecasting Bayesian network clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

Photovoltaic Module Fault Detection Technology Based on Remote Sensing Technology and Deeplabv3+Model

引用

IEEE ACCESS 2024年 12卷 195472-195482页

作者： Xu, Xiaowei Liu, Mingxian Nie, Yongjie Wang, Ke Xu, Wenhua Yunnan Power Grid Co Ltd Elect Power Res Inst Kunming 650000 Peoples R China

With the rapid advancement of renewable energy, the fault detection of photovoltaic modules has become a key link to ensure their efficient operation. The study first utilizes remote sensing technology to obtain high-resolution images of photovoltaic power plants, and then uses the Deeplabv3+model to segment the images and identify faulty components. Combining remote sensing technology with Deeplabv3+ model, fast and accurate photovoltaic module fault detection can be achieved. The research results indicated that bilateral filtering and gamma filtering algorithms showed superior performance in testing, with the highest indicator evaluation results. Meanwhile, the structural similarity index value was also very close to 1. The error of the improved K-means was mainly concentrated between 0.000 and 0.014, while the traditional K-means was mainly distributed between 0.022 and 0.051. The statistical test results showed that the improved K-means algorithm was significantly better than the traditional K-means in clustering accuracy, and its average error was only 0.008, which was much lower than the 0.035 of the traditional K-means. The bilateral filtering showed the highest accuracy, with a classification result of 88%. This method can detect faults in photovoltaic modules, which has significant advantages over traditional methods. It provides a new and efficient method for photovoltaic module fault detection, which helps to optimize the operational efficiency and reliability of photovoltaic power plants and promote the sustainable development of renewable energy.

关键词： Solar panels Fault detection Remote sensing Accuracy Filtering Aircraft Maintenance Brightness Atmospheric modeling Object oriented modeling clustering algorithm Deeplabv3+model fault detection photovoltaic modules remote sensing technology

来源：评论

学校读者我要写书评

暂无评论

Maximum Correntropy Criterion-Based UKF for Loosely Coupling INS and UWB in Indoor Localization

引用

Computer Modeling in Engineering & Sciences 2024年第6期139卷 2673-2703页

作者： Yan Wang You Lu Yuqing Zhou Zhijian Zhao Department of Computer and Communication Engineering Northeastern UniversityQinhuangdao066004China

Indoor positioning is a key technology in today’s intelligent environments,and it plays a crucial role in many application *** paper proposed an unscented Kalman filter(UKF)based on the maximum correntropy criterion(MCC)instead of the minimummean square error criterion(MMSE).This innovative approach is applied to the loose coupling of the Inertial Navigation System(INS)and Ultra-Wideband(UWB).By introducing the maximum correntropy criterion,the MCCUKF algorithm dynamically adjusts the covariance matrices of the system noise and the measurement noise,thus enhancing its adaptability to diverse environmental localization *** in the presence of non-Gaussian noise,especially heavy-tailed noise,the MCCUKF exhibits superior accuracy and robustness compared to the traditional *** method initially generates an estimate of the predicted state and covariance matrix through the unscented transform(UT)and then recharacterizes the measurement information using a nonlinear regression method at the cost of ***,the state and covariance matrices of the filter are updated by employing the unscented transformation on the measurement ***,to mitigate the influence of non-line-of-sight(NLOS)errors positioning accuracy,this paper proposes a k-medoid clustering algorithm based on bisection k-means(Bikmeans).This algorithm preprocesses the UWB distance measurements to yield a more precise position *** results demonstrate that MCCUKF is robust to the uncertainty of UWB and realizes stable integration of INS and UWB systems.

关键词： Maximum correntropy criterion unscented Kalman filter inertial navigation system ultra-wideband bisecting kmeans clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

Clothing-invariant contrastive learning for unsupervised person re-identification

引用

NEURAL NETWORKS 2024年 178卷 106477页

作者： Pang, Zhiqi Zhao, Lingling Wang, Chunyu Harbin Inst Technol Fac Comp Harbin 150001 Heilongjiang Peoples R China

Clothing change person re -identification (CC-ReID) aims to match images of the same person wearing different clothes across diverse scenes. Leveraging biological features or clothing labels, existing CC-ReID methods have demonstrated promising performance. However, current research primarily focuses on supervised CCReID methods, which require a substantial number of manually annotated labels. To tackle this challenge, we propose a novel clothing -invariant contrastive learning (CICL) framework for unsupervised CC-ReID task. Firstly, to obtain clothing change positive pairs at a low computational cost, we propose a random clothing augmentation (RCA) method. RCA initially partitions clothing regions based on parsing images, then applies random augmentation to different clothing regions, ultimately generating clothing change positive pairs to facilitate clothing -invariant learning. Secondly, to generate pseudo -labels strongly correlated with identity in an unsupervised manner, we design semantic fusion clustering (SFC), which enhances identity -related information through semantic fusion. Additionally, we develop a semantic alignment contrastive loss (SAC loss) to encourages the model to learn features strongly correlated with identity and enhances the model's robustness to clothing changes. Unlike existing optimization methods that forcibly bring closer clusters with different pseudo -labels, SAC loss aligns the clustering results of real image features with those generated by SFC, forming a mutually reinforcing scheme with SFC. Experimental results on multiple CC-ReID datasets demonstrate that the proposed CICL not only outperforms existing unsupervised methods but can even achieves competitive performance with supervised CC-ReID methods. Code is made available at https://***/zqpang/CICL.

关键词： Unsupervised learning Contrastive learning clustering algorithm Clothing change person re-identification

来源：评论

学校读者我要写书评

暂无评论

Significant Improvement in Soil Organic Carbon Estimation Using Data-Driven Machine Learning Based on Habitat Patches

引用

REMOTE SENSING 2024年第4期16卷 688页

作者： Yu, Wenping Zhou, Wei Wang, Ting Xiao, Jieyun Peng, Yao Li, Haoran Li, Yuechen Chinese Acad Agr Sci Inst Agr Resources & Reg Planning State Key Lab Efficient Utilizat Arid & Semiarid A Beijing 100081 Peoples R China Southwest Univ Chongqing Engn Res Ctr Remote Sensing Big Data App Sch Geog Sci Chongqing Jinfo Mt Karst Ecosyst Natl Observat & R Chongqing 400715 Peoples R China Chinese Acad Sci Inst Geog Sci & Nat Resources Res State Key Lab Resources & Environm Informat Syst Beijing 100101 Peoples R China Minist Nat Resources Topog Survey Team 6 Chengdu 610500 Peoples R China

Soil organic carbon (SOC) is generally thought to act as a carbon sink;however, in areas with high spatial heterogeneity, using a single model to estimate the SOC of the whole study area will greatly reduce the simulation accuracy. The earth surface unit division is important to consider in building different models. Here, we divided the research area into different habitat patches using partitioning around a medoids clustering (PAM) algorithm;then, we built an SOC simulation model using machine learning algorithms. The results showed that three habitat patches were created. The simulation accuracy for Habitat Patch 1 (R2 = 0.55;RMSE = 2.89) and Habitat Patch 3 (R2 = 0.47;RMSE = 3.94) using the XGBoost model was higher than that for the whole study area (R2 = 0.44;RMSE = 4.35);although the R2 increased by 25% and 6.8%, the RMSE decreased by 33.6% and 9.4%, and the field sample points significantly declined by 70% and 74%. The R2 of Habitat Patch 2 using the RF model increased by 17.1%, and the RMSE also decreased by 10.5%;however, the sample points significantly declined by 58%. Therefore, using different models for corresponding patches will significantly increase the SOC simulation accuracy over using one model for the whole study area. This will provide scientific guidance for SOC or soil property monitoring with low field survey costs and high simulation accuracy.

关键词： soil organic carbon clustering algorithm machine learning digital soil mapping

来源：评论

学校读者我要写书评

暂无评论

A Fast algorithm for Matching AIS Trajectories with Radar Point Data in Complex Environments

引用

REMOTE SENSING 2024年第23期16卷 4360-4360页

作者： Xu, Jialuo Suo, Ying Jiang, Yuqing Yang, Qiang Harbin Inst Technol Sch Elect Informat Engn Harbin 150001 Peoples R China

In high-traffic port areas, vessel traffic-management systems (VTMS) are essential for managing ship movements and preventing collisions. However, inaccuracies and omissions in the Automatic Identification System (AIS), along with frequent false tracks generated by radar false alarms in complex environments, can compromise VTMS stability. To address the challenges of establishing consistent navigation and improving trajectory quality, this study introduces a novel method to directly identify AIS-matched trajectories from radar plots. This approach treats radar points as probability clouds, generating a multi-dimensional information layer by stacking these clouds after differential transformations based on AIS data. The resulting layer undergoes filtering and clustering to extract point sets that align with AIS data, effectively isolating matching trajectories. The algorithm, validated with simulated data, rapidly identifies target trajectories amid extensive interference without requiring strict parameter adjustments. In measured data, the algorithm rapidly provides matching trajectories, although further human judgment is still required due to the potential absence of true values in measured data.

关键词： clustering algorithm AIS track establishment trajectory extraction

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Composite Differential Evolution and Multiobjective Particle Swarm Optimization Evolutionary algorithm and Its Application

引用

IEEE ACCESS 2024年 12卷 74417-74431页

作者： Shang, Jin Li, Guiying Wuxi Inst Technol Control Technol Inst Wuxi 214121 Peoples R China Heilongjiang Univ Sch Mech & Elect Engn Harbin 150080 Peoples R China

The current multi-objective particle swarm algorithms excel in convergence speed for solving complex problems but often suffer from a loss of population diversity. Conversely, composite differential evolution algorithms maintain superior solution distribution but lag in convergence efficiency. This research introduces an improved hybrid algorithm, CoDE-MOPSO, which integrates multi-objective particle swarm optimization with composite differential evolution based on clustering technology. The clustering algorithm is used for all individual clusters to analyze the distribution constructs of populations, which determines whether the new solutions come from global or local populations at a mating restriction probability. The mating restriction probability is updated at each generation. To adapt the balance between the population solution diversities and the convergence speed of the algorithm, at each generation, the control probability is adjusted by a developed adaptive strategy according to the reproduction utility of the two mechanisms of generating new solutions over the last certain generations. This research introduces the CoDE-MOPSO algorithm, designed to transcend existing multi-objective optimization methods' limitations by optimally balancing exploration and exploitation. Our approach significantly advances evolutionary multi-objective optimization, demonstrating superior performance through lower Inverse Generational Distance and higher Hypervolume metrics, indicating enhanced efficiency in solving complex MOPs across various fields. In practical scenarios like gear reducer optimization, CoDE-MOPSO showcases remarkable effectiveness, highlighting its value in engineering applications and setting a foundation for sophisticated optimization strategies that combine speed with solution quality.

关键词： Statistics Social factors Optimization Convergence clustering algorithms Particle swarm optimization Interconnected systems Pareto optimization clustering algorithm composite differential evolution gear reducer multiobjective optimization particle swarm algorithm

来源：评论

学校读者我要写书评

暂无评论

Adaptive Decentralized State Estimation for Multimachine Power Grids Under Measurement Noises With Unknown Statistics

引用

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2025年第2期21卷 1655-1664页

作者： Qu, Bogang Wang, Zidong Shen, Bo Dong, Hongli Peng, Daogang Shanghai Univ Elect Power Coll Automat Engn Shanghai 200090 Peoples R China Brunel Univ London Dept Comp Sci Uxbridge UB8 3PH England Donghua Univ Coll Informat Sci & Technol Shanghai 200051 Peoples R China Minist Educ Engn Res Ctr Digitalized Text & Fash Technol Shanghai 201620 Peoples R China Northeast Petr Univ Artificial Intelligence Energy Res Inst Daqing 163318 Peoples R China Northeast Petr Univ Sanya Offshore Oil & Gas Res Inst Sanya 572024 Peoples R China

This article is concerned with the adaptive dynamic state estimation (DSE) problem for synchronous-generator-based multimachine power grids under measurement noise with unknown statistics. The statistical properties of the measurement noises are efficiently revealed by utilizing limited measurement data contained in a sliding window, and such data is employed to establish the base distribution of the noises, with the aid of the Gaussian mixture model and the kernel density estimation scheme. Subsequently, the component number of the base distribution of the measurement noises is reduced by designing a fuzzy C-means clustering algorithm with the Wasserstein distance criterion. An improved sliding-window-based adaptive cubature Kalman filtering scheme is then proposed, which leverages the already obtained statistical characteristics of the measurement noise and the concept of the Gaussian summation filter. Finally, the validity of the proposed adaptive DSE algorithm under various measurement noise statistics is illustrated by simulation studies conducted on the IEEE 39-bus system featuring three test scenarios.

关键词： Adaptive state estimation (SE) clustering algorithm cubature Kalman filter (CKF) multimachine power grids unknown measurement noises Adaptive state estimation (SE) clustering algorithm cubature Kalman filter (CKF) multimachine power grids unknown measurement noises

来源：评论

学校读者我要写书评

暂无评论

A module partition method for complex product based on the knowledge hypergraph

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 152卷

作者： Wang, Pengchao Chu, Jianjie Yu, Suihuai Cheng, Fangmin Ding, Ning Cong, Yangfan Northwestern Polytech Univ Key Lab Ind Design & Ergon Minist Ind & Informat Technol Xian 710072 Peoples R China Xian Technol Univ Sch Art & Media Xian 710021 Peoples R China Hong Kong Polytech Univ Sch Design Hung Hom Hong Kong 999077 Peoples R China

The modular design can effectively control the development cycle and cost of complex product, with product module partition (PMP) serving as the foundation of modularization. However, models constructed based on expert knowledge are inadequate in effectively capturing the relationships within complex product, which undermines the efficiency and accuracy of PMP. To solve this problem, this paper introduces hypergraph theory into the field of PMP, specifically, proposes a PMP method based on the knowledge hypergraph (KHG). First, the multiple coupling relationships between complex product are defined from the perspective of "FunctionBehavior-Structure-Constraint", to form the pattern layer of the KHG. Then, the joint learning algorithm, which contains the pretraining model, Bi-directional Long Short-Term Memory network, Conditional Random Field and Attention layer, is proposed to automatically extract design knowledge from large-scale text data to form the data layer of the KHG. Furthermore, considering that the PMP model needs to learn nonlinear relationship features, achieve end-to-end optimization, and have strong anti-noise ability, hypergraph neural networks are used to partition the complex product modules, which contains the importance calculation, hypergraph convolution, modularity maximum and self-supervised module. Finally, a case study is conducted using a snow removal equipment as an example, the knowledge extraction accuracy reaches 91.67 %, and the PMP modularity is 0.68, thus validating the feasibility of the proposed method. Additionally, the comparison is made with other knowledge extraction and hypergraph clustering algorithms using public datasets, which further confirms the feasibility and superiority of the proposed method.

关键词： Product design Product module partition Knowledge hypergraph Hypergraph neural network clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

Dual-Task GPR Method: Improved Generative Adversarial Clutter Suppression Network and Adaptive Target Localization algorithm in GPR Image

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2024年 62卷 1页

作者： Hou, Feifei Fang, Mengqi Luo, Tess Xianghuan Fan, Xinyu Guo, Ying Cent South Univ Sch Automat Changsha 410083 Peoples R China Shenzhen Univ Coll Civil & Transportat Engn Shenzhen 518060 Peoples R China Beijing Univ Posts & Telecommun Sch Comp Sci Natl Pilot Software Engn Sch Beijing 100876 Peoples R China Hefei Natl Lab Hefei 230088 Peoples R China

Ground-penetrating radar (GPR), as a geophysical survey method, offers high resolution and fast detection capabilities obtaining rich information about the underground structure. However, under real conditions, GPR is susceptible to interference and clutter. Therefore, there is an urgent need to develop methods for suppressing clutter, highlighting and positioning targets in GPR images. This article proposed an integrated method consisting of two modules: GPR image decluttering and underground target localization, which are used for clutter suppression and hyperbola vertex estimation from GPR image. In the first module, an unsupervised generative adversarial network (GAN) model is developed to map cluttered GPR images to clutter-free GPR images, where the CycleGAN is adapted as the main network architecture. To further improve the performance of the model, the first module proposes a novel loss function that introduces a perceptual loss into the previous CycleGAN loss. It utilizes a multiscale structural similarity index (MS-SSIM) loss to obtain richer and more realistic context information. In the second module, based on the obtained decluttered image, a novel adaptive target characterization algorithm, called gradient points clustering-based localization (GPCL), is proposed for the recognition and localization of GPR target signatures. This algorithm is designed to leverage changes in target position and local characteristics, thereby achieving efficient target vertex evaluation. Experimental results conducted on field datasets demonstrate that the proposed methods can significantly improve the quality and clarity of various cluttered images and exhibit strong applicability for the localization of underground targets.

关键词： Clutter Location awareness Feature extraction clustering algorithms Transforms Generative adversarial networks Data mining clustering algorithm clutter elimination generative adversarial network (GAN) ground-penetrating radar (GPR) perceptual loss subsurface target localization

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：