检索结果-内蒙古大学图书馆

A Novel Hybrid Transformer-Based Framework for Solar Irradiance Forecasting under Incomplete Data Scenarios

IEEE Transactions on Industrial Informatics 2024年第6期20卷 8605-8615页

作者： Zhang, Hanjin Li, Bin Su, Shun-Feng Yang, Wankou Xie, Liping Southeast University School of Economics and Management Nanjing210096 China National Taiwan University of Science and Technology Department of Electrical Engineering Taipei106 Taiwan Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Nanjing210096 China Southeast University Shenzhen Research Institute Shenzhen518063 China

Accurate prediction of solar irradiance is crucial for the effective utilization of solar energy. However, in real-world scenarios, complex irradiance patterns and prevalent incomplete data pose challenges to precise forecasting, resulting in additional uncertainties and instability. To address these issues, this study proposes a novel irradiance forecasting model that integrates a Mask-Transformer data imputation module and a prediction module centered around the typical patterns representation mechanism. The Mask-Transformer leverages a mask modeling mechanism to model the context of missing data, facilitating accurate estimation of missing values and reducing noise and uncertainty in the input data. The typical patterns representation mechanism comprises a series decomposition module and a feature fusion module, providing the module with the capability to mitigate nonlinearity and nonstationarity in solar irradiance data. This enhancement leads to improved short-term forecasting performance while maintaining long-term forecasting capabilities. Experimental results on two datasets demonstrate that the proposed model exhibits sufficient robustness and accuracy, making it effective in scenarios with incomplete data. © 2005-2012 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Distributed control Algorithm for Workload Partition of Multi-agent systems with Time Delay 41

Distributed Control Algorithm for Workload Partition of Mult...

引用

第41届中国控制会议

作者： Pengyang Fan Chao Zhai School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In the problem of multi-agent coverage,a group of agents are required to cover a given region or clean the workload as soon as *** workload partition can improve the work efficiency of multi-agent *** addition,the communication delays play a key role in the stability of multi-agent ***,a distributed control algorithm of workload partition with time delay is proposed in this ***,an approach based on nonlinear matrix inequality is presented to find the maximum delay of multi-agent ***,experiments are carried out to investigate the effect of delay on system stability on the ZigBee platform.

关键词： Multi-agents systems Time delay Nonlinear matrix inequality Distributed algorithm Workload partition

来源：评论

学校读者我要写书评

暂无评论

Finite-time stabilization for high-order nonholonomic systems with full state constraints 41

Finite-time stabilization for high-order nonholonomic system...

引用

第41届中国控制会议

作者： Liangguang Li Shiqi Zheng Jiachun Sun Tao Song Qing Chang School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

This paper studies the finite-time control problem for a class of high-order nonholonomic systems.A new smooth coupling controller is proposed to make the system states converge to zero in *** order to ensure the states constraints of the nonholonomic systems,a new adding a barrier power integrator technique is *** barrier function is integrated into the traditional adding a power integrator ***,the proposed controller is singular-free and can produce smooth control ***,simulations verify the obtained results.

关键词： Finite time nonholonomic system mobile robots constraints

来源：评论

学校读者我要写书评

暂无评论

Prediction Method of Blast Furnace Fuel Ratio Based on Spectral Clustering and Extreme Learning Machine Model 41

Prediction Method of Blast Furnace Fuel Ratio Based on Spect...

引用

第41届中国控制会议

作者： Jingjie Liang Yan Yuan Shuqiao Wang Zhuofu Zhang School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

The blast furnace fuel ratio,as the main index reflecting the blast furnace fuel consumption,plays an important role in guiding blast furnace *** order to solve the problem of insufficient stability of the existing fuel ratio prediction model under the condition of process parameters fluctuation,a prediction method of blast furnace fuel ratio based on spectral clustering and extreme learning machine model is ***,on the basis of analyzing the influencing factors of fuel ratio,the classification results after clustering are visualized with t-SNE dimension reduction downscaling and spectral clustering method;Secondly,for the classification results after clustering,the extreme learning machine is used to establish the sub-models,and the PSO algorithm was used to optimize the input weights of hidden layer and the bias of hidden layer *** results show that the proposed method has high prediction accuracy.

关键词： Fuel Ratio Spectral Clustering Extreme Learning Machine(ELM) t-SNE Particle Swarm optimization(PSO)

来源：评论

学校读者我要写书评

暂无评论

Particle Detection of complex Images Based on Convolutional Neural Network 41

Particle Detection of Complex Images Based on Convolutional ...

引用

第41届中国控制会议

作者： Yuting Ge Yi Liu Chi Xu School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Particle Detection plays important roles in industrial and medical image ***-learning based methods can only deal with the particle images with simple backgrounds and sparse *** most neural network based methods can also hardly to deal with overlapping objects and small particles,besides,the huge amount of parameters of these methods also has a great demand for annotated data,which is difficult to ***,we use bright pixels to represent the spatial position of particles,and artificially divid the sizes of particles into multiple intervals.A feature representation called Light-spots Maps is proposed to replace the bounding box and pixel classifications in our detection *** Light-weight networks based on ResNets is used to transform the particle images into Light-spots maps to detect the particle *** experiments,we prove the effectiveness of our method.

关键词： Objects Detection Particles Detection Convolutional Neural Network

来源：评论

学校读者我要写书评

暂无评论

State Estimation for Static Neural Networks with Time-Varying Delay via Quadratic Function Negative-Determination Lemma 41

State Estimation for Static Neural Networks with Time-Varyin...

引用

第41届中国控制会议

作者： Yong-He Lao Du Xiong Li Jin Chuan-Ke Zhang School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

The H performance state estimation for static neural networks with time-varying delays is studied in this ***,an augmented Lyapunov-Krasovskii functional（LKF） with the triple integral term and the delay-product-type term is ***,a generalized reciprocally convex matrix inequality is employed to deal with the derivative of the *** that,by utilizing the relaxed quadratic function negative-definiteness determination method to dispose of the time derivative of the delay-product-type term,a less conservative state estimation criterion is ***,the effectiveness of the proposed method is shown through a numerical example.

关键词： Static Neural Networks State Estimation Time-Varying Delay Reciprocally Convex Matrix Inequality Quadratic Function Negative-Determination Lemma

来源：评论

学校读者我要写书评

暂无评论

Research on Electricity Price Sensitivity of Smart Park Facing Source and Load Uncertainty 41

Research on Electricity Price Sensitivity of Smart Park Faci...

引用

第41届中国控制会议

作者： Jie Cai Zhijian Fang Wenhe Peng Zihan Zhang Junwen He School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Due to the uncertainty of photovoltaic power generation and the disorder of large-scale electric vehicle charging,new challenges have been brought to the security and stability of the smart park distribution network,hybrid storage plays a significant role in smoothing power *** the goal of maximizing the annual earnings of energy storage,this paper proposes a real-time electricity price model based on the electricity price sensitivity of the tie line power fluctuation *** is verified by numerical example simulation,and the results show that,the model plays a very good role in smoothing power fluctuations and improving the economic benefits of energy storage.

关键词： Smart park hybrid energy storage real-time electricity price electricity price sensitivity

来源：评论

学校读者我要写书评

暂无评论

Research on Virtual USB Storage in Remote File Transfer 41

Research on Virtual USB Storage in Remote File Transfer

引用

第41届中国控制会议

作者： Jie Li Weihua Cao Zhicheng Zhao Han Peng School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Virtual USB storage technology is an application technology that integrates Universal Serial Bus(USB) virtualization,file system virtualization and reliable file data transfer,which is often applied to virtual file transfer in data *** the current traditional virtual USB storage technology relies on specific software and poor system compatibility,this paper proposes a hardware-based virtual USB storage solution that uses the built-in USB driver of each operating system to map the local USB storage device to the remote controlled server to achieve file reading and *** show that the scheme proposed in this paper has the advantages of simple implementation,good system compatibility,safe and stable *** technology has been successfully applied to the data room management of an enterprise.

关键词： USB storage virtualization file transfer remote mapping

来源：评论

学校读者我要写书评

暂无评论

Image Semantic Segmentation Scheme based on XGBoost combination with Convolution Feature Extraction 41

Image Semantic Segmentation Scheme based on XGBoost combinat...

引用

第41届中国控制会议

作者： Zichen Dai Xuewen Liu Chi Xu School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Aiming at the problem that the existing image semantic segmentation schemes based on convolutional neural network require a large number of training data sets and high training cost,this paper presents a novel scheme for image semantic segmentation based on extreme gradient boosting(XGBoost),a scalable tree boosting system and the combination of convolution feature extraction(CFE).The scheme consists of three ***,convolution operation is performed on a small amount of RGB pixel information of the image processed by Gaussian filtering to acquire more multi-dimensional image feature ***,some preprocessing techniques of image feature information,including feature normalization and image label pixel number uniformity are performed to match the ***,the preprocessed image feature information and corresponding labels are input into XGBoost to train and predict the data of the test *** simulation and practical tests,compared with other commonly used few data classification algorithms like k-Nearest-Neighbor(kNN) and Support-VectorMachine(SVM),this scheme can achieve high precision pixel-level image semantic segmentation under the condition of lower training cost.

关键词： Image Semantic Segmentation Convolutional Feature Extraction XGBoost Gaussian Filtering Low Training Cost

来源：评论

学校读者我要写书评

暂无评论

Forward and inverse calculation method for shape and depth of seepage channel of embankment 41

Forward and inverse calculation method for shape and depth o...

引用

第41届中国控制会议

作者： Yue-Cheng Zhai Jun-Lei Song Kai-Feng Dong Fang jin Wen-qin Mo Ya-juan Hui School of Automation China University of Geosciences Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Seepage diseases in embankments are very common,and if they cannot be treated in time,they will bring serious safety hazards and even cause embankment break *** the location and depth of a seepage channel is the prerequisite and basis for the treatment of seepage *** present,there are several methods are used to detect seepage in embankments,but none of them can accurately calculate or explain the depth of seepage *** magnetic gradient tensor method,which is widely used in the depth calculation of magnetic sources,is only suitable for the magnetic dipole model,and not suitable for the tubular model similar to the seepage *** view of this,this paper draws on the idea of magnetic exploration,and proposes a forward and inverse calculation method for the depth of the seepage *** method first builds a variety of basic seepage channel models based on certain constraints,and calculates the magnetic field value of each model at each measuring point on the ground *** compare the actual measured magnetic field value with the model magnetic field value to find the closest seepage channel ***,by continuously optimizing the closest model,the real seepage channel is gradually *** model calculated by this method can better reflect the depth information of the real seepage channel,and the depth error is less than lm.

关键词： seepage depth magnetic gradient tensor forward and inversion calculation

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：