检索结果-内蒙古大学图书馆

FAA-YOLO: A Method for Defects Detection of Small Infrared Targets in Photovoltaic Modules

IEEE SENSORS JOURNAL 2025年第6期25卷 10486-10497页

作者： Li, Weihao Li, Jianqi Cao, Binfang Zhu, Jiang Tian, Minghui Jishou Univ Sch Commun & Elect Engn Jishou 416000 Peoples R China Hunan Univ Arts & Sci Hunan Prov Key Lab Control Technol Distributed Ele Changde 415000 Peoples R China

The regular inspection of photovoltaic (PV) modules is a crucial measure to ensure the safety of solar power generation. To address the challenges posed by small, multiscale infrared defects in PV modules, this article proposes a method called filter and adaptive assisted-you only look once (FAA-YOLO) for detecting small infrared defects in PV modules. First, we design a multiscale parameter-free edge detection (MPED) module to enhance shallow features, such as texture and edges, thereby improving the network's capability to extract features from small defect targets. Second, we introduce an improved feature fusion network named SlimNet, which mitigates the challenges of small infrared defects in PV modules and the tendency of such features to be overlooked by fusing information from different scales. Last, we propose an adaptive auxiliary detection layer (AAD-Layer). The multiscale AAD-Layer enables feature reuse and enriches defect feature representation by cascading features of different scales across layers and combining deep and shallow features. Experimental results show that the proposed FAA-YOLO model achieves a detection accuracy of 87.5%. Compared to others methods, it also strikes a good balance between accuracy and computational complexity.

关键词： Feature extraction Solar panels Image edge detection Sensors Accuracy Standards Shape Computational modeling Auxiliary detection head Deep learning defect detection edge detection hot spot fault photovoltaic (PV) farms YOLOv8 hot spot fault photovoltaic (PV) farms YOLOv8

来源：评论

学校读者我要写书评

暂无评论

Boosting cycling stability through Al(PO3)3 loading in a Na4MnV(PO4)3/C cathode for high-performance sodium-ion batteries

引用

JOURNAL OF COLLOID AND INTERFACE SCIENCE 2023年第1期642卷 705-713页

作者： Wang, Kun Huang, Xiaobing Luo, ChuCheng Shen, YouMing Wang, Haiyan Zhou, Tao Cent South Univ Coll Chem & Chem Engn Hunan Prov Key Lab Chem Power Sources Changsha 410083 Peoples R China Hunan Univ Arts & Sci Coll Chem & Mat Engn Hunan Prov Key Lab Water Treatment Funct Mat Hunan Prov Key Lab Control Technol Distributed Ele Changde 415000 Peoples R China

Mn-based NASICON-type Na4MnV(PO4)3 (NMVP) has been widely investigated as one of the most promising alternatives to Na3V2(PO4)3 cathodes for sodium-ion batteries (SIBs) due to its higher energy density, higher abundance, and lower cost and toxicity compared to V. However, electrochemical performance for large-scale applications is limited by NMVP's inferior conductivity and structural degradation during cycling. Herein, a facile strategy to modify the surface/interphase properties of NMVP/C was reported using the thermally stable Al(PO3)3 precursor with a wet process followed by heat treatment to enhance the interface stability of electrodes. The nanomodified layer has the benefits of an ionic conductor (slight NaPO3) and robust composite (Al(PO3)3), which can facilitate the stability of Mn-based cathode materials and ionic conductivity. These merits endow 1 wt% Al(PO3)3-loaded NMVP/C cathodes with a high rate performance (102/61 mAh g-1 at 0.2/50 C) and impressive cyclability (88.5%/89.7% at 5 C/10 C after 3000/4000 cycles) in Na-ion batteries at 2.5-3.8 V. Moreover, when the cutoff voltage is raised to 4 V, improved electrochemical properties (111.6/50.8 mAh g-1 at 0.2/10 C and 71.4% after 1000 cycles at 5 C) are also realized. Such an enhancement indicates that facial surface modification engineering limits organic electrolyte erosion, inhibits transition metal dissolution and suppresses surface lattice degradation, which is confirmed by ex situ X-ray diffractometry and transmission electron

关键词： Na plus batteries Surface modification High stability Na4MnV(PO4)3 Na plus -storage mechanism

来源：评论

学校读者我要写书评

暂无评论

High-Rate-Capacity Cathode Based on Zn-Doped and Carbonized Polyacrylonitrile-Coated Na4MnV(PO4)3 for Sodium-Ion Batteries

引用

ACS APPLIED MATERIALS & INTERFACES 2023年第18期15卷 22132-22141页

作者： Yang, Anping Huang, Xiaobing Luo, ChuCheng Wang, Haiyan Zhou, Tao Chem Engn Cent South Univ Coll Chem Hunan Prov Key Lab Chem Power Sources Changsha 410083 Peoples R China Hunan Univ Arts & Sci Coll Chem & Mat Engn Hunan Prov Key Lab Water Treatment Funct Mat Hunan Prov Key Lab Control Technol Distributed Ele Changde 415000 Peoples R China

Na4MnV(PO4)3 (NMVP) is a promising cathode material for sodium-ion batteries (SIBs) because of its extraordinary three-dimensional structure that provides plenty of channels for sodium-ion migration. However, the unsatisfied electrical conductivity of NMVP limits its utilization in SIBs. Herein, Zn-doped NMVP with a uniform carbonized polyacrylonitrile (PAN) coating layer, named NMZVP@cPAN, was synthesized via a sol-gel method, and carbonized PAN was uniformly distributed on the surface of NMVP. Therefore, the NMZVP@ cPAN cathodes exhibited an outstanding discharge capacity of 70.6 mA center dot h center dot g-1 at 30 C and remarkable cycling stability with an admirable retention of 89.64% after 1000 cycles at 5 C. Rietveld refinement and ex situ X-ray diffraction analyses were performed to determine the change in the crystal structure. Density functional theory calculations were performed to determine the effects of Zn doping on the density of states and the migration energy barriers. Finally, the NMZVP@cPAN cathodes were successfully modified and could be used in SIBs as NMVP cathodes.

关键词： sodium-ion batteries Na4MnV(PO4)3 carbonized polyacrylonitrile Zn-doped high-rate capacity storage mechanism

来源：评论

学校读者我要写书评

暂无评论

Prescribed Performance control for Double-Integrator Multi-Agent Systems: A Unified Event-Triggered Consensus Framework

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS 2024年第9期71卷 4222-4232页

作者： Hou, Yahui Hu, Wenfeng Li, Jianqi Huang, Tingwen Cent South Univ Sch Automat Changsha 410083 Peoples R China Hunan Univ Arts & Sci Sch Comp & Elect Engn Changde 415000 Peoples R China Key Lab Hunan Prov Control Technol Distributed Ele Changde 415000 Peoples R China

In this paper, we address the event-triggered consensus problem for double-integrator multi-agent systems with prescribed performance. First, we propose a unified event-triggered consensus framework that accommodates various performance specifications. Within this framework, we present a novel nonlinear control protocol that operates at intermittent time instants, utilizing relative positions and absolute velocities. These time instants are determined by a delicately designed edge-based event-triggering mechanism, while guaranteeing the prescribed performance specifications on relative positions. Furthermore, we extend the control protocol to encompass the guaranteed performance specifications for both relative positions and relative velocities. To eliminate the need for continuous monitoring of neighboring agents' states, a unified self-triggered consensus framework with guaranteed performance is developed. With the proposed triggering mechanisms, no agent exhibits Zeno behavior. Finally, we validate the effectiveness of the proposed control protocols through an illustrative example.

关键词： Protocols Vehicle dynamics Transient analysis Laplace equations Tree graphs Monitoring Event-triggered consensus prescribed performance control multi-agent systems double-integrator dynamics

来源：评论

学校读者我要写书评

暂无评论

ADDet: An Efficient Multiscale Perceptual Enhancement Network for Aluminum Defect Detection

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2024年 73卷 1页

作者： Zhu, Jiang Pang, Qingwei Li, Saisi Tian, Shujuan Li, Jianqi Li, Yanchun Xiangtan Univ Sch Automat & Elect Informat Xiangtan 411105 Peoples R China Xiangtan Univ Hunan Int Sci & Technol Cooperat Base Intelligent Xiangtan 411105 Peoples R China Xiangtan Univ Key Lab Hunan Prov Internet Things & Informat Secu Xiangtan 411105 Peoples R China Hunan Prov Key Lab Control Technol Distributed Ele Changde 415000 Peoples R China

As an indispensable material, aluminum requires real-time surface defect detection to effectively control quality. However, defects on the surface of aluminum have the inherent properties of tiny size, diverse morphology, and multiscale variations, which present a significant challenge for defect detection. This article aims to improve the performance and efficiency of a defect detection model and proposes an efficient multiscale perceptual enhancement network for aluminum defect detection (ADDet). First, to compensate for the loss of deep features and mitigate information interference from the background, a multilayer semantic-aware enhancement module (MSEM) is proposed for the feature extraction network. Second, a proximity feature pyramid (PFP) structure in the neck is designed to effectively merge multiscale features with low computational cost and enhance feature representation across spatial coordinates, channels, and scales. Finally, a large kernel-size decoupled head (LKSDH) with a large receptive field and multiple detection branches is constructed in the detection head to improve detection accuracy. Experimental results show that the mean average precision (mAP) of the proposed ADDet is 80.85% with a real-time detection speed of 63.41 frames per second (FPS). Compared to YOLOv7, ADDet improves the mAP by 3.02%, and the number of parameters and FLOPs are reduced by 23.8% and 13%, respectively. Moreover, ADDet is shown to be superior to state-of-the-art detection methods in terms of detection accuracy.

关键词： Feature extraction Aluminum YOLO Surface morphology Steel Convolution Surface treatment Attention mechanism multilevel features multiscale object detection surface defect detection

来源：评论

学校读者我要写书评

暂无评论

A dual-scale hybrid prediction model for UAV demand power: Based on VMD and SSA optimization algorithm

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2024年第1期46卷 1393-1406页

作者： Zhang, Bin Li, Jianqi Li, Zewen Sun, Jian Xia, Yixiang Zou, Pinlong Changsha Univ Sci & Technol Elect & Informat Engn Changsha Peoples R China Hunan Univ Arts & Sci Hunan Prov Key Lab Control Technol Distributed El Changde Peoples R China Hunan Univ Changsha Peoples R China

The prediction of power demand for unmanned aerial vehicles (UAV) is an essential basis to ensure the rational distribution of the energy system and stable economic flight. In order to accurately predict the demand power of oil-electric hybrid UAV, a method based on variational mode decomposition (VMD) and Sparrow Search Algorithm (SSA) is proposed to optimize the hybrid prediction model composed of long-short term memory (LSTM) and Least Squares Support Vector Machine (LSSVM). Firstly, perform VMD decomposition on the raw demand power data and use the sample entropy method to classify the feature-distinct mode components into high-frequency and low-frequency categories. Then, each modality component was separately input into the mixed model for rolling prediction. The LSSVM model and LSTM model were used to process low-frequency and high-frequency components, respectively. Finally, the predicted values for each modal component are linearly combined to obtain the final predicted value for power demand. Compared with the current models, the prediction model constructed in this paper stands out for its superior ability to track the changing trends of power demand and achieve the highest level of prediction accuracy.

关键词： UAV demand power variational mode decomposition sparrow search algorithm long-short term memory long-short term memory

来源：评论

学校读者我要写书评

暂无评论

Quasi-solid electrolytes based on ZIF-8 to improve the electrochemical properties of lithium-ion batteries across a wide temperature range

引用

INTERNATIONAL JOURNAL OF eleCTROCHEMICAL SCIENCE 2024年第5期19卷

作者： Gao, Shuai Long, Hongkun Liu, Weigang Zhang, Zhi Qiu, Shengqiang Yi, Maoyi Li, Jie Cent South Univ Sch Met & Environm Changsha 410083 Peoples R China Hunan Univ Arts & Sci Coll Chem & Mat Engn Hunan Prov Key Lab Water Treatment Funct Mat Hunan Prov Key Lab Control Technol Distributed Ele Changde 415000 Peoples R China Guangdong Mic Power New Energy Co Ltd Huizhou 516000 Peoples R China

Poor safety of liquid electrolytes and low ionic conductivity of solid electrolytes under room temperature are two major constraints for high energy density, long-term stability and safety of lithium-ion batteries (LIBs). In order to remedy the deficiencies, a quasi-solid electrolyte (QSE) is developed by immobilizing liquid electrolyte into the host of porous 2-Methylimidazole zinc salt (ZIF-8), and then mixing them with solid polymer electrolyte solvent of polyoxyethylene (PEO). The QSE has an ionic conductivity of 0.44 mS cm-1 at 20 degrees C and 2.27 mS cm-1 at 50 degrees C. The assembled LiFePO4/QSE/Li batteries exhibit excellent electrochemical performance in a wide temperature range. A reversible capacity of 129.7 mAh g-1 at 0.5 C and 20 degrees C and high capacity retentation of 94.7% at 0.5 C and 50 degrees C are achieved after 100 cycles. Especially, the LiFePO4/QSE/graphite pouch full cell exhibits a capacity retention of 97.7% at 0.5 C and 25 degrees C. These results indicate that QSE is a suitable candidate for enhancing the electrochemical performance of LIBs.

关键词： ZIF-8 Quasi -solid electrolyte PEO Lithium -ion battery Energy storage and conversion Nanocomposites

来源：评论

学校读者我要写书评

暂无评论

Nanosheet-Assembled Hierarchical Petal-like Na4MnV(PO4)3@Carbonized-Polyaniline Microspheres for Stable Sodium-Ion Batteries

引用

ACS APPLIED ENERGY MATERIALS 2022年第12期5卷 15701-15709页

作者： Wang, Kun Huang, Xiaobing Luo, ChuCheng Zhang, Zhi Wang, Haiyan Zhou, Tao Hunan Univ Arts & Sci Coll Chem & Mat Engn Hunan Prov Key Lab Water Treatment Funct Mat Hunan Prov Key Lab Control Technol Distributed Ele Changde 415000 Peoples R China Cent South Univ Coll Chem & Chem Engn Hunan Prov Key Lab Chem Power Sources Changsha 410083 Peoples R China

NASICON-structured Na4MnV(PO4)3 (NMVP) has been counted as one of the best alternatives to Na3V2(PO4)3 because of its higher redox voltage and less cost and toxicity, although it still suffers from poor conductivity. To overcome the disadvantage, this study designed nanosheetassembled hierarchical petal-like NMVP microspheres with a nitrogen-doped carbon matrix via a facile dissolvent evaporation method and heat treatment. After morphological construction and carbonized-polyaniline decoration, the as-prepared NMVP-D@cPANI delivers a robust nanosheet-assembled framework and enhanced electrochemical reaction activity. As a result, the optimized NMVP-D@cPANI half-cell exhibits ultralong cyclability (conservation rate of 85.5% at 10 C (1 C = 111 mA h g-1) over 4000 cycles) and superior rate capability (61.68 mAh g-1 at 50 C). Furthermore, this work achieved a feasible strategy for a low-cost NMVP-D@cPANI//CHC full cell, which proves the possibility of the advancement and application in SIBs for NMVP.

关键词： Na plus batteries Na4MnV(PO4)3 petal-like microspheres surface decoration Na plus -storage mechanism

来源：评论

学校读者我要写书评

暂无评论

Improving Visual Question Answering by Image Captioning

引用

IEEE ACCESS 2025年 13卷 46299-46311页

作者： Shao, Xiangjun Dong, Hongsong Wu, Guangsheng Hunan Univ Arts & Sci Sch Comp & Elect Engn Changde 415000 Peoples R China Key Lab Hunan Prov Control Technol Distributed Ele Changde 415000 Peoples R China Wuhan Univ Sch Comp Sci Wuhan 430072 Peoples R China Lyuliang Univ Dept Comp Sci Luliang 033000 Peoples R China Xinyu Univ Sch Math & Comp Sci Xinyu 338004 Peoples R China

Visual Question Answering (VQA) is a challenging task that bridges the computer vision and natural language processing communities. It provide natural language answers to questions related to an associated image. Most existing VQA methods focus on the fusion and inference of visual features with the textual question. However, visual features often lack the necessary semantic information required to answer the questions accurately. To address this limitation, we propose a novel approach called Question-Guided Parallel Attention (QGPA), which effectively leverages the semantic information provided by an embedded image captioning model to answer related questions. First, we introduce an Attention-Aware (AA) mechanism that extends the traditional attention mechanism, helping to filter out incorrect or irrelevant information during answer prediction. Second, QGPA incorporates AA, which simultaneously utilizes visual features and semantic information from the embedded image captioning model to answer questions. Experiments results demonstrate that the accuracy of "Overall" of our proposed model delivers 72.57% and 72.55% on the test-dev and test-std split set of VQA-v2.0 dataset, respectively, which outperforms most existing VQA methods. The experiment results and ablation studies demonstrate that the proposed method has good performance.

关键词： Visualization Semantics Long short term memory Question answering (information retrieval) Predictive models Accuracy Knowledge based systems Feature extraction Information filters Context modeling Deep learning image captioning multimodal learning visual question answering

来源：评论

学校读者我要写书评

暂无评论

Reading Recognition Method of Mechanical Water Meter Based on Convolutional Neural Network in Natural Scenes

引用

JOURNAL OF ADVANCED COMPUTATIONAL INTELLIGENCE AND INTELLIGENT INFORMATICS 2024年第1期28卷 206-215页

作者： Li, Jiangi Shen, Jinfei Nie, Keheng Du, Rui Zhu, Jiang Long, Hongyu Hunan Univ Arts & Sci Dept Commun & Elect Engn 3150 Dongting Rd Changde 415000 Hunan Peoples R China Hunan Prov Key Lab Control Technol Distributed Ele 3150 Dongting Rd Changde 415000 Hunan Peoples R China Jishou Univ Coll Informat Sci & Engn 120 South Renmin Rd Jishou 416000 Hunan Peoples R China Hunan Acad Bldg Res Co Ltd 7 Wenchuang Rd Changsha 410014 Hunan Peoples R China

To satisfy the demand for real-time and high-precision recognition of mechanical water meter readings in natural scenes, a reading recognition method for mechanical water meters based on you only look once version 4 (YOLOv4) is proposed in this paper. First, a focus structure is introduced into the feature extraction network to expand the receptive field and reduce the loss of original information. Second, a ghost block cross stage partial module is constructed to improve the feature fusion of the network and enhance the feature representation. Finally, the loss function of YOLOv4 is improved to further enhance the detection accuracy of the network. Experimental results show that the mAP@O.5 and mAP@O.5:.95 of the proposed method are 97.9% and 77.3%, respectively, which are 1.6% and 6.0% higher, respectively, than those of YOLOv4. Additionally, the number of parameters and computation amount of the proposed method are 48.6% and 36.8% lower, respectively, whereas its inference speed is 27% higher. The proposed method is applied to assist meter reading, which significantly reduces the workload of onsite meter-reading personnel and improves work efficiency.

关键词： water meter reading convolution neural network automatic meter reading object detection

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：