检索结果-内蒙古大学图书馆

6th International Conference on Computer Information Science and Application Technology, CISAT 2023

作者： Zhang, Shihao Li, Yang Song, Mingzhao Ma, Xiao Shandong Provincial Key Laboratory of Robot and Manufacturing Automation Technology Ji Nan China

ISBN: (纸本)9781510668546

This study ensures the safe operation of bridges by real-time recognition of concrete surface cracks on bridges. Traditional crack recognition methods are slow and have low accuracy. To address this issue, we propose an improved YOLOv5 (You Only Look Once version 5) detection model based on Deformable Convolution (DCN), called YOLOv5-D. The baseline YOLOv5 model has been optimized in three aspects: First, deformable convolution replaces part of the standard convolution in the backbone network, improving the model's recognition accuracy. Second, the SE attention mechanism is added to adaptively recalibrate channel-wise feature responses, stimulating information features and thereby enhancing the shared underlying feature map representations. Third, the CIOU_Loss is proposed as the loss function, achieving a collaborative optimization of crack detection speed and accuracy, and meeting the deployment requirements of embedded terminals. The improved YOLOv5-D model achieves an average recognition rate (mAP) of 76.1% and a recognition speed of 54 FPS with a model size of 14.5 MB. Compared to the original YOLOv5 model, the average recognition rate is increased by approximately 5.9%, the parameter quantity is reduced by about 10%, and the detection speed remains essentially unchanged. In summary, the YOLOv5-D model achieves a better balance in terms of accuracy and speed, effectively locates cracks, and provides a new technology for early warning of bridge collapse disasters. © 2023 SPIE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Central Finite-Difference Based Gradient Estimation methods for Stochastic optimization

Central Finite-Difference Based Gradient Estimation Methods ...

引用

Simulation Winter Conference

作者： Raghu Bollapragada Cem Karamanli Stefan M. Wild Operations Research and Industrial Engineering The University of Texas at Austin Austin TX USA Applied Math. and Comp. Res. Division Lawrence Berkeley National Laboratory Beckeley CA USA

ISBN: (数字)9798331534202

ISBN: (纸本)9798331534219

This paper presents an algorithmic framework for solving unconstrained stochastic optimization problems using only stochastic function evaluations. We employ central finite-difference based gradient estimation methods to approximate the gradients and dynamically control the accuracy of these approximations by adjusting the sample sizes used in stochastic realizations. We analyze the theoretical properties of the proposed framework on nonconvex functions. Our analysis yields sublinear convergence results to the neighborhood of the solution, and establishes the optimal worst-case iteration complexity $\left(\mathscr{O}\left(\varepsilon^{-1}\right)\right)$ and sample complexity $(\theta(\epsilon^{-2}))$ for each gradient estimation method to achieve an $\varepsilon$ -accurate solution. Finally, we demonstrate the performance of the proposed framework and the quality of the gradient estimation methods through numerical experiments on nonlinear least squares problems.

关键词： Accuracy Heuristic algorithms Estimation Approximation algorithms complexity theory optimization Finite difference methods Convergence

来源：评论

学校读者我要写书评

暂无评论

Parameter Recognition of Solar Cell Model Based on ICOOT Algorithm

Parameter Recognition of Solar Cell Model Based on ICOOT Alg...

引用

IEEE International Conference on Mechatronics and Automation

作者： Wang Rong Yanjuan Wu Jisong Ye Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems Tianjin Key Laboratory of New Energy Power Conversion Transmission and Intelligent Control Tianjin University of Technology Tianjin China

ISBN: (数字)9798350388077

ISBN: (纸本)9798350388084

Solar cell model parameter recognition is crucial for accurate photovoltaic power generation prediction, necessitating high accuracy in identification. To tackle this challenge, we introduce the refined Chicken optimization Algorithm (ICOOT), specifically tailored for solar cell model parameter identification. Initially, we validate the algorithm's superiority by comparing it against existing algorithms, followed by further evaluation using measured data from Radiation Tolerant Cell (RTC) solar cells. After comparing it with four alternative methods, the superiority of the introduced ICOOT model is clearly demonstrated. We demonstrate its practical applicability by selecting French RTC silicon solar cells for parameter identification. A comparative analysis, including Root Mean Square Error (RMSE), is conducted against six other models, highlighting the proposed model's lower RMSE and broader applicability.

关键词： Analytical models Parameter estimation Accuracy Photovoltaic cells Predictive models Prediction algorithms Silicon

来源：评论

学校读者我要写书评

暂无评论

A Sensitivity Analysis-based Method For Optimal Allocation of High-capacity Dynamic Voltage Restorers in Radial Distribution Networks

A Sensitivity Analysis-based Method For Optimal Allocation o...

引用

Power Engineering (ICPE), International Conference on

作者： Kangzhi Zheng Ling Wang Chunming Tu Fan Xiao Shantou Chaonan Power Supply Co. Ltd China Southern Power Grid Shantou China Guangdong Provincial Key Laboratory of Electric Power Equipment Reliability Electric Power Research Institute of Guangdong Power Grid Co. Ltd Guangzhou China National Electric Power Conversion and Control Engineering Technology Research Center Hunan University Changsha China

ISBN: (数字)9798331531140

ISBN: (纸本)9798331531157

Overloading some nodes in a complex radial distribution network can lead to serious voltage deviation problems. Configuring a large-capacity dynamic voltage restorer is an effective measure to solve the node voltage offset problem. This paper proposes an optimization method for configuring highcapacity dynamic voltage restorers based on sensitivity analysis, which can quickly and reasonably select the installation location and capacity of high-capacity dynamic voltage restorers in the distribution network. It can quickly solve the installation location and capacity of large-capacity dynamic voltage restorers. Considering the vertical and horizontal structure of the radial distribution network, a governance model that focuses on vertical governance is proposed and supplemented by horizontal governance. First, the sensitivity of the large-capacity dynamic voltage restorer is calculated for all nodes using sensitivity analysis methods. In this way, the installation position of the large-capacity dynamic voltage restorer is obtained. Second, the sum of the absolute values of the voltage offset at the nodes of the radial distribution network is taken as the objective function. Establish a large-capacity dynamic voltage restorer capacity-optimized model. Finally, the optimization model is solved by improving the particle swarm algorithm. A case study was conducted on a 41-node radial system. The simulation results verify the rationality and effectiveness of the proposed scheme.

关键词： Power engineering Voltage measurement Fluctuations Sensitivity analysis Simulation Voltage Distribution networks Dynamic scheduling Resource management Particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Effect of a Double Helical Spring Decompression Structure Backpack on the Lumbar Spine Biomechanics of School-Age Children: A Finite Element Study

引用

MCB Molecular and Cellular Biomechanics 2023年第1期20卷 35-47页

作者： Li, Fengping Sun, Dong Zhang, Qiaolin Chen, Hairong Bíró, István Zheng, Zhiyi Gu, Yaodong Faculty of Sports Science Ningbo University Ningbo315211 China Doctoral School on Safety and Security Science Óbuda University Budapest1034 Hungary Faculty of Engineering University of Szeged Szeged6724 Hungary Anta Sports Sciences Laboratory Anta Group Xiamen362212 China

Background: A children’s backpack is one of the important school supplies for school-age children. Long-term excessive weight can cause spinal deformity that cannot be reversed. This study compared a double helical spring decompression structure backpack (DHSB) with a traditional backpack (TB) to explore the optimization of decompression devices on upper body pressure. The finite element (FE) method was then used to explore the simulation of lumbar stress with different backpacks, in order to prove that DHSB can reduce the influence of backpack weight on lumbar vertebrae, avoid the occurrence of muscle discomfort and spinal deformity in children;methods: 18 male children subjects (age: 12.5 ± 0.6 years;height: 145.5 ± 1.9 cm;bodyweight: 40.8 ± 3.1 kg) ran with DHSB and TB at a speed of 3.3 ± 0.2 m/s. Flexible pressure sensors were used to measure the pressure on the shoulder, back, and waist during running. The pressure data was then inputted into the FE model to simulate the effect of carrying different backpacks on the stress of the lumbar intervertebral disc (IVD);Result: There was a significant difference in shoulder and waist peak pressure between the DHSB and TB during the running posture. At a speed of 3.3 ± 0.2 m/s, the peak pressure of the shoulder and waist decreased. After finite element analysis, it was found that carrying DHSB on the back could effectively reduce the intervertebral disc pressure between L4-5 and L5-S1 by 27.9% and 34.1%, respectively;Conclusion: DHSB can effectively reduce the pressure on the shoulder and waist when children are running and can reduce the influence of backpacks on children’s posture to a certain extent. By finite element analysis, it is found that carrying DHSB can effectively reduce the stress of the lumbar intervertebral disc, and the damage to lumbar vertebrae is lower than with a TB. © 2023 Tech Science Press. All rights reserved.

关键词： Finite element method

来源：评论

学校读者我要写书评

暂无评论

Comprehensive optimization of photovoltaic-thermoelectric hybrid systems: Experimental analysis of cooling methods, photovoltaic strategies, and their synergistic effects

引用

Solar Energy 2025年 298卷

作者： Wang, Chang Zhang, Guoqing Wang, Yaohui Song, Lei Liu, Bo College of Mechatronics and Control Engineering Shenzhen University Guangdong Shenzhen518060 China State Key Laboratory of Intelligent Construction and Healthy Operation and Maintenance of Deep Underground Engineering Shenzhen University Guangdong Shenzhen518060 China

Currently, the photovoltaic-thermoelectric (PV-TEG) hybrid system has attracted attention due to its ability to use photovoltaic waste heat to improve power generation efficiency, but its overall energy conversion efficiency remains relatively low. Existing studies employ single optimization approaches and lack systematic, coordinated strategies, which constrain overall PV-TEG system efficiency. To address this issue, this study proposes a new integrated optimization framework comprising four modules, dividing the system into "PV optimization module, PV module, TEG module, and cooling module" to systematically combine photovoltaic optimization and cooling strategies, thereby constructing an integrated optimized PV-TEG system. First, by experimentally comparing different cooling methods, the impact of these methods on PV module temperature, TEG temperature difference, and system power output was analyzed, highlighting the important role of cooling methods in improving TEG performance. Secondly, regarding photovoltaic optimization strategies, the power gain and temperature control ability of different strategies were explored. Finally, the synergistic effect of photovoltaic optimization and cooling strategies was studied under varying solar radiation conditions, and the effects of diurnal and seasonal irradiance fluctuations were also considered, providing valuable insights into the long-term performance and reliability of PV-TEG systems in real-world environments. Experimental results demonstrate that this integrated optimization method significantly improves the overall performance of the PV-TEG system under different operating conditions. Compared to existing single optimization methods, the proposed integrated approach achieves more efficient energy utilization and offers new insights and research directions for PV-TEG system optimization design. © 2025 International Solar Energy Society

关键词： Solar power generation

来源：评论

学校读者我要写书评

暂无评论

Physics-based compact models of GaN HEMTs for high power RF applications: A review (Invited Paper)

Physics-based compact models of GaN HEMTs for high power RF ...

引用

作者： Mao, Shuman Su, Xiang Wu, Qingzhi Wang, Yan Duan, Xiangyang Tian, Shen Li, Xuehuan Xu, Yuehang Yangtze Delta Region Institute University of Electronic Science and Technology of China Huzhou China Department of RCH system & State Key Laboratory of Mobile Network and Mobile Multimedia Technology ZTE Corporation Shenzhen China

The compact model plays a pivotal role as a critical link between device fabrication and circuit design. While conventional compact model theories and techniques are generally mature, the intricate physical mechanisms of gallium nitride (GaN) high-electron mobility transistors (HEMTs) pose challenges due to their strong non-linearity in high-power radio frequency (RF) applications. This complexity hinders achieving the required precision for applications using traditional modeling methods. Therefore, the development of physics-based compact modeling techniques becomes crucial for a deeper understanding of the intricate features of GaN HEMTs. This paper explores the advancements and the current state-of-the-art in physics-based compact models. The comprehensive review covers both intrinsic core models and real-device effects models. Core models are presented with a focus on fundamental concepts, development overviews, and applications. Additionally, the real-device effects models are introduced, encompassing advanced characterization techniques and modeling methodologies. Furthermore, the paper outlines future trends in physics-based compact modeling, providing valuable insights for individuals engaged in transistor compact modeling work. © 2024 John Wiley & Sons Ltd.

关键词： Gallium nitride

来源：评论

学校读者我要写书评

暂无评论

Enhancing Wind Turbine Blade Icing Prediction Accuracy with Immune Evolution Algorithm

Enhancing Wind Turbine Blade Icing Prediction Accuracy with ...

引用

Smart Electrical Grid and Renewable Energy (SEGRE), International Conference on

作者： Xiaowei Huai Bo Li Zelin Cai Zhongde Liu Qiang Zhou Linwei Huang State Key Laboratory of Disaster Prevention and Reduction for Power Grid Hunan Disaster Prevention Technology Co. Ltd. Changsha China State Key Laboratory of Disaster Prevention and Reduction for Power Grid Changsha China State Power Investment Corporation Jiangxi Electric Power Co. Ltd Nanchang China

The highly imbalanced nature of the sample set hinders the accuracy of predicting wind turbine blade icing. To address this issue and enhance the prediction performance, we utilized the immune evolution algorithm (IEA) to dynamically optimize two critical parameters of the sampling methods: the "p" parameter (representing the ratio of iced and non-iced samples) and the "weight" parameter (indicating the loss function weight for iced samples) in LightGBM. Four sampling methods, including SMOTE (Synthetic Minority Oversampling Technique), random oversampling, random undersampling, and EasyEnsemble, were utilized to address the highly imbalanced sample issue and improve the prediction of wind turbine blade icing. The study compared the prediction performance of post-optimization and pre-optimization (traditional mainstream method) and discussed the applicability of the aforementioned sampling optimization methods. The results showed that SMOTE had the most significant improvement in AUC after optimization while other methods did not show significant improvement. This shows that traditional optimization algorithms may still have important applications in addressing blade icing sample imbalance issues.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel optimization Method for Raw Coal Blending in Coal Preparation Plants Based on Interval Programming

A Novel Optimization Method for Raw Coal Blending in Coal Pr...

引用

2023 China Automation Congress, CAC 2023

作者： Lei, Jiahui Liu, Hanwen Zhao, Jun Wang, Wei Dalian University of Technology Key Laboratory of Intelligent Control and Optimization for Industrial Equipment Ministry of Education Dalian China School of Control Science and Engineering Dalian University of Technology Dalian China Chn Energy Wuda Coal Processing Co. Ltd. Wuhai China

ISBN: (纸本)9798350303759

In the process of coal blending and washing in coal preparation plants, there are various raw coals with different quality that changes greatly, which results in poor quality and low profit. To solve these problems, a novel optimization method for raw coal blending based on interval programming is proposed. Interval numbers are introduced to represent the fluctuation range of ash and sulfur content at each density level of raw coals. A predictive model of quantity and quality of dense medium cyclone products is constructed, which uses Hermite interpolation to obtain washability curves of each raw coal and adopts fitting methods to obtain the distribution curve. In order to obtain optimal coal blending schemes, considering operation and maintenance costs of raw coal feeding line, a mixed integer nonlinear programming (MINLP) model is built, whose objective is to maximize profit with the main constraints of clean coal quality and inventory of raw coal. Interval possibility is introduced to transform constraints with interval number and a customized branch and bound algorithm is used to solve it. In order to verify the effectiveness of the method in this paper, experiments are conducted using manufacturing data from a domestic coal preparation plant. The experimental results indicate that the proposed method is practical and has better economic performance. © 2023 IEEE.

关键词： Profitability

来源：评论

学校读者我要写书评

暂无评论

Maintenance and Production optimization using artificial intelligence (AI) Tools: A Bibliometric Analysis and Review

Maintenance and Production Optimization using artificial int...

引用

Innovative Research in Applied Science, Engineering and Technology (IRASET),Conference on

作者： Mohamed Lamine Soudani Salah Nissabouri Moulay El Houssine Ech-Chhibat M2S2I Laboratory ENSET Mohammedia Hassan II University (UH2) Casablanca Morocco

ISBN: (数字)9798350309508

ISBN: (纸本)9798350309515

The ever-present challenge of optimizing production efficiency and maintenance effectiveness lies at the heart of a company's smooth operations. These two functions are intricately linked, with efficient production relying on well-maintained equipment and effective maintenance minimizing production disruptions. In this context, it is important to analyze the methods used to optimize these two services as part of the evolution of artificial intelligence (AI) tools. In this regard, based on recent literature, the main objective of this paper is to present an overview of the evolution of the use of AI tools in the optimization of maintenance and production. It also studied the AI tools most recommended by researchers. For this purpose, we will successively analyze the sorting and classification of the recent literature according to the established criteria, then, we will present and discuss the AI methods used for the optimization of maintenance and production, to conclude with a conclusion of the bibliography and the suggestions for future research.

关键词： Heart Reviews Bibliometrics Production Machine learning Learning (artificial intelligence) Maintenance

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：