检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Qu, Shuai Ren, Yuhao Hu, Guobiao Dong, Liwei Yang, Jizhong Wu, Zaixin Zhu, Shengyang Yang, Yaowen Zhai, Wanming Train and Track Research Institute State Key Laboratory of Rail Transit Vehicle System Southwest Jiaotong University Chengdu610031 China School of Civil and Environmental Engineering Nanyang Technological University 639798 Singapore Guangzhou China Institute of Rail Transit Tongji University Shanghai201804 China China Railway Eryuan Engineering Group Co. LTD Chengdu China Sichuan Shudao New System Rail Group Co. LTD Chengdu China

This study proposes a comprehensive approach for optimizing piezoelectric energy harvesters (PEHs) in railway settings, aiming at enhancing their applicability for railway structural health monitoring (SHM) applications. Unlike conventional methods that align the fundamental frequency of the PEH with the dominant frequency of the vibration source, this study introduces and applies an event-driven optimization strategy. Our approach begins by developing a high-fidelity dynamic model of the PEH and an advanced vehicle-track coupled dynamic model. The vehicle-track interaction forces and vehicle-induced track vibrations are predicted at various train speeds, on different track structures, and over varying track irregularities. Utilizing these predicted track vibrations, we assess the energy harvesting performance of designed PEHs using the developed high-fidelity PEH dynamic model. In this study, we consider 12 distinct vehicle-track conditions, resulting in a total of 3600 sets of simulation data, each representing a specific event. We employ the particle swarm optimization (PSO) algorithm to identify optimal PEH designs for different events. To streamline the process, instead of offering one optimal solution for each event, we employ the K-means algorithm to cluster similar events. Subsequently, we choose the centroid design for each cluster as the representative to address events in that cluster. This approach allows us to use a limited number of representative PEHs to effectively address most events across different clusters. Finally, we thoroughly examine and evaluate the dynamic responses of these representative designs to demonstrate their robust performance. This study represents a pioneering exploration of PEH design optimization toward applications in rail transportation systems under diverse operational conditions. © 2023, The Authors. All rights reserved.

关键词： Energy harvesting

来源：评论

学校读者我要写书评

暂无评论

Spatial Variation Motion Blur Bridge Image Quality Improvement

Spatial Variation Motion Blur Bridge Image Quality Improveme...

引用

Frontiers Technology of Information and Computer (ICFTIC), IEEE International Conference on

作者： Dan Tao Suyuan Deng Guangying Qiu Dequan You Linming Wu State Key Laboratory of Rail Transit Infrastructure Performance Monitoring and Guarantee East China Jiaotong University Nanchang China School of Electrical and Automation Engineering East China Jiaotong University Nanchang China Fujian Communications Research Institute Co. Ltd. Fuzhou China

ISBN: (数字)9798331541750

ISBN: (纸本)9798331541767

China is a leading nation in bridge construction, with bridge infrastructure not only forming a critical part of the transportation network but also driving regional economic development. To ensure the safety and reliability of these structures, regular inspection and maintenance are required, with crack detection being particularly crucial. With technological advancements, machine vision has started to be applied in bridge health monitoring. However, due to issues such as low light, noise, and camera shake, images often exhibit motion blur, leading to the loss of key details and structural deformation, which affects the accuracy of crack detection. To address this, this paper proposes an image restoration algorithm that incorporates a strip attention mechanism, leveraging intra- and inter-strip attention blocks within the Transformer framework to handle blurs of different directions and magnitudes. Additionally, an operator is used for sharpening to reduce artifacts and noise, thereby improving the deblurring effect. Experimental results demonstrate that this algorithm effectively enhances image quality, improving the reliability of data used for bridge health management.

关键词： Bridges Image quality Strips Machine vision Noise Transportation Transformers Safety Maintenance Monitoring

来源：评论

学校读者我要写书评

暂无评论

Research on Anti-Swing Strategies for Bridge Cranes

Research on Anti-Swing Strategies for Bridge Cranes

引用

2024 China Automation Congress, CAC 2024

作者： Wang, Shiqi Hou, Enguang Zheng, Haoyuan Jiang, Yuyi Shen, Zhen Xiong, Gang The College of Rail Transit Shandong Jiaotong University Jinan250399 China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing100190 China Intelligent Manufacturing Center Qingdao Academy of Intelligent Industries Qingdao266144 China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan523808 China State Key Laboratory of Multimodal Artifcial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9798350368604

A study is conducted on the LH5T-13.5M electric crane, focusing on the swing characteristics of the load during steel coil lifting operations and the displacement issue of the crane. Initially, the system model is formulated using the Lagrange dynamic equations, translating the practical challenges into a solvable mathematical framework and deriving the transfer function of interest. Subsequently, the development of three control strategies is elucidated, formulated on the basis of the established model: a conventional PID control system, a fuzzy PID control system, and an adaptive proportional factor fuzzy neural PID controller. These systems are simulated and validated using Simulink. A comparative experimental setup is employed to evaluate performance. The results show that when the step input signal is 1, the maximum absolute load swing Angle of the traditional PID, fuzzy PID and adaptive scale factor fuzzy neural PID controller are 0.185°, 0.054° and 0.049° respectively for the working condition 1 experiment. The percentage overshoot corresponding to the wheelbarrow is 37.1%, 40.0%, and 30.5%, respectively. The findings indicate that the introduced fuzzy neural PID controller, equipped with an adaptive scaling factor, exhibits superior stability and effectiveness in maintaining the crane’s operation within the optimal range of parameters. © 2024 IEEE.

关键词： Bridge cranes

来源：评论

学校读者我要写书评

暂无评论

Joint Prediction of the state of Health and Remaining Useful Life for Lithium-Ion Batteries Based on Wrapper Cascade-Stacking

SSRN

引用

SSRN 2023年

作者： Qu, Zhijian Ma, Shuaijun Zhu, Lin Hou, Xinxing Yuan, Chen He, Yang State Key Laboratory of Performance Monitoring Protecting of Rail Transit Infrastructure East China Jiaotong University Jiangxi Nanchang330013 China College of Electrical and Automation Engineering East China Jiaotong University Jiangxi Nanchang330013 China

The state of health (SOH) and remaining useful life (RUL) of lithium-ion batteries are important indicators for assessing battery safety and stability. However, using only a single model to predict one of the two makes it difficult to comprehensively assess the health status of lithium-ion batteries. Therefore, this paper proposes a joint SOH and RUL prediction method based on Cascade-Stacking integration. The method first uses the Wrapper feature selection algorithm to select the best health feature. Then, learning algorithms such as long and short-term memory neural network and extreme gradient boosting tree (XGBoost) are stacked using the first Stacking Integration algorithm to build a lithium-ion battery aging model for SOH prediction. A second Stacking integration algorithm is used to superimpose support vector machine, XGBoost and random forest to predict the trend of the optimal health feature with increasing number of cycles, and the predictions are series-coupled with the battery aging model to achieve RUL prediction. The performance of the proposed method is verified using the NASA battery degradation dataset, and the results show that the method can simultaneously achieve RUL prediction error within 4 cycles and SOH root-mean-square error within 1.6%, thus validating the effectiveness and accuracy of the method. © 2023, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Fast and Regularized Reconstruction of Building Fac Ades from Street-View Images Using Binary Integer Programming 24

Fast and Regularized Reconstruction of Building Fac Ades fro...

引用

2020 24th ISPRS Congress on Technical Commission II

作者： Hu, Han Wang, Libin Zhang, Mier Ding, Yulin Zhu, Qing State Key Laboratory of Rail Transit Engineering Informatization China Railway First Survey Design Institute Co. Ltd. Xian China Faculty of Geosciences and Environmental Engineering Southwest Jiaotong University Chengdu China

Regularized arrangement of primitives on building facądes to aligned locations and consistent sizes is important towards structured reconstruction of urban environment. Mixed integer linear programing was used to solve the problem, however, it is extremely time consuming even for state-of-the-art commercial solvers. Aiming to alleviate this issue, we cast the problem into binary integer programming, which omits the requirements for real value parameters and is more efficient to be solved. Firstly, the bounding boxes of the primitives are detected using the YOLOv3 architecture in real-time. Secondly, the coordinates of the upper left corners and the sizes of the bounding boxes are automatically clustered in a binary integer programming optimization, which jointly considers the geometric fitness, regularity and additional constraints;this step does not require a priori knowledge, such as the number of clusters or pre-defined grammars. Finally, the regularized bounding boxes can be directly used to guide the facąde reconstruction in an interactive environment. Experimental evaluations have revealed that the accuracies for the extraction of primitives are above 0.82, which is sufficient for the following 3D reconstruction. The proposed approach only takes about 10% to 20% of the runtime than previous approach and reduces the diversity of the bounding boxes to about 20% to 50%. © 2020 Copernicus GmbH. All rights reserved.

关键词： Integer programming

来源：评论

学校读者我要写书评

暂无评论

Tracking Control of High-Speed Trains Based on An Improve Disturbance Observer

Tracking Control of High-Speed Trains Based on An Improve Di...

引用

Data Driven Control and Learning Systems (DDCLS)

作者： Jian-Ping Zhang Lin-Bao Deng Chun-Hua Xie School of Electrical and Automation Engineering East China Jiaotong University Nanchang Jiangxi China State Key Laboratory of Performance Monitoring Protecting of Rail Transit Infrastructure East China Jiaotong University Nanchang Jiangxi China Key Laboratory of Advanced Control & Optimization of Jiangxi Province Nanchang Jiangxi China

Accurate tracking of position and velocity is a critical problem to be solved for the automatic train operation (ATO) system. However, achieving automatic operation for high-speed trains (HSTs) is difficult due to unknown disturbances and actuator faults. This paper uses an improved disturbance observer-based control (IDOBC) strategy to solve this issue. Each carriage is considered a particle and connected by a flexible coupler to establish the multiple point-mass model for HSTs by considering unknown lumped disturbances and actuator faults. For the lumped disturbances caused by the external environment, an improved disturbance observer is designed to compensate for the impact caused by this component on HSTs. Based on the given linear matrix inequality, the HSTs system satisfies the $H_{\infty}$ performance under the IDOBC strategy. Compared with traditional DOBC, the proposed IDOBC has higher tracking accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Promoting Grain Refinement and Nanocrystal Generation in Surface Nanomachining by Means of Overlapping Collisions

SSRN

引用

SSRN 2024年

作者： Shen, Mingxue Wang, Zhiqiang Hu, Qiang Li, Xiaobo Zhuang, Hui Liu, Shaopeng State Key Laboratory of Performance Monitoring and Protecting of Rail Transit Infrastructure East China Jiaotong University Nanchang330013 China School of Materials Science and Engineering East China Jiaotong University Nanchang330013 China Institute of Applied Physics Jiangxi Academy of Sciences Nanchang330095 China

Surface nanostructuring is an effective method for enhancing the mechanical properties and wear resistance of moving parts, but a comprehensive understanding of its formation mechanism is lacking. This study examined the microstructure evolution of pure copper under various linear overlapping ratios (φ) using a self-made impact wear tester. The results revealed that high Smid factor grains activate the basal slip system to handle deformation during repeated impacts. Still, overlapping impacts can intensify plastic deformation by activating multiple slip systems and boosting dislocation proliferation. Moreover, overlapping collisions will generate Frank's incomplete dislocations, hindering dislocation slip and generating cross-slip trajectories, resulting in the bending of slip trajectories, the formation of uneven wrinkles, and the refinement of superficial grains. © 2024, The Authors. All rights reserved.

关键词： Nanocrystals

来源：评论

学校读者我要写书评

暂无评论

Investigation of Characteristics of Splash Lubrication and Churning Power Loss in Gearboxes with a Guide Plate

SSRN

引用

SSRN 2024年

作者： Liu, Yi Shao, Shuai Yao, Yuan Wang, Xi Zhang, Kailin State Key Laboratory of Rail Transit Vehicle System Southwest Jiaotong University Chengdu610031 China Department of Mechanics and Maritime Sciences Chalmers University of Technology Gothenburg41296 Sweden Simulation Department Suzhou shonCloud Engineering Software Co. Ltd. Suzhou215100 China

In order to clarify the action mechanism of the guide plate's influence on the oil flow and power loss of the gearbox, this paper investigates the churning loss and lubrication performance of the gearbox with guide plate based on an advanced MPS method. The numerical results were compared with the existing experimental results to verify the applicability and accuracy of the numerical method. The effects of rotational speed and oil immersion depth on the oil flow in the gearbox were analyzed, and the structural parameters of the guide plate were changed to reduce the churning loss. It is found that the total churning loss decreases due to the effect of the guide plate, which is related to the weake © 2024, The Authors. All rights reserved.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Optimization of Municipal Solid Waste Incineration Bottom Ash Geopolymer with Granulated Blast Furnace Slag (Ggbfs): Microstructural Development and Heavy Metal Solidification Mechanism

SSRN

引用

SSRN 2024年

作者： Li, Yue Yan, Xinyu Wan, Man Ling, Fan Hu, Junjie Liang, Zhen Liu, Jun CCCC Construction Co. Ltd Guangzhou511466 China Guangdong Engineering Technology Research Centre of Municipal Rail Transit Lean Construction 511466 China Guangdong Provincial Key Laboratory of Durability for Marine Civil Engineering College of Civil and Transportation Engineering Shenzhen University Shenzhen518060 China State Key Laboratory of Intelligent Construction and Healthy Operation and Maintenance of Deep Underground Engineering College of Civil and Transportation Engineering Shenzhen University Shenzhen518060 China

The enormous increase in municipal solid waste (MSW) has resulted in a large volume of incinerator bottom ash (MSWIBA). With the widespread adoption of trash incineration technologies, the disposal of significant amounts of MSWIBA is inevitable to minimize groundwater and soil contamination from direct *** has an oxide composition similar to silicate cement and might be utilized as an alkali-activated material (AAM). However, because MSWIBA has a low active calcium content, the mechanical characteristics of AAM made from MSWIBA alone are unsatisfactory. As a result, this work investigated the optimization of mechanical characteristics and microstructure of alkali-activated bottom ash material (AABAM) by integrating the high calcium mineral GGBFS. The environmental friendliness of AABAM was assessed using mechanical compressive strength tests, XRD, SEM, EDS, MIP, and heavy metal leaching. The results showed that the inclusion of GGBFS greatly improved the early strength of AABAM, with compressive strength increasing by up to 663.7% to 43.0 MPa after 28 days of curing. Meanwhile, GGBFS boosted gel formation and optimized AABAM porosity to better enclose the metal elements, with Cr solidification efficiency reaching 86.4%. The synergistic treatment of MSWIBA and GGBFS not only resulted in the efficient use of solid waste resources but also provided a novel option for municipal solid waste management. © 2024, The Authors. All rights reserved.

关键词： Slags

来源：评论

学校读者我要写书评

暂无评论

An Attentional Deep Learning Model Based on Improved Cp Optimizer for state of Health Prediction of Lithium-Ion Batteries

SSRN

引用

SSRN 2024年

作者： Peng, Simin Zhang, Daohan Jiang, Yuxia Wang, Lin Liu, Yonggang Pecht, Michael School of Electrical Engineering Yancheng Institute of Technology Yancheng Yancheng224051 China School of Mechanical Engineering and Rail Transit Changzhou University Changzhou213164 China State Key Laboratory of Mechanical Transmission for Advanced Equipment Chongqing University Chongqing400000 China University of Maryland College Park20742 United States

Abstract−Accurate prediction and effective management of battery state of health (SOH) can maximize battery utilization. Traditional SOH prediction models based on deep learning frequently encounter issues like inadequate representation capabilities of health features (HFs) and improper hyper-parameter settings. An improved deep learning approach is developed to predict the SOH of lithium-ion batteries, leveraging a channel attention mechanism and improved Crested Porcupine Optimizer (ICPO). In comparison to traditional convolutional neural networks (CNNs), improved CNNs incorporating a channel attention mechanism can emphasize more crucial feature information regardless of input conditions. Aiming at the shortcomings of the recurrent neural network (RNN)-based single model, which ignores the long-term dependencies between battery aging and HFs, the deep learning method based on the GRU-LSTM is developed to address the capacity regeneration phenomenon of batteries and estimate SOH. Furthermore, an ICPO is incorporated into the model to optimize the model's hyper-parameters for SOH prediction. The experimental results demonstrate that all SOH estimation errors using the developed method are below 2.2% in different application scenarios, indicating the highest SOH prediction accuracy among the other methods, such as LSTM and its improved methods. © 2024, The Authors. All rights reserved.

关键词： Lithium-ion batteries

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：