检索结果-内蒙古大学图书馆

OPTIMISATION OF SELF-PUNCHING RIVETING PROCESS PARAMETERS FOR HIGH-SPEED RAIL TOP PLATES

UPB Scientific Bulletin, Series D: Mechanical Engineering 2022年第4期84卷 197-210页

作者： Zheng, Qingchun Guo, Chengmin Zhu, Peihao Liu, Jiaqi Ma, Wenpeng Zhao, Shuoshuo Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China China

To improve the quality of self-pierce riveted joints, this paper uses a multi-objective optimisation method that incorporates a quadratic polynomial response surface model and the NSGA-II algorithm to optimise the parameters of the self-pierce riveting process. First, we carry out finite element simulations of the self-pierce riveted joint to determine the main factors affecting the quality of the joint forming through sensitivity analysis, and specify the optimum range of each parameter. Second, we use central composite design experiments to establish a quadratic polynomial response surface model. Third, we optimise the multi-objective model by using the NSGA-II algorithm and obtain the Pareto optimal solution. Finally, we use cross-sectional measurement and mechanical properties experiments to verify the feasibility of optimising the self-pierce riveted joint. The experimental results show that the bottom thickness increases by 24.7%, the undercut amount by 14.5%, and the tensile shear force by 27% compared to the pre-optimisation period. The quality of the riveted joints was significantly improved after optimisation, laying a good foundation for improving the safety of high-speed railway bodies. © 2022, Politechnica University of Bucharest. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

STUDY ON THE CENTERLINE EXTRACTION METHOD OF WELD IMAGE LINE STRUCTURED LIGHT STRIPE

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical Engineering and Computer Science 2022年第1期84卷 21-32页

作者： Zheng, Qingchun Liu, Qipei Zhu, Peihao Ma, Wenpeng Liu, Jingna Li, Xiaoyang Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China China

In practice, using vision measurement technology based on structured light to reconstruct the complex weld is a feasible way for providing the essential parameters for the welding polishing robot and guiding it to grind the weld by force control. In this paper, we represent a method to extract the centerline of structured light stripe in weld image. First, obtains the high-quality light stripe image using an industrial camera outfitted with a filter and preprocessed to isolate the entire structured light stripe from the background image. Second, using the weighted gray centroid method, roughly extract the original stripe center to obtain the initial point of the stripe center. Then, using principal component analysis, find the normal direction of the light stripe and calculate the gray distribution function of the stripe using second-order Taylor expansion along the normal direction to obtain the correct position of the stripe center. Finally, use cubic spline interpolation to create a smooth centerline. The testing results suggest that this method outperforms the Steger algorithm in terms of speed and extraction accuracy when compared to the classic gray centroid method. These works set the foundation for real-time 3D reconstruction of welds. © 2022, Politechnica University of Bucharest. All rights reserved.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Human Activity Recognition Based on a Modified Capsule Network

引用

Mobile Information systems 2023年第1期2023卷

作者： Zhu, Shanying Chen, Wei Liu, Fulong Zhang, Xiaotao Han, Xiupeng Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology Tianjin China

Human activity recognition (HAR) has attracted considerable research attention in the past decade with the development of wearable sensor technology and deep learning algorithms. However, most of the existing HAR methods ignored the spatial relationship of features, which may lead to recognition errors. In this paper, a novel model based on a modified capsule network (MCN) is proposed to accurately recognize various human activities. This novel model is composed of a convolution block and a capsule block, which can achieve end-to-end intelligent recognition. In the meantime, the spatial information among features is preserved through a dynamic routing process. To validate the effectiveness of the model, a human activity dataset is constructed by placing an inertial measurement unit (IMU) on the calf of the volunteers to collect their activity data in daily life, including walking, jogging, upstairs, downstairs, up-ramps, and down-ramps. The recognition accuracy of this novel approach can reach 96.08%, which performs better than the convolutional neural network (CNN) with an accuracy of 91.62%. In addition, it is evaluated on two public datasets named WISDM and UCI-HAR, and the accuracies achieve 98.21% and 95.28%, respectively, which presents higher accuracy than the reported results obtained from benchmark algorithms like CNN. The experimental results show that the proposed model has better activity detection capability and achieves outstanding performance for HAR. © 2023 Shanying Zhu et al.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

The Influence of Microstructural Evolution on Performance Degradation in Solid Oxide Fuel Cells

SSRN

引用

SSRN 2024年

作者： Shao, Yuqing Shen, Junjie Ren, He Zhao, Liwei Xue, Ziyu Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology Tianjin300384 China

The microstructure evolution effects performance degradation of solid oxide fuel cells (SOFCs) under elevated temperatures. The microstructural evolution, including elemental diffusion, phase changes, and Ni agglomeration, is studied via X-ray diffraction (XRD) and scanning electron microscopy energy dispersive spectrometer (SEM-EDS) techniques. The ohmic resistance and polarization impedance, including activation polarization impedance and concentration resistance, causing the performance degradation, are estimated using electrochemical impedance spectroscopy (EIS) and distribution of relaxation time (DRT) techniques. The voltage gradually decreases from 0.9 V, at the beginning of the load, to 0.75 V after 240 h of service. The formation of pores at the (La0.6Sr0.4Co0.2Fe0.8O3-δ) LSCF/(Gd0.1Ce0.9O2-δ) GDC interface and cracks at the (8 mol% Y2O3-stabilized ZrO2) YSZ/NiO-YSZ interface induce the increase in ohmic resistance. The increase in activation polarization resistance is attributed to the formation of the SrZrO3 phase and Gd2(Zr1-xCex)2O7, at the YSZ/GDC interface, and the redistribution and coarsening of Ni. The formation of Co- or Fe-based oxides in the LSCF layer slightly increases the concentration polarization impedance. © 2024, The Authors. All rights reserved.

关键词： Scanning electron microscopy

来源：评论

学校读者我要写书评

暂无评论

The Influence of Hydrogen on the Recrystallization Texture of a Face Centered Cubic Metal

SSRN

引用

SSRN 2024年

作者： Ren, He Shen, Junjie Guo, Xiangru Shao, Yuqing Zhao, Liwei Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology Tianjin300384 China

The evolution of an alloy’s microstructure in a hydrogen atmosphere at high temperatures is one of the important factors contributing to the degradation in the alloy’s strength. The present study aimed to clarify the influence of hydrogen on the recrystallization texture of a face centered cubic (FCC) metal. As a model of FCC metal, commercially pure nickel (Ni) was cold-rolled and then annealed separately in vacuum and hydrogen atmospheres. Subsequently, the recrystallization textures were analyzed using EBSD and XRD. Hydrogen promoted the recrystallization of -oriented deformed grains while hindering the recrystallization of -oriented deformed grains. It increased the content of {011} texture, promoted the decrease of R-Cube texture content, hindered the increase of Cube texture content， and hindered the reduction in contents of Brass, Copper, Goss, and S textures. In addition, it had an insignificant effect on {011} texture contents. Hydrogen demonstrated an anisotropic effect on the dislocation movement and density of grains with different orientations. Specifically, it impeded the dislocation movement within -oriented deformed grains while facilitating the dislocation movement within -oriented deformed grains. As a result, hydrogen induced an increase in dislocation density in -oriented grains and a decrease in dislocation density in -oriented grains. © 2024, The Authors. All rights reserved.

关键词： Hydrogen

来源：评论

学校读者我要写书评

暂无评论

A Study of Soil Modelling Methods Based on Line-Structured Light——Preparing for the Subsoiling Digital Twin

SSRN

引用

SSRN 2024年

作者： Li, Xia You, Birong Wang, Xuhui Zhao, Zhipeng Qi, Tianyu Xu, Jinyou Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China National Demonstration Centre for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology Tianjin300384 China

The virtual model serves as the foundation for constructing a digital twin system. In order to provide technical guidance for the construction of a digital twin system for subsoiling, this study employed the line structured light method for soil model generation. Field experiments and indoor experiments were conducted separately, using the extreme value method, grayscale centroid method, and Steger algorithm to extract the laser centrelines in the experiments. The results show that the extreme value method and grayscale centroid method have almost the same processing time when dealing with two types of images, which are 1.9ms and 18ms respectively. The Steger algorithm has a significant difference in processing time when dealing with indoor and field images, with the processing time being longer for indoor images, approximately 300ms. Regarding memory usage, there is a large difference when the extreme value method processes two sets of images. Therefore, the grayscale centroid method is the most suitable method for centreline extraction in a digital twin system for subsoiling. When performing 3D reconstruction, the camera shooting frequency is positively correlated with the reconstruction effect, while the moving speed is negatively correlated with the reconstruction effect. Of course, the reconstruction effect is also related to the performance of the binocular camera used. In addition, the processing time for each image during reconstruction is within 1ms, indicating that the method of line laser 3D reconstruction can solve the problem of soil modelling in subsoiling digital twin. © 2024, The Authors. All rights reserved.

关键词： Soils

来源：评论

学校读者我要写书评

暂无评论

Logistics Demand Forecasting and Scheduling Optimization Using K-Means Clustering and Deep Q-Network

Logistics Demand Forecasting and Scheduling Optimization Usi...

引用

Electronics, Energy systems and Power Engineering (EESPE), IEEE International Conference on

作者： Kun Liang Hang Zhang School of Management Tianjin University of Technology Tianjin China Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology Tianjin China

ISBN: (数字)9798350389579

ISBN: (纸本)9798350389586

With the rapid development of e-commerce and supply chain management, logistics demand forecasting and scheduling optimization have become key links in improving logistics efficiency and service quality. To meet this challenge, this paper proposes a logistics demand forecasting and scheduling optimization method that combines K-Means clustering with deep Q network (DQN). Cluster analysis is used to reduce data complexity, and deep reinforcement learning is used to achieve intelligent scheduling. First, the background, challenges and research motivation of logistics demand forecasting and scheduling optimization are introduced. Secondly, the research results in related fields are reviewed, and the shortcomings of current research are pointed out. Then, the K-Means clustering algorithm, deep $\mathbf{Q}$ network theory and specific models of logistics demand prediction and scheduling optimization are elaborated. Then, the performance of the proposed method is designed and tested. The experimental results show that the proposed method can significantly improve the accuracy of logistics demand prediction, up to 0.93, optimize scheduling strategies, reduce logistics costs, and improve customer satisfaction.

关键词： Training Accuracy Costs Computational modeling Customer satisfaction Demand forecasting Clustering algorithms Predictive models Scheduling Logistics

来源：评论

学校读者我要写书评

暂无评论

Research on vision detection technology based on photometric calibration

Research on vision detection technology based on photometric...

引用

2021 IEEE International Conference on Computer Science, Electronic Information Engineering and intelligent control Technology, CEI 2021

作者： Sun, Guoqing Zhou, Haibo Li, Chenming Zhao, Yijiao Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control Tianjin300384 China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin300384 China

ISBN: (纸本)9780738146492

The camera is affected by illumination changes and vignetting effect during the shooting process, resulting in the lack of brightness information, which affects the accuracy of target detection. In order to reduce the impact of illumination changes and vignetting effect on image quality, obtain images closer to the real scene, and improve the accuracy of target detection, this paper conducts photometric calibration on the image from two aspects: the calibration of CRF (Camera Response Function) and the compensation function of vignetting effect. This paper first uses the N-degree polynomial model to construct the camera response function, proposes a functional model of vignetting compensation based on the position of the pixel point, and finally combines the first two experimental results and conducts experimental verification on the data set before and after the photometric calibration on different algorithms of target detection. The experimental results show that the application of photometric calibration in the field of machine vision can improve the adaptability of machine vision to illumination changes and vignetting effect to a certain extent. The self-made data set is trained and tested, when IoU is 0.7, the mAP calculated by the test set after photometric calibration is improved by 2.3% compared with the original data set. © 2021 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

PATH OPTIMIZATION FOR DYNAMIC OBSTACLE AVOIDANCE OF PIONEER ROBOT BASED ON DDPG SMART AGENT

引用

UPB Scientific Bulletin, Series D: Mechanical Engineering 2023年第2期85卷 29-42页

作者： Zheng, Qingchun Peng, Zhi Zhu, Peihao Zhao, Yangyang Ma, Wenpeng Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control Tianjin University of Technology Tianjin300384 China China School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China School of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China

To improve the path efficiency for dynamic obstacle avoidance algorithms of Pioneer robots, this paper proposes an approach to create deep deterministic policy gradient (DDPG) smart agents with recurrent neural networks (RNN) to optimize the path strategy. This approach is realized by training RNN with the backpropagation (BP) algorithm to train the agent. First, the SolidWorks model and obstacle avoidance model of the Pioneer robot is established. The LIDAR sensor is used to obtain environmental information. Further, deep reinforcement learning obstacle avoidance algorithm based on RNN is presented. The dynamic obstacle avoidance path of the Pioneer robot is further simulated in two different virtual robot experiment platform (V-REP) scenarios. The simulation results show that the proposed algorithm shortens the training time by 26.3% compared with the DDPG algorithm. Our proposed scheme can improve the path efficiency for dynamic obstacle avoidance of the Pioneer robot. © 2023, Politechnica University of Bucharest. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Research on Robot Optimal Working Space Based on Spiral Theory

Research on Robot Optimal Working Space Based on Spiral Theo...

引用

2022 International Symposium on Robotics, Artificial Intelligence, and Information Engineering, RAIIE 2022

作者： Li, Yu-Fei Ge, Wei-Min Zhang, Zhi-Li Zhao, Xiang-Bin College of Mechanical Engineering TianJin University of Technology TianJin province TianJin300074 China Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin300384 China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology Tianjin300384 China Intelligent Manufacturing College Tianjin Sino-German University of Applied Science Tianjin300350 China

ISBN: (纸本)9781510660137

Because industrial robots have uneven positioning accuracy in the overall working space, they have greatly limited their applications in the fields of high-precision production and *** this status quo, this article focuses on analyzing the optimal working space of industrial robots, and screening and limiting the optimal working scope of the selected industrial robots to ensure that the robot end is at a relatively high position with high positioning *** article selects the collaborative robot AUBO E3 for modeling, analysis and simulation. Calculate the robot based on the Jacques matrix and the number of conditions under the spiral theory, quantitatively depict the exercise performance of the *** excellent working space is visually simulated, and finally uses the API laser tracker to measure the end error of the robot. As a result, the accuracy of the end point in the optimal working space is higher than the endpoint accuracy of the overall work space. © 2022 SPIE.

关键词： Industrial robots

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：