检索结果-内蒙古大学图书馆

9th International Conference on Business and Industrial Research, ICBIR 2024

作者： Sengaphone, Phongsavanh De Leon, Juan Miguel Augusto, Gerardo L. Gonzaga, Jeremias A. Chua, Joseph Aldrin Lim, Laurence A. Gan Concepcion, Ronnie Bandala, Argel A. Naguib, Raouf Mechanical Engineering Dept Manila Philippines Manufacturing Engineering and Management Dept Manila Philippines Electronics and Communications Engineering Dept Manila Philippines Mathematics Computer Science and Engineering Dept Liverpool United Kingdom

ISBN: (纸本)9798350383010

This study presents an innovative implementation of the Single Shot Multibox Detector (SSD) algorithm for real-time object detection on the Raspberry Pi 4. It harnesses the synergies of Python programming, the OpenCV computer vision library, and the SSD algorithm's adaptability. Python, chosen for its versatility, is the programming language, while OpenCV forms the backbone for implementing the finely tuned SSD algorithm. The resulting modular script, designed for real-time object detection, incorporates optimization techniques such as frame skipping and region of interest cropping to enhance Raspberry Pi 4 performance. The system demonstrates promising results, showcasing accurate and responsive object detection in resource-constrained environments. The Raspberry Pi 4's versatility makes it the solution for diverse edge computing applications, including surveillance, robotics, and intelligent environments. Computational constraints prompted the adoption of optimizations, while identified challenges illuminate future research directions exploring advanced algorithms and considering more potent hardware variants. This study contributes significantly to the intersection of computer vision and edge computing, underscoring the successful implementation of the SSD algorithm on the Raspberry Pi 4 and encapsulating technical achievements, practical implications, and a roadmap for future advancements in real-time object detection. © 2024 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Process parametric optimization of spark plasma sintered Ni–Cr–ZrO2 composites using response surface methodology (RSM)

引用

International Journal of Lightweight Materials and Manufacture 2024年第1期7卷 14-24页

作者： Oketola, Adeola Jamiru, Tamba Ogunbiyi, Olugbenga Rominiyi, Azeez Lawan Smith, Salifu Adedayo, Ojo David Department of Mechanical and Mechatronics Engineering Tshwane University of Technology Pretoria South Africa Department of Mechanical and Industrial Engineering University of Johannesburg Doornfontein Campus Johannesburg2028 South Africa Centre for Nanomechanics and Tribocorrosion School of Mining Metallurgy and Chemical Engineering University of Johannesburg South Africa Department of Computer Science Osun State Polytechnic Osun State Iree Nigeria

Materials properties are highly dependent on the processing parameters and technique used during sintering. The effect of Spark Plasma sintering process parameters (pressure and temperature) on the hardness and relative density of Ni–20Cr–5ZrO2 composite was investigated. Response Surface Methodology (RSM) from the design of experiment (DOE) technique was successfully employed for the experimental design, and statistical analysis was conducted on the obtained experimental results. The microstructural analysis of the sintered composite showed the presence of solid solution phases of Ni and Cr, which were confirmed by the XRD results as (Cr,Ni) alongside unreacted ZrO2 particles at sintering temperatures of 950 °C and 1000 °C. The validity of the model developed with the impact of each variable and their corresponding interaction on the responses was performed using analysis of variance (ANOVA). The relative density and hardness were the two responses considered. The actual values (experiment data) and expected values (simulated data) were subjected to statistical analysis, to develop a predictive model that synchronizes density and hardness as distinct process parameters, with material hardness and relative density serving as the responses of the specified experiment. For the responses, quantitative models were created, and 10 experimental runs were processed to ascertain the desirability of the responses. The SPS processing parameters considered the most desirable were 1000 °C sintering temperature and 50 MPa pressure. The hardness property obtained under this condition is 433.23 HV with a relative density of 98.15%. © 2023 The Authors

关键词： Design of experiments

来源：评论

学校读者我要写书评

暂无评论

IoT-Enhanced Smart Carry to Prevent Spinal Cord Injury by Weight Monitoring

IoT-Enhanced Smart Carry to Prevent Spinal Cord Injury by We...

引用

2023 International Conference on Recent Advances in science and engineering Technology, ICRASET 2023

作者： Varshitha, D.N. Shreya, B.S. Nidhi Shree, S.P. Vinutha, D.C. Gourav, R. Chetan, P. Mysuru India Vidyavardhaka College of Engineering Computer Science Engineering Department Mysuru India Vidyavardhaka College of Engineering Mechanical Engineering Department Mysuru India

ISBN: (纸本)9798350306927

The necessity for students to carry heavy backpacks, laden with books and study materials, is prevalent in numerous educational institutions worldwide, particularly in remote areas where walking long distances is common. However, this practice poses significant health risks, leading to issues like improper posture, neck, shoulder, and back strain, and potentially severe spinal damage. To address these concerns, our study proposes an IoT-based solution. Utilizing components such as Arduino 101 processing board, a Bluetooth module, accelerometers, force-sensitive resistors, backpacks, and a mobile application, our solution aims to alert students when their backpack weight exceeds a predetermined threshold. This paper discusses the methodology, results, and relevant literature associated with our proposed solution. © 2023 IEEE.

关键词： Accelerometers

来源：评论

学校读者我要写书评

暂无评论

A Variable Gain Discrete Time Sliding Mode Observer for MMC Capacitor Voltage Estimation 7

A Variable Gain Discrete Time Sliding Mode Observer for MMC ...

引用

7th IEEE International Electrical and Energy Conference, CIEEC 2024

作者： Lei, Yao Tianhao, Li Xinyu, Zhou Xuanang, Dong Yufei, Zhang College of Mechanical Engineering University of Shanghai for Science and Technology China School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology China College of Information and Electrical Engineering China Agricultural University China

ISBN: (纸本)9798350359558

Modular Multilevel Converter (MMC) is one of the main development directions in the future medium and low voltage DC transmission and distribution field. In engineering, capacitive voltage sensors are usually configured for all submodules to ensure high reliability measurement, but this makes the hardware structure more complex. This paper proposes a control algorithm for online adjustment of observer gain based on discrete-time sliding mode observer (DTSMO). A weighted error judgment energy function is defined and three modes are distinguished. A transition mode is introduced between the approaching mode and sliding mode, and the gain within each mode is adjusted online according to the size of each component error function. This algorithm suppresses the chattering of traditional DTSMO during parameter changes and reduces the voltage error of each observed SM, this observer can eliminate all capacitive voltage sensors within a single bridge arm, and is designed based on the consideration of uncertain parameters outside of MMC. Its stability and convergence have been mathematically proven. Finally, simulation and experimental results of hardware prototypes has verified that the proposed VDTSMO observer has good steady-state and transient performance. © 2024 IEEE.

关键词： Bridges

来源：评论

学校读者我要写书评

暂无评论

Cross-Modal Hyperbolic Subspace Fault Diagnosis 2

Cross-Modal Hyperbolic Subspace Fault Diagnosis

引用

2nd IEEE International Conference on Image Processing and computer Applications, ICIPCA 2024

作者： Su, Shuzhi Xu, Mengjie Chen, Jian Zhu, Yanmin School of Computer Science and Engineering Anhui University of Science & Technology Anhui Huainan232001 China School of Mechanical and Electrical Engineering Anhui University of Science & Technology Anhui Huainan232001 China

ISBN: (纸本)9798350360240

Fault diagnosis is difficult to determine intrinsic locality relationships of multi-modal fault data. Aiming at the issue, we propose a novel cross-modal hyperbolic subspace fault diagnosis method. In the method, we construct a cross-modal hyperbolic subspace learning model by integrating local correlation theory and hyperbolic space learning, and the model can solve the local distortion of the Euclidean space manifolds. Besides, we derive analytical solutions of the model by means of Lagrange multiplier, and the cross-modal fault features with good class separability can be obtained by space projection. Experiments on the Paderborn dataset shows the effectiveness of our method in cross-modal fault diagnosis. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Based Prediction of Machining Characteristics of Super Alloy in EDM Using Green Synthesized Nano Copper Oxide Dispersed Bio Dielectric Fluid 1st

A Machine Learning Based Prediction of Machining Characteris...

引用

1st International Conference on Advanced Materials Manufacturing and Structures, ICAMMS 2024

作者： Baskar, S. Pragadish, N. Shanmugapriya, P. Perumal, S. Vishvanath Department of Mechanical Engineering Rajalakshmi Engineering College Thandalam Tamilnadu Chennai602105 India Department of Mechanical Engineering Rajalakshmi Institute of Technology Tamilnadu Chennai600124 India Computer Science and Business Systems Rajalakshmi Engineering College Thandalam Chennai602105 India Department of Mechanical Engineering S.A. Engineering College Tamilnadu Chennai600077 India

ISBN: (纸本)9783031725265

This present study describes the various machine learning techniques such as artificial neural network (ANN), and support vector machine (SVM) are used to predict and genetic algorithm (GA) is used to optimize the material removal rate (MRR) and surface roughness (SR) of Ti6Al4V in electrical discharge machining (EDM) by using nano copper oxide dispersed bio dielectric fluid. MRR and SR were estimated during EDM under the various operating parameters such as discharge voltage, current and discharge time. In this study, an optimal ANN architecture has been determined as 3-10-10-2 and SVM factors were altered by using grid search method. The predicted R-value of SVM is 0.9999 and the minimum mean absolute percentage error for MRR is 0.0085% and SR is 0.0564%. In addition to that, GA optimization has been employed by using objective function developed from Box-Behnken design and enhanced 6.41% and 16.94% in MRR and SR respectively. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Gravity-Based Kinetostatic Modeling of Parallel Manipulators Using Screw Theory

引用

Chinese Journal of mechanical engineering 2023年第6期36卷 73-86页

作者： Chao Yang Fengli Huang Wei Ye Qiaohong Chen College of Mechanical and Electrical Engineering Jiaxing UniversityJiaxing 314001China National and Local Joint Engineering Research Center of Reliability Analysis and Testing for Mechanical and Electrical Products Zhejiang Sci-Tech UniversityHangzhou 310018China School of Computer Science and Technology Zhejiang Sci-Tech UniversityHangzhou 310018China

The pose accuracy of parallel manipulators(PMs)is a key index to measure their *** the grav-ity-based kinetostatic model of a parallel robot provides an important basis for its error composition and accuracy *** this paper,a kinetostatic modeling approach that takes real gravity distribution into consideration is proposed to analyze the influence of gravity on the infinitesimal twist and actuator forces of ***,the duality of the twist screw and constraint wrenches are used to derive the gravity-attached constraint wrenches independent of the external load and the limb stiffness matrix corresponding to the kinematics-based constraint ***-ond,the gravity model of the mechanism is established based on the screw theory and the principle of virtual ***,the analytical formulas of the infinitesimal twist and the actuator force of PMs are obtained,and the influences of the external load,platform gravity,and rod gravity on the stiffness of the mechanism are *** non-overconstrained 3RPS and overconstrained 2PRU-UPR PMs are taken as examples to verify the proposed *** research proposes a methodology to analyze the infinitesimal deformation of the mechanism under the influence of gravity.

关键词： Parallel manipulator Kinetostatic model Gravity Screw theory

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Parallel Strategy for Isogeometric Topology Optimization via CPU/GPU Heterogeneous Computing

引用

computer Modeling in engineering & sciences 2024年第2期138卷 1103-1137页

作者： Zhaohui Xia Baichuan Gao Chen Yu Haotian Han Haobo Zhang Shuting Wang The State Key Lab of Digital Manufacturing Equipment and Technology Huazhong University of Science and TechnologyWuhan430074China School of Mathematics and Computer Science Wuhan Polytechnic UniversityWuhan430048China School of Mechanical Science and Engineering Huazhong University of Science and TechnologyWuhan430074China

This paper aims to solve large-scale and complex isogeometric topology optimization problems that consumesignificant computational resources. A novel isogeometric topology optimization method with a hybrid parallelstrategy of CPU/GPU is proposed, while the hybrid parallel strategies for stiffness matrix assembly, equationsolving, sensitivity analysis, and design variable update are discussed in detail. To ensure the high efficiency ofCPU/GPU computing, a workload balancing strategy is presented for optimally distributing the workload betweenCPU and GPU. To illustrate the advantages of the proposedmethod, three benchmark examples are tested to verifythe hybrid parallel strategy in this paper. The results show that the efficiency of the hybrid method is faster thanserial CPU and parallel GPU, while the speedups can be up to two orders of magnitude.

关键词： Topology optimization high-efficiency isogeometric analysis CPU/GPU parallel computing hybrid OpenMPCUDA

来源：评论

学校读者我要写书评

暂无评论

NUMERICAL INVESTIGATION OF NONLINEAR INTERACTION OF GUIDED-WAVE MIXING AND MICRO-CRACKS IN PIPES 18

NUMERICAL INVESTIGATION OF NONLINEAR INTERACTION OF GUIDED-W...

引用

18th Symposium on Piezoelectricity, Acoustic Waves, and Device Applications, SPAWDA 2024

作者： Tan, Miaohong Sun, Maoxun Liu, Hongye Chen, Xiaorong School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China School of Mechanical Engineering University of Shanghai for Science and Technology Shanghai200093 China

ISBN: (纸本)9798331523732

Pipes are widely used in various industries but are subject to plastic deformation and corrosion, during which microcracks may appear. Ultrasonic guided wave mixing has gained attention due to its high sensitivity. This study employs phase inversion and two-dimensional Fourier transform to investigate the nonlinear interaction between counter-propagating guided waves and microcracks. The generated sum-frequency components and difference-frequency components contain multiple flexural modes and propagate toward both ends of the pipeline. The generated sum-frequency components and difference-frequency components are used to locate the microcracks. The circumferential location of the microcracks is determined by polar diagrams (i.e., the amplitudes of difference-frequency or sum-frequency components and angles), while the axial location is determined by the relationship between the amplitudes of difference-frequency components or sum-frequency components and distance. © 2024 IEEE.

关键词： Pipeline corrosion

来源：评论

学校读者我要写书评

暂无评论

Multi-robot Task Allocation in E-Commerce Warehouses: A Comparative Analysis of Distance Minimization and Priority-Based Approaches 21st

Multi-robot Task Allocation in E-Commerce Warehouses: A Comp...

引用

21st ISME International conference on Advances in mechanical engineering, ISME 2023

作者： Singhal, Rahul Goyal, Pranjay Agarwal, Shreya Makkar, Mohit Kumar, Pushpendra Department of Mechanical-Mechatronics Engineering LNMIIT Rajasthan Jaipur302031 India Department of Computer Science and Engineering LNMIIT Rajasthan Jaipur302031 India Department of Mechanical Engineering Graphic Era University Uttarakhand Dehradun248002 India

ISBN: (纸本)9789819736508

This paper presents a methodology for warehouse management with multiple robots for the efficient picking and dropping of consignments. Task allocation is a critical challenge in this process, as it requires determining a collision-free path for all robots based on warehouse management preferences. Two task allocation preferences are considered: (1) minimizing the total distance traveled by all robots to reduce power consumption and improve overall efficiency and (2) prioritizing task allocation by assigning tasks to the nearest available robot for faster delivery. The proposed approach uses the A* algorithm to determine the shortest path for each robot and evaluates the overall lower cost with the Kuhn-Munkres algorithm. Simulation results show the effectiveness of the methodology in achieving efficient task allocation and reducing the overall distance traveled. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Multipurpose 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：