检索结果-内蒙古大学图书馆

Artificial Intelligence, Networking and Information Technology (AINIT), International Seminar on

作者： Qingchun Zheng Zhi Peng Peihao Zhu Ran Zhai Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control Tianjin University of Technology Tianjin China 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

To improve the trajectory optimization efficiency of robot manipulators, this paper proposes a novel approach for trajectory optimization and control of manipulators based on multistage nonlinear model predictive control (msNLMPC). This approach is realized by using a neural state space model as the prediction model of nonlinear model predictive control (NLMPC). The simulation results show that the actual trajectory of the manipulator in our proposed scheme coincides with the desired trajectory. The manipulator achieves the control task of following the optimal trajectory. Our proposed method improves the trajectory optimization efficiency of the robot manipulator.

关键词：

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

Pressure-assisted Silver Sintering Structure Optimization for Power Modules 5

Pressure-assisted Silver Sintering Structure Optimization fo...

引用

5th International Conference on Optoelectronic Science and Materials, ICOSM 2023

作者： Zhang, Hao Xing, Yulong Gao, Lilan Liu, Zheng Tan, Yansong Lu, Guoquan Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control Tianjin University of Technology Tianjin300384 China National Demonstration Center or Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology Tianjin300384 China Tianjin Yixunyuan New Material Technology Co. Ltd. Tianjin300380 China School of Chemical Engineering Tianjin University Tianjin300350 China School of Materials Science and Engineering Virginia Polytechnic Institute and State University BlacksburgVA24061 United States

ISBN: (纸本)9781510674547

As mobile technology evolves from 5G to 6G, the demand for third-generation semiconductors such as SiC with higher power and frequency capabilities is increasing. Silicon Carbide power modules generate significant heat during operation, requiring large-area nano-silver sintering technology to improve module performance and reliability. However, in large-area sintering processes, low exhaust efficiency of solder paste by-products and uneven sintering pressure of the nano-silver paste result in poor sintering quality of the silver layer. This study aims to improve the sintering quality of interconnected silver layers by optimizing the sintering pressure distribution and adding rubber spacers to the sintering structure. ABAQUS was used to quantitatively analyze the effects of pressure methods and gasket material, diameter, and thickness on the stress distribution in the silver layer. Finally, based on the simulation results, an optimized sintering structure was proposed to unify the pressure and reduce the stress concentration in the silver layer, and verified experimentally by sintering tests. Compared with the traditional sintering structure, the application of a 2 mm thick fluoro rubber gasket with the same surface area as the silver layer in the optimized structure reduced the porosity to 2.15% and achieved a more dense sintered silver layer. © 2024 SPIE.

关键词： Finite element method

来源：评论

学校读者我要写书评

暂无评论

Design of Underwater Vehicle for Ship Draft Observation

Design of Underwater Vehicle for Ship Draft Observation

引用

Mechatronics and Robotics engineering (ICMRE), International Conference on

作者： Jingyuan Zhu Meng Han Hongliang Zhang Lan Qi Lianyu Zhao Chenglin Wang 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 Deepinfar Ocean Technology Inc Tianjin China

Underwater Vehicles are very important underwater operation equipment, and a new underwater vehicle is designed in order to realize the measurement of the ship draft. The design is based on the ROV(Remote Operated Vehicle) structure, and the mobile power supply and the upper computer are mounted on the underwater vehicle body, aiming to accomplish the task of disconnecting the underwater vehicle from the cable under complex sea conditions. In this paper, the system communication and power supply scheme design, thruster arrangement, the center of gravity and floating center position design, and 3D model design are completed in turn to obtain a structural design scheme of the underwater vehicle based on the actual engineering background. Subsequently, the strength check of the overall frame was carried out based on ANSYS WORKBENCH, which proved that the material selection and structural design met the reliability requirements. Finally, the hydrodynamic characteristics of the robot were analyzed using ANSYS CFD.

关键词： Weight measurement Underwater cables Solid modeling Three-dimensional displays Power supplies Hydrodynamics Finite element analysis

来源：评论

学校读者我要写书评

暂无评论

Knocking Detection in Gasoline Engines Based on Probability Density Functions: A Mixed Gaussian Distribution Approach

Knocking Detection in Gasoline Engines Based on Probability ...

引用

IEEE Annual Conference on Decision and control

作者： Tatsuya Ibuki Yasuhiro Awai Yoshihiro Sakayanagi Mitsuji Sampei Junichi Kako Department of Mechanical and Control Engineering Tokyo Institute of Technology Tokyo 152-8550 JAPAN Advanced Engine Management System Development Div. Unit Center Toyota Motor Corporation Shizuoka 410-1193 JAPAN

ISBN: (纸本)9781479978878

This paper proposes an engine knocking detection approach based on probability density functions (PDFs). In this work, we suppose that the PDF of knocking intensity distribution can be approximated by a mixture of two Gaussian functions due to normal combustion and abnormal one. We first apply EM (Expectation-Maximization) algorithm to actual engine data to show that the knocking intensity probability distribution can be successfully estimated by the mixed Gaussian distribution. We next try to apply the existing online EM algorithm in view of the actual implementation by an engine control unit. However, since the existing algorithm is built for the estimation of a fixed PDF, the effect of new input data is gradually attenuated and vanishes after long time. We thus newly propose a modified online EM algorithm so that the effect of the new input data is not attenuated. Finally, we perform simulations and an actual engine bench test for the validity of the present approach.

关键词： expectation-maximisation algorithm gasoline engine Gaussian distribution incoming data Probability density function engine pedestal

来源：评论

学校读者我要写书评

暂无评论

Augmented Reality and Quick Response Code Technology in engineering Drawing course

Augmented Reality and Quick Response Code Technology in Engi...

引用

IEEE International Conference on Mechatronics and Automation

作者： Xiaofei Wang Chenfei Chen Zhaotong Li 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 School of Electrical and Electronic Engineering Tianjin University of Technology Tianjin China School of Mechanical Engineering Tianjin University of Technology Tianjin China

ISBN: (数字)9781728164168

ISBN: (纸本)9781728164175

Augmented reality (AR) technology is a cutting technology. It can enhance the perception of reality and provide more information of the real world. AR technology is used in many fields, like medical, industry, and education. In this paper, AR is introduced into engineering drawing course. engineering drawing course is difficult to learn as it is a knowledge that students rarely contact with. To have a close contact with the models and the views, a convenient AR application (AR app) is proposed in the paper. With the help of the AR app, virtual models and real views are combined well. The models can be moved and rotated by touching the screen. Some videos of model assembly and disassembly can be obtained when scanning the quick response code (QR code). Thus, it is convenient for students to use mobile phone to study engineering drawing effectively. The interactive teaching environment enhances students' spatial thinking and cultivates their sense of innovation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Springback property of grain refined pure aluminum by ECAP method

引用

Keikinzoku/Journal of Japan Institute of Light Metals 2006年第12期56卷 728-729页

作者： Sakai, Takashi Takahashi, Ryosuke Furushima, Tsuyoshi Koyama, Jun-Ichi Department of Mechanical Engineering Takamatsu National College of Technology 355 Chokushi Takamatsu-shi Kagawa 761-8058 Japan Department of Mechanic Electrical System Engineering Advanced Course of Takamatsu National College of Technology Takamatsu-shi Kagawa Japan Tokyo Metropolitan University Hachioji-shi Tokyo Japan Amada Co. Ltd. Japan

No abstract available

关键词： Bending ECAP method Grained material Pure aluminum Single crystal Springback

来源：评论

学校读者我要写书评

暂无评论

Elucidating the Rate Limitation of Lithium-Ion Batteries Under Different Charging Conditions Through Polarization Analysis

SSRN

引用

SSRN 2023年

作者： Xie, Wenlong Guo, Peng Gao, Xinlei 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 China Dyson School of Design Engineering Imperial College London London United Kingdom

The charging performance of lithium-ion batteries is significantly affected by the polarization effect, which leads to increased resistance and prolonged charging time. this paper combines experimental testing with numerical simulation to qualitatively and quantitatively investigate the polarization effects under different charging conditions. The results indicate that the proportions of positive and negative polarization to cell polarization are comparable and basically constant with variations in the charging rate. The polarization voltages of different categories within the electrode are positively correlated with the charging rate. At high charging rates, electrochemical polarization accounts for the majority, followed by solid-phase and liquid-phase concentration polarization, while solid-phase and liquid-phase ohmic polarization is relatively negligible. On the other hand, the cell polarization exhibits a non-linear trend with temperature. The lower the temperature, the greater the proportion of negative polarization, while positive polarization is insensitive to temperature. At low temperature charging, the solid-phase concentration polarization of the negative electrode accounts for the majority of electrode polarization, which can be attributed to the larger lithium ion concentration gradient induced by the sluggish diffusion of ions in the active material. In-depth investigation of the polarization effect will provide guidance for achieving more efficient charging under different operating conditions. © 2023, 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

Anomaly Detection of Logistics Packages Based on CNN and Image Recognition Technology

Anomaly Detection of Logistics Packages Based on CNN and Ima...

引用

Data Science and Computer Application (ICDSCA), 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)9798350368239

ISBN: (纸本)9798350368246

To address abnormal situations such as packaging damage, liquid leakage, and item displacement during logistics package transportation, this paper introduces Convolutional Neural Network (CNN) and image recognition technology to achieve real-time anomaly detection and alarm, improving the response speed and accuracy of the logistics system. First, by designing multiple layers of convolution and pooling layers, adding Batch Normalization layers and Dropout layers to prevent overfitting, a CNN deep learning model suitable for logistics package anomaly detection is constructed. Key features are extracted through image preprocessing methods such as normalization and data enhancement to ensure that the model has high recognition adaptability to various abnormal situations such as damage and leakage. Secondly, through data enhancement methods such as rotation, scaling, brightness adjustment, and transfer learning using pre-trained models, the model's adaptability in different lighting, angles, and occlusion conditions is improved. Finally, the model is applied to actual monitoring, and real-time alarms are issued for abnormalities such as damage and leakage, which are then fed back to the system closed-loop management. This method is significantly better than traditional methods in terms of detection accuracy and response speed. Under natural light environment, the model detection accuracy is as high as 98.4%, reducing false positives and false negatives. Combining CNN's anomaly detection technology effectively improves the accuracy and efficiency of logistics monitoring and provides technical support for intelligent logistics management.

关键词： Industries Adaptation models Accuracy Image recognition Data models Real-time systems Convolutional neural networks Anomaly detection Monitoring Logistics

来源：评论

学校读者我要写书评

暂无评论

Fabrication of Micro-OLEDs by Room-temperature Curing Nanocontact-print Lithography Using DLC Molds

引用

MRS Online Proceedings Library (OPL) 2013年第1期1511卷 mrsf12-1511-ee05-03-mrsf12-1511-ee05-03页

作者： Ippei Ishikawa Keisuke Sakurai Shuji Kiyohara Taisuke Okuno Hideto Tanoue Yoshiyuki Suda Hirofumi Takikawa Yoshio Taguchi Yoshinari Sugiyama Yukiko Omata Electric and Control System Engineering Course Faculty of Advanced Engineering Maizuru National College of Technology 234 Shiroya Maizuru Kyoto 625-8511 Japan Department of Electrical and Electronic Information Engineering Toyohashi University of Technology 1-1 Hibarigaoka Tenpaku Toyohashi Aichi 441-8580 Japan Application and Technical Section ELIONIX INC. 3-7-6 Motoyokoyama Hachioji Tokyo 192-0063 Japan

The microfabrication technologiesfor organic light-emitting devices (OLEDs) are essential to the fabrication of the next generation of light-emitting devices. The micro-OLEDs fabricated by room-temperature curing nanoimprint lithography (RTC-NIL) using diamond molds have been investigated. However, light emissions from 10 μm-square-dot OLEDs fabricated by the RTC-NIL method have not been uniform. Therefore, we proposed the fabrication of micro-OLEDs by room-temperature curing nanocontact-print lithography (RTC-NCL) using the diamond-like carbon (DLC) mold. The DLC molds used in RTC-NCL were fabricated by an electron cyclotron resonance (ECR) oxygen ion shower with polysiloxane oxide mask in electron beam (EB) lithography technology. The mold patterns are square and rectangle dots which has 10 µm-width, 10 µm-width and50 µm-length, respectively. The height of the patterns is 500 nm. The DLC molds were used to form the insulating layer of polysiloxane in RTC-NCL. We carried out the RTC-NCL process using the DLC mold under the following optimum conditions: 0.1 MPa-pressure for coating DLC mold with polysiloxane film, 2.1 MPa-pressure for transferring polysiloxane from DLC mold pattern to indium tin oxide (ITO) glass substrate. We deposited N, N'-Diphenyl -N, N'-di (m-tolyl)benzidine (TPD) [40 nm-thickness] as hole transport layer / Tris(8-quinolinolato)aluminum (Alq3) [40 nm-thickness] as electron transport layer / Al [200 nm-thickness] as cathode on ITO glass substrateas anode in this order. We succeeded in formation of the insulating layer with square and rectangle dots which has 10 µm-width,10 µm-width and 50 µm-length, and operation of micro-OLEDs by RTC-NIL using DLC molds.

关键词： ion-beam processing microstructure diamond

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：