检索结果-内蒙古大学图书馆

A tactile sensor based on photoelasticity

International Journal of Wireless and Mobile Computing 2024年第3期27卷 281-289页

作者： Tao, Bo Huang, Zhili Zhu, Wenqiong Li, Gongfa Key Laboratory of Metallurgical Equipment and Control Technology Ministry of Education Wuhan University of Science and Technology Hubei Wuhan China Research Centre for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Hubei Wuhan China

In the new industrial revolution, the market demands integrated talents in new engineering fields. To meet the requirements of the new era for cultivating high-level talents in integrated disciplines, this paper takes the photoelastic tactile sensor as a carrier, developing a task-driven teaching method oriented to student achievement. Combining society’s need with professional knowledge learning and innovation ability cultivation of students, a practical and innovative platform is built to meet the needs of different stages of integrated graduate education for bachelor’s and master’s degrees. Achieving simultaneous enhancement of learning, scientific research and innovation capabilities, it proposes a multi-dimensional assessment mechanism for integrated graduate education, involving long-term assessment of students at different stages and levels. It implements a strict entry and exit policy and comprehensively improves the quality of talent cultivation. The results show very obvious effects, significantly improving the quality of graduates and promoting student development. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Tactile sensors

来源：评论

学校读者我要写书评

暂无评论

Maximum ladle shell temperature prediction based on GABP neural network

引用

International Journal of Wireless and Mobile Computing 2023年第2期24卷 120-126页

作者： Sun, Ying Huang, Peng Tao, Bo Yun, Juntong Zhao, Guojun Liu, Xin Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education Wuhan University of Science and Technology Wuhan430081 China Research Center for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Wuhan430081 China

intelligent manufacturing is the main development trend of today's manufacturing industry, and talents are the first resource. Through the analysis of the current situation of cultivating talents in mechanical engineering in colleges and universities, it is found that most students of this major have difficulty in involving in knowledge of other fields outside their specialties, and their knowledge structure is relatively single. In response to the above problems, this paper proposes the training mode of multidisciplinary cross-integration of talents in mechanical engineering, which is analysed through the study of maximum temperature prediction of steel ladle shell. The BP neural network based on the improved genetic algorithm is trained on the experimental data samples to achieve the maximum temperature prediction of ladle shell under different thickness combinations of insulation layer, safety layer and working layer. By learning the knowledge of target prediction, students' overall development is promoted. © 2023 Inderscience Enterprises Ltd.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Indoor object segmentation based on YOLACT++

引用

International Journal of Wireless and Mobile Computing 2023年第2期24卷 127-133页

作者： Sun, Ying Zhao, Zichen Tao, Bo Liu, Xin Yun, Juntong Liu, Ying Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education Wuhan University of Science and Technology Hubei Wuhan China Research Centre for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of science and Technology Hubei Wuhan China Precision Manufacturing Research Institute Wuhan University of Science and Technology Hubei Wuhan China

intelligent Manufacturing originates from the research of artificial intelligence, which can not only reduce operating costs, but also improve product quality, and has become the way to cultivate new advantages in forging international competition in manufacturing. With the transformation of traditional manufacturing to intelligent manufacturing, the course of intelligent manufacturing should also be different from the traditional teaching mode, but through the survey, it has been found that the course of intelligent manufacturing still has a single teaching mode, insufficient innovative guidance for students and insufficient combination of theory and practice. In order to solve the issues mentioned above, the Project-Analysis-Evaluation (PAE) structure is proposed in this paper, and it is combined with constructivist theory and analysed through the study of indoor object instance segmentation detection. The YOLACT++ algorithm is pre-trained on SUNRGBD dataset and applied to indoor environment detection in this paper. © 2023 Inderscience Enterprises Ltd.

关键词： Operating costs

来源：评论

学校读者我要写书评

暂无评论

A 7DOF redundant manipulator inverse kinematic solution algorithm based on bald eagle search optimization algorithm

引用

Soft Computing 2024年第23期28卷 13681-13699页

作者： Zhao, Guojun Sun, Ying Jiang, Du Liu, Xin Tao, Bo Jiang, Guozhang Kong, Jianyi Yun, Juntong Liu, Ying Li, Gongfa Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education Wuhan University of Science and Technology Wuhan430081 China Research Center for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Wuhan430081 China Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering Wuhan University of Science and Technology Wuhan430081 China Precision Manufacturing Research Institute Wuhan University of Science and Technology Wuhan430081 China

Solving inverse kinematics (IK) is an excellent challenge for redundant manipulators due to their highly non-linear and complex coupling, which is not amenable to analytical solutions by conventional methods. In this paper, the conventional solution was replaced by the optimization process of a fitness function. The fitness function aims to obtain a set of solutions for the desired position of the end effector (EE). The function is based on forward kinematics;hence, this method can avoid singularities and be suitable for solving redundant manipulators. For solving this optimization problem, the bald eagle search (BES) optimization algorithm was chosen due to its easy principle and excellent performance. BES integrates the advantages of evolutionary and swarm techniques. On the one hand, BES maximizes the advantages offered by swarm intelligence (SI) in terms of searching within the best position in the swarm. On the other hand, BES capitalizes on the capability of evolutionary techniques to explore the search space frequently and avoid the local optimum. In this study, two 7-degree of freedom (DOF) manipulators were used to test the performance of BES. Meanwhile, several evolutionary and SI optimization algorithms were selected to compare with BES. The experimental results demonstrate that the BES optimization algorithm can efficiently and accurately solve the IK problem of 7DOF redundant manipulators. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Inverse kinematics

来源：评论

学校读者我要写书评

暂无评论

Multi-objective optimisation design of cross-shaft based on Kriging response surface optimisation model

引用

International Journal of Wireless and Mobile Computing 2024年第2期26卷 207-214页

作者： Xie, Yuanmin Xiong, Sijie Yun, Juntong Mao, Yanfeng Li, Boao Tang, Xinjie Cao, Yongcheng Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education Wuhan University of Science and Technology Hubei Wuhan China Precision Manufacturing Research Institute Wuhan University of Science and Technology Hubei Wuhan China Research Centre for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Hubei Wuhan China Technology Research and Development Hubei Jingmen Wusan Machinery Equipment Manufacturing Co. Ltd. Hubei Jingmen China

Cross-universal coupling is a key component of the mechanical transmission system and the cross-shaft is the core component of the coupling for torque transmission. Under normal circumstances, cross-shafts are most susceptible to fatigue and deformation, mainly due to the large torques they carry and the irrationality of their structure. Traditional design methods rely on practical experience to determine the key dimensions of the cross-shaft, resulting in long design cycles and low reliability. To address this problem, parametric modelling of the cross-shaft is carried out in this paper and imported into ANSYS Workbench. In addition, static and finite element analyses are carried out to find the weak parts of the cross shaft as the objective function. Finally, sensitivity analysis is carried out using the main structural parameters of the cross-shaft as design variables. Based on the linear correlation matrix and sensitivity graph, the three design variables that have the greatest impact on the objective function, journal height, thickness and body length, are selected. © 2024 Inderscience Enterprises Ltd.

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

SSD object detection algorithm based on knowledge map

引用

International Journal of Wireless and Mobile Computing 2024年第2期27卷 152-160页

作者： Huang, Li Wang, Xiaofeng Lu, Jianhua Hu, Wei Zhang, Changrong College of Computer Science and Technology Wuhan University of Science and Technology Hubei Wuhan China China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Hubei Wuhan China Key Laboratory of Metallurgical Equipment and Control Technology of the Ministry of Education Wuhan University of Science and Technology Hubei Wuhan China Precision Manufacturing Research Institute Research Centre for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Hubei Wuhan China

With the pervasive integration of artificial intelligence into all aspects of human life, talent emerges as a primary resource. Upon analysing the current state of talent training in higher education institutions, issues such as dispersed knowledge points, overlapping content, a singular practice approach and ineffective evaluation have been identified. In response to these challenges, this paper proposes a multidisciplinary and comprehensive practical teaching methodology grounded in the knowledge graph framework. It delves into diverse paths for practical teaching and assessment, including aspects like teaching objectives, problem decomposition, resource integration, implementation methods and performance evaluation. The practical application of the SSD algorithm in researching service robot indoor object detection serves as an illustrative example. Employing the holistic practical teaching approach facilitated by the knowledge graph, this model guides students in acquiring object detection expertise, thereby enhancing their comprehensive development. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Optimised design of cross-shaft parameters based on response surface optimisation model with MOGA

引用

International Journal of Wireless and Mobile Computing 2024年第2期26卷 198-206页

作者： Xiong, Sijie Xie, Yuanmin Zou, Chunlong Mao, Yanfeng Cao, Yongcheng Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education Wuhan University of Science and Technology Hubei Wuhan China Research Centre for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Hubei Wuhan China Precision Manufacturing Research Institute Wuhan University of Science and Technology Hubei Wuhan China Hubei University of Automotive Technology Hubei Shiyan China Technology Research and Development Hubei Jingmen Wusan Machinery Equipment Manufacturing Co. Ltd. Jingmen Hubei China

Cross-shaft is the core component of the cross-type universal coupling and has a vital transmission function. This paper proposes Sparse Grid and the Kriging interpolation to construct a response surface model to solve the problem of long design cycles, low reliability and high susceptibility to cross-shaft fatigue deformation. The critical dimensions of the cross-shaft are used as design variables, and the maximum equivalent force and deformation are reduced as the optimisation objective. Then experimental points are obtained by Sparse Grid Initialisation and then the response surface model is obtained with high accuracy by Kriging interpolation, and finally, the optimised design of the cross-shaft is completed using MOGA in this paper. Compared with the original structural solution, the maximum deformation of the cross-shaft is reduced by 0.4717 mm (22.35%), the maximum equivalent force is reduced by 130.35 Mpa (17.21%) and the mass increased by only 4.17%. © 2024 Inderscience Enterprises Ltd.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Object Detection with Depth Information in Road Scenes 8th

Object Detection with Depth Information in Road Scenes

引用

8th International Conference on Cognitive Systems and Information Processing, ICCSIP 2023

作者： Liu, Ruowang Chen, Xinbo Tao, Bo Key Laboratory of Metallurgical Equipment and Control Technology Ministry of Education Wuhan University of Science and Technology Wuhan China Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering Wuhan University of Science and Technology Wuhan China Precision Manufacturing Institute Wuhan University of Science and Technology Wuhan China Research Center for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Wuhan China

ISBN: (纸本)9789819980208

In recent years, depth estimation has witnessed significant advancements because of the development of deep learning. It's important to note that depth estimation tasks focus solely on predicting the depth of each pixel in an image and do not include object detection or object recognition. Depth estimation is the use of pixel transformations in the image to obtain distance information from each point in the scene to the camera to generate a depth map. Object detection is the process of classifying and localizing an image, given a picture, so as to identify the objects in the picture and determine their location. To overcome this limitation and integrate object detection into the depth estimation process, this paper proposes a novel self-supervised monocular depth estimation algorithm that leverages an attention mechanism. By combining object detection and depth estimation, a real-time multi-task model is designed to enable simultaneous detection and depth estimation of objects. The framework comprises four essential components: an object detection sub-network, a depth estimation sub-network, a lateral sharing unit, and an attention loss. These components work collaboratively to enhance distance estimation accuracy for objects and improve the object detection performance. Throughout experiments, it is evident that the proposed approach can effectively estimate distances to objects and enhances the accuracy of object detection. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

PINN-based neural network for photoelastic stress recovery

PINN-based neural network for photoelastic stress recovery

引用

2023 Advanced Fiber Laser Conference, AFL 2023

作者： Lin, Peng Tao, Bo Wang, Yan Key Laboratory of Metallurgical Equipment and Control Technology Ministry of Education Wuhan University of Science and Technology Wuhan China Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering Wuhan University of Science and Technology Wuhan China Precision Manufacturing Institute Wuhan University of Science and Technology Wuhan China Research Center for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Wuhan China

ISBN: (纸本)9781510677661

Optical measurement techniques have emerged as a promising alternative to traditional invasive methods for stress recovery. Recent developments in artificial intelligence have enabled researchers to harness Physics-Informed Neural Networks (PINNs) for solving complex physics-based problems, including stress field recovery from photoelastic fringes. This paper explores the potential of PINNs for non-invasive stress analysis, presenting a novel methodology that integrates photoelastic fringes and physical stress distribution constraints within a deep learning framework. Our results demonstrate the model's robustness in handling diverse stress patterns and its ability to accurately recover stress distributions even when trained on significantly reduced datasets. A comparative analysis shows our PINN-based model's performance surpassing or closely matching existing methods like PhotoelastNet, underscoring its competitive advantage in stress recovery. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Stress concentration

来源：评论

学校读者我要写书评

暂无评论

Multi-stream fusion network for continuous gesture recognition based on sEMG

引用

International Journal of Wireless and Mobile Computing 2024年第4期26卷 374-383页

作者： Li, Jun Zou, Chunlong Tang, Dalai Sun, Ying Fan, Hanwen Li, Boao Tang, Xinjie Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering Wuhan University of Science and Technology Hubei Wuhan China College of Mechanical Engineering Hubei University of Automotive Technology Hubei Shiyan China Inner Mongolia University of Finance and Economics Hohhot China Research Centre for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Hubei Wuhan China Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education Wuhan University of Science and Technology Hubei Wuhan China

Dynamic gesture recognition is an essential step in human-computer interaction. However, dynamic gesture recognition based on Surface Electromyography (sEMG) signals faces issues such as incomplete feature extraction and incomplete recognition of temporal information between continuous gestures. Therefore, this paper proposes a multi-stream fusion network (MSK-LCNN) for dynamic gesture recognition to improve accuracy. We combine CNN and LSTM models into a unified framework which extracts spatio-temporal information both globally and in depth, and combines feature fusion to retain essential information. This framework uses an attention mechanism (SKNet) to learn more intricate feature information. The gesture recognition accuracy of this method on our data set is 95.23%, and on the NinaPro DB1 data set, it is 91.45%, which outperforms other similar networks in recent years. Applying this algorithm to prosthetic hand control has achieved flexible and stable control of the prosthetic hand. © 2024 Inderscience Enterprises Ltd.

关键词： Gesture recognition

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

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

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：