检索结果-内蒙古大学图书馆

5th IEEE International Conference on Technology, Informatics, Management, engineering and Environment, TIME-E 2024

作者： Wahid, Muhammad Rizalul Joelianto, Endra Arief Budiman, Bentang Institut Teknologi Bandung Doctoral Program in Engineering Physics Bandung Indonesia Universitas Pendidikan Indonesia Mechatronics and Artificial Intelligence Bandung Indonesia Institut Teknologi Bandung Instrumentation Control and Automation Research Group Bandung Indonesia Institut Teknologi Bandung Faculty of Mechanical and Aerospace Engineering Bandung Indonesia

ISBN: (纸本)9798350364743

Electric vehicles (EV s) boast zero tailpipe emissions, directly improving air quality and lowering greenhouse gas emissions. Despite the promise of EVs for sustainable transportation, their limited range is a key challenge. Regenerative braking is a promising approach for enhancing the driving range. This research proposes a study of Interval Type-2 Fuzzy Logic (IT2FL) control to improve regenerative braking efficiency in an electric trike. Employing IT2FL control for regenerative braking recovers 35.84% of energy, translating to a 91.053 km increase in driving range. The IT2FL method achieved a range of 50 km/kWh, representing a significant 41.7% improvement. Furthermore, utilizing the Nie-Tan Method reducer within the IT2FL framework could extend the range by an additional 2.3 km, resulting in a 3 % increase in energy recovery. These findings demonstrate the effectiveness of IT2FL control in enhancing regenerative braking efficiency for the electric trike. © 2024 IEEE.

关键词： Air quality

来源：评论

学校读者我要写书评

暂无评论

Surface Defects Detection of Cylindrical High-Precision Industrial Parts Based on Deep Learning Algorithms: A Review

引用

Operations Research Forum 2024年第3期5卷 1-71页

作者： Wei, Li Solihin, Mahmud Iwan Saruchi, Sarah ‘Atifah Astuti, Winda Hong, Lim Wei Kit, Ang Chun School of Computer Science and Technology (School of Software) Guangxi University of Science and Technology Guangxi 545006 China Faculty of Engineering Technology and Built Environment UCSI University Kuala Lumpur 56000 Malaysia Faculty of Manufacturing and Mechatronics Engineering Technology Universiti Malaysia Pahang Al-Sultan Abdullah Pahang Pekan 26600 Malaysia Computer Engineering Department Automotive and Robotics Engineering Program BINUS ASO School of Engineering Bina Nusantara University Jakarta Indonesia

High-precision cylindrical parts are critical components across various industries including aerospace, automotive, and manufacturing. Since these parts play a pivotal role in the performance and safety of the systems they are integrated into, they are often subject to stringent quality control measures. Defects on the interior and exterior wall surfaces of these cylindrical parts can severely undermine their function, leading to degraded performance, increased wear, and even catastrophic failures in extreme cases. This article aims to comprehensively summarize the task definition, challenges, mainstream methods, public datasets, evaluation metrics, and other aspects of surface defect detection for high-precision cylindrical parts, in order to help researchers quickly grasp this field. Specifically, the background and characteristics of industrial defect detection are first introduced. Owing to the unique geometric features of cylindrical part surfaces, algorithms and equipment for image data acquisition used in surface defect detection are elaborated in detail. This article presents an extensive overview of state-of-the-art surface defect detection techniques designed for high-precision cylindrical components, all rooted in deep learning. The methods are systematically classified into three main categories: fully supervised, unsupervised, and alternative approaches, based on their data labeling strategies. Additionally, the paper conducts a comprehensive analysis within each category, shedding light on their unique strengths, limitations, and practical use cases. Concluding the discussion, the paper provides insights into future development trends and potential research directions in this field that will lead to manufacturing innovation. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Anomaly detection Computer vision Deep learning Defect detection High-precision cylindrical parts Image processing Optical illumination

来源：评论

学校读者我要写书评

暂无评论

Comparison of Bioinspired MLP Controllers for Mobile Robots Obstacle Following/Avoidance

Comparison of Bioinspired MLP Controllers for Mobile Robots ...

引用

Latin America Congress on Computational Intelligence (LA-CCI)

作者： Matheus de S. Luiz M. A. Pastrana Lukas. A. Da Silva Pamela. R. A. N. Campagnucci Jose Mendoza-Peñaloza Rafael R.L. Benevides Daniel M. Muñoz Faculty of Gama Electronics Engineering Undergraduate Program University of Brasilia Brasilia DF Brazil Department of Mechanical Engineering Mechatronics Graduate Program University of Brasilia Brasilia DF Brazil

ISBN: (数字)9798350374575

ISBN: (纸本)9798350374582

Proportional, integral, and derivative (PID) controllers have been widely adopted for industrial applications. However, these controllers are not very efficient for non-linear systems. Artificial neural networks (ANN) based on the Multilayer Perceptron (MLP) have great potential to replace PID controllers due to their polynomial structure, allowing complex non-linear systems to be controlled. This article introduces the integration of four MLPs as alternatives to a traditional PID controller. These MLPs were trained through four bioinspired algorithms tailored for following tasks in mobile robots. The bioinspired algorithms employed for MLP network training include Particle Swarm Optimization (PSO), Grey Wolf Optimization (GWO), Month-Flame Optimization (MFO), and Artificial Hummingbird Algorithm (AHA). A comparative analysis was conducted between these MLPs and a classic PID controller, focusing on parameters such as overshoot (OS), settling time (ST), and steady-state error for different simulated scenarios.

关键词： Training Process control Artificial neural networks Vectors Stability analysis Steady-state Mobile robots Optimization Videos Testing

来源：评论

学校读者我要写书评

暂无评论

Hardware Implementation of a GMDH Controller for Mobile Robot Obstacle Following/Avoidance

Hardware Implementation of a GMDH Controller for Mobile Robo...

引用

IEEE Latin American Robotics Symposium, LARS

作者： M. A. Pastrana L. H. Oliveira M. S. Santana V. C. Oliveira Jose Mendoza-Peñaloza Daniel M. Muñoz Department of Mechanical Engineering Mechatronics Graduate Program Faculty of Gama Electronics Engineering Undergraduate Program University of Brasilia Brasilia DF Brazil

Proportional, integral, and derivative (PID) controllers have been widely adopted for industrial applications. However, these controllers are not very efficient for non-linear systems. Artificial neural networks (ANN) based on the Group Method of Data Handling (GMDH) have great potential to replace the PID controllers due to their polynomial structure, allowing complex non-linear systems to be controlled. This work presents a hardware architecture of a GMDH network applied to speed control of a mobile robot platform. The proposed GMDH controller was implemented using a 16-bit floating-point arithmetic representation and was mapped on a Zynq7020 device. A hardware-in-the-loop based on the Universal Direct Memory Access methodology was developed to validate the proposed circuits, allowing for performance comparisons between a classical PID and the GMDH controllers for different simulated scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving Control Theory Education Through Face-to-Face Implementation of a Mobile Robotics Methodology

Improving Control Theory Education Through Face-to-Face Impl...

引用

2024 Brazilian Symposium on Robotics (SBR), and 2024 Workshop on Robotics in Education (WRE)

作者： M. A. Pastrana William Humberto Cuéllar Sánchez Jose Mendoza-Peñaloza M. S. Santana Daniel M. Muñoz Department of Mechanical Engineering Mechatronics Graduate Program University of Federal District UDF Brasilia DF Brazil Faculty of Gama Electronics Engineering Undergraduate Program University of Brasilia Brasilia DF Brazil

ISBN: (数字)9798350391084

ISBN: (纸本)9798350391091

Advances in information and communication technologies have significantly transformed engineering education. Virtual laboratories are increasingly adopted to enhance student interaction with control system simulations. The improved visualization and interaction capabilities of modern computers offer a more organic way to teach theoretical foundations. This paper describes the implementation of a methodology for teaching control theory that until now was entirely online in a face-to-face environment at the University of the Federal District in Brasilia, Brazil. This methodology utilizes virtual laboratories with CoppeliaSim, MATLAB, and the EVA mobile robot to teach control theory focused on single-input, single-output (SISO) systems for mobile robot tracking and obstacle avoidance applications. The results of the face-to-face implementation are compared to those of the fully online methodology, revealing that in-person teaching significantly enhances the quality of instruction.

关键词： Visualization mechatronics Educational robots SISO Education Laboratories Software Control theory Mobile robots MATLAB

来源：评论

学校读者我要写书评

暂无评论

Prototype development of VR based personal zone defense practice equipment 4

Prototype development of VR based personal zone defense prac...

引用

4th IEEE Global Conference on Life Sciences and Technologies, LifeTech 2022

作者： Honma, Hiroki Iida, Yoshiaki Okumura, Yasuyuki Fujii, Katsuyuki Umehira, Masahiro Nanzan University Graduate Program of Mechatronics Graduate School of Science and Engineering Nagoya Japan Nanzan University Physical Education Center Nagoya Japan Nanzan University Faculty of Science and Engineering Department of Mechatronics Nagoya Japan Nanzan University Faculty of Science and Engineering Department of Electronics and Communication Technology Nagoya Japan

ISBN: (纸本)9781665419048

In a basketball game, players must act appropriately according to the position and movement of the player. This needs to be learned through team practice. Therefore, if we can build an environment that allows even one person to practice as a team, the efficiency of practice can be greatly improved. It is effective to use virtual reality (VR) technology to realize team practice alone. This paper proposes a VR-based basketball team practice learning system that provides VR environments similar to the actual team practice environments by arranging players in a virtual space. Focusing on zone defense practice, which is said to be difficult to learn even in team practice, we propose a practice system for orthodox 3-2 zone tactics. In addition, because the distance between the player and the surrounding VR player is important for this system, this paper presents the evaluation result of the 3D virtualization accuracy measured by the experiment. © 2022 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Proto-type Development of Vibration-induced Haptic Shoes for Perceiving the Front Obstacle 10

Proto-type Development of Vibration-induced Haptic Shoes for...

引用

10th IEEE Global Conference on Consumer Electronics, GCCE 2021

作者： Nakagawa, Kosuke Okumura, Yasuyuki Fujii, Katsuyuki Umehira, Masahiro Nanzan University Graduate Program of Mechatronics Graduate School of Science And Engineering Nagoya Japan Nanzan University Faculty of Science And Engineering Department of Mechatronics Nagoya Japan

ISBN: (纸本)9781665436762

In this study, we fabricated a device that can detect obstacles before a user and act from the feelings presented to the sole. Specifically, a distance sensor is mounted on a haptic shoe that presents tactile information to the sole, and the haptic shoe notifies the user of obstacles in front of the user. To present the tactile information, we used an amplifier and a vibration actuator based on the TECHTILE toolkit. We fabricated a shoe-shaped device using these components. A pressure sensor was used to detect motion. PureData and Arduino software were linked to process information from the distance sensor. The system uses the sound recorded by a microphone to output information on the feeling of obstacles that prevent the user from walking. To evaluate the performance of the system, we conducted an experiment in which the subject wore the shoes and used them in analyzing the sound output from the shoes. © 2021 IEEE.

关键词： Vibrations Pressure sensors Legged locomotion Actuators Conferences Footwear Software

来源：评论

学校读者我要写书评

暂无评论

Optimising degradation and mechanical performance of additively manufactured biodegradable Fe–Mn scaffolds using design strategies based on triply periodic minimal surfaces

引用

Smart Materials in Medicine 2024年第1期5卷 127-139页

作者： Dargusch, Matthew S. Soro, Nicolas Demir, Ali Gokhan Venezuela, Jeffrey Sun, Qiang Wang, Yuan Abdal-hay, Abdalla Alali, Aya Q. Ivanovski, Saso Previtali, Barbara Kent, Damon School of Mechanical and Mining Engineering The University of Queensland Advanced Engineering Building Bld 49 Staff House Rd St LuciaQLD4072 Australia Department of Mechanical Engineering Politecnico di Milano Via La Masa 1 Milan20156 Italy School of Dentistry The University of Queensland Herston Campus 4072 Australia Department of Engineering Materials and Mechanical Design Faculty of Engineering South Valley University Qena83523 Egypt Faculty of Industry and Energy Technology Mechatronics Technology Program New Cairo Technological University New Cairo - Fifth Settlement Cairo11835 Egypt School of Science Technology and Engineering University of the Sunshine Coast Maroochydore BCQLD4558 Australia

Additively manufactured lattices based on triply periodic minimal surfaces (TPMS) have attracted significant research interest from the medical industry due to their good mechanical and biomorphic properties. However, most studies have focussed on permanent metallic implants, while very little work has been undertaken on manufacturing biodegradable metal lattices. In this study, the mechanical properties and in vitro corrosion of selective laser melted Fe–35%Mn lattices based on gyroid, diamond and Schwarz primitive unit-cells were comprehensively evaluated to investigate the relationships between lattice type and implant performance. The gyroid-based lattices were the most readily processable scaffold design for controllable porosity and matching the CAD design. Mechanical properties were influenced by lattice geometry and pore volume. The Schwarz lattices were stronger and stiffer than other designs with the 42% porosity scaffold exhibiting the highest combination of strength and ductility, while diamond and gyroid based scaffolds had lower strength and stiffness and were more plastically compliant. The corrosion behaviour was strongly influenced by porosity, and moderately influenced by geometry and geometry-porosity interaction. At 60% porosity, the diamond lattice displayed the highest degradation rate due to an inherently high surface area-to-volume ratio. The biodegradable Fe–35Mn porous scaffolds showed a good cytocompatibility to primary human osteoblasts cells. Additive manufacturing of biodegradable Fe–Mn alloys employing TPMS lattice designs is a viable approach to optimise and customise the mechanical properties and degradation response of resorbable implants toward specific clinical applications for hard tissue orthopaedic repair. © 2023 The Authors

关键词： Porosity

来源：评论

学校读者我要写书评

暂无评论

Multi-robot Map Exploration Based on Multiple Rapidly-Exploring Randomized Trees

引用

SN Computer Science 2024年第1期5卷 1-20页

作者： Mukhopadhyay, Shayok Umari, Hassan Koirala, Koshish Electrical & Computer Engineering and Computer Science Department University of New Haven 300 Boston Post Rd West Haven 06516 CT United States Department of Electrical Engineering American University of Sharjah Sharjah P.O. Box 26666 United Arab Emirates Mechatronics Engineering graduate program American University of Sharjah Sharjah P.O. Box 26666 United Arab Emirates

A map is necessary for tasks such as path planning or localization, which are common to mobile robot navigation. However, a map may be unavailable if the environment in which a robot navigates is unknown. Creating a map requires an exploration algorithm. Such algorithms guide robots to boundaries that separate known portions of a map from the unknown portions. Such boundaries are known as frontiers. There are image processing-based algorithms that detect frontiers. The authors’ previous work uses two, i.e., local and global, rapidly exploring random trees (RRTs) for two-dimensional exploration using a single robot. The present work applies the above to a multiagent system with three robots. A market-based strategy is used to allocate exploration tasks to the robots. Results show that the developed exploration strategy successfully explores a map in a reasonable amount of time compared to image processing-based approaches, and also reduces the map exploration cost. This strategy is readily usable for three-dimensional exploration with drones. It is also shown that the usage of a local frontier detector along with a global frontier detector helps reduce exploration time compared to simply using a global frontier detector alone. As an outline to future work, the paper also shows an extension of the proposed approach towards three-dimensional mapping using a single robot. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Exploration Mapping Multi-agent Navigation ROS RRT

来源：评论

学校读者我要写书评

暂无评论

Sub-optimal Perceptron Controller Using WOA Algorithm for Farming Watering Mobile Robot

Sub-optimal Perceptron Controller Using WOA Algorithm for Fa...

引用

Latin America Congress on Computational Intelligence (LA-CCI)

作者： M. A. Pastrana L. H. Oliveira J. Bautista Jesus Pinto-Lopera Jose Mendoza-Peñaloza Daniel M. Muñoz Department of Mechanical Engineering Mechatronics Graduate Program University of Brasilia Brasilia DF Brazil Faculty of Engineering Systems Undergraduate Program Florencia University of the Amazonia Caquetá Colombia Faculty of Gama Electronics Engineering Undergraduate Program University of Brasilia Brasilia DF Brazil

ISBN: (数字)9798350374575

ISBN: (纸本)9798350374582

Artificial neural networks (ANNs) are intricate mathematical models, drawing inspiration from the biological nervous system, and offering intelligence alongside nonparametric capabilities. The efficacy of ANNs heavily relies on their learning process. Heuristic search algorithms have been proposed in literature as reliable options for optimizing neural networks utilizing the Perceptron architecture. This paper presents an suboptimal neural network Perceptron training method employing the Whale Optimization Algorithm for the application of farming watering mobile robots. To achieve this, a fitness function based on system responses such as overshoot, settling Time, and steady-state Error was developed. The sub-optimal Perceptron controller was then implemented using MATLAB, CoppeliaSim software and the EVA robot, resulting in a 66.17% overshoot, a 4.7% steady-state error, and a settling time of 3.05 seconds. Moreover, the sub-optimal Perceptron controller was mapped onto a System on Chip FPGA AMD-Xilinx Zynq 7020, resulting in a hardware resources consumption of 1,870 (3.52%) Lookup table, 2 (0.9%) Digital Signal Processing blocks, 1,019 (0.96%) Flip-Flops and a power consumtion of 0.005 W. Finally, Hardware-in-the-Loop validation was performed using CoppeliaSim, Python, Universal Direct Memory Access, and the EVA robot. The results showed an overshoot of 94.83%, a settling time of 2 seconds, and a steady-state error of 4.5%.

关键词： Software algorithms Signal processing algorithms Software Hardware Whale optimization algorithms Steady-state Mobile robots MATLAB Farming Python

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：