检索结果-内蒙古大学图书馆

5th IEEE International Conference on Artificial Intelligence in engineering and Technology, IICAIET 2023

作者： Wei, Longxin Lim, Kit Guan Tan, Min Keng Liau, Chung Fan Wang, Tianlei Kin Teo, Kenneth Tze Universiti Malaysia Sabah Modelling Simulation & Computing Laboratory Faculty of Engineering Kota Kinabalu Malaysia Fujian Polytechnic of Information Technology Faculty of the Internet of Things and Artificial Intelligence Fuzhou China Wuyi University Faculty of Intelligent Manufacturing Jiangmen China

ISBN: (纸本)9798350304152

The application of mobile robot's path planning and navigation in known map scenarios has been well-established. However, with the absence of a known map, the challenge lies in how a robot can effectively navigate through an unfamiliar environment and generate a sensible path towards its destination. This paper delves into the path planning quandary that mobile robot encountered in unknown environments. It employs a deep reinforcement learning (DRL) algorithm within a simulated environment, where the robot explores its objective. Additionally, an enhanced reward selection strategy is introduced through a performance-based comparison. This strategy tackles issues such as robot freezing and high collision rates during the exploration of uncharted territory. The outcome of this study is an enhancement in search performance and learning efficiency within path planning. The integration of this algorithm into the Robot Operating System (ROS) robot simulation platform, coupled with testing within the Gazebo simulation environment, demonstrates that the proposed strategy effectively diminishes obstacle collisions and boosts the success rate of reaching the intended destination. © 2023 IEEE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

AloT-Driven Machine Learning for Anomaly Detection in Structural Health Monitoring

AloT-Driven Machine Learning for Anomaly Detection in Struct...

引用

IEEE International Conference on Artificial Intelligence in engineering and Technology (IICAIET)

作者： Lorita Angeline Kit Guan Lim Min Keng Tan Muhd. Nur Afnan Uda Joaquim Abel Jenarun Kenneth Tze Kin Teo Modelling Simulation & Computing Laboratory Faculty of Engineering Universiti Malaysia Sabah Kota Kinabalu Malaysia Faculty of Engineering Universiti Malaysia Sabah Kota Kinabalu Malaysia

ISBN: (数字)9798350389692

ISBN: (纸本)9798350389708

Structural health monitoring (SHM) is crucial for real-time assessment of structures to preemptively detect anomalies that may lead to failures. This study explores the integration of Artificial Intelligence of Things (AIoT) principles to enhance anomaly detection using acceleration and gyroscopic sensor data. The study involved setting up hardware comprising acceleration and gyroscopic sensors, integrated with a web server for real-time data monitoring. Issues with the raw dataset, including noise and variability, were addressed through preprocessing techniques. Four machine learning models, Support Vector Machine (SVM), Random Forest, Gradient Boosting, and Neural Network were evaluated on preprocessed data, focusing on recall as critical for anomaly detection in SHM. Models trained on reduced datasets showed varied performance compared to those using large, raw datasets, which, while computationally intensive, exhibited similar performance. SMOTE significantly improved recall, achieving 93.94% in Random Forest after correcting class imbalance and reducing dataset size. The findings underscore the potential of AIoT-driven machine learning approaches, to significantly enhance SHM modelling. By leveraging these technologies, infrastructure management can be fortified with more reliable anomaly detection capabilities, ensuring heightened safety and resilience in the AIoT era.

关键词： Support vector machines Computational modeling Focusing Real-time systems Web servers Safety Internet of Things Anomaly detection Monitoring Random forests

来源：评论

学校读者我要写书评

暂无评论

Dynamic Analysis and Performance Evaluation of Inerter Fractional Nonlinear Quasi-Zero Stiffness Isolator on a Multi-Span Bridge Under Moving Load

SSRN

引用

SSRN 2024年

作者： Nguebem, L.H. Dongmo Mba Feulefack, S.C. Ngounou, A.M. Nana Nbendjo, Blaise Romeo Laboratory of Modelling and Simulation in Engineering Biomimetics and Prototypes Faculty of Science University of Yaounde I P.O. Box 812 Yaounde Cameroon

In this paper we propose a new vibration isolator system, which combines the advantagesof a quasi-zero stiffness (QZS) isolator, a damper exhibiting fractional propertiesand an inerter, to reduce the vibrations of a multi-span continuous beam bridge excitedby moving loads. The inerter produces a ﬁctitious mass ampliﬁcation effect toimprove the controller performance and the fractional order takes into account the previousstate of the viscoelastic material. After formulating the dynamics equation usingbeam theory, the amplitude response is determined analytically using the averagingmethod. The results obtained from the analytical study are validated using the directnumerical simulation method (Newton-Leipnik method). By comparing the isolationperformance of the FQZS (fractional quasi-zero stiffness) isolator and the IFQZS (inerterfractional quasi-zero stiffness) isolator, it is shown that the addition of inertancecan signiﬁcantly suppress the tendency of the curve to slope to the right, allowing us tohave a wider isolation frequency range on force transmissibility while improving theeciency of the isolator. One also shows that increasing the fractional parameter contributesto a decrease in the vibration amplitude of the structure, the amplitude of theforce transmitted and the area in which unstable solutions appear. However, beyond acertain value of the fractional parameter, we observe an increase in the latter. In orderto further extend the study, bifurcation diagram, phase portrait, time history and powerspectral density are explored. © 2024, The Authors. All rights reserved.

关键词： Stiffness

来源：评论

学校读者我要写书评

暂无评论

Numerical study of effects of hydrogen addition on methane combustion behaviors

引用

Journal of Iron and Steel Research International 2023年第11期30卷 2173-2185页

作者： Dian-yu E Ling-yi Weng Guang-wu Tang Jing Li Guang-chao Wei Jia-xin Cui Jiangxi Provincial Key Laboratory for Simulation and Modelling of Particulate Systems Jiangxi University of Science and TechnologyNanchang330013JiangxiChina International Institute for Innovation Jiangxi University of Science and TechnologyNanchang330013JiangxiChina Shenzhen Smoore Technology Limited Shenzhen518102GuangdongChina ARC Research Hub for Computational Particle Technology Department of Chemical and Biological EngineeringMonash UniversityClaytonVIC3800Australia School of Transportation and Vehicle Engineering Shandong University of TechnologyZibo255000ShandongChina

The methane combustion with hydrogen addition can effectively reduce carbon emissions in the iron and steel making industry,while the combustion mechanism is still poorly *** oxy-fuel combustion of methane with hydrogen addition in a 0.8 MW oxy-natural gas combustion experimental furnace was numerically studied to investigate six different combustion *** results show that the 28-step chemical reaction mechanism is the optimal recommendation for the simulation balancing the numerical accuracy and computational *** the hydrogen enrichment increases in fuel,the highest flame temperature ***,the chemical reaction accelerates with enlarging the peak of the highest flame temperature and intermediate OH *** the hydrogen enrichment reaches 75 vol.%,the flame front is the farthest,and the flame high-temperature zone occupies the largest proportion corresponding to the most vigorous chemical reactions in the same oxygen supply.

关键词： Oxy-fuel combustion Hydrogen Combustion mechanism Flame temperature simulation Modeling

来源：评论

学校读者我要写书评

暂无评论

Adaptive Exponential Feeding Control for a Fedbatch Yeast Fermentation Process Using Reinforcement Learning

Adaptive Exponential Feeding Control for a Fedbatch Yeast Fe...

引用

IEEE International Conference on Artificial Intelligence in engineering and Technology (IICAIET)

作者： Khairul Aznizam Sodiwal Wan Ying Chai Min Keng Tan Kenneth Tze Kin Teo Heng Jin Tham Chemical Engineering Programme Faculty of Engineering Universiti Malaysia Sabah Kota Kinabalu Malaysia Modelling Simulation & Computing Laboratory Faculty of Engineering Universiti Malaysia Sabah Kota Kinabalu Malaysia

ISBN: (数字)9798350389692

ISBN: (纸本)9798350389708

The fermentation process is complex and nonlinear because the growth pattern of microorganisms is sensitive to environmental conditions. Exponential feeding (EF) is a common and simple control strategy for regulating substrate feed flow rates using a pre-determined calculation based on growth kinetics. However, this method does not adapt to changes in the fermentation process. Reinforcement Learning (RL) is a subset of Artificial Intelligence (AI) that focuses on teaching optimal behaviors through interaction with an environment using rewards or penalties. This work explores an Adaptive Exponential Feeding (AEF) control using RL to determine the gain value of the feeding rate, aimed at maximizing yeast concentration and minimizing the by-product formation in a fed-batch baker's yeast fermentation. The kinetic and dynamic behavior of the fermentation process was modeled and simulated using MATLAB. The AEF approach uses an RL agent to optimize the feeding rate by interacting with the fermentation environment and selecting actions based on yeast concentration, glucose levels, and ethanol changes. The gain value ranges from 0 to 2.5 with a 0.1 interval. After iterations, the optimal policy is obtained. simulations with four different initial yeast and substrate concentrations showed that AEF significantly improved the fermentation performance, yielding a higher yeast concentration of 64.86 g/L compared to 44.68 g/L with EF, a 45.17 % increase, and reducing ethanol formation by 0.15 g/L. This adaptive approach demonstrates potential for enhanced efficiency and productivity in industrial fermentation processes.

关键词： Productivity Adaptation models Ethanol Reinforcement learning Real-time systems Kinetic theory Fermentation Artificial intelligence Substrates Resilience

来源：评论

学校读者我要写书评

暂无评论

Effect of Cooling Channel Structure on Permanent Magnet Synchronous Motor

Effect of Cooling Channel Structure on Permanent Magnet Sync...

引用

IEEE International Conference on Artificial Intelligence in engineering and Technology (IICAIET)

作者： Zhencai Huang Hui Chen Kit Guan Lim Min Keng Tan Bih Lii Chua Kenneth Tze Kin Teo Modelling Simulation & Computing Laboratory Faculty of Engineering Universiti Malaysia Sabah Kota Kinabalu Malaysia School of Automotive Engineering Liuzhou Polytechnic University Liu Zhou China

ISBN: (数字)9798350389692

ISBN: (纸本)9798350389708

Taking the 135kW magnet synchronous motor as the research object, the CFD simulation was used to analyze the influence of spiral-type runner, single-channel circumferential Z-type runner, and axial Z-type runner on the heat dissipation performance of the motor. The maximum temperature of the inner wall of the shell is 358.93K, compared with the single-channel circumferential Z-type runner and axial Z-type runner decreased by 1.69K, 10.65K and 46.47K, respectively. The velocity uniformity and pressure loss of the helical runner is optimal, and the coefficient of velocity uniformity and the difference between import and export pressure are 0.948 and 14.78kpa, respectively; the runner structure of the PM synchronous motor can be preferred to consider the use of the helical runner form.

关键词： Heating systems Resistance Spirals Fluids Cooling Synchronous motors Permanent magnet motors Magnetic analysis Eddy currents Periodic structures

来源：评论

学校读者我要写书评

暂无评论

Impact of Helical Channel Number on Synchronous Motor Cooling Performance

Impact of Helical Channel Number on Synchronous Motor Coolin...

引用

IEEE International Conference on Artificial Intelligence in engineering and Technology (IICAIET)

作者： Xiang Lei Meng Hui Chen Min Keng Tan Kit Guan Lim Bih Lii Chua Kenneth Tze Kin Te Modelling Simulation & Computing Laboratory Faculty of Engineering Universiti Malaysia Sabah Kota Kinabalu Malaysia School of Automotive Engineering Liuzhou Polytechnic University Liu Zhou China

ISBN: (数字)9798350389692

ISBN: (纸本)9798350389708

In order to deeply explore the specific influence of the number of helical channels on the cooling performance of a motor, we carefully constructed a three-dimensional fluid-solid coupling calculation model of the flow channel with the help of CFD simulation technology. For the helical flow channels of the 135-k water-cooled permanent magnet synchronous motor shell, we conducted detailed numerical simulation calculations of the temperature field, velocity field, and pressure field. The results show that the number of helical channels has a direct impact on the cooling performance of the motor. Specifically, when the number of channels increases from 3 to 7, the maximum temperature on the inner wall of the shell decreases significantly by 94.41-k, and the velocity uniformity coefficient also increases by 0.05. However, this change also leads to an increase in the flow resistance within the channels, resulting in an increase in the pressure difference between the inlet and outlet of the channels by 4.73-kpa. These findings provide powerful data support for us to further optimize motor design and improve cooling performance.

关键词： Resistance Technological innovation Solid modeling Cooling Predictive models Motors Synchronous motors Robustness Vehicle dynamics Sustainable development

来源：评论

学校读者我要写书评

暂无评论

Yield Optimization for Exothermic Batch Process Using Particle Swarm Optimization

Yield Optimization for Exothermic Batch Process Using Partic...

引用

IEEE International Conference on Artificial Intelligence in engineering and Technology (IICAIET)

作者： Min Keng Tan Matthew Laurentius Bansing Huiyi Xu Helen Sin Ee Chuo Heng Jin Tham Kenneth Tze Kin Teo Modelling Simulation & Computing Laboratory Faculty of Engineering Universiti Malaysia Sabah Kota Kinabalu Malaysia School of Marine Science and Engineering Hainan Tropical Ocean University Hainan China

ISBN: (数字)9798350389692

ISBN: (纸本)9798350389708

Modern advancements in optimizing processes have been explored by various researchers, particularly for exothermic batch processes, which are prolific in the chemical and pharmaceutical industries. This paper proposes using artificial intelligence, specifically particle swarm optimization (PSO), to enhance these exothermic batch processes. Given that most exothermic batch processes utilize generic model control (GMC), the PSO algorithm will primarily focus on optimizing the control of the GMC within the process. The precise control of the controllers will aim to maintain the reactor temperature during the processes, ensuring stability and efficiency. This approach leverages AI to improve process performance, highlighting the potential of PSO in industrial applications. The proposed algorithm is shown to be able to produce a result of an increase of 4.5% of production of the desired product, while decreasing by-product production of 97%. The time it takes for the production of the desired product is also improved by 11.8%. This shows an efficiency increase of the entire exothermic batch processes, The results show that an improvement of the efficiency of the process makes the proposed algorithm a great method to improve the controller of the processes.

关键词： Batch production systems Process control Production Space exploration Particle swarm optimization Artificial intelligence Inductors Optimization Chemicals Thermal stability

来源：评论

学校读者我要写书评

暂无评论

A Safe Overtaking Control Scheme for Autonomous Vehicles using Rapid-Exploration Random Tree 4

A Safe Overtaking Control Scheme for Autonomous Vehicles usi...

引用

4th IEEE International Conference on Artificial Intelligence in engineering and Technology, IICAIET 2022

作者： Ma, Yincong Lim, Kit Guan Tan, Min Keng Ee Chuo, Helen Sin Angeline, Lorita Kin Teo, Kenneth Tze Modelling Simulation & Computing Laboratory Universiti Malaysia Sabah Faculty of Engineering Kota Kinabalu Malaysia School of Computer Science Taylor's University Faculty of Innovation & Technology Subang Jaya Malaysia

ISBN: (数字)9781665468374

ISBN: (纸本)9781665468374

In order to enhance the commuting ability of autonomous vehicles on the road and ensure the comfort and safety of passengers, the Rapid-exploration Random Tree (RRT) algorithm is applied to the research of safe overtaking control of autonomous vehicles. Firstly, the kinematics and dynamic model of the vehicle are implemented. Secondly, the RRT algorithm and the A-star algorithm are expounded, and the idea of the A-star algorithm is applied to the RRT algorithm for improvement. The improved algorithm is used to obtain the rough obstacle avoidance of the vehicle. The rough path is optimized by applying the cubic spline interpolation method to solve the problem that the path cannot be applied to the actual vehicle driving task. Finally, the simulation of the overtaking scheme is carried out. The results reveal that the safe overtaking scheme based on RRT algorithm achieves the predetermined requirements in the two actual cases under the premise of ensuring safety, controlling the swing of the sideslip angle of the vehicle's center of mass within a reasonable range. It has certain practical significance for ensuring the road safety of autonomous vehicles. © 2022 IEEE.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Computing Non-Contactable Drowsiness Monitoring System with Mobile Machine Vision 4

Computing Non-Contactable Drowsiness Monitoring System with ...

引用

4th IEEE International Conference on Artificial Intelligence in engineering and Technology, IICAIET 2022

作者： Polumpung, Alixson Angeline, Lorita Ee Chuo, Helen Sin Tan, Min Keng Lim, Kit Guan Tze Kin, Kenneth Teo Universiti Malaysia Sabah Modelling Simulation & Computing Laboratory Faculty of Engineering Kota Kinabalu Malaysia School of Computer Science Taylor's University Faculty of Innovation & Technology Subang Jaya Malaysia

ISBN: (数字)9781665468374

ISBN: (纸本)9781665468374

This project proposes a human facial features detection based on color segmentation via skin color and Viola-Jones algorithm for real time application. YCbCr color space is used to detect the presence of skin in an image where the image is normalized, and luminance is removed to increase face detection accuracy. The second method, Viola-Jones which use Haar feature to detect facial feature such as face and eye also developed and tested. To perform in real time detection, CamShift algorithm and template matching are used to track face and eyes sequentially in Android platform. Then, the real time detection and tracking are evaluated to assess its performance. Finally, the algorithm is applied to drowsiness detection using PERCLOS. © 2022 IEEE.

关键词： Template matching

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：