检索结果-内蒙古大学图书馆

2023 International Conference on Industrial engineering, Applications and Manufacturing, ICIEAM 2023

作者： Samigulina, Galina Samigulina, Zarina Porubov, Dmitriy Institute of Information and Computing Technologies Lab. Intellectual Control Systems and Forecasting Almaty Kazakhstan Kazakh - British Technical University School of Information Technologies and Engineering Almaty Kazakhstan East Kazakhstan Technical University Named after D. Serikbayev Competence and Technology Transfer Center in the Field of Automation and Mechatronics Ust-Kamenogorsk Kazakhstan

ISBN: (纸本)9781665475952

At present, with the development of modern IT technologies and artificial intelligence methods, it is relevant to develop adaptive distance education systems for students of technical specialties capable of providing a personalized cognitive approach to the process of obtaining knowledge and timely adjustment of the learning trajectory. Particular difficulties arise when teaching the principles of operation of complex industrial equipment based on microprocessor technology, the basics of programming and the development of automatic control systems based on them. The problems associated with the complexity of adapting technical training courses for specific students and the peculiarities of information perception in the absence of direct contact with the teacher can be successfully solved with the introduction of algorithms based on a unified artificial immune system (UAIS). An innovative e-learning technology is proposed for students of engineering specialties in order to obtain high-quality technical professional education in a short time on real industrial equipment. When creating the technology and predicting the learning outcomes of students, immunological homeostasis was used to quickly correct the learning process. UAIS was developed on the basis of modified clonal selection, negative selection and immune network algorithms in order to identify the most effective of them in predicting multivariate dynamic data about students and forming an adequate immune response to maintain immunological homeostasis. The main stages and advantages of the proposed technology are given. The simulation results were obtained with the participation of students of the Faculty of Information Technology on the basis of the Kazakh-British Technical University. © 2023 IEEE.

关键词： engineering education

来源：评论

学校读者我要写书评

暂无评论

Adaptive neural network output-feedback tracking control for switched nonlinear ship maneuvering systems with time delays under arbitrary switching

Adaptive neural network output-feedback tracking control for...

引用

2022 Chinese automation Congress, CAC 2022

作者： Li, Zhenhua Ren, Xiangxuan Dong, Botao Chen, Hong Zhang, Weidong SJTU Sanya Yazhou Bay Institute of Deepsea Science and Technology Sanya572024 China Department of Automation Shanghai Jiao Tong University Shanghai200240 China College of Mechatronics and Control Engineering Shenzhen University Shenzhen518061 China School of Information and Communication Engineering Hainan University Haikou570228 China

ISBN: (纸本)9781665465335

This paper focuses on the tracking control problem for switched nonlinear ship maneuvering time-delay systems with only a heading angle available by adaptive neural network (NN) output feedback. Using the backstepping method, an adaptive NN control mechanism is designed to solve the problem cooperated with the state observer. The uncertain terms of the system are approximated by NNs, and the state observer is designed to estimate the yaw rate and rudder angle. The unknown time delays are overcome by exploiting the common Lyapunov-Krasovskii functionals (CLKFs). Combined with error transformation, the proposed control method guarantees that i) all of the signals for the system are semi-global uniformly ultimately boundedness (SGUUB) under arbitrary switching;and, ii) the tracking error of system output keeps within a small neighborhood around the origin. The results of simulation results are shown to demonstrate the feasibility of the control strategy. © 2022 IEEE.

关键词： Time delay

来源：评论

学校读者我要写书评

暂无评论

Detection and Description of Local Features of a Thermal Image

Detection and Description of Local Features of a Thermal Ima...

引用

International Conference on Industrial engineering, Applications and Manufacturing (ICIEAM)

作者： I. I. Naumov R. R. Ibadov A. G. Gazaryan Faculty of Automation Mechatronics and Control Don State Technical University Rostov-on-Don Russia Department of Electrical Engineering and Electronics Don State Technical University Rostov-on-Don Russia Institute of Advanced Mechanical Engineering “Rostselmash” Don State Technical University Rostov-on-Don Russia

ISBN: (数字)9798331512194

ISBN: (纸本)9798331512200

Thermal images present challenges for traditional computer vision methods due to the lack of clear textures and low contrast. In this paper, we present a hybrid architecture based on a Siamese triplet network and transformers, which provides an accuracy improvement of 42 % over classical methods SIFT, SURF and 28% over state-of-the-art CNN approaches SuperPoint, D2-Net. Key innovations include a thermal-adaptive descriptor, dynamic triplet loss, and a fusion module that integrates spatial and thermal features. Evaluations on industry-standard KAIST, FLIR, Thermal Urban datasets demonstrate excellent performance, with the method detecting 91 % of keypoints in daytime scenes and remaining robust in adverse conditions such as fog, rain, and low visibility. Moreover, the algorithm runs at 45 fps on embedded systems, making it suitable for real-time applications. The algorithm has potential applications in autonomous driving, surveillance, and medical diagnostics.

关键词： Technological innovation Accuracy Heuristic algorithms Surveillance Thermal engineering Computer architecture Transformers Feature extraction Convolutional neural networks Thermal stability

来源：评论

学校读者我要写书评

暂无评论

Online Volt-Var control Based on Reinforcement Learning in Active Distribution Systems Considering PV Inverters

Online Volt-Var Control Based on Reinforcement Learning in A...

引用

International Conference on Power and Energy Technology (ICPET)

作者： Changlei Gu Xian Zhang Hong Wang Ahmed Rabee Sayed Guibin Wang School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen China Electric Power Research Institute China Southern Grid Guangzhou China College of Mechatronics and Control Engineering Shenzhen University Shenzhen China

Due to the wide deployment of photovoltaic (PV) power generation, voltage stability is facing a severe challenge in the active distribution networks (ADNs). Reinforcement Learning (RL) techniques have been widely adopted in the power system optimal operation and quick control with high-performance achievements. Existing RL algorithms can handle only homogenous control action spaces, i.e., either continuous or discrete actions. However, the voltage control problem has hybrid action spaces. This paper proposes a hybrid soft actor-critic (H-SAC) algorithm for online quick-optimal voltage control. First, the problem is formulated to consider all types of control actions, including the setpoints of PV inverters. Second, it is standardized to be compatible with RL techniques. Third, the fundamental sample-efficient entropy-based maximization SAC algorithm is enhanced to train a policy with hybrid action spaces, where an action selection method is employed to map the continuous output of the actor-network into the integer action spaces. The proposed method is applied to the modified IEEE 33-bus system, where the voltage has been controlled with a very low computational burden.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dc Leakage Current in Isolated Grid-Connected dc Nanogrid - Origins and Elimination Methods

Dc Leakage Current in Isolated Grid-Connected dc Nanogrid - ...

引用

Compatibility in Power Electronics (CPE)

作者： Mohammadreza Azizi Oleksandr Husev Oleksandr Veligorskyi Marek Turzvński Ryszard Strzelecki Department of Radiotechnic and Embedded Systems Chernihiv Polytechnic National University Chernihiv Ukraine Department of Electric Electronic and Automation Engineering University of Extremadura Badajoz Spain Department of Electrical Power Engineering and Mechatronics Tallinn University of Technology Tallinn Estonia Faculty of Electrical and Control Engineering Gdansk University of Technology Gdansk Poland

ISBN: (数字)9798350318265

ISBN: (纸本)9798350318272

The LV dc system is a relatively new trend in the distribution sector, which seems to grow widely in the near future due to its promising advantages. In this context, LV dc protection and grounding are challenging issues. Although the galvanically isolated connection mode of dc nanogrid to the ac grid has high reliability, the leakage current can still be injected into the ac grid through the interwinding capacitors and the insulation resistance between the primary and secondary windings of the transformer. The way of grounding the dc nanogrid can also be a determining factor in the leakage current and its dc components. This study deals with the leakage current in the galvanically isolated dc nanogrid. Then, it examines the dc leakage current and its relationship with the dc nanogrid grounding and finally provides solutions to remove the dc components in the leakage current.

关键词： Resistance Insulation Grounding Simulation Windings Capacitors Leakage currents

来源：评论

学校读者我要写书评

暂无评论

Improving Road Safety With Enhanced Vehicle Detection for Night-time Traffic in Mirpur

Improving Road Safety With Enhanced Vehicle Detection for Ni...

引用

International Conference on Robotics and Artificial Intelligence (ICRAI)

作者： Usama Younis Faisal Riaz Umar Raza Gokhan Atali Hamid Rabnawaz Control Automotive and Robotics Lab Affiliated Lab of National Centre of Robotics and Automation (NCRA) HEC Islamabad Pakistan Department of Engineering Manchester Metropolitan University Manchester United Kingdom Mechatronics Engineering Sakarya University of Applied Sciences Sakarya Turkey Selftech Pvt Ltd

ISBN: (数字)9798350355703

ISBN: (纸本)9798350355710

This paper presents a study on improving night-time vehicle detection in the Mirpur region through a modified neural network model. Given the challenges of low visibility at night, the research focused on optimizing a deep learning algorithm to enhance detection accuracy. A dataset of 10,000 images covering various vehicle types was collected and annotated to train and test the model. The study found a 7% increase in detection performance compared to the standard model, highlighting the potential for tailored algorithms in specific environmental conditions. The findings suggest significant implications for road safety and autonomous driving systems, particularly in regions with similar night-time driving challenges. The research contributes to the broader field of computer vision by showing the effectiveness of model optimization in real-world conditions.

关键词： Accuracy Computational modeling Vehicle detection Neural networks Road safety Reliability Robotics and automation Optimization Autonomous vehicles Standards

来源：评论

学校读者我要写书评

暂无评论

A Two-Stage Resilient control Strategy for Transient Stability Enhancement of Coastal Ac/Mtdc Grid Under Typhoon Extreme Weather

SSRN

引用

SSRN 2022年

作者： Wen, Xichang Wang, Huaizhi Wu, Ting Peng, Jianchun Jiang, Hui College of Mechatronics and Control Engineering Shenzhen University Shenzhen518060 China School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen518055 China

As global warming is getting worse, more frequent and more intense typhoon extreme weather events have unfolded around the world. Typhoon will undoubtedly lead to serious N-k contingency of coastal AC/multi-terminal high voltage dc (MTDC) power grid, following a large possibility of transient instability. To address this problem, this paper develops a novel two-stage resilient control strategy. In the first stage, we propose a smooth transition model to reschedule power generations, considering security constraint and demand-supply balance. In the second stage, an active power modulation method of modular multi-level converters (MMC) based on model predictive control is proposed to ensure the transient stability of coastal AC/MTDC grid. The proposed control strategy makes full use of the flexible control resources of MMC-MTDC, thereby increasing the transient stability margin of coastal AC/MTDC grid and preventing subsequent N-k-1 contingencies. The usefulness of the proposed control strategy is highlighted on two hybrid power systems built on MATMTDC, a MATLAB based open source software. The obtained results demonstrate that the two-stage control strategy is capable for improving the transient stability of coastal AC/MTDC power system when suffering a typhoon event. © 2022, The Authors. All rights reserved.

关键词： Transients

来源：评论

学校读者我要写书评

暂无评论

Tuning of FP-PID controller based on PSO Algorithm Applied to a Human Gait

Tuning of FP-PID Controller based on PSO Algorithm Applied t...

引用

IEEE Latin American Robotics Symposium, LARS

作者： Rodrigo B. de Medeiros Daniel M. Muñoz Department of Mechanical Engineering Mechatronics Graduate Program Automation and Control Group/GRACO University of Brasilia Brasilia DF Brazil

ISBN: (数字)9781665462808

ISBN: (纸本)9781665462815

Robotic manipulators are multi-input multi-output (MIMO) systems with nonlinear points affected by numerous uncertainties and disturbances. PID controllers are widely used in industry for kinematic and dynamic control. However, when applied to MIMO systems, they are not easy to tune and require performance improvements. In this work, a PID controller is proposed with a fuzzy precompensator (FP-PID), both tuned by the bioinspired particle swarm optimization (PSO) algorithm to a two-degree of freedom (2-DOF) robotic manipulator representing a human leg. To validate the system, two real datasets of human gait were used: normal walking and stair climbing to estimate the error trajectory of the manipulator. The statistical analysis of the PSO algorithm with 16 experiments was satisfactory, and the addition of the fuzzy precompensator to the conventional PID resulted in a reduction of the mean square error of one of the manipulator links by up to 73 percent.

关键词： Legged locomotion Uncertainty Statistical analysis Service robots Stairs Trajectory Robots

来源：评论

学校读者我要写书评

暂无评论

Investigating the dynamic memory effect of human drivers via ON-LSTM

引用

Science China(Information Sciences) 2020年第9期63卷 83-93页

作者： Shengzhe DAI Zhiheng LI Li LI Dongpu CAO Xingyuan DAI Yilun LIN Department of Automation Tsinghua University Shenzhen International Graduate School Tsinghua University Department of Mechanical and Mechatronics Engineering University of Waterloo State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences

It is a widely accepted view that considering the memory effects of historical information(driving operations) is beneficial for vehicle trajectory prediction models to improve prediction accuracy. However,many commonly used models(e.g., long short-term memory, LSTM) can only implicitly simulate memory effects, but lack effective mechanisms to capture memory effects from sequence data and estimate their effective time range(ETR). This shortage makes it hard to dynamically configure the most suitable length of used historical information according to the current driving behavior, which harms the good understanding of vehicle motion. To address this problem, we propose a modified trajectory prediction model based on ordered neuron LSTM(ON-LSTM). We demonstrate the feasibility of ETR estimation based on ON-LSTM and propose an ETR estimation method. We estimate the ETR of driving fluctuations and lane change operations on the NGSIM I-80 dataset. The experiment results prove that the proposed method can well capture the memory effects during trajectory prediction. Moreover, the estimated ETR values are in agreement with our intuitions.

关键词： driving behavior memory effect trajectory prediction historical information ON-LSTM

来源：评论

学校读者我要写书评

暂无评论

Design. Implementation, and control of a Novel Automated Manual Transmission (AMT) System for Manual Transmission Bicycles

Design. Implementation, and Control of a Novel Automated Man...

引用

Innovations in Intelligent Systems and Applications Conference

作者： Fehmi Can Ay Bengisu Kılınç Talha Enes Ercan Ahmet Kağızman Volkan Sezer Department of Mechatronics Engineering Istanbul Technical University Istanbul Turkey Department of Institute of Science Smart and Autonomous System Laboratory (SASlab) Istanbul Technical University Istanbul Turkey Department of Control and Automation Engineering Smart and Autonomous System Laboratory (SASlab) Istanbul Technical University Istanbul Turkey

ISBN: (数字)9798350379433

ISBN: (纸本)9798350379440

In recent years, the bicycle industry has undergone continuous transformation through the introduction of novel technologies and innovations. Automated Manual Transmission (AMT) system, which is widely used in motor vehicles and defined as automating the traditional manual gearbox through electronic components and actuators, has an important place in the automotive industry due to its advantages such as fuel efficiency, low cost, and driver comfort. However, a similar system is not yet available on bicycles. This article describes developing a new gear-shifting system that enables the manual gear-shifting mechanism in bicycles to be automated with an intelligence-based system. The developed system automatically performs the most appropriate gear change by processing the data received from the sensors, such as inclination, wheel, and pedal cadence, thus providing a more efficient and comfortable driving experience that does not require effort. The system has been tested by integrating it into a bicycle with manual transmission and it has been confirmed that automatic gear shifts were successful.

关键词： Industries Technological innovation Gears Wheels Manuals Bicycles Sensor systems Intelligent systems Intelligent sensors Vehicles

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：