检索结果-内蒙古大学图书馆

SSRN 2024年

作者： He, Ying Wang, Jinghua Yan, Lijun Zhang, Leian Li, Jianwei Wen, Yongshuang School of Mechanical Engineering Shandong University of Technology Shandong Zibo China State Key Laboratory of Structural Analysis Optimization and CAE Software for Industrial Equipment Dalian University of Technology Liaoning Dalian China Blade testing center Sinoma Wind Power Blade Co. Ltd Jiangsu Lianyungang China

Root failure is one of the common failure types of composite wind turbine blades. This paper presents a comprehensive study on the connection strength of blade root structure using the latest subcomponent test method. Firstly, the tested subcomponent with embedded bolt sleeves and bolts is designed and manufactured. A finite element model is set up to predict the failure behaviors and danger region of the embedded bolt structure. Then, laboratory tests based on the simulation results are conducted to investigate the mechanical characteristics and failure mechanisms of the blade root. The sensor data are collected to study the damage evolution and failure type of the embedded bolt structure. There is a good agreement between the test and the predicted results. The study shows that the failure types in this test include cracks and delamination of the bonding interface, which lead to the pull-out of the embedded bolt sleeve from the embedded bolt structure. The relationship between tensile load and material stress is linear. The failure process starts from the elastic deformation, and finally, the global brittle fracture leads to the collapse of the embedded bolt structure. © 2024, The Authors. All rights reserved.

关键词： Wind turbine blades

来源：评论

学校读者我要写书评

暂无评论

A Portable and Wearable Visual Brain-Computer Interface for Assessing Patients With Disorders of Consciousness

A Portable and Wearable Visual Brain-Computer Interface for ...

引用

Electronic Information engineering and Computer Communication (EIECC), International Conference on

作者： Huang Wu Jun Xiao Chenxin Xue Di Chen Jiahui Pan Yuanqing Li School of Automation Science and Engineering South China University of Technology Guangzhou China School of Electric Power Engineering South China University of Technology Guangzhou China School of Software South China Normal University Guangzhou China Pazhou Laboratory Research Center for Brain–Computer Interface Guangzhou China

The JFK Coma Recovery Scale-Revised (JFK CRSR) is a clinical behavioral method for assessing patients with disorders of consciousness (DOC). However, due to severe brain injury, the DOC patients may lack sufficient behavioral responses, leading to a relatively high clinical misdiagnosis rate of the JFK CRS-R. To address this limitation, this study developed a portable and wearable Brain-Computer Interface (BCI) to evaluate the visual tracking abilities of the DOC patients and enhance the diagnostic accuracy of the JFK CRS-R. During the experiment, patients wore an Electroencephalogram headband, and the Graphical User Interface of the BCI presented four human images with a background captured by a camera. A target human image was randomly selected, then the four images alternately flashed until the target moved to its initial position. The system guided patients to concentrate their attention on the moving target. In a case study, the BCI system was applied to a patient diagnosed with a minimally conscious state (MCS). In contrast to the lack of visual tracking behavior in CRS-R, our experiment result showed a significant accuracy of 60% achieved by the MCS patient, emphasizing the visual tracking abilities of the MCS patients and highlighting the effectiveness of the system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhanced Assessment of Auditory Perception Function in Disorders of Consciousness Using a Minimalist Wearable Brain-Computer Interface

Enhanced Assessment of Auditory Perception Function in Disor...

引用

Computer, Big Data and Artificial Intelligence (ICCBD+AI), International Conference on

作者： Chenxin Xue Jun Xiao Huang Wu Li Hu Jiahui Pan Yuanqing Li School of Automation Science and Engineering South China University of Technology Guangzhou China School of Electric Power Engineering South China University of Technology Guangzhou China School of Software South China Normal University Guangzhou China Research Center for Brain-Computer Interface Pazhou Laboratory Guangzhou China

ISBN: (数字)9798350373233

ISBN: (纸本)9798350373240

The Coma Recovery Scale-Revised (CRS-R) is a clinical behavioral method for assessing the levels of consciousness and perceptual abilities in patients with Disorders of Consciousness (DOC). However, due to severe impairment of motor functions in DOC patients and subjective factors of clinical evaluators, the misdiagnosis rate of the CRS-R is very high. Brain-computer interfaces (BCIs) can directly detect patients’ brain activity in response to external stimuli, independent of patients’ behavioral representation, thereby achieving a more objective assessment. In this study, we introduced a minimalist wearable BCI system grounded in the auditory oddball paradigm to enhance assessment of auditory perception function in DOC patients. In the experiments, sinusoidal tones and the complex sound of clapping were selected as standard stimuli occurring frequently and occasional deviant stimuli, respectively. The specific event-related potentials evoked by the auditory stimuli facilitated the assessment of auditory perceptual function. The experimental results indicate that the DOC patients with auditory perception functions can also be detected by the BCI system. As a result, the BCI could serve as a valuable adjunct tool in clinical practice of the CRS-R.

关键词： Brain External stimuli Medical services Big Data Motors Brain-computer interfaces Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Economic and environmental analysis of a solar-powered ev charging system in india—a case study 2nd

Economic and environmental analysis of a solar-powered ev ch...

引用

2nd International Conference on Electrical and Electronics engineering, ICEEE 2021

作者： Shrivastava, Prashant Soon, Teykok Mekhilef, Saad Ahmad, Furkan Department of Computer System and Technology Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur50603 Malaysia Power Electronics and Renewable Energy Laboratory Department of Electrical Engineering Faculty of Engineering University of Malaya Kuala Lumpur50603 Malaysia School of Software and Engineering Faculty of Science Engineering and Technology Swinburne University of Technology MelbourneVIC3122 Australia Indian Institute of Technology New Delhi Delhi110016 India

ISBN: (纸本)9789811607486

With the growing environmental concern, the demand for electric vehicle is increasing in India. However, the limited existing charging facilities slow down the rate of adoption in the market. Presently, the solar-based charging system is gaining popularity, due to its low greenhouse gas emission. In this study, a case study for different solar charging systems suited in Delhi is presented. The economic and environmental analysis of different solar-based EV charging systems utilized for charging three types of commercial EVs such as 2, 3, and 4-W is explained. The cost of energy required for 100 km drive is lower with vehicle integrating PV charging system;however, it can act as a supportive system for driving range improvement. The analysis shows that the economically solar rooftop charging system is suitable for all types of EVs. The CO2 emission produced by all types of solar-based EV charging systems is lower than coal-based charging systems. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2021.

关键词： Solar energy

来源：评论

学校读者我要写书评

暂无评论

MRLATO: An Adaptive Task Offloading Mechanism Based on Meta Reinforcement Learning in Edge Computing Environment

引用

IEEE Transactions on Vehicular technology 2025年

作者： Zhang, Peiying Liu, Jiamin Guizani, Maher Wang, Jian Kumar, Neeraj Tan, Lizhuang Qingdao Institute of Software College of Computer Science and Technology Qingdao266580 China Shandong Key Laboratory of Intelligent Oil & Gas Industrial Software Qingdao266580 China Ministry of Education Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Jinan250014 China University of Texas Arlington Computer Science and Engineering Department TX United States College of Science Qingdao266580 China Thapar University Department of Computer Science and Engineering Patiala147004 India Jinan250014 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Jinan250014 China

Traditional cloud computing models struggle to meet the requirements of latency-sensitive applications when processing large amounts of data. As a solution, Multi-access Edge Computing (MEC) extends computing resources to the edge of the network to reduce processing delays and improve user experience. However, in dynamically changing edge computing environments, effective decision making on whether to offload tasks to edge servers remains a core challenge. For this purpose, we propose MRLATO, an adaptive task offloading mechanism based on Meta Reinforcement Learning (MRL), which exploits a large amount of a priori knowledge of different tasks to achieve fast adaptation. The task offloading process is modelled as multiple Markov Decision Processes (MDPs) and solved using a Sequence to Sequence (Seq2Seq) neural network integrating multi-head attention and recursive task sequencing. It is shown by the experimental results that the proposed method has the lowest latency in all experimental settings and the convergence efficiency is improved by 14.06% compared to the traditional Deep Reinforcement Learning (DRL) algorithm. This research fully demonstrates the significant benefits of the deep integration of MRL with the edge computing domain, providing new optimisation ideas for task offloading decisions. © 1967-2012 IEEE.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

Research and development of an information system for speech recognition based on neural network algorithms metrics

Research and development of an information system for speech...

引用

Smart Information Systems and Technologies (SIST), IEEE International Conference on

作者： Maksat Kanashev Assel Mukasheva Didar Yedilkhan Sabina Rakhmetulaeva Sergiy Gnatyuk Mirambayeva Nazym Almaty University of Power Engineering and Telecommunications Almaty Kazakhstan School of Information Technology and Engineering Kazakh-British Technical University Almaty Kazakhstan Department of Computer Engineering Astana IT University Astana Kazakhstan Department of Information Systems International University of Information Technologies Almaty Kazakhstan Faculty of Cybersecurity Computer and Software Engineering National Aviation University National Aviation University Kyiv Ukraine

ISBN: (数字)9798350374865

ISBN: (纸本)9798350374872

This article examines the parameters of speech recognition in audio recordings containing a variety of phrases uttered by different people with different accents and intonations. The aim of the study is to evaluate the recognition speed, the accuracy of audio-to-text conversion and resource consumption when using SpeechRecognition and Levenshtein libraries. During the analysis, the above libraries were used to record and recognize audio files, as well as to calculate the distance between two lines and determine the recognition accuracy. The findings of this study can be useful for improving speech recognition systems and creating more adaptive and efficient solutions for audio data processing. The results of comparing the accuracy of speech recognition models are recorded in JSON format, after which, using the matplotlib library, they are visualized as graphs, comparing the speed and accuracy of recognition. Visualization of data in this way contributes to their improvement and more effective integration into educational systems. In conclusion, the authors emphasize the prospects for further development of speech recognition technologies in different fields.

关键词： Performance evaluation Adaptation models Vocabulary Accuracy Data visualization Speech recognition Libraries

来源：评论

学校读者我要写书评

暂无评论

Research and Application of Nuclear Reactor Computational Data Framework Based on HDF5 7th

Research and Application of Nuclear Reactor Computational Da...

引用

7th International Conference on Artificial Intelligence and Security, ICAIS 2021

作者： Lu, Wei Feng, Jintao Yang, Hao Zeng, Hui Pan, Junjie Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of China Chengdu610213 China School of Computer Science Chengdu University of Information Technology Chengdu610225 China School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu610054 China

ISBN: (纸本)9783030786175

Nuclear reactor computing software need to process and maintain complex and massive data sets. In order to meet the requirement of mass data storage and processing in software, the data storage model and I/O method and programming interface of HDF5 (Hierarchical Data Format v5) are deeply studied. According to the data storage and processing requirement of typical nuclear reactor computing data such as assembly or core neutronics computing data and core thermal-hydraulic computing data, RCDF-H5 (Reactor Compute Data Framework based on HDF5) is proposed. KYMRES (KYlin-2 Main RESults databank) and COMRES (COre Main RESults databank) are designed and implemented based on RCDF-H5. The performance tests show that RCDF-H5 has a higher I/O efficiency than conventional storage solutions. A new data storage and management solution for nuclear reactor computing software is provided. © 2021, Springer Nature Switzerland AG.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

A Thermodynamics-Informed Deep Learning Approach for Lightweight Modelling of Gas Turbine Performance

SSRN

引用

SSRN 2024年

作者： Jiang, Xiaomo Liu, Yiyang Wang, Zhicheng Wei, Manman State Key Lab of Structural Analysis Optimization and CAE Software for Industrial Equipment Provincial Key Lab of Digital Twin for Industrial Equipment Dalian University of Technology Dalian116024 China School of Mechanics and Aerospace Engineering Dalian University of Technology Dalian116024 China School of Energy and Power Engineering Dalian University of Technology Dalian116024 China Laboratory of Ocean Energy Utilization Ministry of Education Dalian University of Technology Dalian116024 China

The heavy-duty gas turbine (HDGT) and its main subsystems, such as compressor andThe heavy-duty gas turbine (HDGT) and its main subsystems, such as compressor and turbine, experience degradation over the time due to extreme operating conditions, leading to decreased efficiency. However, many previous studies have overlooked the impact of ambient conditions and power demand, which can significantly affect gas turbine performance, deviating it from its design conditions. Therefore, there is a critical need to develop effective approaches for efficiently and accurately modeling thermal performance of HDGTs for predictive maintenance. This paper proposes a generalized methodology to implement the physics-informed deep learning model for HDGT performance lightweight modeling. Initially, a mechanism-based thermodynamic model is established to serve as a performance benchmark. Subsequently, corrections are applied by adjusting baseload operating conditions to reference conditions, thereby mitigating the influence of ambient conditions and power demand. Then, a deep operator networks model is constructed by integrating actual and simulation data to rapidly obtain essential gas turbine performance parameters, including compressor and turbine efficiency, HDGT corrected power output, and heat rate. To demonstrate the advantage of the proposed methodology, a comparison study with the classical nonlinear autoregressive network with exogenous inputs model is conducted using data from two real-world HDGT machines. The results highlight the advantages of the proposed approach in accurately capturing the complexities of gas turbine performance. This study serves as a promising tool for performance-based predictive maintenance and gas path fault diagnosis in gas turbines. © 2024, The Authors. All rights reserved.

关键词： Gas turbines

来源：评论

学校读者我要写书评

暂无评论

Application of soft computing algorithms for hybrid modular multilevel inverters

引用

Measurement: Sensors 2024年 31卷

作者： Gireesh Kumar, Devineni Venkata Sireesha, Nagineni Bhoopal, Neerudi Kumar Gatla, Ranjith Kotb, Hossam AboRas, Kareem M. Elrashidi, Ali Alqarni, Mohammed Yasin Ghadi, Yazeed Oubelaid, Adel Department of Electrical & Electronics Engineering B V Raju Institute of Technology Narsapur502313 India Department of Information Technology Institute of Aeronautical Engineering Hyderabad500043 India Department of Electrical & Electronics Engineering Institute of Aeronautical Engineering Hyderabad500043 India Department of Electrical Power and Machines Faculty of Engineering Alexandria University Alexandria21544 Egypt Electrical Engineering Department University of Business and Technology Ar Rawdah Jeddah23435 Saudi Arabia Engineering Mathematics Department Faculty of Engineering Alexandria University Alexandria21544 Egypt Department of Computer Science and Software Engineering Al Ain University Abu Dhabi15322 United Arab Emirates Laboratoire de Technologie Industrielle et de L'Information Faculté de Technologie Université de Bejaia Bejaia06000 Algeria

This study utilized Harris Hawk optimization to analyze the harmonic distortions of a symmetric capacitor based multilevel converter. The proposed multilevel converter uses identical and symmetric DC sources in its input. The proposed topology for a multilevel converter uses fewer switches than typical cascaded designs. It can output 9-level outputs and can be scaled up to higher levels. The proposed multilevel converter can be improved by implementing a low frequency pulse width modulation technique to reduce the stress on the switches. The optimization of the switching angles using Harris Hawk was able to solve the non-linear aspects of the Selective Harmonic Elimination Pulse Width Modulation. The output voltage's THD was compared with that of other optimization methods, such as ant colony and particle swarm. The comparison shows that the output THD of the Harris Hawk optimizer is lower than that of other methods, which is about 5 %, according to the standards of IEEE-519. © 2023

关键词： Pulse width modulation

来源：评论

学校读者我要写书评

暂无评论

EventTrojan: Manipulating Non-Intrusive Speech Quality Assessment via Imperceptible Events

EventTrojan: Manipulating Non-Intrusive Speech Quality Asses...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Ying Ren Kailai Shen Zhe Ye Diqun Yan Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo China Juphoon System Software Co. Ltd Ningbo China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology (Shandong Academy of Sciences) China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Non-Intrusive speech quality assessment (NISQA) has gained significant attention for predicting speech’s mean opinion score (MOS) without requiring the reference speech. Researchers have gradually started to apply NISQA to various practical scenarios. However, little attention has been paid to the security of NISQA models. Backdoor attacks represent the most serious threat to deep neural networks (DNNs) due to the fact that backdoors possess a very high attack success rate once embedded. However, existing backdoor attacks assume that the attacker actively feeds samples containing triggers into the model during the inference phase. This is not adapted to the specific scenario of NISQA. And current backdoor attacks on regression tasks lack an objective metric to measure the attack performance. To address these issues, we propose a novel backdoor triggering approach (EventTrojan) that utilizes an event during the usage of the NISQA model as a trigger. Moreover, we innovatively provide an objective metric for backdoor attacks on regression tasks. Extensive experiments on four benchmark datasets demonstrate the effectiveness of the EventTrojan attack. Besides, it also has good resistance to several defense methods.

关键词： Measurement Resistance Adaptation models Multimedia systems Current measurement Artificial neural networks Benchmark testing

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：