检索结果-内蒙古大学图书馆

Sigma-Mixed Unscented Kalman Filter-Based Fault Detection for Traction systems in High-Speed Trains

Chinese Journal of Electronics 2023年第5期32卷 982-991页

作者： CHENG Chao WANG Weijun MENG Xiangxi SHAO Haidong CHEN Hongtian Department of Computer Science and Technology Changchun University of Technology Department of Mathematics and Statistics Changchun University of Technology Institute of System Research China Industrial Control Systems Cyber Emergency Response Team Department of Mechanical and Vehicle Engineering Hunan University Department of Chemical and Materials Engineering University of Alberta

Fault detection(FD) for traction systems is one of the active topics in the railway and academia because it is the initial step for the running reliability and safety of high-speed trains. Heterogeneity of data and complexity of systems have brought new challenges to the traditional FD methods. For addressing these challenges, this paper designs an FD algorithm based on the improved unscented Kalman filter(UKF) with consideration of performance degradation. It is derived by incorporating a degradation process into the state-space *** network topology of traction systems is taken into consideration for improving the performance of state estimation. We first obtain the mixture distribution by the mixture of sigma points in UKF. Then, the Lévy process with jump points is introduced to construct the degradation model. Finally, the moving average interstate standard deviation(MAISD) is designed for detecting *** the proposed methods via a traction systems in a certain type of trains obtains satisfactory results.

关键词： Degradation Network topology Fault detection Rail transportation State-space methods Safety Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Sizing electrolyzer capacity in conjunction with an off-grid photovoltaic system for the highest hydrogen production

引用

Energy Harvesting and systems 2023年第2期10卷 331-348页

作者： Hassan, Qusay Abbas, Majid K Tabar, Vahid Sohrabi Tohidi, Sajjad Abdulrahman, Imad Saeed Salman, Hayder M. Department of Mechanical Engineering University of Diyala Baqubah Iraq Faculty of Electrical and Computer Engineering University of Tabriz Tabriz Iran College of Technical Engineering Al-Farahidi University Baghdad Iraq Department of Computer Science Al-Turath University College Baghdad Iraq

The electrolysis of renewable energy to produce hydrogen has become a strategy for supporting a decarbonized economy. However, it is typically not cost-effective compared to conventional carbon-emitting methods. Due to the predicted intermediate of low-and zero-marginal-cost renewable energy sources, the ability of electrolysis to connect with electricity pricing offers a novel way to cost reduction. Moreover, renewables, particularly photovoltaics, have a deflationary effect on the value of the grid when they are deployed. This study investigates solar electrolysis configurations employing photovoltaic cells to feed a proton exchange membrane water electrolyzer for hydrogen production. Using experimental meteorological data at 1-min precision, the system has been evaluated in Baghdad, the capital of Iraq. Positioned at the yearly optimum tilt angle for the selected site, the solar array is rated at 12 kWp. Temperature effects on solar module energy loss are taken into account. Several electrolyzers with capacities ranging from 2 to 14 kW in terms of hydrogen production were examined to determine the efficacy and efficiency of renewable sources. MATLAB was utilized for the simulation procedure, with a 2021-2035 project lifespan in mind. The results suggest that a variety of potentially cost-competitive options exist for systems with market configurations that closely approximate wholesale renewable hydrogen. At 4313 h of operation per year, the planned photovoltaic array generated 18,892 kWh of energy. The achieved hydrogen production cost ranges between & amp;dollar;5.39/kg and & amp;dollar;3.23/kg, with an ideal electrolyzer capacity of 8 kW matching a 12 kWp photovoltaic array capable of producing 450 kg/year of hydrogen at a cost of & amp;dollar;3.23/kg. & amp;copy;2022 Walter de Gruyter GmbH, Berlin/Boston. © 2023 Walter de Gruyter GmbH. All rights reserved.

关键词： Electrolysis

来源：评论

学校读者我要写书评

暂无评论

Predictive modeling for concrete properties under variable curing conditions using advanced machine learning approaches

引用

Asian Journal of Civil engineering 2024年第8期25卷 6249-6265页

作者： Mungle, Nischal P. Mate, Dnyaneshwar M. Mankar, Sham H. Tale, Vithoba T. Mehta, Ankita Dhale, Shrikrishna A. Vairagade, Vikrant S. Department of Mechanical Engineering Yeshwantrao Chavan College of Engineering Maharashtra Nagpur 441110 India Department of Mechanical Engineering JSPM’s Rajarshi Shahu College of Engineering Maharashtra Pune 440033 India Department of Mechanical Engineering PCET’s Pimpri Chinchwad College of Engineering and Research Ravet Maharashtra Pune 412101 India Department of Computer Science and Application Ramdeobaba University Maharashtra Nagpur 440013 India Department of Civil Engineering Priyadarshini College of Engineering Maharashtra Nagpur 440019 India

Such is the need for this work, since accurate concrete strength prediction at different curing conditions is critical to having structures that are both strong and long-lasting. Traditional methods for the prediction of concrete strength often lack the complexity that occurs in the interaction of the different environmental factors involved, hence leading to suboptimal practices in curing with potential structural weaknesses. Current research into this area has typically focused on disparate data sources and rather naïve modeling methods, further limiting predictive accuracy and creating a general lack of comprehensive knowledge of curing dynamics. Such limitations bring out the need for a more integrated, sophisticated predictive modeling approach to explain variability in concrete strength levels. This paper proposes a novel predictive modeling framework that will be powered by advanced machine learning techniques to take up these challenges. It will adopt a multimodal data integration approach driven by a combination of sensor data related to temperature, humidity, and strain gauges;environmental data related to weather conditions and atmospheric pressure;and historical records, such as mix design and curing duration, further leveraging techniques from data fusion, including the Kalman filter and Bayesian networks. This will be further integrated into a unified, enriched dataset, encapsulating the complex interaction of factors influencing concrete strength. In the present work, this is a chosen approach: hybrid modeling with ensemble learning using XGBoost for the prediction of static features, and Long Short-Term Memory (LSTM) networks for capturing temporal dependencies. In this case, a combination of these models via weighted averaging or stacking improves the accuracy of the predictions to a very great extent: the R² increased from 0.85 to 0.92, and MAE levels by 10–15%. In addition to that, AutoML with Feature Tools implements advanced feature engineering

关键词： Concrete strength Data fusion Ensemble learning Machine learning Predictive modeling

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Optimization for Identifying Effective Drugs in Breast Cancer on an in Vitro Platform 4

Machine Learning-Based Optimization for Identifying Effectiv...

引用

4th IEEE International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2024

作者： Saxena, Mahima Rao, P.V.V.S. Eswara Choudhary, Amar Reddy, P. Srinivas Sharma, Vipin Kumar Kumar, Vinish Ajay Kumar Garg Engineering College Department of Computer Science Ghaziabad India Sasi Institute of Technology and Engineering Department of Computer Science Tadepalligudem India Department Electronics and Communication Engineering Bengaluru India Cvr College of Engineering Mechanical Engineering Department Rangareddy India Ims Engineering College Department of Mca India Ghaziabad India

ISBN: (纸本)9798350360165

In this innovative quest for more efficient irrigation, we investigate the combined use of sensor technology and machine intelligence to optimize agricultural water usage. We collect precise data on essential variables, including water flow, temperature, humidity, soil moisture, and water level, every 15 days by promptly deploying sensors in the field to monitor them in real-time. We use the vast amount of data available to us to train machine learning models, including Recurrent Neural Networks (RNN), K-Nearest Neighbours (KNN), Artificial Neural Networks (ANN), and Convolutional Neural Networks (CNN), specifically for streams that are anticipated to have a certain distribution. CNN has exceptional precision with a decoding accuracy of 94.5% in visual signal interpretation, surpassing ANN, KNN, and RNN which achieve lower accuracies of 91.1%, 88.7%, and 83.6% respectively. Our investigation uncovers a fluid interaction between sensor data and model training, leading to each model exhibiting unique characteristics. These findings not only showcase the accuracy with which machine learning can distribute water, but they also signify a noteworthy progress in resource-efficient and sustainable agriculture. In addition to generating mathematical discoveries, our research establishes the foundation for advanced irrigation systems that smoothly integrate mechanical and natural processes in agricultural fields. © 2024 IEEE.

关键词： Soil moisture

来源：评论

学校读者我要写书评

暂无评论

Enhanced Security for IOMT Devices: Deep learning Techniques for Network Intrusion Detection 5

Enhanced Security for IOMT Devices: Deep learning Techniques...

引用

5th IEEE International Conference on Communication, Computing and Industry 6.0, C2I6 2024

作者： Gopala Krishnan, D. Diviya, M. Jyoshika Shri, K. Subramanian, M. Amrita School of Computing Department of Computer Science and Engineering Chennai India St Joseph's College of Engineering Department of Mechanical Engineering Chennai India

ISBN: (纸本)9798350379884

The increasing popularity of Internet of Medical Things (IoMT) devices, like wearable sensors, has greatly improved patient care by allowing continuous monitoring and real-time data transfer to the cloud. However, this progress also raises security concerns, as the data sent from these devices can be at risk of tampering or hacking during transmission. Keeping this sensitive medical data safe is crucial for patient safety. To address these issues, a fused CNN and LSTM are developed to check whether the data from wearable IoMT devices has been altered or attacked during transmission to the cloud. The CNN part of the model helps to pull out important features from the data, while the LSTM part looks for patterns to spot any signs of tampering. The model uses two convolutional layers each of which is followed by a MaxPooling layer. Our model, tested on a large dataset, achieved an accuracy of 97.06%, showing its ability to protect the integrity of transmitted medical data. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Empowering Human-Machine Communication in Code Generation with NLP 5

Empowering Human-Machine Communication in Code Generation wi...

引用

5th IEEE International Conference on Recent Trends in computer science and Technology, ICRTCST 2024

作者： Aswal, Upendra Singh Rao, Pappala Mohan Supreeth, B.R. Manikandan, G. Srinivasan, R. Tiwari, Mohit Graphic Era Deemed to be University Department of Computer Science & Engineering Uttarakhand Dehradun248002 India Andhra University College Of Engineering AU College Of Engineering Computer Science and System Engineering AP Visakhapatnam530003 India Oxford Degree and PG College Sir. M. Visveshwaraiah Layout Department of Computer Science Ullal Bangalore India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Electronics and Communication Engineering Thandalam India St. Martins Engineering College Department of Computer Science and Engineering Telangana Secunderabad India Bharati Vidyapeeth's College of Engineering Department of Computer Science and Engineering A-4 Rohtak Road Paschim Vihar Delhi India

ISBN: (纸本)9798350351378

The symbiotic interaction between people and computers in the realm of software development is experiencing a fundamental transition, spurred by improvements in Natural Language Processing (NLP). This study investigates how natural language processing (NLP) is changing the software development process by facilitating better human-machine collaboration throughout the coding phase. Data collection, NLP model creation, and assessment are all part of the rigorous process used in our work, which yields important results. The possibility for improving code quality and efficiency while also democratizing code production is discussed in the context of a fictional situation. Ethical concerns are also highlighted, along with the need to minimize bias in NLP-driven code production. To the benefit of developers, organizations, and society at large, this study not only adds empirical insights but also imagines a future in which software development is more inclusive, efficient, and morally responsible. From improved natural language processing models to real-time feedback loops and multimodal techniques, the future of this transforming discipline promises to further influence the landscape of software development. © 2024 IEEE.

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

Enhancing Consumer Sentiment Analysis and Product Improvement with Aspect-Optimized Adaptive GCN (AOA-GCN) 2

Enhancing Consumer Sentiment Analysis and Product Improvemen...

引用

2nd IEEE International Conference on Integrated Intelligence and Communication systems, ICIICS 2024

作者： Annamalai, Sivakumar Nandhini Priya, T. Basker, N. Yuvaraj, S. Ramasami, S. Suresh, D. Department of Safety and Fire Engineering Excel Engineering College Namakkal Komarapalayam India Department of Electrical and Electronics Engineering Excel Engineering College Namakkal Komarapalayam India Department of Computer Science and Engineering Sona College of Technology Salem India Department of Computer Science and Engineering Sri Eshwar College of Engineering Coimbatore India Department of Computer Science and Engineering Bannari Amman Institute of Technology Sathyamangalam India Department of Mechanical Engineering V.S.B Engineering College Karur India

ISBN: (纸本)9798331504960

The exponential growth in online reviews offers a company the most precious source of information regarding the customers' emotions and potential product improvement areas. However, it is very challenging to derive meaningful information from the unstructured data. The work presents a new model called Aspect-Optimized Adaptive GCN (AOA-GCN), which combines hierarchical structuring with aspect-based optimization for effective consumer sentiment analysis. The AOA-GCN applies a two-level analysis framework that covers both global sentiments and detailed aspect-specific sentiments in order to build a full understanding of the customer review. The model is essentially based on an Adaptive Lightweight GCN with pruning techniques, ensuring that it does not only reduce computations but also takes into account influential aspects along with its high accuracy, even across extended datasets. Dynamic attention in AOA-GCN will help make critical product features in the customer reviews focus on the issues so improvements can be made on those products specifically. Experimental results show that the improved performance is actually as high as 6.45% over global sentiment classification, 9.12% over aspect-based sentiment analysis, and 7.35% over cross-domain generalization, and training time is reduced by 35%. The model also exhibits improved interpretability with clearer insights into customer preferences. The proposed AOA-GCN becomes an effective, efficient, and interpretable business tool for optimizing products through insights from consumers. © 2024 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Advancing Polymer Composites Through Computational Learning and Artificial Intelligence Integration 2

Advancing Polymer Composites Through Computational Learning ...

引用

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Manickaraj, K. Aravind, S. Ramakrishnan, T. Sudha, N. Ramamoorthi, R. Nithyanandhan, T. CMS College of Engineering and Technology Department of Mechanical Engineering Tamilnadu Coimbatore India Karpagam Academy of Higher Education Department of Mechanical Engineering Tamilnadu Coimbatore India Sri Eshwar College of Engineering Department of Mechanical Engineering Tamilnadu Coimbatore India CMS College of Engineering and Technology Department of Computer Science Engineering Tamilnadu Coimbatore India Sri Krishna College of Engineering and Technology Department of Mechanical Engineering Tamilnadu Coimbatore India Sri Krishna College of Technology Department of Mechanical Engineering Tamilnadu Coimbatore India

ISBN: (数字)9798331534967

ISBN: (纸本)9798331534950

The revolutionary effects of computational learning and artificial intelligence (AI) on materials science and engineering - particularly in the field of high-performance fiber -reinforced polymer (FRP) composites - are examined in this article. Efficiency, accuracy, and innovation have significantly increased as a result of the integration of AI and machine learning (ML) approaches across the product lifecycle, from material selection and development to manufacturing process optimization and property prediction. AI-powered deep generative models in material design speed up the development of novel composite formulations, while automated fiber placement and Physics-Informed Machine Learning (PIML) improve manufacturing processes to guarantee consistent quality and cut costs. The large-scale dataset-based predictive models have significantly enhanced mechanical property prediction, simplified material selection and cut down on experimental testing expenses and time. Sustainability, efficiency, and performance in material research and production will be fueled by the ongoing advancements in AI and computational learning, which will further transform material science by allowing the design and production of superior composites suited for contemporary industrial applications. © 2024 IEEE.

关键词： Life cycle

来源：评论

学校读者我要写书评

暂无评论

Supervised and unsupervised learning for characterising the industrial material defects

引用

International Journal of Business Intelligence and Data Mining 2022年第2期21卷 233-246页

作者： Radha, P. Selvakumar, N. Raja Sekar, J. Johnsonselva, J.V. Department of Computer Applications Mepco Schlenk Engineering College Sivakasi India Department of Mechanical Engineering Mepco Schlenk Engineering College Sivakasi India Department of Computer Science and Engineering Mepco Schlenk Engineering College Sivakasi India

The ultrasonic-based NDT is used in industries to examine the internal defects without damaging the components since the materials used in the industrial standard components must be 100% perfect. The ultrasonic signals are difficult to interpret, and the domain expert has to concentrate at every sampling point to identify the defect. Hence, the existing ultrasonic-based NDT method is improved by applying IoT, machine learning, and deep learning techniques to process the ultrasonic data. This work integrates NDT and IoT to analyse the properties of materials using deep learning-based supervised model and filter outliers using unsupervised model like density-based clustering method. After analysing the different categories of defects, the notifications are sent to various stakeholders to either repair or replace the defective components through their mobile using advanced communication techniques to avoid expensive experimentation or maintenance. Copyright © 2022 Inderscience Enterprises Ltd.

关键词： Nondestructive examination

来源：评论

学校读者我要写书评

暂无评论

A Surrogate-Assisted Evolutionary Algorithm for Expensive Dynamic Multimodal Optimzation 13

A Surrogate-Assisted Evolutionary Algorithm for Expensive Dy...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Wu, Xunfeng Liu, Songbai Ji, Junkai Ma, Lijia Leung, Victor C. M. Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China The University of British Columbia Department of Electrical and Computer Engineering Vancouver Canada

ISBN: (纸本)9798350308365

Surrogate-assisted evolutionary algorithms (SAEAs) have demonstrated promising optimization performance in addressing expensive dynamic optimization problems or expensive multimodal optimization problems. However, none of existing SAEAs are designed specifically for tackling expensive dynamic multimodal optimization problems (EDMMOPs). Therefore, in this paper, a first SAEA for tackling EDMMOPs is proposed. First, a nearest density clustering is designed to divide the population into a number of subpopulations, enhancing the diversity of the population. Then, a surrogate-assisted evolutionary optimizer is developed to construct surrogate models for each subpopulation and evolve all solutions in subpopulations by means of the built surrogate models, accelerating the population's converge towards several optimal solutions rapidly. Finally, a transfer learning-based prediction is devised to generate initial samples for next environment by leveraging the stored training samples in the previous environments. To assess the performance of our proposed algorithm, a set of complex benchmark problems is adopted, and the experimental results confirm its superior performance over several competitive algorithms on most test cases. © 2024 IEEE.

关键词： Digital elevation model

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：