检索结果-内蒙古大学图书馆

31st International conference on Metallurgy and Materials (METAL)

作者： Peterkova, Jindra Macurova, Pavla Stefanovova, Zuzana Pracharova, Lenka Kolumber, Stefan Moravian Business Coll Olomouc Olomouc Czech Republic Tech Univ Ostrava Ostrava Czech Republic

ISBN: (纸本)9788088365068

The paper contains new knowledge about the expansion of technologies associated with Industry 4.0 and digitalization in selected companies including metallurgical companies in the Czech Republic and evaluates the intensity of business process innovation with a focus on internal processes implemented in companies. A probe was implemented which was purposefully focused on the analysis of statistical data on innovation activities in innovative companies including metallurgical companies in the Czech Republic in the period under study by. The processing of statistical data obtained by the CZSO by a survey made it possible to obtain more detailed overviews of the relative frequencies of enterprises that implemented individual types of process innovations in the period under study and that have introduced some of the elements or tools of Industry 4.0 and the digitalization. The importance of innovation for the continued existence and development of the company is recognized especially by large companies and companies under foreign control. Many of these companies are already applying technologies associated with Industry 4.0 and the digitalization and they are moving towards the creation of a digital enterprise. On the contrary, the implementation of innovation activities and the use of technologies associated with Industry 4.0 in small and medium-sized companies is low. The main obstacle is insufficient funding for new technologies and human resources.

关键词： Innovation activity business process Innovation internal process Innovation Industry 4.0 digitalization of business processes

来源：评论

学校读者我要写书评

暂无评论

SCADA-BASED LONG-TERM WIND TURBINE PERFORMANCE DEGRADATION analysis BASED ON DEEP LEARNING TECHNIQUES 69

SCADA-BASED LONG-TERM WIND TURBINE PERFORMANCE DEGRADATION A...

引用

69th ASME Turbomachinery Technical conference and Exposition (ASME Turbo Expo) (GT)

作者： Peng, Dandan Terzi, Ludovico Desmet, Wim Gryiliast, Konstantinos Katholieke Univ Leuven Dept Mech Engn LMSD Leuven Belgium Flanders Make KU Leuven Leuven Belgium Leuven AI KU Leuven Inst AI B-3000 Leuven Belgium ENGIE Italia Milan Italy

ISBN: (纸本)9780791888094

In the context of the rapid development of wind energy as a renewable resource, ensuring effective monitoring and maintenance of wind turbines is increasingly important. Despite the large volume of data collected by Supervisory control and data Acquisition (SCADA) systems, extracting key feature information to construct successful condition monitoring models remains a complex and challenging task. This study introduces a deep learning approach, called Convolutional Neural Network-based Support Vector data Description (CNN-SVDD), aiming at effectively monitoring the long-term health status of wind turbines and providing timely warning for potential faults. The method employs Convolutional Neural Network (CNN) to deeply analyze time-series features and the correlations between sensors from SCADA data, capable of overcoming the challenges posed by environmental noise and changes in operational conditions. Subsequently, within the deep feature space learned by CNN, the SVDD classifier constructs a soft-boundary hypersphere. It allows for some samples to reside outside the hypersphere, thereby enhancing robustness against potential outliers in the SCADA data. Notably, the optimization processes of CNN and SVDD are linked, forming together an end-to-end process. The anomaly score generated by SVDD may act as an intelligent health indicator for assessing long-term performance degradation in wind turbines. Additionally, the radius of the hypersphere serves as a threshold for potential fault warnings. Extensive experiments on SCADA data acquired from multiple wind turbines over an 11-year period demonstrate the effectiveness of this method in early fault warning and long-term wind turbine performance degradation monitoring.

关键词： Wind Turbines Condition Monitoring Convolutional Neural Networks Support Vector data Description Long-Term Performance Degradation Fault Detection

来源：评论

学校读者我要写书评

暂无评论

Node-weighted Graph Convolutional Network for Depression Detection in Transcribed Clinical Interviews 24

Node-weighted Graph Convolutional Network for Depression Det...

引用

Interspeech conference

作者： Burdisso, Sergio Villatoro-Tello, Esau Madikeri, Srikanth Motlicek, Petr Idiap Res Inst Martigny Switzerland Brno Univ Technol Fac Informat Technol Brno Czech Republic

We propose a simple approach for weighting self-connecting edges in a Graph Convolutional Network (GCN) and show its impact on depression detection from transcribed clinical interviews. To this end, we use a GCN for modeling non-consecutive and long-distance semantics to classify the transcriptions into depressed or control subjects. The proposed method aims to mitigate the limiting assumptions of locality and the equal importance of self-connections vs. edges to neighboring nodes in GCNs, while preserving attractive features such as low computational cost, data agnostic, and interpretability capabilities. We perform an exhaustive evaluation in two benchmark datasets. Results show that our approach consistently outperforms the vanilla GCN model as well as previously reported results, achieving an F1=0.84% on both datasets. Finally, a qualitative analysis illustrates the interpretability capabilities of the proposed approach and its alignment with previous findings in psychology.

关键词： depression detection graph neural networks node weighted graphs limited training data interpretability

来源：评论

学校读者我要写书评

暂无评论

Flutter boundary prediction method based on HHT and machine learning 17

Flutter boundary prediction method based on HHT and machine ...

引用

conference on Nondestructive Characterization and Monitoring of Advanced Materials, Aerospace, Civil Infrastructure, and Transportation XVII

作者： Hong, Zhongxin Zhou, Li Chen, Mingfeng Nanjing Univ Aeronaut & Astronaut State Key Lab Mech & Control Mech Struct Nanjing 210016 Peoples R China

ISBN: (纸本)9781510660816;9781510660823

A flutter boundary prediction method based on HHT and machine learning is proposed to predict the flutter velocity before the wind speed reaches the subcritical state. Natural excitation technique is used to extract impulse response signals. EMD ( empirical Mode decomposition method) is used to decompose the signal. Hilbert spectrum was obtained and analyzed by HHT to decompose the signal. The analysis methods included HHT spectrum and marginal spectrum analysis, so as to extract the characteristic quantity and establish the classification model according to different flight states. Then, regression models were established under different flutter modes for flutter degree analysis. During the prediction, according to the classification performance of the data to be measured, the flutter degree analysis result is weighted to obtain the flutter degree corresponding to the current wind speed, and then the flutter wind speed is calculated. In the selection of machine learning algorithm, naive Bayes algorithm, K-nearest neighbor algorithm and other machine learning algorithms are used to construct the classification model, linear regression,, Gaussian process regression and so on are used to construct the regression model. The results show that the K-nearest neighbor algorithm performs best in the classification algorithm, while the Gaussian process regression algorithm performs best in the regression algorithm. Through the cross-validation of the test data, the proposed method can accurately predict the critical flutter velocity when it is far away from the flutter boundary through flutter mode recognition and flutter degree analysis.

关键词： Flutter boundary prediction,Machine learning Feature extraction Flutter pattern recognition Flutter degree analysis

来源：评论

学校读者我要写书评

暂无评论

20th International conference on Mobile Web and Intelligent Information Systems, MobiWIS 2024

20th International Conference on Mobile Web and Intelligent ...

引用

20th International conference on Mobile Web and Intelligent Information Systems, MobiWIS 2024

ISBN: (纸本)9783031680045

The proceedings contain 22 papers. The special focus in this conference is on Mobile Web and Intelligent Information Systems. The topics include: Simulation of SARSA-Based Reinforcement- Learning Dynamic SDN Migration process;Dynamic SDN Multiple Nodes Migration Using SARSA Reinforcement Learning;exploring Worst Arc Flow Minimization: A Comparative Study of a Provided Wireless Network and Its Derivation via Spanning Tree Topology;Decentralized Renewable Energy Trading: A Cross-Chain, NFT, and IPFS Framework;Advancing IAM in the Finance Sector by Integrating Zero Trust and Blockchain Technology;Enhanced Security for Animal Health Records Using RSA-Encrypted NFTs on the Blockchain;evaluating Third-Party Involvement in Android Apps: Norms and Anomalies in Usage Patterns;applying the Knowledge Behavior Gap Model to Study the Acceptance of Blockchain-Based Solutions;Transparent Threads: Enhancing Handicraft Supply Chain Ethics and Transparency with Blockchain, Smart Contracts and Encrypted-RSA NFTs;enhancing User control and Transparency in Personal data Trading: A Blockchain-Enabled Platform Approach;Quantum-Blockchain Healthcare System for Invasive and No-Invasive-IoMT data;exploring Human Artificial Intelligence Using the Knowledge Behavior Gap Model;review of Deep Learning Models for Remote Healthcare;Transformation Design Framework for AI-Driven Hyper-performance;a Statistical Approach for modeling the Expressiveness of Symbolic Musical Text;A Domain-Aware Federated Learning Study for CNC Tool Wear Estimation;information and Knowledge Management Methods for the Preparation of New Safety Standards and New Legislation for Use in Smart Cities;lessons Learned: A Usability Study of an Urban data Platform for Citizens;the Impact of Modern Information Technology on the Resistance to Disinformation in the Police;exploring Cognitive Enhancement Technologies in the Workplace: A Systematic Literature Review.

关键词：

来源：评论

学校读者我要写书评

暂无评论

VIEWING OF RADIOACTIVE MATERIAL INCLUDING VITRIFICATION processES

VIEWING OF RADIOACTIVE MATERIAL INCLUDING VITRIFICATION PROC...

引用

ASME International conference on Environmental Remediation and Radioactive Waste Management (ICEM)

作者： Canty, Christopher Canty, Tod JM Canty Frankfurt Germany JM Canty Buffalo NY USA

ISBN: (纸本)9780791887530

High Temperature cameras allow ideal visual inspection and verification in extreme temperature environments. A unique fused glass seal provides an impenetrable safety barrier between the camera electronics and the harsh process environments. The camera is protected from high temperatures, fumes and radiation. The dynamic imaging system provides a live view of the process, and analyzes the process by generating critical real time measurement data. In nuclear waste vitrification, radioactive material is heated with glass forming additives and poured into a containment vessel to cool into a uniform glass product. The use of high temperature camera systems allows verification that the melting and cooling processes are uniform and repeatable, by providing a live view and analysis of the process. This allows for maximum efficiency and safety, while maximizing the percentage of waste that can be immobilized in the glass product. The paper outlines the critical steps in the disposal of nuclear waste, including the vitrification processes. The strategies used to ensure process safety and efficiency are examined and the critical measurements in each step are determined. It is demonstrated that High Temperature cameras are a useful tool for monitoring those critical measurements to improve the processes of nuclear waste vitrification.

关键词： Containment vessels Electronics Radioactive wastes Radioactive substances Safety High temperature Cooling Glass Glass products Melting Optical quality control Radiation (Physics) Vitrification Imaging Temperature

来源：评论

学校读者我要写书评

暂无评论

WORK-IN-PROGRESS: RELIABILITY PREDICTION OF API CENTRIFUGAL PUMPS USING SURVIVAL analysis 19

WORK-IN-PROGRESS: RELIABILITY PREDICTION OF API CENTRIFUGAL ...

引用

19th IMEKO TC10 conference on MACRO meets NANO in Measurement for Diagnostics, Optimization and control

作者： Vila Forteza, M. Galar Pascual, D. Kumar, U. Verma, A.K. Division of Operation and Maintenance Engineering Luleå University of Technology Luleå Sweden Repsol Petronor Oil Refinery Bizkaia Basque Country Muskiz Spain Faculty of Engineering and Natural Sciences Western Norway University of Applied Sciences Haugesund Norway

ISBN: (纸本)9781713884125

In the Oil & Gas Industry, large fleets of centrifugal pumps are used for different services working in diverse process conditions. More specifically in oil refineries, they have many characteristics in common since they are centrifugal machines that handle liquids using the same operating principle and because their design is highly standardized by API 610/ISO 13709 std for centrifugal pumps and API 682 std for sealing systems. As well, operating units and refining processes are well known and do not differ much regardless of where they are installed. Due to their criticality in the refining process, the reliability of these assets is of the utmost importance, being the MTBF (Mean Time Between Failures) one of the most used KPI (Key Performance Indicator) for evaluating it. Considering the characteristics indicated above, the possibility of predicting the MTBF of centrifugal pumps based on historical failure data, design features and expected operating conditions with Cox Proportional Hazards Model (PHM) is suggested. © 2023 19th IMEKO TC10 conference "MACRO meets NANO in Measurement for Diagnostics, Optimization and control".

关键词： Industry API standard Centrifugal pumps Infrastructure Innovation MTBF Proportional Hazards Model Reliability prediction

来源：评论

学校读者我要写书评

暂无评论

Intelligent Assisted Navigation for Ships Using Edge Computing and Neural Networks

Intelligent Assisted Navigation for Ships Using Edge Computi...

引用

Intelligent Computing and Robotics (ICICR), International conference on

作者： Wenge Cheng Department of Maritime Technology Tianjin Maritime College Tianjin China

ISBN: (数字)9798350372274

ISBN: (纸本)9798350372281

In order to meet the requirements of high real-time and stability in the process of ship navigation, this paper applies an intelligent auxiliary means based on edge computing and convolutional neural network (CNN). The edge computing platform is deployed on the ship, and sensors and cameras are used to collect surrounding data. The convolutional neural network models are trained to accurately recognize and classify different types of obstacles, and real-time environmental perception and analysis are performed. Intelligent driving assistance decisions such as automatic obstacle avoidance, path planning, and speed control are provided based on the analysis results. The research results indicate that the average recovery time of the system is between 5.8 minutes and 29.5 minutes, with an accuracy of 0.97 in obstacle recognition tasks. The method can achieve intelligent assistance for ship navigation with high real-time performance and stability.

关键词： Navigation Computational modeling Velocity control Real-time systems Stability analysis Path planning Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

On the Mathematical modeling and Optimization for the Energy Efficiency Performance of CSMA-NOMA Random Access Networks With Channel Inversion

引用

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS 2023年第4期22卷 2867-2884页

作者： Cao, Shengbin Hou, Fen Univ Macau Dept Elect & Comp Engn State Key Lab Internet Things Smart City Macau Peoples R China Univ Macau Guangdong Hong Kong Macau Joint Lab Smart Cities Hong Kong Guangdong Peoples R China

The paradigm of upcoming 5G and beyond is the massive machine type communications (mMTC), where a large number of devices automatically operate wireless communications. Due to their automatic and energy-intensive operations, energy efficiency (EE) becomes crucial, but there is a lack of investigation for EE of random access networks, which is the underlying platform for mMTC. In this paper, we focus on the EE of carrier sense multiple access-based non-orthogonal multiple access (NOMA) random access networks. We first construct mathematical models. Instead of investigating all combinations regarding successful decoding events as in previous works, by pivoting around the decoding process of a specific signal, a hidden pattern of NOMA decoding process is unveiled, which can largely decrease analytical complexity. Then, together with this feature, by adopting Markov chain and Q-function approximation, closed-form formulation for EE is derived. Subsequently, to efficiently solve the complicated non-convex EE maximization problem built via the constructed models, we employ an approach that unifies complementary geometric programming (CGP) and difference of convex programming (DCP) to optimize all the controllable parameters at device side, namely, transmission probability, power, and data rate, with a tightest lower bound strategy to guarantee seamless EE improvement and very fast convergence to local optimal points even in the worst case. Simulation experiments verify the accuracy of mathematical models and efficiency of optimization scheme.

关键词： NOMA Decoding Mathematical models Wireless communication Optimization Power control Multiaccess communication Non-orthogonal multiple access (NOMA) energy efficiency random access performance analysis complementary geometric programming (CGP) difference of convex programming (DCP) CSMA CA

来源：评论

学校读者我要写书评

暂无评论

Marginal Effects Models of Scientific and Technological Fields' Integration in Heterogeneous Systems 6th

Marginal Effects Models of Scientific and Technological Fiel...

引用

6th conference on Computational Methods in Systems and Software (CoMeSySo)

作者： Rozaliev, V. L. Pronichkin, S. V. Donskaya, A. R. Kasymov, O. K. Kuznetsova, A. S. Volgograd State Tech Univ Volgograd Russia Russian Acad Sci Fed Res Ctr Comp Sci & Control Moscow Russia

ISBN: (纸本)9783031214370;9783031214387

Themain problem in the analysis of the marginal effects of the integration of scientific and technological fields in heterogeneous systems is to identify uncertainty and risk indicators in conditions of insufficient volume of initial information. It is proposed to use neural network technologies that allow expanding the possibilities of modeling in real conditions in the absence of reliable data, incomplete and fuzzy information, complex nonlinear dependences of outputs on inputs of complex scientific and technical systems. To describe the qualitative characteristics of the limiting effects of integration, it is proposed to use multiplicities of metric spaces of multisets. Using the developed software, decision rules for the marginal effects of integration are constructed.

关键词： Scientific and technical system Decision making Interdisciplinarity Heterogeneous systems

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：