检索结果-内蒙古大学图书馆

Chinese Automation Congress (CAC)

作者： Xuejin Wu Yanghu Hu Yali Wu Department of Information and Control Engineering Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an University of Technology Xi'an China State Key Laboratory of Metal Extrusion and Forging Equipment Technology China National Heavy Machinery Research Institute Co. Ltd Xi'an China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

The scarcity of fault samples presents a significant challenge for fault diagnosis in industrial processes. Conventional methods often fail to deliver satisfactory results when dealing with small sample sizes. In addressing the issue of small sample fault diagnosis in industrial processes, this paper utilizes the Variational Mode Reconstruction(VMR) algorithm to screen the best components decomposed by the Variational Mode Decomposition(VMD) through the envelope entropy then random weighting them and signal reconstruction to achieve data enhancement, to enrich the sample size and to prevent the model overfitting phenomenon due to the scarcity of samples. Meanwhile, this paper integrates Convolutional Neural Network (CNN) and Long Short-term Memory Neural Network (LSTM) to propose a network model of spatio-temporal feature fusion for feature extraction and classification. The experiments demonstrate that this model not only enhances data diversity but also ensures consistency before and after enhancement, effectively mitigating overfitting. Furthermore, it guarantees high recognition and generalization rates in fault diagnosis.

关键词： Fault diagnosis Training Neural networks Rolling bearings Feature extraction Data models Signal reconstruction Convolutional neural networks Long short term memory Overfitting

来源：评论

学校读者我要写书评

暂无评论

Multi-object Tracking by Detection and Query: an efficient end-to-end manner

arXiv

引用

arXiv 2024年

作者： Jia, Shukun Cao, Yichao Yang, Feng Lu, Xin Lu, Xiaobo School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China School of Instrument Science and Engineering Southeast University Nanjing210096 China

Multi-object tracking is advancing through two dominant paradigms: traditional tracking by detection and newly emerging tracking by query. In this work, we fuse them together and propose the tracking-by-detection-and-query paradigm, which is achieved by a Learnable Associator. Specifically, the basic information interaction module and the content-position alignment module are proposed for thorough information Interaction among object queries. Tracking results are directly Decoded from these queries. Hence, we name the method as LAID. Compared to tracking-by-query models, LAID achieves competitive tracking accuracy with notably higher training efficiency. With regard to tracking-by-detection methods, experimental results on DanceTrack show that LAID significantly surpasses the state-of-the-art heuristic method by 3.9% on HOTA metric and 6.1% on IDF1 metric. On SportsMOT, LAID also achieves the best score on HOTA metric. By holding low training cost, strong tracking capabilities, and an elegant end-to-end approach all at once, LAID presents a forward-looking direction for the field. Copyright © 2024, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Smart Energy system Based on Machine Learning 10

Evaluation of Smart Energy System Based on Machine Learning

引用

10th IEEE Data Driven control and Learning systems Conference, DDCLS 2021

作者： Cheng, Xuran Chai, Lin School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering and School of Automation Southeast University Nanjing210096 China

ISBN: (纸本)9781665424233

In the context of the gradual shortage of fossil energy and serious pollution, the voice of energy transformation is increasing year by year. With the development of Internet and artificial intelligence, the smart energy is getting more and more attention, and it is also the key direction of the upgrading of the world energy industry. In this process, in order to better understand its development and effectively guide the future construction and development of smart energy, appropriate and reasonable evaluation is essential. In the past few years, some researchers have put forward some evaluation methods for smart energy systems, and have achieved some good results. However, only traditional evaluation methods are used which are more subjective. Therefore, the application of machine learning method in the evaluation of smart energy system is worth trying and studying. Starting from the requirements of energy system and human development, this paper first introduces the emergence and development of smart energy and its evaluation methods. Simultaneously indicating the necessity of evaluation. Then the formation of the evaluation index system is briefly introduced. Secondly, machine learning algorithm models such as support vector machines, decision trees, and BP neural networks used are introduced respectively. Finally, experiments are carried out to train the model, and then comparing and analyzing the results. The final results show that the machine learning method plays a good role in the research of smart energy system evaluation, which is worthy of further research. © 2021 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Scheduling optimization of silicon single crystal production process based on adaptive improved particle swarm optimization

Scheduling optimization of silicon single crystal production...

引用

2021 China Automation Congress, CAC 2021

作者： Kang, Lu Liu, Ding Wu, Yali Ping, Guozheng School of Automation and Information Engineering Xi'an University of Technology National and Local Joint Engineering Research Center of Crystal Growth Equipment and System Integration Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an710048 China School of Automation and Information Engineering Xi'an University of Technology National and Local Joint Engineering Research Center of Crystal Growth Xi'an University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an710048 China School of Automation and Information Engineering Xi'an University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an710048 China

ISBN: (纸本)9781665426473

Aiming at the potential safety hazards of silicon single crystal production enterprises in the process of multi-furnace silicon single crystal production, and considering the maximum power load requirements in actual enterprises, a silicon single crystal production process scheduling model with the goal of minimizing the maximum completion time was established. Based on this model, an adaptive improved particle swarm optimization algorithm (Adaptive GPSO) is proposed to solve it. The algorithm retains the individual optimal value and global optimal value of the particle swarm algorithm, and introduces the crossover operation and mutation operation in the genetic algorithm to improve the new individual generation mechanism. At the same time, it performs dynamic iterative calculations on the mutation probability and crossover probability to avoid the algorithm fall into the local optimum, and improve the diversity and convergence of the algorithm. By solving different scales scheduling problems of silicon single crystal production process, the experiments on real-world data shows that the feasibility and effectiveness of the proposed algorithm. © 2021 IEEE

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Health Condition Monitoring of Satellite Momentum Wheel Bearing Based on Canonical Variable Analysis and Sliding Interval Variance

Health Condition Monitoring of Satellite Momentum Wheel Bear...

引用

Industrial Cyber-Physical systems (ICPS)

作者： Sirui Du Shumei Zhang Yang Zhao Tianjin Key Laboratory of Process Measurement and Control School of Electrical and Information Engineering Tianjin University Tianjin China Institute of Spacecraft System Engineering China Academy of Space Technology Beijing China

With the rapid development of space technology, the demand for satellite reliability is getting higher and higher. Momentum wheel is a key component of satellite attitude control system, and its reliability is an important factor affecting the life of satellite. The condition monitoring of momentum wheel bearing (MWB) is of great significance to ensure the long life and high reliable operation of the satellite. In this paper, a new monitoring method based on multivariate statistics and canonical variable analysis (CVA) is proposed, and a new health degree function is defined from both dynamic and static aspects. First, the time-frequency domain analysis technique is used to extract the features of MWB in time domain, frequency domain and time-frequency domain, and the multi-domain high-dimensional health condition feature set is constructed. Then, in order to reduce the complexity of the problem, feature reduction is realized based on CVA. On the basis of considering steady-state error and sliding interval variance (SIV), the health degree (HD) characterizing the performance condition of MWB is defined. Finally, the experimental results based on the bearing test-bed show that the proposed method is feasible and effective, and the data-driven health condition monitoring of satellite momentum wheel bearing is realized.

关键词： Condition monitoring Time-frequency analysis Analytical models Satellites Wheels Feature extraction complexity theory

来源：评论

学校读者我要写书评

暂无评论

key Technologies of IoT Intelligent Sensing Terminal for Smart Energy

Key Technologies of IoT Intelligent Sensing Terminal for Sma...

引用

2022 IEEE International Conference on High Voltage engineering and Applications, ICHVE 2022

作者： Liu, Siyang Mao, Yuxing Long, Yunfeng Pan, Jianyu Jiang, Tianyan Cao, Min State Key Laboratory of Power Equipment & System Security and New Technology School of Electrical Engineering Chongqing University Chongqing China Yunnan Key Laboratory of Green Energy Electric Power Measurement Digitalization Control and Protection Electric Power Research Instute Yunnan Power Grid Co. Ltd. Yunnan Kunming China

ISBN: (数字)9781665407502

ISBN: (纸本)9781665407502

To build a smart energy system, we must first deploy a fully aware terminal layer to connect all energy things through perception. This paper proposes key technologies of IoT intelligent sensing terminal for smart energy. Firstly, smart energy Internet of things function is given to analyze the architecture for smart energy Internet of things. Analysis of Internet of Things terminal ecosystem is located. Finally, the key technologies including resource unified modeling, hardware and software system of Internet of things terminal are proposed. Customized design of intelligent sensing terminal is given to manufacture intelligent sensing terminal for different application scenarios of smart energy. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Close-range Hot Spot Detection based on K-neighbor Algorithm and Experiment on Hot Spot Effect 4

Close-range Hot Spot Detection based on K-neighbor Algorithm...

引用

2022 4th International Conference on Energy systems and Electrical Power, ICESEP 2022

作者： Na, ZhiXiong Wang, Dong Wang, ZiYue Wang, Jian Tang, Yu Zhang, ZiHan State Grid e-commerce Co. Ltd Beijing100053 China State Grid Tianjin Electric Power Company China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University Nanjing210096 China

Abnormalities caused by the hot spot effect are very common in the application of photovoltaic modules, which seriously affect the life and power generation efficiency of photovoltaic modules. Therefore, the study of hot spot effect is of great significance to the development of photovoltaic industry in the future. By analyzing the hot spot effect and its causes, this paper lists possible factors that may affect the hot spot effect, uses the K-proximity algorithm for hot spot detection to classify the near-field infrared images obtained in photovoltaic power plants, and designs experiments to explore the influence of several factors on the hot spot effect, the influence characteristics of the shading area and the types of shading objects are deeply explored, and finally a certain summary is made. © 2022 Institute of Physics Publishing. All rights reserved.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

Glare suppression focusing method for high polarization purity focus generation

引用

Optics letters 2025年第12期50卷 4086-4089页

作者： Kaige Liu Hengkang Zhang Tianhao Zhang Bin Zhang Xing Fu Qiang Yuan Qiang Liu Key Laboratory of Photonics Control Technology (Tsinghua University) Ministry of Education Beijing 100084 China Tsinghua University State Key Laboratory of Precision Measurement Technology and Instruments Department of Precision Instrument Beijing 100084 China Research Center of Laser Fusion China Academy of Engineering Physics Mianyang 621900 China Beijing Institute of Control Engineering Beijing 100190 China Beijing Institute of Electronic System Engineering Beijing 100854 China fuxing@*** yuanqiang2003@***

When a light beam propagates through strongly scattering media, not only does its amplitude and phase distribution become scrambled, but its polarization state also becomes randomized. This depolarization effect imposes significant limitations on the applications of vector light fields in scattering environments. In this Letter, we propose a glare suppression-based method for achieving highly polarization-pure scattering light focusing. For the target polarization direction, we employ the transmission matrix method to calculate the optimized focusing mask. While in its orthogonal-polarization direction, we utilize singular value decomposition (SVD) of the transmission matrix to identify low-eigenvalue transmission channels and reconstruct the focusing mask. Experimentally, we demonstrate over 40-fold enhancement in focal polarization ratio compared to a conventional method. We believe our method provides an effective solution for controlling full-polarization output using single-polarization input, which will be of interest in the fields of wavefront shaping and structured light.

关键词： Light beams Matrix methods Optical fields Phase conjugation Scattering media Spatial light modulators

来源：评论

学校读者我要写书评

暂无评论

Prediction of exosomal piRNAs based on deep learning for sequence embedding with attention mechanism

Prediction of exosomal piRNAs based on deep learning for seq...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Liu, Yajun Ding, Yulian Li, Aimin Fei, Rong Guo, Xie Wu, Fangxiang Xi'an University of Technology Shaanxi Key Laboratory for Network Computing and Security Technology Xi'an China University of Saskatchewan Division of Biomedical Engineering Saskatoon Canada Xi'an University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an China University of Saskatchewan Division of Biomedical Engineering Department of Computer Science Department of Mechanical Engineering Saskatoon Canada

ISBN: (纸本)9781665468190

PIWI-interacting RNAs (piRNAs) are a type of small non-coding RNAs which bind with the PIWI proteins to exert biological effects in various regulatory mechanisms. A growing amount of evidence reveals that exosomal piRNAs are potential biomarkers for diagnosis and treatment of complex diseases. Effective methods for the prediction of exosomal piRNAs are the foundation of piRNA functional research. In this study, we propose an end-to-end deep network for identifying exosomal piRNAs based on features learned from natural language processing (NLP) models for sequence embedding with attention mechanism. First, a benchmark dataset is constructed by processing piRNA subcellular localization annotated data and sequence data. Moreover, bagging positive unlabeled learning is applied to get the reliable negative set. Finally, we treat a piRNA sequence as a sentence and its k-mer subsequence as a token. Sequence embedding models with self-attention mechanism is designed to extract features from exosome piRNA sequences, which are used for the prediction task. Compared with three competing methods, our model achieves the best performance and reveals the key factors of exosomal piRNA sequences by the attention mechanism. Our model characterizes exosomal piRNAs and could be beneficial for researchers to investigate exosomal piRNAs' functions. © 2022 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

ReaxFF molecular dynamic simulation of primary and secondary reactions involving in sub-bituminous coal pyrolysis for tar production

引用

Carbon Resources Conversion 2021年第1期4卷 230-238页

作者： Yanan Qian Jin-Hui Zhan Wei Xu Zhennan Han Xiaoxing Liu Guangwen Xu State Key Laboratory of Safety and Control for Chemicals SINOPEC Research Institute of Safety Engineering Co.Ltd.Qingdao 266071China State Key Laboratory of Multiphase Complex System Institute of Process EngineeringChinese Academy of SciencesBeijing 100190China Key Laboratory on Resources Chemicals and Materials of Ministry of Education of China Shenyang University of Chemical TechnologyShenyang 110142China

ReaxFF molecular dynamic simulation combined with experimental verification was performed to understand the overall reaction mechanism,especially the primary and secondary reactions involving in tar formation of sub-bituminous coal *** relationship at atomic level is clarified between bond breakage of functional groups and products generation,revealing that the amount and order in forming each product are subject to the number of corresponding functional groups and their bond energies *** primary breakage of-C-O-and-C-C-bridge-bonds present in initial coal macromolecular generates molecular of heavy tar,whereas heavy tar can be converted into light tar through cracking side chain of aromatic rings and cyclic hydrocarbons at increased pyrolysis *** very high temperatures the cracking of short-chain hydrocarbons and residual atoms connecting to aromatic rings further occurs to generate light tar and *** remaining aromatic-ring fragments of heavy tar are likely cross-linked to form ***,the simultaneous evolution tendency of tar yield and tar quality under different pyrolysis temperatures and heating rates is obtained at molecular *** obtaining high yield and quality of tar,appropriately high temperature as well as suitable heating rate are needed to compromise the high yield of primary tar and high quality of secondarily upgraded products.

关键词： ReaxFF MD simulation Sub-bituminous coal pyrolysis Reaction paths Primary formation Secondary upgrading

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：