检索结果-内蒙古大学图书馆

Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS), CAA Symposium on

作者： Liangcheng Wang Yang Wang Hong Zhang Yanwei Wang Ying Zheng The Belt and Road Joint Laboratory on Measurement and Control Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China School of Mechanical & Electrical Engineering Wuhan Institute of Technology Wuhan Hubei

Accurate prediction of aero-engine remaining useful life (RUL) is essential for providing reliable maintenance or alarm decisions. The extraction of degraded features has a great impact on the accuracy of RUL prediction. This paper proposes a feature fusion framework that relies on a multi-dimensional convolutional neural network (MD-CNN). First, the data of each working condition is normalized separately to extract degradation features more effectively. Subsequently, the temporal features are extracted using the one-dimensional convolutional neural network (1D-CNN), while the spatial local features are captured through the utilization of the two-dimensional convolutional neural network (2D-CNN). Finally, the long short-term memory network (LSTM) is utilized as the prediction model to establish the mapping relationship from fusion features to RUL. The result shows that the performance in predicting using the proposed method surpasses that of the existing methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Wind Power Scenario Simulation Method Considering Trend and Randomness 16th

A Wind Power Scenario Simulation Method Considering Trend an...

引用

16th Annual Conference of China Electrotechnical Society, ACCES 2021

作者： Ji, Xiu Li, Cong Xie, Beimin Wang, Yan Wang, Qisu National Local Joint Engineering Research Center for Smart Distribution Grid Measurement and Control with Safety Operation Technology Changchun130000 China School of Electrical and Information Engineering Changchun Institute of Technology Changchun130000 China Maintenance Branch State Grid Jilin Electric Power Co. Ltd Changchun130000 China

ISBN: (纸本)9789811918698

In the future, large-scale integration of new energy into the grid is an inevitable trend. In order to effectively analyze the trend and random characteristics of wind power output, a wind power scenario simulation method is proposed. It is divided into scene generation and scene reduction. In the scenario generation part, historical data is used to construct an improved wind power forecast box model, and a non-parametric kernel smooth distribution is used as a fitting function, and then a multivariate standard normal distribution matrix and inverse transform sampling method are used to generate a set of wind power output scenarios that conform to autocorrelation. In the scene reduction part, a BR scene reduction model is constructed to obtain wind power curves representing several original scene characteristics. Taking the wind power output data of the German TenneT Electric Power Company as an example, the probability calibration BS indicator is used as the quantitative evaluation standard for the generated scene, and the case analysis is carried out. Finally, it shows that the scenario simulation method is effective and reasonable, and it is also of great significance to the planning and operation of the wind power system. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Network Intrusion Detection Based on Graph Neural Network and Ensemble Learning

Network Intrusion Detection Based on Graph Neural Network an...

引用

Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS), CAA Symposium on

作者： Lina Zhang Yang Wang Minyue Wu Yanwei Wang Ying Zheng The Belt and Road Joint Laboratory on Measurement and Control Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China School of Mechanical & Electrical Engineering Wuhan Institute of Technology Wuhan China

Network technology has become an inseparable part of daily life, which is easily attacked by some criminals. Therefore, ensuring the security of network becomes an urgent problem. In the past few years, various deep learning techniques have been put forward for identifying network intrusions. However, the majority of these approaches overlook the non-Euclidean nature of relationships within network intrusion data. In this paper, graph neural network (GNN) is used to learn the relationship between data. The sample balancing module is to address the significant disparity between the number of intrusive samples and normal samples. The results obtained from the experiments indicate that the suggested approach can enhance the effectiveness of the intrusion detection system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Physics-Informed LSTM Network-Based Nonlinear Model Predictive control

Physics-Informed LSTM Network-Based Nonlinear Model Predicti...

引用

Data Driven control and Learning Systems (DDCLS)

作者： Yujing Chen Qilin Qui Hong Zhang Yanwei Wang Ying Zheng The Belt and Road Joint Laboratory on Measurement and Control Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China School of Mechanical Electrical Engineering Wuhan Institute of Technology Wuhan China

To address the problems of poor physical interpretability and huge sample size requirement when using neural networks to fit nonlinear control system models for state prediction, this paper proposes a model predictive control algorithm based on a physics-informed long short-term memory(LSTM) network. Firstly, the neural network incorporating physical information is extended to model the ordinary differential equations with variable initial states and external control quantities, which makes the network adaptable to the control task and makes the training model physically interpretable. Secondly, a network structure with a mixture of fully connected layers and LSTM layers is built by using the good learning ability of LSTM for time-series data, and the loss function is designed according to the system characteristics and prediction requirements. The trained neural network model is then used as an internal prediction model to construct a nonlinear model predictive control algorithm. Finally, taking the continuous stirring reactor system as an example, the method is verified to be able to fit the system model highly and reduce the time to reach the steady state with a small number of samples.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Computationally efficient predictive control based on ANN state-space models

arXiv

引用

arXiv 2023年

作者： Hoekstra, Jan H. Cseppento, Bence Beintema, Gerben I. Schoukens, Maarten Kollár, Zsolt Tóth, Roland Dept. of Measurement and Information Systems The Budapest University of Technology and Economics Hungary The Dept. of Electrical Engineering The Eindhoven University of Technology Netherlands Institute for Computer Science and Control Budapest Hungary

Artificial neural networks (ANN) have been shown to be flexible and effective function estimators for identification of nonlinear state-space models. However, if the resulting models are used directly for nonlinear model predictive control (NMPC), the resulting nonlinear optimization problem is often overly complex due the size of the network, requires the use of high-order observers to track the states of the ANN model, and the overall control scheme exploits little of the structural properties or available autograd tools for these models. In this paper, we propose an efficient approach to auto-convert ANN state-space models to linear parameter-varying (LPV) form and solve predictive control problems by successive solutions of linear model predictive problems, corresponding to quadratic programs (QPs). Furthermore, we show how existing ANN identification methods, such as the SUBNET method that uses a state encoder, can provide efficient implementation of MPCs. The performance of the proposed approach is demonstrated via a simulation study on an unbalanced disc system. © 2023, CC BY-SA.

关键词： Neural networks

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

Physics-Based Deep Learning Framework for Terahertz Thickness measurement of Thermal Barrier Coatings

SSRN

引用

SSRN 2023年

作者： Sun, Fengshan Cao, Binghua Fan, Mengbao Liu, Lin School of Mechatronic Engineering China University of Mining and Technology Xuzhou221116 China School of Information and Control Engineering China University of Mining and Technology Xuzhou221116 China Beijing Aerospace Institute for Metrology and Measurement Technology Beijing100076 China

A challenge in Terahertz (THz) thickness measurement of thermal barrier coatings (TBCs) is the change of refractive index due to the uneven microstructure of topcoat, which may degrade the accuracy of the time-of-flight approach. Here, we present a novel physics-based deep learning framework, a method which evolves the entire THz signals into optimal sparse features to decrease the errors of thickness measurement from the uneven microstructure and distorted THz echoes. Firstly, the basics of first three peaks with the feature of the topcoat refractive index are proved by THz transmission rules in TBCs, but there is a non-injective surjective function between the peaks and refractive index. To improve the accuracy of THz thickness measurements, a novel layer, termed as weight constraint layer is developed for assigning the weights for first three peaks with the constraint condition based on THz physics, yielding the optimal physics-based sparse features for thickness measurements. Then, an analytical model is built to generate the simulated THz traces, acting as the training dataset to minimize the expenditure of the specimen preparations. Finally, the experimental results demonstrate that the physics-based deep learning framework can enable the accurate TBCs thickness measurement. © 2023, The Authors. All rights reserved.

关键词： Thickness measurement

来源：评论

学校读者我要写书评

暂无评论

Optimal Scheduling of Multi-Energy Combined Generation System Considering Source Load Uncertainty

SSRN

引用

SSRN 2023年

作者： Chunhui, Liang Chao, Ding Xiaoyang, Zuo Jinfa, Li Qing, Guo School of Electrical and Information Engineering Changchun Institute of Technology Changchun130025 China National local joint Engineering Research Center for Measurement and Control and Safe Operation Technology of Intelligent Distribution Network Changchun130103 China Jilin Institute of Chemical Technology Jilin132022 China

In order to solve the problem of wind and light abandonment in new energy power generation system, a scheduling strategy of wind, light and fire combined power generation system including concentrating solar power (CSP) station is proposed in this paper. The day-ahead scheduling model of the combined power generation system is established with the maximum net income and the maximum load tracking ability as the optimization objectives. The fixed scene method was used to simulate the source load uncertainty. The Latin Hypercube sampling method and synchronous back substitution method were used to generate and reduce the scene, and different typical scenes were selected according to the scene probability. The combined spiral motion control strategy is added to the grasshopper optimization algorithm (GOA) to solve the scheduling model, which enhances the optimization performance of the algorithm. The effectiveness and correctness of the proposed model and the improved algorithm are verified by simulation in IEEE-30 node system. The numerical results show that the optimal scheduling strategy of multi-energy system proposed in this paper has significant functions in calming load fluctuation and improving system absorption ability. © 2023, The Authors. All rights reserved.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Capacity Configuration Optimization of Wind-Solar Combined Power Generation System Based on Improved Grasshopper Algorithm

SSRN

引用

SSRN 2023年

In this paper, a wind-solar combined power generation system is proposed in order to solve the absorption problem of new energy power generation. Based on the existing installed capacity of local wind power, a concentrating solar power (CSP) station and its energy storage system are configured, and a two-layer capacity optimization allocation method considering the incentive user response is proposed. Firstly, a two-layer capacity optimization model considering incentive user response is established. Secondly, grasshopper optimization algorithm based on embedded spiral motion control strategy was used to solve the upper configuration model, and the lower scheduling model was solved by Cplex solver. Finally, three typical scenarios are set up for simulation, and the wind power, CSP and energy storage configuration capacity are respectively given in different scenarios. The simulation results show that the addition of a CSP station can effectively improve the absorption capacity of local wind power generation system and reduce the amount of wind abandonment. The capacity optimization allocation method proposed in this paper can effectively alleviate the load peak demand, improve the optimization allocation model of wind-solar combined power generation system, make the configuration results more reasonable, and improve the economy of the system. © 2023, The Authors. All rights reserved.

关键词： Wind power

来源：评论

学校读者我要写书评

暂无评论

Reconstructing Three-Degree-of-Freedom Pose through Temporal Phase-Shifted Low-Coherence Spatial Interferograms

Reconstructing Three-Degree-of-Freedom Pose through Temporal...

引用

Pacific Rim Conference on Lasers and Electro-Optics (CLEO/Pacific Rim)

作者： Liheng Shi Jinxu Zhang Yingying GU Fangqin Gai Jing Liu Guanhao Wu Department of Precision Instrument State Key Laboratory of Precision Measurement Technology and Instruments Tsinghua University Beijing China Research Center of Opto-electronic Sensing Yangtze Delta Region Institute of Tsinghua University Zhejiang Zhejiang China Space Optoelectronic Measurement and Perception Lab. Beijing Institute of Control Engineering Beijing China National Key Laboratory of Space Intelligent Control China Academy of Space Technology Beijing China

We introduce a method for measuring three degrees of freedom using low-coherence light and temporal phase-shifting to discern position and orientation from the coherence envelope shape, enabling direct measurement wit... 详细信息

ISBN: (数字)9798350372076

ISBN: (纸本)9798350372083

关键词： Phase measurement Shape Shape measurement measurement by laser beam Coherence Position measurement Lasers and electrooptics

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：