检索结果-内蒙古大学图书馆

arXiv 2023年

作者： He, Yong Yu, Hongshan Yang, Zhengeng Sun, Wei Feng, Mingtao Mian, Ajmal The National Engineering Laboratory for Robot Visual Perception and Control Technology College of Electrical and Information Engineering Hunan University Lushan South Rd. Yuelu Dist. Changsha410082 China The School of Computer Science and Technology Xidian University Xi’an710071 China The Department of Computer Science The University of Western Australia PerthWA6009 Australia

Local features and contextual dependencies are crucial for 3D point cloud analysis. Many works have been devoted to designing better local convolutional kernels that exploit the contextual dependencies. However, current point convolutions lack robustness to varying point cloud density. Moreover, contextual modeling is dominated by non-local or self-attention models which are computationally expensive. To solve these problems, we propose density adaptive convolution, coined DAConv. The key idea is to adaptively learn the convolutional weights from geometric connections obtained from the point density and position. To extract precise context dependencies with fewer computations, we propose an interactive attention module (IAM) that embeds spatial information into channel attention along different spatial directions. DAConv and IAM are integrated in a hierarchical network architecture to achieve local density and contextual direction-aware learning for point cloud analysis. Experiments show that DAConv is significantly more robust to point density compared to existing methods and extensive comparisons on challenging 3D point cloud datasets show that our network achieves state-of-the-art classification results of 93.6% on ModelNet40, competitive semantic segmentation results of 68.71% mIoU on S3DIS and part segmentation results of 86.7% mIoU on ShapeNet. Copyright © 2023, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach of Energy and Reserve Scheduling for Hybrid Power Systems: Frequency Security Constraints

SSRN

引用

SSRN 2023年

作者： Zhang, Tengxi Wang, Shunjiang Guo, Ren Wang, Wentao Cui, Jia School of Control and Computer Engineering North China Electric Power University Beijing102206 China State Grid Liaoning Electric Power Supply Company Limited Shenyang110004 China School of Electrical Engineering Shenyang University of Technology Shenyang110870 China

The increasing incorporation of solar and wind energy sources into the power system results in a diminishing power system inertia. This gives rise to challenges in frequency dynamics, thereby compromising the security of power system operation. This paper proposes a novel scheduling approach for hybrid power systems (HyPS) considering frequency security, which accounts for the time-varying characteristics related to frequency security requirements and interdependencies among various components, including generation units and the delivery network. Firstly, the optimal objective is to minimize overall operational costs and the pressure on energy delivery, ensuring the reserve capacities for fast frequency regulation remain within the predefined limits. Secondly, the frequency constrained unit commitment (FCUC) problem is formulated as a Markov decision process (MDP), and a deep reinforcement learning (DRL) framework is integrated to correct the advanced scheduling scheme in real-time. Thirdly, the coordinated scheduling scheme dynamically adjusts to operational events like fluctuations and line failures in the HyPS by employing the reward function of a comprehensive assessment. Finally, numerical results demonstrate the practicality of the novel coordinated scheduling approach for hybrid power systems through simulations in the Grid2Op environment. The frequency security margin of the HyPS is capable of remaining within the predefined range across diverse scenarios, including fluctuations in power demand, renewable energy variations, and power line failures. Integrates PE-interfaced renewable energy sources with conventional synchronous units as a hybrid power system for improving frequency security requirements. © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Prediction Method of Truck Travel Time in Open Pit Mines Based on LSTM Model 42

Prediction Method of Truck Travel Time in Open Pit Mines Bas...

引用

42nd Chinese control Conference, CCC 2023

作者： Ao, Mengting Li, Changhe Yang, Shengxiang School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan430074 China School of Computer Science and Informatics De Montfort University LeicesterLE1 9BH United Kingdom

ISBN: (纸本)9789887581543

Aiming at the prediction of truck travel time in open pit mines, we established a prediction model based on long short-term memory(LSTM). This model fully accounts for 11 factors, including the nature of trucks, weather, road conditions, and driver's behaviors, as well as the influence of neighbor road segments in the route on the current predicted road segment. The experiment shows that the error of the LSTM prediction model is significantly reduced compared with SVR and BP models. In addition, the maximum absolute mean error under different conditions is less than 12 seconds. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Multi-step Ahead Time Series Forecasting Based on the Improved Process Neural Networks 9th

Multi-step Ahead Time Series Forecasting Based on the Improv...

引用

9th International Conference on computer engineering and Networks, CENet2019

作者： Shao, Haijian Hu, Chunlong Deng, Xing Jiang, Dengbiao School of Computer Science and Engineering Jiangsu University of Science and Technology JiangsuZhenjiang China Key Laboratory of Measurement and Control for CSE School of Automation Ministry of Education Southeast University Nanjing China

ISBN: (纸本)9789811537523

This paper proposes a multi-step ahead time series forecasting based on the improved process neural network. The intelligent algorithm particle swarm optimization (PSO) is used to overcome the potential disadvantages of the neural network, such as slow convergence speed and derivative local minima. Firstly, the theoretical analysis of the PSO is given to optimize the multilayer perceptron (MLP) neural network architecture. Secondly, the theoretical analysis and processing flow about the MLP architecture optimization is given. Thirdly, the performance criteria are applied to verify the performance of the proposed approach. Finally, the experimental evaluation based on a typically chaotic time series with rich spectrum information is utilized to demonstrate that the proposed approach has comparative results and superior on forecasting accuracy comparing to the traditional methods. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Time series analysis

来源：评论

学校读者我要写书评

暂无评论

Recursively Feasible Data-Driven Distributionally Robust Model Predictive control with Additive Disturbances

arXiv

引用

arXiv 2022年

作者： Mark, Christoph Liu, Steven Institute of Control Systems Department of Electrical and Computer Engineering University of Kaiserslautern Erwin-Schrödinger-Str. 12 Kaiserslautern67663 Germany

In this paper we propose a data-driven distributionally robust Model Predictive control framework for constrained stochastic systems with unbounded additive disturbances. Recursive feasibility is ensured by optimizing over a linearly interpolated initial state constraint in combination with a simplified affine disturbance feedback policy. We consider a moment-based ambiguity set with data-driven radius for the second moment of the disturbance, where we derive a minimum number of samples in order to ensure user-given confidence bounds on the chance constraints and closed-loop performance. The paper closes with a numerical example, highlighting the performance gain and chance constraint satisfaction based on different sample sizes. Copyright © 2022, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

EMG Onset and Offset Detection via a Modified Threshold Crossings Algorithm

EMG Onset and Offset Detection via a Modified Threshold Cros...

引用

Mediterranean Conference on control and Automation (MED)

作者： Vasiliki Theofili Nikolaidi George Andrikopoulos Dimitris Tsipianitis Dimosthenis Kazakos Department of Electrical and Computer Engineering University of Patras Greece Unit of Mechatronics and Embedded Control Systems KTH Royal Institute of Technology Stockholm Sweden

ISBN: (数字)9781665406734

ISBN: (纸本)9781665406741

In this study, we propose a novel family of onset and offset detection algorithms for electromyographic (EMG) signals, based on the Teager-Kaiser Energy Operator (TKEO). These algorithms are derived from an existing double-threshold statistical detector, which is modified to use Shifted Skew Log Laplace Distribution (SSLLD) probabilities and likelihoods to take advantage of the improved TKEO SNR ratio. The performance of the proposed algorithms are compared against existing approaches on synthetic EMG signals generated using an heteroscedastic autoregressive Gaussian model.

关键词： Automation Detectors Benchmark testing Probability Approximation algorithms Electromyography Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Cascade Filtering System for fNIRS Data Analysis

Machine Learning-Based Cascade Filtering System for fNIRS Da...

引用

2023 Progress in Applied Electrical engineering, PAEE 2023

作者： Pelc, Mariusz Mikolajewski, Dariusz Ruotsalo, Tuukka Leiva, Luis A. Sudol, Adam Gorzelanczyk, Edward Jacek Lysiak, Adam Kawala-Sterniuk, Aleksandra Opole University of Technology Faculty of Electrical Engineering Automatic Control and Informatics Opole Poland Institute of Computer Science Kazimierz Wielki University Bydgoszcz Poland University of Helsinki Finland University of Copenhagen Denmark Faulty of Natural and Technical Sciences University of Opole Opole Poland University of Opole Faculty of Natural and Technical Sciences Opole Poland Institute of Philosophy Kazimierz Wielki University Bydgoszcz Poland

ISBN: (纸本)9798350316254

This paper presents a preliminary study on the use of machine learning-based methods to select the appropriate parameters of cascade filters in the analysis of brain signals recorded using functional infrared spectroscopy (fNIRS), which shows the level of oxygenation in the brain and, unlike EEG signals (showing electrical brain activity), are less prone to potential interference, disturbances or artifacts occurrence. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Risk Identification Method for Smuggled Frozen Meat in Urban Public Safety Awareness and Early Warning

Risk Identification Method for Smuggled Frozen Meat in Urban...

引用

2023 International Conference on Intelligent Communication and Networking, ICN 2023

作者： Li, Xueru Zhang, Yan Liu, Lingjie Tian, Ye Zhang, Yue Harbin Engineering University College of Computer Science and Technology Harbin China China Industrial Control Systems Cyber Emergency Response Team Beijing China Environment and Food and Drug Crime Investigation Detachment of Hangzhou Public Security Bureau Hangzhou China Xidian University Hangzhou Institute of Technology Hangzhou China Key Laboratory of Peace-Building Big Data of Zhejiang Province Zhejiang China

ISBN: (纸本)9798350357677

With the continuous growth in demand for meat and frozen products in the cold chain market, illegally smuggled frozen goods have quickly entered the market due to their low prices, leading to a series of food safety issues. This article proposes a method for identifying the risks of smuggled frozen meat for urban public safety awareness using the YOLOv7 model. The YOLOv7 model is used to detect data captured at various traffic checkpoints, obtaining spatiotemporal information of frozen goods vehicles. This information is then combined with map data to generate vehicle trajectory information. The trajectory similarity between the frozen vehicle trajectories and the specialized database of frozen transportation routes is analyzed using the EDwP distance algorithm. The EDwP algorithm employs a threshold-free approach, dynamically interpolating using the concept of projection, and automatically adapting to non-uniform sampling rates to address the issue of inconsistent trajectory data sampling rates. The experimental results of the YOLOv7-EDwP algorithm were verified by verifying the alerts generated in the recent period through on-site verification by a third-party inspection agency, with a recognition accuracy of 90.77%. This holds significant significance in the detection and warning of smuggled frozen meat. © 2023 IEEE.

关键词： Transportation routes

来源：评论

学校读者我要写书评

暂无评论

Physics-Informed Neural Networks: A Step Towards Data-Driven Optimization of Additive Manufacturing

Physics-Informed Neural Networks: A Step Towards Data-Driven...

引用

International Conference on Emerging Technologies and Factory Automation (ETFA)

作者： Fabio Depaoli Stefano Felicioni Francesco Ponzio Alessandro Aliberti Enrico Macii Federica Bondioli Elisa Padovano Santa Di Cataldo Dept. of Control and Computer Engineering Politecnico di Torino Italy Dept. of Applied Science and Technology Politecnico di Torino Italy Interuniv. Dept. of Reg. and Urban Studies and Planning Politecnico di Torino Italy

ISBN: (数字)9798350361230

ISBN: (纸本)9798350361247

Laser powder bed fusion (L-PBF) is the most popular Additive Manufacturing (AM) process for metals. It builds a 3D object layer-by-layer, by spreading metal powder on top of the previous layer and selectively melting it with a laser. Despite its many advantages, large-scale production may be hampered by the large number of process parameters and the challenges associated with their optimization. We propose an automated parameter selection approach based on process signatures extracted from a parameterized simulation of the process. Specifically, we outline a rapid data-driven simulation method based on Physics-Informed Neural Network (PINN). This approach involves training a neural network to solve the partial differential equation describing the process at varying values of a parameter of interest (for example, the laser power), thus eliminating the need for repeated Finite Elements Method (FEM) simulations. Our preliminary experiments demonstrate the feasibility of our approach.

关键词： Training Powders Three-dimensional displays Neural networks Metals Production Three-dimensional printing Finite element analysis Laser fusion Optimization

来源：评论

学校读者我要写书评

暂无评论

Efficiency Optimization of Induction Motor Using a Modified Gray Wolf Optimization

Efficiency Optimization of Induction Motor Using a Modified ...

引用

International Conference on Sciences and Techniques of Automatic control and computer engineering (STA)

作者： Oussama Zeghba Salim Chakroun Ali Aillane Research Laboratory on the Electrical Engineering University of M'Sila Algeria Laboratory of Sciences and Techniques of Automatic Control and Computer Engineering (Lab-STA) National School of Engineering of Sfax (ENIS) University of Sfax Sfax Tunisia

ISBN: (纸本)9781665482622

In this research, a method for improving the efficiency of induction motors based on the modified gray wolf optimizer (mGWO) is proposed and examined. In order to reduce the overall copper and iron losses of the machine, the efficiency improvement technique entails modifying the geometric dimensions with regard to the lower and upper bound of those parameters. A comparison between the findings achieved utilizing the mGWO and GAs approach is done, and some simulation performances are shown along with a comparison of efficiency, electric current, and torque. The approach mGWO provided good results and required less time to extract results once the simulation results were obtained using the aforementioned methods.

关键词： Energy consumption Induction motors Upper bound Torque Simulation Iron Data models

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：