检索结果-内蒙古大学图书馆

6th IEEE International Conference on Electronic Information and Communication Technology, ICEICT 2023

作者： Yu, Canping Li, Li Li, Yingsong Sun, Dazhi Li, Liping Huang, Zhixiang Loh, Tian Hong Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China Beijing101399 China National Physical Laboratory Electromagnetic and Eletrochemical Technologies Department Middlesex Teddington United Kingdom

ISBN: (纸本)9798350399059

Reconfigurable intelligent surface (RIS) can control the phase of reflected signals, and has become a hotspot in the field of wireless communication. In this paper, we propose a direction-of-arrival (DOA) estimation algorithm for RIS assisted multi-user wireless communication systems with squared-sine error criterion and Lawson norm constraint. This algorithm utilizes the sparsity of the signal and can achieve fast and accurate DOA estimation under the interference of impulsive noises. To suppress the line-of-sight (LOS) interference and thus to maximize the received signal-to-interference-plus-noise ratio (SINR), we also propose a random optimal phase selection (ROPS) technique to design the control matrix of RIS elements. The simulation results show that the proposed algorithm performs better than the existing methods. © 2023 IEEE.

关键词： Impulse noise

来源：评论

学校读者我要写书评

暂无评论

Expanding Hyperspherical Space for Few-Shot Class-Incremental Learning

Expanding Hyperspherical Space for Few-Shot Class-Incrementa...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Yao Deng Xiang Xiang Key Lab of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

In today’s ever-changing world, the ability of machine learning models to continually learn new data without forgetting previous knowledge is of utmost importance. However, in the scenario of few-shot class-incremental learning (FSCIL), where models have limited access to new instances, this task becomes even more challenging. Current methods use prototypes as a replacement for classifiers, where the cosine similarity of instances to these prototypes is used for prediction. However, we have identified that the embedding space created by using the relu activation function is incomplete and crowded for future classes. To address this issue, we propose the Expanding Hyperspherical Space (EHS) method for FSCIL. In EHS, we utilize an odd-symmetric activation function to ensure the completeness and symmetry of embedding space. Additionally, we specify a region for base classes and reserve space for unseen future classes, which increases the distance between class distributions. Pseudo instances are also used to enable the model to anticipate possible upcoming samples. During inference, we provide rectification to the confidence to prevent bias towards base classes. We conducted experiments on benchmark datasets such as CIFAR100 and miniimageNet, which demonstrate that our proposed method achieves state-of-the-art performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A critical review of direct laser additive manufacturing ceramics

引用

International Journal of Minerals,Metallurgy and Materials 2024年第12期31卷 2607-2626页

作者： Dake Zhao Guijun Bi Jie Chen WaiMeng Quach Ran Feng Antti Salminen Fangyong Niu Institute of Intelligent Manufacturing Guangdong Academy of SciencesGuangzhou 510070China Guangdong Key Laboratory of Modern Control Technology Guangzhou 510070China Department of Civil and Environmental Engineering University of MacaoMacao 310058China School of Civil and Environmental Engineering Harbin Institute of TechnologyShenzhen 518055China Department of Mechanical and Materials Engineering Faculty of TechnologyUniversity of TurkuFI-20014 Turun yliopistoFinland Key Laboratory for Precision and Non-traditional Machining Technology of Ministry of Education Dalian University of TechnologyDalian 116000China

The urgent need for integrated molding and sintering across various industries has inspired the development of additive manu-facturing(AM)*** the different AM technologies,direct laser additive manufacturing(DLAM)stands out as a group of highly promising technology for flexibly manufacturing ceramics without molds and adhesives in a single *** the last decade,sig-nificant and encouraging progress has been accomplished in DLAM of high-performance ceramics,including Al_(2)O_(3),ZrO_(2),Al_(2)O_(3)/ZrO_(2),SiC,and ***,high-performance ceramics fabricated by DLAM face challenges such as formation of pores and cracks and resultant low mechanical properties,hindering their practical application in high-end *** improvements are necessary be-fore they can be widely *** such as field-assisted techniques and post-processing can be employed to address these chal-lenges,but a more systematic review is *** work aims to critically review the advancements in direct selective laser sintering/melting(SLS/SLM)and laser directed energy deposition(LDED)for various ceramic material ***,it provides an overview of the current challenges,future research opportunities,and potential applications associated with DLAM of high-perform-ance ceramics.

关键词： 3D printing laser additive manufacturing ceramics quality microstructure mechanical properties

来源：评论

学校读者我要写书评

暂无评论

Power Switching Based on Trajectory Planning and Sliding Mode control for Solid Oxide Fuel Cell Systems

引用

Journal of Modern Power Systems and Clean Energy 2024年第6期12卷 1968-1979页

作者： Zhen Wang Guoqiang Liu Xingbo Liu Jie Wang Zhiyang Jin Xiaowei Fu Zhuo Wang Bing Jin Zhonghua Deng Xi Li Key Laboratory of Imaging Processing and Intelligent Control of Ministry of Education School of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhanChina Research Institute of Huazhong University of Science and Technology in Shenzhen ShenzhenChina Hubei Huazhong Electric Power Technology Development Co. Ltd.WuhanChina School of Computer Science and Technology Wuhan University of Science and TechnologyWuhanChina School of Artificial Intelligence and Automation Huazhong University of Science and TechnologyWuhanChinaand he is also with the Wuhan Huamao Automation Co.Ltd.WuhanChina

To improve the safety of the solid oxide fuel cell(SOFC)systems and avoid the generation of large amounts of pollutants during power switching,this paper designs a power switching strategy based on trajectory planning and sliding mode control(TP-SMC).The design elements of the power switching strategy are proposed through simulation analysis at ***,based on the gas transmission delay time and the change of gas flow obtained from testing,trajectory planning(TP)is *** with other power switching strategies,it has been proven that the power switching strategy based on TP has significantly better control ***-thermore,considering the shortcomings and problems of TP in practical application,this paper introduces sliding mode control(SMC)on the basis of TP to improve the power switching *** final simulation results also prove that the TP-SMC can effectively suppress the impact of uncertainty in gas flow and gas transmission delay *** with TP,TP-SMC can ensure that under uncertain conditions,the SOFC system does not experience fuel starvation and temperature exceeding limit during power ***,the NOx emissions are also within the normal and acceptable *** paper can guide the power switching process of the actual SOFC sys-tems to avoid safety issues and excessive generation of NOx,which is very helpful for improving the performance and ser-vice lifeof the SOFCsystems.

关键词： Solid oxide fuel cell(SOFC)system power switching safety NOx emission trajectory planning sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Stabilization of switched systems with unstable modes via mode-partition-dependent ADT

引用

Journal of the Franklin Institute 2023年第2期360卷 1308-1326页

作者： Jin, Cui-Li Wang, Qing-Guo Wang, Rui Wu, Di Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education and School of Control Science and Engineering Dalian University of Technology Dalian116024 China Institute of Artificial Intelligence and Future Networks Beijing Normal University at ZhuhaiGuangdong Key Lab of AI and Multi-Modal Data Processing BNU-HKBU United International College Zhuhai519087 China Key Laboratory of Advanced Technology for Aerospace Vehicles Liaoning Province and School of Aeronautics and Astronautics Dalian University of Technology Dalian116024 China

This paper concerns the stability of switched systems orchestrating between unstable modes. First, a mode partition is applied to select stabilizing switching from the switching between modes from different subsets. Second, a piecewise Lyapunov-like function is applied to decline at stabilizing switching times. Then, the stability criteria build on mode-partition-dependent average dwell time by collecting enough stabilizing switching behavior to stabilize the destabilizing switching behavior and unstable modes. Finally, the simulation verification shows the feasibility and effectiveness of the method. © 2022 The Franklin Institute

关键词： Stability criteria

来源：评论

学校读者我要写书评

暂无评论

Cross-Domain Few-Shot Incremental Learning for Point-Cloud Recognition

Cross-Domain Few-Shot Incremental Learning for Point-Cloud R...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Yuwen Tan Xiang Xiang Key Lab of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

Sensing 3D objects is critical when 2D object recognition is not accessible. A robot pre-trained on a large point-cloud dataset will encounter unseen classes of 3D objects after deploying it. Therefore, the robot should be able to learn continuously in real-world scenarios. Few-shot class-incremental learning (FSCIL) requires the model to learn from few-shot new examples continually and not forget past classes. However, there is an implicit but strong assumption in the FSCIL that the distribution of the base and incremental classes is the same. In this paper, we focus on cross-domain FSCIL for point-cloud recognition. We decompose the catastrophic forgetting into base class forgetting and incremental class forgetting and alleviate them separately. We utilize the base model to discriminate base samples and new samples by treating base samples as in-distribution samples, and new objects as out-of-distribution samples. We retain the base model to avoid catastrophic forgetting of base classes and train an extra domain-specific module for all new samples to adapt to new classes. At inference, we first discriminate whether the sample belongs to the base class or the new class. Once classified at the model level, test samples are then passed to the corresponding model for class-level classification. To better mitigate the forgetting of new classes, we adopt the soft label and hard label replay together. Extensive experiments on synthetic-to-real incremental 3D datasets show that our proposed method can balance the performance between the base and new objects and outperforms the previous state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Streaming-Data-Driven Multi-Objective Optimal Operation for Ammonia-based Integrated Energy Chemical Systems: An Event-Triggered Scheme 42

Streaming-Data-Driven Multi-Objective Optimal Operation for ...

引用

42nd Chinese control Conference, CCC 2023

作者： Li, Longyan Ning, Chao Shanghai Jiao Tong University Department of Automation Shanghai200240 China East China University of Science and Technology Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of Education Shanghai200237 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China

ISBN: (纸本)9789887581543

As an important component in the industry sector, the integrated energy chemical system is inescapably responsible for carbon reduction in addition to economic and reliability performance. We propose a novel streaming-data-driven multi-objective optimal operation for ammonia-based integrated energy chemical systems (AIECS). In the day ahead scheduling, a detailed mathematical model for AIECS is presented, upon which a multi-objective optimization considering cost, CO2 emission and reliability is established. For the intra-day operation, an event-triggered mechanism is firstly developed in the real-time operation of AIECS, and it enables the AIECS to be risk-aware just in time. By monitoring the difference between the predicted state of charge and the capacity limitations of battery, the AIECS identifies whether it is in hazardous regime. Then, the intelligent switch between certainty equivalence model predictive control and online-learning based distributionally robust model predictive control is proposed, such that their respective advantages are leveraged. Case studies demonstrate that the proposed approach guarantees the system safety, and brings good revenue. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Data-driven Fault Diagnosis Method Based on Fusion of Multi-direction and Multi-source Signals 5

Data-driven Fault Diagnosis Method Based on Fusion of Multi-...

引用

5th International Conference on intelligent Autonomous Systems, ICoIAS 2022

作者： Yang, Yang Wang, Junda Li, Ning Shanghai Jiaotong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Department of Automation Shanghai China

ISBN: (数字)9781665498388

ISBN: (纸本)9781665498388

As a pivotal mechanical component of turbine drive-chain, gearbox suffers from various accidents and fault diagnosis could remarkably enhance its reliability and maintain running safety and lifetime. Vibration-based analysis on single-channel is mainly adopted in previous diagnostic, which cannot catch full vibration inner information in gearbox sensors and bring model performance down. In this paper, a novel method based on the fusion of multi-direction and multi-source signals and the convolutional neural network (MDMS-CNN) is presented. This method can obtain multi-dimensional feature maps from MDMS and preserve the time correlation among different signal sequences. First, features from MDMS are extracted via a corrosion conversion method that converts signals into two-dimensional (2-D) gray images. Then, homologous images are spliced into same channels, while heterogeneous images are superimposed to different channels. Finally, fusion features are input into CNN for fault classification. In experiments, the method is validated on a gearbox diagnosis case. Results have shown that the proposed method achieves 99.86% recognition accuracy and faster convergence speed compared to others. © 2022 IEEE.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Research on Temperature Correction Method of Insulator Infrared image Based on Monocular Distance Measurement 1st

Research on Temperature Correction Method of Insulator Infra...

引用

1st Electrical Artificial Intelligence Conference, EAIC 2024

作者： Han, Sheng Li, Yufeng Dong, Jialong Li, Zhimin Key Laboratory of Cleaner Intelligent Control on Coal and Electricity Ministry of Education Taiyuan University of Technology Shanxi030024 China Chongqing University Chongqing400044 China

ISBN: (纸本)9789819640621

Insulator defects can lead to insulation performance degradation and structural damage, affecting the regular operation of the power transmission and transformation system. It is important to Detect anomalies promptly, which can help prevent such accidents to the greatest extent possible. Temperature is one of the key indicators of the condition of insulators, and infrared thermal imaging technology is widely applied, which can detect latent defects in insulators. One of the critical parameters for infrared temperature measurement is target distance. However, infrared cameras cannot set distance parameters for different targets within an image, which presents challenges for inspecting multiple insulator strings based on one image. This paper proposes a multi-distance parameter temperature correction method based on monocular distance measurement algorithms to solve the problem. First, this paper uses a monocular distance measurement model to get the distance automatically. Then, this paper proposes a temperature-distance correction method to correct the temperature. Finally, re-image with the corrected temperature. The test results show that the average temperature correction is 0.6K, indicating that the correction is non-negligible. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Thermography (imaging)

来源：评论

学校读者我要写书评

暂无评论

ACBL:Attentive CNN-BiLSTM Model For Trajectory Prediction 43

ACBL:Attentive CNN-BiLSTM Model For Trajectory Prediction

引用

43rd Chinese control Conference, CCC 2024

作者： Yang, Gan Wang, Guangwei Li, Yichen Yu, Wenbin Shanghai Jiao Tong University Department of Automation Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Tianjin Navigation Instruments Research Institute Tianjin300131 China

ISBN: (纸本)9789887581581

Predicting the future trajectory of a target becomes particularly challenging while dealing with occlusion conditions, where current information is unavailable, and historical data becomes the only basis for prediction. In this paper, we propose a trajectory prediction model that utilizes scaled dot product attention mechanism, a convolution neural network, and a bidirectional long short term memory network. The scaled dot product attention mechanism gauges the impact of historical sequences, while the convolution neural network extracts intricate feature information from these sequences. Subsequently, these data is fed into the bidirectional long short term memory network to forecast the target's navigation path. Experimental results highlight that the Attentive CNN-BiLSTM (ACBL) network which we proposed has lower root mean square error (RMSE) by 23 % on average than current methods. © 2024 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Convolutional neural networks

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：