检索结果-内蒙古大学图书馆

42nd Chinese control Conference, CCC 2023

作者： Guo, Ziang Li, Beijia Zeng, Linghong Fu, Jun Sheng, Chuang Li, Xi Huazhong University of Science and Technology School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control of Education Ministry Hubei Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen518055 China

ISBN: (纸本)9789887581543

Proton Exchange Membrane Fuel Cells(PEMFCs) are prone to decreased lifespan due to the degradation of the plat-inum(Pt) catalyst during operation. In this study, we have established a one-dimensional model to investigate the effects of different voltage conditions on Pt degradation. High potential is found to be the most significant factor affecting the degradation. Prolonged exposure to high potentials will significantly reduce the PEMFC's lifespan, and frequent voltage changes will exac-erbate the problem. To mitigate this issue, we have designed three energy management strategies with different limitations and simulated their performance in the operating scenario of a fuel-cell hybrid electric vehicle(FCHEV). The results demonstrate that strategies restricting high potential occurrences and voltage variations can effectively alleviate Pt degradation. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Proton exchange membrane fuel cells (PEMFC)

来源：评论

学校读者我要写书评

暂无评论

Path Planning Method of Unmanned Surface Vessel Based on Strategy Integration 23rd

Path Planning Method of Unmanned Surface Vessel Based on Str...

引用

23rd IFToMM China International Conference on Mechanism and Machine Science and Engineering, IFToMM CCMMS 2022

作者： Yang, Caipei Zhao, Yingqi Liu, Jie Zhou, Kaibo MOE Key Laboratory of Image Information Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China School of Civil and Hydraulic Engineering Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9789811993978

In the task of path planning, the unmanned surface vessels (USV) are required to reach the destination while avoiding obstacle. However, it is difficult for USV to prioritize the two sub-target tasks of destination arrival and obstacle avoidance in a complex dynamic environment using traditional path planning methods. Based on the above considerations, a path planning method for USVs based on strategy integration is proposed. Firstly, the path planning scenario containing dynamic obstacles and two sub-target scenarios are set up. In order to strengthen its ability to reach the destination and avoid dynamic obstacles, the dynamic obstacles and the destination are removed separately in the two sub-target scenarios. Furthermore, the model for strategy selection is trained on action decisions in sub-target scenarios through double deep Q-Network with prioritized experience replay. Finally, a framework for strategy integration is designed to optimize strategy selection for USV. The simulation results show that the proposed method achieves a good overall performance and a higher path planning success rate than the traditional path planning method. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Memristor crossbar architectures for implementing deep neural networks

引用

COMPLEX & intelligent SYSTEMS 2022年第2期8卷 787-802页

作者： Liu, Xiaoyang Zeng, Zhigang Educ Minist China Key Lab Image Proc & Intelligent Control Wuhan Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China

The paper presents memristor crossbar architectures for implementing layers in deep neural networks, including the fully connected layer, the convolutional layer, and the pooling layer. The crossbars achieve positive and negative weight values and approximately realize various nonlinear activation functions. Then the layers constructed by the crossbars are adopted to build the memristor-based multi-layer neural network (MMNN) and the memristor-based convolutional neural network (MCNN). Two kinds of in-situ weight update schemes, which are the fixed-voltage update and the approximately linear update, respectively, are used to train the networks. Consider variations resulted from the inherent characteristics of memristors and the errors of programming voltages, the robustness of MMNN and MCNN to these variations is analyzed. The simulation results on standard datasets show that deep neural networks (DNNs) built by the memristor crossbars work satisfactorily in pattern recognition tasks and have certain robustness to memristor variations.

关键词： Memristor Memristor-based neural network Deep neural network Multi-layer neural network Convolutional neural network Neuromorphic architecture

来源：评论

学校读者我要写书评

暂无评论

Stability of Delayed Homogeneous Positive Differential-Difference Systems

引用

IEEE TRANSACTIONS ON AUTOMATIC control 2024年第1期69卷 559-565页

作者： Xiao, Qiang Zeng, Zhigang Huang, Tingwen Lewis, Frank L. Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Minist Educ China Key Lab Image Informat Proc & Intelligent Control Wuhan 430074 Peoples R China Texas A&M Univ Qatar Doha 23874 Qatar Univ Texas Arlington UTA Res Inst Ft Worth TX 76118 USA

Stability theory of linear differential-difference system has been well-established, while fewer results can be found for nonlinear differential-difference systems. In this article, stability and boundedness of homogeneous differential-difference system with bounded delay is studied based on the system positivity. At first, an exponential stability criterion is obtained, which is an extension of an existing result. Next, another boundary is computed under the previous condition, which proves to be tighter than the first result at least in some cases. Then, a finite-time stability condition is achieved for the delay-free system, and an upper bound of the settling time and an explicit boundary of the state are derived. Finally, a numerical example is given to verify the results presented in this article.

关键词： Boundedness differential-difference system exponential stability homogeneous system positive system time delay

来源：评论

学校读者我要写书评

暂无评论

Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting

Represent, Compare, and Learn: A Similarity-Aware Framework ...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Shi, Min Lu, Hao Feng, Chen Liu, Chengxin Cao, Zhiguo Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Minist Educ Wuhan Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Class-agnostic counting (CAC) aims to count all instances in a query image given few exemplars. A standard pipeline is to extract visual features from exemplars and match them with query images to infer object counts. Two essential components in this pipeline are feature representation and similarity metric. Existing methods either adopt a pretrained network to represent features or learn a new one, while applying a naive similarity metric with fixed inner product. We find this paradigm leads to noisy similarity matching and hence harms counting performance. In this work, we propose a similarity-aware CAC framework that jointly learns representation and similarity metric. We first instantiate our framework with a naive baseline called Bilinear Matching Network (BMNet), whose key component is a learnable bilinear similarity metric. To further embody the core of our framework, we extend BMNet to BMNet+ that models similarity from three aspects: 1) representing the instances via their self-similarity to enhance feature robustness against intra-class variations;2) comparing the similarity dynamically to focus on the key patterns of each exemplar;3) learning from a supervision signal to impose explicit constraints on matching results. Extensive experiments on a recent CAC dataset FSC147 show that our models significantly outperform state-of-the-art CAC approaches. In addition, we also validate the cross-dataset generality of BMNet and BMNet+ on a car counting dataset CARPK. Code is at ***/BMNet

关键词： Visualization Computer vision Computational modeling Pipelines Feature extraction Robustness Power capacitors

来源：评论

学校读者我要写书评

暂无评论

Interval Type-2 Fuzzy Disturbance Observer-Based T-S Fuzzy control for a Pneumatic Flexible Joint

引用

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS 2022年第6期69卷 5962-5972页

作者： Chen, Cheng Huang, Jian Wu, Dongrui Tu, Xikai Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Hubei Univ Technol Sch Ind Design Wuhan 430074 Peoples R China

In this article, an interval type-2 fuzzy disturbance observer (IT2FDO) is proposed for the trajectory tracking control of a flexible joint actuated by a pneumatic artificial muscle and a torsion spring. Interval type-2 fuzzy sets are introduced into the fuzzy disturbance observer (FDO) to enhance the fuzzy approximation capability. A novel adaptive law that updates all the parameters of the FDO, including the control representative values, the center vectors, and the width vectors, is developed. A new control strategy incorporating the proposed IT2FDO and Takagi-Sugeno (T-S) fuzzy model-based control is designed for the trajectory tracking task. With the newly designed adaptive law, the stability of the IT2FDO and that of the closed-loop system are guaranteed. Simulation studies verify the effectiveness of the proposed IT2FDO, and real-world experiments demonstrate the robustness of the proposed control strategy to the external disturbance.

关键词： Disturbance observers Springs Robustness Fuzzy logic Uncertainty Stability analysis Fuzzy sets Fuzzy disturbance observer (FDO) interval type-2 fuzzy sets pneumatic artificial muscle (PAM) Takagi-Sugeno (T-S) fuzzy model-based control

来源：评论

学校读者我要写书评

暂无评论

Spiking neural P systems with mute rules

引用

INFORMATION AND COMPUTATION 2024年 299卷

作者： Wu, Tingfang Valencia-Cabrera, Luis Perez-Jimenez, Mario J. Pan, Linqiang Soochow Univ Sch Comp Sci & Technol Prov Key Lab Comp Informat Proc Technol Suzhou 215006 Peoples R China Univ Seville Res Grp Nat Comp Dept Comp Sci & Artificial Intelligence Seville 41012 Spain Univ Seville Inst I3US SCORE Lab Seville 41012 Spain Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Informat Proc & Intelligent Control Educ Minist China Wuhan 430074 Peoples R China

Spiking neural P (SNP) systems are a class of neural network models that draw inspiration from the functioning of biological neurons. It was experimentally found that there exist autapses from neurons onto themselves in the brain, i.e., a neuron can transmit a signal back to itself through an autapse. In this work, inspired by the characteristics of autapses, a new variant of the SNP system, termed SNP systems with mute rules (SNPMR systems), is considered. Specifically, mute rules have no communication functioning, namely the execution of a mute rule only applies the change on the number of spikes within its residing neuron, rather than affecting other postsynaptic neurons. The computational power of SNPMR systems is examined by demonstrating that SNPMR systems achieve Turing universality with four or ten neurons. In addition, a simulator for SNPMR systems is developed to provide an experimental validation of the systems designed theoretically. (c) 2024 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.

关键词： Bio-inspired computing Membrane computing Neural computation Spiking neural P system P-Lingua

来源：评论

学校读者我要写书评

暂无评论

A multi-period multi-product green supply network design problem with price and greenness dependent demands under uncertainty

引用

APPLIED SOFT COMPUTING 2022年第0期114卷 108078-108078页

作者： Wang, Jian Wan, Qian Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Minist Educ Wuhan 430074 Peoples R China

Governmental limitations and customer expectations have increased the focus on sustainability in supply chain network design (SCND). To address this issue, a bi-objective mixed-integer mathematical model is introduced with the aim of simultaneously maximizing supply chain profit and minimizing overall carbon emissions. Additionally, customer demands are considered price- and greenness-sensitive for multiple products, and uncertainty in the production process is estimated by a finite number of scenarios. The Monte Carlo sampling approach is used to produce the initial scenarios, and a heuristic scenario reduction approach is subsequently utilized. Due to the complexity of the model, we develop a hybrid metaheuristic algorithm that embeds variable neighborhood search (VNS) in two genetic algorithms to accelerate the convergence of the algorithm to high-quality solutions. These algorithms are compared to multi-objective particle swarm optimization (MOPSO) with two leader selection procedures. To improve the performance of these algorithms, the response surface method is applied to modulate the algorithm parameters. Finally, several analyses are performed to investigate the efficiency and effectiveness of the proposed approach. (C) 2021 Published by Elsevier B.V.

关键词： Green supply chain network Multi-period stochastic programming Price and greenness management Scenario reduction Hybrid metaheuristic approaches

来源：评论

学校读者我要写书评

暂无评论

A Generalized Graph Contrastive Learning Framework for Few-Shot Machine Fault Diagnosis

引用

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2024年第2期20卷 2692-2701页

作者： Yang, Chaoying Liu, Jie Xu, Qi Zhou, Kaibo Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat MOE Key Lab Image Informat Proc & Intelligent Cont Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Belt & Rd Joint Lab Measurement & Control Technol Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Civil & Hydraul Engn Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Hubei Key Lab Digital River Basin Sci & Technol Wuhan 430074 Peoples R China

Graph data-driven machine fault diagnosis methods make success using sufficient data recently. However, in the actual industry, there are rare failure data in historical data, leading to insufficient graph representation ability and reducing diagnosis performance. In this article, a generalized graph contrastive learning (GCL) framework for few-shot machine fault diagnosis is proposed. First, spectrum features of vibration data-based samples are used to calculate Euclidean distance matrix for constructing K-nearest neighborhood graph (KNNG), where K adjacent neighbors of each sample are connected. Avoiding excess calculation cost for graph construction, positive and negative KNNGs are constructed by changing parameter K. To make full use of few-shot samples, an unsupervised GCL subtask is set for pretraining graph deep learning model. Further, the unsupervised pretrained model is semisupervised trained using original KNNGs for outputting unlabeled nodes' labels. The proposed method achieves 99.83%, 99.56% in bearing and gearbox dataset, respectively, and the proposed GCL framework works for different graph neural networks.

关键词： Few-shot learning (FSL) graph contrastive learning (GCL) K-nearest neighborhood graph machine fault diagnosis model pretraining

来源：评论

学校读者我要写书评

暂无评论

An approach for accessibility assessment and vulnerability analysis of national multimodal transport systems

引用

RISK ANALYSIS 2023年第11期43卷 2312-2329页

作者： Zhang, Hui Ouyang, Min Sun, Wenjing Hong, Liu Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan Peoples R China Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Minist Educ Wuhan Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automation Wuhan 430074 Peoples R China

A series of ambitious accessibility-oriented policies have been launched in the world, which center around improving accessibility via the national multimodal transport systems including road, airline, and railway. The national multimodal transport accessibility assessment is one of the "basic" analyses for the design and implementation of these policies, whereas existing national-scale accessibility studies either focus on single-mode or two-mode transport or ignore the schedule-dependent nature of railway and airline. This article models the integrated road, railway, airline, and walking transport as a four-layer network with the consideration of their interdependencies. An algorithm is then developed to accurately assess the travel time-based accessibility on the four-layer network with the consideration of the daily schedule of trains and flights. The proposed approach is applied to map accessibility to 363 cities in mainland China and analyze the optimal travel modes. In addition, this article investigates the travel time-based vulnerability of the national multimodal transport system in mainland China under the extreme storm recently occurred in Zhengzhou (July 2021). The findings in this work provide insightful suggestions for transport planners to design the national multimodal transport systems and for stakeholders to schedule travels.

关键词： extreme storm national multimodal transport system schedule travel-time based accessibility vulnerability

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：