检索结果-南通市图书馆

continual learning fault diagnosis:A dual-branch adaptive aggregation residual network for fault diagnosis with machine increments

引用

Chinese Journal of Aeronautics 2023年第6期36卷 361-377页

作者： Bojian CHEN Changqing SHEN Juanjuan SHI Lin KONG Luyang TAN Dong WANG Zhongkui ZHU School of Rail Transportation Soochow UniversitySuzhou 215131China China Chang Guang Satellite Technology CO.LTD Changchun 130102China Department of Industrial Engineering and Management and in the State Key Laboratory of Mechanical System and Vibration Shanghai Jiao Tong UniversityShanghai 200030China

As a data-driven approach, Deep learning(DL)-based fault diagnosis methods need to collect the relatively comprehensive data on machine fault types to achieve satisfactory performance. A mechanical system may include multiple submachines in the real-world. During condition monitoring of a mechanical system, fault data are distributed in a continuous flow of constantly generated information and new faults will inevitably occur in unconsidered submachines, which are also called machine increments. Therefore, adequately collecting fault data in advance is difficult. Limited by the characteristics of DL, training existing models directly with new fault data of new submachines leads to catastrophic forgetting of old tasks, while the cost of collecting all known data to retrain the models is excessively high. DL-based fault diagnosis methods cannot learn continually and adaptively in dynamic environments. A new continual learning Fault Diagnosis method(CLFD) is proposed in this paper to solve a series of fault diagnosis tasks with machine increments. The stability–plasticity dilemma is an intrinsic issue in continual learning. The core of CLFD is the proposed Dual-branch Adaptive Aggregation Residual Network(DAARN).Two types of residual blocks are created in each block layer of DAARN: steady and dynamic blocks. The stability–plasticity dilemma is solved by assigning them with adaptive aggregation weights to balance stability and plasticity, and a bi-level optimization program is used to optimize adaptive aggregation weights and model parameters. In addition, a feature-level knowledge distillation loss function is proposed to further overcome catastrophic forgetting. CLFD is then applied to the fault diagnosis case with machine increments. Results demonstrate that CLFD outperforms other continual learning methods and has satisfactory robustness.

关键词： Catastrophic forgetting continual learning Fault diagnosis Knowledge distillation Machine increments Stability-plasticity dilemma

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Communication-efficient federated continual learning for distributed learning system with Non-IID data

引用

Science China(Information Sciences) 2023年第2期66卷 94-113页

作者： Zhao ZHANG Yong ZHANG Da GUO Shuang ZHAO Xiaolin ZHU School of Electronic Engineering Beijing University of Posts and Telecommunications Beijing Key Laboratory of Work Safety Intelligent Monitoring Beijing University of Posts and Telecommunication

Due to the privacy preserving capabilities and the low communication costs, federated learning has emerged as an efficient technique for distributed deep learning/machine learning training. However, given the typical heterogeneous data distributions in the realistic scenario, federated learning faces the challenge of performance degradation on non-independent identically distributed(Non-IID) data across clients. Therefore, we propose federated continual learning to improve the performance on Non-IID data by introducing the knowledge of the other local models. Specifically, we propose a novel federated continual learning method called Fed SI, adapting the synaptic intelligence method to the federated learning scenario. Furthermore,in order to reduce the communication overheads, we propose the bidirectional compression and error compensation(BCEC) algorithm to produce the communication-efficient federated continual learning method,called CFedSI. Specifically, the proposed BCEC algorithm compresses both the uplink and the downlink transmission data and utilizes the error compensation locally to ensure training divergence. Experiments show that CFedSI improves the accuracy on Non-IID data by up to 46% with KDDCUP’99 dataset, 23%with CICIDS2017 dataset, 22% with MNIST dataset, and 8% with FashionMNIST dataset, along with the reduced communication overheads.

关键词： distributed learning system federated learning continual learning model compression error compensation

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

continual driver behaviour learning for connected vehicles and intelligent transportation systems: Framework, survey and challenges

引用

Green Energy and Intelligent Transportation 2023年第4期2卷 69-80页

作者： Zirui Li Cheng Gong Yunlong Lin Guopeng Li Xinwei Wang Chao Lu Miao Wang Shanzhi Chen Jianwei Gong Chair of Traffic Process Automation “Friedrich List”Faculty of Transport and Traffic SciencesTU Dresden01069 DresdenGermany School of Mechanical Engineering Beijing Institute of Technology100081 BeijingChina Transport and Planning Civil Engineering and GeosciencesDelft University of Technology2628 CD Delft School of Engineering and Materials Science Queen Mary University of LondonE14NS LondonUK Baidu Inc Beijing 100085China State Key Laboratory of Wireless Mobile Communications China Information and Communication Technology Group Co.Ltd.(CICT)China

Modelling,predicting and analysing driver behaviours are essential to advanced driver assistance systems(ADAS)and the comprehensive understanding of complex driving scenarios.Recently,with the development of deep learning(DL),numerous driver behaviour learning(DBL)methods have been proposed and applied in connected vehicles(CV)and intelligent transportation systems(ITS).This study provides a review of DBL,which mainly focuses on typical applications in CV and ITS.First,a comprehensive review of the state-of-the-art DBL is presented.Next,Given the constantly changing nature of real driving scenarios,most existing learning-based models may suffer from the so-called“catastrophic forgetting,”which refers to their inability to perform well in previously learned scenarios after acquiring new ones.As a solution to the aforementioned issue,this paper presents a framework for continual driver behaviour learning(CDBL)by leveraging continual learning technology.The proposed CDBL framework is demonstrated to outperform existing methods in behaviour prediction through a case study.Finally,future works,potential challenges and emerging trends in this area are highlighted.

关键词： Driver behaviours Connected vehicles continual learning Machine learning Intelligent transportation systems

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

learning to Navigate for Mobile Robot with continual Reinforcement learning

Learning to Navigate for Mobile Robot with Continual Reinfor...

引用

第三十九届中国控制会议

作者： Ning Wang Dingyuan Zhang Yong Wang Department of Automation University of Science and Technology of China

Autonomous navigation of mobile ground robots is a promising research topic due to its extensive applications.Existing works are difficult to deal with obstacle-cluttered problems and often do not generalize well because of the differences between training scenarios and practical environments. In this paper, we present an end-to-end motion planning model that has the ability to navigate the mobile robot to the given destination safely in an unknow environment without any prior knowledge.Specifically, with the application of continual reinforcement learning, our approach is able to learn subtasks in a sequential fashion by decomposing the arbitrarily complex navigating task. The experiments show that our approach is more effective and can be directly transferable to other unseen environments.

关键词： Navigation Mobile Robot Reinforcement learning continual learning

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

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：