检索结果-南通市图书馆

Active label-denoising algorithm based on broad learning for annotation of machine health status

Science China(Technological Sciences) 2022年第9期65卷 2089-2104页

作者： LIU GuoKai SHEN WeiMing GAO Liang kusiak andrew State Key Laboratory of Digital Manufacturing Equipment and Technology Huazhong University of Science and TechnologyWuhan 430074China Department of Industrial and System Engineering The University of IowaSeamans CenterIowa CityIA 52242USA

Deep learning has led to tremendous success in machine maintenance and fault ***,this success is predicated on the correctly annotated *** in large industrial datasets can be noisy and thus degrade the performance of fault diagnosis *** emerging concept of broad learning shows the potential to address the label noise *** with existing deep learning algorithms,broad learning has a simple architecture and high training *** active label denoising algorithm based on broad learning(ALDBL)is ***,ALDBL captures the embedded representation from the time-frequency features by a recurrent memory ***,it augments wide features with a sparse autoencoder and projects the sparse features into an orthogonal space.A proposed corrector then iteratively changes the weights of source examples during the training and corrects the labels by using a label adaptation ***,ALDBL finetunes the model parameters with actively sampled target data with reliable pseudo *** performance of ALDBL is validated with three benchmark datasets,including 30 label denoising *** results demonstrate the effectiveness and advantages of the proposed algorithm over the other label denoising algorithms.

关键词： data annotation broad learning deep learning domain adaptation fault diagnosis noisy label

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

Editorial for the Special Issue on Intelligent Manufacturing

引用

Engineering 2021年第6期7卷 704-705页

作者： Peigen Li andrew kusiak Liang Gao Weiming Shen The State Key Laboratory of Digital Manufacturing Equipment and Technology School of Mechanical Science and EngineeringHuazhong University of Science and TechnologyWuhan 430074China Department of Industrial and Systems Engineering The University of IowaIowa CityIA 52242-1527USA

Intelligent manufacturing is the development trend of manufac-turing *** comprises the deep integration of new-genera-tion information and communication technologies(i.e.,fifth generation mobile networks(5G),artificial intelligence,the Indus-trial Internet,etc.)with advanced manufacturing technologies,covering the whole life cycle of a product,including design,pro-duction,logistics,services,and so *** it is largely based on automation and machine intelligence,humans play essential roles in intelligent manufacturing.

关键词： services Intelligent artificial

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

Extreme Engineering: Polarization in Product Development and Manufacturing

引用

Engineering 2021年第3期7卷 282-284页

作者： andrew kusiak Department of Industrial and Systems Engineering The University of IowaIowa CityIA 52242-1527USA

*** Products and solutions are usually developed to meet customer needs at a cost justified by the *** technologies are likely to be adopted by pr omising applications involving tolerable *** time,some application domains become saturated with new *** naturally occurring market phenomenon and progress in the technology itself are likely to lead to newd evelopments that normally would not be considered.

关键词： likely customer saturated

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

Active label-denoising algorithm based on broad learning for annotation of machine health status

引用

Science China Technological Sciences 2022年

作者： LIU GuoKai SHEN WeiMing GAO Liang kusiak andrew Department of Industrial and System Engineering The University of IowaSeamans Center State Key Laboratory of Digital Manufacturing Equipment and Technology Huazhong University of Science and Technology

Deep learning has led to tremendous success in machine maintenance and fault diagnosis. However, this success is predicated on the correctly annotated datasets. Labels in large industrial datasets can be noisy and thus degrade the performance of fault diagnosis models. The emerging concept of broad learning shows the potential to address the label noise problem. Compared with existing deep learning algorithms, broad learning has a simple architecture and high training efficiency. An active label denoising algorithm based on broad learning(ALDBL) is proposed. First, ALDBL captures the embedded representation from the time-frequency features by a recurrent memory cell. Second, it augments wide features with a sparse autoencoder and projects the sparse features into an orthogonal space. A proposed corrector then iteratively changes the weights of source examples during the training and corrects the labels by using a label adaptation matrix. Finally, ALDBL finetunes the model parameters with actively sampled target data with reliable pseudo labels. The performance of ALDBL is validated with three benchmark datasets, including 30 label denoising tasks. Computational results demonstrate the effectiveness and advantages of the proposed algorithm over the other label denoising algorithms.

关键词：

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

基于知识的成组技术

引用

成组技术与生产现代化 1992年第2期9卷 24-30页

作者： andrew kusiak 汤和高东天津大学机械系

一、引言本文叙述了一个用来解决成组技术问题的基于知识的系统(KBGT)。成组技术问题的内容包括与机器能力、材料输送系统的能力、制造单元的大小以及技术要求等有关的约束。它已向自动制造环境方向发展。KBGT是以kusiak提出的串联系... 详细信息

一、引言本文叙述了一个用来解决成组技术问题的基于知识的系统(KBGT)。成组技术问题的内容包括与机器能力、材料输送系统的能力、制造单元的大小以及技术要求等有关的约束。它已向自动制造环境方向发展。KBGT是以kusiak提出的串联系统结构为基础建立的。它考虑了备选工艺方案和多功能机床,并利用了专家系统和优化方面的先进成果。文中讨论了基于知识的系统(或称之为知识库系统)的两个基本组成——专家系统和启发式聚类算法。

关键词：成组技术基于知识

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

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

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

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：