检索结果-南通市图书馆

Identification of abnormal conditions in high-dimensional chemical process based on feature selection and deep learning

引用

Chinese Journal of Chemical Engineering 2020年第7期28卷 1875-1883页

作者： Wende Tian Zijian Liu Lening Li Shifa Zhang Chuankun Li College of Chemical Engineering Qingdao University of Science&TechnologyQingdao 266042China Qingdao NOVAN Electromechanical Technology Qingdao 266100China State Key Laboratory of Safety and Control for Chemicals SINOPEC Qingdao Research Institute of Safety EngineeringQingdao 266071China

Identification of abnormal conditions is essential in the chemical *** the rapid development of artificial intelligence technology,deep learning has attracted a lot of attention as a promising fault identification method in chemical process *** the high-dimensional data identification using deep neural networks,problems such as insufficient data and missing data,measurement noise,redundant variables,and high coupling of data are often *** tackle these problems,a feature based deep belief networks(DBN)method is proposed in this ***,a generative adversarial network(GAN)is used to reconstruct the random and non-random missing data of chemical ***,the feature variables are selected by spearman’s rank correlation coefficient(SRCC)from high-dimensional data to eliminate the noise and redundant variables and,as a consequence,compress data dimension of chemical ***,the feature filtered data is deeply abstracted,learned and tuned by DBN for multi-case fault *** application in the Tennessee Eastman(TE)process demonstrates the fast convergence and high accuracy of this proposal in identifying abnormal conditions for chemical process,compared with the traditional fault identification algorithms.

关键词： Chemical process Deep Belief Networks Fault identification Generative Adversarial Networks spearman rank correlation

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

Data quality evaluation and calibration of on-road remote sensing systems based on exhaust plumes

引用

Journal of Environmental Sciences 2023年第1期123卷 317-326页

作者： Shijie Liu Xinlu Zhang Linlin Ma Liqiang He Shaojun Zhang Miaomiao Cheng State Key Laboratory of Environmental Criteria and Risk Assessment Chinese Research Academy of Environmental SciencesBeijing 100012China Institute of Atmospheric Environment Chinese Research Academy of Environmental SciencesBeijing 100012China School of Environment State Key Joint Laboratory of Environment Simulation and Pollution ControlTsinghua UniversityBeijing 100084China State Environmental Protection Key Laboratory of Sources and Control of Air Pollution Complex Beijing 100084China

In recent years,with rapid increases in the number of vehicles in China,the contribution of vehicle exhaust emissions to air pollution has become increasingly *** achieve the precise control of emissions,on-road remote sensing(RS)technology has been developed and applied for law enforcement and ***,data quality is still an existing issue affecting the development and application of *** this study,the RS data from a cross-road RS system used at a single site(from 2012 to 2015)were collected,the data screening process was reviewed,the issues with data quality were summarized,a new method of data screening and calibration was proposed,and the effectiveness of the improved data quality control methods was finally *** results showed that this method reduces the skewness and kurtosis of the data distribution by up to nearly 67%,which restores the actual characteristics of exhaust diffusion and is conducive to the identification of actual clean and high-emission *** annual variability of emission factors of nitric oxide decreases by 60%-on average-eliminating the annual drift of fleet emissions and improving data reliability.

关键词： On-road remote sensing(RS) Data quality spearman rank correlation Least-square regression with a non-zero intercept Cook value

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

Ray tracing/correlation approach to estimation of surface-based duct parameters from radar clutter

引用

Chinese Physics B 2010年第4期19卷 484-491页

作者：赵小峰黄思训盛峥 Institute of Meteorology PLA University of Science and Technology

This paper describes a technique to estimate surface-based duct parameters by using a simple ray tracing/correlation method. The approach is novel in that it incorporates the spearman rank-order correlation scheme between the observed surface clutter and the surface ray density for a given propagation path. The simulation results and the real data results both demonstrate the ability of this method to estimate surface-based duct parameters. Compared with the results obtained by a modified genetic algorithm combined with the parabolic wave equation, the results retrieved from the ray tracing/correlation scheme show a minor reduction in accuracy but a great improvement on computation time. Therefore the ray tracing/correlation method might be used as a precursor to more sophisticated and slower techniques, such as genetic algorithm and particle filters, by narrowing the parameter search space and providing a comprehensive and more efficient estimation algorithm.

关键词： ray tracing spearman rank correlation surface-based duct radar clutter

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

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

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：