检索结果-南通市图书馆

Local multi-model integrated soft sensor based on just-in-time learning for mechanical properties of hot strip mill process

引用

Journal of Iron and Steel Research International 2021年第7期28卷 830-841页

作者： Jie Dong Ying-ze Tian Kai-xiang Peng Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education School of Automation and Electrical EngineeringUniversity of Science and Technology BeijingBeijing 100083China National Engineering Research Center for Advanced Rolling Technology University of Science and Technology BeijingBeijing 100083China

The mechanical properties of hot rolled strip are the key index of product quality,and the soft sensing of them is an important decision basis for the control and optimization of hot rolling *** solve the problem that it is difficult to measure the mechanical properties of hot rolled strip in time and accurately,a soft sensor based on ensemble local modeling was ***,outliers of process data are removed by local outlier *** standardization and transformation,normal data that can be used in the model are ***,in order to avoid redundant variables participating in modeling and reducing performance of models,feature selection was applied combing the mechanism of hot rolling process and mutual information among ***,features of samples were extracted by supervised local preserving projection,and a prediction model was constructed by Gaussian process regression based on just-in-time learning(JITL).Other JITL-based models,such as support vector regression and gradient boosting regression tree models,keep all variables and make up for the lost information during dimension ***,the soft sensor was developed by integrating individual models through stacking *** and reliability of proposed soft sensors were verified by actual process data from a real hot rolling process.

关键词： Soft sensor just-in-time learning Multi-model Hot rolling

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

Modeling of Penicillin Fermentation Process Based on FCM and Improved just-in-time learning Algorithm 36

Modeling of Penicillin Fermentation Process Based on FCM and...

引用

第36届中国控制会议

作者： Dapeng Niu Huiyuan Gao Yuanqing Liu School of Information Science ＆ Engineering Northeastern University

ISBN: (纸本)9781538629185

Penicillin fermentation process has the characteristics of time variation,non-linearity and *** accurate mechanism model is quite difficult to *** order to establish a rapid and accurate model to describe the characteristics of penicillin fermentation process,a local modeling method based on just-In-time algorithm is proposed for product concentration prediction during penicillin fermentation *** the segmentation characteristics penicillin fermentation process,fuzzy C-means clustering algorithm is used to classify the historical *** the process of on-line modeling,the historical database is selected from the corresponding fermentation period and the adjacent time *** least squares support vector machines method is used for local modeling to improve the real-time performance of the *** simulation results show that the prediction model for penicillin product concentration based on FCM and improved just-In-time algorithm is more effective in accuracy and real-time performances.

关键词： Penicillin fermentation fuzzy C-means clustering algorithm just-in-time learning Least Squares Support Vector Machines

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

Re-defining the performance of just-in-time learning based soft sensor for high dimensional process data

Re-defining the performance of just-in-time learning based s...

引用

第32届中国过程控制会议(CPCC2021)

作者： Xiaoyu Jiang Zhiqiang Ge State Key Laboratory of Industrial Control Technology Institute of Industrial Process ControlCollege of Control Science and EngineeringZhejiang University

just-in-time learning(JITL) is a widely used online soft sensing method for time-varying *** the increase of dimensionality of industrial dataset,both reliability and usability of JITL would be seriously damaged due to the sparseness caused in the high-dimensional data *** this paper,variational autoencoder is introduced as a generative model to provide virtual samples for augmenting high-dimensional sparse *** on this,a data augmentation just-in-time learning framework is formulated and implemented with two different ***,we carefully discuss the effect of virtual data on just-in-time learning,as well as the influence of virtual data volume,virtual data ratio and other factors on the proposed ***,a real industrial example is applied to verify the effectiveness of the proposed method,in which two indicators(RMSE and R2) have been improved by an average of 22%,15%,respectively,compared to the traditional JITL approach.

关键词： Data augmentation just-in-time learning variational autoencoder soft sensor

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

Soft Measurement Modeling of Cement Ball Mill Particle Size Based on just-in-time learning

Soft Measurement Modeling of Cement Ball Mill Particle Size ...

引用

第43届中国控制会议

作者： Xuezhen Lei Zhao Liu Qiang Zhang Honghao Ma Wanjie Ding Yuzhu Li College of Automation and Electrical Engineering University of Jinan

During the grinding process of cement ball mill, the cement particle size distribution determines the setting time,stability, strength grade and other characteristics of cement. The accurate measurement of cement particle size distribution is of great significance to the control of cement quality. Once the traditional soft sensing model of cement ball mill particle size is established, the model parameters will not change, and the performance of the model will gradually degrade or even fail with the change of cement grinding conditions. To address this issue, this paper proposes a cement ball mill particle size soft measurement model based on just-in-time learning. Within the framework of just-in-time learning, a local model is established by selecting the modeling dataset of current query samples using similarity criteria. This method enables the updating of model parameters as the operating conditions change. Using the proposed method can achieve precise measurement of cement particle size distribution, with a mean square error of 0.0147, root mean square error of 0.1211, and mean absolute error of 0.0417, providing valuable references for controlling cement quality in practical production.

关键词： Cement Particle Size just-in-time learning Soft Measurement Modeling

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

A just-in-time learning based integrated IMC-ILC control strategy for batch processes

A just-in-time learning based integrated IMC-ILC control str...

引用

第40届中国控制会议

作者： Chengyu Zhou Li Jia Department of Automation College of Mechatronics Engineering and AutomationShanghai University Shanghai Key Laboratory of Power Station Automation Technology Department of AutomationCollege of Mechatronics Engineering and AutomationShanghai University

This paper deals with issue of two dimensional(2 D) control for batch ***,in order to derive high efficiency and accuracy process model,a novelty hierarchical searching mechanism just-in-time learning(JITL) model is ***,on the basis of the JITL model,an integrated internal model control(IMC) and iterative learning control(ILC)2 D control scheme is presented,where the IMC in time-axis can reject disturbances and uncertainties,and the ILC in batch-axis can guarantee the control system asymptotically ***,the initial batch control input trajectory of the IMCILC algorithm can be obtained by using the JITL from inverse model *** a result,not only the issue of model-plant mismatches and real-time disturbances can be solved,but also obtain faster system convergence rate and smaller tracking ***,a typical batch process is proved to demonstrate the feasibility and superiority.

关键词： Batch processes Iterative learning control just-in-time learning Internal model control

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

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：