SIA OpenIR  > 广州中国科学院沈阳自动化研究所分所
基于深层神经网络的多输出自适应软测量建模
Alternative TitleA Multi-output adaptive soft-sensor modeling based on deep neural network
邱禹; 刘乙奇; 吴菁; 黄道平
Department广州中国科学院沈阳自动化研究所分所
Source Publication化工学报
ISSN0438-1157
2018
Volume69Issue:7Pages:3101-3113
Indexed ByCSCD
CSCD IDCSCD:6285104
Contribution Rank2
Funding Organization国家自然科学基金资助项目(61673181,61533002) ; 广东省自然科学基金资助项目(2015A030313225) ; 广东省科技计划项目(2016A020221007)
Keyword污水 软测量 神经网络 多输出 预测 时差建模 Vip变量选择
Abstract

在污水处理运行过程中,多个重要的难测过程变量的存在,不仅妨碍了生产过程的监控,而且阻碍了过程控制策略的调整或优化。即使软测量模型得到合理的构建,在投入运行后仍然遭受性能的退化和同时带来的高昂的维护成本。此外,合适辅助变量的选取直接影响后续建模的效果。因此,文中提出了一种基于深层神经网络的多输出自适应软测量模型,用于污水处理过程中多个目标变量的同步在线预测。其中,深层神经网络基于一种栈式自编码而构建,在极端复杂场景下具有优异的在线预测性能;并在建模中引入时差建模和变量重要性投影(VIP)这两种算法,以应对性能退化问题和实现辅助变量的精选。最后,通过一个实际案例对所提出模型进行验证。结果表明,所提出的软测量模型不仅具有较好的多输出预测性能,且在单目标预测结果上也有不错的表现。

Other Abstract

In the wastewater treatment process (WWTP), the existence of several important but hard-to-measure process variables hinders not only the monitoring of productive processes, but also the adjustment or optimization of process control strategies. Even though the soft-sensor models are reasonably constructed, which also suffer the degradation problem, resulting in high maintenance cost. Additionally, the selection of proper secondary variables affects the subsequent modeling directly. Therefore, a multi-output adaptive soft sensor model based on deep neural network is proposed, which used for simultaneous online prediction of multiple target variables in wastewater treatment. The deep neural network is constructed on the basis of a stacked auto-encoder, displaying satisfactory online prediction performance under extremely complex scenarios. In order to deal with the degradation problem and select proper secondary variables, a time difference modeling method and VIP (Variable importance in projection) method are assimilated in modeling. Finally, the proposed model is validated through a real WWTP case. Results show that the proposed soft-sensor model not only has the better multi-output prediction performance, but also has satisfactory results on single-target prediction.

Language中文
Citation statistics
Cited Times:1[CSCD]   [CSCD Record]
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/21572
Collection广州中国科学院沈阳自动化研究所分所
Corresponding Author邱禹
Affiliation1.华南理工大学自动化科学与工程学院
2.广州中国科学院沈阳自动化研究所分所
Recommended Citation
GB/T 7714
邱禹,刘乙奇,吴菁,等. 基于深层神经网络的多输出自适应软测量建模[J]. 化工学报,2018,69(7):3101-3113.
APA 邱禹,刘乙奇,吴菁,&黄道平.(2018).基于深层神经网络的多输出自适应软测量建模.化工学报,69(7),3101-3113.
MLA 邱禹,et al."基于深层神经网络的多输出自适应软测量建模".化工学报 69.7(2018):3101-3113.
Files in This Item: Download All
File Name/Size DocType Version Access License
基于深层神经网络的多输出自适应软测量建模(1813KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[邱禹]'s Articles
[刘乙奇]'s Articles
[吴菁]'s Articles
Baidu academic
Similar articles in Baidu academic
[邱禹]'s Articles
[刘乙奇]'s Articles
[吴菁]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[邱禹]'s Articles
[刘乙奇]'s Articles
[吴菁]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 基于深层神经网络的多输出自适应软测量建模.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.