帮助 关于我们

返回检索结果

基于深层神经网络的多输出自适应软测量建模
A self-adaptive multi-output soft sensor modeling based on deep neural network

查看参考文献30篇

邱禹 1   刘乙奇 1,2   吴菁 1   黄道平 1 *  
文摘 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。
其他语种文摘 In wastewater treatment process (WWTP), existence of several important but difficult-to-measure process variables hinders not only monitoring of the production process but also adjustment or optimization of process control strategies. Even though soft-sensor models are reasonably constructed, it will still suffer degradation problem and high maintenance cost in real-time operation. Additionally, selection of proper secondary variables directly affects subsequent modeling. Therefore, a self-adaptive multi-output soft sensor model based on deep neural network was proposed for simultaneous online prediction of multiple target variables in wastewater treatment. Deep neural network was constructed from a stacked auto-encoder, which had satisfactory performance of online prediction under extremely complex scenarios. In order to overcome degradation problem and select proper secondary variables, time difference modeling and VIP (variable importance in projection) methods were added. Finally, validation on a true WWTP process shows that the proposed soft-sensor model has good performance on multiple output prediction and satisfactory prediction on single target.
来源 化工学报 ,2018,69(7):3101-3113 【核心库】
DOI 10.11949/j.issn.0438-1157.20171624
关键词 污水 ; 软测量 ; 神经网络 ; 多输出 ; 预测 ; 时差建模 ; 变量重要性投影
地址

1. 华南理工大学自动化科学与工程学院, 广东, 广州, 510640  

2. 广州中国科学院沈阳自动化研究所分所, 广东, 广州, 511458

语种 中文
文献类型 研究性论文
ISSN 0438-1157
学科 自动化技术、计算机技术
基金 国家自然科学基金项目 ;  广东省自然科学基金 ;  广东省科技计划项目
文献收藏号 CSCD:6285104

参考文献 共 30 共2页

1.  黄道平. 软测量在污水处理过程中的研究与应用. 化工学报,2011,62(1):1-9 被引 19    
2.  曹鹏飞. 化工过程软测量建模方法研究进展. 化工学报,2013,64(3):788-800 被引 53    
3.  Kano M. Data-based process monitoring, process control, and quality improvement:recent developments and applications in steel industry. Computers & Chemical Engineering,2008,32(1/2):12-24 被引 31    
4.  Kadlec P. Data-driven soft sensors in the process industry. Computers & Chemical Engineering,2009,33(4):795-814 被引 102    
5.  Borchani H. A survey on multi-output regression. Wiley Interdisciplinary Reviews Data Mining & Knowledge Discovery,2015,5(5):216-233 被引 11    
6.  Zhong W. MIMO soft sensors for estimating product quality with on-line correction. Chemical Engineering Research & Design,2000,78(4):612-620 被引 1    
7.  Kocev D. Using single-and multi target regression trees and ensembles to model a compound index of vegetation condition. Ecological Modelling,2009,220(8):1159-1168 被引 3    
8.  Breiman L. Predicting multivariate responses in multiple linear regression. Journal of the Royal Statistical Society,1997,59(1):3-54 被引 7    
9.  Simila T. Input selection and shrinkage in multiresponse linear regression. Computational Statistics & Data Analysis,2007,52(1):406-422 被引 4    
10.  Fu Y. MIMO soft-sensor model of nutrient content for compound fertilizer based on hybrid modeling technique 1. Chinese Journal of Chemical Engineering,2007,15(4):554-559 被引 1    
11.  郭民. 基于模糊神经网络的出水总磷和氨氮软测量方法研究. 计算机与应用化学,2017,34(1):79-84 被引 2    
12.  Qiu Y. Date-driven soft-sensor design for biological wastewater treatment using deep neural networks and genetic algorithms. Journal of Chemical Engineering of Japan,2016,49(10):925-936 被引 8    
13.  Kadlec P. Review of adaptation mechanisms for data-driven soft sensors. Computers & Chemical Engineering,2011,35(1):1-24 被引 42    
14.  Jiang J H. Wavelength interval selection in multicomponent spectral analysis by moving window partial least-squares regression with applications to mid-infrared and near-infrared spectroscopic data. Analytical Chemistry,2002,74(14):3555-3565 被引 53    
15.  Dayal B S. Recursive exponentially weighted PLS and its applications to adaptive control and prediction. Journal of Process Control,1997,7(3):169-179 被引 20    
16.  Qin S J. Recursive PLS algorithms for adaptive data modeling. Computers & Chemical Engineering,1998,22(4/5):503-514 被引 62    
17.  Cheng C. A new data-based methodology for nonlinear process modeling. Chemical Engineering Science,2004,59(13):2801-2810 被引 30    
18.  Fujiwara K. Soft-sensor development using correlation-based just-in-time modeling. AIChE Journal,2009,55(7):1754-1765 被引 27    
19.  刘乙奇. 基于改进JIT算法的软测量建模及其在污水处理中的应用. 华南理工大学学报(自然科学版),2011,39(5):55-60,67 被引 3    
20.  Kaneko H. Development of a new soft sensor method using independent component analysis and partial least squares. AIChE J,2009,55(1):87-98 被引 11    
引证文献 8

1 赵超 基于互信息和IGSA优化ELM的重整芳烃收率软测量 仪器仪表学报,2019,40(3):255-263
被引 7

2 刘鸿斌 废水处理过程的典型相关分析建模方法研究 山东大学学报. 工学版,2020,50(1):101-108
被引 0 次

显示所有8篇文献

论文科学数据集
PlumX Metrics
相关文献

 作者相关
 关键词相关
 参考文献相关

版权所有 ©2008 中国科学院文献情报中心 制作维护:中国科学院文献情报中心
地址:北京中关村北四环西路33号 邮政编码:100190 联系电话:(010)82627496 E-mail:cscd@mail.las.ac.cn 京ICP备05002861号-4 | 京公网安备11010802043238号