Soft Sensor Modeling Method of Dynamic liquid Level Based on Improved KS Algorithm

被引:0
作者
Wang Tong [1 ]
Duan Zewen [2 ]
机构
[1] Shenyang Univ Technol, Sch Elect Engn, Shenyang 110870, Liaoning, Peoples R China
[2] Shenyang Univ Technol, Sch Informat Sci & Engn, Shenyang 110870, Liaoning, Peoples R China
来源
2017 29TH CHINESE CONTROL AND DECISION CONFERENCE (CCDC) | 2017年
关键词
dynamic liquid level; soft sensor; subspace; sample selection; Kennard-Stone; CROSS-VALIDATION;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Duing to the problem that the sample data of the soft-sensor modeling in the oilfield production process has influence on the modeling quality, this paper proposes a subspace-based Kennard-Stone algorithm. Firstly, according to the characteristics of oil production data, production process parameters are divided into subspace of different working conditions. Then, the method of similarity of spatial data is used to replace the original Euclidean distance calculation method to complete the sample selection of KS algorithm. Finally; the soft-sensing model of the dynamic liquid level is constructed based on the sample selected and BH-LSSVM algorithm. Experimental results show that compared with random sample selection and KS algorithm based on Euclidean distance, this method can improve the prediction quality of the model, and save the modeling time.
引用
收藏
页码:6510 / 6515
页数:6
相关论文
共 15 条
[1]   Fast cross-validation algorithms for least squares support vector machine and kernel ridge regression [J].
An, Senjian ;
Liu, Wanquan ;
Venkatesh, Svetha .
PATTERN RECOGNITION, 2007, 40 (08) :2154-2162
[2]  
Cheng Dianfang, 2008, OIL GAS WELL TEST, V17, P60
[3]  
[高学金 Gao Xuejin], 2015, [仪器仪表学报, Chinese Journal of Scientific Instrument], V36, P401
[4]   Black hole: A new heuristic optimization approach for data clustering [J].
Hatamlou, Abdolreza .
INFORMATION SCIENCES, 2013, 222 :175-184
[5]   Preparation of comprehensive data from huge data sets for predictive soft sensors [J].
Kaneko, Hiromasa ;
Funatsu, Kimito .
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2016, 153 :75-81
[6]   A convex hull-based data selection method for data driven models [J].
Khosravani, H. R. ;
Ruano, A. E. ;
Ferreira, P. M. .
APPLIED SOFT COMPUTING, 2016, 47 :515-533
[7]  
[李翔宇 Li Xiangyu], 2016, [化工学报, CIESC Journal], V67, P2469
[8]  
Li Xiangyu, 2016, CIESE J, V66, P2150
[9]  
Su Cheng-li, 2015, Control and Decision, V30, P721, DOI 10.13195/j.kzyjc.2014.0044
[10]   Subspace distance analysis with application to adaptive Bayesian algorithm for face recognition [J].
Wang, LW ;
Wang, X ;
Feng, JF .
PATTERN RECOGNITION, 2006, 39 (03) :456-464