Soft sensor for determination of dynamic fluid levels based on enhanced just-in-time learning algorithm

被引：2

作者：

Wang, Tong ^{[1
]}

Gao, Xian-Wen ^{[1
]}

Liu, Wen-Fang ^{[2
]}

机构：

[1] School of Information Science & Engineering, Northeastern University, Shenyang

[2] School of Electrical Engineering, Shenyang University of Technology, Shenyang

来源：

Dongbei Daxue Xuebao/Journal of Northeastern University | 2015年 / 36卷 / 07期

关键词：

Dynamic fluid level; Just-in-time learning; Model update; Similarity; Subspace;

D O I：

10.3969/j.issn.1005-3026.2015.07.002

中图分类号：

学科分类号：

摘要：

When soft sensor model is used to predict dynamic fluid levels in oil production, it will gradually degenerate during the process, resulting in the larger deviation of prediction results and the difficulties to be used in practical oilfield production. To solve this problem, a new just-in-time model based on the similarity of subspaces was proposed to realize adaptive dynamic updates for a prediction model of dynamic fluid level. According to the production data, the similarity of subspaces was calculated to improve the accuracy of selecting modeling samples. Two memory parameters were designed to change the update method in traditional just-in-time learning model, which could reduce the amount of calculation and improve the prediction accuracy of dynamic fluid level. Compared with the traditional just-in-time learning algorithm, the improved method has better measurement accuracy and adaptation for the prediction of dynamic fluid levels. The example showed that the proposed method was fitted in with the standard of oil production and could be applied to actual production. ©, 2015, Northeastern University. All right reserved.

引用

页码：918 / 922

页数：4

共 10 条

[1]

Kadlec P., Grbic R., Gabrys B., Review of adaptation mechanisms for data-driven soft sensors, Computers and Chemical Engineering, 35, 1, pp. 1-24, (2011)

[2]

Luo J.-X., Shao H.-H., Developing dynamic soft sensors using multiple neural networks, Journal of Chemical Industry and Engineering, 54, 12, pp. 170-177, (2003)

[3]

Du W.L., Guan Z.Q., Qian F., The time series soft-sensor modeling based on Adaboost LS-SVM, The 8th World Congress on Intelligent Control and Automation(WCICA), pp. 1491-1495, (2010)

[4]

Wang H.Q., Li P., Gao F.R., Et al., Kernel classifier with adaptive structure and fixed memory for process diagnosis, AIChE Journal, 52, 10, pp. 3515-3531, (2006)

[5]

Liu Y., Jin F.-J., Gao Z.-L., Online identification of time-varying processes using just-in-time recursive kernel learning approach, Acta Automatica Sinica, 39, 5, pp. 602-609, (2013)

[6]

Ge Z.-Q., Liu Y., Song Z.-H., Et al., Local model based monitoring for nonlinear multiple mode process, Acta Automatica Sinica, 34, 7, pp. 792-797, (2008)

[7]

Cheng C., Chiu M.S., A new data-based methodology for nonlinear process modeling, Chemical Engineering Science, 59, 13, pp. 2801-2810, (2004)

[8]

Fujiwara K., Kano M., Hasebe S., Development of correlation-based pattern recognition algorithm and adaptive soft-sensor design, Control Engineering Practice, 20, 4, pp. 371-378, (2010)

[9]

Wang L.W., Wang X., Feng J.F., Subspace distance analysis with application to adaptive Bayesian algorithm for face recognition, Pattern Recognition, 39, 3, pp. 456-464, (2006)

[10]

Raich A., Cinar A., Statistical process monitoring and disturbance diagnosis in multivariable continuous processes, AIChE Journal, 42, 4, pp. 995-1009, (1994)

← 1 →