东北大学学报（自然科学版）

东北大学学报:自然科学版 ›› 2015, Vol. 36 ›› Issue (7): 918-922.DOI: 10.12068/j.issn.1005-3026.2015.07.002

• 信息与控制 • 上一篇    下一篇

基于改进即时学习算法的动液面软测量建模

王通1， 高宪文1， 刘文芳2   

  1. (1.东北大学 信息科学与工程学院， 辽宁 沈阳110819； 2.沈阳工业大学 电气工程学院， 辽宁 沈阳110870)
  • 收稿日期:2014-05-06 修回日期:2014-05-06 出版日期:2015-07-15 发布日期:2015-07-15
  • 通讯作者: 王通
  • 作者简介:王通(1976-)，男，辽宁沈阳人，东北大学博士研究生; 高宪文(1955-)，男，辽宁沈阳人，东北大学教授，博士生导师.
  • 基金资助:
    国家自然科学基金资助项目(61433004)。

Soft Sensor for Determination of Dynamic Fluid Levels Based on Enhanced Just-in-Time Learning Algorithm

WANG Tong1， GAO Xian-wen1， LIU Wen-fang2   

  1. 1. School of Information Science & Engineering， Northeastern University， Shenyang 110819， China； 2. School of Electrical Engineering， Shenyang University of Technology， Shenyang 110870， China.
  • Received:2014-05-06 Revised:2014-05-06 Online:2015-07-15 Published:2015-07-15
  • Contact: WANG Tong
  • About author:-
  • Supported by:
    -

RichHTML

0

PDF (PC)

931

摘要： 油田动液面参数软测量预测应用中，软测量模型随生产的进行会逐步退化，导致预测结果偏差较大，无法在油田生产过程中加以使用.对此，提出采用基于子空间相似度的即时学习策略来对动液面预测模型进行自适应动态更新.通过对生产阶段数据进行子空间的相似度计算，提高建模样本选取的准确性.设计两个记忆参数改变以往即时学习策略模型的更新方法，在减少计算量的同时提高动液面的预测精度.与以往即时学习算法进行实验对比，结果表明，改进算法对油田动液面测量精度高，适应性强，符合油田生产标准，可以应用于油田实际生产.

关键词: 子空间, 即时学习, 模型更新, 相似度, 动液面

Abstract: 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.

Key words: subspace, just-in-time learning, model update, similarity, dynamic fluid level

中图分类号: