Soft sensor method for moisture content of well oil based on automatic spectral clustering and multiple extreme learning

doi:10.11949/j.issn.0438-1157.20151785

Abstract

Abstract:

Moisture content of the well oil is a key production variable in the oilfield, and it has great significance for improving the oil production efficiency by timely and accurate measurement of it. In order to overcome some deficiencies of the traditional manual measurement, the soft sensor technology is introduced to establish a soft sensor model based on automatic spectral clustering - multiple extreme learning machines (ASC-MELM). An automatic spectral clustering (ASC) algorithm is proposed and an improved firefly algorithm (FA) is applied to reach an optimal selection of the clustering number and the scale parameter. The proposed improved firefly algorithm (IFA) adopts a mechanism of jumping out of the current solution at a certain probability, which can avoid the deficiency of falling into the local optimal solution earlier of the traditional FA. For different training subsets after the clustering, the multiple extreme learning machines (ELM) are adopted to establish the different sub-models, in which IFA is used to reach an optimal selection of the hidden layer input weights, the hidden layer biases and the number of the hidden layer nodes. Finally, the output is obtained by calculating the weighted average of multiple sub-models. An application example of an oil well in a domestic oilfield is given. The simulation results show that the proposed method has better predicted accuracy and it is reasonable and effective to realize the soft sensor for moisture content of the well oil.

Key words: soft sensor, moisture content of well oil, spectral clustering, extreme learning machine, firefly algorithm, measurement, petroleum, model

摘要：

油井油液的含水率是石油生产中的一个重要参数，及时、准确的测量对提高采油生产效率具有重要的意义。针对传统人工测量所存在的不足，引入软测量技术，建立基于自动谱聚类与多极端学习机（automatic spectral clustering-multiple extreme learning machines, ASC-MELM）的软测量模型。提出一种自动谱聚类（spectral clustering, SC）算法，由改进的萤火虫算法（firefly algorithm, FA）对聚类数目和尺度参数进行优化选取，所提出的改进萤火虫算法（improved firefly algorithm, IFA）采用以一定概率跳出当前解的机制，避免传统FA过早陷入局部最优解的不足；对聚类后的不同训练子集，分别由极端学习机（extreme learning machine, ELM）建立子模型，由IFA对其中的隐含层输入权值、隐含层神经元的偏置和隐含层节点个数进行优化选取；最后，将多个子模型的结果取加权平均值输出。由国内某油田作业区一口生产井进行实例验证，结果表明所提出方法具有较高的预测精度，对于实现油井油液含水率的软测量是合理有效的。

关键词: 软测量, 油井油液含水率, 谱聚类, 极端学习机, 萤火虫算法, 测量, 石油, 模型

CLC Number:

TP273

LI Kun, HAN Ying, HUANG Haijiao. Soft sensor method for moisture content of well oil based on automatic spectral clustering and multiple extreme learning[J]. CIESC Journal, 2016, 67(7): 2925-2933.

李琨, 韩莹, 黄海礁. 基于自动谱聚类与多极端学习机模型的油井油液含水率软测量[J]. 化工学报, 2016, 67(7): 2925-2933.

References 27

[1]	李志明, 孔令富. 基于SVM的软测量在原油含水率估算中的应用[J]. 燕山大学学报, 2006, 30(4): 328-333. LI Z M, KONG L F. Application of soft sensor based on SVM on estimation of water cut of crude oil[J]. Journal of Yanshan University, 2006, 30(4): 328-333.
[2]	王丽娜, 刘翠玲. 基于CPN网络井口计量原油含水率预测模型[J]. 东北石油大学学报, 2009, 33(6): 101-104. WANG L N, LIU C L. Model for prediction of crude oil water content at wellhead metering based on CPN neural network[J]. Journal of Daqing Petroleum Institute, 2009, 33(6): 101-104.
[3]	吴良海. 基于粒子群优化RBF神经网络原油含水率预测[J]. 计算机仿真, 2010, 27(5): 261-263. WU L H. Prediction of crude oil moisture based on RBF neural network optimized by PSO[J]. Computer Simulation, 2010, 27(5): 261-263.
[4]	刘翠玲, 张路路, 王进旗, 等. 基于FOA-GRNN油井计量原油含水率的预测[J]. 计算机仿真, 2012, 29(11): 243-246. LIU C L, ZHANG L L, WANG J Q, et al. Application of FOA-GRNN to prediction of moisture content in crude oil of wellhead metering[J]. Computer Simulation, 2012, 29(11): 243-246.
[5]	王振雷, 唐苦, 王昕. 一种基于D-S和ARIMA的多模型软测量方法[J]. 控制与决策, 2014, 29(7): 1160-1166. WANG Z L, TANG K, WANG X. A multi-model soft sensing method based on D-S and ARIMA model[J]. Control and Decision, 2014, 29(7):1160-1166.
[6]	唐苦, 王昕, 王振雷. 基于证据合成规则的多模型软测量[J]. 控制理论与应用, 2014, 31(5):632-637. TANG K, WANG X, WANG Z L. Multi-model soft sensor based on Dempster-Shafer rule[J]. Control Theory & Applications, 2014, 31(5):632-637.
[7]	梅从立, 杨铭, 刘国海. 基于证据合成的高斯过程回归多模型软测量方法[J]. 化工学报, 2015, 66(11): 4555-4564. MEI C L, YANG M, LIU G H. A multi-model based soft sensor using evidence theory and Gaussian process regression[J]. CIESC Journal, 2015, 66(11): 4555-4564.
[8]	王开军, 张军英, 李丹, 等. 自适应仿射传播聚类[J]. 自动化学报, 2007, 33(12): 1242-1246. WANG K J, ZHANG J Y, LI D, et al. Adaptive affinity propagation clustering[J]. Acta Automatic Sinica, 2007, 33(12): 1242-1246.
[9]	嵇小辅, 张翔. 基于FCM与集成高斯过程回归的赖氨酸发酵软测量[J]. 智能系统学报, 2015, 10(1): 156-162. JI X F, ZHANG X. Soft measurement of lysine fermentation based on FCM and integrated Gaussian process regression[J]. CAAI Transactions on Intelligent Systems, 2015, 10(1): 156-162.
[10]	VON LUXBURG U. A tutorial on spectral clustering[J]. Statistics and Computing, 2007, 17(4): 395-416.
[11]	HU H, WANG X, YANG Z, et al. A spectral clustering approach to identifying cuts in wireless sensor networks[J]. Sensors Journal, IEEE, 2015, 15(3): 1838-1848.
[12]	WANG S, LU J, GU X, et al. Unsupervised discriminant canonical correlation analysis based on spectral clustering[J]. Neurocomputing, 2016, 171: 425-433.
[13]	LIU H, ZHAO F, JIAO L. Fuzzy spectral clustering with robust spatial information for image segmentation[J]. Applied Soft Computing, 2012, 12(11): 3636-3647.
[14]	MEHRKANOON S, ALZATE C, MALL R, et al. Multiclass semisupervised learning based upon kernel spectral clustering[J]. IEEE Transactions on Neural Networks and Learning Systems, 2015, 26(4): 720-733.
[15]	HUANG G B, ZHU Q Y, SIEW C K. Extreme learning machine: theory and applications[J]. Neurocomputing, 2006, 70(1): 489-501.
[16]	BREABAN M, LUCHIAN H. A unifying criterion for unsupervised clustering and feature selection[J]. Pattern Recognition, 2011, 44(4): 854-865.
[17]	YANG X S. Nature-inspired Metaheuristic Algorithms[M]. Beckington: Luniver Press, 2010.
[18]	LONG N C, MEESAD P, UNGER H. A highly accurate firefly based algorithm for heart disease prediction[J]. Expert Systems with Applications, 2015, 42(21): 8221-8231.
[19]	SAHU R K, PANDA S, PADHAN S. A hybrid firefly algorithm and pattern search technique for automatic generation control of multi area power systems[J]. International Journal of Electrical Power & Energy Systems, 2015, 64: 9-23.
[20]	OLATOMIWA L, MEKHILEF S, SHAMSHIRBAND S, et al. A support vector machine-firefly algorithm-based model for global solar radiation prediction[J]. Solar Energy, 2015, 115: 632-644.
[21]	BAYKASOGLU A, OZSOYDAN F B. Adaptive firefly algorithm with chaos for mechanical design optimization problems[J]. Applied Soft Computing, 2015, 36: 152-164.
[22]	YU S, ZHU S, MA Y, et al. Enhancing firefly algorithm using generalized opposition-based learning[J]. Computing, 2015: 1-14.
[23]	于剑, 程乾生. 模糊聚类方法中的最佳聚类数的搜索范围[J]. 中国科学(E辑), 2002, 32(2): 274-280. YU J, CHEN Q S. Search range of the optimal cluster number in fuzzy clustering [J]. Science in China (Series E), 2002, 32(2): 274-280.
[24]	王超, 王建辉, 顾树生, 等. 改进式混合增量极限学习机算法[J]. 控制与决策, 2015, 30(11): 1981-1986. WANG C, WANG J H, GU S S, et al. Improved hybrid incremental extreme learning machine algorithm[J]. Control & Decision, 2015, 30(11): 1981-1986.
[25]	田中大, 李树江, 王艳红, 等. 短期风速时间序列混沌特性分析及预测[J]. 物理学报, 2015, 64(3): 030506-1-12. TIAN Z D, LI S J, WANG Y H, et al. Chaotic characteristics analysis and prediction for short-term wind speed time series[J]. Acta Phys. Sin., 2015, 64(3): 030506-1-12.
[26]	李翔宇, 高宪文, 侯延彬. 基于在线动态高斯过程回归抽油井动液面软测量建模[J]. 化工学报, 2015, 6(6): 2150-2158. LI X Y, GAO X W, HOU Y B. Online dynamic Gaussian process regression for dynamic liquid level soft sensing of sucker-rod pumping well[J]. CIESC Journal, 2015, 6(6): 2150-2158.
[27]	王通, 高宪文, 刘文芳. 自适应软测量方法在动液面预测中的研究与应用[J]. 化工学报, 2014, 65(12): 4898-4904. WANG T, GAO X W, LIU W F. Adaptive soft sensor method and application in determination of dynamic fluid levels[J]. CIESC Journal, 2014, 65(12): 4898-4904.