基于多源信息特征融合的抽油井动液面集成软测量建模

doi:10.11949/j.issn.0438-1157.20151673

摘要/Abstract

摘要：

针对传统抽油井动液面(DLL)检测只能依靠人工操作回声仪测试,无法实时在线检测的问题,提出基于多源信息特征融合的抽油井动液面集成软测量新方法。采用快速傅里叶变换(FFT)将抽油机悬点载荷及振动时域信号转换成频域信号;采用核主元分析(KPCA)提取悬点载荷及振动频谱和电功率、井口油、套压时域信号非线性特征;利用改进的模糊交互式自组织数据分析聚类(ISODATA)和高斯过程回归(GPR)融合时频信息特征,建立多个动态子模型;利用权重优化证据理论(D-S)构造的概率分配函数作为权值因子,对子模型输出进行集成以得到最终的DLL预测值。油田现场应用证明了该方法的有效性。

关键词: 信息融合, 动液面, 高斯过程回归, 预测, 石油, 动态建模

Abstract:

The dynamic liquid level (DLL) of an oil well is traditionally measured onsite by using the acoustic method. This method, however, has its limitation in determining real-time dynamic liquid level. A new ensemble soft-sensor approach of DLL based on the multi-source information feature fusion was proposed. The polish rod load and vibration signal in the time domain was transformed into the frequency domain using fast Fourier transform (FFT). The kernel principal component analysis (KPCA) was used to extract the nonlinear feature of the load and vibration spectral signal and the power, casing head pressure and tubing head pressure time signal. The improved fuzzy interactive self-organizing data analysis technique algorithm (ISODATA) and Gaussian process regression (GPR) were used to fuse time/frequency information feature and establish multiple sub-models. Then, the final DLL prediction model was obtained through the ensemble of the sub-models based on the weight factor calculated by optimized-weighted Dempster-Shafer (D-S) theory. The oil field application showed the validity of the proposed method.

Key words: information fusion, dynamic liquid level, Gaussian process regression, prediction, petroleum, dynamic modeling

中图分类号:

TP273

李翔宇, 高宪文, 李琨, 侯延彬. 基于多源信息特征融合的抽油井动液面集成软测量建模[J]. 化工学报, 2016, 67(6): 2469-2479.

LI Xiangyu, GAO Xianwen, LI Kun, HOU Yanbin. Ensemble soft sensor modeling for dynamic liquid level of oil well based on multi-source information feature fusion[J]. CIESC Journal, 2016, 67(6): 2469-2479.

参考文献 32

[1]	李兆敏, 林日亿, 付路长, 等. 有杆抽油系统效率分析及抽汲参数优化设计 [J]. 石油学报, 2005, 26 (5): 102-106. LI Z M, LIN R Y, FU L C, et al. Efficiency analysis of sucker-rod pumping system and optimal design of swabbing parameter [J]. Acta Petrolei Sinica, 2005, 26 (5): 102-106.
[2]	姚春冬. 提高抽油机井系统效率的计算机仿真分析 [J]. 石油学报, 2005, 26 (4): 106-110. YAO C D. Computer simulation for enhancing system efficiency of rod pumping well [J]. Acta Petrolei Sinica, 2005, 26 (4): 106-110.
[3]	董世民, 张喜顺, 吴长杰, 等. 抽油机井区块整体节能参数仿真优化方法 [J]. 石油学报, 2010, 31 (3): 475-479. DONG S M, ZHANG X S, WU C J, et al. Simulation and optimization method for the integral energy-saving suction parameters of rod pumping wells in an oil field [J]. Acta Petrolei Sinica, 2010, 31 (3): 475-479.
[4]	林日亿, 孙茂盛, 张邵东, 等. 有杆抽油泵沉没度的优化设计方法 [J]. 石油大学学报, 2005, 29 (4): 87-90. LIN R Y, SUN M S, ZHANG S D, et al. Optimization design method to determine submergence depth of sucker rod pump [J]. Journal of the University of Petroleum, 2005, 29 (4): 87-90.
[5]	董世民, 邢明明, 张红, 等. 基于系统效率最高的抽油机合理流压研究 [J]. 燕山大学学报, 2011, 35 (4): 296-301. DONG S M, XING M M, ZHANG H, et al. Study of reasonable flowing pressure of rod pumping wells based on maximum system efficiency [J]. Journal of Yanshan University, 2011, 35 (4): 296-301.
[6]	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.
[7]	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, 66 (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, 66 (6): 2150-2158.
[8]	SUYKENS J A K, VANDEWALLE J. Least squares support vector machine classifiers [J]. Neural Processing Letters, 1999, 9 (3): 293-300.
[9]	王华忠. 高斯过程及其在软测量建模中的应用 [J]. 化工学报, 2007, 58 (11): 2840-2845. WANG H Z. Gaussian process and its application to soft-sensor modeling [J]. Journal of Chemical Industry and Engineering (China), 2007, 58 (11): 2840-2845.
[10]	何志昆, 刘光斌, 赵曦晶, 等. 高斯过程回归方法综述 [J]. 控制与决策, 2013, 28 (8): 1121-1129. HE Z K, LIU G B, ZHAO X J, et al. Overview of Gaussian process regression [J]. Control and Decision, 2013, 28 (8): 1121-1129.
[11]	于涛, 王建林, 何坤, 等. 基于MPCA-GP的发酵过程分阶段软测量建模方法 [J]. 仪器仪表学报, 2013, 34 (12): 2703-2708. YU T, WANG J L, HE K, et al. Staged soft-sensor modeling method for fermentation process based on MPCA-GP [J]. Chinese Journal of Scientific Instrument, 2013, 34 (12): 2703-2708.
[12]	汤健, 郑秀萍, 赵立杰, 等. 基于频域特征提取与信息融合的磨机负荷软测量 [J]. 仪器仪表学报, 2010, 31 (10): 2161-2167. TANG J, ZHENG X P, ZHAO L J, et al. Soft sensing of mill load based on frequency domain feature extraction and information fusion [J]. Chinese Journal of Scientific Instrument, 2010, 31 (10): 2161-2167.
[13]	雷瑜, 杨慧中. 基于高斯过程和贝叶斯决策的组合模型软测量 [J]. 化工学报, 2013, 64 (12): 4434-4438. LEI Y, YANG H Z. Combination mode soft sensor based on Gaussian process and Bayesian committee machine [J]. CIESC Journal, 2013, 64 (12): 4434-4438.
[14]	汤健, 柴天佑, 丛秋梅, 等. 基于EMD和选择性集成学习算法的磨机负荷参数软测量 [J]. 自动化学报, 2014, 40 (9): 1853-1866. TANG J, CHAI T Y, CONG Q M, et al. Soft sensor approach for modeling mill load parameters based on EMD and selective ensemble learning algorithm [J]. Acta Automatica Sinica, 2014, 40 (9): 1853-1866.
[15]	李修亮,苏宏业,褚健. 基于在线聚类的多模型软测量建模方法 [J]. 化工学报, 2007, 58 (11): 2834-2839. LI X L, SU H Y, CHU J. Multiple models soft-sensing technique based on online clustering arithmetic [J]. Journal of Chemical Industry and Engineering (China), 2007, 58 (11): 2834-2839.
[16]	吴敏, 丁雷, 曹卫华, 等. 铅锌烧结过程烧穿点的集成预测模型 [J]. 控制理论与应用, 2009, 26 (7): 739-744. WU M, DING L, CAO W H, et al. An integrated prediction model for burn-through-point in lead-zinc sintering process [J]. Control Theory & Applications, 2009, 26 (7): 739-744.
[17]	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.
[18]	汤健, 柴天佑, 赵立杰, 等. 基于振动频谱的磨矿过程球磨机负荷参数集成建模方法 [J]. 控制理论与应用, 2012, 29 (2): 183-191. TANG J, CHAI T Y, ZHAO L J, et al. Ensemble modeling for parameters of ball-mill load in grinding process based on frequency spectrum of shell vibration [J]. Control Theory & Applications, 2012, 29 (2): 183-191.
[19]	汤健, 柴天佑, 余文, 等. 在线KPLS建模方法及在磨机负荷参数集成建模中的应用 [J]. 自动化学报, 2013, 39 (5): 471-486. TANG J, CHAI T Y, YU W, et al. On-line KPLS algorithm with application to ensemble modeling parameters of mill load [J]. Acta Automatica Sinica, 2013, 39 (5): 471-486.
[20]	李丽娟, 宋坤, 赵英凯. 基于仿射传播聚类的ARA发酵过程建模 [J]. 化工学报, 2011, 62 (8): 2116-2121. LI L J, SONG K, ZHAO Y K. Modeling of ARA fermentation based on affinity propagation clustering [J]. CIESC Journal, 2011, 62 (8): 2116-2121.
[21]	张文清, 傅雨佳, 杨慧中. 基于改进聚类和加权bagging的多模型软测量建模 [J]. 化工学报, 2012, 63 (9): 2697-2702. ZHANG W Q, FU Y J, YANG H Z. Multi-model soft-sensor modeling based on improved clustering and weighted bagging [J]. CIESC Journal, 2012, 63 (9): 21697-2702.
[22]	何岩峰, 吴晓东, 韩国庆, 等. 示功图频谱分析新方法 [J]. 石油学报, 2008, 29 (4): 619-624. HE Y F, WU X D, HAN G Q, et al. Frequency spectrum analysis method for recognition of dynamometer card [J]. Acta Petrolei Sinica, 2008, 29 (4): 619-624.
[23]	曹鹏飞, 罗雄麟. 化工过程软测量建模方法研究进展 [J]. 化工学报, 2013, 64 (3): 788-800. CAO P F, LUO X L. Modeling of soft sensor for chemical process [J]. CIESC Journal, 2013, 64 (3): 788-800.
[24]	汤健, 赵立杰, 岳恒, 等. 基于多源数据特征融合的球磨机负荷软测量 [J]. 浙江大学学报, 2010, 44 (7): 1406-1413. TANG J, ZHAO L J, YUE H, et al. Soft sensor for ball mill load based on multi-source data feature fusion [J]. Journal of Zhejiang University, 2010, 44 (7): 1406-1413.
[25]	MOGHADDAM B. Principal manifolds and probabilistic subspaces for visual recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24 (6): 780-788.
[26]	TWINING C J, TAYLOR C J. The use of kernel principal component analysis to model data distributions [J]. Pattern Recognition, 2003, 36 (1): 217-227.
[27]	李海波, 柴天佑, 岳恒. 浮选工艺指标KPCA-ELM软测量模型及应用 [J]. 化工学报, 2012, 63 (9): 2892-2898. LI H B, CHAI T Y, YUE H. Soft sensor of technical indices based on KPCA-ELM and application for flotation process [J]. CIESC Journal, 2012, 63 (9): 2892-2898.
[28]	王强, 田学民. 基于KPCA-LSSVM的软测量建模方法 [J]. 化工学报, 2011, 62 (10): 2813-2817. WANG Q, TIAN X M. Soft sensing based on KPCA and LSSVM [J]. CIESC Journal, 2011, 62 (10): 2813-2817.
[29]	LI K, GAO X W, ZHOU H B, et al. Fault diagnosis for down-hole conditions of beam pumping unit based on improved fuzzy ISODATA dynamic clustering algorithm [C]//Proc. 2013 10th International Conference on Fuzzy Systems and Knowledge Discovery. Shenyang, China: IEEE Computer Society, 2013: 279-284.
[30]	李琨. 基于示功图的游梁式抽油机井下故障诊断方法研究[D]. 沈阳: 东北大学, 2013. LI K. Study on diagnostic method for down-hole faults of the beam pumping unit based on dynamometer card [D]. Shenyang: Northeastern University, 2013.
[31]	田中大, 高宪文, 李琨. 基于KPCA与LSSVM的网络控制系统时延预测方法 [J]. 系统工程与电子技术, 2013, 35 (6): 1281-1285. TIAN Z D, GAO X W, LI K. Networked control system time-delay prediction method based on KPCA and LSSVM [J]. Systems Engineering and Electronics, 2013, 35 (6): 1281-1285.
[32]	PETELIN D, GRANCHAROVA A, KOCIJAN J. Evolving Gaussian process models for prediction of ozone concentration in the air [J]. Simulation Modelling Practice and Theory, 2013, 24 (6): 68-80.