双作用分层抽油泵故障诊断技术
|
摘要
针对我国油田的多层系、非均质构造，国内各油田大多采用注水开发方式来提高采收率，但同时也造成了各油层间存在较大的物性差异，导致了严重的层间干扰问题。为解决这一问题而研制开发了一种新型的采油设备，即双作用分层抽油系统。目前该系统在一些油田已投入使用。现有的采油系统领域的故障诊断技术难以满足对该系统进行故障诊断的需要，国内外也没有这方面的研究报导。人工神经网络是近几年迅速发展的热点和前沿问题之一，同传统的专家系统相比，神经网络专家系统在知识获取、并行处理、适应性学习、容错能力等方面都具有明显的优越性，这在一定程度上满足了对复杂、非平稳、有干扰的抽油系统的井下示功图进行识别的要求。
目前应用的若干神经网络模型中，BP网络模型是人们认识最早应用最广泛的一种，它也是在设备故障诊断领域应用最成功的一种神经网络模型。本文简要论述了BP算法，在总结了其缺点和不足的基础上，用改进的BP动量算法建立神经网络专家系统。
双作用抽油泵是适应分层开采的一种新式抽油泵，文章在简要论述双作用抽油泵的结构及工作原理的基础上重点对双作用分层抽油系统的力学特性进行分析，建立预测模型，利用显示差分法求解，得到抽油杆柱各个截面上的受力状态，特别是光杆处的位移和载荷随时间的变化规律，并绘出任意截面的示功图。这将为对整个抽油系统进行静态和动态特性分析，进而为系统参数合理选择、各部件优化设计和设备的故障诊断奠定基础。文中结合常规有杆抽油系统的故障图谱加上作者通过计算、模拟等手段构造出双作用分层抽油系统部分故障图谱，此图谱作为样本输入集可用于神经网络模型的建立。本文还提出了一种基于MATLAB语言工具箱的示功图的预处理方法及双作用分层抽油系统井下故障诊断专家系统的总体方案，并分别对各个模块的功能及其整个系统的运行机制进行了论述，系统地阐明了神经网络诊断模块的初始化、训练和测试过程。借助MATLAB语言系统及其工具箱完成了故障诊断专家系统软件的设计，并用试验井的实测示功图对其诊断结果的正确性进行了测试。本文所开发的故障诊断专家系统软件解决了分层采油系统的故障诊断问题，有利于双作用分层抽油系统的推广应用，对分层采油技术有较重要的意义。
Aiming the interbedded disturb problem of multilayer heterosphere oil field, most oil fields adopt the waterflood development to improve recovery ratio, but it can create greatly divergence and cause grave interfere problem in every stratum. A new sucker-rod pumping system of double-acting separate recovery is developed in order to solve the problem, now it is used in most oil fields in our country. The present fault diagnosis technique can't well suit to diagnose the pumping system. So far, the public reports in the field are few at home and overseas. The artificial neural networks grow rapidly and become to be one of the most advanced problems lately. In comparison with traditional expert system, the artificial neural nets expert system is possessed of obvious superiority in the aspects of knowledge acquisition, parallel reasoning, adaptability studying, error containing capability and so on. It satisfies the needs to recognize the down-hole dynagraph of sucker-rod pumping system that is complicated, nonst
eady and disturbed to some extent.
In many kinds of artificial neural networks, BP neural nets is one of the most pioneer and common models, it is successfully applied to equipment fault diagnosis. In the paper, BP neural nets is briefly introduced, and based on the shortcoming of the BP neural nets are summed up, expert system of neural networks are established by using improved BP momentum algorithm.
Double-acting pump is a new type pump for separate layer recovery, in this paper, the structure and work principle of double-acting pump are briefly introduced, and the mechanics characteristics of separate layer recovery are stressly analysised, the prediction model has been established, we can gain the forced condition of each section of sucker rod by using the display difference method to divide, and can paint the dynagraph of each section of sucker rod string. This will establish base for analyzing static and dynamic behavior, selecting parameters, optimizing design and diagnosing fault. In the paper, the diagnosis atlas of double-acting pumping system is established by calculating, simulating and uniting the diagnosis atlas of rule pumping system. The atlas is used to established modules of neural networks as specimen input set. A pretreatment method of MATLAB-Toolbox-based is proposed so that a computer can recognize the real dynagraph and the total scheme of double-acting fault diagnosis expert system
is presented. Function of various modules and run mechanism of the expert system is discussed. The course to initialize, train and test for neural network modules has been illustrated in detail. The fault diagnosis expert system software has been designed with the MATLAB-Toolbox, then the correctness of diagnostic conclusions for the expert system is verified with the real dynagraph of experimental well. Programs of diagnosis system has been designed, it may provide a powerful tool for fault diagnosis of separate layer recovery system, and has an important sense for the technique development of separate layer recovery.
目前应用的若干神经网络模型中，BP网络模型是人们认识最早应用最广泛的一种，它也是在设备故障诊断领域应用最成功的一种神经网络模型。本文简要论述了BP算法，在总结了其缺点和不足的基础上，用改进的BP动量算法建立神经网络专家系统。
双作用抽油泵是适应分层开采的一种新式抽油泵，文章在简要论述双作用抽油泵的结构及工作原理的基础上重点对双作用分层抽油系统的力学特性进行分析，建立预测模型，利用显示差分法求解，得到抽油杆柱各个截面上的受力状态，特别是光杆处的位移和载荷随时间的变化规律，并绘出任意截面的示功图。这将为对整个抽油系统进行静态和动态特性分析，进而为系统参数合理选择、各部件优化设计和设备的故障诊断奠定基础。文中结合常规有杆抽油系统的故障图谱加上作者通过计算、模拟等手段构造出双作用分层抽油系统部分故障图谱，此图谱作为样本输入集可用于神经网络模型的建立。本文还提出了一种基于MATLAB语言工具箱的示功图的预处理方法及双作用分层抽油系统井下故障诊断专家系统的总体方案，并分别对各个模块的功能及其整个系统的运行机制进行了论述，系统地阐明了神经网络诊断模块的初始化、训练和测试过程。借助MATLAB语言系统及其工具箱完成了故障诊断专家系统软件的设计，并用试验井的实测示功图对其诊断结果的正确性进行了测试。本文所开发的故障诊断专家系统软件解决了分层采油系统的故障诊断问题，有利于双作用分层抽油系统的推广应用，对分层采油技术有较重要的意义。
Aiming the interbedded disturb problem of multilayer heterosphere oil field, most oil fields adopt the waterflood development to improve recovery ratio, but it can create greatly divergence and cause grave interfere problem in every stratum. A new sucker-rod pumping system of double-acting separate recovery is developed in order to solve the problem, now it is used in most oil fields in our country. The present fault diagnosis technique can't well suit to diagnose the pumping system. So far, the public reports in the field are few at home and overseas. The artificial neural networks grow rapidly and become to be one of the most advanced problems lately. In comparison with traditional expert system, the artificial neural nets expert system is possessed of obvious superiority in the aspects of knowledge acquisition, parallel reasoning, adaptability studying, error containing capability and so on. It satisfies the needs to recognize the down-hole dynagraph of sucker-rod pumping system that is complicated, nonst
eady and disturbed to some extent.
In many kinds of artificial neural networks, BP neural nets is one of the most pioneer and common models, it is successfully applied to equipment fault diagnosis. In the paper, BP neural nets is briefly introduced, and based on the shortcoming of the BP neural nets are summed up, expert system of neural networks are established by using improved BP momentum algorithm.
Double-acting pump is a new type pump for separate layer recovery, in this paper, the structure and work principle of double-acting pump are briefly introduced, and the mechanics characteristics of separate layer recovery are stressly analysised, the prediction model has been established, we can gain the forced condition of each section of sucker rod by using the display difference method to divide, and can paint the dynagraph of each section of sucker rod string. This will establish base for analyzing static and dynamic behavior, selecting parameters, optimizing design and diagnosing fault. In the paper, the diagnosis atlas of double-acting pumping system is established by calculating, simulating and uniting the diagnosis atlas of rule pumping system. The atlas is used to established modules of neural networks as specimen input set. A pretreatment method of MATLAB-Toolbox-based is proposed so that a computer can recognize the real dynagraph and the total scheme of double-acting fault diagnosis expert system
is presented. Function of various modules and run mechanism of the expert system is discussed. The course to initialize, train and test for neural network modules has been illustrated in detail. The fault diagnosis expert system software has been designed with the MATLAB-Toolbox, then the correctness of diagnostic conclusions for the expert system is verified with the real dynagraph of experimental well. Programs of diagnosis system has been designed, it may provide a powerful tool for fault diagnosis of separate layer recovery system, and has an important sense for the technique development of separate layer recovery.
引文
[1] 杜永军，王金东，管荣达等．两层分采同步抽油技术．大庆石油学院学报，1999，23(2)：57～59
[2] 钟秉林，黄仁．机械故障诊断学．机械工业出版社，1997
[3] 黄文虎，夏松波等．设备故障诊断原理、技术及应用．北京：科学出版社，1997
[4] 程慧霞等．用C++建造专家系统．北京：电子工业出版社，1996
[5] Derek H. J., Jennings J. W., Morgan S. M. Sucker rod pumping unit diagnostics using an ES. SPE 17318
[6] Svinos J. G. Successful application of microcomputers to analyze sucker rod pumps. SPE 17789
[7] 杨叔子等．基于知识的诊断推理．北京：清华大学出版社，南宁：广西科学技术出版社，1993
[8] Weisbin C. R., et al. Minimal Cut-Set Methodology for Artificial Intelligence Applications. DE84-016674
[9] Kumar A. N. Function-Based Reasoning: An Introduction. Applied Artificial Intelligence, 1994, Vol. 8, No.2
[10] 裴峻峰，杨其俊．机械故障诊断技术．石油大学出版社，1996
[11] 佘梅卿，申秀丽等．分层采油技术的研究与应用．石油机械，1995，23(12)：3～49
[12] 姚红星，席风岭等．用于低产和边远油井的活动采油装备．石油机械，1998，26(6)：30～31
[13] 王金尔，杜永军，王庆丰．低产油田螺杆泵机动间歇采油技术及设备．石油机械，1999，27(4)：27～28
[14] 王金东，杜永军，陈浩然．机动间歇注水技术．大庆石油学院学报，1999，23(4)：56～57
[15] 王金东，杜永军等．低产油田机动间歇注水技术及设备．石油机械，2000，28(2)
[16] S. G. Gibbs and A. B. Neely. Computer Diagnosis of Down-hole Conditions in Sucker Rod Pumping wells. J. Pet. Tech. (January 1966)91～98
[17] G. Gibbs. Method of Determining Sucker Rod Pump Performance. U. S. Patent 3, 343, 409, Sept 26, 1967
[18] 崔振华，余国安等．有杆抽油系统．北京：石油工业出版社，1994
[19] P. Schirmer, P. Toutain. Use of advanced pattern recognition and knowledge based system in analyzing dynamometer cards. SPE 22305
[20] 张嗣伟．有杆泵抽油诊断的专冢系统．石油机械，1991，19(11)：33～44
[21] E. R. Martinez, W. J. Moreno, V. I. Castillo and J. A. Moreno. Rod pumping expert system. SPE 26246
[22] 潘志坚，葛家理．自适应神经网络示功图识别．石油学报，1996，17(3)：104～109
[23] W. S. McCulloch and W. Pitts. A Logical Calculations of the Ideas Immanent in Nervous Activity. Bulletin of Mathematical Biophysics, 1943, Vol. 5: 115～133
[24] J. Hertz, et al. Introduction to the Theory of Neural Computation. Addison-Wesley Publishing Company, 1991
[25] Stephen I. Gallant. Connectionist expert systems. Communication of the ACM, 1988, 31(2): 152～169
[26] 沈迪成，艾万诚，盛曾顺等．抽油泵．北京：石油工业出版社，1994：8～97
[27] 邬亦炯，刘卓钧，赵贵祥等．抽油机．北京：石油工业出版社，1994：52～82
[28] D. J. Schafer, and J. W. Jennings. An Investion of Analytical and Numerical Sucker Rod Pumping Mathemetical Models. SPE 16919, 1987
[29] 王金尔，陈浩然，杜永军．两层分采同步抽油系统故障诊断模型的数值分析法．机械强度，2002，24(2)：172～175
[30] S. G. Gibbs. Predicting the Behavior of Sucker Rod Pumping Systems. SPE 588, 1963
[31] 陈家林．有杆抽油井井下功图的一种快速计算法．石油学报，Vol 9(3)，1988
[32] 王金东，陈浩然，杜永军．分层有杆抽油系统诊断模型的反问题计算法．应用力学学报，2002，19(2)：100～103
[33] 蔡东升，王金东，范纪国．有杆抽油系统预测模型的隐式差分法．石油机械，2002，30(2)：40～42
[34] 张嗣伟．有杆泵抽油诊断的专家系统．石油机械，1991，19(11)：33～40
[35] J. D. Rogers, G. G. Guffey, W. J. B. Oldham. Artificial Neural Networks for Identification of Beam Pump Dynamometer Load Cards. SPE 20651. 1990
[36] 冯定，周迪勋．神经网络有杆泵诊断专家系统．石油机械，1996，24(1)：29～33
[37] 庞振国，袁秀明．抽油井的声测技术．石油钻采工艺，1990，12(6)：63～65
[38] 王金东，蔡东升，张嘉钟，刘树林．基于神经网络的两层分采同步抽油系统井下故障诊断技术．中国机械工程，2002，13(15)：1302～1305
[39] 张培强．MATLAB语言——演算纸式的科学工程计算语言．合肥：中国科学技术大学出版社，1995
[40] 施阳，李俊等．MATLAB语言工具箱二——TOOLBOX实用指南．西安：西北工业大学出版社，1998年5月
[41] 王学辉，张明辉等．MATLAB6.1最新应用详解．中国水利水电出版社，2002
[42] 丛爽．面向MATLAB工具箱的神经网络理论与应用．合肥：中国科学技术大学出版社，1998
[43] 王金东，李枫，杜永军．两层分采有杆抽油井示功图预测．石油矿场机械，2001，30(1)：7～9
[44] 刘合，王广昀等．当代有杆泵抽油系统．石油工业出版社，2000
[2] 钟秉林，黄仁．机械故障诊断学．机械工业出版社，1997
[3] 黄文虎，夏松波等．设备故障诊断原理、技术及应用．北京：科学出版社，1997
[4] 程慧霞等．用C++建造专家系统．北京：电子工业出版社，1996
[5] Derek H. J., Jennings J. W., Morgan S. M. Sucker rod pumping unit diagnostics using an ES. SPE 17318
[6] Svinos J. G. Successful application of microcomputers to analyze sucker rod pumps. SPE 17789
[7] 杨叔子等．基于知识的诊断推理．北京：清华大学出版社，南宁：广西科学技术出版社，1993
[8] Weisbin C. R., et al. Minimal Cut-Set Methodology for Artificial Intelligence Applications. DE84-016674
[9] Kumar A. N. Function-Based Reasoning: An Introduction. Applied Artificial Intelligence, 1994, Vol. 8, No.2
[10] 裴峻峰，杨其俊．机械故障诊断技术．石油大学出版社，1996
[11] 佘梅卿，申秀丽等．分层采油技术的研究与应用．石油机械，1995，23(12)：3～49
[12] 姚红星，席风岭等．用于低产和边远油井的活动采油装备．石油机械，1998，26(6)：30～31
[13] 王金尔，杜永军，王庆丰．低产油田螺杆泵机动间歇采油技术及设备．石油机械，1999，27(4)：27～28
[14] 王金东，杜永军，陈浩然．机动间歇注水技术．大庆石油学院学报，1999，23(4)：56～57
[15] 王金东，杜永军等．低产油田机动间歇注水技术及设备．石油机械，2000，28(2)
[16] S. G. Gibbs and A. B. Neely. Computer Diagnosis of Down-hole Conditions in Sucker Rod Pumping wells. J. Pet. Tech. (January 1966)91～98
[17] G. Gibbs. Method of Determining Sucker Rod Pump Performance. U. S. Patent 3, 343, 409, Sept 26, 1967
[18] 崔振华，余国安等．有杆抽油系统．北京：石油工业出版社，1994
[19] P. Schirmer, P. Toutain. Use of advanced pattern recognition and knowledge based system in analyzing dynamometer cards. SPE 22305
[20] 张嗣伟．有杆泵抽油诊断的专冢系统．石油机械，1991，19(11)：33～44
[21] E. R. Martinez, W. J. Moreno, V. I. Castillo and J. A. Moreno. Rod pumping expert system. SPE 26246
[22] 潘志坚，葛家理．自适应神经网络示功图识别．石油学报，1996，17(3)：104～109
[23] W. S. McCulloch and W. Pitts. A Logical Calculations of the Ideas Immanent in Nervous Activity. Bulletin of Mathematical Biophysics, 1943, Vol. 5: 115～133
[24] J. Hertz, et al. Introduction to the Theory of Neural Computation. Addison-Wesley Publishing Company, 1991
[25] Stephen I. Gallant. Connectionist expert systems. Communication of the ACM, 1988, 31(2): 152～169
[26] 沈迪成，艾万诚，盛曾顺等．抽油泵．北京：石油工业出版社，1994：8～97
[27] 邬亦炯，刘卓钧，赵贵祥等．抽油机．北京：石油工业出版社，1994：52～82
[28] D. J. Schafer, and J. W. Jennings. An Investion of Analytical and Numerical Sucker Rod Pumping Mathemetical Models. SPE 16919, 1987
[29] 王金尔，陈浩然，杜永军．两层分采同步抽油系统故障诊断模型的数值分析法．机械强度，2002，24(2)：172～175
[30] S. G. Gibbs. Predicting the Behavior of Sucker Rod Pumping Systems. SPE 588, 1963
[31] 陈家林．有杆抽油井井下功图的一种快速计算法．石油学报，Vol 9(3)，1988
[32] 王金东，陈浩然，杜永军．分层有杆抽油系统诊断模型的反问题计算法．应用力学学报，2002，19(2)：100～103
[33] 蔡东升，王金东，范纪国．有杆抽油系统预测模型的隐式差分法．石油机械，2002，30(2)：40～42
[34] 张嗣伟．有杆泵抽油诊断的专家系统．石油机械，1991，19(11)：33～40
[35] J. D. Rogers, G. G. Guffey, W. J. B. Oldham. Artificial Neural Networks for Identification of Beam Pump Dynamometer Load Cards. SPE 20651. 1990
[36] 冯定，周迪勋．神经网络有杆泵诊断专家系统．石油机械，1996，24(1)：29～33
[37] 庞振国，袁秀明．抽油井的声测技术．石油钻采工艺，1990，12(6)：63～65
[38] 王金东，蔡东升，张嘉钟，刘树林．基于神经网络的两层分采同步抽油系统井下故障诊断技术．中国机械工程，2002，13(15)：1302～1305
[39] 张培强．MATLAB语言——演算纸式的科学工程计算语言．合肥：中国科学技术大学出版社，1995
[40] 施阳，李俊等．MATLAB语言工具箱二——TOOLBOX实用指南．西安：西北工业大学出版社，1998年5月
[41] 王学辉，张明辉等．MATLAB6.1最新应用详解．中国水利水电出版社，2002
[42] 丛爽．面向MATLAB工具箱的神经网络理论与应用．合肥：中国科学技术大学出版社，1998
[43] 王金东，李枫，杜永军．两层分采有杆抽油井示功图预测．石油矿场机械，2001，30(1)：7～9
[44] 刘合，王广昀等．当代有杆泵抽油系统．石油工业出版社，2000