Design method, device and equipment for lifting system of sucker-rod pump of oil pumping unit and storage medium

Abstract

The invention discloses an oil pumping unit sucker-rod pump lifting system design method, device and equipment and a storage medium, and the method comprises the steps: obtaining a main control factor analysis result of the oil pumping unit sucker-rod pump lifting system design by combining an existing oil pumping unit sucker-rod pump lifting system design influence factor set and a main control factor analysis model of an oil field; performing data expansion on the main control factor analysis results through simulation, and performing clustering analysis fusion on the main control factor analysis results after expansion and before expansion to obtain a multi-class design sample library of the pumping unit sucker-rod pump lifting system; feature value construction is carried out on each type of design sample libraries, geological comprehensive indexes, lifting design comprehensive indexes and lifting operation effect comprehensive indexes corresponding to each type of design sample libraries are obtained, and the design sample libraries matched with the geological development conditions of the rod pumped well to be designed are searched for. The invention aims to design the pumping unit sucker-rod pump lifting system capable of being matched with geological reservoir physical properties and development characteristics, and provides effective guidance for the design of a pumping unit well lifting scheme.

Description

Technical Field

[0001] The invention relates to the field of oil production engineering in the petroleum industry, and in particular to a design method, device, equipment and storage medium for a pumping rod pump lifting system. Background Art

[0002] The design of the pumping rod pump lifting system is to determine the reasonable pumping parameters and supporting facilities based on the reservoir production allocation and current production conditions. Usually, the method for determining the design of the pumping rod pump lifting system is: first take a certain range of submergence, and select the minimum pump diameter that can meet the bottom liquid supply; the sucker rod combination is selected according to a simple empirical chart. After the pumping parameters are determined, the calculation method provided by the American API Association is used to calculate the sucker rod load, donkey head load, crank torque, motor power, etc. to check whether their values ​​are within the permitted range. At present, the commonly used design methods for pumping rod pump lifting systems at home and abroad can be summarized as follows: empirical formula method, API recommendation method, chart method, prediction model method, and big data recommendation method.

[0003] API recommendation method: It is a chart recommendation design method. This method not only has a strong theoretical basis, but also is easy to use. It is between the empirical formula method and the prediction model method. Li Ce et al. studied how to use the API method to design the sucker rod string and gave detailed usage steps, making this method more widely applicable in the sucker rod string design process. He Dongsheng et al. analyzed the theoretical basis of the API evaluation method for pipeline corrosion defects and derived the evaluation formula of the API evaluation method.

[0004] Chart method: After a certain amount of research, the design experience and summary of the pumping rod pump lifting system of the oil pumping unit were summarized and a guiding chart with language description and corresponding scores was developed. In order to make it easier to use the flexible sucker rod pumping unit chart selection method, Fan Qingzhu et al. conducted a brief theoretical analysis of the flexible continuous sucker rod pumping unit chart selection method and developed a corresponding program. Zhang Yanting et al. analyzed and derived the theoretical calculation formula of the oil pump displacement coefficient, and on this basis drew a selection diagram of the oil pump displacement coefficient and reasonable submergence used in the new series of walking beam pumping units and oil pumping units, which is convenient for on-site workers and technicians to use.

[0005] Prediction model method: Computer prediction simulation is to establish a dynamic relationship model between system parameters based on the coupling relationship between the components of the rod pumping system, obtain the boundary conditions and initial conditions of the model according to the movement law of the pumping well, and use the numerical solution method to realize the calculation of the model through the computer to obtain the parameters of a certain position of the system at a certain time, corresponding to the working condition of the system. Computer simulation prediction technology is mainly used in the prediction of system dynamic parameters. Gibbs et al. organized the wave equation of the pumping rod into a general mathematical model, and used the finite difference method to obtain some numerical solutions of the system parameters. Zhu Daojun, Wang Yuandi et al. used the IPR curve calculated by Padden and Vogel equations to predict the fluid supply of the oil well, and used the deep well pump displacement formula to determine the pumping parameters.

[0006] Big data recommendation method: Use big data analysis to mine the potential value and rules of data and find similar samples from massive similar databases. In accordance with the production and management needs of Daqing Oilfield, Zhang Jiamin et al. divided the parameters of the rod pumping system into oil well parameters, system parameters and working parameters, established a mathematical model of the system, further explored the working conditions and load functions of the pumping pump, compiled a set of calculation procedures for the main parameters of the pumping system, and gave the selection method and selection procedure for the energy-saving working condition parameters of the pumping system.

[0007] In summary, the current design of the pumping rod pump lifting system mainly relies on the above methods and establishes corresponding analytical models. Although the above models are based on strict theoretical foundations and show certain effects in practical applications, it is still difficult to accurately consider the complex geological, fluid and wellbore actual conditions. Some parameters need to be idealized and data loss often occurs. Summary of the invention

[0008] In response to the problems existing in the prior art, the present invention provides a design method, device, equipment and storage medium for a pumping rod pump lifting system, with the aim of designing a pumping rod pump lifting system that can match the geological reservoir physical properties and development characteristics, and provide effective guidance for the design of pumping well lifting schemes.

[0009] In order to solve the above technical problems, the present invention is implemented by the following technical solutions:

[0010] According to a first aspect of the present invention, a method for designing a lifting system of a pumping rod pump is provided, comprising:

[0011] Combining the design influencing factor set and main control factor analysis model of the existing pumping rod pump lifting system in the oil field, the main control factor analysis results of the design of the pumping rod pump lifting system are obtained;

[0012] Data expansion is performed on the main control factor analysis results through simulation, and cluster analysis and fusion are performed on the main control factor analysis results after expansion and the main control factor analysis results before expansion to obtain a multi-class design sample library of the pumping rod pump lifting system;

[0013] The characteristic values ​​of each type of design sample library are constructed to obtain the geological comprehensive index, lifting design comprehensive index and lifting operation effect comprehensive index corresponding to each type of design sample library;

[0014] According to the geological comprehensive indicators, lifting design comprehensive indicators and lifting operation effect comprehensive indicators corresponding to the multi-category design sample library, find the design sample library that matches the geological development conditions of the pumping well to be designed;

[0015] The lifting system of the pumping rod pump is designed using a design sample library that matches the geological development conditions of the pumping well to be designed.

[0016] In a possible implementation of the first aspect, the acquisition of the design influencing factor set of the existing pumping rod pump lifting system of the oil field is specifically as follows:

[0017] Obtain the original design data of the existing pumping rod pump lifting system in the oil field;

[0018] A correlation analysis is performed on the original design data, characteristic indicators related to the design of the pumping rod pump lifting system of the oil field are selected, and a set of influencing factors for the design of the pumping rod pump lifting system of the existing oil field pumping unit is formed.

[0019] In a possible implementation manner of the first aspect, the performing correlation analysis on the original design data specifically includes:

[0020] The correlation analysis of the characteristic indicators in the original design data is performed by Pearson.

[0021] In a possible implementation manner of the first aspect, the data expansion of the main control factor analysis result through simulation is specifically:

[0022] The DeepinSite simulation software is used to perform data expansion on the main controlling factor analysis results to obtain expanded main controlling factor analysis results.

[0023] In a possible implementation of the first aspect, searching for a design sample library that matches the geological development conditions of the pumping well to be designed according to the geological comprehensive indicators, lifting design comprehensive indicators, and lifting operation effect comprehensive indicators corresponding to the multiple types of design sample libraries includes:

[0024] The Euclidean distance matching algorithm is used to find a design sample library that matches the geological development conditions of the pumping well to be designed from the geological comprehensive indicators, lifting design comprehensive indicators and lifting operation effect comprehensive indicators corresponding to multiple types of design sample libraries.

[0025] In a possible implementation of the first aspect, after designing a pumping rod pump lifting system using a design sample library matching the geological development conditions of the pumping well to be designed, the method further includes:

[0026] The design scheme is evaluated using the effect quantification evaluation model and the comprehensive decision-making evaluation model.

[0027] In a possible implementation of the first aspect, the main controlling factor analysis model uses the production of the pumping well as the label data, and the design data of the existing pumping rod pump lifting system of the oil field as the feature data input model, establishes a pumping well production regression model based on MID, XGBoost and LightGBM and calculates the feature weights, uses the root mean square error, determination coefficient and mean absolute error to evaluate the prediction effect, and selects the model with the best performance.

[0028] According to a second aspect of the present invention, there is provided a design device for a pumping rod pump lifting system, characterized in that it comprises:

[0029] The main control factor analysis module is used to combine the influencing factor set of the existing pumping rod pump lifting system design in the oil field and the main control factor analysis model to obtain the main control factor analysis results of the pumping rod pump lifting system design;

[0030] The cluster analysis module never performs data expansion on the main control factor analysis results through simulation, performs cluster analysis fusion on the main control factor analysis results after expansion and the main control factor analysis results before expansion, and obtains a multi-class design sample library of the pumping rod pump lifting system;

[0031] The characteristic value construction module is used to construct characteristic values ​​for each type of design sample library, and obtain the geological comprehensive index, lifting design comprehensive index and lifting operation effect comprehensive index corresponding to each type of design sample library;

[0032] A matching search module is used to search for a design sample library that matches the geological development conditions of the pumping well to be designed based on the geological comprehensive indicators, lifting design comprehensive indicators and lifting operation effect comprehensive indicators corresponding to the multiple types of design sample libraries;

[0033] The design module is used to design the lifting system of the pumping rod pump by using the design sample library matching the geological development conditions of the pumping well to be designed.

[0034] According to a third aspect of the present invention, there is provided a device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method for designing a lifting system for a pumping rod pump when executing the computer program.

[0035] According to a fourth aspect of the present invention, there is provided a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of a method for designing a lifting system for a pumping rod pump.

[0036] Compared with the prior art, the present invention has at least the following beneficial effects:

[0037] The present invention provides a method for designing a pumping rod pump lifting system. The method combines an influencing factor set and a main control factor analysis model of an existing pumping rod pump lifting system design in an oil field to obtain a main control factor analysis result for the design of the pumping rod pump lifting system. The main control factor analysis result is expanded by simulation, and cluster analysis and fusion are performed on the expanded main control factor analysis result and the main control factor analysis result before and after expansion to obtain a multi-category design sample library for the pumping rod pump lifting system. Characteristic values ​​are constructed for each type of design sample library to obtain geological comprehensive indicators, lifting design comprehensive indicators and lifting operation effect comprehensive indicators corresponding to each type of design sample library. According to the geological comprehensive indicators, lifting design comprehensive indicators and lifting operation effect comprehensive indicators corresponding to the multi-category design sample library, a design sample library matching the geological development conditions of the pumping well to be designed is searched. The pumping rod pump lifting system is designed using the design sample library matching the geological development conditions of the pumping well to be designed. The design of the pumping rod lifting system has achieved a transformation from traditional mechanism analysis to a combination of big data and artificial intelligence analysis, which has improved the accuracy of the design of the pumping rod lifting system, reduced the time required for the design of the pumping rod lifting system, and designed a pumping rod lifting system that can match the geological reservoir physical properties and development characteristics, providing effective guidance for the design of lifting schemes for pumping wells. The present invention realizes the transformation from mechanism-driven to data-driven, and uses a deep learning algorithm to form a design model for the pumping rod lifting system. Field applications have shown that the average pump efficiency of more than 95% of the pumping wells has increased by 4.23%, the system efficiency has increased by 1.28%, the power consumption per 100 tons of liquid has decreased by 0.089KW / h, and the output has increased by 2.12m 3 / d, the maximum load of the suspension point is reduced by 1.07KN.

[0038] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the specific implementation modes of the present invention, the drawings required for use in the description of the specific implementation modes will be briefly introduced below. Obviously, the drawings described below are some implementation modes of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1 It is a flow chart of a method for designing a lifting system of a pumping rod pump according to an embodiment of the present invention;

[0041] Figure 2 This is a comparison diagram of the well-to-well distance calculation results of an embodiment of the present invention;

[0042] Figure 3 This is a schematic diagram of feature sorting of a random forest model according to an embodiment of the present invention;

[0043] Figure 4 This is a schematic diagram of feature sorting of the XGBoost model according to an embodiment of the present invention;

[0044] Figure 5 This is a schematic diagram of the feature sorting of the LightGBM model according to an embodiment of the present invention;

[0045] Figure 6 This is a data table of feature importance of embodiments of the present invention;

[0046] Figure 7 Frequency distribution diagram of three types of comprehensive indicators and production capacity;

[0047] Figure 8 The K-means++ model contour coefficient and CH value change curve of the embodiment of the present invention;

[0048] Fig. 9 This is a comparison chart of the well-to-well distance calculation results of an embodiment of the present invention. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] like Figure 1 As shown, a method for designing a lifting system of a pumping rod pump according to an embodiment of the present invention specifically comprises the following steps:

[0051] Step 1: Combine the influencing factor set and the main control factor analysis model of the existing pumping rod pump lifting system design of the oil field to obtain the main control factor analysis results of the pumping rod pump lifting system design.

[0052] Preferably, the acquisition of the influencing factor set of the existing pumping rod pump lifting system design in the oil field is specifically as follows:

[0053] Collect and organize the original design data of the existing pumping rod pump lifting system in the oil field;

[0054] Through the Pearson correlation analysis of the original design data, the characteristic indicators related to the design of the pumping rod pump lifting system are selected to form the influencing factor set of the existing pumping rod pump lifting system design in the oil field. Figure 2 As shown in the figure, the correlation heat map can be used to determine the strength of the correlation between the indicators.

[0055] It should be noted that the original design data includes geological development characteristic data and lifting system operation effect data, including: production capacity, medium depth of reservoir, reservoir static pressure, saturation pressure, water content, crude oil density, crude oil viscosity, oil-gas ratio, dynamic liquid level, oil well liquid production, pump depth, stroke, stroke frequency, pump diameter, maximum load, minimum load, pump efficiency, surface efficiency, downhole efficiency, system efficiency, and power consumption per ton of liquid per 100 meters. For examples, see Table 1.

[0056] Preferably, the main controlling factor analysis model uses the production of the pumping well as the label data, and the design data of the existing pumping rod pump lifting system of the oil field as the feature data input model, establishes a pumping well production regression model based on MID, XGBoost and LightGBM and calculates the feature weights, and uses the root mean square error, determination coefficient and mean absolute error to evaluate the prediction effect, and selects the model with the best performance.

[0057] Step 2: perform data expansion on the main control factor analysis results through simulation, perform cluster analysis and fusion on the main control factor analysis results after expansion and the main control factor analysis results before expansion, and obtain a multi-category design sample library of the pumping rod pump lifting system.

[0058] Preferably, DeepinSite simulation software is used to perform data expansion on the main control factor analysis results.

[0059] Step 3: construct characteristic values ​​for each type of design sample library to obtain comprehensive geological indicators, lifting design indicators and lifting operation effect indicators corresponding to each type of design sample library.

[0060] In other words, the feature construction method is adopted to combine the field knowledge of the pumping rod pump lifting system to reconstruct three new features: geological comprehensive indicators, lifting design comprehensive indicators and lifting operation effect comprehensive indicators, so as to achieve data dimensionality reduction; cluster analysis is performed on the pumping wells, and wells with similar geological conditions are divided into one category. The reasons for the differences in production capacity among the wells are analyzed, and a sample library for the design of pumping unit lifting systems based on the geological characteristics and production capacity characteristics of the pumping wells is established.

[0061] Step 4: According to the geological comprehensive indicators, lifting design comprehensive indicators and lifting operation effect comprehensive indicators corresponding to the multi-category design sample library, find a design sample library that matches the geological development conditions of the pumping well to be designed.

[0062] Preferably, a Euclidean distance matching algorithm is used to find a design sample library that matches the geological development conditions of the pumping well to be designed from comprehensive geological indicators, comprehensive lifting design indicators and comprehensive lifting operation effect indicators corresponding to multiple types of design sample libraries.

[0063] Step 5: Design the lifting system of the pumping rod pump by using the design sample library that matches the geological development conditions of the pumping well to be designed.

[0064] In one embodiment, after designing a pumping rod pump lifting system using a design sample library matching the geological development conditions of the pumping well to be designed, the method further includes:

[0065] The design scheme is evaluated using the effect quantification evaluation model and the comprehensive decision-making evaluation model.

[0066] In one embodiment, the establishment of a design data set for a pumping rod pump lifting system includes data preparation and data preprocessing, which includes outlier identification and cleaning, missing data processing, data normalization, and the like.

[0067] Table 1 Statistical results of the lifting system data set obtained after data preprocessing

[0068]

[0069]

[0070] In this embodiment, combined with Table 2, Figure 3 , Figure 4 and Figure 5As shown in the figure, based on the three evaluation indicators of determination coefficient (R2), root mean square error (RMSE) and mean absolute error (MAE), the effects of three yield prediction models, random forest, XGBoost and LightGBM, are compared, and finally the XGBoost algorithm is used to analyze the main controlling factors; by comparing the feature sorting results of the three models, it is found that the feature weight of displacement is always the largest, followed by stroke and number of strokes, and finally the key factors affecting the yield are determined.

[0071] In this embodiment, Figure 6 As shown in the figure, the XGBoost algorithm was used to analyze the main influencing factors of 24 numerical geological development characteristic data, and 14 indicators were obtained: annual oil production, reservoir static pressure, monthly water production, daily fluid supply capacity, annual water production, flowing pressure, crude oil density, sand content, water content, oil pressure, gas-oil ratio, crude oil viscosity, submergence, and casing pressure.

[0072] Table 2 Index evaluation results of three regression models

[0073]

[0074] After data preprocessing and data analysis, data items with strong correlation were eliminated. The new data set includes 14 geological parameters such as annual oil production, reservoir static pressure, monthly water production, daily fluid supply capacity, annual water production, flow pressure, crude oil density, sand content, water content, oil pressure, gas-oil ratio, crude oil viscosity, submergence, and casing pressure; 5 lifting design parameters such as stroke, stroke frequency, pump diameter, pump depth, and displacement; and 6 lifting operation effect parameters such as production, pump efficiency, downhole efficiency, system efficiency, ground efficiency, and electricity consumption per 100 tons of liquid. In order to carry out subsequent clustering analysis, the feature construction method is used to reduce the feature dimension. As shown in Table 3, the comprehensive index of geological data is set as C1, the comprehensive index of lifting design data is set as C2, and the comprehensive index of lifting operation effect data is set as C3. After feature construction, the original data item features are reconstructed into three new features with physical significance: C1, C2, and C3. Figure 7 and Figure 8 As shown in the figure, according to the changing trend of silhouette coefficient and CH value with the number of clusters K, it can be seen that when k = 4, both silhouette coefficient and CH value reach the maximum value. Therefore, the optimal number of clusters based on K-means clustering is 4, and finally the relationship between reservoir geological characteristics and lifting design parameters is established.

[0075] Table 3 Distribution statistics of four types of wells in the sample set

[0076]

[0077] like Fig. 9As shown in the figure, 10 pumping wells were selected, and the distance between wells was quantitatively calculated using four matching algorithms, including Euclidean distance, Manhattan distance, Pearson distance, and cosine similarity. A comparative analysis was performed, and the Euclidean distance was determined to be the best matching algorithm. Combined with the table shown in Table 4, the weights of the six lifting design effect indicators (production, pump efficiency, downhole efficiency, system efficiency, surface efficiency, and electricity consumption per 100 tons of liquid) of the lifting system design sample library of the pumping well were calculated using four methods. Based on the calculation results of the effect quantitative evaluation weight, the CRITIC method is more in line with the quantitative comparison of the lifting design scheme effect. A certain pumping well was selected, and the recommended wells with similar geological conditions to the actual production wells were selected from the sample library using the Euclidean distance. The corresponding design effect quantitative score and comprehensive decision score of each recommended well were calculated. From Table 5, it can be seen that the comprehensive decision score of the W1 well is the highest, the Euclidean distance between the well to be designed is also small, and the design effect quantitative score is high. Therefore, the lifting design scheme of the W1 well is preferred as the lifting design scheme of the pumping rod pump of the well to be designed.

[0078] Table 4 Comprehensive decision-making evaluation analysis table

[0079]

[0080] Table 5 Optimal Scheme Results

[0081]

[0082] The present invention combines the big data analysis method with the pumping unit lifting design theory, deeply explores the relationship between the measured data in the oil field, and improves the accuracy of the design of the pumping unit rod pump lifting system. By sorting out the relevant data of the pumping unit rod pump lifting system design scheme, the machine learning algorithm is used to compare and analyze the main control factors affecting the output, and the algorithm with the best applicability is selected. Based on the analysis results of the main control factors, the application software simulation obtains the design sample of the pumping unit rod pump lifting system, and then the eigenvalue construction and cluster analysis fusion method are used to prepare the lifting design sample library. Finally, a deep learning model for the design of the pumping unit rod pump lifting system is established. Specifically including:

[0083] (1) Parameter analysis and preprocessing of the pumping rod lifting system

[0084] In view of the characteristics of the factors affecting the design of the lifting system of the rod pump of the oil pumping unit, which have many parameters, influence each other and have complex relationships, a step-by-step process of data processing is established, and data preprocessing is carried out to form a systematic management of the lifting system design data so that the data meets the modeling standards.

[0085] (2) Constructing an application mechanism combining big data technology with the rod pump lifting system

[0086] Since the lifting design effects of different pumping wells vary greatly, in order to find out the reasons for the large differences in lifting design effects of different pumping wells and the key factors affecting the lifting design effects of pumping wells, the main control factor analysis was performed using a machine learning algorithm. Based on the results of the main control factor analysis, feature extraction and cluster analysis fusion were performed on the actual lifting samples of the pumping rod pump and the samples obtained by software simulation to establish a sample library for the design of the pumping lift system.

[0087] (3) Establish a data-driven deep learning model for the design of the pumping rod lifting system

[0088] The big data analysis method is used to explore the mapping relationship between the pumping rod pump lifting system and production parameters, and the laws of geology, fluid, wellbore and pumping rod pump lifting system are identified and revealed online. A similar matching algorithm is used to establish a deep learning model of the pumping rod pump to improve the accuracy of the design of the pumping rod pump lifting system.

[0089] In one embodiment of the present invention, a computer device is provided, which includes a processor and a memory, wherein the memory is used to store a computer program, wherein the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more instructions to implement the corresponding method flow or corresponding function; the processor described in the embodiment of the present invention can be used to implement the operation of a method for designing a pumping rod pump lifting system.

[0090] In one embodiment of the present invention, a method for designing a pumping rod pump lifting system can be stored in a computer-readable storage medium if it is implemented in the form of a software functional unit and sold or used as an independent product. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing related hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by a processor, it can implement the steps of the above-mentioned method embodiments. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. Computer-readable storage media include permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data.

[0091] The computer storage medium can be any available medium or data storage device that can be accessed by a computer, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical storage (such as CD, DVD, BD, HVD, etc.), and semiconductor storage (such as ROM, EPROM, EEPROM, non-volatile memory (NANDFLASH), solid-state drive (SSD)), etc.

[0092] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0093] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products of the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0094] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0095] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0096] In the present invention, the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" etc. mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the described specific features, structures, materials or characteristics may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0097] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for designing a lifting system of a pumping rod pump, characterized in that: include: Combining the design influencing factor set and main control factor analysis model of the existing pumping rod pump lifting system in the oil field, the main control factor analysis results of the design of the pumping rod pump lifting system are obtained; Data expansion is performed on the main control factor analysis results through simulation, and cluster analysis and fusion are performed on the main control factor analysis results after expansion and the main control factor analysis results before expansion to obtain a multi-class design sample library of the pumping rod pump lifting system; The characteristic values ​​of each type of design sample library are constructed to obtain the geological comprehensive index, lifting design comprehensive index and lifting operation effect comprehensive index corresponding to each type of design sample library; According to the geological comprehensive indicators, lifting design comprehensive indicators and lifting operation effect comprehensive indicators corresponding to the multi-category design sample library, find the design sample library that matches the geological development conditions of the pumping well to be designed; The lifting system of the pumping rod pump is designed using a design sample library that matches the geological development conditions of the pumping well to be designed.

2. A method for designing a lifting system of a pumping rod pump according to claim 1, characterized in that: The acquisition of the design influencing factor set of the existing pumping rod pump lifting system of the oil field is specifically as follows: Obtain the original design data of the existing pumping rod pump lifting system in the oil field; A correlation analysis is performed on the original design data, characteristic indicators related to the design of the pumping rod pump lifting system of the oil field are selected, and a set of influencing factors for the design of the pumping rod pump lifting system of the existing oil field pumping unit is formed.

3. A method for designing a pumping rod pump lifting system according to claim 2, characterized in that: The performing correlation analysis on the original design data is specifically as follows: The correlation analysis of the characteristic indicators in the original design data is performed by Pearson.

4. A method for designing a pumping rod pump lifting system according to claim 1, characterized in that: The data expansion of the main control factor analysis result by simulation is specifically as follows: The DeepinSite simulation software is used to perform data expansion on the main controlling factor analysis results to obtain expanded main controlling factor analysis results.

5. The method for designing a pumping rod pump lifting system according to claim 1, characterized in that: The method of searching for a design sample library matching the geological development conditions of the pumping well to be designed according to the geological comprehensive indicators, lifting design comprehensive indicators and lifting operation effect comprehensive indicators corresponding to the multiple types of design sample libraries comprises: The Euclidean distance matching algorithm is used to find a design sample library that matches the geological development conditions of the pumping well to be designed from the geological comprehensive indicators, lifting design comprehensive indicators and lifting operation effect comprehensive indicators corresponding to multiple types of design sample libraries.

6. A method for designing a pumping rod pump lifting system according to claim 1, characterized in that: After designing the pumping rod pump lifting system using the design sample library that matches the geological development conditions of the pumping well to be designed, it also includes: The design scheme is evaluated using the effect quantification evaluation model and the comprehensive decision-making evaluation model.

7. The method for designing a pumping rod pump lifting system according to claim 1, characterized in that: The main controlling factor analysis model uses the production of the pumping well as the label data, and the design data of the existing pumping rod pump lifting system of the oil field as the feature data input model, establishes the pumping well production regression model based on MID, XGBoost and LightGBM and calculates the feature weights, uses the root mean square error, determination coefficient and mean absolute error to evaluate the prediction effect, and selects the model with the best performance.

8. A design device for a pumping rod pump lifting system, characterized in that: include: The main control factor analysis module is used to combine the influencing factor set of the existing pumping rod pump lifting system design in the oil field and the main control factor analysis model to obtain the main control factor analysis results of the pumping rod pump lifting system design; The cluster analysis module never performs data expansion on the main control factor analysis results through simulation, performs cluster analysis fusion on the main control factor analysis results after expansion and the main control factor analysis results before expansion, and obtains a multi-class design sample library of the pumping rod pump lifting system; The characteristic value construction module is used to construct characteristic values ​​for each type of design sample library, and obtain the geological comprehensive index, lifting design comprehensive index and lifting operation effect comprehensive index corresponding to each type of design sample library; A matching search module is used to search for a design sample library that matches the geological development conditions of the pumping well to be designed based on the geological comprehensive indicators, lifting design comprehensive indicators and lifting operation effect comprehensive indicators corresponding to the multiple types of design sample libraries; The design module is used to design the lifting system of the pumping rod pump by using the design sample library matching the geological development conditions of the pumping well to be designed.

9. A device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for designing a lifting system of a pumping rod pump as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of a method for designing a lifting system of a pumping rod pump as described in any one of claims 1 to 7 are implemented.

Images