A new well production prediction method based on time series alignment and related equipment

Abstract

This invention discloses a new well production prediction method and related equipment based on time series alignment, belonging to the field of oilfield development technology. This method acquires historical data from all individual wells, classifies the historical data according to region, production year, and well type, and then uses time series alignment to establish a reference table for daily oil production of individual wells by region, well type, and year. Finally, it combines this with the production plan data of new wells to predict the production of new wells. This method reduces inefficient and repetitive data collection and processing, improves work efficiency, replaces existing contribution rate prediction methods, and improves prediction accuracy, with an average prediction error rate of less than 5%. It provides technical support for annual production allocation, monthly production allocation, planning scheme preparation, production monitoring, and early warning operations. Furthermore, it can be extended to the fields of previous year's well production prediction and measure effect prediction, showing broad application prospects.

Description

Technical Field

[0001] This invention belongs to the field of oilfield development technology, specifically relating to a new well production prediction method and related equipment based on time series alignment. Background Technology

[0002] Production forecasting is the core of oilfield production allocation and planning. Currently, oilfields mainly use the "three rates" (decline rate, arrival rate, and contribution rate) to grasp the reservoir change patterns and predict future production. However, as development targets become increasingly complex and development methods and technologies continue to advance, more and more factors influence oil well production, making it increasingly difficult to predict the arrival rate and contribution rate. How to accurately and precisely predict the production of new wells is an important research direction.

[0003] Currently, publicly available methods mainly focus on applying machine learning for production prediction. For example, CN114925623A discloses a method and system for predicting oil and gas reservoir production, which uses a long short-term memory network static model to predict oil and gas production, and then dynamically adjusts the predicted production using Kalman filtering. The production prediction object is the oil and gas reservoir. However, this method can only predict the production of the oil and gas reservoir and does not refine it to the individual well level. CN110400006A discloses an oil well production prediction method based on deep learning algorithms, which comprehensively considers the dynamic and static parameters of the oil well and applies deep learning methods to construct the model. The method for prediction is limited to the production of wells already in production because the input dataset consists of dynamic and static data of oil wells. CN114575802A discloses a machine learning-based method for predicting the production of oil wells in high water-cut reservoirs. This method uses a vector autoregression algorithm to take the oil production of the well and the injection volume of the water injection well as the prediction influencing factors. It constructs a time series model using the fluid volume change curves of the water injection well and the production well. The time step of the fitted curve is determined by selecting the lag order, and the production of the well under different time steps in the future is iteratively calculated. However, this method is only applicable to the production prediction of old wells in water-drive reservoirs. Summary of the Invention

[0004] To overcome the shortcomings of the above-mentioned technologies, the present invention provides a new well production prediction method and related equipment based on time series alignment, which can solve the technical problem that existing prediction methods cannot make high-precision predictions of the production of new wells.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] A new well production prediction method based on time series alignment includes:

[0007] Acquire historical data for all individual wells and categorize the historical data according to region, year of commissioning, and well type;

[0008] Based on the time series alignment method and combined with classified historical data, a reference table for daily oil production of a single well is established.

[0009] By combining the production plan data of the new well with the daily oil production reference table of a single well, the predicted production of the new well is obtained.

[0010] Furthermore, the historical data includes basic information and production data for all individual wells.

[0011] Furthermore, the basic information includes well number, well type, well type, deployment year, production date, target coordinates, affiliated unit, operating area, oilfield, development unit, and geographical location; the production data includes production date, daily fluid production, daily oil production, daily water production, verified daily fluid production, verified daily oil production, verified daily water production, production time, and water cut.

[0012] Furthermore, the specific steps for establishing a reference table for daily oil production from a single well are as follows:

[0013] The categorized historical data are aligned according to time steps, and the average daily oil production of all single wells corresponding to each time point is calculated. All average daily oil production is screened according to region, production year and well type. Based on the screened average daily oil production, a reference table of daily oil production of single wells is obtained.

[0014] Furthermore, the average daily oil production of all single wells at each time point is calculated using a weighted average method.

[0015] Furthermore, the production plan data is obtained by the production plan input device through batch parsing import or manual entry.

[0016] Furthermore, the predicted production of the new well is based on the predicted oil production of the corresponding directional well, the predicted oil production of the highly deviated well, and the predicted oil production of the horizontal well; the predicted oil production of the directional well, the predicted oil production of the highly deviated well, and the predicted oil production of the horizontal well are all calculated through production plan data and a single well daily oil production reference table.

[0017] A new well production prediction system based on time series alignment, comprising the steps of implementing the above-mentioned new well production prediction method based on time series alignment, including:

[0018] The data classification module is used to acquire historical data for all individual wells and classify the historical data according to region, production year, and well type.

[0019] The time-series alignment module is used to establish a reference table for daily oil production of a single well based on the time-series alignment method and the classified historical data.

[0020] The production forecasting module is used to combine the production plan data of new wells with the daily oil production reference table of single wells to obtain the predicted production of new wells.

[0021] An apparatus comprising:

[0022] Memory, used to store computer programs;

[0023] A processor is used to implement the steps of the above-described time-series aligned new well production prediction method when executing the computer program.

[0024] A computer-readable storage medium storing a computer program, which, when executed by a processor, is used to implement the steps of the above-described method for predicting new well production based on time series alignment.

[0025] Compared with the prior art, the present invention has the following beneficial effects:

[0026] This invention also provides a new well production prediction method based on time series alignment. This method acquires historical data from all individual wells, classifies the historical data according to region, production year, and well type, and then uses time series alignment to establish a reference table for daily oil production of individual wells by region, well type, and year. Finally, it combines the production plan data of new wells to predict the production of new wells. This method can reduce the inefficient and repetitive work of data collection and processing, improve work efficiency, replace existing contribution rate prediction methods, improve prediction accuracy, and achieve an average prediction error rate of less than 5%. It provides technical support for annual production allocation, monthly production allocation, planning scheme preparation, production monitoring, and early warning operations. At the same time, it can be extended to the fields of previous year's well production prediction and measure effect prediction, and has broad application prospects. Attached Figure Description

[0027] Figure 1 A flowchart illustrating a new well production prediction method based on time series alignment provided in this embodiment of the invention;

[0028] Figure 2 A comparison chart of the monthly predicted and actual production of new wells in 2020 for the first oil production plant using the time-series aligned new well production prediction method provided in this embodiment of the invention;

[0029] Figure 3 A flowchart of a new well production prediction method based on time series alignment provided by the present invention;

[0030] Figure 4 This is a schematic diagram of the structure of a new well production prediction system based on time series alignment provided by the present invention. Detailed Implementation

[0031] This invention provides a new well production prediction method based on time series alignment, such as... Figure 3 As shown, it includes the following steps:

[0032] S1: Obtain historical data for all individual wells and classify the historical data according to region, production year, and well type.

[0033] The aforementioned historical data includes basic information and production data for all individual wells.

[0034] Specifically, the basic information includes well number, well type, well type, deployment year, production date, target coordinates, affiliated unit, operating area, oilfield, development unit, and geographical location; the production data includes production date, daily fluid production, daily oil production, daily water production, verified daily fluid production, verified daily oil production, verified daily water production, production time, and water cut.

[0035] S2: Based on the time series alignment method and combined with classified historical data, a reference table for daily oil production of a single well is established.

[0036] The specific steps for establishing a reference table for daily oil production of a single well are as follows:

[0037] The categorized historical data are aligned according to time steps, and the average daily oil production of all single wells corresponding to each time point is calculated. All average daily oil production is screened according to region, production year and well type. Based on the screened average daily oil production, a reference table of daily oil production of single wells is obtained.

[0038] Specifically, the average daily oil production of all single wells at each time point (i.e. each natural month) is calculated by weighted averaging.

[0039] S3: Combine the production plan data of the new well with the daily oil production reference table of a single well to obtain the predicted production of the new well.

[0040] Here, the production plan data is obtained by the production plan input device through batch parsing import or manual entry.

[0041] Specifically, the predicted production of new wells is based on the predicted production of directional wells, highly deviated wells, and horizontal wells corresponding to the new wells; the predicted production of directional wells, highly deviated wells, and horizontal wells are all calculated using production plan data and a reference table of daily production of single wells.

[0042] like Figure 4 As shown, the present invention also provides a new well production prediction system based on time series alignment, comprising: a data classification module for acquiring historical data of all single wells and classifying the historical data according to region, production year, and well type; a time series alignment module for establishing a single well daily oil production reference table based on the time series alignment method and the classified historical data; and a production prediction module for obtaining the predicted production of the new well by combining the new well's production plan data and the single well daily oil production reference table.

[0043] The present invention also provides an apparatus comprising: a memory for storing a computer program; and a processor for executing the computer program to implement the steps of the time-series aligned new well production prediction method.

[0044] When the processor executes the computer program, it implements the above-mentioned steps for predicting the production output of new wells based on time series alignment. For example, it acquires historical data of all individual wells and classifies the historical data according to region, production year, and well type; based on the time series alignment method and combined with the classified historical data, it establishes a reference table for the daily oil production of individual wells; and combines the production plan data of new wells and the reference table for the daily oil production of individual wells to obtain the predicted production output of new wells.

[0045] Alternatively, when the processor executes the computer program, it implements the functions of each module in the above system, such as: a data classification module, used to acquire historical data of all single wells and classify the historical data according to region, production year, and well type; a time series alignment module, used to establish a reference table for daily oil production of single wells based on the time series alignment method and the classified historical data; and a production prediction module, used to obtain the predicted production of new wells by combining the production plan data of new wells and the reference table for daily oil production of single wells.

[0046] For example, the computer program can be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing preset functions, wherein the instruction segments describe the execution process of the computer program in the time-series aligned new well production prediction device. For example, the computer program can be divided into a data classification module, a time-series alignment module, and a production prediction module; the specific functions of each module are as follows: the data classification module is used to acquire historical data of all single wells and classify the historical data according to region, production year, and well type; the time-series alignment module is used to establish a single-well daily oil production reference table based on the time-series alignment method and the classified historical data; the production prediction module is used to obtain the predicted production of the new well by combining the new well's production plan data and the single-well daily oil production reference table.

[0047] The time-series aligned new well production forecasting device can be a computing device such as a desktop computer, laptop, handheld computer, or cloud server. The time-series aligned new well production forecasting device may include, but is not limited to, processors and memory. Those skilled in the art will understand that the above examples of time-series aligned new well production forecasting devices do not constitute a limitation on time-series aligned new well production forecasting devices. It may include more components than described above, or combine certain components, or different components. For example, the time-series aligned new well production forecasting device may also include input / output devices, network access devices, buses, etc.

[0048] The processor referred to can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor, or any conventional processor. This processor is the control center of the time-series aligned new well production prediction system, connecting various parts of the system via various interfaces and lines.

[0049] The memory can be used to store the computer program and / or modules. The processor implements various functions of the time-series aligned new well production prediction device by running or executing the computer program and / or modules stored in the memory and calling the data stored in the memory.

[0050] The memory may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a function (such as sound playback, image playback, etc.). The data storage area may store data created based on the use of the mobile phone (such as audio data, phonebook, etc.). Furthermore, the memory may include high-speed random access memory and non-volatile memory, such as hard disks, RAM, plug-in hard disks, smart media cards (SMC), secure digital cards (SD cards), flash cards, at least one disk storage device, flash memory device, or other volatile solid-state storage devices.

[0051] The present invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the new well production prediction method based on time series alignment.

[0052] If the modules / units integrated in the time-series aligned new well production prediction system are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium.

[0053] Based on this understanding, the present invention can implement all or part of the processes in the above-described time-series aligned new well production prediction method, or it can be accomplished by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the above-described time-series aligned new well production prediction method. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or a preset intermediate form, etc.

[0054] The computer-readable storage medium may include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0055] It should be noted that the content contained in the computer-readable storage medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable storage medium does not include electrical carrier signals and telecommunication signals.

[0056] The present invention will be further described below with reference to embodiments and accompanying drawings:

[0057] Example

[0058] To address the issues mentioned in the background section: currently disclosed methods primarily focus on applying machine learning for production prediction. For example, CN114925623A discloses an oil and gas reservoir production prediction method and system, which uses a long short-term memory network static model to predict oil and gas production, and then dynamically adjusts the predicted production using Kalman filtering. The production prediction object is the oil and gas reservoir; however, this method can only predict the production of the oil and gas reservoir and does not refine it to the individual well level. CN110400006A discloses an oil well production prediction method based on a deep learning algorithm, which comprehensively considers the dynamic and static parameters of the oil well and applies deep learning... The method for model building and prediction is only applicable to the production prediction of wells that have already been put into production because the input dataset consists of dynamic and static data of oil wells. CN114575802A discloses a machine learning-based method for predicting the production of oil wells in high water-cut reservoirs. It uses the vector autoregression algorithm to take the oil production of oil wells and the injection volume of water injection wells as prediction influencing factors. It constructs a time series model using the fluid volume change curves of water injection wells and oil production wells, determines the time step of the fitting curve by selecting the lag order, and iteratively calculates the production of oil wells at different time steps in the future. However, this method is only applicable to the production prediction of old wells in water-drive reservoirs.

[0059] like Figure 1 As shown, this embodiment provides a new well production prediction method based on time series alignment. By automatically extracting historical production data, it applies time series alignment to establish a reference table for daily oil production levels of single wells by region, well type, and year. Combined with annual deployment and production plans, it provides detailed monthly predictions of new well production. This method is simple to operate and can replace contribution rate prediction methods. The reference table can be dynamically revised over time, offering advantages such as greater precision, accuracy, and convenience. It is suitable for predicting the production of newly commissioned wells, providing intelligent technical support for oilfield production allocation, planning scheme development, production monitoring, and early warning.

[0060] This method comprises three stages: data preparation, time series alignment and statistics, and yield forecasting; the specific steps are as follows:

[0061] Data preparation stage:

[0062] The system automatically extracts basic information and production data (collectively referred to as historical data) of each oil well from the oil and gas production database (A2), and classifies and stores the data according to region, production year, and well type to provide data support for subsequent calculations.

[0063] The basic well information includes well number, well type, well type, deployment year, production date, target coordinates, affiliated unit, operating area, oilfield, development unit, and geographical location. Production data includes production date, daily fluid production, daily oil production, daily water production, verified daily fluid production, verified daily oil production, verified daily water production, production time, and water cut. These two types of information are linked by well number and the production data is categorized and stored according to three conditions: region, production year, and well type.

[0064] Time series alignment statistics phase:

[0065] Align the historical data of all single wells in each category according to time steps, then calculate the average daily oil production (average daily oil production level) of all single wells at each time point, and extract the data of the previous 12 months (i.e. average daily oil production) to establish a reference table of single well daily oil production by region and well type.

[0066] In this stage, a weighted average was calculated for the wells that have been put into production in the past three years to obtain a reference value for the daily oil production level in the region, as shown in formula (1):

[0067] = *0.7+ *0.2+ *0.1 (1)

[0068] In equation (1), where This represents the average daily oil production per well in the jth month of the i-th year. It is the (i) 1) The wells put into production in the year were in the The average daily oil production of all individual wells at the month.

[0069] Production forecasting phase:

[0070] The production plan data for the following year is collected by the production plan input device and combined with the daily oil production reference table of single wells to accurately predict the production of new wells in each month of the following year. The total production for 12 months is the annual production allocation.

[0071] The production plan input tool supports batch parsing and importing or manual entry.

[0072] Production forecast calculations are shown in formulas (2) and (3):

[0073] (2)

[0074] = (3)

[0075] The daily oil production of a single well is referenced to the value of the directional well in the i-th month in the table. Let n be the number of directional wells put into production in month n-i+1. Assume n=3. = + + .

[0076] = (4)

[0077] The daily oil production of a single well is referenced from the value of the i-th month for highly deviated wells in the table. Let n be the number of directional wells put into production in month n-i+1. Assume n=3. = + + .

[0078] = (5)

[0079] The daily oil production of a single well is referenced to the value of the horizontal well in the i-th month in the table. Let n be the number of directional wells put into production in month n-i+1. Assume n=3. = + + .

[0080] The following set of examples will further explain and illustrate the method used in this embodiment:

[0081] The method for predicting the production of new wells in a certain region's No. 1 oil production plant in 2020 is as follows:

[0082] (1) Data preparation

[0083] a. The data extractor automatically extracts the single-well production data and basic well information of the wells put into production in 2019, 2018 and 2017 of the First Oil Production Plant from the oil and water well production database (A2).

[0084] b. Classify and store production data according to well type using a data classifier, such as 2019 horizontal wells, 2019 directional wells, 2019 highly deviated wells, and 2018 qualitative wells.

[0085] (2) Time series alignment statistics

[0086] a. Use a monthly tagger to tag all the wells that have been classified. For example, for a new well that started production in March 2018, March is its first month, April is its second month, and so on. February 2019 is its twelfth month, thus completing the extraction of data for the first 12 months.

[0087] b. Horizontally, the average daily oil production level is calculated by applying the alignment calculator to all single wells with the same number of months in the same category. Vertically, the daily oil production of the same type in 2019, 2018 and 2017 is weighted and averaged to calculate the daily oil production level of the single well in 2020 for that type.

[0088] c. After repeating step b multiple times, the reference values ​​for daily oil production per well for each type of month are obtained, as shown in Table 1, and stored in the result storage device.

[0089] Table 1. Reference Table of Daily Oil Production per Well in the First Oil Production Plant in 2020

[0090]

[0091] (3) Production forecast

[0092] a. Import monthly production plans for 2020 in batches using the plan input tool.

[0093] b. Calculate the production for each type and each natural month using the production forecaster, and sum the results month by month and type by type to obtain the total predicted production of new wells in the first oil production plant.

[0094] Figure 2 As shown, Figure 2 The graph shows the comparison between the monthly predicted and actual production of new wells in the First Oil Production Plant in 2020. It can be seen that the new well production prediction method based on time series alignment provided in this embodiment is very close to the actual production value in each natural month. For example, in March, April and September, the error is almost zero. According to actual tests, the average prediction error rate is less than 5%. The use of this prediction method not only improves work efficiency and replaces the traditional contribution rate prediction method, but also improves prediction accuracy.

[0095] In summary, this invention provides a new well production prediction method based on time series alignment, which has the following advantages compared to existing prediction methods:

[0096] This method acquires historical data from all individual wells, categorizes the data by region, production year, and well type, and then uses time series alignment to establish daily oil production reference tables for individual wells by region, well type, and year. Finally, it combines this with production plan data for new wells to predict their production output. This method reduces inefficient and repetitive data collection and processing, improves work efficiency, replaces existing contribution rate prediction methods, and enhances prediction accuracy. It provides technical support for annual production allocation, monthly production allocation, planning scheme preparation, production monitoring, and early warning operations. Furthermore, it can be extended to the fields of predicting the production output of wells from the previous year and predicting the effectiveness of measures, demonstrating broad application prospects.

[0097] The above embodiments are merely one of the implementation methods for achieving the technical solution of the present invention. The scope of protection claimed by the present invention is not limited to this embodiment, but also includes any variations, substitutions and other implementation methods that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention.

Claims

1. A new well production prediction method based on time series alignment, characterized in that, include: Acquire historical data for all individual wells and categorize the historical data according to region, year of commissioning, and well type; Based on the time series alignment method and combined with classified historical data, a reference table for daily oil production of a single well is established. By combining the production plan data of the new well and the daily oil production reference table of a single well, the predicted production of the new well is obtained; The specific steps for establishing a daily oil production reference table for a single well are as follows: The categorized historical data is aligned according to time steps, and the average daily oil production of all single wells corresponding to each time point is calculated. All average daily oil productions are then filtered based on region, year of commissioning, and well type. A reference table of single-well daily oil production is obtained based on the filtered average daily oil productions. The average daily oil production of all single wells corresponding to each time point is calculated using a weighted average method, with the specific calculation formula as follows: = ×0.7+ ×0.2+ ×0.1 In the formula, This represents the average daily oil production per well in the jth month of the i-th year. It is the (i) 1) The wells put into production in the year were in the The average daily oil production of all single wells during the month; The predicted production of new wells is based on the predicted production of corresponding directional wells, highly deviated wells, and horizontal wells. The predicted production of directional wells, highly deviated wells, and horizontal wells are all calculated using production plan data and a reference table of daily production per well. The specific calculation formulas are as follows: = = = In the formula, Arai's projected production; These are the predicted oil production rates for directional wells, highly deviated wells, and horizontal wells, respectively. The daily oil production of a single well is referenced to the value of the directional well in the i-th month in the table. This represents the number of directional wells put into production in month n-i+1. The daily oil production of a single well is referenced from the value of the i-th month for highly deviated wells in the table. This represents the number of directional wells put into production in month n-i+1. The daily oil production of a single well is referenced to the value of the horizontal well in the i-th month in the table. This represents the number of directional wells put into production in month n-i+1.

2. The new well production prediction method based on time series alignment according to claim 1, characterized in that, in, The historical data includes basic information and production data for all individual wells.

3. The new well production prediction method based on time series alignment according to claim 2, characterized in that, The basic information includes well number, well type, well type, deployment year, production date, target coordinates, affiliated unit, operating area, oilfield, development unit, and geographical location; the production data includes production date, daily fluid production, daily oil production, daily water production, verified daily fluid production, verified daily oil production, verified daily water production, production time, and water cut.

4. The new well production prediction method based on time series alignment according to claim 1, characterized in that, in, Production plan data is obtained by the production plan input device through batch parsing and import or manual entry.

5. A new well production prediction system based on time series alignment, used to implement the steps of the new well production prediction method based on time series alignment as described in any one of claims 1-4, characterized in that, include: The data classification module is used to acquire historical data for all individual wells and classify the historical data according to region, production year, and well type. The time-series alignment module is used to establish a reference table for daily oil production of a single well based on the time-series alignment method and the classified historical data. The production forecasting module is used to combine the production plan data of new wells with the daily oil production reference table of single wells to obtain the predicted production of new wells.

6. A device, characterized in that, include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the steps of the new well production prediction method based on time series alignment as described in any one of claims 1-4.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it is used to implement the steps of the new well production prediction method based on time series alignment as described in any one of claims 1-4.

Images