Sand blockage intelligent real-time monitoring method based on dimensionless parameters

Abstract

The invention discloses a sand blockage intelligent real-time monitoring method based on dimensionless parameters, and belongs to the technical field of petroleum and natural gas development, and the method comprises the following steps: S1, building a data channel, and obtaining construction pressure, displacement, sand concentration and optical fiber data in real time on a fracturing construction site; s2, defining dimensionless construction parameters and calculating an NSD value; s3, constructing a sand plugging risk real-time prediction model based on a neural network; s4, analyzing and verifying the model effect based on the NSD change of the key time node; s5, making a sand blockage early warning risk grade and an early warning index; and S6, outputting a sand plugging risk monitoring result in real time and optimizing construction parameters. According to the sand blockage intelligent real-time monitoring method based on the dimensionless parameters, the dimensionless mortar distribution parameter model is constructed, and the real-time construction data and the neural network algorithm are combined, so that early warning can be provided before sand blockage occurs, fracturing construction design is optimized, and construction efficiency is improved.

Description

Technical Field

[0001] This invention relates to the field of oil and gas development technology, and in particular to a method for intelligent real-time monitoring of sand blockage based on dimensionless parameters. Background Technology

[0002] Sand plugging is one of the most common problems encountered during fracturing operations in oil and gas field development. Sand plugging not only reduces fracturing efficiency but can also significantly increase construction costs. It severely impacts reservoir stimulation effects and construction cycles. Therefore, developing a technology that can effectively monitor sand plugging risks and optimize construction design is of great significance for improving fracturing operation efficiency and stimulation results.

[0003] Traditional sand plugging monitoring techniques primarily rely on Nolte-Smith curves, analyzing the relationship between pressure and time to determine whether sand plugging has occurred. Net pressure fitting is one of the most commonly used methods, detecting sand plugging by monitoring changes in net pressure. Furthermore, the slope inversion method, which utilizes the surface pressure slope to identify sand plugging events, is particularly suitable for situations where net fracture pressure changes are small, providing an effective basis for sand plugging prediction. Although traditional methods are widely used in fracturing processes and sand plugging assessment, they still rely heavily on qualitative analysis or human experience, making them susceptible to subjective judgment and prone to misjudgment under complex conditions. With the increasing volume of fracturing data and improved computing power, machine learning-based construction pressure prediction is gradually emerging as a new and effective alternative.

[0004] Therefore, machine learning methods, due to their advantages in complex working conditions, are expected to become an important tool for sand blockage early warning. Summary of the Invention

[0005] The purpose of this invention is to provide an intelligent real-time monitoring method for sand blockage based on dimensionless parameters. By constructing a dimensionless mortar distribution parameter model and combining real-time construction data with neural network algorithms, it can provide early warning before sand blockage occurs, optimize fracturing construction design, and improve construction efficiency.

[0006] To achieve the above objectives, this invention provides a method for intelligent real-time monitoring of sand blockage based on dimensionless parameters, comprising the following steps:

[0007] S1, establish a data channel to acquire real-time data on construction pressure, displacement, sand concentration, and fiber optic data at the fracturing construction site;

[0008] S2, define dimensionless construction parameters and calculate NSD values;

[0009] S3, Construct a real-time prediction model for sand blockage risk based on neural networks;

[0010] S4, verifying the model effect based on the key time node NSD change analysis;

[0011] S5, formulating the sand plug early warning risk level and early warning index;

[0012] S6, outputting the sand plug risk monitoring result in real time and optimizing the construction parameter.

[0013] Preferably, S1 specifically comprises: acquiring the key construction parameters of wellhead pressure, pumping displacement and proppant concentration in real time through the sensors and data acquisition equipment at the fracturing construction site, and combining the optical fiber distributed vibration sensing data to monitor the flow state of the sand-carrying fluid underground, thereby providing the basic data for subsequent sand plug monitoring.

[0014] Preferably, S2 specifically comprises: the construction data needs to be processed by dimensionless before sand plug monitoring, calculating the dimensionless sand-carrying fluid distribution parameter NSD, and quantifying the uniformity of sand-carrying fluid distribution.

[0015] Preferably, the NSD value ranges from 0 to 1, and the closer the value is to 1, the higher the fluid distribution uniformity, and the closer the value is to 0, the more concentrated the sand-carrying fluid distribution, thereby providing the core quantitative index for sand plug risk monitoring.

[0016] The calculation of NSD is as follows:

[0017]

[0018] In order to simplify the calculation, the flow rate ratio can be normalized to a form with a total sum of 1:

[0019]

[0020] Therefore:

[0021]

[0022] In formula (1)-(5), σ is the standard deviation of the flow rate of each cluster; μ is the average flow rate of each cluster; n is the total number of perforation clusters; q i is the flow rate of the i-th cluster.

[0023] Preferably, the dimensionless construction parameters include: friction force to hydrostatic pressure ratio, wellhead pressure to hydrostatic pressure ratio, Reynolds number, normalized proppant concentration, sand slurry to fracturing fluid displacement ratio, total sand volume to total sand slurry volume ratio, fracturing fluid size to total sand slurry volume ratio;

[0024] The calculation of the dimensionless construction parameters is as follows:

[0025] Friction force to hydrostatic pressure ratio:

[0026]

[0027] Wellhead pressure to hydrostatic pressure ratio:

[0028]

[0029] Reynolds number:

[0030]

[0031] Normalized proppant concentration:

[0032]

[0033] Sand fluid to frac fluid rate ratio:

[0034]

[0035] Total sand to total sand fluid ratio:

[0036]

[0037] Frac fluid size to total sand fluid ratio:

[0038]

[0039] In formula (6)-(12), v is the flow rate of the fracturing fluid; D is the wellbore diameter; MD is the measured depth; TVD is the true vertical depth; P is the wellhead operating pressure; C is the fracturing fluid flow rate proportion; p prop is the proppant density.

[0040] Preferably, S3 specifically comprises: by constructing LSTM and GRU neural network models, using dimensionless operating parameters as input, real-time output of NSD results, dynamic calculation of NSD value and its change trend, and providing sufficient early warning time for the scene.

[0041] Preferably, S4 specifically comprises: recording the initial NSD value NSD1 when the operation reaches the designed displacement, and recording the key NSD value NSD2 5 minutes before the sand plug occurs, observing that the NSD value significantly decreases when approaching the sand plug, and verifying the physical meaning of NSD as an evaluation parameter;

[0042] The hourly NSD decline rate is used as a key parameter, and the hourly NSD decline rate is time-averaged to stably reflect the sand plug trend and provide a reliable basis for rapid prediction of sand plug risk.

[0043] Preferably, S5 specifically comprises: according to the dynamic change trend of NSD and the rock complexity index CI, a grading standard for sand plug risk is formulated, including I, II, III and IV levels;

[0044] High CI value and low NSD drop rate correspond to low risk, low CI value and high NSD drop rate correspond to increased risk;

[0045] In combination with the background information of rock properties and fluid efficiency, the demarcation value of NSD drop rate is refined, providing basis for real-time monitoring and classification of sand plug risk.

[0046] Preferably, S6 specifically comprises: dynamically outputting sand plug risk level through real-time monitoring of NSD drop rate and rock complexity index, and giving corresponding construction adjustment suggestions;

[0047] Under high risk level, the construction personnel is prompted to adjust displacement and sand concentration parameters to reduce the risk of sand plug; under extremely high risk level, it is suggested to suspend construction and take displacement measures.

[0048] Preferably, in combination with historical data analysis, the construction parameters of subsequent well sections are optimized and configured to reduce the occurrence of sand plug and improve construction efficiency and safety.

[0049] Therefore, the present application adopts the above-mentioned sand plug intelligent real-time monitoring method based on dimensionless parameters, which has the following beneficial effects:

[0050] The present application utilizes fracturing construction data to calculate the dimensionless sand-carrying fluid distribution parameter (NSD) and its dynamic change trend, constructs a sand plug risk prediction model based on neural network, and realizes efficient early warning and risk classification of sand plug. Compared with the traditional monitoring method relying on pressure change, the present application can penetrate the noise of wellbore, directly reflect the change of sand-carrying fluid distribution underground, and improve the monitoring accuracy; at the same time, by combining with the rock complexity index (CI), scientific basis is provided for the dynamic adjustment and optimization of construction parameters. The present application is suitable for various reservoirs and completion types, has strong universality and generalization, effectively improves the fracturing construction efficiency and safety, and significantly reduces the risk and construction cost of sand plug.

[0051] The technical solutions of the present application will be further described in detail below through the drawings and examples. BRIEF DESCRIPTION OF DRAWINGS

[0052] Figure 1 The method flowchart of the present application;

[0053] Figure 2 The prediction example of the trained model in the test stage of the present application Figure 1 ;

[0054] Figure 3 The prediction example of the trained model in the test stage of the present application Figure 2 ;

[0055] Figure 4 The evolution diagram of NSD with changes in surface pressure, displacement and proppant concentration of the present application;

[0056] Figure 5 This is a sand blockage level discrimination diagram for the present invention. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages disclosed in the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of the embodiments of the present invention and are not intended to limit the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments in this application without creative effort are within the scope of protection of this application. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout.

[0058] It should be noted that the terms “comprising” and “having”, and any variations thereof, are intended to cover non-exclusive inclusion, such that a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to such processes, methods, products, or devices.

[0059] Similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0060] In the description of this invention, it should be noted that the terms "upper," "lower," "inner," "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship in which the product of this invention is usually placed when in use. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limiting this invention.

[0061] In the description of this invention, it should also be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," and "connect" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0062] Example

[0063] like Figure 1As shown, this embodiment provides a method for intelligent real-time monitoring of sand blockage based on dimensionless parameters. Taking well 2039 as an example, the method includes the following steps:

[0064] S1 establishes a data channel to acquire real-time data on construction pressure, displacement, sand concentration, and fiber optic data at the fracturing construction site.

[0065] S1 specifically includes: acquiring key construction parameters in real time through sensors and data acquisition equipment at the fracturing construction site: wellhead pressure, pumping flow rate and proppant concentration, and monitoring the flow status of sand-carrying fluid downhole by combining fiber optic distributed vibration sensing (hDVS) data, providing basic data for subsequent sand plugging monitoring.

[0066] like Figures 2-4 As shown, S2 defines dimensionless construction parameters and calculates the NSD value.

[0067] S2 specifically includes: Before sand plugging monitoring, the construction data needs to be dimensionlessly processed to eliminate the influence of different well types and reservoir conditions on the data, thereby improving the adaptability and versatility of the model. The dimensionless sand-carrying fluid distribution parameter NSD is calculated to quantify the uniformity of the sand-carrying fluid distribution.

[0068] The NSD value ranges from 0 to 1. The closer the value is to 1, the higher the uniformity of fluid distribution. The closer the value is to 0, the more concentrated the distribution of sand-carrying fluid. This provides a core quantitative indicator for monitoring sand blockage risk.

[0069] The NSD is calculated as follows:

[0070]

[0071] To simplify calculations, the flow ratio can be normalized to a form where the sum is 1:

[0072]

[0073] therefore:

[0074]

[0075] In equations (1)-(5), σ is the standard deviation of the flow rate of each cluster; μ is the average flow rate of each cluster; n is the total number of perforation clusters; q i Let be the flow rate of the i-th cluster.

[0076] Dimensionless construction parameters include: the ratio of frictional force to hydrostatic pressure, the ratio of wellhead pressure to hydrostatic pressure, Reynolds number, normalized proppant concentration, the ratio of mixed sand fluid to fracturing fluid discharge, the ratio of total sand volume to total mixed sand fluid volume, and the ratio of fracturing fluid volume to total mixed sand fluid volume.

[0077] The dimensionless construction parameters are calculated as follows:

[0078] Ratio of frictional force to hydrostatic pressure:

[0079]

[0080] Ratio of wellhead pressure to hydrostatic pressure:

[0081]

[0082] Reynolds number:

[0083]

[0084] Normalized proppant concentration:

[0085]

[0086] The ratio of sand-mixing fluid to fracturing fluid discharge:

[0087]

[0088] Ratio of total sand volume to total mixing liquid volume:

[0089]

[0090] Ratio of fracturing fluid volume to total sand mixing fluid volume:

[0091]

[0092] In equations (6)-(12), v is the fracturing fluid velocity; D is the wellbore diameter; MD is the measurement depth; TVD is the actual vertical depth; P is the wellhead construction pressure; C is the fracturing fluid flow rate ratio; ρ prop This refers to the proppant density.

[0093] S3, Construct a real-time prediction model for sand blockage risk based on neural networks.

[0094] S3 specifically includes: constructing LSTM and GRU neural network models, using dimensionless construction parameters as input, outputting NSD results in real time, dynamically calculating NSD values ​​and their changing trends, and providing sufficient early warning time for the site.

[0095] S4. Verify the model's effectiveness based on NSD change analysis at key time points.

[0096] S4 specifically includes: recording the initial NSD value NSD1 when the construction reaches the design discharge rate, and recording the critical NSD value NSD2 5 minutes before sand blockage occurs. Observations show that the NSD value drops significantly when approaching sand blockage, with a decrease of up to 67%, which verifies the physical significance of NSD as an evaluation parameter.

[0097] Although the instantaneous derivative has been tried as an evaluation index, its value range fluctuates greatly, affecting the interpretation effect, so the hourly NSD decline rate is used as a key parameter, and the hourly NSD decline rate is time-averaged to stably reflect the sand plug trend and provide a reliable basis for rapid prediction of sand plug risk.

[0098] As shown in S5, the sand plug early warning risk level and early warning index are formulated. Figure 5

[0099] S5 specifically includes: according to the NSD dynamic change trend and the rock complexity index CI, the grading standard of sand plug risk is formulated, including I level (no risk), II level (operation needs to be cautious), III level (preparation to terminate) and IV level (stop construction immediately).

[0100] High CI value and low NSD decline rate correspond to low risk, and low CI value and high NSD decline rate correspond to increased risk.

[0101] Combined with the background information of rock properties (such as Young's modulus) and fluid efficiency, the demarcation value of NSD decline rate is refined to provide a basis for real-time monitoring and classification of sand plug risk. This method can provide rapid adjustment suggestions for fracturing construction through comprehensive analysis.

[0102] S6, real-time output of sand plug risk monitoring results and optimization of construction parameters, determination of the optimal intelligent prediction model and hyperparameters of the shale oil fracturing construction curve.

[0103] S6 specifically includes: through real-time monitoring of NSD decline rate and rock complexity index, the sand plug risk level is dynamically output, and the corresponding construction adjustment suggestion is given.

[0104] Under high risk level, the construction personnel is prompted to adjust the displacement and sand concentration parameters to reduce the sand plug risk. Under the extremely high risk level, it is suggested to suspend the construction and take displacement measures.

[0105] Combined with historical data analysis, the construction parameters of subsequent well sections are optimized and configured to reduce the occurrence of sand plug and improve the construction efficiency and safety.

[0106] Therefore, the sand plug intelligent real-time monitoring method based on dimensionless parameters is adopted, the dimensionless sand mortar distribution parameter model is constructed, real-time construction data and neural network algorithm are combined, early warning can be provided before sand plug occurs, fracturing construction design is optimized, and construction efficiency is improved.

[0107] ​It should be pointed out finally that the above examples are only used to illustrate the technical solutions of the present application but not to limit it, and although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solutions of the present application can still be modified or replaced equivalently, and these modifications or equivalent replacements should not make the modified technical solutions deviate from the spirit and scope of the technical solutions of the present application.

Claims

1. A dimensionless parameter based intelligent real-time monitoring method for sand plug, characterized in that: Comprise the following steps: S1, build a data channel, real-time acquisition of construction pressure, displacement, sand concentration and optical fiber data at the fracturing site; S2, define dimensionless construction parameters and calculate NSD value; S3, build a neural network-based real-time prediction model for sand plug risk; S4, verify the model effect based on the NSD change analysis of key time nodes; S5, develop sand plug early warning risk level and early warning index; S6, real-time output of sand plug risk monitoring results and optimization of construction parameters.

2. The method of claim 1, wherein: S1 specifically includes: through the sensors and data acquisition equipment at the fracturing site, real-time acquisition of key construction parameters: wellhead pressure, pumping displacement and proppant concentration, and combination of optical fiber distributed vibration sensing data to monitor the flow state of downhole sand-carrying fluid, providing basic data for subsequent sand plug monitoring.

3. The method of claim 1, wherein: S2 specifically includes: construction data needs to be processed by dimensionless before sand plug monitoring, calculating the dimensionless sand-carrying fluid distribution parameter NSD to quantify the uniformity of sand-carrying fluid distribution.

4. The method of claim 3, wherein: The NSD value ranges from 0 to 1, the closer the value is to 1, the higher the fluid distribution uniformity, and the closer the value is to 0, the more concentrated the sand-carrying fluid distribution, providing a core quantitative index for sand plug risk monitoring; The calculation of NSD is as follows: The flow ratio is normalized to a total of 1: Therefore: In equations (1)-(5), σ is the standard deviation of the cluster flow rate; μ is the average flow rate of the cluster; n is the total number of perforation clusters; q i is the flow rate of the ith cluster.

5. The method of claim 3, wherein: The dimensionless construction parameters include: friction to hydrostatic pressure ratio, wellhead pressure to hydrostatic pressure ratio, Reynolds number, normalized proppant concentration, sand slurry to fracturing fluid displacement ratio, total sand volume to total sand slurry volume ratio, fracturing fluid size to total sand slurry volume ratio; The calculation of dimensionless construction parameters is as follows: Friction to hydrostatic pressure ratio: Wellhead pressure to hydrostatic pressure ratio: Reynolds number: Normalized proppant concentration: Sand slurry to fracturing fluid displacement ratio: Total sand volume to total sand slurry volume ratio: Fracturing fluid size to total sand slurry volume ratio: In equations (6)-(12), v is the fracturing fluid flow rate; D is the wellbore diameter; MD is the measured depth; TVD is the true vertical depth; P is the surface operating pressure; C is the fracturing fluid flow rate proportionality constant; p prop is the proppant density.

6. The method of claim 1, wherein: S3 specifically includes: by constructing LSTM and GRU neural network models, using dimensionless construction parameters as input, real-time output of NSD results, dynamic calculation of NSD value and its trend, providing early warning time for the site.

7. The method of claim 1, wherein: S4 specifically includes: recording the initial NSD value NSD1 when the construction reaches the designed displacement, and recording the key NSD value NSD2 5 minutes before sand plug occurs, observing that the NSD value decreases when approaching sand plug, verifying the physical meaning of NSD as an evaluation parameter; Using the hourly NSD decline rate as a key parameter, time-averaging processing of the hourly NSD decline rate to reflect the sand plug trend, providing a reliable basis for rapid prediction of sand plug risk.

8. The method of claim 1, wherein: S5 specifically includes: developing sand plug risk classification standards according to the dynamic change trend of NSD and rock complexity index CI, including I, II, III and IV levels; High CI value and low NSD decline rate correspond to low risk, low CI value and high NSD decline rate correspond to increased risk; Combined with the background information of rock properties and fluid efficiency, the dividing value of NSD decline rate is refined, providing a basis for real-time monitoring and classification of sand plug risk.

9. The method of claim 1, wherein: S6 specifically includes: through real-time monitoring of NSD decline rate and rock complexity index, dynamically outputting sand plug risk level and giving corresponding construction adjustment suggestions; Under high risk level, prompt the construction personnel to adjust the displacement and sand concentration parameters to reduce the sand plug risk; under very high risk level, suggest to suspend the construction and take displacement measures.

10. The method of claim 9, wherein: Combined with historical data analysis, the construction parameters of the subsequent well section are optimized and configured to reduce the occurrence of sand plug.

Images