Prediction method and model for squeezing amount of scale inhibitor / scale dissolving agent in immediate vicinity of wellbore and storage medium

Abstract

The invention discloses a method and a model for predicting the squeezing amount of a near-wellbore area scale inhibitor / scale dissolving agent and a storage medium, and relates to the technical field of oilfield chemical auxiliaries. Comprising the following steps: acquiring stratum characteristic parameters of a near wellbore area, such as reservoir parameters of stratum porosity, permeability, reservoir thickness and the like, and parameters of water yield, liquid yield, water content, wellbore radius, anti-scale agent acting radius and the like, establishing a geometric model, performing an anti-scale agent concentration test to obtain effective anti-scale parameters, and collecting core permeability before and after adsorption. The concentration data and the effective anti-scaling parameters are mapped to generate a training sample data set, a neural network model is established based on the training sample data set for training, and the effective anti-scaling parameters and the permeability after adsorption are predicted. The stratum parameters including the temperature and the pH value and the squeezing construction parameters such as the pressure and the thickness are obtained, the squeezing volume is dynamically corrected, and the scale inhibitor is squeezed into the near wellbore area with the condition that the squeezing volume is smaller than the maximum injection flow as the limiting condition. The injection flow of the scale inhibitor can be effectively controlled in the construction process, the operation risk is reduced, and the controllability and economical efficiency of construction are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of oil field chemical additives, in particular to a method and model for predicting the injection amount of scale inhibitors in the near wellbore zone and a storage medium. BACKGROUND

[0002] In order to maintain formation pressure and improve recovery, the general practice in domestic and foreign oilfields is water injection development. However, water injection development oil wells are usually accompanied by scaling problems. The main reasons for scaling are changes in temperature, pressure, pH during the recovery process or incompatibility of formation fluids. Scale deposits are almost distributed in the entire injection-production system and gathering system, such as the inside and outside of the oil pump, the inside and outside of the tubing wall, the inside of the casing, etc. in the oil well, the injection pipeline, filter, plunger pump, etc. in the injection well, the inside wall of the injection pipeline and the oil pipeline, in addition, the formation and the vicinity of the perforation hole are also prone to scaling and are the most difficult to handle, which can seriously reduce the reservoir permeability and cause a sharp decrease in oil and gas production.

[0003] In the fields of oil and gas exploration and geothermal resource development, the accumulation of scale materials in the formation often leads to wellbore plugging, fluid flow obstruction, and equipment efficiency reduction. This phenomenon not only increases maintenance costs, but also can affect the production and economic benefits of the entire oil and gas field. Therefore, the effective application of scale inhibitors has become one of the key technologies to improve production efficiency. Traditional scale inhibitor application methods rely heavily on experience and lack systematic theoretical guidance and data support, resulting in often failing to achieve ideal results in actual application.

[0004] The existing scale inhibitor injection technology mainly operates based on preset concentration and fixed injection amount. However, due to the large differences in formation characteristics and fluid properties in the near wellbore zone, a single injection strategy cannot meet the needs of different formations. In addition, the complexity of the near wellbore zone such as core length, diameter, permeability, and porosity makes the same scale inhibitor perform significantly differently in different environments. In current technology, there is a lack of systematic research and effective prediction models that combine scale inhibitor concentration with near wellbore zone characteristics, resulting in low efficiency of scale inhibitor use and difficulty in dynamic adjustment.

[0005] In the prior art, the patent for grant announcement No. CN103666425B discloses a kind of solution of dissolving sulphate compound scale and the method for plugging removal, the method for plugging removal includes: first well washing is joined with pretreatment agent, after 2h of reaction of well closing, large displacement backwashing, then with 300-500L / min of displacement of main body fluid of squeeze injection plugging removal agent, after injection of main body fluid, then squeeze injection protective fluid, well closing reaction 24h, observe pressure change, finally complete well and bet.

[0006] The above information disclosed in the background section is only used to enhance the understanding of the background of the present disclosure, and therefore it can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0007] The purpose of the present application is to provide a method for predicting the injection volume of scale inhibitor / dissolution agent in the near wellbore zone, a model and a storage medium, to solve the problems raised in the background.

[0008] To achieve the above-mentioned purpose, the present application provides the following technical solutions:

[0009] A method for predicting the injection volume of scale inhibitor / dissolution agent in the near wellbore zone, comprising the following specific steps:

[0010] Obtain a plurality of near wellbore zone formation characteristic parameters, and based on the obtained near wellbore zone formation characteristic parameters, establish a near wellbore zone geometric model, and by injecting scale inhibitors of different concentrations into the near wellbore zone geometric model, obtain effective scale prevention parameters, and at the same time, collect the core permeability before and after the near wellbore zone geometric model is adsorbed by the scale inhibitor, wherein the formation characteristic parameters include core length, core diameter, core permeability and core porosity, and the effective scale prevention parameters include minimum effective concentration of scale inhibitor and effective period of scale prevention.

[0011] The anti-scaling agent concentration experimental data and the formation characteristic parameters are mapped to the effective anti-scaling parameters obtained through corresponding tests one by one to generate a training sample data set, a neural network model is established based on the data in the training sample data set, the anti-scaling agent concentration experimental data and the formation characteristic parameters in the training sample data set are taken as inputs of the neural network model, and the corresponding effective anti-scaling parameters and the core permeability after adsorption of the anti-scaling agent are taken as target output variables, the neural network model is trained, and an anti-scaling agent performance prediction model is obtained.

[0012] The formation characteristic parameters of the target near-wellbore zone are obtained, and the injection concentration of the anti-scaling agent is determined according to the anti-scaling agent formula; the formation parameters and the concentration data are input into the anti-scaling agent performance prediction model that has been trained, and the effective anti-scaling parameter prediction value and the core permeability prediction value under the dynamic adsorption condition are obtained; based on the effective anti-scaling parameter prediction value, the squeeze volume of the anti-scaling agent is calculated.

[0013] The formation parameters of the target near-wellbore zone are obtained, and the squeeze volume of the anti-scaling agent is dynamically corrected based on the formation characteristic parameters and the core permeability prediction value under the anti-scaling agent adsorption condition to obtain a dynamic anti-scaling agent squeeze volume, and the construction characteristic parameters of the near-wellbore zone to be squeezed with the anti-scaling agent are obtained; the formation parameters include the near-wellbore zone formation temperature and the downhole fluid pH value.

[0014] A maximum injection flow calculation model is constructed based on the construction characteristic parameters, the dynamic anti-scaling agent squeeze volume is subjected to upper limit constraint through the maximum injection flow, the anti-scaling agent is squeezed into the near-wellbore zone under the condition that the injection flow is less than the maximum injection flow, and the cumulative squeeze volume reaches the dynamic anti-scaling agent squeeze volume, and the anti-scaling agent squeeze operation process in the near-wellbore zone is completed; the construction characteristic parameters include key engineering parameters such as formation pore pressure, target treatment layer thickness, wellbore structure depth, injection well control radius, wellbore inner radius and formation average permeability.

[0015] Further, the method for establishing the near-wellbore zone geometric model is as follows: a man-made core with similar lithology and porosity and permeability is selected to establish the near-wellbore zone geometric model, so as to exclude the influence of other factors on the core permeability, the formation temperature condition is determined, the damage experiment of scaling on the core permeability before and after injection of different mass concentration scaling solvents is carried out, the damage of scaling on the reservoir core is reflected through the change of the core permeability before and after injection of the scaling solvent, and the influence of different concentration scaling solvents on the effective anti-scaling parameter is mastered.

[0016] The training sample data set is generated by mapping the concentration data of the anti-scaling agent and the formation characteristic parameters to the effective anti-scaling parameters obtained through corresponding tests one by one to form corresponding grids, and the formed grids are recorded as the training sample data set.

[0017] Further, based on the data in the training sample data set, a neural network model is established, and the neural network model is established based on a long short-term memory network model (LSTM model). The LSTM model selects an activation function and an optimization algorithm, wherein a Tanh function is selected as the activation function, and Adam is selected as the optimization algorithm of the LSTM model. The formula of the Tanh function is as follows:

[0018]

[0019] In the formula, f(r) represents the Tanh function, and the independent variable r represents the input weighted sum of the neuron, that is, the result of the weighted sum of the input received by the neuron from the previous layer;

[0020] Meanwhile, the hyperparameters of the LSTM model are set, including the number of network layers, the number of iterations, the learning rate, the batch size, the number of training times, the batch quantity, and the number of hidden layer neurons.

[0021] The number of network layers is set to 4-layer network structure, the number of iterations is set to 300, the learning rate is set to 0.001, the batch size is set to 32, the number of training times is set to 100, the batch quantity is set to 256, and the number of hidden layer neurons is set to 32.

[0022] The performance characteristic prediction model after training is input with the concentration data of the scale inhibitor and the formation characteristic parameters, and is output with the corresponding effective scale inhibition parameter prediction value and the core permeability prediction value after the scale inhibitor is adsorbed. The effective scale inhibition parameter prediction value includes the dynamic effective scale inhibition minimum concentration prediction value and the effective period prediction value of the squeeze scale inhibition.

[0023] Further, the squeeze volume of the scale inhibitor is calculated according to the obtained effective scale inhibition parameter prediction value, and the formula for calculating the squeeze volume of the scale inhibitor is as follows:

[0024]

[0025] In the formula, V z is the squeeze volume of the scale inhibitor, V pw is the volume of the scale inhibitor within the squeeze effective period, C avg is the average desorption concentration of the scale inhibitor before desorption to the dynamic minimum effective scale inhibition concentration.

[0026] The average desorption concentration C avg of the scale inhibitor before desorption to the dynamic minimum effective scale inhibition concentration is calculated according to the formula as follows:

[0027] C avg = F act *MIC for

[0028] In the formula, F act is the backflow experience coefficient, MIC for is the predicted value of the dynamic minimum effective anti-scaling concentration;

[0029] wherein the volume V pw is calculated by the daily liquid production of the oil well and the water cut in the daily liquid production of the oil well, and the specific formula is:

[0030] V pw = Q*Y for *f w

[0031] In the formula, Q is the daily liquid production of the oil well to be squeezed, Y for is the predicted value of the effective period of the squeeze anti-scaling, f w is the water cut in the daily liquid production of the oil well.

[0032] Further, the formation parameters in the near-wellbore zone of the anti-scaling agent to be squeezed are collected, and the squeeze volume of the anti-scaling agent is dynamically corrected based on the formation parameters and the predicted value of the core permeability after the anti-scaling agent is adsorbed, to obtain a dynamic anti-scaling agent squeeze volume, and the formula for calculating the dynamic anti-scaling agent squeeze volume is:

[0033]

[0034] In the formula, V z ′ is the dynamic anti-scaling agent squeeze volume, T S is the formation temperature in the near-wellbore zone, T0 is the test temperature, PH S is the PH value of the downhole fluid in the near-wellbore zone, PH0 is the reference PH value, HP S is the earth damage rate;

[0035] wherein the earth damage rate HP S is calculated by the predicted value of the core permeability after the anti-scaling agent is adsorbed, and the specific formula is:

[0036]

[0037] In the formula, ST0 is the original core permeability, ST for is the predicted value of the core permeability after adsorption.

[0038] Further, the maximum allowable injection flow rate is calculated based on the construction characteristic parameters, and the formula for calculating the maximum allowable injection flow rate is:

[0039]

[0040] In the formula, Q max is the maximum allowable injection flow rate, K avis the average permeability of the formation, h is the treatment zone thickness, g is the gravitational constant f is the formation fracture pressure gradient, H is the well depth, P is the formation pressure s is the formation pressure, μ is the viscosity of the scale inhibitor, r is the outer radius of the injection well e is the outer radius of the injection well, r is the outer radius of the injection well w is the radius of the wellbore, M is the formation storage constant

[0041] wherein the scale inhibitor is injected into the near wellbore zone according to a flow rate less than the maximum injection flow rate until the injection volume reaches the dynamic scale inhibitor injection volume, and the scale inhibitor injection in the near wellbore zone is completed.

[0042] The application also provides a prediction model for the injection volume of a scale inhibitor / dissolution agent in a near wellbore zone, which is used to perform the prediction method for the injection volume of a scale inhibitor / dissolution agent in a near wellbore zone described above, and comprises:

[0043] a training sample acquisition module that acquires formation characteristic parameters of a near wellbore zone, establishes a near wellbore zone geometric model based on the obtained formation characteristic parameters of the near wellbore zone, performs an experiment by injecting scale inhibitors of different concentrations into the near wellbore zone geometric model, and obtains effective scale inhibition parameters, and simultaneously acquires the core permeability before and after the near wellbore zone geometric model is subjected to scale inhibitor adsorption, wherein the formation characteristic parameters include core length, core diameter, core permeability, and core porosity, and the effective scale inhibition parameters include the minimum effective concentration of the scale inhibitor and the effective period of scale inhibition injection;

[0044] a prediction model training module that maps the scale inhibitor concentration experimental data and the formation characteristic parameters one by one to the effective scale inhibition parameters obtained through the corresponding experiment, generates a training sample data set, establishes a neural network model based on the data in the training sample data set, takes the scale inhibitor concentration experimental data and the formation characteristic parameters in the training sample data set as the input of the neural network model, and takes the corresponding effective scale inhibition parameters and the core permeability after scale inhibitor adsorption as the target output variables, trains the neural network model, and obtains a scale inhibitor performance prediction model;

[0045] an injection volume analysis module that is used to acquire formation characteristic parameters of a target near wellbore zone, determine the injection concentration of the scale inhibitor in combination with the scale inhibitor formula, input the formation parameters and the concentration data into the scale inhibitor performance prediction model that has been trained, acquire the effective scale inhibition parameter prediction value and the core permeability prediction value under the dynamic adsorption condition, and calculate the injection volume of the scale inhibitor based on the effective scale inhibition parameter prediction value.

[0046] The injection volume correction module is used for collecting formation parameters in the target near-wellbore zone, dynamically correcting the injection volume of the scale inhibitor based on the formation characteristic parameters and the predicted core permeability of the scale inhibitor under the adsorption condition of the scale inhibitor, obtaining the dynamic injection volume of the scale inhibitor, and simultaneously obtaining the operation characteristic parameters of the near-wellbore zone to be injected with the scale inhibitor, wherein the formation parameters include the formation temperature in the near-wellbore zone and the pH value of the downhole fluid.

[0047] The maximum volume limiting module is used for constructing a maximum injection flow calculation model based on the operation characteristic parameters, implementing upper limit constraint on the dynamic injection volume of the scale inhibitor by the maximum injection flow, injecting the scale inhibitor into the near-wellbore zone under the condition of being less than the maximum injection flow as a limiting condition, until the cumulative injection amount reaches the dynamic injection volume of the scale inhibitor, and completing the injection operation process of the scale inhibitor in the near-wellbore zone. The operation characteristic parameters include key engineering parameters such as the formation pore pressure, the target treatment layer thickness, the wellbore structure depth, the injection well control radius, the radius in the wellbore and the average formation permeability.

[0048] The application further provides a nonvolatile computer readable storage medium containing computer executable instructions, which, when executed by one or more processors, cause the processors to perform the method for predicting the injection amount of the scale inhibitor / dissolution agent in the near-wellbore zone.

[0049] Compared with the prior art, the application has the following beneficial effects:

[0050] The system obtains the characteristic parameters of the near-wellbore zone, and establishes a performance characteristic prediction model based on a neural network in combination with the concentration data of the scale inhibitor, so that the use of the scale inhibitor is more scientific and accurate. The method realizes the mapping between the concentration data and the effective scale inhibition parameters through the training of the sample data set, and then forms a model capable of predicting the scale inhibition effect in real time. Secondly, the injection volume of the scale inhibitor is dynamically corrected, and the injection strategy is adjusted in a timely manner according to the real-time formation parameters such as the temperature, the pH value and the predicted core permeability. This dynamic adjustment mechanism improves the use efficiency of the scale inhibitor, reduces the resource waste caused by errors, and to some extent, protects the integrity of the formation and avoids the formation rupture or other negative effects caused by excessive injection amount. In addition, the scheme also calculates the maximum allowable injection amount to ensure the safety of the injection operation. This makes it possible to effectively control the injection flow of the scale inhibitor during the construction process, reduces the operation risk under the premise of ensuring the construction efficiency, and improves the controllability and economy of the construction. BRIEF DESCRIPTION OF DRAWINGS

[0051] Figure 1 It is a schematic diagram of the overall method flow of the application;

[0052] Figure 2 It is a schematic diagram of the overall model structure of the application. DETAILED DESCRIPTION

[0053] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with specific examples.

[0054] It should be noted that, unless otherwise defined, technical terms or scientific terms used in the present application should be understood as their common meanings to those skilled in the art to which the present application belongs. The terms "first", "second" and similar terms used in the present application do not represent any order, number or importance, but are only used to distinguish different components. The terms "include" or "contain" and similar terms mean that the elements or objects before the terms cover the elements or objects listed after the terms and their equivalents, without excluding other elements or objects. The terms "connect" or "connected" and similar terms are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. The terms "upper", "lower", "left", "right" and the like only represent relative positional relationships, which can change accordingly when the absolute positions of the described objects change.

[0055] Embodiment:

[0056] Please refer to Figure 1 The present application provides a technical solution:

[0057] A method for predicting the amount of scale inhibitor / dissolving agent for squeeze in the near wellbore zone, comprising the following specific steps:

[0058] Step 1: Obtain a plurality of formation characteristic parameters of the near wellbore zone, and based on the obtained formation characteristic parameters of the near wellbore zone, establish a near wellbore zone geometric model, and by injecting different concentrations of scale inhibitors into the near wellbore zone geometric model for testing, obtain effective scale inhibition parameters, and at the same time collect the core permeability before and after the near wellbore zone geometric model is subjected to scale inhibitor adsorption, wherein the formation characteristic parameters include core length, core diameter, core permeability and core porosity, and the effective scale inhibition parameters include minimum effective concentration of scale inhibitor and effective period of scale inhibition for squeeze.

[0059] The specific method for establishing the near wellbore zone geometric model is: selecting artificial cores with similar lithology and porosity and permeability to establish the near wellbore zone geometric model, so as to exclude the influence of other factors on the core permeability, determining the formation temperature conditions for research, and carrying out experiments on the damage of scale formation to core permeability before and after injecting different mass concentrations of scale dissolving agents, reflecting the damage of scale formation to the reservoir core through the change of core permeability before and after injecting the scale dissolving agent, and mastering the influence of different concentrations of scale dissolving agents on the effective scale inhibition parameters.

[0060] The core permeability is obtained by the following method: firstly, the core is fully saturated with simulated formation water solution at formation temperature (85°C), then a certain amount of brine (3% KCl fresh water solution) is injected to pretreat the core, and the differential pressure between the inlet and outlet of the core is recorded during the process, and the core liquid permeability is calculated by Darcy formula after the pressure production is stable, and the permeability is taken as the initial permeability of the core. Then, simulated formation water and simulated injection water are slowly injected into the core, and the pressure change at the inlet and outlet of the core is observed and recorded in real time by means of a sensitive pressure sensor every 2 PV.

[0061] Among them, a lot of research has been done in the prediction of the effective period of squeeze anti-scaling, among which the two most widely used are Hong & Shuler model and Sorbie model. In the preferred experimental study of scale inhibitors, the compatibility of various scale inhibitors with formation water solution should be analyzed first. If the incompatible scale inhibitor is injected into the formation or reacts with the formation water to produce precipitate under the temperature condition of the formation, it will cause secondary damage to the reservoir, which is not conducive to the production increase of oilfield.

[0062] The compatibility of scale inhibitors is the basis of their anti-scaling performance, and the study of the compatibility of scale inhibitors with formation water is the first step in evaluating the anti-scaling performance of scale inhibitors. In this paper, the compatibility of scale inhibitors of different concentrations with formation water solution in different time periods is explored. Different concentrations of scale inhibitor solutions are prepared with simulated formation water solution, and are placed at formation temperature (85°C) for observation after different time (0 hours, 12 hours, 24 hours, 36 hours, 48 hours). If the solution appears mist or precipitate, etc. The selected 11 kinds of scale inhibitors (set concentration gradient as 10mg / L, 100mg / L, 500mg / L, 10000mg / L, 100000mg / L) are mixed with simulated formation water solution (50ml) in a ground triangular flask, then placed in an oven for 48 hours (set temperature as formation temperature 85°C), during which the solution is fully stirred 3 to 4 times, and whether precipitate or turbidity is produced in the solution is observed. If precipitate or turbidity is produced, it indicates that the scale inhibitor is not compatible with the formation water. The conditions of the mixed solution producing precipitate under different concentration of scale inhibitor and different reaction time are recorded in detail during the experiment.

[0063] The dynamic loop method is used to explore the dynamic minimum effective anti-scaling concentration (MIC) of the anti-scaling agent, which is a very important production data in the squeeze anti-scaling process. Once the anti-scaling agent concentration in the oil well production fluid is detected to be less than the MIC, the next squeeze operation needs to be performed. To measure the MIC value of the anti-scaling agent, the dynamic loop method is used. At the formation temperature (85°C), simulated formation water and simulated injection water are injected into the annular capillary. The simulated injection water contains different concentrations of anti-scaling agents. The pressure difference between the two ends of the mixing pipeline is monitored and recorded in real time. The sudden increase in pressure difference indicates that scaling occurs in the mixing pipeline. The time of pressure surge is used to characterize the anti-scaling effect of different concentrations of anti-scaling agents, and the minimum effective anti-scaling concentration is determined.

[0064] In the squeeze anti-scaling process, the anti-scaling agent concentration in the oil well production fluid needs to be continuously detected by technical personnel. Predicting the effective period of squeeze can greatly reduce the workload of technical personnel. This section combines the experimental results of the dynamic minimum effective anti-scaling concentration of the anti-scaling agent and the dynamic adsorption and desorption experiment results. A one-dimensional core displacement model is established by using the SQUEEZE simulation software to fit the anti-scaling agent adsorption and desorption experimental data and calculate the isothermal adsorption curve of the anti-scaling agent. Then, an oil well radial flow model is established. According to the isothermal adsorption data, the return flow curve of different anti-scaling agents is predicted. According to the dynamic minimum effective anti-scaling concentration of the anti-scaling agent, the effective period of the squeeze anti-scaling of different concentrations of anti-scaling agents and different volumes of post-positioning liquids is obtained.

[0065] The generation method of the training sample data set is that the concentration data of the anti-scaling agent and the formation characteristic parameters are one-to-one mapped with the effective anti-scaling parameters obtained in the corresponding test to form a corresponding grid. The formed grid is recorded as the training sample data set.

[0066] Step 2: Map the anti-scaling agent concentration experimental data and the formation characteristic parameters to the effective anti-scaling parameters obtained in the corresponding test one by one to generate a training sample data set. Based on the data in the training sample data set, a neural network model is established. The anti-scaling agent concentration experimental data and the formation characteristic parameters in the training sample data set are used as the input of the neural network model, and the corresponding effective anti-scaling parameters and the core permeability after the adsorption of the anti-scaling agent are used as the target output variables. The neural network model is trained to obtain an anti-scaling agent performance prediction model.

[0067] Based on the data in the training sample data set, a neural network model is established. The long short-term memory network model (LSTM model) is used as the basis to establish the neural network model. The long short-term memory network model (LSTM model) selects an activation function and an optimization algorithm. The Tanh function is selected as the activation function, and Adam is selected as the optimization algorithm of the LSTM model. The formula of the Tanh function is:

[0068]

[0069] In the formula, f(r) represents a Tanh function, and the independent variable r represents the input weight sum of the neuron, i.e., the result of the weighted sum of the inputs received by the neuron from the previous layer;

[0070] Meanwhile, the hyperparameters of the LSTM model are set, including the number of network layers, the number of iterations, the learning rate, the batch size, the number of training times, the number of batches, and the number of hidden layer neurons.

[0071] The number of network layers is set to a 4-layer network structure, the number of iterations is set to 300, the learning rate is set to 0.001, the batch size is set to 32, the number of training times is set to 100, the number of batches is set to 256, and the number of hidden layer neurons is set to 32.

[0072] The performance characteristic prediction model after training is input with the concentration data of the scale inhibitor and the formation characteristic parameters, and is output with the corresponding effective scale inhibition parameter prediction value and the core permeability prediction value after the scale inhibitor is adsorbed, and the effective scale inhibition parameter prediction value includes the dynamic effective scale inhibition minimum concentration prediction value and the squeeze injection scale inhibition effective period prediction value.

[0073] Since the LSTM model can adapt to dynamically changing data, it can continuously update the prediction according to the real-time collected parameters such as formation condition changes. This adaptability makes the use of scale inhibitors more flexible, and the injection strategy can be adjusted according to real-time data.

[0074] The change of the effective scale inhibition parameter is often nonlinear, and the LSTM can capture the complex nonlinear relationship in the data through its deep structure. This means that the LSTM model can better fit the actual situation and provide more accurate prediction results.

[0075] Step 3: Obtain the formation characteristic parameters of the target near-wellbore zone, and determine the injection concentration of the scale inhibitor according to the scale inhibitor formula; input the formation parameters and concentration data into the trained scale inhibitor performance prediction model to obtain the effective scale inhibition parameter prediction value and the core permeability prediction value under dynamic adsorption conditions; based on the effective scale inhibition parameter prediction value, calculate the squeeze volume of the scale inhibitor.

[0076] The squeeze volume of the scale inhibitor is calculated according to the obtained effective scale inhibition parameter prediction value, and the formula for calculating the squeeze volume of the scale inhibitor is:

[0077]

[0078] In the formula, V z is the squeeze volume of the scale inhibitor, V pw is the volume of the scale inhibitor within the squeeze effective period, C avg is the average desorption concentration of the scale inhibitor before desorption to the dynamic minimum effective scale inhibition concentration;

[0079] The average desorption concentration of the antiscalant before desorption to the dynamic minimum effective antiscaling concentration is C avg The calculation is based on the formula:

[0080] C avg =F act *MIC for

[0081] Where, F act is the flowback experience coefficient, MIC for is the predicted value of the dynamic minimum effective anti-scaling concentration;

[0082] The volume of anti-scaling agent during the effective period of squeezing is V pw It is calculated by the daily liquid production of the oil well and the water content in the daily liquid production of the oil well, and the specific formula is:

[0083] V pw =Q*Y for *f w

[0084] Where, Q is the daily fluid production of the oil well to be squeezed, Y for is the predicted effective period of squeezing anti-scaling, f w It is the water content in the daily liquid production of the oil well.

[0085] The above method for calculating the volume of the anti-scaling agent during the effective period of squeezing is specifically based on the calculation model of the anti-scaling agent squeezing volume proposed by KOMeyers.

[0086] Consult relevant scientific literature or industry standards to obtain the empirical flowback coefficient F for different formations, fluid properties and types of anti-scaling agents. act The flowback coefficient is usually in the range of 0.5 to 1.5. The specific value is usually determined by the formation characteristics, the properties of the flowback fluid, and the type of antiscalant.

[0087] The method for obtaining the formation characteristic parameters of the near-wellbore area where the scale inhibitor is to be squeezed is as follows: Use a tape measure or laser rangefinder to accurately measure the retrieved core and record its actual length. Usually, marks are placed at both ends of the core to ensure the accuracy of the measurement; use a caliper or a special core diameter measuring tool to measure the diameter of the core. Multiple points should be measured at different locations of the core (such as the two ends and the middle) to obtain the average value. Use a core permeability tester (such as a core analyzer) and follow relevant standard test methods (such as ASTM D5084, ISO 13503, etc.) to conduct experiments to obtain the core permeability. Use a gas such as nitrogen to displace the core, and calculate the porosity by measuring the mass change of the core and the volume change of the gas.

[0088] Step 4: Obtain formation parameters of the target near-wellbore zone, dynamically correct the squeeze volume of the scale inhibitor based on the formation characteristic parameters and the predicted core permeability after the scale inhibitor adsorption, obtain the dynamic scale inhibitor squeeze volume, and obtain the operating characteristic parameters of the near-wellbore zone to be squeezed with the scale inhibitor.

[0089] Obtain formation parameters in the target near-wellbore zone, dynamically correct the squeeze volume of the scale inhibitor based on the formation parameters and the predicted core permeability after the scale inhibitor adsorption, and obtain the dynamic scale inhibitor squeeze volume, wherein the formula for calculating the dynamic scale inhibitor squeeze volume is:

[0090]

[0091] In the formula, V z is the dynamic scale inhibitor squeeze volume, T S is the formation temperature in the near-wellbore zone, T0 is the test temperature, PH S is the pH value of the downhole fluid in the near-wellbore zone, PH0 is the reference pH value, and HP S is the core damage rate.

[0092] The core damage rate HP S is calculated based on the predicted core permeability after the scale inhibitor adsorption, and the specific formula is:

[0093]

[0094] In the formula, ST0 is the original core permeability, and ST for is the predicted core permeability after adsorption.

[0095] It should be noted that temperature has a significant impact on the chemical and physical properties of the scale inhibitor. Increasing the temperature generally accelerates the reaction rate, which may result in changes in the adsorption amount and effectiveness of the scale inhibitor. If the formation temperature is higher or lower than the test temperature, the squeeze volume will increase, and vice versa. The greater the temperature change, the more scale inhibitor is needed to achieve the desired effect. By the impact of the deviation of the formation temperature on the scale inhibitor is described.

[0096] The pH value affects the ionization state of the scale inhibitor and its solubility and stability in the fluid. Different pH values affect the adsorption behavior and scale inhibition effect of the scale inhibitor. When the pH value deviates from the reference value, the dynamic correction volume is adjusted. If the fluid pH is higher or lower, the effectiveness of the scale inhibitor will change, and the squeeze volume may need to be increased to ensure the scale inhibition effect. By the impact of the deviation of the pH value from the reference value on the properties of the scale inhibitor is described.

[0097] The reservoir damage rate reflects the damage of the core permeability after the scale inhibitor is adsorbed, and the higher the reservoir damage rate is, the smaller the volume of the scale inhibitor should be, so as to avoid excessive damage to the reservoir, so the reservoir damage rate is inversely proportional to the dynamic scale inhibitor injection volume, and the complexity of the reservoir damage can be effectively captured through the logarithmic function ln(1+HP S ) especially when the injection volume of the scale inhibitor is different, and the influence is more significant.

[0098] Step 5: A maximum injection flow calculation model is constructed based on construction characteristic parameters, the dynamic scale inhibitor injection volume is subjected to upper limit constraint through the maximum injection flow, the scale inhibitor is injected into the near wellbore zone under the condition of being less than the maximum injection flow, and the cumulative injection amount reaches the dynamic scale inhibitor injection volume until the scale inhibitor injection operation process in the near wellbore zone is completed. The construction characteristic parameters include key engineering parameters such as formation pore pressure, target treatment layer thickness, well structure depth, injection well control radius, wellbore inner radius and formation average permeability.

[0099] The allowed maximum injection flow is calculated based on construction characteristic parameters, and the formula for calculating the allowed maximum injection flow is as follows:

[0100]

[0101] In the formula, Q max is the allowed maximum injection flow, K av is the formation average permeability, h is the treatment layer thickness, g f is the formation fracture pressure gradient, H is the well depth, P s is the formation pressure, μ is the scale inhibitor viscosity, r e is the outer radius of the injection well, r w is the radius of the wellbore, and M is the formation storage constant.

[0102] The scale inhibitor is injected into the near wellbore zone according to the flow value less than the maximum injection flow until the injection volume reaches the dynamic scale inhibitor injection volume, and the scale inhibitor injection work in the near wellbore zone is completed. The maximum injection flow and injection volume of the scale remover are calculated in the same way.

[0103] Please refer to Figure 2 The application also provides a prediction model for the injection amount of the scale inhibitor / scale remover in the near wellbore zone, which is used to execute the prediction method for the injection amount of the scale inhibitor / scale remover in the near wellbore zone, and includes:

[0104] The training sample collection module acquires formation characteristic parameters of the near wellbore zone, establishes a near wellbore zone geometric model based on the obtained formation characteristic parameters of the near wellbore zone, performs an experiment by injecting scale inhibitors of different concentrations into the near wellbore zone geometric model, obtains effective scale inhibition parameters, and simultaneously collects core permeability before and after the near wellbore zone geometric model is subjected to scale inhibitor adsorption, wherein the formation characteristic parameters include core length, core diameter, core permeability, and core porosity, and the effective scale inhibition parameters include minimum effective concentration of the scale inhibitor and effective period of squeeze scale inhibition.

[0105] The prediction model training module one-to-one maps scale inhibitor concentration experimental data and formation characteristic parameters to effective scale inhibition parameters obtained in corresponding experiments, generates a training sample data set, establishes a neural network model based on data in the training sample data set, takes the scale inhibitor concentration experimental data and the formation characteristic parameters in the training sample data set as inputs of the neural network model, takes corresponding effective scale inhibition parameters and core permeability after scale inhibitor adsorption as target output variables, trains the neural network model, and obtains a scale inhibitor performance prediction model.

[0106] The squeeze volume analysis module is used to acquire formation characteristic parameters of a target near wellbore zone, determine the injection concentration of the scale inhibitor in combination with a scale inhibitor formula, input the formation parameters and the concentration data into the trained scale inhibitor performance prediction model, acquire effective scale inhibition parameter prediction values and core permeability prediction values under dynamic adsorption conditions, and calculate the squeeze volume of the scale inhibitor based on the effective scale inhibition parameter prediction values.

[0107] The squeeze volume correction module is used to collect formation parameters in a target near wellbore zone, dynamically correct the squeeze volume of the scale inhibitor based on the formation characteristic parameters and the core permeability prediction values under scale inhibitor adsorption conditions, obtain a dynamic scale inhibitor squeeze volume, and acquire construction characteristic parameters of the near wellbore zone to be squeezed for scale inhibition, wherein the formation parameters include near wellbore zone formation temperature and downhole fluid pH value.

[0108] The maximum volume limiting module is used to construct a maximum injection flow calculation model based on construction characteristic parameters, implement upper limit constraints on the dynamic scale inhibitor squeeze volume through the maximum injection flow, inject the scale inhibitor into the near wellbore zone under the condition that the injection flow is less than the maximum injection flow, and until the cumulative squeeze amount reaches the dynamic scale inhibitor squeeze volume, the scale inhibitor squeeze operation process in the near wellbore zone is completed.

[0109] The application further provides a nonvolatile computer-readable storage medium containing computer executable instructions, which, when executed by one or more processors, cause the processors to perform the method for predicting the squeeze volume of a scale inhibitor in a near wellbore zone.

[0110] The above formulas are all dimensionless values calculated, the formula is obtained by collecting a large amount of data to simulate the recent real situation, and the preset parameters in the formula are set by a person skilled in the art according to the actual situation.

[0111] The above embodiments can be realized wholly or partially by software, hardware, firmware or any other combination. When realized by software, the above embodiments can be realized wholly or partially in the form of a computer program product. Those skilled in the art can realize that the units and algorithm steps of the examples described in connection with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized by hardware or software methods depends on the specific application and design constraints of the technical solutions.

[0112] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, which can be located in one place or distributed on multiple network units. Part or all of the units can be selected to achieve the purpose of the embodiments according to actual needs.

[0113] The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered within the protection scope of the present application.

Claims

1. A method for predicting the injection amount of a scale inhibitor / scaling agent in a near-wellbore zone, comprising the following steps: Acquire formation characteristic parameters of several near-wellbore zones, establish a near-wellbore zone geometric model based on the obtained near-wellbore zone formation characteristic parameters, and conduct tests by injecting different concentrations of anti-scaling agents into the near-wellbore zone geometric model to obtain effective anti-scaling parameters. Simultaneously, collect core permeability of the near-wellbore zone geometric model before and after adsorption of the anti-scaling agent, wherein the formation characteristic parameters include core length, core diameter, core permeability, and core porosity, and the effective anti-scaling parameters include the minimum effective concentration of the anti-scaling agent and the effective period of anti-scaling by squeezing; The scale inhibitor concentration experimental data and formation characteristic parameters are mapped one-to-one with the effective scale inhibitor parameters obtained from the corresponding experiments to generate a training sample data set. A neural network model is established based on the data in the training sample data set. The scale inhibitor concentration experimental data and formation characteristic parameters in the training sample data set are used as inputs of the neural network model. The corresponding effective scale inhibitor parameters and the core permeability after the scale inhibitor adsorption are used as target output variables to train the neural network model and obtain a scale inhibitor performance prediction model. Obtain formation characteristic parameters in the target near-wellbore area and determine the injection concentration based on the anti-scaling agent formula. Input the formation parameter and concentration data into the trained anti-scaling agent performance prediction model to obtain predicted values ​​for effective anti-scaling parameters and predicted values ​​for core permeability under dynamic adsorption conditions. Calculate the squeezed injection volume of the anti-scaling agent based on the predicted effective anti-scaling parameters. Acquire formation parameters of the target near-wellbore zone, dynamically correct the squeezing volume of the scale inhibitor based on the formation characteristic parameters and the predicted core permeability under the scale inhibitor adsorption condition, and obtain a dynamic squeezing volume of the scale inhibitor. Simultaneously, obtain construction characteristic parameters of the near-wellbore zone where the scale inhibitor is to be squeezed, including the formation temperature of the near-wellbore zone and the pH value of the downhole fluid. A maximum injection rate calculation model is constructed based on construction characteristic parameters. The maximum injection rate is used to impose an upper limit on the dynamic anti-scaling agent squeeze volume. The anti-scaling agent is squeezed into the near-wellbore area, limiting the injection rate to less than the maximum injection rate, until the cumulative injection volume reaches the dynamic anti-scaling agent squeeze volume, completing the near-wellbore anti-scaling agent squeeze process. These construction characteristic parameters include key engineering parameters such as formation pore pressure, target treatment layer thickness, wellbore structure depth, injection well control radius, wellbore inner radius, and average formation permeability.

2. The method for predicting the injection amount of scale inhibitor / scaling agent in the near-wellbore area according to claim 1, characterized in that: The logic for establishing the near-wellbore zone geometric model is as follows: artificial cores with similar lithology and porosity / permeability are selected to establish the near-wellbore zone geometric model. This eliminates the influence of other factors on the core permeability, determines the formation temperature conditions, and conducts experiments on the damage of the core permeability by injecting different mass concentrations of scale dissolving agents. The changes in core permeability before and after the injection of the scale dissolving agent reflect the damage caused by scaling to the reservoir core, and the influence of different concentrations of scale dissolving agents on the effective anti-scaling parameters is understood. The training sample data set is generated by mapping the concentration data of the antiscalant and the formation characteristic parameters with the effective antiscaling parameters obtained from the corresponding test one by one to form a corresponding grid, and recording the formed grid as the training sample data set.

3. The method for predicting the injection amount of scale inhibitors / scaling agents in the near-wellbore area according to claim 2, characterized in that: Based on the data in the training sample data set, a neural network model is established. The neural network model is established based on the long short-term memory network model LSTM model. The activation function and optimization algorithm of the long short-term memory network model LSTM model are selected, among which the Tanh function is selected as the activation function and Adam is selected as the optimization algorithm of the LSTM model; the formula of the Tanh function is: Where f(r) represents the Tanh function, and the independent variable r represents the weighted sum of the neuron's input, that is, the result of the weighted summation of the input received by the neuron from the previous layer; At the same time, the hyperparameters of the LSTM model are set, including the number of network layers, number of iterations, learning rate, batch size, number of training times, batch size, and number of hidden layer neurons; The network layer is set to 4 layers, the number of iterations is set to 300, the learning rate is set to 0.001, the batch size is set to 32, the number of training times is set to 100, the batch size is set to 256, and the number of hidden layer neurons is 32; The trained performance characteristic prediction model takes as input the concentration data of the scale inhibitor and formation characteristic parameters, and outputs the corresponding predicted values ​​of effective scale inhibition parameters and the predicted values ​​of core permeability after the scale inhibitor is adsorbed. The predicted values ​​of effective scale inhibition parameters include the predicted value of the minimum concentration of dynamic effective scale inhibition and the predicted value of the effective period of scale inhibition by squeeze injection.

4. The method for predicting the injection amount of scale inhibitors / scaling agents in the near-wellbore area according to claim 1, characterized in that: The squeezing volume of the anti-scaling agent is calculated based on the obtained effective anti-scaling parameter prediction value, wherein the squeezing volume of the anti-scaling agent is calculated based on the formula: Where V z is the squeezing volume of the antiscalant, V pw is the volume of anti-scaling agent during the effective period of squeezing, C avg It is the average desorption concentration of the antiscalant before it desorbs to the dynamic minimum effective antiscaling concentration; The average desorption concentration of the antiscalant before desorption to the dynamic minimum effective antiscaling concentration is C avg The calculation is based on the formula: C avg =F act *MIC for Where, F act is the flowback experience coefficient, MIC for is the predicted value of the dynamic minimum effective anti-scaling concentration; The volume of anti-scaling agent during the effective period of squeezing is V pw It is calculated by the daily liquid production of the oil well and the water content in the daily liquid production of the oil well, and the specific formula is: V pw =Q*Y for *f w Where, Q is the daily fluid production of the oil well to be squeezed, Y for is the predicted effective period of squeezing anti-scaling, f w It is the water content in the daily liquid production of the oil well.

5. The method for predicting the injection amount of scale inhibitor / scaling agent in the near-wellbore area according to claim 4, characterized in that: The formation parameters of the area near the wellbore where the anti-scaling agent is to be squeezed are collected. The squeezed volume of the anti-scaling agent is dynamically corrected based on the formation parameters and the predicted value of the core permeability after the anti-scaling agent is adsorbed to obtain the dynamic anti-scaling agent squeezed volume. The formula for calculating the dynamic anti-scaling agent squeezed volume is: Where V z ' is the dynamic antiscalant injection volume, T S is the formation temperature in the near-wellbore area, T0 is the test temperature, PH S is the pH value of the downhole fluid in the near-wellbore area, PH0 is the reference pH value, HP S is the geocentric damage rate; The core damage rate HP S The predicted value of the core permeability after the anti-scaling agent adsorption is calculated based on the following formula: Where ST0 is the original permeability of the core, ST for is the predicted value of core permeability after adsorption.

6. The method for predicting the injection amount of scale inhibitor / scaling agent in the near-wellbore area according to claim 5, characterized in that: The maximum allowable injection flow rate is calculated based on the construction characteristic parameters, wherein the maximum allowable injection flow rate is calculated based on the formula: Where Q max is the maximum allowable injection flow rate, K av is the average permeability of the formation, h is the thickness of the treated layer, g f is the formation fracture pressure gradient, H is the well depth, P s is the formation pressure, μ is the viscosity of the antiscalant, r e is the outer radius of the injection well, r w is the radius of the wellbore, M is the formation storage constant; The anti-scaling agent is squeezed into the near-wellbore area according to a flow rate value less than the maximum injection flow rate until the squeezed amount reaches the dynamic anti-scaling agent squeezed volume, thereby completing the anti-scaling agent squeezed work in the near-wellbore area.

7. A prediction model for the injection rate of anti-scaling / scaling agents in the near-wellbore zone, characterized by: The prediction model for the squeezing amount of a scale inhibitor / scaling agent in a near-wellbore zone is used to execute the method for predicting the squeezing amount of a scale inhibitor / scaling agent in a near-wellbore zone according to any one of claims 1 to 6, comprising: A training sample acquisition module is provided to obtain formation characteristic parameters of several near-wellbore zones. Based on the obtained formation characteristic parameters of the near-wellbore zone, a geometric model of the near-wellbore zone is established. Effective anti-scaling parameters are obtained by injecting different concentrations of anti-scaling agents into the geometric model of the near-wellbore zone for testing. The core permeability of the geometric model of the near-wellbore zone before and after the adsorption of the anti-scaling agent is also collected. The formation characteristic parameters include core length, core diameter, core permeability, and core porosity. The effective anti-scaling parameters include the minimum effective concentration of the anti-scaling agent and the effective period of anti-scaling by squeezing. The prediction model training module maps the experimental data on scale inhibitor concentration and formation characteristic parameters to the effective scale inhibitor parameters obtained from the corresponding experiments to generate a training sample data set. Based on the data in the training sample data set, a neural network model is established. The experimental data on scale inhibitor concentration and formation characteristic parameters in the training sample data set are used as inputs to the neural network model. The corresponding effective scale inhibitor parameters and core permeability after scale inhibitor adsorption are used as target output variables to train the neural network model and obtain a scale inhibitor performance prediction model. The squeeze volume analysis module is used to obtain formation characteristic parameters in the target near-wellbore area and determine the injection concentration based on the anti-scaling agent formula. The formation parameters and concentration data are input into the trained anti-scaling agent performance prediction model to obtain the predicted effective anti-scaling parameters and the predicted core permeability under dynamic adsorption conditions. The squeeze volume of the anti-scaling agent is calculated based on the predicted effective anti-scaling parameters. The squeezing volume correction module is used to collect formation parameters in the target near-wellbore area, dynamically correct the squeezing volume of the scale inhibitor based on the formation characteristic parameters and the predicted core permeability under the scale inhibitor adsorption condition, and obtain the dynamic scale inhibitor squeezing volume. At the same time, it obtains the construction characteristic parameters of the near-wellbore area where the scale inhibitor is to be squeezed, such as the formation temperature in the near-wellbore area and the pH value of the downhole fluid; The maximum volume limitation module is used to construct a maximum injection flow calculation model based on construction characteristic parameters. This module uses the maximum injection flow rate to impose an upper limit on the dynamic anti-scaling agent squeeze volume. The anti-scaling agent is squeezed into the near-wellbore area, subject to a constraint of less than the maximum injection flow rate, until the cumulative squeezed volume reaches the dynamic anti-scaling agent squeeze volume, completing the near-wellbore anti-scaling agent squeeze process. These construction characteristic parameters include key engineering parameters such as formation pore pressure, target treatment layer thickness, wellbore structure depth, injection well control radius, wellbore inner radius, and average formation permeability.

8. A non-volatile computer-readable storage medium containing computer-executable instructions, characterized in that: When the computer-executable instructions are executed by one or more processors, the processors are caused to execute the method for predicting the squeezing amount of a scale inhibitor / scaling agent in a near-wellbore zone according to any one of claims 1 to 6.

Images