CN116693762A - Clay stabilizer for fracturing and preparation method thereof - Google Patents

Abstract

Discloses a clay stabilizer for fracturing and a preparation method thereof. Firstly, sequentially adding an acrylamide monomer, an anionic monomer, a cationic monomer and distilled water into a reactor, stirring until the monomers are dissolved to obtain a mixed solution, controlling the temperature of the mixed solution to be 30-40 ℃, regulating the pH value of the mixed solution to be 5-7 through a NaOH solution, regulating the water content to ensure that the total monomer mass percentage concentration is 20-30% to obtain a polymer solution, then, introducing high-purity nitrogen into the polymer solution, slowly dropwise adding an initiator, dropwise adding a sulfhydryl chitosan aqueous solution to react to obtain a transparent polymer product after the temperature of the solution is raised to 45-55 ℃, and finally, washing the polymer product for multiple times through methanol, and then, carrying out vacuum drying and granulating to obtain the chitosan-containing clay stabilizer with light yellow particles. In this way, a clay stabilizer with stable quality and performance can be obtained.

Description

Clay stabilizer for fracturing and preparation method thereof

Technical Field

The present disclosure relates to the field of intelligent preparation, and more particularly, to a clay stabilizer for fracturing and a preparation method thereof.

Background

China has rich compact oil gas resources, and hydraulic fracturing is a main construction method in the reconstruction of compact oil reservoirs at present. However, during such large scale fracturing, large amounts of aqueous solutions come into contact with the clay, causing the clay to swell, disperse and migrate, thereby reducing the permeability of the reservoir or plugging reservoir channels. Thus, it is necessary to use clay stabilizers to improve the swelling resistance of the working fluid, reduce clay dispersion and migration, and improve reservoir permeability.

Common clay stabilizers can be classified into inorganic clay stabilizers and organic clay stabilizers. Inorganic clay stabilizers include salts and inorganic cationic polymers, while organic clay stabilizers include cationic surfactants and organic cationic polymers. Wherein the organic cationic polymer has an ability to stabilize clay in excess of inorganic salts, inorganic cationic polymers and cationic surfactant-based clay stabilizers. The method has the advantages of small dosage, good effect, strong adsorption capacity, small influence on pH value, strong adaptability to stratum and the like, and therefore, the method becomes an important object for research and application at home and abroad in recent years.

However, organic cationic polymers are relatively high in molecular weight and tend to form plugs in formation pore channels, thereby exacerbating the damage to low permeability reservoir permeability. Meanwhile, the polymer has a longer molecular chain, contains a large number of cation centers, and is easy to reduce the compatibility and the anti-swelling effect of the fracturing fluid due to the electrostatic adsorption effect between anions and cations after being contacted with the anionic additive. In severe cases, even turbidity, flocculation delamination and other problems occur, which greatly limits the application range. Thus, there is a need to develop clay stabilizers with low relative molecular weight, which protect the formation from damage, and which have good biodegradability, and which have good compatibility with other treatments.

Thus, an optimized formulation of clay stabilizers for fracturing is desired.

Disclosure of Invention

In view of the above, the disclosure provides a clay stabilizer for fracturing and a preparation method thereof, which can perform adaptive control of a dropping speed value of a NaOH solution in real time based on a pH change of an actual solution, thereby optimizing stability of a preparation process of the clay stabilizer for fracturing and improving quality and performance of a clay stabilizer product.

According to an aspect of the present disclosure, there is provided a method for preparing a clay stabilizer for fracturing, including: sequentially adding an acrylamide monomer, an anionic monomer, a cationic monomer and distilled water into a reactor, and stirring until the monomers are dissolved to obtain a mixed solution; controlling the temperature of the mixed solution to be 30-40 ℃, adjusting the pH value of the mixed solution to be 5-7 through NaOH solution, and adjusting the water quantity to enable the mass percentage concentration of the total monomer to be 20-30% so as to obtain polymer solution; introducing high-purity nitrogen into the polymer solution, slowly dropwise adding an initiator, and dropwise adding a sulfhydryl chitosan aqueous solution to react after the temperature of the solution is raised to 45-55 ℃ to obtain a transparent polymer product; and washing the polymer product for a plurality of times by methanol, and then carrying out vacuum drying and taking out granulation treatment to obtain the chitosan-containing clay stabilizer with light yellow particles.

In the preparation method of the clay stabilizer for fracturing, the temperature of the mixed solution is controlled to be 30-40 ℃, the pH value of the mixed solution is regulated to be 5-7 by NaOH solution, and then the water quantity is regulated to ensure that the total monomer mass percentage concentration is 20-30%, so as to obtain polymer solution, and the preparation method comprises the following steps: acquiring solution reaction temperature values at a plurality of preset time points in a preset time period and pH values at the preset time points; performing data interaction feature analysis on the solution reaction temperature values at the plurality of preset time points and the pH values at the plurality of preset time points to obtain a temperature-pH value interaction synergistic feature vector; and determining that the drop rate value of the NaOH solution should be increased or decreased based on the temperature-pH value interaction cooperative characteristic vector.

In the preparation method of the clay stabilizer for fracturing, the data interaction characteristic analysis is performed on the solution reaction temperature values at a plurality of preset time points and the pH values at a plurality of preset time points to obtain a temperature-pH value interaction synergistic characteristic vector, and the preparation method comprises the following steps: arranging the solution reaction temperature values at a plurality of preset time points and the solution pH values at a plurality of preset time points into a reaction temperature time sequence input vector and a pH value time sequence input vector according to a time dimension respectively; performing time sequence change feature extraction on the reaction temperature time sequence input vector and the pH value time sequence input vector to obtain a reaction temperature time sequence feature vector and a pH value time sequence feature vector; and performing feature interaction association coding on the reaction temperature time sequence feature vector and the pH value time sequence feature vector to obtain the temperature-pH value interaction cooperative feature vector.

In the above method for preparing a clay stabilizer for fracturing, performing time-series change feature extraction on the reaction temperature time-series input vector and the pH time-series input vector to obtain a reaction temperature time-series feature vector and a pH time-series feature vector, comprising: and passing the reaction temperature time sequence input vector and the pH value time sequence input vector through a time sequence feature extractor based on a one-dimensional convolution layer to obtain the reaction temperature time sequence feature vector and the pH value time sequence feature vector.

In the preparation method of the clay stabilizer for fracturing, performing feature interaction association coding on the reaction temperature time sequence feature vector and the pH value time sequence feature vector to obtain the temperature-pH value interaction synergistic feature vector, wherein the preparation method comprises the following steps of: and performing feature level data interaction based on an attention mechanism on the reaction temperature time sequence feature vector and the pH value time sequence feature vector by using an inter-feature attention layer to obtain the temperature-pH value interaction cooperative feature vector.

In the preparation method of the clay stabilizer for fracturing, determining whether the dropping speed value of the NaOH solution should be increased or decreased based on the temperature-pH value interaction synergistic characteristic vector comprises the following steps: performing feature distribution optimization on the temperature-pH value interaction coordination feature vector to obtain an optimized temperature-pH value interaction coordination feature vector; calculating a transfer matrix of the pH value time sequence feature vector relative to the optimized temperature-pH value interaction cooperative feature vector as a pH value time sequence mapping association feature matrix; and passing the pH time sequence mapping correlation characteristic matrix through a classifier to obtain a classification result, wherein the classification result is used for indicating that the dropping speed value of the NaOH solution should be increased or decreased.

In the preparation method of the clay stabilizer for fracturing, the feature distribution optimization is performed on the temperature-pH value interaction coordination feature vector to obtain an optimized temperature-pH value interaction coordination feature vector, and the preparation method comprises the following steps: based on the temperature-pH interaction cooperative feature vector, respectively calculating quantized transferable sensing factors of transferable features of the reaction temperature timing feature vector and the pH timing feature vector to obtain a first transferable sensing factor and a second transferable sensing factor; taking the first transferable sensing factor and the second transferable sensing factor as weighting coefficients to carry out weighted optimization on the reaction temperature time sequence feature vector and the pH value time sequence feature vector so as to obtain a weighted reaction temperature time sequence feature vector and a weighted pH value time sequence feature vector; and performing feature level data interaction based on an attention mechanism on the weighted reaction temperature time sequence feature vector and the weighted pH value time sequence feature vector by using an attention layer among features to obtain the optimized temperature-pH value interaction cooperative feature vector.

In the preparation method of the clay stabilizer for fracturing, quantification of transferable characteristics of the reaction temperature time sequence characteristic vector and the pH value time sequence characteristic vector is calculated respectively based on the temperature-pH value interaction synergistic characteristic vector To derive a first transferable sensing factor and a second transferable sensing factor, comprising: based on the temperature-pH interaction synergistic feature vector, calculating quantized transferable sensing factors of transferable features of the reaction temperature time series feature vector and the pH time series feature vector respectively in the following optimization formula to obtain the first transferable sensing factor and the second transferable sensing factor; wherein, the optimization formula is:wherein->、/>And->The reaction temperature time sequence feature vector, the pH value time sequence feature vector and the temperature-pH value interaction cooperative feature vector are respectively->Represents the +.sup.th in the time sequence feature vector of the reaction temperature>Characteristic value of individual position->Represents the +.sup.th in the pH time sequence feature vector>Characteristic value of individual position->Representing the +.sup.th in the temperature-pH interaction co-characteristic vector>Characteristic value of individual position->Is a logarithmic function based on 2, and +.>Is a weighted superparameter,/->And->The first transferable sensing factor and the second transferable sensing factor, respectively.

In the preparation method of the clay stabilizer for fracturing, the pH value time sequence mapping association characteristic matrix is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating that the dropping speed value of the NaOH solution is increased or decreased, and the preparation method comprises the following steps: expanding the pH value time sequence mapping association characteristic matrix into a classification characteristic vector according to a row vector or a column vector; performing full-connection coding on the classification feature vectors by using a full-connection layer of the classifier to obtain coded classification feature vectors; and inputting the coding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.

According to another aspect of the present disclosure, there is provided a clay stabilizer for fracturing, wherein the clay stabilizer for fracturing is prepared by the aforementioned preparation method of the clay stabilizer for fracturing.

Compared with the prior art, the clay stabilizer for fracturing and the preparation method thereof are provided, and the self-adaptive control of the dropping speed value of the NaOH solution can be performed in real time based on the pH value change of the actual solution, so that the stability of the preparation process of the clay stabilizer for fracturing is optimized, and the quality and performance of a clay stabilizer product are improved.

Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate exemplary embodiments, features and aspects of the present disclosure and together with the description, serve to explain the principles of the disclosure.

Fig. 1 shows a flowchart of a method of preparing a clay stabilizer for fracturing according to an embodiment of the present disclosure.

Fig. 2 shows a flowchart of substep S120 of a method of preparing a clay stabilizer for fracturing according to an embodiment of the present disclosure.

Fig. 3 shows a schematic diagram of the architecture of substep S120 of the preparation method of the clay stabilizer for fracturing according to the embodiment of the present disclosure.

Fig. 4 shows a flowchart of sub-step S122 of a method of preparing a clay stabilizer for fracturing according to an embodiment of the present disclosure.

Fig. 5 shows a flowchart of sub-step S123 of a method of preparing a clay stabilizer for fracturing according to an embodiment of the present disclosure.

Fig. 6 shows a flowchart of sub-step S1231 of a method of preparing a clay stabilizer for fracturing according to an embodiment of the disclosure.

Fig. 7 shows a flowchart of sub-step S1233 of a method of preparing a clay stabilizer for fracturing according to an embodiment of the disclosure.

Fig. 8 shows a block diagram of a preparation system of a clay stabilizer for fracturing according to an embodiment of the disclosure.

Fig. 9 shows an application scenario diagram of a preparation method of a clay stabilizer for fracturing according to an embodiment of the present disclosure.

Detailed Description

The following description of the embodiments of the present disclosure will be made clearly and fully with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some, but not all embodiments of the disclosure. All other embodiments, which can be made by one of ordinary skill in the art without undue burden based on the embodiments of the present disclosure, are also within the scope of the present disclosure.

As used in this disclosure and in the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.

Various exemplary embodiments, features and aspects of the disclosure will be described in detail below with reference to the drawings. In the drawings, like reference numbers indicate identical or functionally similar elements. Although various aspects of the embodiments are illustrated in the accompanying drawings, the drawings are not necessarily drawn to scale unless specifically indicated.

In addition, numerous specific details are set forth in the following detailed description in order to provide a better understanding of the present disclosure. It will be understood by those skilled in the art that the present disclosure may be practiced without some of these specific details. In some instances, methods, means, elements, and circuits well known to those skilled in the art have not been described in detail in order not to obscure the present disclosure.

Fig. 1 shows a flowchart of a method of preparing a clay stabilizer for fracturing according to an embodiment of the present disclosure. As shown in fig. 1, a method for preparing a clay stabilizer for fracturing according to an embodiment of the present disclosure includes the steps of: s110, sequentially adding an acrylamide monomer, an anionic monomer, a cationic monomer and distilled water into a reactor, and stirring until the monomers are dissolved to obtain a mixed solution; s120, controlling the temperature of the mixed solution to be 30-40 ℃, adjusting the pH value of the mixed solution to be 5-7 through NaOH solution, and adjusting the water quantity to enable the total monomer mass percentage concentration to be 20-30% so as to obtain polymer solution; s130, introducing high-purity nitrogen into the polymer solution, slowly dropwise adding an initiator, and dropwise adding a sulfhydryl chitosan aqueous solution to react after the temperature of the solution is raised to 45-55 ℃ so as to obtain a transparent polymer product; and S140, washing the polymer product for a plurality of times by methanol, and then carrying out vacuum drying and taking out granulation treatment to obtain the light yellow granular chitosan-containing clay stabilizer for fracturing.

In one embodiment of the application, the addition amount of the acrylamide monomer accounts for 10-60% of the total molar amount of the monomers, and the anionic monomer comprises one or a mixture of several of acrylic acid, methacrylic acid and 2-acrylamide-2-methylpropanesulfonic acid, and the addition amount accounts for 5-25% of the total molar amount of the monomers; the cationic monomer comprises one or a mixture of more of dimethyl diallyl ammonium chloride, trimethyl allyl ammonium chloride, acryloyloxyethyl trimethyl ammonium chloride and methacryloyloxyethyl trimethyl ammonium chloride, and the addition amount of the cationic monomer accounts for 20-79% of the total molar amount of the monomer; the initiator is one or a mixture of more of ammonium persulfate/sodium bisulfite or sodium metabisulfite redox initiator, azo initiator or peroxide initiator, and the addition amount of the initiator is 0.4-1.2% of the total weight of the monomers; the deacetylation degree of the sulfhydryl chitosan is more than or equal to 80 percent, the molecular weight is 1000-5000, and the addition amount accounts for 5-15 percent of the total weight of the monomers.

Accordingly, it is considered that the control of the reaction conditions is critical to the quality and performance of the final product in the preparation process of the clay stabilizer for fracturing actually performed. For example, the dropping rate of NaOH solution is one of the key factors affecting the pH of the mixed solution, and the adjustment of pH has an important influence on the progress of the polymerization reaction and the properties of the product. At the same time, the mutual relationship between the reaction temperature and the pH value needs to be fully considered because the reaction temperature and the pH value have a synergistic effect.

Based on the above, the technical concept of the disclosure is that in the actual dropping process of NaOH solution, a sensor is used to collect a reaction temperature value and a pH value of a mixed solution, and a data processing and analysis algorithm is introduced at the rear end to perform time sequence cross-correlation analysis of the reaction temperature value and the pH value of the mixed solution so as to perform dropping speed value control of NaOH solution. Therefore, the self-adaptive control of the dropping speed value of the NaOH solution can be performed in real time based on the pH value change of the actual solution, so that the stability of the preparation process of the clay stabilizer for fracturing is optimized, and the quality and performance of the clay stabilizer product are improved.

Fig. 2 shows a flowchart of substep S120 of a method of preparing a clay stabilizer for fracturing according to an embodiment of the present disclosure. Fig. 3 shows a schematic diagram of the architecture of substep S120 of the preparation method of the clay stabilizer for fracturing according to the embodiment of the present disclosure. As shown in fig. 2 and 3, according to the preparation method of the clay stabilizer for fracturing according to the embodiment of the present disclosure, the temperature of the mixed solution is controlled to be 30-40 ℃, and after the pH value of the mixed solution is adjusted to be 5-7 by NaOH solution, the water amount is adjusted to make the total monomer mass percentage concentration be 20-30% to obtain a polymer solution, comprising the steps of: s121, obtaining solution reaction temperature values at a plurality of preset time points in a preset time period and pH values at the preset time points; s122, carrying out data interaction characteristic analysis on the solution reaction temperature values at the plurality of preset time points and the pH values at the plurality of preset time points to obtain temperature-pH value interaction cooperative characteristic vectors; and S123, determining that the dropping speed value of the NaOH solution should be increased or decreased based on the temperature-pH value interaction cooperative characteristic vector.

Specifically, in the technical scheme of the present disclosure, first, solution reaction temperature values at a plurality of predetermined time points within a predetermined period of time and pH values at the plurality of predetermined time points are acquired. Next, considering that the solution reaction temperature and pH are two important parameters in the process of preparing clay stabilizers for fracturing, they may change over time. That is, the solution reaction temperature value and the pH value have respective dynamic change rules in the time dimension, and have a time sequence cooperative association relationship. Therefore, in the technical solution of the disclosure, the solution reaction temperature values at the plurality of predetermined time points and the solution pH values at the plurality of predetermined time points need to be further arranged into a reaction temperature time sequence input vector and a pH value time sequence input vector according to a time dimension, so as to integrate distribution information of the solution reaction temperature values and the pH values on time sequence, respectively, and be favorable for capturing rules and trends of temperature and pH value changes with time by a model. And, by carrying out characteristic extraction and analysis on the time series data later, the correlation and the synergy between the temperature and the pH value can be revealed, so that the accuracy of the drop velocity value control of the NaOH solution is improved.

And then, carrying out feature mining on the reaction temperature time sequence input vector and the pH value time sequence input vector through a time sequence feature extractor based on a one-dimensional convolution layer so as to extract time sequence dynamic associated feature information of the reaction temperature value and the pH value in a time dimension respectively, namely, time sequence dynamic change feature information of the reaction temperature value and the pH value in the time dimension respectively, thereby obtaining a reaction temperature time sequence feature vector and a pH value time sequence feature vector.

Further, the inter-feature attention layer is used for carrying out feature level data interaction based on an attention mechanism on the reaction temperature time sequence feature vector and the pH value time sequence feature vector to obtain a temperature-pH value interaction cooperative feature vector, so that the correlation and the mutual influence between the time sequence change feature of the reaction temperature value and the time sequence change feature of the pH value are captured. It should be appreciated that since the goal of the traditional attention mechanism is to learn an attention weight matrix, a greater weight is given to important features and a lesser weight is given to secondary features, thereby selecting more critical information to the current task goal. This approach is more focused on weighting the importance of individual features, while ignoring the dependency between features. And the attention layer between the features can capture the correlation and the mutual influence between the time sequence change feature of the reaction temperature value and the time sequence change feature of the pH through the feature interaction based on an attention mechanism, so that the dependency relationship between different features is learned, and the features are interacted and integrated according to the dependency relationship, so as to obtain the interaction feature vector between the system operations.

In the preparation of clay stabilizers for fracturing, the temperature and pH of the reaction solution are two key parameters, and the interaction and synergy between them are critical to the preparation of the stabilizer. Specifically, the dropping rate of the NaOH solution affects the pH of the reaction solution, which is also affected by the temperature change. Therefore, in order to be able to pay attention to the correlation feature between the temperature and the pH value when the pH value of the reaction solution is monitored for the control of the dropping speed value of the NaOH solution, in the technical solution of the present disclosure, a transfer matrix of the pH value time series feature vector relative to the temperature-pH value interaction synergy feature vector is further calculated as a pH value time series mapping correlation feature matrix. Therefore, the time sequence change characteristic information about the pH value under the background of the time sequence cooperative interaction correlation characteristic of the temperature value of the reaction liquid and the pH value can be captured, so that the dripping acceleration control of the NaOH solution can be better carried out.

Accordingly, as shown in fig. 4, performing data interaction feature analysis on the solution reaction temperature values at the plurality of predetermined time points and the pH values at the plurality of predetermined time points to obtain a temperature-pH interaction synergistic feature vector, including: s1221, arranging the solution reaction temperature values at a plurality of preset time points and the solution pH values at a plurality of preset time points into a reaction temperature time sequence input vector and a pH value time sequence input vector according to a time dimension respectively; s1222, extracting time sequence change characteristics of the reaction temperature time sequence input vector and the pH value time sequence input vector to obtain a reaction temperature time sequence characteristic vector and a pH value time sequence characteristic vector; and S1223, performing feature interaction association coding on the reaction temperature time sequence feature vector and the pH value time sequence feature vector to obtain the temperature-pH value interaction coordination feature vector. It should be understood that, in step S1221, the purpose of this step is to sort and arrange the solution reaction temperature values and pH values according to the time dimension to form a time sequence input vector, and by arranging in time sequence, the time sequence information in the reaction process can be retained, so as to provide preparation for subsequent time sequence feature extraction and feature interaction; in step S1222, the function of this step is to extract the time-series change feature from the reaction temperature time-series input vector and the pH time-series input vector by the time-series feature extractor, for example, the one-dimensional convolution layer may capture the local feature in the time-series data, help the model understand the dynamic change condition of the reaction temperature and the pH, and extract the useful feature representation; in step S1223, this step may perform feature-level data interaction on the reaction temperature time-series feature vector and the pH time-series feature vector using the inter-feature attention layer. Through the attention mechanism, the model can learn the correlation and the weight between the characteristics, and realize the interaction and the association coding between the temperature and the pH value. This helps extract interactive synergy features between temperature-pH values, providing a richer feature representation for subsequent analysis and modeling tasks. In summary, the three steps together complete the data interaction characteristic analysis between the reaction temperature and the pH value of the solution, and the temperature-pH value interaction cooperative characteristic vector is obtained through time sequence change characteristic extraction and characteristic interaction association coding, so that richer and accurate characteristic representation is provided for the subsequent reaction process modeling and prediction.

More specifically, in step S1222, performing time-series variation feature extraction on the reaction temperature time-series input vector and the pH time-series input vector to obtain a reaction temperature time-series feature vector and a pH time-series feature vector, including: and passing the reaction temperature time sequence input vector and the pH value time sequence input vector through a time sequence feature extractor based on a one-dimensional convolution layer to obtain the reaction temperature time sequence feature vector and the pH value time sequence feature vector. It is worth mentioning that the one-dimensional convolution layer is a neural network layer commonly used in deep learning, and is used for processing data with a time sequence structure, and it applies a set of learnable filters (also called convolution kernels) on each time step of the time sequence data, and extracts local features by means of sliding windows. Through convolution operation, the one-dimensional convolution layer can extract local features in time sequence data, and the convolution kernel can capture correlation among different time steps, so that feature representation with strong discrimination capability is extracted. One-dimensional convolution layers typically use pooling operations (e.g., maximum pooling or average pooling) to reduce the dimensions of features, which helps reduce model complexity, improve computational efficiency, and may preserve the most significant feature information. The one-dimensional convolution layer has the characteristic of translational invariance, i.e. the characteristic representation of the output remains unchanged for the translation of the input data, which is very useful for local pattern recognition in time series data, because the position information of the pattern may change at different time steps. In step S1222, the reaction temperature timing input vector and the pH timing input vector may be converted into a reaction temperature timing characteristic vector and a pH timing characteristic vector by a one-dimensional convolutional layer-based timing characteristic extractor. The one-dimensional convolution layer may extract key timing features from the input timing data that may be used for subsequent analysis, modeling, or prediction tasks.

More specifically, in step S1223, performing feature cross-correlation encoding on the reaction temperature time series feature vector and the pH time series feature vector to obtain the temperature-pH value interaction synergistic feature vector, including: and performing feature level data interaction based on an attention mechanism on the reaction temperature time sequence feature vector and the pH value time sequence feature vector by using an inter-feature attention layer to obtain the temperature-pH value interaction cooperative feature vector. It should be noted that the inter-feature attention layer is a neural network layer, which is used for performing interaction and association coding on different features at the feature level, and learns importance weights between the features through an attention mechanism, so as to realize data interaction at the feature level. Through the attention mechanism, the attention layer among the features can learn the correlation among the features and weight different features according to the correlation, so that the interaction among the features can be realized, and the dependency relationship and interaction effect among the features can be captured better. The inter-feature attention layer can learn the importance weight of each feature in the interaction process, and by adaptively learning the weight, the model can automatically focus on features more useful for the current task and suppress features that are irrelevant or redundant to the task. The inter-feature attention layer can capture complex relationships between features, thereby providing a richer representation of features, which helps to improve the performance of the model, allowing it to better understand the structure and semantic information of the input data. In step S1223, the inter-feature attention layer is used to perform feature-level data interaction on the reaction temperature time series feature vector and the pH value time series feature vector, in order to extract interaction synergy features between temperature and pH value by learning the correlation between features. This can help the model better understand the relationship between temperature and pH and improve the modeling ability of the reaction process.

Further, the pH time sequence mapping correlation characteristic matrix is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating that the dropping speed value of the NaOH solution is increased or decreased. That is, classification processing is performed based on time sequence variation characteristic information about the pH value under the background of time sequence cooperative interaction characteristics of the temperature value and the pH value of the reaction solution, so that adaptive control of the dropping speed value of the NaOH solution is performed in real time based on the pH value variation of the actual solution, thereby optimizing the stability and efficiency of the preparation process of the clay stabilizer for fracturing.

Accordingly, as shown in fig. 5, determining that the drop rate value of NaOH solution should be increased or decreased based on the temperature-pH interaction synergy eigenvector includes: s1231, optimizing the characteristic distribution of the temperature-pH value interaction coordination characteristic vector to obtain an optimized temperature-pH value interaction coordination characteristic vector; s1232, calculating a transfer matrix of the pH value time sequence feature vector relative to the optimized temperature-pH value interaction cooperative feature vector as a pH value time sequence mapping association feature matrix; and S1233, the pH value time sequence mapping correlation characteristic matrix is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating that the dropping speed value of the NaOH solution is increased or decreased.

More specifically, in step S1231, as shown in fig. 6, the feature distribution optimization is performed on the temperature-pH interaction coordination feature vector to obtain an optimized temperature-pH interaction coordination feature vector, which includes: s12311, based on the temperature-pH value interaction cooperative feature vector, respectively calculating quantized transferable sensing factors of transferable features of the reaction temperature time sequence feature vector and the pH value time sequence feature vector to obtain a first transferable sensing factor and a second transferable sensing factor; s12312, carrying out weighted optimization on the reaction temperature time sequence characteristic vector and the pH value time sequence characteristic vector by taking the first transferable sensing factor and the second transferable sensing factor as weighting coefficients so as to obtain a weighted reaction temperature time sequence characteristic vector and a weighted pH value time sequence characteristic vector; and S12313, performing feature level data interaction based on an attention mechanism on the weighted reaction temperature time sequence feature vector and the weighted pH value time sequence feature vector by using an attention layer between features to obtain the optimized temperature-pH value interaction cooperative feature vector.

Particularly, in the technical solution of the present disclosure, when the attention layer is used to perform attention mechanism-based feature level data interaction on the reaction temperature time sequence feature vector and the pH value time sequence feature vector to obtain the temperature-pH value interaction coordination feature vector, since the attention layer between features may extract time sequence distribution dependency characteristics between the reaction temperature time sequence feature vector and the pH value time sequence feature vector, the temperature-pH value interaction coordination feature vector may deviate from distribution association characteristics of a solution reaction temperature value and a solution pH value in a time sequence direction, thereby affecting calculation accuracy of a transfer matrix of the pH value time sequence feature vector relative to the temperature-pH value interaction coordination feature vector.

Based on this, the applicant of the present disclosure calculates the transferable sensing factors of quantification of transferable characteristics thereof, respectively, taking into consideration the dependency characteristic transfer of the reaction temperature time series characteristic vector with respect to the temperature-pH value interaction cooperative characteristic vector, and the dependency characteristic transfer of the pH value time series characteristic vector with respect to the temperature-pH value interaction cooperative characteristic vector.

Accordingly, in one specific example, based on the temperature-pH interaction synergy feature vector, respectively calculating quantized transferable sensing factors of transferable features of the reaction temperature time series feature vector and the pH time series feature vector to obtain a first transferable sensing factor and a second transferable sensing factor, comprising: based on the temperature-pH interaction synergistic feature vector, calculating quantized transferable sensing factors of transferable features of the reaction temperature time series feature vector and the pH time series feature vector respectively in the following optimization formula to obtain the first transferable sensing factor and the second transferable sensing factor; wherein, the optimization formula is:

wherein->、/>And->The reaction temperature time sequence feature vector, the pH value time sequence feature vector and the temperature-pH value interaction cooperative feature vector are respectively- >Represents the +.sup.th in the time sequence feature vector of the reaction temperature>Characteristic value of individual position->Represents the +.sup.th in the pH time sequence feature vector>Characteristic value of individual position->Representing the first of the temperature-pH value interaction cooperative characteristic vectorsCharacteristic value of individual position->Is a logarithmic function based on 2, and +.>Is a weighted superparameter,/->And->The first transferable sensing factor and the second transferable sensing factor, respectively.

The quantized transferable sensing factors of the transferable features are used for respectively estimating domain uncertainty of the feature space domain transfer through uncertainty measurement under the domain transfer, and because the domain uncertainty estimation can be used for identifying feature representations transferred among domains, by weighting the reaction temperature time sequence feature vector and the pH value time sequence feature vector respectively by taking the factors as weights and then carrying out feature level data interaction based on an attention mechanism, whether feature mapping is effectively transferred among domains or not can be identified through cross-domain alignment during the feature space domain transfer, so that the transferability of transferable features in the reaction temperature time sequence feature vector and the pH value time sequence feature vector is quantitatively perceived, the inter-domain self-adaptive dependency relation feature transfer is realized, and accordingly, the correspondence of the temperature-pH value interaction coordination feature vector and time sequence direction distribution association features is improved, and the calculation accuracy of the pH value time sequence feature vector relative to the transfer matrix of the temperature-pH value interaction coordination feature vector is improved. Therefore, the self-adaptive control of the dropping speed value of the NaOH solution can be performed in real time based on the pH value change of the actual solution, so that the efficiency and stability of the preparation process of the clay stabilizer for fracturing are optimized, and the quality and performance of the clay stabilizer product are improved.

Further, in step S1233, as shown in fig. 7, the pH timing mapping correlation feature matrix is passed through a classifier to obtain a classification result, where the classification result is used to indicate that the dropping speed value of NaOH solution should be increased or decreased, and includes: s12331, expanding the pH value time sequence mapping association characteristic matrix into classification characteristic vectors according to row vectors or column vectors; s12332, performing full-connection coding on the classification feature vectors by using a full-connection layer of the classifier to obtain coded classification feature vectors; and S12333, inputting the coding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.

That is, in the technical solution of the present disclosure, the labels of the classifier include that the dripping speed value of NaOH solution should be increased (first label) and that the dripping speed value of NaOH solution should be decreased (second label), wherein the classifier determines to which classification label the pH timing mapping correlation feature matrix belongs through a soft maximum function. It is noted that the first tag p1 and the second tag p2 do not contain the concept of artificial setting, and in fact, during the training process, the computer model does not have the concept of "the dropping speed value of NaOH solution should be increased or should be decreased", which is only two kinds of classification tags and the probability that the output characteristic is under the two classification tags, i.e. the sum of p1 and p2 is one. Therefore, the classification result that the dropping speed value of the NaOH solution should be increased or decreased is actually that the classification label is converted into the classification probability distribution conforming to the natural rule, and the physical meaning of the natural probability distribution of the label is essentially used instead of the language text meaning that the dropping speed value of the NaOH solution should be increased or decreased.

It should be appreciated that the role of the classifier is to learn the classification rules and classifier using a given class, known training data, and then classify (or predict) the unknown data. Logistic regression (logistics), SVM, etc. are commonly used to solve the classification problem, and for multi-classification problems (multi-class classification), logistic regression or SVM can be used as well, but multiple bi-classifications are required to compose multiple classifications, but this is error-prone and inefficient, and the commonly used multi-classification method is the Softmax classification function.

In summary, according to the preparation method of the clay stabilizer for fracturing, disclosed by the embodiment of the invention, the self-adaptive control of the dropping speed value of the NaOH solution can be performed in real time based on the pH value change of the actual solution, so that the stability of the preparation process of the clay stabilizer for fracturing is optimized, and the quality and performance of a clay stabilizer product are improved.

Further, in the technical scheme of the disclosure, there is also provided a clay stabilizer for fracturing, wherein the clay stabilizer for fracturing is prepared by the preparation method of the clay stabilizer for fracturing as described in any one of the foregoing.

Fig. 8 shows a block diagram of a preparation system 100 of a clay stabilizer for fracturing in accordance with an embodiment of the disclosure. As shown in fig. 8, a preparation system 100 of a clay stabilizer for fracturing according to an embodiment of the present disclosure includes: a mixing module 110 for sequentially adding an acrylamide monomer, an anionic monomer, a cationic monomer and distilled water into the reactor and stirring until the monomers are dissolved to obtain a mixed solution; the pH value adjusting module 120 is used for controlling the temperature of the mixed solution to be 30-40 ℃, adjusting the pH value of the mixed solution to be 5-7 through NaOH solution, and adjusting the water quantity to enable the total monomer mass percentage concentration to be 20-30% so as to obtain polymer solution; the reaction module 130 is used for introducing high-purity nitrogen into the polymer solution, slowly dripping an initiator, and dripping a sulfhydryl chitosan aqueous solution for reaction after the temperature of the solution is raised to 45-55 ℃ to obtain a transparent polymer product; and a forming module 140 for washing the polymer product for a plurality of times by methanol, and then vacuum drying and taking out the polymer product for granulation treatment to obtain the light yellow granular clay stabilizer for fracturing containing chitosan.

In one possible implementation, the pH adjustment module 120 includes: a value acquisition unit for acquiring solution reaction temperature values at a plurality of predetermined time points within a predetermined period of time and pH values at the plurality of predetermined time points; the data interaction characteristic analysis unit is used for carrying out data interaction characteristic analysis on the solution reaction temperature values at a plurality of preset time points and the pH values at a plurality of preset time points to obtain temperature-pH value interaction cooperative characteristic vectors; and a drop acceleration control unit, configured to determine, based on the temperature-pH value interaction synergistic feature vector, whether a drop acceleration value of the NaOH solution should be increased or decreased.

Here, it will be understood by those skilled in the art that the specific functions and operations of the respective units and modules in the above-described preparation system 100 of the clay stabilizer for fracturing have been described in detail in the above description of the preparation method of the clay stabilizer for fracturing with reference to fig. 1 to 7, and thus, repetitive descriptions thereof will be omitted.

As described above, the preparation system 100 of the clay stabilizer for fracturing according to the embodiment of the present disclosure may be implemented in various wireless terminals, such as a server or the like having a preparation algorithm of the clay stabilizer for fracturing. In one possible implementation, the preparation system 100 of the clay stabilizer for fracturing according to embodiments of the present disclosure may be integrated into a wireless terminal as one software module and/or hardware module. For example, the preparation system 100 of the clay stabilizer for fracturing may be a software module in the operating system of the wireless terminal, or may be an application developed for the wireless terminal; of course, the fracturing clay stabilizer preparation system 100 may also be one of the many hardware modules of the wireless terminal.

Alternatively, in another example, the preparation system 100 of the clay stabilizer for fracturing and the wireless terminal may be separate devices, and the preparation system 100 of the clay stabilizer for fracturing may be connected to the wireless terminal through a wired and/or wireless network and transmit interactive information in an agreed data format.

Fig. 9 shows an application scenario diagram of a preparation method of a clay stabilizer for fracturing according to an embodiment of the present disclosure. As shown in fig. 9, in this application scenario, first, solution reaction temperature values (e.g., D1 shown in fig. 9) at a plurality of predetermined time points and pH values (e.g., D2 shown in fig. 9) at the plurality of predetermined time points within a predetermined period of time are acquired, and then, the solution reaction temperature values at the plurality of predetermined time points and the pH values at the plurality of predetermined time points are input to a server (e.g., S shown in fig. 9) where a preparation algorithm of a clay stabilizer for fracturing is deployed, wherein the server is capable of processing the solution reaction temperature values at the plurality of predetermined time points and the pH values at the plurality of predetermined time points using the preparation algorithm of the clay stabilizer for fracturing to obtain classification results indicating that a dropping speed value of NaOH solution should be increased or should be decreased.

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.

The foregoing description of the embodiments of the present disclosure has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the improvement of technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

Claims (9)

1. The preparation method of the clay stabilizer for fracturing is characterized by comprising the following steps: sequentially adding an acrylamide monomer, an anionic monomer, a cationic monomer and distilled water into a reactor, and stirring until the monomers are dissolved to obtain a mixed solution; controlling the temperature of the mixed solution to be 30-40 ℃, adjusting the pH value of the mixed solution to be 5-7 through NaOH solution, and adjusting the water quantity to enable the mass percentage concentration of the total monomer to be 20-30% so as to obtain polymer solution; introducing high-purity nitrogen into the polymer solution, slowly dropwise adding an initiator, and dropwise adding a sulfhydryl chitosan aqueous solution to react after the temperature of the solution is raised to 45-55 ℃ to obtain a transparent polymer product; washing the polymer product for a plurality of times by methanol, and then carrying out vacuum drying and taking out granulation treatment to obtain the light yellow granular clay stabilizer for fracturing containing chitosan; wherein, the temperature of the mixed solution is controlled to be 30-40 ℃, and after the pH value of the mixed solution is adjusted to be 5-7 by NaOH solution, the water quantity is adjusted to ensure that the total monomer mass percentage concentration is 20-30%, so as to obtain polymer solution, which comprises the following steps: acquiring solution reaction temperature values at a plurality of preset time points in a preset time period and pH values at the preset time points; performing data interaction feature analysis on the solution reaction temperature values at the plurality of preset time points and the pH values at the plurality of preset time points to obtain a temperature-pH value interaction synergistic feature vector; and determining that the drop rate value of the NaOH solution should be increased or decreased based on the temperature-pH value interaction cooperative characteristic vector.

2. The method of preparing a clay stabilizer for fracturing according to claim 1, wherein performing data interaction feature analysis on the solution reaction temperature values at the plurality of predetermined time points and the pH values at the plurality of predetermined time points to obtain a temperature-pH value interaction synergistic feature vector comprises: arranging the solution reaction temperature values at a plurality of preset time points and the solution pH values at a plurality of preset time points into a reaction temperature time sequence input vector and a pH value time sequence input vector according to a time dimension respectively; performing time sequence change feature extraction on the reaction temperature time sequence input vector and the pH value time sequence input vector to obtain a reaction temperature time sequence feature vector and a pH value time sequence feature vector; and performing feature interaction association coding on the reaction temperature time sequence feature vector and the pH value time sequence feature vector to obtain the temperature-pH value interaction cooperative feature vector.

3. The method of preparing a clay stabilizer for fracturing according to claim 2, wherein performing time-series change feature extraction on the reaction temperature time-series input vector and the pH time-series input vector to obtain a reaction temperature time-series feature vector and a pH time-series feature vector, comprises: and passing the reaction temperature time sequence input vector and the pH value time sequence input vector through a time sequence feature extractor based on a one-dimensional convolution layer to obtain the reaction temperature time sequence feature vector and the pH value time sequence feature vector.

4. The method of producing a clay stabilizer for fracturing according to claim 3, wherein performing feature cross-correlation encoding on the reaction temperature time series feature vector and the pH time series feature vector to obtain the temperature-pH value cross-correlation feature vector, comprises: and performing feature level data interaction based on an attention mechanism on the reaction temperature time sequence feature vector and the pH value time sequence feature vector by using an inter-feature attention layer to obtain the temperature-pH value interaction cooperative feature vector.

5. The method for preparing a clay stabilizer for fracturing according to claim 4, wherein determining whether a drop rate value of NaOH solution should be increased or decreased based on the temperature-pH interaction synergistic eigenvector comprises: performing feature distribution optimization on the temperature-pH value interaction coordination feature vector to obtain an optimized temperature-pH value interaction coordination feature vector; calculating a transfer matrix of the pH value time sequence feature vector relative to the optimized temperature-pH value interaction cooperative feature vector as a pH value time sequence mapping association feature matrix; and passing the pH time sequence mapping correlation characteristic matrix through a classifier to obtain a classification result, wherein the classification result is used for indicating that the dropping speed value of the NaOH solution should be increased or decreased.

6. The method for preparing a clay stabilizer for fracturing according to claim 5, wherein optimizing the feature distribution of the temperature-pH value interaction coordination feature vector to obtain an optimized temperature-pH value interaction coordination feature vector comprises: based on the temperature-pH interaction cooperative feature vector, respectively calculating quantized transferable sensing factors of transferable features of the reaction temperature timing feature vector and the pH timing feature vector to obtain a first transferable sensing factor and a second transferable sensing factor; taking the first transferable sensing factor and the second transferable sensing factor as weighting coefficients to carry out weighted optimization on the reaction temperature time sequence feature vector and the pH value time sequence feature vector so as to obtain a weighted reaction temperature time sequence feature vector and a weighted pH value time sequence feature vector; and performing feature level data interaction based on an attention mechanism on the weighted reaction temperature time sequence feature vector and the weighted pH value time sequence feature vector by using an attention layer among features to obtain the optimized temperature-pH value interaction cooperative feature vector.

7. The method for producing a clay stabilizer for fracturing according to claim 6, wherein the reaction temperature time series feature vector and the pH time series feature vector are calculated based on the temperature-pH value interaction synergistic feature vector, respectively Transferring the quantized transferable sensing factors of the feature to obtain a first transferable sensing factor and a second transferable sensing factor, comprising: based on the temperature-pH interaction synergistic feature vector, calculating quantized transferable sensing factors of transferable features of the reaction temperature time series feature vector and the pH time series feature vector respectively in the following optimization formula to obtain the first transferable sensing factor and the second transferable sensing factor; wherein, the optimization formula is:wherein->、/>And->The reaction temperature time sequence feature vector, the pH value time sequence feature vector and the temperature-pH value interaction cooperative feature vector are respectively->Represents the +.sup.th in the time sequence feature vector of the reaction temperature>Characteristic value of individual position->Represents the +.sup.th in the pH time sequence feature vector>Characteristic value of individual position->Representing the +.sup.th in the temperature-pH interaction co-characteristic vector>Characteristic value of individual position->Is a logarithmic function based on 2, and +.>Is a weighted superparameter,/->And->The first transferable sensing factor and the second transferable sensing factor, respectively.

8. The method for preparing a clay stabilizer for fracturing according to claim 7, wherein the pH time series mapping correlation characteristic matrix is passed through a classifier to obtain a classification result, the classification result is used for indicating that a dropping speed value of NaOH solution should be increased or decreased, and the method comprises: expanding the pH value time sequence mapping association characteristic matrix into a classification characteristic vector according to a row vector or a column vector; performing full-connection coding on the classification feature vectors by using a full-connection layer of the classifier to obtain coded classification feature vectors; and inputting the coding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.

9. A clay stabilizer for fracturing, characterized in that the clay stabilizer for fracturing is produced by the method for producing a clay stabilizer for fracturing according to any one of claims 1 to 8.