CN116680620A - Preparation method and system of anti-emulsifying agent for fracturing - Google Patents

Preparation method and system of anti-emulsifying agent for fracturing Download PDF

Info

Publication number
CN116680620A
CN116680620A CN202310941663.2A CN202310941663A CN116680620A CN 116680620 A CN116680620 A CN 116680620A CN 202310941663 A CN202310941663 A CN 202310941663A CN 116680620 A CN116680620 A CN 116680620A
Authority
CN
China
Prior art keywords
reactor
temperature
surface state
time sequence
training
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202310941663.2A
Other languages
Chinese (zh)
Other versions
CN116680620B (en
Inventor
张雷
李巧丽
王建梅
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Qaramay Ziguang Technology Co ltd
Original Assignee
Qaramay Ziguang Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Qaramay Ziguang Technology Co ltd filed Critical Qaramay Ziguang Technology Co ltd
Priority to CN202310941663.2A priority Critical patent/CN116680620B/en
Publication of CN116680620A publication Critical patent/CN116680620A/en
Application granted granted Critical
Publication of CN116680620B publication Critical patent/CN116680620B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • C—CHEMISTRY; METALLURGY
    • C08—ORGANIC MACROMOLECULAR COMPOUNDS; THEIR PREPARATION OR CHEMICAL WORKING-UP; COMPOSITIONS BASED THEREON
    • C08G—MACROMOLECULAR COMPOUNDS OBTAINED OTHERWISE THAN BY REACTIONS ONLY INVOLVING UNSATURATED CARBON-TO-CARBON BONDS
    • C08G14/00—Condensation polymers of aldehydes or ketones with two or more other monomers covered by at least two of the groups C08G8/00 - C08G12/00
    • C08G14/02—Condensation polymers of aldehydes or ketones with two or more other monomers covered by at least two of the groups C08G8/00 - C08G12/00 of aldehydes
    • C08G14/04—Condensation polymers of aldehydes or ketones with two or more other monomers covered by at least two of the groups C08G8/00 - C08G12/00 of aldehydes with phenols
    • C08G14/06—Condensation polymers of aldehydes or ketones with two or more other monomers covered by at least two of the groups C08G8/00 - C08G12/00 of aldehydes with phenols and monomers containing hydrogen attached to nitrogen
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
    • B01F—MIXING, e.g. DISSOLVING, EMULSIFYING OR DISPERSING
    • B01F33/00—Other mixers; Mixing plants; Combinations of mixers
    • B01F33/80—Mixing plants; Combinations of mixers
    • B01F33/836—Mixing plants; Combinations of mixers combining mixing with other treatments
    • B01F33/8362—Mixing plants; Combinations of mixers combining mixing with other treatments with chemical reactions
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
    • B01J—CHEMICAL OR PHYSICAL PROCESSES, e.g. CATALYSIS OR COLLOID CHEMISTRY; THEIR RELEVANT APPARATUS
    • B01J3/00—Processes of utilising sub-atmospheric or super-atmospheric pressure to effect chemical or physical change of matter; Apparatus therefor
    • B01J3/006—Processes utilising sub-atmospheric pressure; Apparatus therefor
    • C—CHEMISTRY; METALLURGY
    • C09—DYES; PAINTS; POLISHES; NATURAL RESINS; ADHESIVES; COMPOSITIONS NOT OTHERWISE PROVIDED FOR; APPLICATIONS OF MATERIALS NOT OTHERWISE PROVIDED FOR
    • C09K—MATERIALS FOR MISCELLANEOUS APPLICATIONS, NOT PROVIDED FOR ELSEWHERE
    • C09K8/00—Compositions for drilling of boreholes or wells; Compositions for treating boreholes or wells, e.g. for completion or for remedial operations
    • C09K8/60—Compositions for stimulating production by acting on the underground formation
    • C09K8/62—Compositions for forming crevices or fractures
    • C09K8/66—Compositions based on water or polar solvents
    • C09K8/68—Compositions based on water or polar solvents containing organic compounds
    • C—CHEMISTRY; METALLURGY
    • C09—DYES; PAINTS; POLISHES; NATURAL RESINS; ADHESIVES; COMPOSITIONS NOT OTHERWISE PROVIDED FOR; APPLICATIONS OF MATERIALS NOT OTHERWISE PROVIDED FOR
    • C09K—MATERIALS FOR MISCELLANEOUS APPLICATIONS, NOT PROVIDED FOR ELSEWHERE
    • C09K8/00—Compositions for drilling of boreholes or wells; Compositions for treating boreholes or wells, e.g. for completion or for remedial operations
    • C09K8/60—Compositions for stimulating production by acting on the underground formation
    • C09K8/84—Compositions based on water or polar solvents
    • C09K8/86—Compositions based on water or polar solvents containing organic compounds
    • C09K8/88—Compositions based on water or polar solvents containing organic compounds macromolecular compounds
    • C09K8/885—Compositions based on water or polar solvents containing organic compounds macromolecular compounds obtained otherwise than by reactions only involving carbon-to-carbon unsaturated bonds
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2123/00—Data types
    • G06F2123/02—Data types in the time domain, e.g. time-series data
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P20/00—Technologies relating to chemical industry
    • Y02P20/141—Feedstock

Landscapes

  • Engineering & Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • General Physics & Mathematics (AREA)
  • Chemical Kinetics & Catalysis (AREA)
  • Artificial Intelligence (AREA)
  • Organic Chemistry (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Health & Medical Sciences (AREA)
  • Materials Engineering (AREA)
  • General Life Sciences & Earth Sciences (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Polymers & Plastics (AREA)
  • Medicinal Chemistry (AREA)
  • Investigating Or Analyzing Materials Using Thermal Means (AREA)

Abstract

The invention discloses a preparation method and a system of an anti-emulsifying agent for fracturing, wherein phenol-amine aldehyde resin and potassium persulfate are heated to a preset temperature to obtain a first mixed solution; fully reacting ethylene oxide with the first mixed solution to obtain a first drying agent; cooling the first drying agent, and then adding ethylene glycol butyl ether to obtain a component A; heating dichloropropanol and the potassium persulfate to a preset temperature to obtain a second mixed solution; fully reacting the ethylene oxide with the second mixed solution to obtain a second drying agent; cooling the second drying agent, and then adding the ethylene glycol butyl ether to obtain a component B; and uniformly mixing the component A and the component B to obtain the anti-emulsifying agent for fracturing. In this way, the preparation quality and performance of the anti-emulsifying agent can be ensured, and the stability and reliability of the anti-emulsifying agent can be ensured.

Description

Preparation method and system of anti-emulsifying agent for fracturing
Technical Field
The invention relates to the technical field of intelligent preparation, in particular to a preparation method and a system of an anti-emulsifying agent for fracturing.
Background
Fracturing is a commonly used oilfield development technique to increase well production. During fracturing, water and chemical additives are injected into the wellhead, and then high pressure is created within the well, expanding the rock fracture, thereby increasing the mobility of the oil or natural gas. However, during fracturing, water and chemical additives in the fracturing fluid may emulsify the oil in the subterranean reservoir, causing the oil to mix with the water, reducing well production. Therefore, the anti-emulsifying agent plays an important role in the fracturing process.
The function of the anti-emulsifying agent is to prevent the water and chemical additives from undergoing an emulsifying reaction with the oil, thereby maintaining the fluidity and yield of the oil. However, existing anti-emulsifiers have some problems. For example, certain anti-emulsifying agents are effective only for a particular type of oil field or well, and may be ineffective for other oil fields or wells. In addition, existing anti-emulsifiers have limited performance in stabilizing emulsions, which can easily lead to coalescence and instability of the droplets.
Thus, an optimized formulation of a fracturing anti-emulsifier is desired.
Disclosure of Invention
The embodiment of the invention provides a preparation method and a system of an anti-emulsifying agent for fracturing, which can ensure the preparation quality and performance of the anti-emulsifying agent and simultaneously ensure the stability and reliability of the anti-emulsifying agent.
The embodiment of the invention also provides a preparation method of the anti-emulsifying agent for fracturing, which comprises the following steps: adding phenol-amine aldehyde resin and potassium persulfate into a first reactor for stirring and vacuumizing treatment, and heating to a preset temperature to obtain a first mixed solution; introducing ethylene oxide into the first reactor to fully react with the first mixed solution to obtain a first drier; cooling the first drying agent, and then adding ethylene glycol butyl ether to obtain a component A; adding dichloropropanol and the potassium persulfate into a second reactor for stirring and vacuumizing treatment, and heating to a preset temperature to obtain a second mixed solution; introducing the ethylene oxide into the second reactor to fully react with the second mixed solution to obtain a second dry agent; cooling the second drying agent, and then adding the ethylene glycol butyl ether to obtain a component B; and uniformly mixing the component A and the component B to obtain the anti-emulsifying agent for fracturing.
In the preparation method of the anti-emulsifying agent for fracturing, ethylene oxide is introduced into the first reactor to fully react with the first mixed solution to obtain a first drier, and the preparation method comprises the following steps of: acquiring temperature values in a reactor at a plurality of preset time points in a preset time period, and acquiring surface state images of the reaction liquid at the preset time points by a camera; performing time sequence collaborative correlation analysis on the temperature values in the reactor at a plurality of preset time points and the surface state images at a plurality of preset time points to obtain temperature-surface state time sequence correlation characteristics; and determining whether the reaction is complete based on the temperature-surface state timing correlation characteristic.
In the above method for preparing a fracturing demulsifier, performing a time-series collaborative correlation analysis on the in-reactor temperature values at the plurality of predetermined time points and the surface state images at the plurality of predetermined time points to obtain a temperature-surface state time-series correlation feature, including: extracting in-reactor temperature time-series variation characteristics from the in-reactor temperature values at the plurality of predetermined time points; extracting surface state timing variation features from the surface state images at the plurality of predetermined time points; and fusing the temperature time sequence variation characteristic and the surface state time sequence variation characteristic in the reactor to obtain the temperature-surface state time sequence correlation characteristic.
In the above method for producing a fracturing demulsifier, extracting a time-series change characteristic of the temperature in the reactor from the temperature values in the reactor at the plurality of predetermined time points, the method comprising: arranging the temperature values in the reactor at a plurality of preset time points into a time sequence input vector of the temperature in the reactor according to a time dimension; calculating the difference value between the temperature values in the reactor at every two adjacent preset time points in the temperature time sequence input vector in the reactor to obtain a temperature time sequence change input vector in the reactor; and the temperature time sequence change input vector in the reactor passes through a time sequence feature extractor based on a one-dimensional convolution layer to obtain a second-order time sequence feature vector of the temperature in the reactor as the time sequence change feature in the reactor.
In the above-described method of producing a fracturing demulsifier, extracting a surface state time-series change feature from the surface state images at the plurality of predetermined time points includes: and aggregating the surface state images of the plurality of preset time points into a three-dimensional input tensor along the time dimension, and then obtaining a surface state time sequence feature vector serving as the surface state time sequence change feature through a surface state time sequence feature extractor based on a three-dimensional convolutional neural network model.
In the preparation method of the anti-emulsifying agent for fracturing, the method for obtaining the temperature-surface state time sequence correlation characteristic by fusing the temperature time sequence variation characteristic and the surface state time sequence variation characteristic in the reactor comprises the following steps: and fusing the temperature second-order time sequence characteristic vector and the surface state time sequence characteristic vector in the reactor to obtain a temperature-surface state time sequence correlation characteristic vector as the temperature-surface state time sequence correlation characteristic.
In the above preparation method of the anti-emulsifying agent for fracturing, determining whether the reaction is complete based on the temperature-surface state time sequence correlation characteristics includes: and passing the temperature-surface state time sequence correlation characteristic vector through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the reaction is complete or not.
The preparation method of the anti-emulsifying agent for fracturing further comprises the training steps of: training the timing sequence feature extractor based on the one-dimensional convolution layer, the surface state timing sequence feature extractor based on the three-dimensional convolution neural network model and the classifier; wherein the training step comprises: acquiring training data, wherein the training data comprises temperature values in a training reactor at a plurality of preset time points in a preset time period, and training surface state images of reaction liquid at the preset time points; arranging the temperature values in the training reactor at a plurality of preset time points into a time sequence input vector of the temperature in the training reactor according to a time dimension; calculating the difference value between the temperature values in the training reactor at every two adjacent preset time points in the temperature time sequence input vector in the training reactor to obtain a temperature time sequence change input vector in the training reactor; the temperature time sequence change input vector in the training reactor passes through the time sequence feature extractor based on the one-dimensional convolution layer to obtain a temperature second-order time sequence feature vector in the training reactor; aggregating the training surface state images of the plurality of preset time points into training three-dimensional input tensors along the time dimension, and then passing through the surface state time sequence feature extractor based on the three-dimensional convolutional neural network model to obtain training surface state time sequence feature vectors; fusing the temperature second-order time sequence feature vector in the training reactor and the training surface state time sequence feature vector to obtain a training temperature-surface state time sequence correlation feature vector; passing the training temperature-surface state time sequence associated feature vector through the classifier to obtain a classification loss function value; calculating a common manifold implicit similarity factor of the temperature second-order time sequence feature vector in the training reactor and the training surface state time sequence feature vector to obtain a common manifold implicit similarity loss function value; and training the time sequence feature extractor based on the one-dimensional convolution layer, the surface state time sequence feature extractor based on the three-dimensional convolution neural network model and the classifier by taking the weighted sum of the classification loss function value and the common manifold implicit similarity loss function value as the loss function value and transmitting the time sequence feature extractor based on the one-dimensional convolution layer in the gradient descending direction.
In the preparation method of the anti-emulsifying agent for fracturing, the common manifold implicit similarity factor of the temperature second-order time sequence characteristic vector in the training reactor and the training surface state time sequence characteristic vector is calculated to obtain the common manifold implicit similarity factorA manifold implicit similarity loss function value comprising: calculating a common manifold implicit similarity factor of the training reactor internal temperature second-order time sequence feature vector and the training surface state time sequence feature vector according to the following loss formula to obtain a common manifold implicit similarity loss function value; wherein, the loss formula is: wherein ,/> and />Is the temperature second order time sequence characteristic vector in the training reactor and the training surface state time sequence characteristic vector, respectively, < >>Is the transpose of the training surface state timing feature vector,/->Representing the two norms of the vector, and +.>Representing the square root of the Frobenius norm of the matrix, the training reactor internal temperature second order time sequence feature vector and the training surface state time sequence feature vector are in the form of column vectors, and the training reactor internal temperature second order time sequence feature vector and the training surface state time sequence feature vector are in the form of column vectors>、/>、/> and />For the weight super parameter, ++>Representing the multiplication of the vectors,/>representing multiplication by location +.>Representing difference by position +.>Representing the common manifold implicit similarity loss function value.
The embodiment of the invention also provides a preparation system of the anti-emulsifying agent for fracturing, which comprises the following steps: the first mixing module is used for adding phenol-amine aldehyde resin and potassium persulfate into the first reactor for stirring and vacuumizing treatment, and heating to a preset temperature to obtain a first mixed solution; a first reaction module for introducing ethylene oxide into the first reactor to react with the first mixed solution sufficiently to obtain a first dry agent; the first component generating module is used for cooling the first drying agent and then adding ethylene glycol butyl ether to obtain a component A; the second mixing module is used for adding dichloropropanol and the potassium persulfate into a second reactor for stirring and vacuumizing treatment, and heating to a preset temperature to obtain a second mixed solution; a second reaction module for introducing the ethylene oxide into the second reactor to fully react with the second mixed solution to obtain a second dry agent; the second component generating module is used for cooling the second drying agent and then adding the second drying agent into the ethylene glycol butyl ether to obtain a component B; and an anti-emulsifying agent generation module for uniformly mixing the component A and the component B to obtain an anti-emulsifying agent for fracturing; in the preparation system of the anti-emulsifying agent for fracturing, the first reaction module comprises: the image acquisition unit is used for acquiring temperature values in the reactor at a plurality of preset time points in a preset time period and surface state images of the reaction liquid acquired by the camera at the preset time points; the correlation analysis unit is used for carrying out time sequence collaborative correlation analysis on the temperature values in the reactor at a plurality of preset time points and the surface state images at a plurality of preset time points so as to obtain temperature-surface state time sequence correlation characteristics; and a reaction completion determination unit configured to determine whether the reaction is complete based on the temperature-surface state timing correlation characteristic.
The beneficial effects are that: the preparation method and the system for the anti-emulsifying agent for fracturing, provided by the embodiment of the invention, can ensure the preparation quality and performance of the anti-emulsifying agent, and simultaneously ensure the stability and reliability of the anti-emulsifying agent.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
In the drawings: fig. 1 is a flowchart of a preparation method of an anti-emulsifying agent for fracturing according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a system architecture of a preparation method of an anti-emulsifying agent for fracturing according to an embodiment of the present invention.
Fig. 3 is a flowchart of a sub-step of step 120 in a preparation method of a fracturing emulsifier according to an embodiment of the present invention.
Fig. 4 is a block diagram of a preparation system of an anti-emulsifying agent for fracturing according to an embodiment of the present invention.
Fig. 5 is an application scenario diagram of a preparation method of an anti-emulsifying agent for fracturing, which is provided in an embodiment of the invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention will be described in further detail with reference to the accompanying drawings. The exemplary embodiments of the present invention and their descriptions herein are for the purpose of explaining the present invention, but are not to be construed as limiting the invention.
As used in the specification 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.
A flowchart is used in the present invention to describe the operations performed by a system according to embodiments of the present invention. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.
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.
The word "exemplary" is used herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.
It should be appreciated that the anti-emulsifying agent for fracturing is a special chemical used in oil and gas exploitation and has the main function of preventing water and oil from emulsifying during the fracturing process. In fracturing operations, water and oil may mix together to form an emulsion, resulting in the inability of the oil and gas to flow out effectively. The use of the anti-emulsifying agent can effectively reduce the emulsification risk and improve the oil and gas yield.
The anti-emulsifying agent for fracturing is usually a surfactant, and forms a surface active film between water and oil to prevent them from mixing. Thus, the separation state of water and oil can be maintained, and oil gas can smoothly flow out. The choice of the anti-emulsifying agent for fracturing is determined according to the specific oil and gas exploitation conditions and the effect to be achieved.
Generally speaking, the anti-emulsifying agent should have the following characteristics: 1. the high efficiency can effectively prevent the emulsification of water and oil and improve the yield of oil gas. 2. Stability, stability under severe conditions such as high temperature, high pressure, acid and alkali, and the like, and is not easy to decompose or fail. 3. Environmental friendliness, no toxicity and no harm to the environment, and meets the environmental protection requirement. 4. The economical efficiency, the cost is moderate, the usage amount is small, and the effect is obvious.
The preparation of the anti-emulsifying agent for fracturing is usually carried out by a chemical synthesis method, and the specific preparation process and formulation can be different according to different anti-emulsifying agents.
In one embodiment of the present invention, fig. 1 is a flowchart of a preparation method of an anti-emulsifying agent for fracturing provided in the embodiment of the present invention. As shown in fig. 1, a preparation method 100 of an anti-emulsifying agent for fracturing according to an embodiment of the present invention includes: 110, adding phenol-amine aldehyde resin and potassium persulfate into a first reactor for stirring and vacuumizing treatment, and heating to a preset temperature to obtain a first mixed solution; 120, introducing ethylene oxide into the first reactor to fully react with the first mixed solution to obtain a first drying agent; 130, cooling the first drying agent, and then adding ethylene glycol butyl ether to obtain a component A;140, adding dichloropropanol and the potassium persulfate into a second reactor for stirring and vacuumizing treatment, and heating to a preset temperature to obtain a second mixed solution; 150, introducing the ethylene oxide into the second reactor to fully react with the second mixed solution to obtain a second dry agent; 160, cooling the second drying agent, and then adding the ethylene glycol butyl ether to obtain a component B; and, 170, uniformly mixing the component A and the component B to obtain the anti-emulsifying agent for fracturing.
Wherein, in the step 110, the temperature is controlled during the heating process to ensure that the reaction proceeds smoothly. Meanwhile, stirring and vacuumizing can promote the reaction and ensure uniform mixing. The addition of the phenol-amine aldehyde resin and the potassium persulfate can provide the raw materials and the catalyst required by the reaction, and promote the subsequent reaction.
In step 120, the ethylene oxide feed controls the time and temperature of the reaction to ensure that the reaction is sufficiently conducted. Meanwhile, safety measures are taken to ensure the safety of operators. The reaction of ethylene oxide can crosslink the phenol-amine-aldehyde resin to form a dry agent with anti-emulsifying properties.
In the step 130, the temperature reduction process is gradually performed to avoid a severe temperature change. Meanwhile, the ethylene glycol butyl ether needs to be stirred uniformly when being added, so that uniform mixing is ensured. The addition of butyl glycol ether may provide solvent properties that allow for proper flowability and stability of component a.
In step 140, the heating process is controlled to a temperature to ensure that the reaction proceeds smoothly. Stirring and vacuum can promote the reaction and ensure uniform mixing. The addition of dichloropropanol and potassium persulfate can provide raw materials and catalysts required by the reaction, and promote the subsequent reaction.
In step 150, the ethylene oxide feed controls the time and temperature of the reaction to ensure that the reaction is sufficiently conducted. Meanwhile, safety measures are required to be taken, so that the safety of operators is ensured. The reaction of ethylene oxide can lead dichloropropanol to generate crosslinking reaction to form the dry agent with anti-emulsifying property.
In step 160, the temperature reduction process is gradually performed to avoid a severe temperature change. Meanwhile, the ethylene glycol butyl ether needs to be stirred uniformly when being added, so that uniform mixing is ensured. The addition of butyl glycol ether may provide solvent properties that allow for proper flowability and stability of component B.
In step 170, the mixing process is thoroughly stirred to ensure that component a and component B are uniformly mixed. The uniform mixing of the component A and the component B can obtain the anti-emulsifying agent for fracturing with stability and high efficiency.
The method for preparing the anti-emulsifying agent for fracturing comprises a series of reaction and mixing steps, and the anti-emulsifying agent with high efficiency, stability and environmental friendliness can be obtained by controlling the factors such as temperature, time, mixing uniformity and the like.
Accordingly, in the preparation of the anti-emulsifying agent for fracturing, it is considered that the completeness judgment of the reaction is particularly important when ethylene oxide is introduced into the first reactor to fully react with the first mixed solution to prepare the first dry agent. The purpose of the adequate reaction judgment is to determine whether the reaction has been completed, which if not done completely, may lead to unstable or undesirable properties of the anti-emulsifying agent; if the reaction is incomplete, there may be a case where unreacted ethylene oxide remains in the product, which may affect the quality and effect of the emulsifier. In addition, the temperature in the reactor is changed and the surface state of the reaction liquid is changed in the reaction process, so that whether the reaction is complete can be accurately judged relatively by combining the two.
Based on the above, the technical concept of the application is that after the temperature value in the reactor and the surface state image of the reaction liquid at a plurality of preset time points are respectively acquired through the sensor and the camera, a data processing and analyzing algorithm is introduced at the rear end to respectively carry out temperature time sequence change analysis in the reactor and surface state time sequence change analysis of the reaction liquid, and then detection and judgment of complete reaction are comprehensively carried out based on the time sequence change characteristics of the temperature in the reactor and the correlation characteristic information between the surface state time sequence change characteristics of the reaction liquid, so that the preparation quality and performance of the anti-emulsifying agent are ensured, and meanwhile, the stability and reliability of the anti-emulsifying agent are ensured.
Fig. 2 is a schematic diagram of a system architecture of a preparation method of an anti-emulsifying agent for fracturing according to an embodiment of the present application. Fig. 3 is a flowchart of a sub-step of step 120 in a preparation method of a fracturing emulsifier according to an embodiment of the present application. As shown in fig. 2 and 3, passing ethylene oxide into the first reactor to react substantially with the first mixed solution to obtain a first dry agent, comprising: 121, acquiring temperature values in the reactor at a plurality of preset time points in a preset time period, and acquiring surface state images of the reaction liquid at the preset time points by a camera; 122, performing time sequence collaborative correlation analysis on the temperature values in the reactor at the plurality of preset time points and the surface state images at the plurality of preset time points to obtain temperature-surface state time sequence correlation characteristics; and, 123, determining whether the reaction is complete based on the temperature-surface state timing correlation characteristic.
Wherein, first, by installing a temperature sensor to record temperature data in the reactor, the temperature value in the reactor at a plurality of time points in a preset time period can be obtained, thereby being beneficial to monitoring the progress of the reaction and controlling the reaction condition. Then, by continuously collecting the surface of the reaction liquid by using a camera, a plurality of reaction liquid surface state images at preset time points can be obtained, and the reaction liquid surface state images can be used for analyzing the change in the reaction process and judging the progress of the reaction. Then, by performing time sequence analysis on the temperature value and the surface state image in the reactor at a preset time point, the change of the temperature and the surface state can be correlated, so that the relationship between the temperature change and the surface state of the reaction solution can be known, and the progress of the reaction can be further judged. Finally, by analyzing the temperature-surface state time sequence correlation characteristics, whether the reaction is completely performed can be judged. For example, if the temperature tends to be stable and the surface state image shows that the reaction liquid has reached a desired state, it can be inferred that the reaction has completely progressed.
Through the steps, the reaction process can be monitored and analyzed in real time, and whether the reaction is complete or not can be determined, so that the reaction condition is optimized and the product quality is improved. Meanwhile, more visual reaction information can be obtained by collecting the surface state image of the reaction liquid, and the reaction progress is assisted to be judged.
Specifically, in the step 121, in-reactor temperature values at a plurality of predetermined time points within a predetermined period of time are acquired, and surface state images of the reaction liquid at the plurality of predetermined time points are acquired by the camera.
In the technical scheme of the application, firstly, temperature values in the reactor at a plurality of preset time points in a preset time period and surface state images of the reaction liquid at the preset time points, which are acquired by a camera, are acquired. The surface state images of the reaction liquid at a plurality of predetermined time points acquired by the camera can provide visual information about the progress of the reaction and the reaction liquid. These images can be analyzed using computer vision techniques and image processing algorithms to determine the extent of the reaction and whether the reaction is complete.
For example, an image processing algorithm may be used to detect an index such as a color change, a concentration change, or a liquid level change of the reaction liquid to evaluate the progress of the reaction; a specific threshold or reference image may also be set to compare with the current image to determine if the reaction has progressed completely.
It should be noted that the image captured by the camera only provides information on the surface state, which may not be fully reflected for the case inside the reactor. Thus, the progress of the reaction can be more comprehensively evaluated by combining the temperature data and the image analysis.
Specifically, in the step 122, performing a time-series collaborative correlation analysis on the in-reactor temperature values at the plurality of predetermined time points and the surface state images at the plurality of predetermined time points to obtain a temperature-surface state time-series correlation feature, including: extracting in-reactor temperature time-series variation characteristics from the in-reactor temperature values at the plurality of predetermined time points; extracting surface state timing variation features from the surface state images at the plurality of predetermined time points; and fusing the temperature time sequence change characteristic and the surface state time sequence change characteristic in the reactor to obtain the temperature-surface state time sequence correlation characteristic.
Wherein extracting the in-reactor temperature time-series variation features from the in-reactor temperature values at the plurality of predetermined time points comprises: arranging the temperature values in the reactor at a plurality of preset time points into a time sequence input vector of the temperature in the reactor according to a time dimension; calculating the difference value between the temperature values in the reactor at every two adjacent preset time points in the temperature time sequence input vector in the reactor to obtain a temperature time sequence change input vector in the reactor; and the temperature time sequence change input vector in the reactor passes through a time sequence feature extractor based on a one-dimensional convolution layer to obtain a second-order time sequence feature vector of the temperature in the reactor as the time sequence change feature in the reactor.
Then, for the temperature values in the reactor at the plurality of preset time points, the temperature values in the reactor have a time sequence dynamic change rule in the time dimension, and the time sequence change characteristic of the temperature is weak, which is small-scale change information relative to the temperature values in the reactor in the time dimension. Therefore, in the technical scheme of the application, after the temperature values in the reactor at a plurality of preset time points are arranged into the time sequence input vector of the temperature in the reactor according to the time dimension, the distribution information of the temperature values in the reactor on the time sequence is integrated, and then the difference value between the temperature values in the reactor at every two adjacent preset time points in the time sequence input vector of the temperature in the reactor is further calculated to obtain the time sequence change input vector of the temperature in the reactor. In this way, capturing the time sequence characteristic of the temperature value in the reactor according to the time sequence relative change characteristic of the temperature value in the reactor can increase the sensitivity to temperature change, so that the time sequence dynamic change characteristic information of the temperature value in the reactor in the time dimension can be extracted more effectively.
And then, carrying out feature mining on the temperature time sequence change input vector in the reactor by a time sequence feature extractor based on a one-dimensional convolution layer so as to extract time sequence dynamic associated feature information of time sequence relative change information of temperature values in the reactor in a time dimension, thereby obtaining a second-order time sequence feature vector of the temperature in the reactor.
In one embodiment of the present application, extracting the surface state timing variation features from the surface state images at the plurality of predetermined time points includes: and aggregating the surface state images of the plurality of preset time points into a three-dimensional input tensor along the time dimension, and then obtaining a surface state time sequence feature vector serving as the surface state time sequence change feature through a surface state time sequence feature extractor based on a three-dimensional convolutional neural network model.
Further, as for the surface state images at the plurality of predetermined time points, it is considered that the surface state implicit characteristic information about the reaction liquid at the predetermined time point exists due to the presence of the surface state information at the respective predetermined time points in the surface state images. Therefore, in order to capture time sequence change characteristic information of the surface state characteristics of the reaction liquid in the time dimension, in the technical scheme of the application, after the surface state images of a plurality of preset time points are further aggregated into a three-dimensional input tensor along the time dimension, characteristic mining is carried out in a surface state time sequence characteristic extractor based on a three-dimensional convolution neural network model so as to extract dynamic change characteristic information of the surface state characteristics of the reaction liquid in the time dimension, thereby obtaining a surface state time sequence characteristic vector. In particular, the convolution kernel of the three-dimensional convolution neural network model is a three-dimensional convolution kernel, which has W (width), H (height) and C (channel dimension), and in the technical solution of the present application, the channel dimension of the three-dimensional convolution kernel corresponds to the time dimension in which the surface state images of the plurality of predetermined time points are aggregated into the three-dimensional input tensor, so that the dynamic change feature of the surface state distribution feature of the reaction liquid along the time dimension can be extracted when the three-dimensional convolution encoding is performed.
In one embodiment of the application, fusing the temperature time series variation characteristic and the surface state time series variation characteristic in the reactor to obtain the temperature-surface state time series correlation characteristic comprises: and fusing the temperature second-order time sequence characteristic vector and the surface state time sequence characteristic vector in the reactor to obtain a temperature-surface state time sequence correlation characteristic vector as the temperature-surface state time sequence correlation characteristic.
And then fusing the second-order temperature time sequence characteristic vector and the surface state time sequence characteristic vector in the reactor, so as to fuse the temperature time sequence change characteristic information in the reactor and the surface state time sequence change characteristic information of the reaction liquid, thereby obtaining the temperature-surface state time sequence correlation characteristic vector with fusion correlation characteristic distribution information between the temperature time sequence change in the reactor and the surface state time sequence change of the reaction liquid.
Specifically, in the step 123, determining whether the reaction is complete based on the temperature-surface state timing related features includes: and passing the temperature-surface state time sequence correlation characteristic vector through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the reaction is complete or not.
Further, the temperature-surface state time-series correlation feature vector is passed through a classifier to obtain a classification result, which is used for indicating whether the reaction is complete. That is, the detection and judgment of the complete reaction are comprehensively carried out by the fusion correlation characteristic between the temperature time sequence change characteristic in the reactor and the surface state time sequence change characteristic of the reaction liquid, so that the sufficiency of the reaction is improved, and the preparation quality and performance of the emulsifier are ensured.
Further, in the present application, the preparation method of the anti-emulsifying agent for fracturing further comprises a training step: training the timing sequence feature extractor based on the one-dimensional convolution layer, the surface state timing sequence feature extractor based on the three-dimensional convolution neural network model and the classifier; wherein the training step comprises: acquiring training data, wherein the training data comprises temperature values in a training reactor at a plurality of preset time points in a preset time period, and training surface state images of reaction liquid at the preset time points; arranging the temperature values in the training reactor at a plurality of preset time points into a time sequence input vector of the temperature in the training reactor according to a time dimension; calculating the difference value between the temperature values in the training reactor at every two adjacent preset time points in the temperature time sequence input vector in the training reactor to obtain a temperature time sequence change input vector in the training reactor; the temperature time sequence change input vector in the training reactor passes through the time sequence feature extractor based on the one-dimensional convolution layer to obtain a temperature second-order time sequence feature vector in the training reactor; aggregating the training surface state images of the plurality of preset time points into training three-dimensional input tensors along the time dimension, and then passing through the surface state time sequence feature extractor based on the three-dimensional convolutional neural network model to obtain training surface state time sequence feature vectors; fusing the temperature second-order time sequence feature vector in the training reactor and the training surface state time sequence feature vector to obtain a training temperature-surface state time sequence correlation feature vector; passing the training temperature-surface state time sequence associated feature vector through the classifier to obtain a classification loss function value; calculating a common manifold implicit similarity factor of the temperature second-order time sequence feature vector in the training reactor and the training surface state time sequence feature vector to obtain a common manifold implicit similarity loss function value; and training the time sequence feature extractor based on the one-dimensional convolution layer, the surface state time sequence feature extractor based on the three-dimensional convolution neural network model and the classifier by taking the weighted sum of the classification loss function value and the common manifold implicit similarity loss function value as the loss function value and transmitting the time sequence feature extractor based on the one-dimensional convolution layer in the gradient descending direction.
In particular, in the technical scheme of the application, the in-reactor temperature second-order time sequence feature vector expresses one-dimensional time sequence local correlation features of the in-reactor temperature value, and the surface state time sequence feature vector expresses time sequence correlated image semantic local correlation features of the surface state image, so that the in-reactor temperature second-order time sequence feature vector and the surface state time sequence feature vector have large differences under the source data mode and the feature expression dimension, thereby causing significant feature distribution differences between the in-reactor temperature second-order time sequence feature vector and the surface state time sequence feature vector, and in this way, when the in-reactor temperature second-order time sequence feature vector and the surface state time sequence feature vector are fused, the obtained high-dimensional feature manifold geometric monotonicity of the temperature-surface state time sequence correlation feature vector is possibly poor, and the convergence effect of the temperature-surface state time sequence correlation feature vector through the classification regression of the classifier, namely, the accuracy of training speed and training results is influenced.
Based on this, the applicant of the present application addresses the temperature second order time series eigenvector in the reactor, e.g. noted as And said surface state timing feature vector, e.g. denoted +.>The common manifold implicit similarity factor is introduced as a loss function, specifically expressed as: calculating the temperature second order time sequence characteristic vector in the training reactor and the training surface state time sequence characteristic according to the following loss formulaA common manifold implicit similarity factor for a vector to obtain the common manifold implicit similarity loss function value; wherein, the loss formula is: wherein ,/> and />Is the temperature second order time sequence characteristic vector in the training reactor and the training surface state time sequence characteristic vector, respectively, < >>Representing the two norms of the vector, and +.>Representing the square root of the Frobenius norm of the matrix, the training reactor internal temperature second order time sequence feature vector and the training surface state time sequence feature vector are in the form of column vectors, and the training reactor internal temperature second order time sequence feature vector and the training surface state time sequence feature vector are in the form of column vectors>、/>、/> and />For the weight super parameter, ++>Representing vector multiplication, ++>Representing multiplication by location +.>Representing difference by position +.>Representing the common manifold implicit similarity loss function value.
Here, the common manifold implicit similarity factor may be expressed as a second order timing eigenvector of the temperature within the reactorAnd the surface state timing feature vector +. >The structural association between the two characteristic manifolds represents the common manifold of the respective characteristic manifolds in the cross dimension, and the temperature second-order time sequence characteristic vector in the reactor is shared by the same factorization weight>And the surface state timing feature vector +.>And (3) common constraints of manifold structural factors such as variability, correspondence, relevance and the like, so as to measure the distribution similarity of geometric derivative structure representations depending on a common manifold, to realize nonlinear geometric monotonicity of fusion features among feature distributions in different modes of cross-dimension, and to improve the geometric monotonicity of high-dimension feature manifolds of the temperature-surface state time sequence correlation feature vectors, thereby improving the convergence effect of the temperature-surface state time sequence correlation feature vectors through classification regression of a classifier, namely, improving the training speed and the accuracy of training results. Therefore, detection and judgment of complete reaction can be comprehensively carried out based on time sequence change conditions of temperature in the reactor and surface state time sequence change conditions of the reaction liquid, so that the preparation quality and performance of the anti-emulsifying agent are ensured, and meanwhile, the stability and reliability of the anti-emulsifying agent are ensured.
In summary, the preparation method 100 of the anti-emulsifying agent for fracturing according to the embodiment of the invention is illustrated, after the sensor and the camera acquire the temperature value in the reactor and the surface state image of the reaction liquid at a plurality of preset time points respectively, a data processing and analyzing algorithm is introduced at the rear end to analyze the temperature time sequence variation in the reactor and the surface state time sequence variation in the reaction liquid respectively, and further, detection and judgment of complete reaction are comprehensively performed based on the time sequence variation characteristic of the temperature in the reactor and the correlation characteristic information between the surface state time sequence variation characteristic of the reaction liquid, so that the preparation quality and performance of the anti-emulsifying agent are ensured, and meanwhile, the stability and reliability of the anti-emulsifying agent are ensured.
In one embodiment of the present invention, fig. 4 is a block diagram of a preparation system of an anti-emulsifying agent for fracturing provided in the embodiment of the present invention. As shown in fig. 4, a preparation system 200 of an anti-emulsifying agent for fracturing according to an embodiment of the present invention includes: a first mixing module 210 for adding phenol-amine aldehyde resin and potassium persulfate to the first reactor to perform stirring and vacuuming treatment, and heating to a predetermined temperature to obtain a first mixed solution; a first reaction module 220 for introducing ethylene oxide into the first reactor to react with the first mixed solution sufficiently to obtain a first dry agent; a first component generating module 230, configured to cool the first drying agent and add ethylene glycol butyl ether to obtain a component a; a second mixing module 240 for adding dichloropropanol and the potassium persulfate into the second reactor for stirring and vacuumizing treatment, and heating to a predetermined temperature to obtain a second mixed solution; a second reaction module 250 for introducing the ethylene oxide into the second reactor to react with the second mixed solution sufficiently to obtain a second dry agent; a second component generating module 260, configured to cool the second drying agent and add the second drying agent to the butyl cellosolve to obtain a component B; and an anti-emulsifier generation module 270 for uniformly mixing the component a and the component B to obtain an anti-emulsifier for fracturing.
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 of the anti-emulsifying agent for fracturing have been described in detail in the above description of the preparation method of the anti-emulsifying agent for fracturing with reference to fig. 1 to 3, and thus, repetitive descriptions thereof will be omitted.
As described above, the preparation system 200 of the anti-emulsifier for fracturing according to the embodiment of the present invention may be implemented in various terminal devices, such as a server or the like for preparation of the anti-emulsifier for fracturing. In one example, the preparation system 200 of the anti-emulsifying agent for fracturing according to an embodiment of the present invention may be integrated into the terminal device as one software module and/or hardware module. For example, the fracturing demulsifier preparation system 200 may be a software module in the operating system of the terminal equipment or may be an application developed for the terminal equipment; of course, the fracturing demulsifier preparation system 200 can also be one of many hardware modules of the terminal equipment.
Alternatively, in another example, the preparation system 200 for the anti-emulsifying agent for fracturing and the terminal device may be separate devices, and the preparation system 200 for the anti-emulsifying agent for fracturing may be connected to the terminal device through a wired and/or wireless network and transmit interactive information in a agreed data format.
Fig. 5 is an application scenario diagram of a preparation method of an anti-emulsifying agent for fracturing, which is provided in an embodiment of the invention. As shown in fig. 5, in this application scenario, first, in-reactor temperature values at a plurality of predetermined time points within a predetermined period of time (e.g., C1 as illustrated in fig. 5) and surface state images of the reaction liquid at the plurality of predetermined time points acquired by the camera (e.g., C2 as illustrated in fig. 5) are acquired; the obtained in-reactor temperature values and surface state images are then input into a server (e.g., S as illustrated in fig. 5) that is deployed with a preparation algorithm of a fracturing anti-emulsifier, wherein the server is capable of processing the in-reactor temperature values and the surface state images based on the preparation algorithm of the fracturing anti-emulsifier to determine whether the reaction is complete.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.

Claims (9)

1. The preparation method of the anti-emulsifying agent for fracturing is characterized by comprising the following steps of: adding phenol-amine aldehyde resin and potassium persulfate into a first reactor for stirring and vacuumizing treatment, and heating to a preset temperature to obtain a first mixed solution; introducing ethylene oxide into the first reactor to fully react with the first mixed solution to obtain a first drier; cooling the first drying agent, and then adding ethylene glycol butyl ether to obtain a component A; adding dichloropropanol and the potassium persulfate into a second reactor for stirring and vacuumizing treatment, and heating to a preset temperature to obtain a second mixed solution; introducing the ethylene oxide into the second reactor to fully react with the second mixed solution to obtain a second dry agent; cooling the second drying agent, and then adding the ethylene glycol butyl ether to obtain a component B; uniformly mixing the component A and the component B to obtain the anti-emulsifying agent for fracturing; wherein passing ethylene oxide into the first reactor to react substantially with the first mixed solution to obtain a first dry agent comprises: acquiring temperature values in a reactor at a plurality of preset time points in a preset time period, and acquiring surface state images of the reaction liquid at the preset time points by a camera; performing time sequence collaborative correlation analysis on the temperature values in the reactor at a plurality of preset time points and the surface state images at a plurality of preset time points to obtain temperature-surface state time sequence correlation characteristics; and determining whether the reaction is complete based on the temperature-surface state timing correlation characteristic.
2. The method of preparing a fracturing demulsifier as defined in claim 1, wherein performing a time-series collaborative correlation analysis on the in-reactor temperature values at the plurality of predetermined time points and the surface state images at the plurality of predetermined time points to obtain a temperature-surface state time-series correlation feature comprises: extracting in-reactor temperature time-series variation characteristics from the in-reactor temperature values at the plurality of predetermined time points; extracting surface state timing variation features from the surface state images at the plurality of predetermined time points; and fusing the temperature time sequence variation characteristic and the surface state time sequence variation characteristic in the reactor to obtain the temperature-surface state time sequence correlation characteristic.
3. The method for producing a fracturing demulsifier as defined in claim 2, wherein extracting the time-series change characteristics of the in-reactor temperature from the in-reactor temperature values at the plurality of predetermined time points comprises: arranging the temperature values in the reactor at a plurality of preset time points into a time sequence input vector of the temperature in the reactor according to a time dimension; calculating the difference value between the temperature values in the reactor at every two adjacent preset time points in the temperature time sequence input vector in the reactor to obtain a temperature time sequence change input vector in the reactor; and the temperature time sequence change input vector in the reactor passes through a time sequence feature extractor based on a one-dimensional convolution layer to obtain a second-order time sequence feature vector of the temperature in the reactor as the time sequence change feature in the reactor.
4. The method of producing a fracturing demulsifier according to claim 3, wherein extracting the surface state time-series change features from the surface state images at the plurality of predetermined time points comprises: and aggregating the surface state images of the plurality of preset time points into a three-dimensional input tensor along the time dimension, and then obtaining a surface state time sequence feature vector serving as the surface state time sequence change feature through a surface state time sequence feature extractor based on a three-dimensional convolutional neural network model.
5. The method of preparing a fracturing demulsifier according to claim 4, wherein the fusing of the temperature time series variation characteristic and the surface state time series variation characteristic in the reactor to obtain the temperature-surface state time series correlation characteristic comprises: and fusing the temperature second-order time sequence characteristic vector and the surface state time sequence characteristic vector in the reactor to obtain a temperature-surface state time sequence correlation characteristic vector as the temperature-surface state time sequence correlation characteristic.
6. The method of preparing a fracturing demulsifier according to claim 5, wherein determining whether the reaction is complete based on the temperature-surface state time series correlation characteristics comprises: and passing the temperature-surface state time sequence correlation characteristic vector through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the reaction is complete or not.
7. The method of preparing a fracturing demulsifier as defined in claim 6, further comprising the training step of: training the timing sequence feature extractor based on the one-dimensional convolution layer, the surface state timing sequence feature extractor based on the three-dimensional convolution neural network model and the classifier; wherein the training step comprises: acquiring training data, wherein the training data comprises temperature values in a training reactor at a plurality of preset time points in a preset time period, and training surface state images of reaction liquid at the preset time points; arranging the temperature values in the training reactor at a plurality of preset time points into a time sequence input vector of the temperature in the training reactor according to a time dimension; calculating the difference value between the temperature values in the training reactor at every two adjacent preset time points in the temperature time sequence input vector in the training reactor to obtain a temperature time sequence change input vector in the training reactor; the temperature time sequence change input vector in the training reactor passes through the time sequence feature extractor based on the one-dimensional convolution layer to obtain a temperature second-order time sequence feature vector in the training reactor; aggregating the training surface state images of the plurality of preset time points into training three-dimensional input tensors along the time dimension, and then passing through the surface state time sequence feature extractor based on the three-dimensional convolutional neural network model to obtain training surface state time sequence feature vectors; fusing the temperature second-order time sequence feature vector in the training reactor and the training surface state time sequence feature vector to obtain a training temperature-surface state time sequence correlation feature vector; passing the training temperature-surface state time sequence associated feature vector through the classifier to obtain a classification loss function value; calculating a common manifold implicit similarity factor of the temperature second-order time sequence feature vector in the training reactor and the training surface state time sequence feature vector to obtain a common manifold implicit similarity loss function value; and training the time sequence feature extractor based on the one-dimensional convolution layer, the surface state time sequence feature extractor based on the three-dimensional convolution neural network model and the classifier by taking the weighted sum of the classification loss function value and the common manifold implicit similarity loss function value as the loss function value and transmitting the time sequence feature extractor based on the one-dimensional convolution layer in the gradient descending direction.
8. The method of preparing a fracturing demulsifier according to claim 7, wherein calculating a common manifold implicit similarity factor for the training reactor internal temperature second order time series feature vector and the training surface state time series feature vector to obtain a common manifold implicit similarity loss function value comprises: calculating a common manifold implicit similarity factor of the training reactor internal temperature second-order time sequence feature vector and the training surface state time sequence feature vector according to the following loss formula to obtain a common manifold implicit similarity loss function value; wherein, the loss formula is: wherein ,/> and />The temperature second order time sequence characteristic vector in the training reactor and the training surface state time sequence characteristic vector are respectively +.>Is the transpose of the training surface state timing feature vector,/->Representing the two norms of the vector, and +.>Representing the square root of the Frobenius norm of the matrix, the training reactor internal temperature second order time sequence feature vector and the training surface state time sequence feature vector are in the form of column vectors, and the training reactor internal temperature second order time sequence feature vector and the training surface state time sequence feature vector are in the form of column vectors>、/>、/> and />For the weight super parameter, ++>Representing vector multiplication, ++>Representing multiplication by location +.>Representing difference by position +. >Representing the common manifold implicit similarity loss function value.
9. A system for preparing an anti-emulsifying agent for fracturing, comprising: the first mixing module is used for adding phenol-amine aldehyde resin and potassium persulfate into the first reactor for stirring and vacuumizing treatment, and heating to a preset temperature to obtain a first mixed solution; a first reaction module for introducing ethylene oxide into the first reactor to react with the first mixed solution sufficiently to obtain a first dry agent; the first component generating module is used for cooling the first drying agent and then adding ethylene glycol butyl ether to obtain a component A; the second mixing module is used for adding dichloropropanol and the potassium persulfate into a second reactor for stirring and vacuumizing treatment, and heating to a preset temperature to obtain a second mixed solution; a second reaction module for introducing the ethylene oxide into the second reactor to fully react with the second mixed solution to obtain a second dry agent; the second component generating module is used for cooling the second drying agent and then adding the second drying agent into the ethylene glycol butyl ether to obtain a component B; and an anti-emulsifying agent generation module for uniformly mixing the component A and the component B to obtain an anti-emulsifying agent for fracturing; wherein the first reaction module comprises: the image acquisition unit is used for acquiring temperature values in the reactor at a plurality of preset time points in a preset time period and surface state images of the reaction liquid acquired by the camera at the preset time points; the correlation analysis unit is used for carrying out time sequence collaborative correlation analysis on the temperature values in the reactor at a plurality of preset time points and the surface state images at a plurality of preset time points so as to obtain temperature-surface state time sequence correlation characteristics; and a reaction completion determination unit configured to determine whether the reaction is complete based on the temperature-surface state timing correlation characteristic.
CN202310941663.2A 2023-07-28 2023-07-28 Preparation method and system of anti-emulsifying agent for fracturing Active CN116680620B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310941663.2A CN116680620B (en) 2023-07-28 2023-07-28 Preparation method and system of anti-emulsifying agent for fracturing

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310941663.2A CN116680620B (en) 2023-07-28 2023-07-28 Preparation method and system of anti-emulsifying agent for fracturing

Publications (2)

Publication Number Publication Date
CN116680620A true CN116680620A (en) 2023-09-01
CN116680620B CN116680620B (en) 2023-10-27

Family

ID=87779499

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310941663.2A Active CN116680620B (en) 2023-07-28 2023-07-28 Preparation method and system of anti-emulsifying agent for fracturing

Country Status (1)

Country Link
CN (1) CN116680620B (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080101705A1 (en) * 2006-10-31 2008-05-01 Motorola, Inc. System for pattern recognition with q-metrics
CN110437820A (en) * 2019-08-15 2019-11-12 山东滨州昱诚化工科技有限公司 A kind of oil field fracturing acidification preparation method and applications of non-emulsifier
WO2021189848A1 (en) * 2020-09-22 2021-09-30 平安科技（深圳）有限公司 Model training method and apparatus, cup-to-disc ratio determination method and apparatus, and device and storage medium
CN115456012A (en) * 2022-08-24 2022-12-09 华能新能源股份有限公司 Wind power plant fan major component state monitoring system and method
CN115859437A (en) * 2022-12-13 2023-03-28 深圳量云能源网络科技有限公司 Jacket underwater stress detection system based on distributed optical fiber sensing system
CN116052050A (en) * 2023-02-03 2023-05-02 深圳市橙洁士日用化工科技有限公司 Intelligent production system and method for detergent
CN116068891A (en) * 2022-12-30 2023-05-05 杭州灼粤数码科技有限公司 Intelligent equipment working parameter regulation and control system and method based on Internet of things
CN116434117A (en) * 2023-04-14 2023-07-14 河南正佳能源环保股份有限公司 Preparation method of composite polyacrylamide oil displacement agent

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080101705A1 (en) * 2006-10-31 2008-05-01 Motorola, Inc. System for pattern recognition with q-metrics
CN110437820A (en) * 2019-08-15 2019-11-12 山东滨州昱诚化工科技有限公司 A kind of oil field fracturing acidification preparation method and applications of non-emulsifier
WO2021189848A1 (en) * 2020-09-22 2021-09-30 平安科技（深圳）有限公司 Model training method and apparatus, cup-to-disc ratio determination method and apparatus, and device and storage medium
CN115456012A (en) * 2022-08-24 2022-12-09 华能新能源股份有限公司 Wind power plant fan major component state monitoring system and method
CN115859437A (en) * 2022-12-13 2023-03-28 深圳量云能源网络科技有限公司 Jacket underwater stress detection system based on distributed optical fiber sensing system
CN116068891A (en) * 2022-12-30 2023-05-05 杭州灼粤数码科技有限公司 Intelligent equipment working parameter regulation and control system and method based on Internet of things
CN116052050A (en) * 2023-02-03 2023-05-02 深圳市橙洁士日用化工科技有限公司 Intelligent production system and method for detergent
CN116434117A (en) * 2023-04-14 2023-07-14 河南正佳能源环保股份有限公司 Preparation method of composite polyacrylamide oil displacement agent

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
祁超;: "一种基于子空间学习的图像标签推荐方法", 计算机与现代化, no. 03 *

Also Published As

Publication number Publication date
CN116680620B (en) 2023-10-27

Similar Documents

Publication Publication Date Title
Schlegel et al. Towards a rigorous evaluation of XAI methods on time series
CN116189179B (en) Circulating tumor cell scanning analysis equipment
US7162076B2 (en) Face detection method and apparatus
CN116820052B (en) PBT material production equipment and control method thereof
Lu et al. Robust alternative minimization for matrix completion
CN109284668B (en) Pedestrian re-identification method based on distance regularization projection and dictionary learning
CN114912533B (en) State monitoring system and monitoring method applied to transformer
CN116434117A (en) Preparation method of composite polyacrylamide oil displacement agent
CN111949012A (en) Intermittent process fault detection method based on double-weight multi-neighborhood preserving embedding algorithm
Wu et al. VP-NIQE: An opinion-unaware visual perception natural image quality evaluator
CN116680620B (en) Preparation method and system of anti-emulsifying agent for fracturing
Zhang et al. Patch diffusion: a general module for face manipulation detection
He et al. The detonation heat prediction of nitrogen-containing compounds based on quantitative structure-activity relationship (QSAR) combined with random forest (RF)
CN116051853A (en) Automatic water adding dough kneading tank and application method thereof
Hassani et al. A glance at the applications of singular spectrum analysis in gene expression data
Zhang et al. Energy-based generative cooperative saliency prediction
Shi et al. PRIOR: Personalized Prior for Reactivating the Information Overlooked in Federated Learning.
Liu et al. A verified open-access AI-based chemical microparticle image database for in-situ particle visualization and quantification in multi-phase flow
JP2021190110A (en) ANALYTICAL METHOD OF DRUG MOLECULE KINETIC RESULT BASED ON rmsd MULTIPLE CHARACTERISTIC
Ali et al. Self-supervised learning for 3d medical image analysis using 3d simclr and monte carlo dropout
CN115527097A (en) CNN interpretation graph object correlation analysis method based on ablation analysis
Wang et al. Raman spectrum model transfer method based on Cycle-GAN
CN110210522A (en) The training method and device of picture quality Fraction Model
CN113420718B (en) Hyperspectral anomaly detection method and device based on component analysis and sparse constraint
CN115723280A (en) Production equipment of polyimide film with adjustable thickness

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant