Horizontal well coiled tubing high-pressure jet flow dredging process parameter analysis method and electronic equipment

Through data acquisition and genetic algorithm optimization, the high-pressure jet dredging process parameters of horizontal wells are analyzed, which solves the problem of insufficient parameter selection in the existing technology, and achieves efficient blockage removal and production recovery, improving dredging efficiency and cost-effectiveness.

CN119089808AInactive Publication Date: 2024-12-06XINJIANG PETROLEUM ADMINISTRATION BUREAU +1
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202411598264.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-11
Publication Date
2024-12-06
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing horizontal well dredging technology cannot find the best operating parameters under different well conditions, resulting in difficulty in maximizing dredging effect and efficiency, and lack of systematic analysis.

Method used

Using methods of data acquisition, preprocessing, parameter optimization model establishment and genetic algorithm design, we will find the best parameter combination to improve dredging effect and efficiency by scientifically analyzing the key parameters in the high-pressure jet dredging process.

Benefits of technology

The optimal jet parameter combination determination in different well conditions is achieved to ensure effective removal of blockages, restore well production capacity, improve dredging efficiency and reduce costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119089808A_ABST
    Figure CN119089808A_ABST
Patent Text Reader

Abstract

The invention provides a horizontal well coiled tubing high-pressure jet flow dredging process parameter analysis method, relates to the technical field of oil exploitation, and aims to improve the efficiency, safety and economical efficiency of horizontal well dredging operation. According to the method, data such as jet flow pressure, jet flow speed, jet flow angle and the like in the horizontal well coiled tubing dredging operation process are collected and preprocessed to ensure the data quality. And then, a parameter optimization model is established, correlation among parameters is found by adopting a regression analysis method in machine learning, and the dredging effect is predicted. Besides, an innovative parameter optimization algorithm, such as a genetic algorithm, is designed, so that multi-objective optimization is realized, and the dredging effect, the operation cost and the time are considered. The effectiveness of the algorithm is verified through a laboratory or a field experiment, and adjustment is performed according to a result to obtain a better optimization effect. The dredging efficiency can be effectively improved, the dredging effect is enhanced, and the operation cost is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of oil production, and in particular to a method for analyzing process parameters of high-pressure jet dredging of a horizontal well coiled tubing and electronic equipment. Background Art

[0002] With the continuous advancement of oil extraction technology, horizontal wells have been widely used in the oil industry as an effective way to improve crude oil recovery. However, horizontal wells encounter many challenges during production, especially under conditions such as wellbore bending, formation pressure changes, and changes in fluid properties, which often lead to blockages. These blockages seriously hinder the normal production and efficiency of oil wells and increase extraction costs.

[0003] In order to overcome these problems, the industry has developed a variety of unblocking technologies. For example, the "rotating jet descaling and unblocking combined device for oil and water wells" disclosed in announcement number CN203948056U uses a nozzle to spray at a constant speed to impact the pipe wall, but the jet efficiency is limited. Another example is the "oil pipe unblocking tool" mentioned in announcement number CN114427383A, which uses drilling and grinding operations to unblock and descale the inner wall of the pipe column. Although the operation efficiency is high, due to the gap between the tool and the pipe wall, it is impossible to achieve full coverage of the pipe wall unblocking.

[0004] Existing unclogging technologies usually focus on improving the internal structure of the tool to improve unclogging efficiency, but this approach often fails to fully consider the optimal operating parameters under all well conditions. In addition, due to the lack of systematic analysis of various parameters during the operation, it is difficult to maximize the unclogging effect and efficiency. Summary of the invention

[0005] The purpose of the present invention is to provide a method and electronic equipment for analyzing process parameters of high-pressure jet dredging in horizontal well coiled tubing, and to find the best parameter combination by scientifically analyzing key parameters in the high-pressure jet dredging process to improve the dredging effect and operating efficiency.

[0006] To achieve the above object, the present invention is implemented through the following technical solutions: A method for analyzing process parameters of high-pressure jet dredging of coiled tubing in a horizontal well, comprising the following steps: S1: Data collection: Collecting jet data during the operation, wherein the jet data is the actual measured value of the jet parameters, and the jet parameters include at least one of jet pressure, jet velocity, nozzle area, oil pipe diameter, oil pipe length, jet medium viscosity and jet medium density; S2: Data preprocessing: preprocessing the jet data; S3: Establishment of parameter optimization model: A parameter optimization model is established by using statistical methods. The parameter optimization model is used to determine the prediction result according to the jet data preprocessed in S2. The prediction result is the operation time and dredging effect. S4: parameter optimization algorithm design: based on the parameter optimization model established in S3, a parameter optimization algorithm is designed, wherein the parameter optimization algorithm is used to obtain an optimized jet parameter combination according to the prediction result; S5: Parameter optimization experimental verification: Based on the optimized jet parameter combination described in S4, the effectiveness and feasibility of the parameter optimization algorithm are verified through experiments to obtain experimental results, and the parameter optimization algorithm is adjusted according to the experimental results. The best jet parameter combination is calculated through the adjusted parameter optimization algorithm.

[0007] Furthermore: the data preprocessing method in S2 includes at least one of denoising, filtering, and correction.

[0008] Further: The specific steps of establishing the model in step S3 are: S301: Establish model expression:

[0009]

[0010] Where, C: operation time, unit: hour; T : Dredging effect, unit: flow increase rate; P : Jet pressure, unit: MPa; V : jet velocity, unit: meters per second; A : Nozzle area, unit: square millimeter; D : Oil pipe diameter, unit: mm; L : Oil pipe length, unit: meter; : Jet medium viscosity, unit: centipoise; : Density of jet medium, unit: kilograms per cubic meter; ( , ; , ; , ;...; , ): regression coefficient.

[0011] S302: Based on the preprocessed jet data obtained in S2 and the parameter optimization model expression established in S301, a regression analysis method is used to obtain coefficient estimates of the parameter optimization model expression, and a parameter optimization model is established based on the coefficient estimates.

[0012] Furthermore: the parameter optimization algorithm in step S4 is a genetic algorithm.

[0013] Further: The specific steps of using the genetic algorithm to optimize parameters are: S401: Initialize the population: randomly generate a set of initial parameter combinations as individuals of the population; S402: Evaluate fitness: Use parameter optimization model to evaluate individual dredging effects; S403: Selection operation: According to the fitness value of the individual, a selection algorithm is used to select a part of the individuals as the parent generation; S404: Crossover operation: perform a crossover operation on the parent individuals to generate new individuals; S405: mutation operation: introducing a random factor, and performing a mutation operation on the individuals in the population after the crossover operation based on the random factor; S406: Evaluate fitness: for the individuals in the population after the mutation operation, use the parameter optimization model again to evaluate the dredging effect of the individuals; S407: updating the population: according to the fitness value, selecting individuals that meet the preset conditions and retaining them for the generation of the next generation population; the individuals that meet the preset conditions are individuals whose fitness values ​​are greater than a preset threshold; S408: Termination condition: judging whether to terminate the genetic algorithm according to the set termination condition, wherein the termination condition is reaching the maximum number of iterations or finding a set solution.

[0014] Further: the crossover operation in S404 adopts a crossover rate adaptive adjustment strategy, and the crossover rate adaptive adjustment strategy is to set a crossover rate greater than a preset crossover rate in the initial stage of the genetic algorithm; as the algorithm iterates, the crossover rate is gradually reduced according to a first preset step size; wherein the initial stage of the algorithm is an iterative process corresponding to an iteration number less than a preset number threshold; the first preset step size is the difference in crossover rate between two adjacent iteration numbers.

[0015] Further: the mutation operation in S405 adopts a mutation rate adaptive adjustment strategy, and the mutation rate adaptive adjustment strategy is to set a mutation rate less than a preset mutation rate at the initial stage of the genetic algorithm; as the algorithm iterates, the mutation rate is gradually increased according to a second preset step size; wherein the initial stage of the algorithm is an iterative process corresponding to an iteration number less than a preset number threshold; the second preset step size is the difference in mutation rate between two adjacent iteration numbers.

[0016] The present invention also provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor implements any of the above-mentioned methods.

[0017] Compared with the prior art, the present invention has the following beneficial effects: 1. The method of the present invention can find the best combination of jet pressure, flow rate, injection angle and injection time by scientifically analyzing the process parameters of high-pressure jet dredging to ensure that the jet can effectively clear the blockage in the well and restore the normal production capacity of the well.

[0018] 2. The present invention can accurately analyze the influence of jet pressure, jet velocity and jet angle on dredging time and cleaning degree by establishing a multivariate parameter optimization model, so as to select the best parameter combination to improve the dredging effect and efficiency.

[0019] 3. The present invention can predict and control the progress of the dredging operation through accurate analysis of the process parameters of high-pressure jet dredging, avoid ineffective or repeated work, thereby improving operation efficiency and reducing operation costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 The present invention is a flowchart of a method for analyzing process parameters of a horizontal well coiled tubing high-pressure jet dredging method in one of the embodiments of the present invention. DETAILED DESCRIPTION

[0021] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0023] A method for analyzing process parameters of high-pressure jet dredging of coiled tubing in a horizontal well, comprising the following steps: S1: Data collection: Collecting jet data during the operation, wherein the jet data is the actual measured value of the jet parameters, and the jet parameters include at least one of jet pressure, jet velocity, nozzle area, oil pipe diameter, oil pipe length, jet medium viscosity and jet medium density; S2: Data preprocessing: preprocessing the jet data; S3: Establishment of parameter optimization model: A parameter optimization model is established by using statistical methods. The parameter optimization model is used to determine the prediction result according to the jet data preprocessed in S2. The prediction result is the operation time and dredging effect. S4: parameter optimization algorithm design: based on the parameter optimization model established in S3, a parameter optimization algorithm is designed, wherein the parameter optimization algorithm is used to obtain an optimized jet parameter combination according to the prediction result; S5: Parameter optimization experimental verification: Based on the optimized jet parameter combination described in S4, the effectiveness and feasibility of the parameter optimization algorithm are verified through experiments to obtain experimental results, and the parameter optimization algorithm is adjusted according to the experimental results. The best jet parameter combination is calculated through the adjusted parameter optimization algorithm.

[0024] In some embodiments: the data preprocessing method in S2 includes at least one of denoising, filtering, and correction.

[0025] In some embodiments: the specific steps of establishing the model in step S3 are: S301: Establish model expression:

[0026]

[0027] Where, C: operation time, unit: hour; T : Dredging effect, unit: flow increase rate; P : Jet pressure, unit: MPa; V : jet velocity, unit: meters per second; A : Nozzle area, unit: square millimeter; D : Oil pipe diameter, unit: mm; L : Oil pipe length, unit: meter; : Jet medium viscosity, unit: centipoise; : Density of jet medium, unit: kilograms per cubic meter; ( , ; , ; , ;...; , ): regression coefficient.

[0028] Tubing diameter and length: The diameter and length of the tubing have an important influence on the transmission and dredging effect of the jet. Smaller diameter and longer length may lead to jet energy loss and increased flow resistance, affecting the dredging effect. Therefore, the tubing diameter and length can be added to the model as additional factors.

[0029] Jet medium: The properties and flow pattern of the jet medium also affect the dredging effect. For example, a medium with a viscosity greater than the preset crossover rate may result in jet energy loss and reduced dredging effect. The viscosity and density of the jet medium can be considered as factors.

[0030] Jet nozzle shape and size: The shape and size of the jet nozzle have an impact on the velocity and angle of the jet. A smaller nozzle aperture may result in an increase in jet velocity and enhance the dredging effect. Therefore, the nozzle shape and size can be added to the model as an additional factor.

[0031] Jetting operation time and frequency: The time and frequency of jetting operation will also affect the dredging effect. Longer operation time and operation frequency greater than the preset cross-rate may lead to better dredging effect. Therefore, the operation time and frequency can be added as factors to the model.

[0032] When more factors are considered, the optimization model will more comprehensively analyze the parameter effects of high-pressure jet dredging in horizontal well coiled tubing. The consideration of these factors will make the model more accurate and reliable, and can better guide the parameter selection and optimization of actual dredging operations, thereby improving the dredging effect and efficiency.

[0033] By introducing factors such as tubing diameter, tubing length, jet medium viscosity and density, we can more comprehensively analyze the parameter optimization effect of horizontal well coiled tubing high-pressure jet dredging. The importance and influence of these factors can be determined through regression analysis and coefficient estimation of the model. Based on the results of the model, the best parameter combination can be selected to improve the dredging effect and efficiency.

[0034] The flow increase rate indicates the change ratio of fluid flow or flow velocity before and after the dredging work.

[0035] S302: Based on the preprocessed jet data obtained in S2 and the parameter optimization model expression established in S301, a regression analysis method is used to obtain coefficient estimates of the parameter optimization model expression, and a parameter optimization model is established based on the coefficient estimates. The model can be optimized by using optimization algorithms such as the least squares method and the gradient descent method to obtain the best parameter combination.

[0036] In some embodiments: the parameter optimization algorithm in step S4 is a genetic algorithm.

[0037] In some embodiments: the specific steps of using the genetic algorithm to perform parameter optimization are: S401: Initialize the population: randomly generate a set of initial parameter combinations as individuals of the population; S402: Evaluate fitness: Use parameter optimization model to evaluate individual dredging effects; S403: Selection operation: According to the fitness value of the individual, a selection algorithm is used to select a part of the individuals as the parent generation; S404: Crossover operation: perform a crossover operation on the parent individuals to generate new individuals; S405: mutation operation: introducing a random factor, and performing a mutation operation on the individuals in the population after the crossover operation based on the random factor; S406: Evaluate fitness: for the individuals in the population after the mutation operation, use the parameter optimization model again to evaluate the dredging effect of the individuals; S407: updating the population: according to the fitness value, selecting individuals that meet the preset conditions and retaining them for the generation of the next generation population; the individuals that meet the preset conditions are individuals whose fitness values ​​are greater than a preset threshold; S408: Termination condition: judging whether to terminate the genetic algorithm according to the set termination condition, wherein the termination condition is reaching the maximum number of iterations or finding a set solution.

[0038] In some embodiments: the crossover operation in S404 adopts a crossover rate adaptive adjustment strategy, and the crossover rate adaptive adjustment strategy is to set a crossover rate greater than a preset crossover rate in the initial stage of the genetic algorithm; as the algorithm iterates, the crossover rate is gradually reduced according to a first preset step size; wherein the initial stage of the algorithm is an iterative process corresponding to an iteration number less than a preset number threshold; the first preset step size is the difference in the crossover rate between two adjacent iteration numbers. The crossover rate controls the probability of the crossover operation and is used to generate the next generation of individuals. In the initial stage of the algorithm, a crossover rate greater than a preset crossover rate can be set to promote the diversity of the population. As the algorithm iterates, if the diversity of the population is low, that is, the similarity of the fitness values ​​of the individuals is high, the crossover rate can be gradually reduced to reduce the crossover operations between individuals and improve the convergence speed of the algorithm.

[0039] The mutation operation in S405 adopts a mutation rate adaptive adjustment strategy, which is to set a mutation rate less than the preset mutation rate in the early stage of the genetic algorithm; as the algorithm iterates, the mutation rate is gradually increased according to the second preset step size; wherein the initial stage of the algorithm is an iterative process corresponding to the number of iterations less than the preset number threshold; the second preset step size is the difference in mutation rate between two adjacent iterations. The mutation rate controls the probability of the mutation operation and is used to introduce new individuals into the population. In the early stage of the algorithm, a mutation rate less than the preset mutation rate can be set to retain the better individuals in the population. As the algorithm iterates, if the diversity of the population is low, that is, the similarity of the fitness values ​​of the individuals is high, the mutation rate can be gradually increased to introduce more random factors, which helps to jump out of the local optimal solution.

[0040] The crossover rate and mutation rate can be adjusted according to the trend of the fitness value of the population. Set a threshold for the change of the fitness value. If the fitness value of the population changes little, that is, the convergence speed is slow, the mutation rate can be increased to increase the diversity of the population. On the contrary, if the fitness value of the population changes greatly, that is, the convergence speed is fast, the crossover rate can be reduced to reduce the crossover operation between individuals.

[0041] This genetic algorithm optimization method has the following beneficial effects: Comprehensive consideration of multiple factors: Genetic algorithms can optimize multiple parameters at the same time, thereby comprehensively considering the impact of multiple factors on the dredging effect and finding the best parameter combination.

[0042] Adaptive search capability: Genetic algorithms have adaptive search capabilities. Through continuous iteration and evolution, they can gradually approach the optimal solution and find a better solution even when the search space is large or complex.

[0043] Parallelizable: The computational process of genetic algorithms can be well parallelized. Using multi-core processors or distributed computing resources can accelerate the optimization process and improve efficiency.

[0044] Scalability and adaptability: Genetic algorithms can be flexibly applied to different problems and models, and can be adjusted and expanded according to specific circumstances to meet different optimization needs.

[0045] In summary, the use of innovative genetic algorithms to optimize the effect of high-pressure jet dredging in horizontal well coiled tubing can comprehensively consider multiple factors and find the best combination of parameters, thereby improving the optimization effect of dredging effect.

[0046] In another embodiment, the present invention further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor implements any of the above-described methods.

[0047] The above embodiments are only for illustrating the technical concept and features of the present invention, and their purpose is to enable people familiar with the technology to understand the content of the present invention and implement it accordingly, and they cannot be used to limit the protection scope of the present invention. Any equivalent transformation or modification made according to the spirit of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for analyzing process parameters of high-pressure jet dredging of coiled tubing in horizontal wells. Features: The following steps are involved: S1: Data collection: Collecting jet data during the operation, wherein the jet data is the actual measured value of the jet parameters, and the jet parameters include at least one of jet pressure, jet velocity, nozzle area, oil pipe diameter, oil pipe length, jet medium viscosity and jet medium density; S2: Data preprocessing: preprocessing the jet data; S3: Establishment of parameter optimization model: A parameter optimization model is established by using statistical methods. The parameter optimization model is used to determine the prediction result according to the jet data preprocessed in S2. The prediction result is the operation time and dredging effect. The specific steps are: S301: Establish parameter optimization model expression: Where, C: operation time, unit: hour; T: dredging effect, unit: flow increase rate; P: jet pressure, unit: MPa; V: jet velocity, unit: meters per second; A: nozzle area, unit: square millimeter; D: oil pipe diameter, unit: mm; L: oil pipe length, unit: meter; : Jet medium viscosity, unit: centipoise; : Density of jet medium, unit: kilograms per cubic meter; , ; , ; , ;...; , : regression coefficient; S302: according to the preprocessed jet data obtained in S2 and the parameter optimization model expression established in S301, using a regression analysis method, obtain coefficient estimation values ​​of the parameter optimization model expression, and establish a parameter optimization model according to the coefficient estimation values; S4: parameter optimization algorithm design: based on the parameter optimization model established in S3, a parameter optimization algorithm is designed, wherein the parameter optimization algorithm is used to obtain an optimized jet parameter combination according to the prediction result, and the parameter optimization algorithm is a genetic algorithm; S5: Parameter optimization experimental verification: Based on the optimized jet parameter combination described in S4, the effectiveness and feasibility of the parameter optimization algorithm are verified through experiments to obtain experimental results, and the parameter optimization algorithm is adjusted according to the experimental results. The best jet parameter combination is calculated through the adjusted parameter optimization algorithm.

2. According to claim 1, a method for analyzing process parameters of high-pressure jet dredging of horizontal well coiled tubing, Features: In S1, the jet data is collected through sensors and monitoring equipment.

3. According to the method for analyzing process parameters of horizontal well coiled tubing high pressure jet dredging according to claim 1, Features: The preprocessing in S2 includes at least one of denoising, filtering, and correction.

4. According to claim 1, a method for analyzing process parameters of high-pressure jet dredging of horizontal well coiled tubing, Features: The specific steps of designing parameter optimization algorithm are: S401: Initialize the population: randomly generate a set of initial parameter combinations as individuals of the population; S402: Evaluate fitness: Use parameter optimization model to evaluate individual dredging effects; S403: Selection operation: According to the fitness value of the individual, a selection algorithm is used to select a part of the individuals as the parent generation; S404: Crossover operation: perform a crossover operation on the parent individuals to generate new individuals; S405: mutation operation: introducing a random factor, and performing a mutation operation on the individuals in the population after the crossover operation based on the random factor; S406: Evaluate fitness: for the individuals in the population after the mutation operation, use the parameter optimization model again to evaluate the dredging effect of the individuals; S407: updating the population: according to the fitness value, selecting individuals that meet the preset conditions and retaining them for the generation of the next generation population; the individuals that meet the preset conditions are individuals whose fitness values ​​are greater than a preset threshold; S408: Termination condition: judging whether to terminate the genetic algorithm according to the set termination condition, wherein the termination condition is finding a set solution.

5. According to claim 4, a method for analyzing process parameters of horizontal well coiled tubing high-pressure jet dredging, Features: In S404, the crossover operation adopts a crossover rate adaptive adjustment strategy, wherein the crossover rate adaptive adjustment strategy is to set a crossover rate greater than a preset crossover rate at the initial stage of the genetic algorithm; and gradually reduce the crossover rate according to a first preset step size as the algorithm iterates; The initial stage of the algorithm is an iterative process corresponding to the number of iterations being less than a preset number threshold; the first preset step size is the difference in the crossover rate between two adjacent iteration numbers.

6. A method for analyzing process parameters of horizontal well coiled tubing high pressure jet dredging according to claim 4, Features: The mutation operation in S405 adopts a mutation rate adaptive adjustment strategy, wherein the mutation rate adaptive adjustment strategy is to set a mutation rate that is less than a preset mutation rate at the initial stage of the genetic algorithm; As the algorithm iterates, the mutation rate is gradually increased according to the second preset step size; The initial stage of the algorithm is an iterative process corresponding to the number of iterations being less than the preset number threshold; The second preset step size is the difference in mutation rate between two adjacent iteration times.

7. An electronic device, It is characterized in that The method comprises a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor implements the method according to any one of claims 1 to 6.

Citation Information

Patent Citations

  • Time sequence database multi-objective optimization method based on genetic algorithm parameter adjustment

    CN117743294A