A safety evaluation method for the whole life cycle of a gas well borehole
The gas wellbore life-cycle safety evaluation method constructed by machine learning algorithms solves the problem of insufficient comprehensive analysis of the wellbore life-cycle in existing technologies, and realizes accurate assessment of well barrier service capability and optimized management of production conditions.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- PETROCHINA CO LTD
- Filing Date
- 2022-04-29
- Publication Date
- 2026-07-31
AI Technical Summary
Existing technologies cannot comprehensively analyze the entire life cycle of high-yield sulfur-containing gas wells, resulting in inaccurate assessments of well barrier service capabilities and a lack of comprehensive evaluation methods in well life cycle management.
Using machine learning algorithms and based on a large amount of field detection data, a safety evaluation method for the entire life cycle of gas well shafts is constructed. Real-time dynamic evaluation is carried out through neural network models, and gas well production condition parameters are optimized by combining learning models of multiple monitoring objects.
It enables intelligent management and control of the entire life cycle of gas wellbore, improves the reliability and scientific nature of evaluation, prevents well barrier failure, and guides the optimization of production conditions and management measures.
Smart Images
Figure CN117010261B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of oil and gas extraction technology, and more specifically to the field of safety assessment methods for the entire life cycle of gas well shafts. Background Technology
[0002] For high-yield sulfur-containing gas wells, current technologies only simulate single parameters of the wellbore to assess corrosion / erosion of critical well barriers such as the wellhead and downhole tubing. However, well barrier failure is the result of multiple interacting factors. Therefore, wellbore lifecycle management cannot rely on a single or isolated analysis, which would be overly simplistic.
[0003] In addition, existing technologies mainly rely on indoor experiments conducted during the early design phase to obtain relevant data on well barriers by simulating gas well operating conditions. This data is then input into theoretical models for prediction, but the reliability is poor and the analytical factors are limited.
[0004] There is currently no method in the technology to comprehensively analyze all the influencing factors of the entire life cycle of a gas wellbore, so as to achieve an effective evaluation of the entire life cycle.
[0005] The corrosion / erosion of critical well barriers, such as the wellhead and downhole tubing, in high-yield sulfur gas wells directly affects their serviceability. A well barrier is a structural unit that directly prevents uncontrolled flow of formation fluids into outer space. Typical well barrier components include downhole safety valves, packers, tubing strings, tubing heads, casing strings, casing heads, Christmas trees, cement sheaths, gas lift valves, and other downhole tools.
[0006] Existing technologies offer analysis and monitoring of individual indicators, but can only analyze single parameters. For example, the study "Safety Evaluation of Wellbore Integrity in High-Sulfur Gas Wells" analyzes single parameters such as annular pressure well management and safety evaluation, methods for predicting the life of oil casing in high-sulfur gas wells, corrosion experiments in hydrogen sulfide-containing environments, and sulfide stress corrosion cracking. Another example is the study "Research and Application of Wellbore Integrity Evaluation Technology for High-Temperature, High-Pressure, and High-Sulfur Gas Wells," which analyzes special working conditions of gas well completion tubing, annular pressure diagnostic testing, sealing integrity analysis of completion tubing in high-temperature, high-pressure, and high-sulfur gas wells, and the sealing integrity of cement sheaths in high-sulfur gas wells.
[0007] The reliability of a gas wellbore throughout its lifecycle relies on a combination of multiple parameters and various objects. Judging the reliability of a gas wellbore based on a single parameter is too simplistic. Furthermore, current technologies only monitor and manage parameters during the process, failing to incorporate the initial state parameters of the gas wellbore at the time of completion. Summary of the Invention
[0008] The purpose of this invention is to address the aforementioned technical problems by providing a method and system for safety evaluation of the entire lifecycle of a gas wellbore. Specifically targeting corrosion / erosion of critical well barriers such as the wellhead and downhole tubing in high-yield sulfur-containing gas wells, this invention, based on extensive field testing data and employing machine learning algorithms, develops a comprehensive wellbore safety evaluation method. This method provides real-time dynamic evaluation of the long-term service capability of well barriers, guiding the optimization of gas well production parameters and the formulation of control measures.
[0009] To achieve the above objectives, the present invention specifically adopts the following technical solution:
[0010] A method for safety assessment of the entire life cycle of a gas well shaft includes the following steps:
[0011] Step 1: Establish an initial parameter database for the life cycle of the gas wellbore. The data in the initial parameter database are obtained during well completion.
[0012] Step 2: Based on the known experimental evaluation, on-site detection, and monitoring data, construct learning models for multiple monitoring objects;
[0013] Step 3: Substitute the data from the initial parameter database into the learning models of the multiple monitoring objects above to obtain the original theoretical monitoring data of the gas wellbore.
[0014] Step 4: Randomly collect sample data from several gas well shafts, and substitute the sample data into the learning model of multiple monitoring objects above to obtain the actual monitoring data of the current gas well shaft.
[0015] Step 5: Establish a gas wellbore lifecycle management model. This model is a machine learning model based on neural networks. The original theoretical monitoring data obtained in Step 3 and the actual monitoring data obtained in Step 4 are substituted into the gas wellbore lifecycle management model and trained according to the machine learning algorithm to obtain an optimized gas wellbore lifecycle management model.
[0016] Step 6: Based on the actual life cycle data from the gas wellbore test, the optimized gas wellbore life cycle management model is revised to obtain the revised gas wellbore life cycle management model.
[0017] Step 7: Using the modified gas wellbore lifecycle management model, manage the lifecycle of each gas wellbore, achieve a full-process safety assessment of the wellbore, and classify the safety risks of the gas wellbore according to the various indicators obtained from the modified gas wellbore lifecycle management model, dividing them into multiple risk levels according to the risk hazard procedure.
[0018] Furthermore, in step one, the initial parameter model includes: physical parameter data of the tubing, parameter data of the production casing, parameter data of the technical casing, parameter data of the surface casing, pressure data of each annulus zone, gas composition data of each annulus zone, parameter data of the wellbore itself, and geological data of the location of the wellbore.
[0019] Furthermore, in step two, based on the known experimental evaluation, field detection and monitoring data in the existing technology, four monitoring object learning models are constructed, including a gas wellbore pressure model, a well barrier corrosion model for well barrier corrosion / erosion, an annular pressure model for annular pressure, and an environmental analysis model for each area of the gas wellbore.
[0020] Furthermore, a wellbore pressure model is constructed for gas wellbore pressure calculation, used to calculate and simulate pressure changes in the gas wellbore. This can be simulated using the following formula:
[0021] P h = f(x+y+z+x(t),+P k +ρ)
[0022] Where x represents the gas well depth, y represents the wellbore trajectory, z represents the tubing structure and dimensions, x(t) represents the gas production / liquid production of the gas well, and P k ρ represents the wellhead oil pressure, and ρ represents the gas density. The gas production / liquid production and oil pressure can be obtained through existing monitoring systems, while the well depth, wellbore trajectory, tubing structure and dimensions are obtained from the well completion data.
[0023] Furthermore, a well barrier corrosion model is constructed to calculate and simulate changes in well barrier corrosion / erosion.
[0024] For wellheads: The main parameters for corrosion assessment include the overall neck thickness, the remaining valve thickness, and the remaining Nyquist alloy layer thickness. These can be measured using electromagnetic ultrasound, ultrasonic phased array, and other methods. The thickness change can be obtained by subtracting the initial thickness from the thickness at the time of measurement, and then by comparing and analyzing the measurement cycle (years) to obtain the thickness change rate.
[0025] For downhole tubing: The main parameter for corrosion assessment is the remaining wall thickness of the tubing. This can be obtained using techniques such as multi-arm caliper, magnetic thickness gauge, and electromagnetic flaw detection for multi-layer tubing corrosion testing. The thickness change is obtained by subtracting the initial thickness of the tubing from the thickness at the time of measurement. This is then compared and analyzed with the measurement cycle (years) to obtain the tubing corrosion rate (usually mm / year). Finally, the remaining strength of the tubing is calculated using strength theory to evaluate the strength and safety of the tubing.
[0026] In practical applications, to design anti-corrosion measures for a specific area, a special study on the corrosion situation in that area should be conducted first. This involves experimental analysis of the corrosion products on-site using methods such as SEM (scanning electron microscopy). Then, combined with the results of on-site well fluid analysis, indoor corrosion plate tests should be carried out, and the corrosion rate should be calculated using mathematical formulas. If the corrosion products affect the later corrosion rate of the pipe, it is also necessary to fit the results measured at different time points, simulate the long-term corrosion patterns using computer data, and obtain a well barrier corrosion change model.
[0027] Furthermore, an annular pressure model is constructed for annular pressure zone to calculate and simulate annular pressure conditions. The parameters used to calculate annular pressure include wellbore structure, wellbore trajectory, gas production / liquid production, wellhead temperature and pressure, formation temperature and pressure, gas compressibility factor and viscosity, gas density, cement sheath length, mud compressibility factor and density, gas column length, liquid column length, cement sheath thermal conductivity, casing and tubing dimensions and thermal conductivity, cement sheath thermal conductivity, and formation thermal conductivity.
[0028] The above parameters can be obtained from drilling and completion data and production data. Using the above basic data, the annular pressure situation is predicted based on machine learning algorithms and annular pressure models.
[0029] Furthermore, an environmental analysis model is constructed for each area of the gas wellbore to analyze the impact of environmental factors on each area of the wellbore. The parameters include rock type, rock structure, mineral composition and content, rock heterogeneity, matrix pore structure, macro / micro scale of secondary pores and relative permeability parameters, organic matter abundance index of the rock strata, properties of crude oil and natural gas, pressure gradient, wettability, capillary force oil cut height, gas-water inversion, oil-water inversion, capping characteristics, lithology, physical properties, oil and gas distribution, mechanical properties, formation stress analysis, and brittleness index. The above indicators reflect the specific environment of the formation characteristics, and the environmental analysis model is used to analyze and simulate the environment in which the tubing is located.
[0030] The beneficial effects of this invention are as follows:
[0031] This invention utilizes neural network machine learning to comprehensively consider various factors affecting gas wellbore systems, enabling intelligent management and control throughout the entire gas wellbore lifecycle. This aims to improve operational procedures and prevent well barrier failure. Based on extensive actual monitoring data from different stages of the gas well's lifecycle, this invention establishes an evaluation model for real-time assessment, resulting in enhanced reliability and scientific rigor. Attached Figure Description
[0032] Appendix Figure 1 This is a schematic diagram of heat transfer in the wellbore.
[0033] Appendix Figure 2 This is a schematic diagram of the gas wellbore safety evaluation process. Detailed Implementation
[0034] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.
[0035] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.
[0036] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, the terms "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.
[0037] In the description of the embodiments of the present invention, it should be noted that the terms "inner", "outer", "upper", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship in which the product of the invention is usually placed when in use. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limiting the present invention.
[0038] Example 1
[0039] like Figures 1 to 2 As shown in the figure, this embodiment provides a safety evaluation method for the entire life cycle of a gas well shaft, including the following steps:
[0040] Step 1: Establish an initial parameter database for the life cycle of the gas wellbore. The data in the initial parameter database are obtained during well completion.
[0041] Step 2: Based on the known experimental evaluation, on-site detection, and monitoring data, construct learning models for multiple monitoring objects;
[0042] Step 3: Substitute the data from the initial parameter database into the learning models of the multiple monitoring objects above to obtain the original theoretical monitoring data of the gas wellbore.
[0043] Step 4: Randomly collect sample data from several gas well shafts, and substitute the sample data into the learning model of multiple monitoring objects above to obtain the actual monitoring data of the current gas well shaft.
[0044] Step 5: Establish a gas wellbore lifecycle management model. This model is a machine learning model based on neural networks. The original theoretical monitoring data obtained in Step 3 and the actual monitoring data obtained in Step 4 are substituted into the gas wellbore lifecycle management model and trained according to the machine learning algorithm to obtain an optimized gas wellbore lifecycle management model.
[0045] Step 6: Based on the actual life cycle data from the gas wellbore test, the optimized gas wellbore life cycle management model is revised to obtain the revised gas wellbore life cycle management model.
[0046] Step 7: Using the revised gas wellbore lifecycle management model, manage the lifecycle of each gas wellbore to achieve a full-process safety assessment. Based on the indicators obtained from the revised gas wellbore lifecycle management model, classify the safety risks of the gas wellbore into multiple risk levels according to the degree of risk hazard, as shown in Table 1 below. Then, according to the risk level, provide feedback to the relevant operational departments responsible for that risk.
[0047] Table 1 Well Integrity Classification and Response Measures
[0048]
[0049]
[0050]
[0051] Further analysis of various indicators in the gas wellbore lifecycle management model, such as wellbore pressure, well barrier corrosion, annular pressure, and environmental analysis, identifies key factors affecting wellbore life. Based on these key factors, adjustments or replacements are made to corresponding structures, components, or operational plans. Simultaneously, further analysis of these key factors can lead to the standardization and optimization of well completion operation procedures.
[0052] Based on the above evaluation methods, a corresponding evaluation system is constructed and implemented using a computer. The evaluation system is implemented through a UI interface; by inputting the original parameters and the parameters measured in real time, it can automatically output various indicators and lifespan status of the current wellbore.
[0053] A corresponding early warning module can also be added to this evaluation system to directly warn the relevant operating departments about situations involving wellbore life safety. The risks here mainly refer to the situations corresponding to the orange and red level wells in the superscript.
[0054] Example 2
[0055] This embodiment is a further optimization based on Embodiment 1, specifically:
[0056] In step one, the initial parameter model includes: physical parameter data of the tubing, parameter data of the production casing, parameter data of the technical casing, parameter data of the surface casing, pressure data of each annulus zone, gas composition data of each annulus zone, parameter data of the wellbore itself (such as cement sheath quality, well depth, well diameter, etc.), and geological data of the wellbore location (such as water cut, pressure conditions, geological composition, etc.).
[0057] Example 3
[0058] This embodiment is a further optimization based on embodiment 1 or 2, specifically:
[0059] In step two, based on the known experimental evaluations, field detections, and monitoring data in the existing technology, four monitoring object learning models are constructed, including a gas wellbore pressure model, a well barrier corrosion model for well barrier corrosion / erosion, an annular pressure model for annular pressure, and an environmental analysis model for different areas of the gas wellbore.
[0060] A wellbore pressure model is constructed to calculate and simulate pressure changes in the gas wellbore. This model can be used to simulate these changes using the following formula:
[0061] P h = f(x+y+z+x(t),+P k +ρ)
[0062] Where x represents the gas well depth, y represents the wellbore trajectory, z represents the tubing structure and dimensions, x(t) represents the gas production / liquid production of the gas well, and P k ρ represents the wellhead oil pressure, and ρ represents the gas density. The gas production / liquid production and oil pressure can be obtained through existing monitoring systems, while the well depth, wellbore trajectory, tubing structure and dimensions are obtained from the well completion data.
[0063] In addition, a wellbore temperature model is constructed to address the temperature variations in the gas wellbore. The factors influencing temperature and pressure are mutually restrictive and interdependent. Calculating temperature-influencing factors (such as isobaric heat capacity and Joule-Thomson coefficient) requires known pressure. Similarly, calculating pressure-influencing factors (such as friction coefficient) requires known temperature. In short, pressure and temperature factors are mutually influential; therefore, their coupling must be considered when calculating temperature and pressure, and an iterative solution is necessary. For specific methods, please refer to "Prediction Model for Temperature and Pressure Distribution in High-Sulfur Gas Wells," which will not be elaborated upon here.
[0064] Furthermore, a well barrier corrosion model is constructed to calculate and simulate changes in well barrier corrosion / erosion.
[0065] For wellhead corrosion assessment, the main parameters include the overall neck thickness, the remaining valve thickness, and the remaining Nyquist alloy layer thickness. These can be measured using electromagnetic ultrasound, ultrasonic phased array, and other methods. By subtracting the initial thickness from the measured thickness, the thickness change can be obtained. By comparing and analyzing the measurement cycle (years), the thickness change rate can be obtained. Based on the analysis of previous inspections, the thickness of each part decreases with the extension of gas well production time, which is related to factors such as gas production and solid content.
[0066] For downhole tubing: the main parameter for corrosion assessment is the remaining wall thickness of the tubing. This can be obtained using techniques such as multi-arm caliper, magnetic thickness gauge, and electromagnetic flaw detection for multi-layer tubing corrosion testing. The thickness variation is obtained by subtracting the initial thickness from the measured thickness, and then compared with the measurement cycle (years) to obtain the tubing corrosion rate (usually mm / year). This is then combined with strength theory calculations to obtain the remaining strength of the tubing and evaluate its strength safety. Analysis of previous indoor experiments and field inspections shows that the tubing corrosion rate decreases with the extension of gas well production time, and is related to wellbore temperature, pressure, acid gas content, Cl- content, etc. - It is related to factors such as content and gas production.
[0067] The main corrosive media in conventional oil and gas wells include CO2, H2S, and microorganisms. The differences in corrosive media lead to different corrosion mechanisms in the tubing. However, due to the complexity of the factors affecting corrosion, the standard for CO2 oil casing corrosion only specifies that, for the CNOOC block, the chloride ion concentration should be less than 25,000 mg / L, the well flow rate should be less than 2.0 m / s, and the diagrams and calculation methods should be provided under neutral solution conditions. Regarding H2S corrosion, due to the sudden and unpredictable nature of the corrosion, only diagrams are provided for reference.
[0068] In practical applications, to design anti-corrosion measures for a specific area, a special study on the corrosion situation in that area should be conducted first. This involves experimental analysis of the corrosion products on-site using methods such as SEM (scanning electron microscopy). Then, combined with the results of on-site well fluid analysis, indoor corrosion plate tests should be carried out, and the corrosion rate should be calculated using mathematical formulas. If the corrosion products affect the later corrosion rate of the pipe, it is also necessary to fit the results measured at different time points, simulate the long-term corrosion patterns using computer data, and obtain a well barrier corrosion change model.
[0069] An annular pressure model is constructed to calculate and simulate annular pressure conditions. The parameters used to calculate annular pressure include wellbore structure, wellbore trajectory, gas production / liquid production, wellhead temperature and pressure, formation temperature and pressure, gas compressibility factor and viscosity, gas density, cement sheath length, mud compressibility factor and density, gas column length, liquid column length, cement sheath thermal conductivity, casing and tubing dimensions and thermal conductivity, cement sheath thermal conductivity, and formation thermal conductivity.
[0070] The above parameters can be obtained from drilling and completion data and production data. Using the above basic data, the annular pressure situation is predicted based on machine learning algorithms and annular pressure models.
[0071] An environmental analysis model is constructed for each area of the gas wellbore to analyze the impact of environmental factors on each area of the wellbore. The parameters include rock type, rock structure, mineral composition and content, rock heterogeneity, matrix pore structure, macro / micro scale of secondary pores and relative permeability parameters, organic matter abundance index of the rock layer, crude oil and natural gas properties, pressure gradient, wettability, capillary force oil cut, gas-water inversion, oil-water inversion, capping characteristics, lithology, physical properties, oil and gas distribution, mechanical properties, formation stress analysis, and brittleness index. The above indicators reflect the specific environment of the formation characteristics, and the environmental analysis model is used to analyze and simulate the environment in which the tubing is located.
Claims
1. A method for safety evaluation of the entire life cycle of a gas well shaft, characterized in that, Includes the following steps: Step 1: Establish an initial parameter database for the life cycle of the gas wellbore. The data in the initial parameter database are obtained during well completion. Step 2: Based on the known experimental evaluation, on-site detection, and monitoring data, construct learning models for multiple monitoring objects; Step 3: Substitute the data from the initial parameter database into the learning models of the multiple monitoring objects above to obtain the original theoretical monitoring data of the gas wellbore. Step 4: Randomly collect sample data from several gas well shafts, and substitute the sample data into the learning model of multiple monitoring objects above to obtain the actual monitoring data of the current gas well shaft. Step 5: Establish a gas wellbore lifecycle management model. This model is a machine learning model based on neural networks. The original theoretical monitoring data obtained in Step 3 and the actual monitoring data obtained in Step 4 are substituted into the gas wellbore lifecycle management model and trained according to the machine learning algorithm to obtain an optimized gas wellbore lifecycle management model. Step 6: Based on the actual life cycle data from the gas wellbore test, the optimized gas wellbore life cycle management model is revised to obtain the revised gas wellbore life cycle management model. Step 7: Using the modified gas wellbore lifecycle management model, manage the lifecycle of each gas wellbore, achieve a full-process safety assessment of the wellbore, and classify the safety risks of the gas wellbore according to the various indicators obtained from the modified gas wellbore lifecycle management model, dividing them into multiple risk levels according to the risk hazard procedure. In step one, the initial parameter model includes: physical parameter data of the tubing, parameter data of the production casing, parameter data of the technical casing, parameter data of the surface casing, pressure data of each annulus, gas composition data of each annulus, wellbore trajectory parameter data of the wellbore itself, and geological data of the location of the wellbore. In step two, based on the known experimental evaluation, field detection and monitoring data in the existing technology, four monitoring object learning models are constructed, including a gas wellbore pressure model, a well barrier corrosion model for well barrier corrosion / erosion, an annular pressure model for annular pressure, and an environmental analysis model for each area of the gas wellbore. A gas wellbore pressure calculation model is constructed to calculate and simulate pressure changes in the gas wellbore. This can be simulated using the following formula: Where x represents the gas well depth, y represents the wellbore trajectory, z represents the tubing structure and dimensions, x(t) represents the gas production / liquid production of the gas well, and P k ρ represents the wellhead oil pressure, and ρ represents the gas density. The gas production / liquid production and oil pressure can be obtained through existing monitoring systems, while the well depth, wellbore trajectory, tubing structure and dimensions can be obtained from completion data.
2. The method for safety evaluation of the whole life cycle of a gas well shaft according to claim 1, characterized in that, A well barrier corrosion model was constructed to calculate and simulate well barrier corrosion changes, including wellhead analysis and downhole tubing analysis.
3. The method for safety evaluation of the whole life cycle of a gas well shaft according to claim 2, characterized in that, For wellheads: Corrosion assessment parameters include overall neck thickness, remaining valve thickness, and remaining corrosion-resistant alloy layer thickness; these can be measured using electromagnetic ultrasound or ultrasonic phased array methods. By subtracting the initial thickness from the measured thickness, the thickness change can be obtained. By combining the measurement cycle for comparative analysis, the thickness change rate can be obtained. Based on the analysis of previous inspections, the thickness of each part decreases as the gas well production time increases, which is related to factors such as gas production and solid content.
4. The method for safety evaluation of the whole life cycle of a gas well shaft according to claim 2, characterized in that, For downhole tubing: The parameter for corrosion assessment is the remaining wall thickness of the tubing. This can be obtained using multi-arm caliper, magnetic thickness gauge, and electromagnetic flaw detection multi-layer tubing corrosion detection technology. The thickness change is obtained by subtracting the initial thickness of the tubing from the thickness at the time of measurement. The corrosion rate of the tubing is then obtained by comparing and analyzing the measurement cycles. Finally, the remaining strength of the tubing is calculated using strength theory to evaluate the strength and safety of the tubing.
5. The method for safety evaluation of the whole life cycle of a gas well shaft according to claim 1, characterized in that, An annular pressure model is constructed to calculate and simulate annular pressure conditions. The parameters used to calculate annular pressure include wellbore structure, wellbore trajectory, gas production / liquid production, wellhead temperature and pressure, formation temperature and pressure, gas compressibility factor and viscosity, gas density, cement sheath length, mud compressibility factor and density, gas column length, liquid column length, cement sheath thermal conductivity, casing and tubing dimensions and thermal conductivity, and formation thermal conductivity. The above parameters can be obtained from drilling and completion data and production data; using the above parameters, the annular pressure situation is predicted based on machine learning algorithms and annular pressure models.
6. The method for safety evaluation of the whole life cycle of a gas well shaft according to claim 1, characterized in that, An environmental analysis model is constructed for each area of the gas wellbore to analyze the impact of environmental factors on each area of the wellbore, collect parameter indicators, reflect the specific environmental characteristics of the formation through the parameter indicators, and analyze and simulate the environment in which the tubing string is located through the environmental analysis model.
7. The method for safety evaluation of the entire life cycle of a gas wellbore according to claim 6, characterized in that, The parameters include the rock type, rock structure, mineral composition and content, rock heterogeneity, matrix pore structure, macro / micro scale and relative permeability parameters of secondary pores, organic matter abundance index of the rock layer, crude oil and natural gas properties, pressure gradient, wettability, capillary force oil-bearing height, gas-water inversion, oil-water inversion, capping characteristics, lithology, physical properties, oil and gas distribution, mechanical properties, formation stress analysis, and brittleness index of each casing column.