Physical field prediction method, apparatus and system

Abstract

The present application relates to the field of oil and gas field safety, and discloses a physical field prediction method, apparatus and system. On the basis of the solution provided in the present application, by establishing a thermal radiation field prediction model, a temperature field prediction model and a fluid velocity field prediction model, when a physical field around a well needs to be predicted, it is only necessary to input real-time working condition information into the thermal radiation field prediction model, the temperature field prediction model and the fluid velocity field prediction model to obtain a prediction result of the physical field around the well, without the need to use a complex and time-consuming fluid dynamics numerical simulation method to predict the physical field around the well, thereby realizing rapid prediction of a physical field around an out-of-control blowout well.

Description

Physical field prediction methods, devices and systems

[0001] Cross-references to related applications

[0002] This application claims the benefit of Chinese Patent Application No. 202411883069.3, filed on December 19, 2024, the contents of which are incorporated herein by reference. Technical Field

[0003] This invention relates to the field of oil and gas field safety technology, and specifically to a physical field prediction method, a physical field prediction device, and a physical field prediction system. Background Technology

[0004] Well control risk is the primary safety risk in oil and gas field production, especially for "high-energy-consuming, high-polluting, and high-risk" wells. These wells face numerous uncertainties during exploration and development, increasing the risk of uncontrolled blowouts. An uncontrolled blowout occurs when formation fluids are uncontrollably ejected from an oil or gas well and ignited by a source of ignition. It is one of the most common, widespread, and serious safety accidents in the oil and gas extraction industry. A blowout can easily cause significant personal injury and economic losses.

[0005] After a blowout goes out of control and catches fire, the ejected flames emit intense heat radiation; under typical leakage rates, the surface of the ejected flames can generate up to 250 kW / m³. 2 The radiation intensity. Human exposed skin is exposed to a lower radiation intensity of 17.87 kW / m². 2 Within 2 seconds, pain will begin, and burns will occur rapidly in a short time. Clearly, the heat radiation emitted by the jet flame is extremely dangerous.

[0006] Currently, the common method for handling blowout accidents is to control the ignition zone by spraying cooling water. However, the ejected flame is difficult to control due to the influence of many factors, including the form of wellhead damage, gas production, formation fluid velocity, and surrounding environmental conditions. Therefore, predicting the physical field around the well after a blowout has gradually become crucial for achieving effective spraying.

[0007] Considering that the jet combustion process involves the coupling of flow fields, radiation fields, temperature fields, and chemical composition fields, current methods for simulating and predicting the physical field around a blowout-affected well are mostly based on multi-field coupling. In specific calculations, the prediction of the physical field around a blowout-affected well is generally solved using computational fluid dynamics (CFD) numerical simulation methods. However, CFD numerical simulation methods often involve complex physical processes, requiring the simulation of flame turbulence, heat transfer, radiation, chemical reactions, and multiphase flow, resulting in extremely large computational loads. This makes it difficult to achieve rapid prediction of the physical field around a blowout-affected well, thus hindering timely and effective rescue and relief efforts. Summary of the Invention

[0008] The purpose of this invention is to overcome the problem of the difficulty in rapidly predicting the physical field around a blowout-out well in the prior art, and to provide a physical field prediction method, a physical field prediction device, a physical field prediction system, a machine-readable storage medium, and a processor.

[0009] To achieve the above objectives, the present invention provides a physical field prediction method, the prediction method comprising:

[0010] Acquire physical field data around the well, including thermal radiation intensity data, temperature field data, and wind vector data;

[0011] Flame morphology parameters are determined based on flame analysis theory. These parameters include flame tilt angle, flame lift height, and flame centerline length. An initial thermal radiation field prediction model is established based on these parameters. The initial thermal radiation field prediction model is then optimized based on hydrodynamic thermal radiation field simulation data and the physical field data to obtain a target thermal radiation field prediction model.

[0012] Machine learning is performed based on fluid dynamics temperature field simulation data to obtain a target temperature field prediction model;

[0013] Machine learning is performed based on fluid velocity field simulation data from fluid dynamics to obtain a prediction model for the target fluid velocity field.

[0014] The well perimeter physical field is predicted based on the target thermal radiation field prediction model, the target thermal radiation field prediction model, and the target fluid velocity field prediction model.

[0015] A second aspect of this application provides a physical field prediction device, comprising:

[0016] The acquisition module is used to acquire physical field data around the well, including thermal radiation intensity data, temperature field data, and wind vector data.

[0017] The thermal radiation field prediction model construction module is used to determine the flame morphology parameters based on flame analytical theory. The flame morphology parameters include the flame tilt angle, flame lift height and flame centerline length. An initial thermal radiation field prediction model is established based on the flame morphology parameters. The initial thermal radiation field prediction model is optimized based on the fluid dynamics thermal radiation field simulation data and the physical field data to obtain the target thermal radiation field prediction model.

[0018] The temperature field prediction model building module is used to perform machine learning based on fluid dynamics temperature field simulation data to obtain the target temperature field prediction model.

[0019] The fluid velocity field prediction model building module is used to perform machine learning based on fluid dynamics fluid velocity field simulation data to obtain a target fluid velocity field prediction model.

[0020] The prediction module is used to predict the well perimeter physical field based on the target thermal radiation field prediction model, the target thermal radiation field prediction model, and the target fluid velocity field prediction model.

[0021] A third aspect of this application provides a physical field prediction system, including a measurement unit and a physical field prediction device provided in the second aspect;

[0022] The measurement unit includes a heat flux measuring instrument, an infrared thermal imager, and a wind vector measuring instrument. The heat flux measuring instrument is used to measure the thermal radiation intensity data around the well, the infrared thermal imager is used to measure the temperature field data around the well, and the wind vector measuring instrument is used to measure the wind vector data around the well.

[0023] A fourth aspect of this application provides a processor configured to perform the above-described physical field prediction method.

[0024] A fifth aspect of this application provides a machine-readable storage medium storing instructions that, when executed by a processor, configure the processor to perform the aforementioned physical field prediction method.

[0025] Based on the above technical solution, by establishing a thermal radiation field prediction model, a thermal radiation field prediction model, and a fluid velocity field prediction model, when it is necessary to predict the physical field around the well, only real-time operating condition information needs to be input into the thermal radiation field prediction model, the thermal radiation field prediction model, and the fluid velocity field prediction model to obtain the prediction result of the physical field around the well. There is no need to use complex and time-consuming fluid dynamics numerical simulation methods to predict the physical field around the well, thereby enabling rapid prediction of the physical field around the well in a blowout runaway well.

[0026] Other features and advantages of the embodiments of this application will be described in detail in the following detailed description section. Attached Figure Description

[0027] The accompanying drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the following detailed description to explain the embodiments of this application, but do not constitute a limitation on the embodiments of this application. In the drawings:

[0028] Figure 1 schematically illustrates a flowchart of a physical field prediction method according to an embodiment of this application;

[0029] Figure 2 schematically illustrates well perimeter temperature field data measured by an infrared thermal imager according to an embodiment of this application;

[0030] Figure 3 schematically illustrates the prediction effect diagram and comparison diagram of a target thermal radiation field prediction model and a computational fluid dynamics numerical simulation method according to an embodiment of this application;

[0031] Figure 4 schematically illustrates the prediction effect diagram and comparison diagram of a target temperature field prediction model and a computational fluid dynamics numerical simulation method according to an embodiment of this application;

[0032] Figure 5 schematically illustrates the prediction effect diagram and comparison diagram of a target fluid velocity field prediction model and a computational fluid dynamics numerical simulation method according to an embodiment of this application;

[0033] Figure 6 schematically illustrates a flowchart of another physical field prediction method according to an embodiment of this application;

[0034] Figure 7 schematically illustrates a structural block diagram of a physical field prediction device according to an embodiment of this application;

[0035] Figure 8 schematically illustrates a structural block diagram of a physical field prediction system according to an embodiment of this application;

[0036] Figure 9 schematically illustrates the internal structure of a computer device according to an embodiment of this application.

[0037] Explanation of reference numerals in the attached figures: 210 - Acquisition module; 220 - Thermal radiation field prediction model construction module; 230 - Temperature field prediction model construction module; 240 - Fluid velocity field prediction model construction module; 250 - Prediction module; 301 - Heat flux measuring instrument; 302 - Infrared thermal imager; 303 - Wind vector measuring instrument; 304 - Computer equipment; A01 - Processor; A02 - Network interface; A03 - Internal memory; A04 - Display screen; A05 - Input device; A06 - Non-volatile storage medium; B01 - Operating system; B02 - Computer program. Detailed Implementation

[0038] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for illustration and explanation of the embodiments of this application and are not intended to limit the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0039] It should be noted that if the embodiments of this application involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of the components in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.

[0040] Furthermore, if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0041] One embodiment of this application provides a physical field prediction method for predicting the physical field around a blowout-affected well. As shown in Figure 1, the physical field prediction method may include the following steps:

[0042] Step 101: Obtain physical field data around the well, including thermal radiation intensity data, temperature field data, and wind vector data.

[0043] Specifically, the well perimeter can refer to the well perimeter of a blowout-out well, which is a well where a blowout-out accident has occurred.

[0044] In practical applications, the thermal radiation intensity data around a well can be obtained by measuring a heat flux meter. The heat flux meter has a circular cross-section. In specific implementation, multiple heat flux meters can be set up around the well, and each heat flux meter can be installed at any monitoring position around the well to measure the thermal radiation intensity at the corresponding position, thus obtaining the scattered thermal radiation intensity around the well.

[0045] The temperature field data around the well can be obtained by measuring with an infrared thermal imager, which records the local temperature field around the well. In a specific embodiment, the temperature field data around the well obtained by the infrared thermal imager can be shown in Figure 2.

[0046] The wind vector data can include wind speed data and wind direction data. Wind speed data represents the magnitude of the wind speed, and wind direction data represents the distribution of wind direction. The wind vector data around the well can be obtained by measuring a wind vector measuring instrument, which can measure the magnitude of the wind speed and the distribution of wind direction in the local area around the well.

[0047] In practical applications, after the heat flux meter, infrared thermal imager, and wind vector measuring instrument obtain the corresponding data, this data can be stored in a storage unit, such as locally, which can be built into a computer device. Therefore, step 101, acquiring the thermal radiation intensity data, temperature field data, and wind vector data around the well, can specifically be obtained from the aforementioned storage unit.

[0048] Step 102: Determine the flame morphology parameters based on flame analysis theory. The flame morphology parameters include the flame tilt angle, flame lift height, and flame centerline length. Establish an initial thermal radiation field prediction model based on the flame morphology parameters. Optimize the initial thermal radiation field prediction model based on hydrodynamic thermal radiation field simulation data and the physical field data to obtain the target thermal radiation field prediction model.

[0049] The target thermal radiation field prediction model is the final thermal radiation field prediction model.

[0050] In this embodiment of the application, the flame tilt angle can be determined based on the following formula (1):

[0051] In formula (1) above, α is the flame tilt angle, in degrees; θ jv R is the angle between the wind direction and the axis of the leak, in degrees. w L is the ratio of wind speed to jet velocity. b0 R is the length of a flame in still air (also known as under windless conditions), measured in meters (m). i (L b0 ) is the Richardson number of a flame in still air, which is dimensionless.

[0052] Furthermore, the flame lift height can be determined based on the following formula:

[0053] In the above formula (2), b is the flame lift height, in meters; L b R represents the flame length under windy conditions, in meters (m); α represents the flame tilt angle, in degrees (°); w It is the ratio of wind speed to jet speed.

[0054] Furthermore, the length of the flame centerline can be determined based on the following formula (3):

[0055] In the above formula (3), R1 is the length of the flame centerline, in meters; L b α represents the flame length under windy conditions, in meters; b represents the flame lift height, in meters; and α represents the flame tilt angle, in degrees.

[0056] In this embodiment of the application, establishing an initial thermal radiation field prediction model based on the flame morphology parameters may include steps one, two, and three, as follows:

[0057] Step 1: Determine the combustion energy of the flame per unit time based on the leakage flow rate and the heat of combustion of the leaked substance.

[0058] The combustion energy of the flame per unit time can be determined based on the following formula (4): Q=mΔH (4);

[0059] In the above formula (4), Q is the combustion energy of the flame per unit time, in J / s; m is the leakage flow rate, in kg / s; ΔH is the heat of combustion of the leaked substance, in J / kg.

[0060] Step 2: Determine the linear density heat load based on the combustion energy of the flame per unit time and the length of the flame centerline.

[0061] The linear density heat load can be determined based on the following formula (5):

[0062] In the above formula (5), q′ is the linear density heat load, in J / (s·m); Q is the combustion energy of the flame per unit time, in J / s; and R1 is the flame centerline length, in m.

[0063] Step 3: Establish an initial thermal radiation field prediction model based on linear density heat load, flame tilt angle, flame lift height, and flame centerline length.

[0064] The initial thermal radiation field prediction model can be established based on the following formula (6), that is, the initial thermal radiation field prediction model can be as shown in the following formula (6):

[0065] In the above formula (6), q(x0,y0,z0) is the thermal radiation intensity at any point, with units of W / m². 2 ξ represents combustion efficiency, which can be taken as 0.8. For thermal radiation efficiency, we can take 0.6; for atmospheric transmittance, we can take 1.0; for flame tilt angle, we take degrees; for flame centerline length, we take meters; for z a0 This represents the height of the flame nozzle, in meters (m).

[0066] In this embodiment of the application, optimizing the initial thermal radiation field prediction model based on hydrodynamic thermal radiation field simulation data and the physical field data may include steps i and ii, as follows:

[0067] Step i: Use a computational fluid dynamics analysis system (CFD analysis system) to simulate the jet flame around the well to obtain simulation data of the hydrodynamic thermal radiation field.

[0068] The CFD analysis system can obtain physical field simulation data of the well perimeter after simulating the jet flame around the well. This physical field simulation data includes thermal radiation field simulation data, which is the same as the hydrodynamic thermal radiation field simulation data.

[0069] In this embodiment, the CFD analysis system simulates the jet flames around the well, specifically simulating flames during runaway jetting at the wellhead, flames during blowout prevention, and flames during droplet atomization and cooling, to obtain physical field simulation data around the well. In practical applications, after the CFD analysis system simulates the jet flames around the well, post-processing software such as CFD-Post can be used for further processing to obtain physical field simulation data around the well.

[0070] During the simulation, the operating conditions can be set as follows: spray volume of 50,000 cubic meters / day to 10 million cubic meters / day; uniform airflow from the side with a velocity of 1 m / s to 17 m / s; and spray volume of 40 L / s to 120 L / s.

[0071] Furthermore, considering the significant differences between nozzle size, flame size, and overall space size (i.e., total computational domain size), unstructured meshes can be used to refine the wellhead, spray nozzle, and flame areas during simulation. The mesh types used can include structured meshes, unstructured meshes, hybrid meshes, and cellular meshes; the number of meshes can range from 500,000 to 2,000,000.

[0072] Step ii: Optimize the initial thermal radiation field prediction model based on the fluid dynamics thermal radiation field simulation data and the physical field data.

[0073] The physical field data used to optimize the initial thermal radiation field prediction model specifically refers to the real physical field data obtained by measuring various instruments in step 101.

[0074] In this embodiment of the application, the hydrodynamic thermal radiation field simulation data can be used to optimize the overall trend of the initial thermal radiation field prediction model, and the physical field data is well-circumferential scattered correlation data or well-circumferential local correlation data, which can be used to optimize the local trend of the initial thermal radiation field prediction model.

[0075] From formula (6), it can be seen that the three flame morphology parameters that affect the calculation of thermal radiation intensity q(x0,y0,z0) are the flame tilt angle α, the flame lift height b, and the flame centerline length R1. By working backward layer by layer, the main influencing factor is the wind speed u. w Leakage outlet ejection speed u j and the effective flame source diameter D s Therefore, when optimizing the initial thermal radiation field prediction model based on hydrodynamic thermal radiation field simulation data and physical field data, wind speed u can be introduced. w and leakage speed u j And correct the effective flame source diameter D s The optimization objective is achieved through parameters such as [parameter name missing]. The optimization objective can be set according to actual needs; for example, the optimization objective could be to minimize the global average error of the thermal radiation field.

[0076] Specifically, the initial thermal radiation field prediction model can be optimized based on the following formula (7), or the target thermal radiation field prediction model can be as shown in the following formula (7):

[0077] In the above formula (7),

[0078] Where q(x0,y0,z0) is the thermal radiation intensity at any point, with units of W / m². 2 ;u w Wind speed, in m / s; u j α is the ejection velocity from the leak, in m / s; α is the flame tilt angle, in degrees; R1 is the flame centerline length, in m; q′ is the linear density heat load, in J / (s·m); b is the flame lift height, in m; z a0 D is the height of the flame nozzle, in meters (m). s d is the effective diameter of the flame source, in meters (m). j ρ is the diameter of the leak outlet, in meters (m); j The density of the jet fluid is expressed in kg / m³. 3 ;ρ air Air density, unit: kg / m³ 3 c1, c2, and c3 are all optimization parameters; R w R is the ratio of wind speed to jet velocity. i (L b0 (m1) represents the Richardson number of a flame in still air; m2 is 0.37 (m / s); m3 is 1 (m / s); m4 is 1 (m / s); m5 is 1 (m / s).

[0079] In a specific embodiment, the prediction results of the target thermal radiation field prediction model and the prediction effect of the computational fluid dynamics numerical simulation method in the prior art, as well as the comparison diagram, can be shown in Figure 3. In Figure 3, "model calculation" corresponds to the target thermal radiation field prediction model, and "computational fluid dynamics system" corresponds to the computational fluid dynamics numerical simulation method in the prior art.

[0080] Step 103: Perform machine learning based on the fluid dynamics temperature field simulation data to obtain the target temperature field prediction model.

[0081] The target temperature field prediction model is the final temperature field prediction model.

[0082] In practical implementation, a computational fluid dynamics (CFD) analysis system can be used to simulate the jet flame around the well to obtain hydrodynamic temperature field simulation data. Specifically, after simulating the jet flame around the well, the CFD analysis system can obtain physical field simulation data of the well perimeter; this physical field simulation data includes temperature field simulation data, which is the hydrodynamic temperature field simulation data. Specifically, the CFD analysis system can simulate the jet flame around the well, including flames during runaway jetting at the wellhead, flames during blowout prevention, and flames during droplet atomization and cooling, to obtain the physical field simulation data of the well perimeter. In practical applications, after the CFD analysis system simulates the jet flame around the well, post-processing software such as CFD-Post can be used for further processing to obtain the physical field simulation data of the well perimeter.

[0083] In this embodiment of the application, the fluid dynamics temperature field simulation data may specifically include temperature field simulation data under different working conditions and at different heights.

[0084] When performing machine learning, fluid dynamics temperature field simulation data can be used as the training data source. The simulation data samples are converted into matrices to form the training set. The pre-trained model is then trained using this training set to obtain the target temperature field prediction model. The pre-trained model is a deep learning model pre-trained on a large dataset. During training, the learning rate can be set, and an optimizer can be used to update the weights of the pre-trained model to improve generalization accuracy. For example, the learning rate can be set to 1e-4, and the optimizer can be the Adam optimizer.

[0085] In a specific embodiment, the prediction results of the target temperature field prediction model and the prediction effect of the computational fluid dynamics numerical simulation method in the prior art, as well as the comparison diagram, can be shown in Figure 4. In Figure 4, "model calculation" corresponds to the target temperature field prediction model, and "computational fluid dynamics system" corresponds to the computational fluid dynamics numerical simulation method in the prior art.

[0086] Step 104: Perform machine learning based on the fluid velocity field simulation data from fluid dynamics to obtain a prediction model for the target fluid velocity field.

[0087] The target fluid velocity field prediction model is the final fluid velocity field prediction model.

[0088] In practical implementation, a computational fluid dynamics (CFD) analysis system can be used to simulate the jet flame around the well, obtaining simulation data of the fluid velocity field. Specifically, after simulating the jet flame around the well, the CFD analysis system can obtain simulation data of the physical field around the well; this physical field simulation data includes simulation data of the fluid velocity field, which is the same as the simulation data of the fluid velocity field in the hydrodynamics. Specifically, the CFD analysis system can simulate the jet flame around the well, including the flame during the runaway jet process at the wellhead, the flame during the cutting and blowout prevention process, and the flame during the droplet atomization and cooling process, to obtain the physical field simulation data of the well. In practical applications, after the CFD analysis system simulates the jet flame around the well, post-processing software such as CFD-Post can be used for further processing to obtain the physical field simulation data of the well.

[0089] In this embodiment of the application, the fluid dynamics velocity field simulation data may specifically include fluid velocity field simulation data under different working conditions and at different heights.

[0090] When performing machine learning, fluid dynamics velocity field simulation data can be used as the training data source. The simulation data samples are converted into matrices to form the training set. The pre-trained model is then trained using this training set to obtain the target fluid velocity field prediction model. The pre-trained model is a deep learning model pre-trained on a large dataset. During training, the learning rate can be set, and an optimizer can be used to update the weights of the pre-trained model to improve generalization accuracy. For example, the learning rate can be set to 1e-4, and the optimizer can be the Adam optimizer.

[0091] In a specific embodiment, the prediction results of the target fluid velocity field prediction model and the prediction effect of the existing computational fluid dynamics numerical simulation method, as well as the comparison diagram, can be shown in Figure 5. In Figure 5, "model calculation" corresponds to the target temperature field prediction model, and "computational fluid dynamics system" corresponds to the existing computational fluid dynamics numerical simulation method.

[0092] Step 105: Predict the well perimeter physical field based on the target thermal radiation field prediction model, the target thermal radiation field prediction model, and the target fluid velocity field prediction model.

[0093] In practice, when a blowout occurs again, real-time operating information can be input into the target thermal radiation field prediction model, the target thermal radiation field prediction model, and the target fluid velocity field prediction model to simulate and predict the thermal radiation field, temperature field, and fluid velocity field around the blowout well, respectively.

[0094] The real-time operating information may include the leak orifice diameter, spray volume, scatter thermal radiation intensity measured by a heat flux meter, local temperature field around the well measured by an infrared thermal imager, and local wind speed measured by an anemometer.

[0095] In a specific embodiment, the implementation process of the physical field prediction method provided in this application can also be shown in Figure 6.

[0096] It is understood that the physical field prediction method provided in this application includes: acquiring physical field data around the well, the physical field data including thermal radiation intensity data, temperature field data, and wind vector data; determining flame morphology parameters based on flame analytical theory, the flame morphology parameters including flame tilt angle, flame lift height, and flame centerline length; establishing an initial thermal radiation field prediction model based on the flame morphology parameters; optimizing the initial thermal radiation field prediction model based on hydrodynamic thermal radiation field simulation data and the physical field data to obtain a target thermal radiation field prediction model; performing machine learning based on hydrodynamic temperature field simulation data to obtain a target temperature field prediction model; performing machine learning based on hydrodynamic fluid velocity field simulation data to obtain a target fluid velocity field prediction model; and predicting the physical field around the well based on the target thermal radiation field prediction model, the target thermal radiation field prediction model, and the target fluid velocity field prediction model. Based on the solution provided in the embodiments of this application, by establishing a thermal radiation field prediction model, a thermal radiation field prediction model and a fluid velocity field prediction model, when it is necessary to predict the physical field around the well, only real-time operating condition information needs to be input into the thermal radiation field prediction model, the thermal radiation field prediction model and the fluid velocity field prediction model to obtain the prediction result of the physical field around the well. There is no need to use a complex and time-consuming fluid dynamics numerical simulation method to predict the physical field around the well, thereby enabling rapid prediction of the physical field around the well in a blowout runaway well.

[0097] By comparison, the thermal radiation field prediction model, thermal radiation field prediction model, and fluid velocity field prediction model provided in the embodiments of this application can obtain the wellbore physical field prediction results in just seconds, while the existing fluid dynamics numerical simulation methods require 10-100 hours to obtain the wellbore physical field prediction results. In addition, the prediction results of thermal radiation field, temperature field, and fluid velocity field under different operating conditions (jet rate, wind speed) and different heights have small errors compared with the results of fluid dynamics numerical simulation methods, indicating that the thermal radiation field prediction model, thermal radiation field prediction model, and fluid velocity field prediction model provided in the embodiments of this application can simultaneously achieve accurate predictions.

[0098] Based on the same inventive concept, as shown in Figure 7, Figure 7 schematically illustrates a structural block diagram of a physical field prediction device according to an embodiment of this application. In one embodiment, a physical field prediction device 200 is provided, including an acquisition module 210, a thermal radiation field prediction model construction module 220, a temperature field prediction model construction module 230, a fluid velocity field prediction model construction module 240, and a prediction module 250, wherein:

[0099] The acquisition module 210 is used to acquire physical field data around the well, including thermal radiation intensity data, temperature field data, and wind vector data.

[0100] The thermal radiation field prediction model construction module 220 is used to determine the flame morphology parameters based on flame analytical theory. The flame morphology parameters include the flame tilt angle, flame lift height and flame centerline length. An initial thermal radiation field prediction model is established based on the flame morphology parameters. The initial thermal radiation field prediction model is optimized based on the fluid dynamics thermal radiation field simulation data and the physical field data to obtain the target thermal radiation field prediction model.

[0101] Temperature field prediction model building module 230 is used to perform machine learning based on fluid dynamics temperature field simulation data to obtain the target temperature field prediction model;

[0102] The fluid velocity field prediction model building module 240 is used to perform machine learning based on fluid dynamics fluid velocity field simulation data to obtain a target fluid velocity field prediction model.

[0103] The prediction module 250 is used to predict the well perimeter physical field based on the target thermal radiation field prediction model, the target thermal radiation field prediction model and the target fluid velocity field prediction model.

[0104] In one embodiment, the wind vector data includes wind speed data and wind direction data.

[0105] In one embodiment, the thermal radiation field prediction model building module 220 is used to determine the flame tilt angle based on the following formula:

[0106] Where α is the flame tilt angle, in degrees; θ jv R is the angle between the wind direction and the axis of the leak, in degrees. w R is the ratio of wind speed to jet velocity. i (L b0 ) represents the Richardson number of a flame in still air.

[0107] In one embodiment, the thermal radiation field prediction model building module 220 is used to determine the flame lift height based on the following formula:

[0108] Where b is the flame lift height, in meters; L b R represents the length of the flame under windy conditions, in meters (m). w α is the ratio of wind speed to jet speed; α is the flame tilt angle in degrees.

[0109] In one embodiment, the thermal radiation field prediction model building module 220 is used to determine the flame centerline length based on the following formula:

[0110] Where R1 is the flame centerline length in meters (m); b is the flame lift height in meters (m); L b α represents the flame length under windy conditions, in meters; α represents the flame tilt angle, in degrees.

[0111] In one embodiment, the thermal radiation field prediction model building module 220 is used to determine the combustion energy of the flame per unit time based on the leakage flow rate and the heat of combustion of the leaked material.

[0112] The linear density heat load is determined based on the combustion energy of the flame per unit time and the flame centerline length.

[0113] An initial thermal radiation field prediction model is established based on linear density heat load, flame tilt angle, flame lift height, and flame centerline length.

[0114] In one embodiment, the thermal radiation field prediction model building module 220 is used to determine the combustion energy of the flame per unit time based on the following formula: Q=mΔH;

[0115] Where Q is the combustion energy of the flame per unit time, in J / s; m is the leakage flow rate, in kg / s; and ΔH is the heat of combustion of the leaked substance, in J / kg.

[0116] In one embodiment, the thermal radiation field prediction model building module 220 is used to determine the linear density heat load based on the following formula:

[0117] Where q′ is the linear density heat load, in J / (s·m); R1 is the flame centerline length, in m; and Q is the combustion energy of the flame per unit time, in J / s.

[0118] In one embodiment, the initial thermal radiation field prediction model is shown in the following formula:

[0119] Where q(x0,y0,z0) is the thermal radiation intensity at any point, with units of W / m². 2 ξ represents combustion efficiency; τ is the thermal radiation efficiency; q′ is the atmospheric transmittance; α is the linear density heat load in J / (s·m); α is the flame tilt angle in degrees; φ is the flame nozzle height in meters; R1 is the flame centerline length in meters; and b is the flame lift height in meters.

[0120] In one embodiment, the thermal radiation field prediction model building module 220 is used to simulate the jet flame around the well using a computational fluid dynamics analysis system to obtain hydrodynamic thermal radiation field simulation data.

[0121] The initial thermal radiation field prediction model is optimized based on the fluid dynamics thermal radiation field simulation data and the physical field data.

[0122] In one embodiment, the target thermal radiation field prediction model is shown in the following formula:

[0123] In the above formula,

[0124] Where q(x0,y0,z0) is the thermal radiation intensity at any point, with units of W / m². 2 ;u w Wind speed, in m / s; u j α is the ejection velocity from the leak, in m / s; α is the flame tilt angle, in degrees; R1 is the flame centerline length, in m; q′ is the linear density heat load, in J / (s·m); b is the flame lift height, in m; z a0 D is the height of the flame nozzle, in meters (m). s d is the effective diameter of the flame source, in meters (m). j ρ is the diameter of the leak outlet, in meters (m); j The density of the jet fluid is expressed in kg / m³. 3 ;ρ air Air density, unit: kg / m³ 3 c1, c2, and c3 are all optimization parameters; R w R is the ratio of wind speed to jet velocity.i (L b0 (m1) represents the Richardson number of a flame in still air; m2 is 0.37 (m / s); m3 is 1 (m / s); m4 is 1 (m / s); m5 is 1 (m / s).

[0125] The physical field prediction device includes a processor and a memory. The aforementioned acquisition module 210, thermal radiation field prediction model construction module 220, temperature field prediction model construction module 230, fluid velocity field prediction model construction module 240, and prediction module 250 are all stored in the memory as program units. The processor executes the aforementioned program modules stored in the memory to implement the corresponding functions.

[0126] A processor contains a core, which retrieves the corresponding program unit from memory. One or more cores can be configured, and by adjusting the core parameters, fast and efficient computation can be achieved at the entire chip scale.

[0127] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0128] Furthermore, based on the physical field prediction method and apparatus provided in the above embodiments of this application, this application also provides a physical field prediction system, which includes a measurement unit and the aforementioned physical field prediction apparatus. As shown in FIG8, the measurement unit includes a heat flux measuring instrument 301, an infrared thermal imager 302, and a wind vector measuring instrument 303. The heat flux measuring instrument is used to measure the thermal radiation intensity data around the well, the infrared thermal imager is used to measure the temperature field data around the well, and the wind vector measuring instrument is used to measure the wind vector data around the well.

[0129] The measurement unit ensures the accuracy and real-time nature of the data. In practical implementation, multiple heat flux meters 301 can be installed around the well. These multiple heat flux meters can be installed at any monitoring position around the well to measure the thermal radiation intensity at the corresponding position, thus obtaining the scattered thermal radiation intensity around the well.

[0130] In practical applications, the physical field prediction system may also include a storage unit. After the heat flux meter 301, infrared thermal imager 302, and wind vector meter 303 measure the corresponding data, this data can be stored in the storage unit, for example, locally. Then, the physical field prediction device retrieves the well perimeter thermal radiation intensity data, temperature field data, and wind vector data from the storage unit. Both the storage unit and the physical field prediction device can be built into the computer device 304.

[0131] It is understood that by using the physical field prediction system provided in the embodiments of this application, by establishing a thermal radiation field prediction model, a thermal radiation field prediction model and a fluid velocity field prediction model, when it is necessary to predict the physical field around the well, only real-time operating condition information needs to be input into the thermal radiation field prediction model, the thermal radiation field prediction model and the fluid velocity field prediction model to obtain the prediction result of the physical field around the well. There is no need to use complex and time-consuming fluid dynamics numerical simulation methods to predict the physical field around the well, thereby enabling rapid prediction of the physical field around the well in blowout runaway wells.

[0132] This application provides a machine-readable storage medium storing a program that, when executed by a processor, implements the aforementioned physical field prediction method.

[0133] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in Figure 9. The computer device includes a processor A01, a network interface A02, a display screen A04, an input device A05, and a memory (not shown) connected via a system bus. The processor A01 provides computing and control capabilities. The memory includes internal memory A03 and a non-volatile storage medium A06. The non-volatile storage medium A06 stores an operating system B01 and a computer program B02. The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 stored in the non-volatile storage medium A06. The network interface A02 is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor A01, it implements a physical field prediction method. The display screen A04 may be a liquid crystal display (LCD) or an e-ink display. The input device A05 may be a touch layer covering the display screen, or buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse, etc.

[0134] Those skilled in the art will understand that the structure shown in Figure 9 is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0135] In one embodiment, the physical field prediction device provided in this application can be implemented as a computer program, which can run on a computer device as shown in FIG9. The memory of the computer device can store various program modules that constitute the intelligent scheduling device for construction tasks. For example, the physical field prediction device 200 shown in FIG7 includes an acquisition module 210, a thermal radiation field prediction model construction module 220, a temperature field prediction model construction module 230, a fluid velocity field prediction model construction module 240, and a prediction module 250. The computer program composed of these program modules causes the processor to execute the steps in the physical field prediction methods of the various embodiments of this application described in this specification.

[0136] The computer device shown in Figure 9 can execute the method through the physical field prediction device 200 in the physical field prediction device shown in Figure 7, which includes an acquisition module 210, a thermal radiation field prediction model construction module 220, a temperature field prediction model construction module 230, a fluid velocity field prediction model construction module 240, and a prediction module 250.

[0137] This application provides a device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs the following steps:

[0138] Acquire physical field data around the well, including thermal radiation intensity data, temperature field data, and wind vector data;

[0139] Flame morphology parameters are determined based on flame analysis theory. These parameters include flame tilt angle, flame lift height, and flame centerline length. An initial thermal radiation field prediction model is established based on these parameters. The initial thermal radiation field prediction model is then optimized based on hydrodynamic thermal radiation field simulation data and the physical field data to obtain a target thermal radiation field prediction model.

[0140] Machine learning is performed based on fluid dynamics temperature field simulation data to obtain a target temperature field prediction model;

[0141] Machine learning is performed based on fluid velocity field simulation data from fluid dynamics to obtain a prediction model for the target fluid velocity field.

[0142] The well perimeter physical field is predicted based on the target thermal radiation field prediction model, the target thermal radiation field prediction model, and the target fluid velocity field prediction model.

[0143] In one embodiment, the wind vector data includes wind speed data and wind direction data.

[0144] In one embodiment, the flame tilt angle is determined based on the following formula:

[0145] Where α is the flame tilt angle, in degrees; θ jv R is the angle between the wind direction and the axis of the leak, in degrees. w R is the ratio of wind speed to jet velocity. i (L b0 ) represents the Richardson number of a flame in still air.

[0146] In one embodiment, the flame lift height is determined based on the following formula:

[0147] Where b is the flame lift height, in meters; L b R represents the length of the flame under windy conditions, in meters (m). w α is the ratio of wind speed to jet speed; α is the flame tilt angle in degrees.

[0148] In one embodiment, the flame centerline length is determined based on the following formula:

[0149] Where R1 is the flame centerline length in meters (m); b is the flame lift height in meters (m); L b α represents the flame length under windy conditions, in meters; α represents the flame tilt angle, in degrees.

[0150] In one embodiment, establishing an initial thermal radiation field prediction model based on the flame morphology parameters includes:

[0151] The combustion energy of the flame per unit time is determined based on the leakage flow rate and the heat of combustion of the leaked material.

[0152] The linear density heat load is determined based on the combustion energy of the flame per unit time and the flame centerline length.

[0153] An initial thermal radiation field prediction model is established based on linear density heat load, flame tilt angle, flame lift height, and flame centerline length.

[0154] In one embodiment, the combustion energy of the flame per unit time is determined based on the following formula: Q = mΔH;

[0155] Where Q is the combustion energy of the flame per unit time, in J / s; m is the leakage flow rate, in kg / s; and ΔH is the heat of combustion of the leaked substance, in J / kg.

[0156] In one embodiment, the linear density heat load is determined based on the following formula:

[0157] Where q′ is the linear density heat load, in J / (s·m); R1 is the flame centerline length, in m; and Q is the combustion energy of the flame per unit time, in J / s.

[0158] In one embodiment, the initial thermal radiation field prediction model is shown in the following formula:

[0159] Where q(x0,y0,z0) is the thermal radiation intensity at any point, with units of W / m². 2 ξ represents combustion efficiency; τ is the thermal radiation efficiency; q′ is the atmospheric transmittance; α is the linear density heat load in J / (s·m); α is the flame tilt angle in degrees; φ is the flame nozzle height in meters; R1 is the flame centerline length in meters; and b is the flame lift height in meters.

[0160] In one embodiment, optimizing the initial thermal radiation field prediction model based on hydrodynamic thermal radiation field simulation data and the physical field data includes:

[0161] The jet flame around the well was simulated using a computational fluid dynamics analysis system to obtain simulation data of the hydrodynamic thermal radiation field;

[0162] The initial thermal radiation field prediction model is optimized based on the fluid dynamics thermal radiation field simulation data and the physical field data.

[0163] In one embodiment, the target thermal radiation field prediction model is shown in the following formula:

[0164] In the above formula,

[0165] Where q(x0,y0,z0) is the thermal radiation intensity at any point, with units of W / m². 2 ;u w Wind speed, in m / s; u j α is the ejection velocity from the leak, in m / s; α is the flame tilt angle, in degrees; R1 is the flame centerline length, in m; q′ is the linear density heat load, in J / (s·m); b is the flame lift height, in m; z a0 D is the height of the flame nozzle, in meters (m). s d is the effective diameter of the flame source, in meters (m). j ρ is the diameter of the leak outlet, in meters (m); j The density of the jet fluid is expressed in kg / m³. 3 ;ρ air Air density, unit: kg / m³ 3c1, c2, and c3 are all optimization parameters; R w R is the ratio of wind speed to jet velocity. i (L b0 (m1) represents the Richardson number of a flame in still air; m2 is 0.37 (m / s); m3 is 1 (m / s); m4 is 1 (m / s); m5 is 1 (m / s).

[0166] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0167] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in one or more flowchart illustrations and / or one or more block diagrams.

[0168] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams.

[0169] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide steps for implementing the functions specified in one or more flowcharts and / or one or more block diagrams.

[0170] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0171] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0172] Computer-readable media include both permanent and non-permanent, removable and non-removable media, which can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0173] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0174] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for predicting physical fields, characterized in that, The prediction method includes: Acquire physical field data around the well, including thermal radiation intensity data, temperature field data, and wind vector data; Flame morphology parameters are determined based on flame analysis theory. These parameters include flame tilt angle, flame lift height, and flame centerline length. An initial thermal radiation field prediction model is established based on these parameters. The initial thermal radiation field prediction model is then optimized based on hydrodynamic thermal radiation field simulation data and the physical field data to obtain a target thermal radiation field prediction model. Machine learning is performed based on fluid dynamics temperature field simulation data to obtain a target temperature field prediction model; Machine learning is performed based on fluid velocity field simulation data from fluid dynamics to obtain a prediction model for the target fluid velocity field. The well perimeter physical field is predicted based on the target thermal radiation field prediction model, the target thermal radiation field prediction model, and the target fluid velocity field prediction model.

2. The physical field prediction method according to claim 1, characterized in that, The wind vector data includes wind speed data and wind direction data.

3. The physical field prediction method according to claim 1, characterized in that, The flame tilt angle is determined based on the following formula: where a is the flame tilt angle in degrees; θ jv is the angle between the wind direction and the axis of the leak in degrees; R w is the ratio of wind speed to jet velocity; R i (L b0 ) is the flame Richardson number in still air.

4. The physical field prediction method according to claim 3, characterized in that, The flame lift height is determined based on the following formula: where b is the flame lift-off height, in meters; L b is the flame length in the wind, in meters; R w is the ratio of wind speed to injection velocity; and a is the flame tilt angle, in degrees.

5. The physical field prediction method according to claim 4, characterized in that, The flame centerline length is determined based on the following formula: Wherein, R1 is the flame center line length, unit is m; b is the flame push height, unit is m; L b is the flame length under wind condition, unit is m; α is the flame inclination angle, unit is degree.

6. The physical field prediction method according to claim 1, characterized in that, The step of establishing an initial thermal radiation field prediction model based on the flame morphology parameters includes: The combustion energy of the flame per unit time is determined based on the leakage flow rate and the heat of combustion of the leaked material. The linear density heat load is determined based on the combustion energy of the flame per unit time and the flame centerline length. An initial thermal radiation field prediction model is established based on linear density heat load, flame tilt angle, flame lift height, and flame centerline length.

7. The physical field prediction method according to claim 6, characterized in that, The combustion energy of a flame per unit time is determined based on the following formula: Q = mΔH; Where Q is the combustion energy of the flame per unit time, in J / s; m is the leakage flow rate, in kg / s; and ΔH is the heat of combustion of the leaked substance, in J / kg.

8. The physical field prediction method according to claim 7, characterized in that, The linear density heat load is determined based on the following formula: Where q′ is the linear density heat load, in J / (s·m); R1 is the flame centerline length, in m; and Q is the combustion energy of the flame per unit time, in J / s.

9. The physical field prediction method according to claim 8, characterized in that, The initial thermal radiation field prediction model is shown in the following formula: Where q(x0,y0,z0) is the thermal radiation intensity at any point, with units of W / m². 2 ξ represents combustion efficiency; is the thermal radiation efficiency; τ is the atmospheric transmissivity; q' is the linear heat flux, in J / (s-m); a is the flame tilt angle, in degrees; z a0 is the flame nozzle height, in m; R1 is the flame centerline length, in m; b is the flame lift height, in m.

10. The physical field prediction method according to claim 1, characterized in that, The optimization of the initial thermal radiation field prediction model based on hydrodynamic thermal radiation field simulation data and the physical field data includes: The jet flame around the well was simulated using a computational fluid dynamics analysis system to obtain simulation data of the hydrodynamic thermal radiation field; The initial thermal radiation field prediction model is optimized based on the fluid dynamics thermal radiation field simulation data and the physical field data.

11. The physical field prediction method according to claim 10, characterized in that, The target thermal radiation field prediction model is shown in the following formula: In the above formula, where q(x0, y0, z0) is the heat radiation intensity of any point, with the unit of W / m 2 ; u w is the wind speed, with the unit of m / s; u j is the jet velocity of the leakage port, with the unit of m / s; a is the flame inclination angle, with the unit of degree; R1 is the length of the flame center line, with the unit of m; q' is the linear density heat load, with the unit of J / (s·m); b is the flame push height, with the unit of m; z a0 is the height of the flame spout, with the unit of m; D s is the effective source diameter of the flame, with the unit of m; d j is the diameter of the leakage port, with the unit of m; p j is the jet fluid density, with the unit of kg / m 3 ; p air is the air density, with the unit of kg / m 3 ; c1, c2 and c3 are all optimization parameters; R w is the ratio of the wind speed to the jet velocity; R i (L b0 ) is the flame Richardson number in static air; m1 is 0.37, with the unit of m / s; m2 is 206, with the unit of m / s; m3 is 1, with the unit of m / s; m4 is 1, with the unit of m / s; m5 is 1, with the unit of m / s.

12. A physical field prediction device, characterized in that, include: The acquisition module is used to acquire physical field data around the well, including thermal radiation intensity data, temperature field data, and wind vector data. The thermal radiation field prediction model construction module is used to determine the flame morphology parameters based on flame analytical theory. The flame morphology parameters include the flame tilt angle, flame lift height and flame centerline length. An initial thermal radiation field prediction model is established based on the flame morphology parameters. The initial thermal radiation field prediction model is optimized based on the fluid dynamics thermal radiation field simulation data and the physical field data to obtain the target thermal radiation field prediction model. The temperature field prediction model building module is used to perform machine learning based on fluid dynamics temperature field simulation data to obtain the target temperature field prediction model. The fluid velocity field prediction model building module is used to perform machine learning based on fluid dynamics fluid velocity field simulation data to obtain a target fluid velocity field prediction model. The prediction module is used to predict the well perimeter physical field based on the target thermal radiation field prediction model, the target thermal radiation field prediction model, and the target fluid velocity field prediction model.

13. A physical field prediction system, characterized in that, The prediction system includes a measurement unit and the physical field prediction device as described in claim 12; The measurement unit includes a heat flux measuring instrument, an infrared thermal imager, and a wind vector measuring instrument. The heat flux measuring instrument is used to measure the thermal radiation intensity data around the well, the infrared thermal imager is used to measure the temperature field data around the well, and the wind vector measuring instrument is used to measure the wind vector data around the well.

14. A processor, characterized in that, It is configured to perform the physical field prediction method according to any one of claims 1 to 11.

15. A machine-readable storage medium storing instructions thereon, characterized in that, When executed by a processor, this instruction causes the processor to be configured to perform the physical field prediction method according to any one of claims 1 to 11.

Images