Method, device and equipment for predicting heat treatment parameters of large-thickness-wall welded pipes

Abstract

The application relates to a large-thick-wall welded pipe heat treatment parameter prediction method, device and equipment, relates to the technical field of data analysis, and aims to solve the problem that heat treatment parameters cannot be accurately determined, multiple heat treatments are required to make residual stress reach the standard, and the heat treatment efficiency is low. The method comprises the following steps: according to the thermal physical performance parameters, thermal boundary conditions and electromagnetic distribution of an induction heating coil of a large-thick-wall welded pipe, the multi-physical field coupling relationship between the temperature field, stress field and electromagnetic field of the large-thick-wall welded pipe in a heat treatment process is determined; according to the multi-physical field coupling relationship, different candidate residual stress parameters generated by the large-thick-wall welded pipe in the heat treatment process under different heat treatment parameters are determined; and according to the candidate heating width, candidate holding width and candidate residual stress parameters, the correlation between the heating width, holding width and residual stress parameters is determined, so that the target heating width and target holding width meeting the target residual stress parameters are determined.

Description

Technical Field

[0001] This application relates to the field of data analysis technology, and in particular to methods, apparatus and equipment for predicting heat treatment parameters of thick-walled welded pipes. Background Technology

[0002] G115 steel is a new type of martensitic heat-resistant steel, mainly used in thick-walled, high-temperature components such as main steam pipelines and high-temperature reheat steam pipelines in ultra-supercritical units through fusion welding. After welding, this steel requires appropriate heat treatment to eliminate residual welding stress, improve microstructure stability, and enhance the overall mechanical properties of the welded joint. With the increase in steam temperature and pressure in power units, the wall thickness of G115 thick-walled welded pipelines is increasing, leading to greater residual welding stress after heat treatment and subsequent cracking during use. Therefore, studying the influence of heat treatment parameters on residual stress is crucial for controlling residual welding stress and developing appropriate heat treatment processes.

[0003] Research has found that considering only the influence of a heat source on pipeline stress leads to poor accuracy of heat treatment parameters, making it impossible to eliminate residual stress after welding in one go. This results in G115 thick-walled welded pipelines having excessive residual stress or failing to meet technical requirements, necessitating repeated heat treatments, which leads to low heat treatment efficiency. Summary of the Invention

[0004] This invention provides a method, apparatus, and equipment for predicting heat treatment parameters of thick-walled welded pipes, to at least solve the problem of low heat treatment efficiency caused by the inability to accurately determine heat treatment parameters and the need for multiple heat treatments to achieve the required residual stress. The technical solution of this invention is as follows.

[0005] According to a first aspect of the present invention, a method for predicting heat treatment parameters of a thick-walled welded pipe is provided. The method includes: determining the multi-physics coupling relationship between the temperature field, stress field, and electromagnetic field of the thick-walled welded pipe during heat treatment based on the thermophysical performance parameters, thermal boundary conditions, and electromagnetic distribution of the induction heating coil; determining different candidate residual stress parameters generated in the thick-walled welded pipe during heat treatment under different heat treatment parameters based on the multi-physics coupling relationship; the heat treatment process characterizing the entire process of the thick-walled welded pipe passing through an induction heating stage, a holding stage, and a cooling stage; the heat treatment parameters include candidate heating width and candidate holding width; the candidate heating width characterizing the width of the induction heating region during heat treatment and interacting with the electromagnetic distribution of the induction heating coil; the candidate holding width characterizing the width of the holding region during heat treatment and interacting with the thermal boundary conditions of the thick-walled welded pipe; determining the correlation between the heating width, holding width, and residual stress parameters based on the candidate heating width, candidate holding width, and determined candidate residual stress parameters; and determining the target heating width and target holding width that satisfy the target residual stress parameters based on the correlation.

[0006] As one approach, before determining the multi-physics coupling relationship between the temperature field, stress field, and electromagnetic field during the heat treatment of a thick-walled welded pipe, the method further includes: determining the pipe volume distribution heat flux density of the thick-walled welded pipe based on the total heat power of the welding power source and the welding heat effect coefficient; determining the welding temperature field and welding stress field distribution during the welding process based on the pipe volume distribution heat flux density and the coupling relationship between the temperature field and stress field; and determining the welding residual stress parameters based on the welding temperature field and welding stress field distribution, wherein the welding residual stress parameters characterize the residual stress generated by the temperature gradient during the cooling process of the thick-walled welded pipe from high-temperature welding.

[0007] In this embodiment, by determining the heat flux density of the pipe volume distribution of the thick-walled welded pipe, the strain of the temperature field and stress field of the thick-walled welded pipe during the welding process is simulated, and the welding residual stress parameters generated during the welding process are accurately quantified.

[0008] As one way to achieve this, thermophysical performance parameters include the metal's density, specific heat capacity, electrical conductivity, magnetic permeability, elastic modulus, plasticity curve, thermal conductivity, and coefficient of thermal expansion at different temperatures.

[0009] Based on the thermophysical performance parameters, thermal boundary conditions, and electromagnetic distribution of the induction heating coil of the thick-walled welded pipeline, the multi-physics coupling relationship between the temperature field, stress field, and electromagnetic field during the heat treatment process is determined. This includes: determining Joule heating based on conductivity, permeability, and the electromagnetic distribution of the induction heating coil; determining the heat source intensity during heat conduction based on Joule heating; determining the coupling relationship between the electromagnetic field and the temperature field based on the correlation between Joule heating and heat source intensity; determining the coupling relationship between the temperature field and the stress field based on the correlation between the elastic modulus, plasticity curve, and coefficient of thermal expansion of the thick-walled welded pipeline and creep stress; and determining the multi-physics coupling relationship based on the coupling relationship between the electromagnetic field and the temperature field, and the coupling relationship between the temperature field and the stress field.

[0010] In this embodiment, induction heating coils are used for induction heating. The coupling relationship between the electromagnetic field and the temperature field is determined, and the heat source intensity of induction heating is accurately obtained. Based on this, according to the coupling relationship between the temperature field and the stress field, the stress influence of the heat source generated by induction heating on the thick-walled welded pipe is accurately determined. Therefore, by using the thermophysical performance parameters, thermal boundary conditions, and electromagnetic distribution of the induction heating coils of the thick-walled welded pipe, the multi-physics coupling relationship between the temperature field, stress field, and electromagnetic field during the heat treatment of the thick-walled welded pipe is determined. This provides a more accurate simulation environment for subsequently determining the parameters for eliminating welding residual stress during the heat treatment process.

[0011] As one implementation method, based on the multi-physics coupling relationship, different candidate residual stress parameters generated during the heat treatment process of large and thick-walled welded pipes under different heat treatment parameters are determined. Specifically, this includes: determining the steady-state temperature field during the induction heating stage of the heat treatment process under the heating width based on the coupling relationship between the electromagnetic field and the temperature field; determining the thermal stress corresponding to the steady-state temperature field based on the coupling relationship between the temperature field and the stress field; determining the creep strain rate during the heat holding stage of the heat treatment process under the heat holding width based on the thermal boundary conditions, thermal stress, and welding residual stress parameters; determining the residual stress field generated during the cooling stage of the heat treatment process based on the creep strain rate; and identifying stresses in the residual stress field that are higher than a threshold as candidate residual stress parameters.

[0012] In this embodiment, by establishing the multi-physics coupling relationship between the temperature field, stress field and electromagnetic field, the entire heat treatment process of a large, thick-walled welded pipe from the induction heating stage to the heat preservation stage to the cooling stage can be simulated more realistically, thereby accurately predicting the distribution and magnitude of residual stress parameters.

[0013] As one approach, a thermo-mechanical coupled finite element analysis model is established. Based on the multi-physics coupling relationship, the thermo-mechanical coupled finite element analysis model determines different candidate residual stress parameters generated during the heat treatment process of thick-walled welded pipes under different heat treatment parameters. Based on the ratio of the outer diameter to the wall thickness of different thick-walled welded pipes, multiple sets of candidate heating widths and candidate insulation widths are determined. The candidate heating widths and candidate insulation widths are input into the thermo-mechanical coupled finite element analysis model to obtain the candidate residual stress parameters.

[0014] In this embodiment, the residual stress parameters after heat treatment under preset heat treatment parameters are quickly and accurately determined. Due to the special nature of the thick-walled welded pipe structure, it is not possible to repeatedly conduct heat treatment experiments on the thick-walled welded pipe, and the prediction model lacks data support. Therefore, the established thermo-mechanical coupled finite element analysis model is used to simulate the residual stress parameters corresponding to multiple sets of different heat treatment parameters, providing a large amount of accurate data for the subsequent prediction process.

[0015] As one implementation method, multiple sets of candidate heating widths and candidate insulation widths are determined based on the ratio of the outer diameter to the wall thickness of different thick-walled welded pipes. Specifically, this includes: if the ratio is detected to be less than or equal to a preset ratio, the corresponding candidate heating width is set to the first product of a first multiple and the wall thickness; and the corresponding candidate insulation width is set to the second product of a second multiple and the wall thickness; the difference between the second multiple and the first multiple is greater than or equal to 2; if the ratio is detected to be greater than a preset ratio, the candidate heating width is set to the third product of a third multiple and the wall thickness; and the corresponding candidate insulation width is set to the fourth product of a fourth multiple and the wall thickness; the difference between the fourth multiple and the third multiple is greater than or equal to 2; and the first multiple is less than the third multiple.

[0016] As one implementation method, the target heating width and target insulation width that satisfy the target residual stress parameters are determined based on the correlation relationship. This includes: constructing a preset model, which characterizes the correlation between the heating width and insulation width and the residual stress parameters; training the preset model based on multiple sets of candidate heating widths and candidate insulation widths and their corresponding candidate residual stress parameters to obtain a target prediction model; and inputting the target residual stress parameters into the target prediction model to obtain the target heating width and target insulation width.

[0017] In this embodiment, a prediction model is used to learn the complex relationship between the heating width, the insulation width and the residual stress parameters, and to accurately predict the target heating width and the target insulation width that meet the target prediction model. Based on the target heating width and the target insulation width, the thick-walled welded pipe is heat-treated, thereby effectively improving the efficiency of heat treatment.

[0018] As one implementation method, the target heating width and target insulation width are input into the thermo-mechanical coupled finite element analysis model to obtain the verification residual stress parameters; the verification residual stress parameters are compared with the target residual stress parameters; when the verification residual stress parameters are consistent with the target residual stress parameters, it is determined that the target heating width and target insulation width meet the requirements; when the verification residual stress parameters are inconsistent with the target residual stress parameters, the parameters of the thermo-mechanical coupled finite element analysis model are automatically adjusted to generate multiple sets of new candidate heating widths and new candidate insulation widths and corresponding new candidate residual stress parameters, thereby adjusting the target prediction model.

[0019] In this implementation, the accuracy of the prediction results is improved by inputting the prediction results into a thermo-coupled finite element analysis model for reverse verification of the data.

[0020] According to a second aspect of the present invention, a device for predicting heat treatment parameters of a large, thick-walled welded pipe is provided, the device comprising:

[0021] The analysis unit is configured to determine the multi-physics coupling relationship between the temperature field, stress field, and electromagnetic field of a thick-walled welded pipe during heat treatment, based on the thermophysical performance parameters, thermal boundary conditions, and electromagnetic distribution of the induction heating coil. Based on this multi-physics coupling relationship, it determines different candidate residual stress parameters generated during heat treatment under different heat treatment parameters. The heat treatment process characterizes the entire process of the thick-walled welded pipe through the induction heating stage, the holding stage, and the cooling stage. Heat treatment parameters include candidate heating width and candidate holding width. The candidate heating width characterizes the width of the induction heating region during heat treatment and interacts with the electromagnetic distribution of the induction heating coil. The candidate holding width characterizes the width of the holding region during heat treatment and interacts with the thermal boundary conditions of the thick-walled welded pipe. Based on the candidate heating width, candidate holding width, and determined candidate residual stress parameters, the correlation between the heating width, holding width, and residual stress parameters is determined.

[0022] The determining unit is configured to determine the target heating width and target insulation width that satisfy the target residual stress parameters based on the correlation relationship.

[0023] According to a third aspect of the present invention, a system for predicting heat treatment parameters of thick-walled welded pipes is provided, the system being configured to perform a method for predicting heat treatment parameters of thick-walled welded pipes as described in the first aspect and any possible implementation thereof.

[0024] According to a fourth aspect of the present invention, a heat treatment parameter prediction device for thick-walled welded pipes is provided, the device being configured to perform a heat treatment parameter prediction method for thick-walled welded pipes as described in the first aspect and any possible implementation thereof.

[0025] According to a fifth aspect of the present invention, a computer-readable storage medium is provided, on which instructions are stored, such that when the instructions in the computer-readable storage medium are executed by a processor of a heat treatment parameter prediction device for thick-walled welded pipes, the heat treatment parameter prediction device for thick-walled welded pipes is able to perform a heat treatment parameter prediction method for thick-walled welded pipes as described in the first aspect and any possible implementation thereof.

[0026] According to a sixth aspect of the present disclosure, a computer program product is provided, the computer program product including computer instructions, which, when the computer instructions are run on a heat treatment parameter prediction device for thick-walled welded pipes, cause the heat treatment parameter prediction device for thick-walled welded pipes to execute the heat treatment parameter prediction method for thick-walled welded pipes described in the first aspect and any possible implementation thereof.

[0027] The technical solutions provided by the embodiments of the present invention offer at least the following beneficial effects: Based on the multi-physics coupling relationship of temperature field, stress field, and electromagnetic field, the entire heat treatment process of a large, thick-walled welded pipe, from induction heating stage to heat preservation stage and then to cooling stage, is simulated more realistically, and the residual stress parameters after heat treatment are accurately determined. Specifically, by understanding the thermal boundary conditions of the large, thick-walled welded pipe and the electromagnetic distribution of the induction heating coil, the heat treatment parameters directly affecting the magnitude of the residual stress parameters are clarified, including the heating width and heat preservation width. Through electromagnetic induction heating, the heating width is controlled to uniformly heat the welded pipe, and by setting the heat preservation width, the relaxation process of the welded pipe's residual stress is ensured to proceed fully and uniformly within a uniform high-temperature zone, avoiding rapid cooling at the edges that generates new stress. Based on this, the residual stress parameters are solved in reverse by adjusting the heating width and heat preservation width, thereby reducing the number of trial and error attempts during heat treatment in the production process; and based on the correlation between the heating width, heat preservation width, and residual stress parameters, a predictive model is established to efficiently determine the target heating width and target heat preservation width that meet the target residual stress parameters, improving heat treatment efficiency.

[0028] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0029] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0030] Figure 1 This is a schematic diagram of a heat treatment parameter prediction system for a large, thick-walled welded pipe according to an exemplary embodiment;

[0031] Figure 2 This is a flowchart illustrating a method for predicting heat treatment parameters of a large, thick-walled welded pipe according to an exemplary embodiment;

[0032] Figure 3 This is a temperature distribution diagram of a pipe cross-section during a welding process, according to an exemplary embodiment.

[0033] Figure 4 This is a temperature distribution diagram of a pipe cross-section during the final welding process, according to an exemplary embodiment.

[0034] Figure 5 This is a residual stress distribution diagram shown after welding is completed, according to an exemplary embodiment;

[0035] Figure 6 This is a magnetic flux distribution diagram during induction heating according to an exemplary embodiment;

[0036] Figure 7 This is a residual stress field of a heat-treated, thick-walled welded pipe, as illustrated in an exemplary embodiment.

[0037] Figure 8 This is a residual stress diagram corresponding to the heating width and the heat preservation width, according to an exemplary embodiment.

[0038] Figure 9 This is a graph illustrating the stress variation perpendicular to the welding direction during an optimized heating width process, according to an exemplary embodiment.

[0039] Figure 10 This is a block diagram illustrating a heat treatment parameter prediction device for a large, thick-walled welded pipe according to an exemplary embodiment;

[0040] Figure 11 This is a schematic diagram of a heat treatment parameter prediction device for a large, thick-walled welded pipe according to an exemplary embodiment. Detailed Implementation

[0041] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0042] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0043] Before providing a detailed introduction to the method for predicting heat treatment parameters of thick-walled welded pipes provided in the embodiments of this application, we will first briefly introduce the application scenarios and implementation environment involved in the embodiments of this application.

[0044] Research has shown that compared to existing flexible ceramic resistance heating, electromagnetic induction heating of G115 thick-walled welded pipes can significantly reduce residual stress, decrease cracking tendency, and reduce microstructural inhomogeneity. Electromagnetic induction heating also offers significant advantages in heating speed, temperature field uniformity, and environmental friendliness. Furthermore, in actual production, the thermal simulation for eliminating residual stress only considered the influence of the heating source on pipe stress, neglecting the combined effects of welding and heating heat sources on pipe stress during welding, and failing to fully consider the coupling relationships between the electromagnetic field, temperature field, and stress field during the electromagnetic induction heating process.

[0045] Currently, existing heat treatment processes cannot accurately determine heat treatment parameters, leading to situations where residual stress in G115 welded thick-walled pipes exceeds the standard or fails to meet technical requirements during the heat treatment process. This necessitates repeated heat treatments, resulting in a significant waste of electrical energy and labor costs.

[0046] To address the aforementioned issues, this application proposes a method for predicting heat treatment parameters for thick-walled welded pipes. This method utilizes electromagnetic induction coils for induction heating and considers the multi-physics coupling relationship between temperature, stress, and electromagnetic fields during the induction heating heat treatment process. This allows for a more realistic simulation of the entire heat treatment process for thick-walled welded pipes, from induction heating to holding and cooling, accurately determining the residual stress parameters after heat treatment. Specifically, by understanding the thermal boundary conditions of the thick-walled welded pipe and the electromagnetic distribution of the induction heating coil, the heat treatment parameters directly affecting the magnitude of residual stress parameters are identified, including the heating width and holding width. Therefore, by adjusting the heating and holding widths, the residual stress parameters are adjusted in reverse, reducing the number of trial-and-error steps in heat treatment during production. Furthermore, based on the correlation between the heating and holding widths and the residual stress parameters, the target heating and holding widths that satisfy the target residual stress parameters are efficiently determined, improving heat treatment efficiency and achieving economic benefits.

[0047] Secondly, the implementation architecture involved in this application will be briefly introduced below.

[0048] Figure 1 This is a schematic diagram of a heat treatment parameter prediction system for large, thick-walled welded pipes provided in this application. Figure 1 As shown, the heat treatment parameter prediction system for large thick-walled welded pipes includes a thermo-mechanical coupling analysis module 101 and a heat treatment parameter prediction module 102.

[0049] The thermo-coupling analysis module 101 and the heat treatment parameter prediction module 102 are connected via communication.

[0050] The thermo-coupling analysis module 101 is configured to establish a thermo-coupling finite element analysis model. The thermo-coupling finite element analysis model determines different candidate residual stress parameters generated during the heat treatment of thick-walled welded pipes under different heat treatment parameters based on the multi-physics coupling relationship. Based on the ratio of the outer diameter to the wall thickness of different thick-walled welded pipes, multiple sets of candidate heating widths and candidate insulation widths are determined. The candidate heating widths and candidate insulation widths are input into the thermo-coupling finite element analysis model to obtain the candidate residual stress parameters.

[0051] The heat treatment parameter prediction module 102 is configured to determine the target heating width and target insulation width that satisfy the target residual stress parameters based on the correlation between the heating width and insulation width and the residual stress parameters. This includes: constructing a preset model, which characterizes the correlation between the heating width and insulation width and the residual stress parameters; training the preset model based on multiple sets of candidate heating widths and candidate insulation widths and their corresponding candidate residual stress parameters to obtain a target prediction model; and inputting the target residual stress parameters into the target prediction model to obtain the target heating width and target insulation width.

[0052] For ease of understanding, the following section provides a detailed description of the method for predicting heat treatment parameters for thick-walled welded pipes provided in this application, in conjunction with the accompanying drawings.

[0053] Figure 2 This is a flowchart illustrating a method for predicting heat treatment parameters of a large, thick-walled welded pipe according to an exemplary embodiment, such as... Figure 2 As shown, the method for predicting heat treatment parameters of large, thick-walled welded pipes includes the following steps.

[0054] S21. Based on the thermophysical performance parameters, thermal boundary conditions, and electromagnetic distribution of the induction heating coil of the thick-walled welded pipe, determine the multi-physics coupling relationship between the temperature field, stress field, and electromagnetic field during the heat treatment process of the thick-walled welded pipe.

[0055] The thermophysical performance parameters include the density, specific heat capacity, electrical conductivity, magnetic permeability, elastic modulus, plasticity curve, thermal conductivity, and coefficient of thermal expansion of the selected metal at different temperatures.

[0056] Thermal boundary conditions characterize the heat transfer boundary defined by applying convective heat transfer coefficients (convection coefficients with air) and thermal radiation parameters (surface emissivity) to all the outer surfaces of a thick-walled welded pipe.

[0057] To more realistically reflect the entire process of generating welding residual stress during the welding of thick-walled G115 welded pipes and eliminating welding residual stress parameters through heat treatment, the process is implemented based on the following three points.

[0058] A thermo-mechanical coupled finite element analysis model of a thick-walled G115 welded pipe was established. Within this model, a model of the thick-walled G115 welded pipe was created to simulate the welding residual stress parameters generated during the welding process. Furthermore, the heat treatment process of the welded pipe was simulated based on the multi-physics coupling relationship between the temperature field, stress field, and electromagnetic field. In this way, the welding residual stress parameters and the residual stress parameters obtained after eliminating the welding residual stress parameters through the heat treatment process were obtained, respectively.

[0059] First, a model of a thick-walled G115 welded pipe is established based on the following two specific procedures.

[0060] First, a model of a thick-walled G115 welded pipe was established using finite element software.

[0061] The diameter of the thick-walled G115 welded pipe is set to Φ590. 70mm. Eight-node hexahedral reduced integral elements were used to mesh the thick-walled G115 welded pipe. The mesh was further subdivided near the weld seam, and the seed type was set to offset to achieve a smooth transition from fine to coarse meshes. Specifically, a boundary layer mesh with a thickness of 15mm, 3 layers, and a stretch factor of 1.2 was created for the pipe model to capture the skin effect generated by induction heating. This model has 6126 mesh nodes and 31686 mesh elements. This provides an accurate basis for subsequently determining the location of the heat source.

[0062] The air properties and range around the thick-walled welded pipe were determined, as well as the thermophysical properties of the G115 material as a function of temperature.

[0063] Secondly, thermal and mechanical boundary conditions are set for thick-walled welded pipes.

[0064] Thermal boundary conditions are set, with the weld zone temperature set to ambient temperature. The ambient temperature is uniformly set to room temperature, and convective heat transfer coefficients and thermal radiation parameters are applied to all outer surfaces of the welded pipe to define heat exchange. The ambient temperature is determined to be 20℃, and the convective heat transfer coefficient is set to 50. The surface emissivity is set to 0.8.

[0065] The mechanical boundary conditions involve selecting three non-collinear nodes on the outer surface, completely restricting their translational degrees of freedom in the X, Y, and Z directions. This prevents the rigid body movement of the thick-walled welded pipe as a whole, while allowing the pipe itself to undergo thermal expansion and elasto-plastic deformation.

[0066] Secondly, based on the coupling relationship between the temperature field and the stress field, the welding residual stress parameters of the thick-walled welded pipe are determined.

[0067] Specifically, the heat flux density of the pipe volume distribution in the thick-walled welded pipe is determined based on the total heat power of the welding power source and the welding heat effect coefficient; based on the heat flux density of the pipe volume distribution, the welding temperature field and welding stress field distribution during the welding process are determined according to the coupling relationship between the temperature field and the stress field; and the welding residual stress parameters are determined based on the welding temperature field and welding stress field distribution.

[0068] Among them, the welding residual stress parameter characterizes the residual stress generated by the temperature gradient during the cooling process of a large, thick-walled welded pipe from high-temperature welding.

[0069] In one embodiment, the volumetric heat flux density of the thick-walled G115 welded pipe is determined according to the conical volumetric heat source equation.

[0070] Based on the total heat power of the welding power source and the welding heat effect coefficient, the heat flux density of the pipe volume distribution of the thick-walled welded pipe is determined by the following formula (1).

[0071] (1).

[0072] Where q(x,y,z) is the volumetric heat flux density at spatial coordinates (x,y,z); η is the welding thermal efficiency coefficient, reflecting the proportion of heat power actually absorbed by the welded pipe material to the input power; Q is the total heat power output by the welding power source; R is the projection radius of the welding heat source at the surface (z=0); and H is the heating influence depth of the heat source at the surface (z=0). It is a linear factor, reflecting the attenuation of the heat source along the depth direction; and it only satisfies this condition when the point (x,y,z) simultaneously satisfies this condition. and Only when the heat flux density is non-zero can it exist.

[0073] Based on the conical volume heat source equation for thick-walled welded pipes, a three-dimensional thermo-mechanical coupling numerical simulation is performed on the circumferential welding path based on the heat transfer differential equation. According to the three-dimensional thermo-mechanical coupling numerical simulation, the complex interaction between heat and force during the welding process is realistically reproduced. The historical distribution of temperature field and stress-strain field of thick-walled welded pipes during the entire welding process is dynamically and accurately obtained. Based on the distribution of welding temperature field and welding stress field, the welding residual stress parameters are determined.

[0074] For example, based on the above-mentioned model of a thick-walled G115 welded pipe, the thermal load of the welded pipe during the welding heating process is simulated.

[0075] Thermal load characterizes the localized rapid heating and cooling of the material by a highly concentrated heat source (such as an electric arc) during welding, resulting in uneven expansion and contraction of the material and thus internal stress.

[0076] A time-varying volumetric heat flux is applied to the entire pipeline; this heat load is implemented by a user-defined subroutine. The DFLUX subroutine, edited in Fortran, is configured based on the conical volumetric heat source equation for thick-walled welded pipelines, setting the power Q = 12000 W, thermal efficiency η = 0.8, cone apex radius R = 4 mm, and cone height H = 6 mm. The welding process is numerically simulated using finite element method (FEM) software, which performs heat transfer analysis based on differential equations for heat transfer control. The distributions of the welding temperature and stress fields are determined based on the coupling between the temperature and stress fields.

[0077] The highest temperature of the welded joint was 2209℃, and the temperature along the weld penetration direction also exceeded the melting point of G115 steel. Figure 3 and Figure 4 The temperature distribution diagrams of the pipe cross-section during the welding process and the pipe cross-section during the final welding process shown indicate that the temperature peak occurs in the central region of the weld.

[0078] The welding residual stress parameters were determined based on the coupling relationship between the welding temperature field and the welding stress field. The residual stress distribution upon completion of welding is as follows: Figure 5 As shown, the residual stress in the heat-affected zone (HAZ) is the highest, mainly because this zone experiences the most severe temperature gradient during the cooling process: from the edge of the molten pool to the base material, the cooling rate from melting to near room temperature is the fastest, leading to the concentration of thermal expansion and contraction stress, which ultimately forms the peak residual stress in the HAZ region.

[0079] Understandably, the stress field arises from uneven temperature distribution. Materials expand when heated and contract when cooled. If the temperature of the entire part is uniform, it will only expand and contract freely without generating stress. However, welding creates an extremely uneven temperature field. Local areas are intensely heated and expand, which is constrained by the surrounding cold material, thus generating compressive stress. Subsequently, when this area cools and contracts, it is held back by the surrounding material, generating tensile stress. Therefore, thick-walled welded pipes generate residual welding stress after welding.

[0080] Finally, based on the thermophysical properties of the thick-walled welded pipe and the electromagnetic distribution of the induction heating coil, the multi-physical coupling relationship in the heat treatment process is determined.

[0081] The multi-physical coupling relationships during heat treatment are mainly manifested in the interaction between the electromagnetic field and the temperature field, and the interaction between the temperature field and the stress field. Heating a thick-walled welded pipe using the electromagnetic heating principle of an induction heating coil generates a coupling relationship between the electromagnetic field and the temperature field. After heating, both heating and cooling of the thick-walled welded pipe affect the stress changes in the pipe material, resulting in a coupling relationship between the temperature field and the stress field. Therefore, accurately determining the multi-physical coupling relationships of thick-walled welded pipes during heat treatment provides strong support for obtaining accurate candidate residual stress parameters.

[0082] Specifically, based on the thermophysical performance parameters, thermal boundary conditions, and electromagnetic distribution of the induction heating coil of the thick-walled welded pipe, the multi-physics coupling relationship between the temperature field, stress field, and electromagnetic field during the heat treatment of the thick-walled welded pipe is determined. This includes: determining Joule heating based on conductivity, permeability, and the electromagnetic distribution of the induction heating coil; determining the heat source intensity during heat conduction based on Joule heating; determining the coupling relationship between the electromagnetic field and the temperature field based on the correlation between Joule heating and heat source intensity; determining the coupling relationship between the temperature field and the stress field based on the correlation between the elastic modulus, plasticity curve, and coefficient of thermal expansion of the thick-walled welded pipe and creep stress; and determining the multi-physics coupling relationship based on the coupling relationship between the electromagnetic field and the temperature field, and the coupling relationship between the temperature field and the stress field.

[0083] In this method, induction heating is used to heat large, thick-walled welded pipes. The electromagnetic distribution of the induction heating coil is determined by the number of turns, the direction of current flow in the conductors, and the operating frequency. The specific magnetic flux distribution diagram during induction heating is shown below. Figure 6 As shown. The geometry of the induction heating coil was set using finite element software to simulate the heating process of a thick-walled welded pipe by an electromagnetic induction coil. The dimensions of the induction heating coil were set as follows. 685 The G115 thick-walled welded pipe is divided into an insulation zone and a heating zone by a 20mm finer mesh. The number of turns of the induction coil is set to 16, the gate spacing is 42mm, the frequency is 1000Hz, and the coil material property is defined as copper.

[0084] Based on the following two specific implementation processes, the coupling relationship between the electromagnetic field and the temperature field, as well as the coupling relationship between the temperature field and the stress field, are clarified.

[0085] First, determine the coupling relationship between the electromagnetic field and the temperature field.

[0086] First, the alternating magnetic field generated by the induction heating coil is calculated through frequency domain analysis, and the current density in the sample is determined based on the magnetic field distribution.

[0087] Maxwell's equations are constructed based on electric displacement, electric field strength, magnetic field strength, and magnetic induction, respectively, to determine the current density. Maxwell's equations are specifically represented by the following formulas (2) to (5).

[0088] (2).

[0089] (3).

[0090] (4).

[0091] (5).

[0092] in, Eddy currents characterize electromagnetic fields, where D is electric displacement, ρ is charge density, B is magnetic induction, E is electric field strength, H is magnetic field strength, and J is current density.

[0093] Secondly, the current density is used as the heat source to calculate the Joule heating caused by eddy currents.

[0094] Joule heating characterizes the heat generated when an electric current flows in a conductor.

[0095] Based on the thermophysical properties of the thick-walled welded pipe, including dielectric constant, permeability, and conductivity, and the electric displacement, electric field strength, magnetic field strength, and magnetic induction intensity of the induction heating coil, an electromagnetic constitutive relation is constructed to determine the Joule heat generated by the eddy current. The electromagnetic constitutive relation is specifically characterized by the following formulas (6) to (8).

[0096] (6).

[0097] (7).

[0098] (8).

[0099] Where ε, μ, and σ1 are the permittivity, permeability, and conductivity, respectively; D is the electric displacement; B is the magnetic flux density; H is the magnetic field strength; E is the electric field strength; and J is the current density. The volumetric power density, or Joule heat, is used as a heat source coupled to the temperature field.

[0100] Third, based on Joule heating, the heat source intensity in the heat conduction process is determined by substituting it into the heat conduction equation. The heat conduction formula is specifically characterized as shown in the following formula (9).

[0101] (9).

[0102] in, Charge density; Specific heat capacity; t represents temperature; t represents time. Thermal conductivity; Eddy currents characterize electromagnetic fields; The heat source intensity per unit volume is mainly provided by Joule heat.

[0103] Understandably, the calculated temperature increase will cause a change in conductivity σ1 (generally, σ1 decreases as temperature increases). The updated σ1 will then affect the electromagnetic field calculation in the first step, thus forming a two-way coupling between the electromagnetic field and the temperature field.

[0104] Secondly, the coupling relationship between the temperature field and the stress field is determined.

[0105] Considering the softening and creep effects of materials, and based on the correlation between the elastic modulus, plasticity curve, and coefficient of thermal expansion of thick-walled welded pipes and creep stress, and according to Norton's creep law, the creep strain rate is determined.

[0106] The Norton creep law it follows is specifically represented by the following formula (10).

[0107] (10).

[0108] in, The creep strain rate, Let be the creep stress, n be the stress exponent, A be the material constant, Q1 be the nominal creep activation energy, and T be the temperature.

[0109] In this embodiment, induction heating coils are used for induction heating. The coupling relationship between the electromagnetic field and the temperature field is determined, and the heat source intensity of induction heating is accurately obtained. Based on this, according to the coupling relationship between the temperature field and the stress field, the stress influence of the heat source generated by induction heating on the thick-walled welded pipe is accurately determined. Therefore, by using the thermophysical performance parameters, thermal boundary conditions, and electromagnetic distribution of the induction heating coils of the thick-walled welded pipe, the multi-physics coupling relationship between the temperature field, stress field, and electromagnetic field during the heat treatment of the thick-walled welded pipe is determined. This provides a more accurate simulation environment for subsequently determining the parameters for eliminating welding residual stress during the heat treatment process.

[0110] S22. Based on the multi-physics coupling relationship, different candidate residual stress parameters generated during the heat treatment process of thick-walled welded pipes under different heat treatment parameters are determined.

[0111] The heat treatment process characterizes the entire process of a large, thick-walled welded pipe going through the induction heating stage, the heat preservation stage, and the cooling stage.

[0112] The heat treatment parameters include the candidate heating width and the candidate holding width.

[0113] The candidate heating width characterizes the width of the induction heating region during heat treatment and is influenced by the electromagnetic distribution of the induction heating coil.

[0114] The candidate insulation width characterizes the width of the insulation region during heat treatment and is influenced by the thermal boundary conditions of thick-walled welded pipes.

[0115] Based on the multiphysics coupling relationship established in step S21 above, the residual stress change process during heat treatment is simulated using a thermo-mechanical coupling finite element analysis model, thereby determining the candidate residual stress parameters after heat treatment.

[0116] Specifically, based on the coupling relationship between the electromagnetic field and the temperature field, the steady-state temperature field during the induction heating stage of the heat treatment process under the heating width is determined; based on the coupling relationship between the steady-state temperature field and the stress field, the thermal stress corresponding to the steady-state temperature field is determined; based on the thermal boundary conditions, thermal stress, and welding residual stress parameters, the creep strain rate during the holding stage of the heat treatment process under the holding width is determined; based on the creep strain rate, the residual stress field generated during the cooling stage of the heat treatment process is determined; and stresses above a threshold in the residual stress field are identified as candidate residual stress parameters.

[0117] Based on the following three stages, this paper specifically explains how to simulate the entire process of heat treatment of G115 welded pipe by integrating Maxwell's equations, electromagnetic constitutive relations and heat conduction equations in finite element software, including heating, heat preservation and air cooling.

[0118] During the heating stage, the Joule heat generated by the Maxwell equations and electromagnetic constitutive relation equations established by the above formulas (2) to (8) is used as a heat source and input into the heat conduction equation characterized by formula (9). Based on the coupling relationship between the electromagnetic field and the temperature field, the distribution range of the heat source in the electromagnetic induction heating process of the thick-walled welded pipe under the preset heating width is simulated, that is, the steady-state temperature field.

[0119] During the heat preservation stage, the temperature field directly causes the material mechanical properties of the thick-walled welded pipe to soften, i.e., the elastic modulus and other parameters decrease, making it easier for the welding residual stress generated during welding to relax. Under the preset heat preservation width, the Norton creep law characterized by the above formula (10) is used to determine the creep strain rate of the thick-walled welded pipe material under the combined drive of the thermal stress generated by the continuous high temperature and the initial welding residual stress. The increase in creep strain will irreversibly dissipate the stored elastic strain energy, thereby significantly reducing the stress. Among them, the heat preservation width ensures that the relaxation process can be carried out fully and uniformly in a uniform high temperature zone, avoiding the generation of new stress by rapid cooling at the edges.

[0120] During the cooling phase, the temperature of the thick-walled welded pipe is cooled to room temperature via air cooling. As the temperature decreases, the pipe material is re-strengthened, new thermal stresses are generated, and these stresses eventually "freeze," forming a new, relaxed residual stress field. The residual stress field of the heat-treated thick-walled welded pipe is as follows: Figure 7 As shown.

[0121] Determine the point with the maximum stress value in the residual stress field, that is, the candidate residual stress parameter corresponding to the preset candidate heating width and candidate insulation width.

[0122] In this embodiment, by establishing the multi-physics coupling relationship between the temperature field, stress field and electromagnetic field, the entire heat treatment process of a large, thick-walled welded pipe from the induction heating stage to the heat preservation stage to the cooling stage can be simulated more realistically, thereby accurately predicting the distribution and magnitude of residual stress parameters.

[0123] S23. Based on the candidate heating width, candidate insulation width, and candidate residual stress parameters, determine the correlation between the heating width, insulation width, and residual stress parameters.

[0124] Based on the thermo-mechanical coupled finite element analysis model established in steps S21 and S22 above, the welding residual stress parameters generated during the welding process and the welding residual stress parameters eliminated during the heat treatment process can be accurately simulated, thus obtaining the entire process of residual stress parameters. Therefore, it can be seen that the heat treatment effect can be optimized by changing the heating width and holding width during the heat treatment process, resulting in different corresponding residual stress parameters. Thus, the correlation between the heating width, holding width, and residual stress parameters can be determined.

[0125] Specifically, a thermo-mechanical coupled finite element analysis model is established. The thermo-mechanical coupled finite element analysis model determines the residual stress parameters generated during the heat treatment of thick-walled welded pipes under heat treatment parameters based on the multi-physics coupling relationship. Based on the ratio of the outer diameter to the wall thickness of different thick-walled welded pipes, multiple sets of candidate heating widths and candidate insulation widths are determined. The candidate heating widths and candidate insulation widths are input into the thermo-mechanical coupled finite element analysis model to obtain the candidate residual stress parameters.

[0126] Understandably, the thermo-mechanical coupled finite element analysis model can quickly and accurately determine the candidate residual stress parameters after heat treatment under different preset heat treatment parameters. Due to the special nature of the thick-walled welded pipe structure, it is not possible to repeatedly conduct heat treatment experiments on the thick-walled welded pipe, and the subsequent target prediction model lacks data support. Therefore, the established thermo-mechanical coupled finite element analysis model is used to simulate the candidate residual stress parameters corresponding to multiple sets of different heat treatment parameters, providing a large amount of accurate data for the subsequent prediction process.

[0127] Specifically, if the ratio is detected to be less than or equal to a preset ratio, the corresponding candidate heating width is set to the first product of a first multiple and the wall thickness; and the corresponding candidate insulation width is set to the second product of a second multiple and the wall thickness; the difference between the second multiple and the first multiple is greater than or equal to 2. If the ratio is detected to be greater than a preset ratio, the candidate heating width is set to the third product of a third multiple and the wall thickness; and the corresponding candidate insulation width is set to the fourth product of a fourth multiple and the wall thickness; the difference between the fourth multiple and the third multiple is greater than or equal to 2; and the first multiple is less than the third multiple.

[0128] For example, starting from the weld center, the heating width and insulation width are divided into left and right sides. When the outer diameter / wall thickness is ≤15, the heating width on one side shall not be less than 5 times the wall thickness. When the outer diameter / wall thickness is >15, the heating width on one side shall not be less than 6 times the wall thickness. Furthermore, the insulation width shall be at least 2 times the wall thickness based on the heating width, and the insulation width on one side shall not be less than 150mm.

[0129] Initially, the heating width can be set to 380mm and the insulation width to 220mm. Then, both can be expanded in increments of 1.2 times the wall thickness until a maximum of 10 times the wall thickness is reached. This creates multiple parameter combinations for different heating and insulation widths. The final results can be summarized by... Figure 8 As shown. The stress distribution perpendicular to the welding direction, with the heating width as a variable, is as follows. Figure 9 As shown.

[0130] The insulation width and heating width were adjusted separately to determine the residual stress parameters under different parameter combinations. This provides specific and accurate data support for subsequent target prediction model training. Details are as follows: Figure 8 The residual stress parameters corresponding to different combinations of heat treatment parameters are shown.

[0131] When the heating width is 380mm, the insulation width is set to 220mm, and the residual stress is 50MPa.

[0132] When the heating width is 380mm and the insulation width is set to 300mm, the residual stress is 49MPa.

[0133] When the heating width is 380mm and the insulation width is set to 380mm, the residual stress is 48MPa.

[0134] When the heating width is 380mm and the insulation width is set to 460mm, the residual stress is 47MPa.

[0135] When the heating width is 380mm and the insulation width is set to 540mm, the residual stress is 45MPa.

[0136] When the heating width is 380mm, the insulation width is set to 220mm, and the residual stress is 50MPa.

[0137] When the heating width is 460mm and the insulation width is set to 220mm, the residual stress is 45MPa.

[0138] When the heating width is 540mm, the insulation width is set to 220mm, and the residual stress is 35MPa.

[0139] When the heating width is 620mm and the insulation width is set to 220mm, the residual stress is 26MPa.

[0140] When the heating width is 700mm and the insulation width is set to 220mm, the residual stress is 23MPa.

[0141] S24. Based on the correlation, determine the target heating width and target insulation width that satisfy the target residual stress parameters.

[0142] Based on the residual stress parameters corresponding to the multiple heat treatment parameter combinations provided in step S23 above, a prediction model is trained to predict the target heating width and target insulation width that meet the target residual stress parameters.

[0143] Specifically, a preset model is constructed, which represents the relationship between the heating width and the insulation width and the residual stress parameters; the preset prediction model is trained based on multiple sets of candidate heating widths and candidate insulation widths and their corresponding candidate residual stress parameters to obtain the target prediction model; the target residual stress parameters are input into the target prediction model to obtain the target heating width and the target insulation width.

[0144] The default model is a random forest model.

[0145] When applying the random forest model, the maximum residual stress is set as the dependent variable, and the heating width and insulation width are the independent variables.

[0146] Based on the relationship between the heating width and the insulation width and the residual stress parameters, a random forest model is constructed, which is specifically characterized by the following formula (11).

[0147] (11).

[0148] Where M is the total number of trees in the forest; m is the m-th tree in the forest, representing its predicted value for a given parameter; For space, For the leaf region, c jm As a leaf node constant, the tree will Space is divided into J m leaf area When the input falls in the j-th region, the output leaf node constant c jm ;1(·) is an indicator function that satisfies if If it is 1, then it is 1; otherwise, it is 0.

[0149] Finally, the outputs of all trees are averaged to obtain the final prediction of the residual stress difference between the inner and outer walls, and the final predicted residual stress parameters are determined.

[0150] For example, numerical simulation data is fitted using a regression algorithm, and the maximum residual stress is extracted based on engineering requirements. For width combinations ≤20MPa, the recommended optimal heating and insulation width combinations are 720mm and 290mm.

[0151] In this embodiment, a prediction model is used to learn the complex relationship between the heating width, the insulation width and the residual stress parameters, and to accurately predict the target heating width and the target insulation width that meet the target prediction model. Based on the target heating width and the target insulation width, the thick-walled welded pipe is heat-treated, thereby effectively improving the efficiency of heat treatment.

[0152] Optionally, the target heating width and target insulation width are input into the thermo-mechanical coupled finite element analysis model to obtain the verification residual stress parameters; the verification residual stress parameters are compared with the target residual stress parameters; when the verification residual stress parameters are consistent with the target residual stress parameters, it is determined that the target heating width and target insulation width meet the requirements; when the verification residual stress parameters are inconsistent with the target residual stress parameters, the parameters of the thermo-mechanical coupled finite element analysis model are automatically adjusted to generate multiple sets of new candidate heating widths and new candidate insulation widths and corresponding new candidate residual stress parameters, thereby adjusting the target prediction model.

[0153] In this embodiment, the accuracy of the predicted heat treatment parameters is improved by inputting the prediction results into the thermo-coupled finite element analysis model for reverse verification of the data, thus ensuring that the actual residual stress parameters meet the design requirements.

[0154] Numerical simulation analysis was conducted on the welding and heat treatment process of thick-walled G115 pipes. Based on the simulation results, the optimal heat treatment curve was selected to provide precise heat treatment parameter guidance for on-site heat treatment processes.

[0155] To achieve the above functions, the device for predicting heat treatment parameters for large, thick-walled welded pipes includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art will readily recognize that, based on the algorithmic steps of the examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0156] This disclosure also provides an embodiment such as Figure 10 The device shown is a heat treatment parameter prediction device for thick-walled welded pipes. The device includes an analysis unit 301 and a determination unit 302.

[0157] Analysis unit 301 is configured to determine the multi-physics coupling relationship between the temperature field, stress field, and electromagnetic field of a thick-walled welded pipe during heat treatment, based on the thermophysical performance parameters, thermal boundary conditions, and electromagnetic distribution of the induction heating coil. Based on this multi-physics coupling relationship, it determines different candidate residual stress parameters generated during heat treatment under different heat treatment parameters. The heat treatment process characterizes the entire process of the thick-walled welded pipe through the induction heating stage, the holding stage, and the cooling stage. Heat treatment parameters include candidate heating width and candidate holding width. The candidate heating width characterizes the width of the induction heating region during heat treatment and interacts with the electromagnetic distribution of the induction heating coil. The candidate holding width characterizes the width of the holding region during heat treatment and interacts with the thermal boundary conditions of the thick-walled welded pipe. Based on the candidate heating width, candidate holding width, and the determined candidate residual stress parameters, it determines the correlation between the heating width, holding width, and residual stress parameters.

[0158] The determining unit 302 is configured to determine the target heating width and the target insulation width that satisfy the target residual stress parameters based on the correlation relationship.

[0159] As one implementation method, the analysis unit 301 is specifically configured such that, before determining the multi-physics coupling relationship between the temperature field, stress field, and electromagnetic field during the heat treatment of the thick-walled welded pipe, the method further includes: determining the pipe volume distribution heat flux density of the thick-walled welded pipe based on the total heat power of the welding power source and the welding heat effect coefficient; determining the welding temperature field and welding stress field distribution during the welding process based on the pipe volume distribution heat flux density and the coupling relationship between the temperature field and the stress field; and determining the welding residual stress parameters based on the welding temperature field and welding stress field distribution, wherein the welding residual stress parameters characterize the residual stress generated by the temperature gradient during the cooling process of the thick-walled welded pipe from high-temperature welding.

[0160] As one way to achieve this, thermophysical performance parameters include the metal's density, specific heat capacity, electrical conductivity, magnetic permeability, elastic modulus, plasticity curve, thermal conductivity, and coefficient of thermal expansion at different temperatures.

[0161] The analysis unit 301 is specifically configured to determine the multi-physics coupling relationship between the temperature field, stress field, and electromagnetic field of the thick-walled welded pipe during heat treatment, based on the thermophysical performance parameters, thermal boundary conditions, and electromagnetic distribution of the induction heating coil. This includes: determining Joule heating based on conductivity, permeability, and the electromagnetic distribution of the induction heating coil; determining the heat source intensity during heat conduction based on Joule heating; determining the coupling relationship between the electromagnetic field and the temperature field based on the correlation between Joule heating and heat source intensity; determining the coupling relationship between the temperature field and the stress field based on the correlation between the elastic modulus, plasticity curve, and coefficient of thermal expansion of the thick-walled welded pipe and creep stress; and determining the multi-physics coupling relationship based on the coupling relationship between the electromagnetic field and the temperature field, and the coupling relationship between the temperature field and the stress field.

[0162] As one implementation method, the analysis unit 301 is specifically configured to determine different candidate residual stress parameters generated during the heat treatment of large, thick-walled welded pipes under different heat treatment parameters based on the multi-physics coupling relationship. Specifically, this includes: determining the steady-state temperature field during the induction heating stage of the heat treatment process under the heating width based on the coupling relationship between the electromagnetic field and the temperature field; determining the thermal stress corresponding to the steady-state temperature field based on the coupling relationship between the temperature field and the stress field; determining the creep strain rate during the heat treatment process under the heat treatment width based on the thermal boundary conditions, thermal stress, and welding residual stress parameters; determining the residual stress field generated during the cooling stage of the heat treatment process based on the creep strain rate; and identifying stresses in the residual stress field that are higher than a threshold as candidate residual stress parameters.

[0163] As one implementation method, the analysis unit 301 is specifically configured to establish a thermo-coupled finite element analysis model; the thermo-coupled finite element analysis model determines different candidate residual stress parameters generated by the thick-walled welded pipe under different heat treatment parameters based on the multi-physics coupling relationship; based on the ratio of the outer diameter to the wall thickness of different thick-walled welded pipes, multiple sets of candidate heating widths and candidate insulation widths are determined; the candidate heating widths and candidate insulation widths are input into the thermo-coupled finite element analysis model to obtain the candidate residual stress parameters.

[0164] As one implementation method, the analysis unit 301 is specifically configured to determine multiple sets of candidate heating widths and candidate insulation widths based on the ratio of the outer diameter to the wall thickness of different thick-walled welded pipes. Specifically, this includes: if the ratio is detected to be less than or equal to a preset ratio, the corresponding candidate heating width is set to the first product of a first multiple and the wall thickness; and the corresponding candidate insulation width is set to the second product of a second multiple and the wall thickness; the difference between the second multiple and the first multiple is greater than or equal to 2; if the ratio is detected to be greater than a preset ratio, the candidate heating width is set to the third product of a third multiple and the wall thickness; and the corresponding candidate insulation width is set to the fourth product of a fourth multiple and the wall thickness; the difference between the fourth multiple and the third multiple is greater than or equal to 2; and the first multiple is less than the third multiple.

[0165] As one implementation method, the specific configuration of the determining unit 302 is as follows: based on the correlation, the target heating width and target insulation width that satisfy the target residual stress parameters are determined, including: constructing a preset model, which characterizes the correlation between the heating width and insulation width and the residual stress parameters; training the preset model based on multiple sets of candidate heating widths and candidate insulation widths and corresponding candidate residual stress parameters to obtain a target prediction model; and inputting the target residual stress parameters into the target prediction model to obtain the target heating width and target insulation width.

[0166] As one implementation method, the specific configuration of the unit 302 is as follows: the target heating width and the target insulation width are input into the thermo-coupled finite element analysis model to obtain the verification residual stress parameters; the verification residual stress parameters are compared with the target residual stress parameters; when the verification residual stress parameters are consistent with the target residual stress parameters, the target heating width and the target insulation width are determined to meet the requirements; when the verification residual stress parameters are inconsistent with the target residual stress parameters, the parameters of the thermo-coupled finite element analysis model are automatically adjusted to generate multiple sets of new candidate heating widths and new candidate insulation widths and corresponding new candidate residual stress parameters, thereby adjusting the target prediction model.

[0167] Regarding the apparatus in the above embodiments, the specific manner in which each unit module performs its operations has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0168] Figure 11 This is a schematic diagram of a heat treatment parameter prediction device for large, thick-walled welded pipes provided in this application. Figure 11 The device for predicting heat treatment parameters of large thick-walled welded pipes includes: a first processor 501, a communication bus 502, a memory 503, a communication interface 504, an output device 505, an input device 506, and a second processor 507.

[0169] The heat treatment parameter prediction device 50 for large, thick-walled welded pipes may include at least one first processor 501 and a memory 503 for storing processor-executable instructions. The first processor 501 is configured to execute the instructions in the memory 503 to implement the heat treatment parameter prediction method for large, thick-walled welded pipes in the following embodiments.

[0170] In addition, the heat treatment parameter prediction device 50 for large thick-walled welded pipes may also include a communication bus 502, at least one communication interface 504, an input device 506, and an output device 505.

[0171] The first processor 501 may be a processor (central processing unit, CPU), a microprocessor unit, an ASIC, or one or more integrated circuits for controlling the execution of programs according to the present application.

[0172] The communication bus 502 may include a path for transmitting information between the aforementioned components.

[0173] Communication interface 504 uses any transceiver-like device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0174] Input device 506 is used to receive input signals and output device 505 is used to output signals.

[0175] Memory 503 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed discs, laser discs, optical discs, digital universal discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. Memory may exist independently and be connected to the processing unit via a bus. Memory may also be integrated with the processing unit.

[0176] The memory 503 stores instructions for executing the scheme of this application, and the execution is controlled by the first processor 501. The first processor 501 executes the instructions stored in the memory 503 to realize the functions of the method of this application.

[0177] In a specific implementation, as one example, the first processor 501 may include one or more CPUs, for example... Figure 11 CPU0 and CPU1 in the CPU.

[0178] In a specific implementation, as one example, the heat treatment parameter prediction device 50 for large thick-walled welded pipes may include multiple processors, such as... Figure 11 The first processor 501 and the second processor 507 are described. Each of these processors can be a single-core processor or a multi-core processor. A processor here can refer to one or more devices, circuits, and / or processing cores used to process data (such as computer program instructions).

[0179] The equipment for predicting heat treatment parameters of large, thick-walled welded pipes, such as... Figure 11 The diagram includes a first processor 501 and a memory 503 for storing executable instructions of the first processor 501. The first processor 501 is configured to execute the executable instructions to implement the heat treatment parameter prediction method for large, thick-walled welded pipes as described in any of the possible embodiments above. Furthermore, it achieves the same technical effect, and to avoid repetition, will not be elaborated further here.

[0180] This application also provides a computer-readable storage medium. When the instructions in the computer-readable storage medium are executed by the processor of the heat treatment parameter prediction device for thick-walled welded pipes, the heat treatment parameter prediction device for thick-walled welded pipes can perform the heat treatment parameter prediction method for thick-walled welded pipes as described in any of the above possible embodiments, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0181] This application also provides a computer program product, including a computer program or instructions, which are executed by a processor as described in any of the possible embodiments above for predicting heat treatment parameters of thick-walled welded pipes. This achieves the same technical effect, and to avoid repetition, it will not be described again here.

[0182] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0183] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for predicting heat treatment parameters of large, thick-walled welded pipes, characterized in that, The method includes: Based on the thermophysical performance parameters, thermal boundary conditions, and electromagnetic distribution of the induction heating coil of the thick-walled welded pipe, the multi-physics coupling relationship between the temperature field, stress field, and electromagnetic field during the heat treatment process of the thick-walled welded pipe is determined; the thermophysical performance parameters include the density, specific heat capacity, electrical conductivity, magnetic permeability, elastic modulus, plasticity curve, thermal conductivity, and coefficient of thermal expansion of the metal at different temperatures. The method of determining the multi-physics coupling relationship between the temperature field, stress field, and electromagnetic field of the thick-walled welded pipe during heat treatment, based on the thermophysical performance parameters, thermal boundary conditions, and electromagnetic distribution of the induction heating coil, includes: determining Joule heating based on the conductivity, permeability, and electromagnetic distribution of the induction heating coil; determining the heat source intensity during heat conduction based on the Joule heating; determining the coupling relationship between the electromagnetic field and the temperature field based on the correlation between the Joule heating and the heat source intensity; determining the coupling relationship between the temperature field and the stress field based on the correlation between the elastic modulus, plasticity curve, and coefficient of thermal expansion of the thick-walled welded pipe and creep stress; and determining the multi-physics coupling relationship based on the coupling relationship between the electromagnetic field and the temperature field and the coupling relationship between the temperature field and the stress field. Based on the multiphysics coupling relationship, different candidate residual stress parameters generated during the heat treatment process of the thick-walled welded pipe under different heat treatment parameters are determined; the heat treatment process characterizes the entire process of the thick-walled welded pipe going through the induction heating stage, the holding stage, and the cooling stage; the heat treatment parameters include candidate heating width and candidate holding width; the candidate heating width characterizes the width of the induction heating region during the heat treatment process and interacts with the electromagnetic distribution of the induction heating coil; the candidate holding width characterizes the width of the holding region during the heat treatment process and interacts with the thermal boundary conditions of the thick-walled welded pipe. Before determining the multi-physics coupling relationship between the temperature field, stress field, and electromagnetic field during the heat treatment of the thick-walled welded pipe, the method further includes: determining the pipe volume distribution heat flux density of the thick-walled welded pipe based on the total heat power of the welding power source and the welding heat effect coefficient; determining the welding temperature field and welding stress field distribution during the welding process based on the pipe volume distribution heat flux density and the coupling relationship between the temperature field and the stress field; and determining welding residual stress parameters based on the welding temperature field and welding stress field distribution, wherein the welding residual stress parameters characterize the residual stress generated by the temperature gradient during the cooling process of the thick-walled welded pipe from high-temperature welding. Based on the multiphysics coupling relationship, different candidate residual stress parameters generated during the heat treatment process of the thick-walled welded pipe under different heat treatment parameters are determined, specifically including: Based on the coupling relationship between the electromagnetic field and the temperature field, the steady-state temperature field of the induction heating stage during the heat treatment process under the heating width is determined; Based on the coupling relationship between the temperature field and the stress field, the thermal stress corresponding to the steady-state temperature field is determined; based on the thermal boundary conditions, the thermal stress, and the welding residual stress parameters, the creep strain rate of the heat treatment stage under the heat treatment width is determined. Based on the creep strain rate, the residual stress field generated during the cooling stage of the heat treatment process is determined; the stresses in the residual stress field that are higher than a threshold are determined as candidate residual stress parameters. Based on the candidate heating width, the candidate insulation width, and the candidate residual stress parameter, determine the correlation between the heating width, the insulation width, and the residual stress parameter; Based on the aforementioned correlation, the target heating width and target insulation width that satisfy the target residual stress parameters are determined, including: A preset model is constructed, which characterizes the relationship between the heating width and the insulation width and the residual stress parameter; the preset model is trained according to multiple sets of candidate heating widths and candidate insulation widths and the corresponding candidate residual stress parameters to obtain a target prediction model; the target residual stress parameter is input into the target prediction model to obtain the target heating width and the target insulation width; The preset model is a random forest model; the target residual stress parameter is determined as the dependent variable, and the target heating width and the target insulation width are determined as independent variables; the correlation between the heating width and insulation width and the residual stress parameter is represented by the following formula: ； in, The target residual stress parameter; The width of the heating element; denoted as the insulation width; M is the total number of trees in the forest; m is the m-th tree in the forest, representing its predicted value for a given parameter; For space, For the leaf region, c jm As a leaf node constant, the tree will The space is divided into Jm leaf regions. When the input falls in the j-th region, the output leaf node constant c jm ;1(·) is an indicator function, if it satisfies If it is 1, then it is 1; otherwise, it is 0.

2. The method for predicting heat treatment parameters of thick-walled welded pipes according to claim 1, characterized in that, The method further includes: A thermo-mechanical coupled finite element analysis model is established; the thermo-mechanical coupled finite element analysis model is based on the multi-physics coupling relationship to determine different candidate residual stress parameters generated by the large thick-walled welded pipe during the heat treatment process under different heat treatment parameters; Based on the ratio of the outer diameter to the wall thickness of the different thick-walled welded pipes, multiple sets of candidate heating widths and candidate insulation widths are determined. The candidate heating width and the candidate insulation width are input into the thermo-coupled finite element analysis model to obtain the candidate residual stress parameters.

3. The method for predicting heat treatment parameters of thick-walled welded pipes according to claim 2, characterized in that, The step of determining multiple sets of candidate heating widths and candidate insulation widths based on different ratios of the outer diameter to the wall thickness of the thick-walled welded pipes specifically includes: If the ratio is detected to be less than or equal to a preset ratio, the corresponding candidate heating width is set to the first product of a first multiple and the wall thickness; and the corresponding candidate insulation width is set to the second product of a second multiple and the wall thickness; the difference between the second multiple and the first multiple is greater than or equal to 2. If the ratio is detected to be greater than the preset ratio, the candidate heating width is set to the third product of the third multiple and the wall thickness; and the corresponding candidate insulation width is set to the fourth product of the fourth multiple and the wall thickness; the difference between the fourth multiple and the third multiple is greater than or equal to 2; the first multiple is less than the third multiple.

4. The method for predicting heat treatment parameters of thick-walled welded pipes according to claim 3, characterized in that, The method further includes: Input the target heating width and the target insulation width into the thermo-coupled finite element analysis model to obtain the verification residual stress parameters; The verified residual stress parameters are compared with the target residual stress parameters; When the verified residual stress parameter is consistent with the target residual stress parameter, it is determined that the target heating width and the target insulation width meet the requirements. When the verified residual stress parameters are inconsistent with the target residual stress parameters, the parameters of the thermo-coupled finite element analysis model are automatically adjusted to generate multiple sets of new candidate heating widths and new candidate insulation widths and corresponding new candidate residual stress parameters, thereby adjusting the target prediction model.

5. A device for predicting heat treatment parameters of large, thick-walled welded pipes, characterized in that, The device includes: The analysis unit, based on the thermophysical performance parameters, thermal boundary conditions, and electromagnetic distribution of the induction heating coil of the thick-walled welded pipe, determines the multi-physics coupling relationship between the temperature field, stress field, and electromagnetic field during the heat treatment process of the pipe. The thermophysical performance parameters include the metal's density, specific heat capacity, electrical conductivity, magnetic permeability, elastic modulus, plasticity curve, thermal conductivity, and coefficient of thermal expansion at different temperatures. The coupling relationships include: determining Joule heating based on the electrical conductivity, magnetic permeability, and electromagnetic distribution of the induction heating coil; determining the heat source intensity during heat conduction based on the Joule heating; determining the coupling relationship between the electromagnetic field and the temperature field based on the correlation between the Joule heating and the heat source intensity; determining the coupling relationship between the temperature field and the stress field based on the correlation between the elastic modulus, the plasticity curve, and the coefficient of thermal expansion and creep stress of the thick-walled welded pipe; and determining the multiphysics coupling relationship based on the coupling relationship between the electromagnetic field and the temperature field and the coupling relationship between the temperature field and the stress field. Based on the multiphysics coupling relationship, different candidate residual stress parameters generated during the heat treatment process of the thick-walled welded pipe under different heat treatment parameters are determined; the heat treatment process characterizes the entire process of the thick-walled welded pipe going through the induction heating stage, the holding stage, and the cooling stage; the heat treatment parameters include candidate heating width and candidate holding width; the candidate heating width characterizes the width of the induction heating region during the heat treatment process and interacts with the electromagnetic distribution of the induction heating coil; the candidate holding width characterizes the width of the holding region during the heat treatment process and interacts with the thermal boundary conditions of the thick-walled welded pipe. Before determining the multi-physics coupling relationship between the temperature field, stress field, and electromagnetic field during the heat treatment of the thick-walled welded pipe, the method further includes: determining the pipe volume distribution heat flux density of the thick-walled welded pipe based on the total heat power of the welding power source and the welding heat effect coefficient; determining the welding temperature field and welding stress field distribution during the welding process based on the pipe volume distribution heat flux density and the coupling relationship between the temperature field and the stress field; and determining the welding residual stress parameters based on the welding temperature field and welding stress field distribution, wherein the welding residual stress parameters characterize the residual stress generated by the temperature gradient during the cooling process of the thick-walled welded pipe from high-temperature welding. Based on the multi-physics coupling relationship, different candidate residual stress parameters generated during the heat treatment process of the large thick-walled welded pipe under different heat treatment parameters are determined. Specifically, this includes: determining the steady-state temperature field during the induction heating stage of the heat treatment process at the heating width based on the coupling relationship between the electromagnetic field and the temperature field; determining the thermal stress corresponding to the steady-state temperature field based on the coupling relationship between the temperature field and the stress field; determining the creep strain rate during the heat holding stage of the heat treatment process at the heat holding width based on the thermal boundary conditions, the thermal stress, and the welding residual stress parameters; determining the residual stress field generated during the cooling stage of the heat treatment process based on the creep strain rate; identifying stresses in the residual stress field that are higher than a threshold as candidate residual stress parameters; and determining the correlation between the heating width, the heat holding width, and the residual stress parameters based on the candidate heating width, the candidate heat holding width, and the candidate residual stress parameters. The determining unit is configured to determine, based on the aforementioned correlation, the target heating width and the target insulation width that satisfy the target residual stress parameters, including: A preset model is constructed, which characterizes the relationship between the heating width and the insulation width and the residual stress parameter; the preset model is trained according to multiple sets of candidate heating widths and candidate insulation widths and the corresponding candidate residual stress parameters to obtain a target prediction model; the target residual stress parameter is input into the target prediction model to obtain the target heating width and the target insulation width; The preset model is a random forest model; the target residual stress parameter is determined as the dependent variable, and the target heating width and the target insulation width are determined as independent variables; the correlation between the heating width and insulation width and the residual stress parameter is represented by the following formula: ； in, The target residual stress parameter; The width of the heating element; denoted as the insulation width; M is the total number of trees in the forest; m is the m-th tree in the forest, representing its predicted value for a given parameter; For space, The tree will be a leaf region, where cjm is the leaf node constant. The space is divided into Jm leaf regions. When the input falls in the j-th region, the output leaf node constant cjm is given; 1(·) is an indicator function, if it satisfies If it is 1, then it is 1; otherwise, it is 0.

6. A device for predicting heat treatment parameters of large, thick-walled welded pipes, characterized in that, It is configured to perform the method for predicting heat treatment parameters of large, thick-walled welded pipes as described in any one of claims 1-4.

Images