Method for generating prediction model of crush strength of steel pipe, method for predicting crush strength of steel pipe, method for determining manufacturing characteristics of steel pipe, and method for manufacturing steel pipe

Abstract

Provided are a method for generating a steel pipe collapse strength prediction model capable of accurately predicting the collapse strength of a coated steel pipe formed by coating a steel pipe after forming, taking into account not only the bending strain at the time of laying but also the pipe forming strain at the time of steel pipe forming and coating conditions, a method for predicting the collapse strength of a steel pipe, a method for determining the manufacturing characteristics of a steel pipe, and a method for manufacturing a steel pipe. The steel pipe collapse strength prediction model generated by the method for generating a steel pipe collapse strength prediction model is input with the steel pipe manufacturing characteristics of a coated steel pipe to be predicted, including the steel pipe shape after forming, the steel pipe strength characteristics after forming, the pipe forming strain at the time of steel pipe forming, the coating conditions, and the bending strain at the time of laying, to predict the collapse strength of the coated steel pipe at the time of pressure bending (steps S1 to S5).

Description

Technical Field

[0001] This invention relates to a method for generating a steel pipe crush strength prediction model, a method for predicting the crush strength of steel pipes, a method for determining the manufacturing characteristics of steel pipes, and a method for manufacturing steel pipes. Background Technology

[0002] In steel pipes used under external pressure, crushing (also known as collapse) can sometimes occur due to the external pressure. For example, in submarine pipelines, such crushing can lead to damage to the structure and cause significant economic and environmental impacts. The most dangerous scenario for this type of collapse is when the submarine pipeline is laid without internal pressure, but with the added bending strain caused by the laying process. Estimated formulas have been developed to predict the crushing intensity under such external pressure bending conditions.

[0003] Here, a presumed formula for predicting the crushing strength under external pressure bending is described, for example, in Non-Patent Literature 1. In Non-Patent Literature 1, standards such as DNV OS-F101 are established, and a presumed formula for predicting the crushing strength under external pressure bending is proposed based on the Ovality of the outer diameter shape of the steel pipe being evaluated, the yield stress (stress corresponding to 0.5% strain) collected from the center of the material wall thickness or 1 / 4 of the wall thickness (inner surface side), Young's modulus, Poisson's ratio, and data on bending strain during laying (D 400 Chapter Local Buckling-External over pressure only 401 Equation (5.10)).

[0004] Existing technical documents

[0005] Non-patent literature

[0006] Non-Patent Literature 1: OFFSHORE STANDARD DNV-OS-F101, SUBMARINE PIPELINE SYSTEMS, DET NORSKE VERITAS, October 2010, SEC5, pp. 41-56 Summary of the Invention

[0007] The problem that the invention aims to solve

[0008] However, the following problems exist in the estimation formula for predicting the crushing strength under external pressure bending as described in Non-Patent Document 1.

[0009] That is, in particular, steel pipes used in submarine pipelines are coated (applied) for corrosion protection. This coating process sometimes involves heating the steel pipe, and depending on the coating conditions, the compressive properties of the coated steel pipe, and consequently its crushing characteristics, change. Furthermore, the crushing strength of a coated steel pipe depends not only on the shape and strength properties (tensile strength, compressive strength, Young's modulus, Poisson's ratio, etc.) of the formed steel pipe, but also on the strain during pipe forming (the strain history during pipe forming). This is because the strain during pipe forming significantly affects the shape and strength properties of the formed steel pipe, and consequently, the crushing characteristics of the coated steel pipe.

[0010] On the other hand, in Non-Patent Literature 1, the pipe-forming strain and coating conditions during steel pipe forming were not considered. The accuracy of the predicted crush strength under external pressure bending of the coated steel pipe was poor, and the actual measured crush strength under external pressure bending of the coated steel pipe differed significantly from the predicted value. Therefore, excessively prioritizing safety in steel pipe design, or allowing crushing under lower-than-predicted external pressure, could lead to major accidents.

[0011] Therefore, the present invention was made to solve the previous problems, and its purpose is to provide a method for generating a steel pipe crush strength prediction model that can accurately predict the crush strength of a coated steel pipe formed after coating under external pressure bending, taking into account not only the bending strain during laying but also the pipe forming strain and coating conditions during steel pipe forming, as well as the pipe forming strain and coating conditions. The invention also includes a method for predicting the crush strength of a steel pipe, a method for determining the manufacturing characteristics of a steel pipe, and a method for manufacturing a steel pipe.

[0012] Methods for solving problems

[0013] To address the aforementioned issues, one aspect of the present invention relates to a method for generating a steel pipe crush strength prediction model. This method involves performing machine learning on multiple training datasets to generate a steel pipe crush strength prediction model that predicts the crush strength of a coated steel pipe formed after forming and then coated. The multiple training datasets include past steel pipe manufacturing characteristics as input data, such as the shape of the steel pipe after forming, the strength characteristics of the steel pipe after forming, the pipe-making strain during forming, the coating conditions, and the bending strain during laying. The output data is the past crush strength of a coated steel pipe formed after forming and then coated, relative to the input data, under external pressure bending.

[0014] Furthermore, the main idea of ​​another aspect of the present invention regarding the method for predicting the crushing strength of steel pipes is to input the steel pipe manufacturing characteristics, including the shape of the steel pipe after forming, the strength characteristics of the steel pipe after forming, the pipe forming strain during forming, the coating conditions, and the bending strain during laying, into the steel pipe crushing strength prediction model generated by the aforementioned method, and predict the crushing strength of the coated steel pipe formed after forming and coating under external pressure bending.

[0015] Furthermore, the main idea of ​​another aspect of the present invention regarding the method for determining the manufacturing characteristics of a steel pipe is to determine the manufacturing characteristics of the steel pipe by successively changing at least one of the following: the shape of the steel pipe after forming, the strength characteristics of the steel pipe after forming, the pipe forming strain, the coating conditions, and the bending strain during laying, in order to make the crushing strength of the coated steel pipe predicted by the aforementioned method for predicting the crushing strength of the steel pipe gradually approach the desired crushing strength of the coated steel pipe during the external pressure bending.

[0016] Furthermore, another aspect of the present invention relates to a method for manufacturing a steel pipe, which includes: a coated steel pipe forming process, wherein a steel pipe is formed and coated to form a coated steel pipe; a crushing strength prediction process, wherein the crushing strength of the coated steel pipe formed in the coated steel pipe forming process is predicted under external pressure bending using the aforementioned method for predicting the crushing strength of a steel pipe; and a performance prediction value assignment process, wherein the crushing strength of the coated steel pipe predicted by the crushing strength prediction process under external pressure bending is correlated with the coated steel pipe formed in the coated steel pipe forming process.

[0017] Furthermore, the main idea of ​​another aspect of the present invention regarding the manufacturing method of steel pipe is to determine the manufacturing conditions of coated steel pipe based on the manufacturing characteristics of steel pipe determined by the aforementioned steel pipe manufacturing characteristic determination method, and to manufacture coated steel pipe using the determined manufacturing conditions of coated steel pipe.

[0018] Invention Effects

[0019] According to the method for generating a steel pipe crush strength prediction model, the method for predicting the crush strength of steel pipe, the method for determining the manufacturing characteristics of steel pipe, and the manufacturing method of steel pipe involved in this invention, it is possible to predict with high accuracy the crush strength of coated steel pipe formed after coating after steel pipe forming under external pressure bending, taking into account not only the bending strain during laying but also the pipe forming strain and coating conditions. Attached Figure Description

[0020] Figure 1This is a functional block diagram of the general structure of a steel pipe manufacturing characteristic determination device, which is a method for generating a steel pipe crush strength prediction model, a method for predicting the crush strength of steel pipe, and a method for determining the manufacturing characteristics of steel pipe, according to an embodiment of the present invention.

[0021] Figure 2 This is a diagram illustrating the processing flow of a steel pipe crush strength prediction model generated as a neural network model by a method for generating a steel pipe crush strength prediction model according to an embodiment of the present invention.

[0022] Figure 3 This is a flowchart illustrating the processing flow of the steel pipe manufacturing characteristic calculation unit in the calculation processing unit of the steel pipe manufacturing characteristic determination device applied to an embodiment of the present invention. Detailed Implementation

[0023] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. The embodiments shown below illustrate apparatus and methods for embodying the technical concept of the present invention. The technical concept of the present invention does not specify the materials, shapes, structures, arrangements, etc., of the constituent components as described in the following embodiments. Furthermore, the drawings are schematic. Therefore, it should be noted that the relationship between thickness and planar dimensions, ratios, etc., differ from reality, and the drawings also include portions with different dimensional relationships and ratios.

[0024] exist Figure 1 The diagram shows a functional block diagram of a schematic structure of a steel pipe manufacturing characteristic determination device, which is a method for generating a steel pipe crush strength prediction model, a method for predicting the crush strength of steel pipe, and a method for determining the manufacturing characteristics of steel pipe according to an embodiment of the present invention.

[0025] Figure 1 The steel pipe manufacturing characteristic determination device 1 shown generates a steel pipe crush strength prediction model for coated steel pipes formed after steel pipe forming and coating, predicts the crush strength of coated steel pipes formed after steel pipe forming and coating under external pressure bending using the generated steel pipe crush strength prediction model, and determines the steel pipe manufacturing characteristics in a way that makes the predicted crush strength of coated steel pipes under external pressure bending gradually approach the desired target crush strength of coated steel pipes under external pressure bending.

[0026] Figure 1The steel pipe manufacturing characteristic determination device 1 shown is a computer system comprising an arithmetic unit 2, an input device 8, a storage device 9, and an output device 10. Although described later, the arithmetic unit 2 includes RAM 3, ROM 4, and an arithmetic processing unit 5, which are connected to the input device 8, storage device 9, and output device 10 via a bus 11. The arithmetic unit 2 and the input device 8, storage device 9, and output device 10 are not limited to this connection method; they can also be connected wirelessly, or a combination of wired and wireless methods.

[0027] Input device 8, such as a keyboard, handwriting tablet, touchpad, or mouse, functions as an input port for the operator of this system to input various information. For example, inputting commands for generating a steel pipe crush strength prediction model, calculating steel pipe manufacturing characteristics, and determining the crush strength prediction model of the target coated steel pipe under external pressure bending, including the steel pipe shape after forming, the steel pipe strength characteristics after forming, the pipe forming strain during forming, the coating conditions, and the bending strain during laying, as well as the crush strength under external pressure bending of the target coated steel pipe and the steel pipe manufacturing characteristics determination mode information.

[0028] Here, steel pipes are generally formed and manufactured by bending plate-shaped steel sheets into round tube shapes, and then coated on the surface to form coated steel pipes.

[0029] The steel pipe shape after forming, input to input device 8, refers to the shape of the steel pipe after the steel plate is formed into a round tube shape. Specifically, this steel pipe shape includes the maximum outer diameter Dmax (mm), the minimum outer diameter Dmin (mm), the average outer diameter Dave (mm), the average tube sheet thickness t (mm), and the roundness (Ovality) fO (%) of the outer diameter shape. Measured values ​​are input to input device 8 for the steel pipe shape after forming. This steel pipe shape significantly affects the predicted crush strength of the coated steel pipe under external pressure bending, therefore it is input.

[0030] It should be noted that the crush strength of a coated steel pipe under external pressure bending means the load stress (MPa) of the coated steel pipe when it is crushed. The term "crushing" here refers to the state in which the load stress reaches its maximum value and the deformation is such that it can no longer maintain its shape relative to the external pressure.

[0031] Furthermore, the strength characteristics of the steel pipe after forming refer to the strength characteristics of the steel pipe after the steel plate is formed into a tubular shape. Specifically, these strength characteristics are the Young's modulus E (GPa), Poisson's ratio μ (-), tensile strength YS (MPa), compressive strength 0.23%YS (stress corresponding to 0.23% strain), and compressive strength 0.5%YS (stress corresponding to 0.5% strain). These strength characteristics significantly affect the predicted crushing strength of the coated steel pipe under external pressure bending; therefore, they are input as follows: For the strength characteristics of the steel pipe after forming, input values ​​obtained from finite element analysis simulation based on the strength characteristics of the steel plate before forming, and measured values.

[0032] Furthermore, the tube-forming strain during steel pipe forming is either the tensile strain (%) or the compressive strain (%) during forming. This tube-forming strain significantly affects the shape and strength characteristics of the formed steel pipe, consequently impacting the predicted crush strength of the coated steel pipe under external pressure bending. Therefore, the input for tube-forming strain is the strain obtained through finite element analysis simulation based on the strength characteristics of the steel plate before forming, or the measured strain.

[0033] Additionally, the coating conditions here are the maximum temperature (°C) and holding time (min) during coating. Enter the measured values ​​for these coating conditions.

[0034] Coating the formed steel pipe is for corrosion prevention, especially for steel pipes used in submarine pipelines, which are generally coated after forming to ensure excellent corrosion resistance. The coating conditions (maximum temperature (°C) and holding time (min)) affect the strength characteristics of the formed steel pipe, directly influencing its crushing performance, and are therefore input to input device 8. Due to the effects of coating heating, the material properties of the steel pipe change (dislocation accumulation / recovery / strain aging, etc.), thus increasing or decreasing its crushing strength compared to the crushing strength of the formed steel pipe (crushing performance before coating).

[0035] In addition, the bending strain during laying is the tensile strain (%) or compressive strain (%) when the coated steel pipe is laid, for example, to the seabed. Regarding the occurrence of crushing, the most dangerous situation is when the bending strain caused by laying is superimposed on the pipeline without the application of internal pressure.

[0036] Furthermore, the storage device 9, such as a hard disk drive, semiconductor drive, or optical drive, is a device that stores information required by this system (information required for the realization of the functions of the steel pipe crush strength prediction model generation unit 6 and the steel pipe manufacturing characteristic calculation unit 7, described later). Examples of information required for the realization of the functions of the steel pipe crush strength prediction model generation unit 6 include multiple training data sets that take past steel pipe manufacturing characteristics, consisting of the shape of the formed steel pipe, the strength characteristics of the formed steel pipe, the pipe forming strain, the coating conditions, and the bending strain during laying, as input data, and take the crush strength of a coated steel pipe formed after coating following the forming process as output data, relative to the past input data.

[0037] Furthermore, as information required for the realization of the function of the steel pipe manufacturing characteristic calculation unit 7, the steel pipe crush strength prediction model generated by the steel pipe crush strength prediction model generation unit 6 can be cited as an example. Additionally, as information required for the realization of this function, the steel pipe manufacturing characteristics, which are the steel pipe shape after forming, the steel pipe strength characteristics after forming, the pipe strain during forming, the coating conditions, and the bending strain during laying, which are input to the input device 8 as the target coated steel pipe and are subject to crush strength prediction under pressure bending, can be cited as an example. Furthermore, as information required for the realization of this function, steel pipe manufacturing characteristic determination mode information (information on whether it is a mode that determines the optimal steel pipe manufacturing characteristics) can also be cited as an example.

[0038] Furthermore, the output device 10 functions as an output port for outputting output data from the arithmetic unit 2 (e.g., information on the crush strength (predicted value) of a coated steel pipe formed after coating and forming, predicted by the crush strength prediction unit 72, and information on the steel pipe manufacturing characteristics determined by the steel pipe manufacturing characteristic determination unit 73). The output device 10 can display a screen based on the output data, for example, using any display such as a liquid crystal display or an organic display.

[0039] Next, as Figure 1 As shown, the arithmetic unit 2 includes RAM 3, ROM 4, and a processing unit 5. ROM 4 stores a steel pipe crush strength prediction model generation program 41 and a steel pipe manufacturing characteristic calculation program 42. The processing unit 5 has arithmetic processing functions and is connected to RAM 3 and ROM 4 via bus 11. In addition, RAM 3, ROM 4, and processing unit 5 are connected to input device 8, storage device 9, and output device 10 via bus 11.

[0040] The calculation and processing unit 5 is a functional block that includes a steel pipe crush strength prediction model generation unit 6 and a steel pipe manufacturing characteristic calculation unit 7.

[0041] The steel pipe crush strength prediction model generation unit 6 of the processing unit 5 performs machine learning on multiple learning data stored in the storage device 9 to generate a steel pipe crush strength prediction model. The multiple learning data take as input data the past steel pipe manufacturing characteristics, consisting of the shape of the formed steel pipe, the strength characteristics of the formed steel pipe, the pipe-making strain during forming, the coating conditions, and the bending strain during laying. The output data is the crush strength under external pressure bending of a coated steel pipe formed after forming, relative to the past input data. The machine learning method used here is a neural network; the steel pipe crush strength prediction model is a prediction model constructed from a neural network.

[0042] Here, the steel pipe crush strength prediction model generation unit 6, as a functional block, includes a learning data acquisition unit 61, a preprocessing unit 62, a model generation unit 63, and a result storage unit 64. Furthermore, when the steel pipe crush strength prediction model generation unit 6 receives a generation command for a steel pipe crush strength prediction model from the input device 8, it executes the steel pipe crush strength prediction model generation program 41 stored in the ROM 4, performing the functions of the learning data acquisition unit 61, the preprocessing unit 62, the model generation unit 63, and the result storage unit 64. Each time the steel pipe crush strength prediction model generation unit 6 performs its functions, the steel pipe crush strength prediction model is updated.

[0043] The execution processing of the functions of the steel pipe crush strength prediction model generation unit 6 on the learning data acquisition unit 61, the preprocessing unit 62, the model generation unit 63, and the result storage unit 64 corresponds to a method for generating a steel pipe crush strength prediction model according to an embodiment of the present invention. This method performs machine learning on multiple learning data sets to generate a steel pipe crush strength prediction model that predicts the crush strength of a coated steel pipe formed after forming and then coated, under pressure bending. The multiple learning data sets include past steel pipe manufacturing characteristics, such as the shape of the steel pipe after forming, the strength characteristics of the steel pipe after forming, the pipe-making strain during forming, the coating conditions, and the bending strain during laying, as input data. The output data is the past crush strength of a coated steel pipe formed after forming and then coated, relative to the input data, under pressure bending.

[0044] Here, the learning data acquisition unit 61 performs the following processing: it acquires multiple learning data stored in the storage device 9, which are input data consisting of past steel pipe manufacturing characteristics, including the shape of the steel pipe after forming, the strength characteristics of the steel pipe after forming, the pipe forming strain during forming, the coating conditions, and the bending strain during laying, and output data the crushing strength of the coated steel pipe formed after coating after forming, relative to the past input data. Each learning data consists of a set of input data and output data.

[0045] In addition, the preprocessing unit 62 processes multiple learning data acquired by the learning data acquisition unit 61 into a model for generating a steel pipe crush strength prediction model. Specifically, the preprocessing unit 62 standardizes (normalizes) the learning data between 0 and 1, using past data on the steel pipe manufacturing characteristics (comprising the shape of the steel pipe after forming, the strength characteristics of the steel pipe after forming, the pipe forming strain, the coating conditions, and the bending strain during laying) and past data on the crush strength of coated steel pipes formed after coating after forming.

[0046] Furthermore, the model generation unit 63 performs the following processing: it performs machine learning on multiple learning data preprocessed by the preprocessing unit 62 to generate a steel pipe crush strength prediction model. The model's input data includes past steel pipe manufacturing characteristics comprised of the steel pipe shape after forming, the steel pipe strength characteristics after forming, the pipe-making strain during forming, the coating conditions, and the bending strain during laying. The output data is the crush strength under external pressure bending of a coated steel pipe formed after forming. In this embodiment, since a neural network is used as a machine learning method, a neural network model is generated as the steel pipe crush strength prediction model. That is, the model generation unit 63 creates a neural network model that correlates the input performance data (past performance data of steel pipe manufacturing characteristics) and the output performance data (past performance data of the crush strength under external pressure bending of a coated steel pipe after forming) in the learning data used to generate the steel pipe crush strength prediction model. The neural network model is, for example, expressed by a function.

[0047] Specifically, the model generation unit 63 sets the hyperparameters used in the neural network model and performs learning based on the neural network model using these hyperparameters. Common hyperparameters include, but are not limited to, the number of hidden layers, the number of neurons in each hidden layer, the dropout rate in each hidden layer, and the activation function in each hidden layer.

[0048] exist Figure 2The diagram illustrates the processing flow of a steel pipe crush strength prediction model generated as a neural network model by a method for generating a steel pipe crush strength prediction model according to an embodiment of the present invention.

[0049] The steel pipe crushing strength prediction model, which is a neural network model, includes an input layer 101, an intermediate layer 102, and an output layer 103 in sequence from the input side.

[0050] When the model generation unit 63 performs learning based on a neural network model using hyperparameters, the input layer 101 stores past steel pipe manufacturing characteristics information, which constitutes the learning data processed by the preprocessing unit 62. This information consists of the shape of the steel pipe after forming, the strength characteristics of the steel pipe after forming, the pipe forming strain during forming, the coating conditions, and the bending strain during laying. In other words, it stores past steel pipe manufacturing characteristics information that is standardized between 0 and 1.

[0051] The intermediate layer 102 consists of multiple hidden layers, each containing multiple neurons.

[0052] The output layer 103 combines the information from the neurons transmitted from the intermediate layer 102 and outputs the final crush strength of the coated steel pipe under pressure bending after the steel pipe is formed and coated. Based on the output result and the input past performance of the crush strength of coated steel pipes under pressure bending, the neural network model is gradually optimized to learn.

[0053] The result storage unit 64 stores the learning data, the parameters (weighting coefficients) of the neural network model, and the output results of the neural network model relative to the learning data to the storage device 9.

[0054] The steel pipe manufacturing characteristic calculation unit 7 of the calculation processing unit 5 performs the following processing: It inputs the steel pipe manufacturing characteristics of the coated steel pipe to be predicted, including the shape of the steel pipe after forming, the strength characteristics of the steel pipe after forming, the pipe-making strain during forming, the coating conditions, and the bending strain during laying, into the steel pipe crushing strength prediction model generated by the steel pipe crushing strength prediction model generation unit 6. It then predicts the crushing strength of the coated steel pipe formed after forming and then coated under external pressure bending. Furthermore, the steel pipe manufacturing characteristic calculation unit 7 performs the following processing: when the steel pipe manufacturing characteristic determination mode information is a steel pipe manufacturing characteristic determination mode, it sequentially changes at least one of the following constituting the steel pipe manufacturing characteristics—the shape of the steel pipe after forming, the strength characteristics of the steel pipe after forming, the pipe-making strain during forming, the coating conditions, and the bending strain during laying—in a manner that gradually approaches the predicted crushing strength of the coated steel pipe under pressure bending towards the desired target crushing strength of the coated steel pipe under pressure bending, thereby determining the steel pipe manufacturing characteristics.

[0055] To perform this process, such as Figure 1 As shown, the steel pipe manufacturing characteristic calculation unit 7 is a functional block that includes an information reading unit 71, a crush strength prediction unit 72, a steel pipe manufacturing characteristic determination unit 73, and a result output unit 74.

[0056] The information reading unit 71 performs the following processing: reads the steel pipe crush strength prediction model generated by the steel pipe crush strength prediction model generation unit 6, the information input to the steel pipe crush strength prediction model regarding the steel pipe that is the object of the crush strength prediction, including the shape of the steel pipe after forming, the strength characteristics of the steel pipe after forming, the pipe forming strain during forming, the coating conditions and the bending strain during laying, the information on the crush strength of the target coated steel pipe under pressure bending, and the steel pipe manufacturing characteristic determination mode information.

[0057] In addition, the crushing strength prediction unit 72 performs the following processing: it inputs the steel pipe manufacturing characteristics of the coated steel pipe, which is the object of the crushing strength prediction, which is read by the information reading unit 71, consisting of the shape of the steel pipe after forming, the strength characteristics of the steel pipe after forming, the pipe forming strain, the coating conditions, and the bending strain during laying, into the steel pipe crushing strength prediction model read by the information reading unit 71, and predicts the crushing strength of the coated steel pipe formed after coating after forming under pressure bending.

[0058] Furthermore, the steel pipe manufacturing characteristic determination unit 73 and the crushing strength prediction unit 72 perform the following processing: When the steel pipe manufacturing characteristic determination mode information read by the information reading unit 71 is a steel pipe manufacturing characteristic determination mode, the steel pipe manufacturing characteristics are determined by successively changing at least one of the following factors constituting the steel pipe manufacturing characteristics: the shape of the formed steel pipe, the strength characteristics of the formed steel pipe, the pipe forming strain, the coating conditions, and the bending strain during laying, in a manner that gradually approaches the crushing strength of the predicted coated steel pipe under pressure bending. The determined steel pipe manufacturing characteristic information is then output to the result output unit 74. Additionally, the steel pipe manufacturing characteristic determination unit 73 performs the following processing: When the steel pipe manufacturing characteristic determination mode information read by the information reading unit 71 is not a steel pipe manufacturing characteristic determination mode, the information (predicted value) of the crushing strength of the coated steel pipe under pressure bending predicted by the crushing strength prediction unit 72 is output to the result output unit 74.

[0059] In addition, the result output unit 74 performs the process of outputting the information on the determined steel pipe manufacturing characteristics or the information on the predicted crush strength of the coated steel pipe (predicted value) to the output device 10, and performs the process of storing this information to the storage device 9.

[0060] Next, refer to Figure 3The process flow of the steel pipe manufacturing characteristic calculation unit 7 in the calculation processing unit 5 of the steel pipe manufacturing characteristic determination device 1 applied to one embodiment of the present invention will be explained.

[0061] When the steel pipe manufacturing characteristic calculation unit 7 receives the calculation instruction for the steel pipe manufacturing characteristics from the input device 8, it executes the steel pipe manufacturing characteristic calculation program 42 stored in ROM 4, and performs the functions of the information reading unit 71, the crushing strength prediction unit 72, the steel pipe manufacturing characteristic determination unit 73, and the result output unit 74.

[0062] First, in step S1, the information reading unit 71 of the steel pipe manufacturing characteristic calculation unit 7 reads the steel pipe crushing strength prediction model generated by the steel pipe crushing strength prediction model generation unit 6, which is stored in the storage device 9.

[0063] Next, in step S2, the information reading unit 71 reads the information on the crushing strength of the coated steel pipe formed after the steel pipe is coated following forming, which is input into the host computer (not shown) and stored in the storage device 9, and is the target of the requirement.

[0064] Next, in step S3, the information reading unit 71 reads the information input by the operator to the input device 8 and stored in the storage device 9, which is the information of the coated steel pipe that is the prediction object input to the steel pipe crush strength prediction model. The information consists of the shape of the steel pipe after forming, the strength characteristics of the steel pipe after forming, the pipe forming strain during forming, the coating conditions, and the bending strain during laying.

[0065] Next, in step S4, the information reading unit 71 reads the steel pipe manufacturing characteristic determination mode information (information on whether it is a mode that determines the steel pipe manufacturing characteristics) that was input by the operator to the input device 8 and stored in the storage device 9.

[0066] Subsequently, in step S5, the crushing strength prediction unit 72 inputs the steel pipe manufacturing characteristics of the coated steel pipe, which is the object of prediction, read in step S3, into the steel pipe crushing strength prediction model read in step S1. These characteristics consist of the shape of the steel pipe after forming, the strength characteristics of the steel pipe after forming, the pipe forming strain during forming, the coating conditions, and the bending strain during laying. The unit then predicts the crushing strength of the coated steel pipe under pressure bending.

[0067] Steps S1 to S5 correspond to an embodiment of the present invention, which involves a method for predicting the crush strength of a coated steel pipe under pressure bending by inputting the steel pipe as the prediction object into a steel pipe crush strength prediction model generated by a method for generating a steel pipe crush strength prediction model. The method predicts the crush strength of the coated steel pipe under pressure bending by inputting the steel pipe as the prediction object into the steel pipe manufacturing characteristics, which are composed of the shape of the steel pipe after forming, the strength characteristics of the steel pipe after forming, the pipe forming strain, the coating conditions, and the bending strain during laying.

[0068] Next, in step S6, the steel pipe manufacturing characteristic determination unit 73 determines whether the steel pipe manufacturing characteristic determination mode information (information on whether it is a mode for determining steel pipe manufacturing characteristics) read in step S4 is a steel pipe manufacturing characteristic determination mode (mode for determining steel pipe manufacturing characteristics).

[0069] Furthermore, if the determination result in step S6 is yes (when the steel pipe manufacturing characteristics determination mode is in progress), proceed to step S7; if the determination result in step S6 is no (when the steel pipe manufacturing characteristics determination mode is not in progress), proceed to step S9.

[0070] In step S7, the steel pipe manufacturing characteristic determination unit 73 determines whether the difference between the crushing strength (predicted value) of the coated steel pipe under pressure bending predicted in step S5 and the crushing strength (target value) of the desired coated steel pipe under pressure bending read in step S2 is within a specified threshold.

[0071] Here, the threshold for this regulation is roughly set at 0.5% to 1%.

[0072] Furthermore, if the determination result in step S7 is yes (when it is determined that the difference between the predicted value and the target value is within the specified threshold), the process moves to step S8; if the determination result in step S7 is no (when it is determined that the difference between the predicted value and the target value is greater than the specified threshold), the process moves to step S10.

[0073] In step S10, the steel pipe manufacturing characteristic determination unit 73 changes at least one of the following in the steel pipe manufacturing characteristics of the coated steel pipe that is the object of the crushing strength prediction read in step S3: the shape of the steel pipe after forming, the strength characteristics of the steel pipe after forming, the pipe forming strain during forming, the coating conditions, and the bending strain during laying, and returns to step S5.

[0074] If returning to step S5, the crushing strength prediction unit 72 inputs at least one modified steel pipe manufacturing characteristic from step S10—the steel pipe shape after forming, the steel pipe strength characteristics after forming, the pipe forming strain, the coating conditions, and the bending strain during laying—into the steel pipe crushing strength prediction model read in step S1, and predicts again the crushing strength of the coated steel pipe under pressure bending. Then, after step S6, the steel pipe manufacturing characteristic determination unit 73 determines in step S7 whether the difference between the crushing strength (predicted value) of the coated steel pipe under pressure bending predicted again in step S5 and the target crushing strength (target value) of the coated steel pipe under pressure bending read in step S2 is within a predetermined threshold. Furthermore, steps S10, S5, S6, and S7 are repeatedly executed until this determination result is yes.

[0075] On the other hand, if the determination result in step S7 is yes (when it is determined that the difference between the predicted value and the target value is within a predetermined threshold), the process moves to step S8. In step S8, the steel pipe manufacturing characteristic determination unit 73 determines the steel pipe manufacturing characteristics, which are composed of the shape of the steel pipe after forming, the strength characteristics of the steel pipe after forming, the pipe forming strain, the coating conditions, and the bending strain during laying, when it is determined that the difference between the predicted value and the target value is within a predetermined threshold.

[0076] Steps S6, S7, S10, S5, S6, S7, and S8 correspond to a method for determining the manufacturing characteristics of a steel pipe according to an embodiment of the present invention. This method determines the manufacturing characteristics of a steel pipe by successively changing at least one of the following factors included in the manufacturing characteristics: the shape of the steel pipe after forming, the strength characteristics of the steel pipe after forming, the pipe-making strain during forming, the coating conditions, and the bending strain during laying.

[0077] Then, in step S9, if the result output unit 74 of the steel pipe manufacturing characteristic calculation unit 7 determines the steel pipe manufacturing characteristics in step S6 (in the steel pipe manufacturing characteristic determination mode), it outputs the information of the steel pipe manufacturing characteristics determined in step S8 to the output device 10. On the other hand, if the result output unit 74 determines the steel pipe manufacturing characteristics in step S6 (in the non-steel pipe manufacturing characteristic determination mode), it outputs the information (predicted value) of the crushing strength of the coated steel pipe formed after coating after steel pipe forming, predicted in step S5, during pressure bending to the output device 10.

[0078] Thus, the processing of the steel pipe manufacturing characteristic calculation unit 7 is completed.

[0079] Thus, the method for generating a steel pipe crush strength prediction model according to one embodiment of the present invention generates a steel pipe crush strength prediction model (steel pipe crush strength prediction model generation unit 6) by performing machine learning on multiple learning data to predict the crush strength of a coated steel pipe formed after coating after steel pipe forming under external pressure bending. The multiple learning data include past steel pipe manufacturing characteristics, including the shape of the steel pipe after forming, the strength characteristics of the steel pipe after forming, the pipe forming strain, the coating conditions, and the bending strain during laying, as input data, and the past crush strength of a coated steel pipe formed after coating after steel pipe forming under external pressure bending relative to the input data as output data.

[0080] Therefore, it is possible to appropriately generate a steel pipe crush strength prediction model that, in addition to the bending strain during laying, also considers the pipe forming strain and coating conditions during steel pipe forming, and accurately predicts the crush strength of coated steel pipes formed after coating.

[0081] In addition, when generating the prediction model for the crushing strength of coated steel pipes under external pressure bending, the coating conditions that have a significant impact on the crushing strength of coated steel pipes under external pressure bending are also taken into account, which makes the prediction model for the crushing strength of steel pipes more accurate.

[0082] In addition, when generating the prediction model for the crush strength of coated steel pipes under external pressure bending, the bending strain during laying, which has a significant impact on the crush strength of coated steel pipes under external pressure bending, is taken into account, thus making the prediction model for the crush strength of steel pipes more accurate.

[0083] In addition, one embodiment of the present invention relates to a method for predicting the crushing strength of a steel pipe by inputting the steel pipe crushing strength prediction model generated by the method for generating a steel pipe crushing strength prediction model into a steel pipe manufacturing characteristic of the coated steel pipe to be predicted, including the shape of the steel pipe after forming, the strength characteristics of the steel pipe after forming, the pipe forming strain, the coating conditions, and the bending strain during laying, to predict the crushing strength of the coated steel pipe formed after coating after forming (steps S1 to S5).

[0084] Therefore, in addition to the bending strain during laying, the pipe-making strain during steel pipe forming and the coating conditions are also considered to accurately predict the crushing strength of the coated steel pipe formed after coating after steel pipe forming under external pressure bending.

[0085] Furthermore, one embodiment of the present invention relates to a method for determining the manufacturing characteristics of a steel pipe, which gradually approaches the crushing strength of a predicted coated steel pipe under external pressure bending to the desired target coated steel pipe under external pressure bending by successively changing at least one of the following factors included in the manufacturing characteristics of the steel pipe: the shape of the steel pipe after forming, the strength characteristics of the steel pipe after forming, the pipe forming strain, the coating conditions, and the bending strain during laying, to determine the manufacturing characteristics of the steel pipe (steps S6, S7, S10, S5, S6, S7, and S8).

[0086] Therefore, the crushing strength of the coated steel pipe under external pressure bending, which is predicted to gradually approach the target crushing strength of the coated steel pipe under external pressure bending, is determined by the steel pipe shape after forming, the strength characteristics of the steel pipe after forming, the pipe forming strain, the coating conditions, and the bending strain during laying.

[0087] In addition, when manufacturing coated steel pipes, it is possible to establish a correlation between the information (predicted value) of the crushing strength of the coated steel pipe under pressure bending, which is predicted in step S5 and output by the output device 10, and the coated steel pipe formed in the forming process.

[0088] In other words, the steel pipe manufacturing method according to one embodiment of the present invention may also include: a coated steel pipe forming process, in which a steel pipe is formed and coated to form a coated steel pipe; a crushing strength prediction process, in which the crushing strength prediction method of the steel pipe (steps S1 to S5) is used to predict the crushing strength of the coated steel pipe formed in the coated steel pipe forming process under pressure bending; and a performance prediction value assignment process, in which the crushing strength of the coated steel pipe predicted by the crushing strength prediction process under pressure bending is associated with the coated steel pipe formed in the coated steel pipe forming process.

[0089] Here, the correlation between the predicted crushing strength of the coated steel pipe under pressure bending and the predicted value of the performance prediction value is established for the coated steel pipe, for example, by marking the coated steel pipe to assign the predicted crushing strength (predicted value) of the coated steel pipe under pressure bending, or by affixing a label to the coated steel pipe that records the predicted crushing strength (predicted value) of the coated steel pipe under pressure bending.

[0090] Therefore, those who handle coated steel pipes can determine the crushing strength (predicted value) of the coated steel pipe under pressure bending.

[0091] In addition, when manufacturing coated steel pipes, the manufacturing conditions of coated steel pipes (selection of pipe-making method, bending rate during pipe-making, strain during pipe-making, heating rate during coating, maximum temperature reached during coating, holding time of maximum temperature reached during coating, cooling rate after holding time of maximum temperature reached during coating, etc.) can be determined based on the information of the optimal steel pipe manufacturing characteristics determined in step S8 output by the output device 10. Coated steel pipes are manufactured using the manufacturing conditions determined by this.

[0092] In other words, the steel pipe manufacturing method according to one embodiment of the present invention can also determine the manufacturing conditions of the coated steel pipe based on the optimal steel pipe manufacturing characteristics determined by the method for determining the manufacturing characteristics of coated steel pipe (steps S6, S7, S10, S5, S6, S7 and S8), and manufacture the coated steel pipe with the determined manufacturing conditions of the coated steel pipe.

[0093] Therefore, the manufactured coated steel pipe meets the optimal steel pipe manufacturing characteristics determined by the design. As a result, the predicted crush strength (predicted value) of the coated steel pipe under pressure bending gradually approaches the target crush strength of the coated steel pipe under pressure bending, thus becoming a coated steel pipe with excellent crush resistance, which can avoid damage and destruction accidents to structures.

[0094] The embodiments of the present invention have been described above, but the present invention is not limited thereto and various changes and improvements can be made.

[0095] For example, in the method for generating a steel pipe crush strength prediction model, when generating the steel pipe crush strength prediction model, the past steel pipe manufacturing characteristics that become the input data only need to include the shape of the steel pipe after it has been formed, the strength characteristics of the steel pipe after it has been formed, the pipe forming strain, the coating conditions, and the bending strain during laying. Alternatively, it can include other past steel pipe manufacturing characteristics (e.g., the strength characteristics of the steel plate before the steel pipe was formed).

[0096] In addition, in the method for generating the steel pipe crush strength prediction model, when generating the steel pipe crush strength prediction model, the past steel pipe shape after forming, which becomes the input data, is not limited to the maximum outer diameter Dmax (mm), the minimum outer diameter Dmin (mm), the average outer diameter Dave (mm), the average tube sheet thickness t (mm), and the roundness (Ovality) fO (%) of the outer diameter shape of the steel pipe.

[0097] In addition, in the method for generating the steel pipe crush strength prediction model, when generating the steel pipe crush strength prediction model, the strength characteristics of the steel pipe after forming, which are used as input data, are not limited to the Young's modulus E (GPa), the Poisson's ratio μ (-), the tensile strength YS (MPa), the compressive strength 0.23%YS (stress corresponding to 0.23% strain), and the compressive strength 0.5%YS (stress corresponding to 0.5% strain).

[0098] In addition, in the method for predicting the crushing strength of steel pipes, the input to the prediction model includes the shape of the coated steel pipe after forming, the strength characteristics of the steel pipe after forming, the pipe-making strain during forming, the coating conditions, and the bending strain during laying. However, the manufacturing characteristics of the steel pipe only need to include the shape of the steel pipe after forming, the strength characteristics of the steel pipe after forming, the pipe-making strain during forming, the coating conditions, and the bending strain during laying; other manufacturing characteristics (e.g., the strength characteristics of the steel plate before forming) can also be input.

[0099] In addition, in the method for predicting the crushing strength of steel pipes, the shape of the steel pipe after forming, which is input into the steel pipe crushing strength prediction model, is not limited to the maximum outer diameter Dmax (mm), the minimum outer diameter Dmin (mm), the average outer diameter Dave (mm), the average tube sheet thickness t (mm), and the roundness (Ovality) fO (%) of the outer diameter shape of the steel pipe.

[0100] In addition, in the method for predicting the crushing strength of steel pipes, the strength characteristics of the steel pipe after forming, which are input into the steel pipe crushing strength prediction model, are not limited to the Young's modulus E (GPa), the Poisson's ratio μ (-), the tensile strength YS (MPa), the compressive strength 0.23%YS (stress corresponding to 0.23% strain), and the compressive strength 0.5%YS (stress corresponding to 0.5% strain).

[0101] In addition, the machine learning method is set to neural networks, but it is not limited to learning based on neural networks. It can apply various supervised learning, unsupervised learning, and reinforcement learning methods such as decision tree learning, logistic regression, K-nearest neighbor algorithm, support vector machine regression, Q-learning, and SARSA method.

[0102] Example

[0103] To verify the effectiveness of the present invention, the crushing strength of the coated steel pipe under pressure bending was predicted under the conditions shown in Table 2.

[0104] [Table 1]

[0105]

[0106] [Table 2]

[0107]

[0108] In Examples 1 and 2, machine learning was used to generate a steel pipe crush strength prediction model from the following training data. Each training data set included the shape of the steel pipe after past forming (maximum outer diameter Dmax (mm), minimum outer diameter Dmin (mm), average outer diameter Dave (mm), average tube sheet thickness t (mm), and roundness fO (%) of the outer diameter shape), and the strength characteristics of the steel pipe after past forming (Young's modulus E (GPa), Poisson's ratio μ (-), tensile strength YS (MPa), and compressive strength). The input data includes 0.23%YS (stress corresponding to 0.23% strain), the compressive strength of the steel pipe 0.5%YS (stress corresponding to 0.5% strain), the pipe forming strain (tensile strain (%) during pipe forming), the coating conditions (maximum temperature (°C) and holding time (min)), and the bending strain (%) during laying. The output data is the crushing strength (MPa) of the coated steel pipe formed after coating after forming, relative to the input data in the past.

[0109] Furthermore, in Example 1, the steel pipe shape after forming (maximum outer diameter Dmax (mm), minimum outer diameter Dmin (mm), average outer diameter Dave (mm), average tube sheet thickness t (mm), and roundness fO (%) of the outer diameter shape of the steel pipe) of the test material 1 shown in Table 1 were input into the generated steel pipe crushing strength prediction model. The steel pipe strength characteristics after forming (Young's modulus E (GPa), Poisson's ratio μ (-), tensile strength YS (MPa), compressive strength 0.23%YS (stress corresponding to 0.23% strain) and compressive strength 0.5%YS (stress corresponding to 0.5% strain)), pipe forming strain (tensile strain (%)), coating conditions (maximum temperature (°C) and holding time (min)) and bending strain (%) during laying were used to predict the crushing strength of the steel pipe under external pressure bending after forming.

[0110] In addition, in Example 2, the steel pipe shape after forming of the test material 2 (maximum outer diameter Dmax (mm), minimum outer diameter Dmin (mm), average outer diameter Dave (mm), average tube sheet thickness t (mm), and roundness fO (%) of the outer diameter shape) of the steel pipe were input into the generated steel pipe crush strength prediction model, as shown in Table 1. The steel pipe strength characteristics after forming (Young's modulus E (GPa), Poisson's ratio μ (-), tensile strength YS (MPa), compressive strength 0.23%YS (stress corresponding to 0.23% strain) and compressive strength 0.5%YS (stress corresponding to 0.5% strain)), pipe forming strain (tensile strain (%)), coating conditions (maximum temperature (°C) and holding time (min)) and bending strain (%) during laying were used to predict the crush strength of the steel pipe under external pressure bending after forming.

[0111] In addition, in Example 1, the actual crush strength of the test material 1 under external pressure bending as shown in Table 1 was measured (actual tube test results).

[0112] In addition, in Example 2, the actual crush strength of the test material 2 under external pressure bending as shown in Table 1 was measured (actual tube test results).

[0113] In addition, in Comparative Example 1, the shape of the steel pipe after forming (maximum outer diameter Dmax (mm), minimum outer diameter Dmin (mm), average outer diameter Dave (mm), average tube sheet thickness t (mm), and roundness fO (%) of the outer diameter shape of the steel pipe), the strength characteristics of the steel pipe after forming (Young's modulus E (GPa), Poisson's ratio μ (-), and tensile strength YS (MPa)) of the steel pipe, and the bending strain (%) during laying of the steel pipe were input into the predictive formula shown in Non-Patent Document 1, and the prediction of the crushing strength of the coated steel pipe during bending processing after forming was made.

[0114] In addition, in Comparative Example 2, the shape of the steel pipe after forming of the test material 2 (maximum outer diameter Dmax (mm), minimum outer diameter Dmin (mm), average outer diameter Dave (mm), average tube sheet thickness t (mm), and roundness (Ovality) fO (%)) of the outer diameter shape of the steel pipe) and the strength characteristics of the steel pipe after forming (Young's modulus E (GPa), Poisson's ratio μ (-), and tensile strength YS (MPa)) and bending strain (%) during laying were input into the predictive formula shown in Non-Patent Document 1, and the crushing strength of the coated steel pipe during bending processing after forming was predicted.

[0115] In addition, in Comparative Example 1, the actual crush strength of test material 1 under external pressure bending as shown in Table 1 was measured (actual tube test results).

[0116] In addition, in Comparative Example 2, the actual crush strength of the test material 2 under external pressure bending as shown in Table 1 was measured (actual tube test results).

[0117] The judgment criteria for the actual tube test results in Examples 1-2 and Comparative Examples 1-2 are the same. The difference between the actual crushing strength obtained in the experiment and the standard reference value is evaluated. The case where the actual crushing strength is lower than the standard reference value is set as NG. The case where the actual crushing strength exceeds the standard reference value by less than 10% is set as C. The case where the actual crushing strength exceeds the standard reference value by more than 10% but less than 20% is set as B. The case where the actual crushing strength exceeds the standard reference value by more than 20% is set as A.

[0118] As a result, in Example 1, the actual crush strength of the coated steel pipe under external pressure bending (actual pipe test result) exceeded the standard benchmark value (specified standard value) by more than 20%, and the judgment result was A. In addition, the predicted value of the crush strength of the coated steel pipe under external pressure bending using the steel pipe crush strength prediction model also exceeded the standard benchmark value (specified standard value) by more than 20%, and the judgment result was A. The experimental evaluation and prediction results were consistent.

[0119] In addition, in Example 2, the actual crush strength of the coated steel pipe under external pressure bending (actual pipe test result) exceeded the standard reference value (specified standard value) by more than 10% and less than 20%, and the judgment result was B. The predicted value of the crush strength of the coated steel pipe under external pressure bending using the steel pipe crush strength prediction model also exceeded the standard reference value (specified standard value) by more than 10% and less than 20%, and the judgment result was B. The experimental evaluation and prediction results were consistent.

[0120] On the other hand, in Comparative Example 1, the actual crush strength of the coated steel pipe under external pressure bending (actual pipe test result) exceeded the standard reference value (specified standard value) by more than 20%, and the judgment result was A. However, the predicted value of the crush strength of the coated steel pipe under external pressure bending using the predictive method shown in Non-Patent Document 1 exceeded the standard reference value (specified standard value) by less than 10%, and the judgment result was C. The experimental evaluation and the predicted result were inconsistent.

[0121] Furthermore, in Comparative Example 2, the actual crush strength of the coated steel pipe under external pressure bending (actual pipe test result) exceeded the standard reference value (specified standard value) by more than 10% and less than 20%, and the judgment result was B. However, the predicted value of the crush strength of the coated steel pipe under external pressure bending using the predictive method shown in Non-Patent Document 1 exceeded the standard reference value (specified standard value) by less than 10%, and the judgment result was C. The experimental evaluation and the predicted result were inconsistent.

[0122] Therefore, as explained in Examples 1 and 2, in this invention, the predicted values ​​of the crushing strength of the coated steel pipe under pressure bending are consistent with the experimental results, confirming high prediction accuracy.

[0123] Explanation of reference numerals in the attached figures

[0124] 1. Steel pipe manufacturing characteristics determination device

[0125] 2. Arithmetic Unit

[0126] 3RAM

[0127] 4ROM

[0128] 5. Computational Processing Unit

[0129] 6. Steel Pipe Crushing Strength Prediction Model Generation Section

[0130] 7 Steel Pipe Manufacturing Characteristics Calculation Department

[0131] 8 input devices

[0132] 9 storage devices

[0133] 10 output devices

[0134] 11 bus

[0135] 41 Steel Pipe Crushing Strength Prediction Model Generation Program

[0136] Calculation program for manufacturing characteristics of 42 steel pipe

[0137] 61 Learning Data Acquisition Department

[0138] 62 Pre-processing Department

[0139] 63 Model Generation Department

[0140] 64 Results Preservation Department

[0141] 71 Information Reading Department

[0142] 72 Crushing Intensity Prediction Department

[0143] 73 Steel Pipe Manufacturing Characteristics Determination Department

[0144] 74 Results Output Section

[0145] 101 Input Layer

[0146] 102 intermediate layer

[0147] 103 Output layer.

Claims

1. A method for generating a prediction model for the crushing strength of steel pipes, characterized in that, Machine learning is applied to multiple training datasets to generate a steel pipe crush strength prediction model that predicts the crush strength of coated steel pipes formed after coating during external pressure bending. The training datasets include past steel pipe manufacturing characteristics as input data, such as the shape of the steel pipe after forming, the strength characteristics of the steel pipe after forming, the pipe-making strain during forming, the coating conditions, and the bending strain during laying. The output data is the past crush strength of coated steel pipes formed after coating relative to these input data during external pressure bending. The steel pipe shape after forming is defined by the maximum outer diameter Dmax (mm), the minimum outer diameter Dmin (mm), the average outer diameter Dave (mm), the average tube sheet thickness t (mm), and the roundness fO (%) of the outer diameter shape. The strength characteristics of the steel pipe after forming are defined by the Young's modulus E (GPa), the Poisson's ratio μ (-), the tensile strength YS (MPa), the compressive strength 0.23%YS, and the compressive strength 0.5%YS. The pipe forming strain is defined as the tensile strain (%) or compressive strain (%) during forming. The coating conditions are defined as the maximum temperature and holding time during coating. The bending strain during laying is defined as the tensile strain (%) or compressive strain (%) during the laying of the coated steel pipe.

2. The method for generating the steel pipe crushing strength prediction model according to claim 1, characterized in that, The machine learning method mentioned is a neural network, and the steel pipe crush strength prediction model is a prediction model constructed by a neural network.

3. A method for predicting the crushing strength of steel pipes, characterized in that, The steel pipe crush strength prediction model generated by the method of generating the steel pipe crush strength prediction model according to claim 1 or 2 is input with the steel pipe manufacturing characteristics of the coated steel pipe as the prediction object, including the shape of the steel pipe after forming, the strength characteristics of the steel pipe after forming, the pipe forming strain, the coating conditions and the bending strain during laying, to predict the crush strength of the coated steel pipe formed by coating after forming under external pressure bending.

4. A method for determining the manufacturing characteristics of a steel pipe, characterized in that, The steel pipe manufacturing characteristics are determined by successively changing at least one of the following: the shape of the steel pipe after forming, the strength characteristics of the steel pipe after forming, the pipe forming strain during forming, the coating conditions, and the bending strain during laying, in order to make the crushing strength of the coated steel pipe predicted by the crushing strength prediction method of the steel pipe according to claim 3 gradually approach the desired crushing strength of the coated steel pipe during external pressure bending.

5. A method for manufacturing a steel pipe, characterized in that, include: The coating steel pipe forming process involves forming a steel pipe and then coating the formed steel pipe to form a coated steel pipe; the crush strength prediction process involves using the crush strength prediction method for steel pipes as described in claim 3 to predict the crush strength of the coated steel pipe formed in the coating steel pipe forming process under external pressure bending; and the performance prediction value assignment process involves establishing a correlation between the crush strength of the coated steel pipe predicted by the crush strength prediction process under external pressure bending and the coated steel pipe formed in the coating steel pipe forming process.

6. A method for manufacturing a steel pipe, characterized in that, The manufacturing conditions for the coated steel pipe are determined based on the manufacturing characteristics of the steel pipe determined by the manufacturing characteristics determination method of the steel pipe according to claim 4, and the coated steel pipe is manufactured under the determined manufacturing conditions.

Images