Steel pipe total cross-section performance prediction method, device, equipment, medium and product

Abstract

The invention discloses a steel pipe total cross-section performance prediction method, device and equipment, a medium and a product. The method comprises the following steps: carrying out an indentation test on a to-be-tested steel pipe, and determining a surface indentation load displacement curve and surface indentation contour morphology characteristics of the to-be-tested steel pipe; inputting the surface press-in load displacement curve and the surface indentation contour morphology characteristics of the steel pipe to be tested into a pipe surface performance prediction model obtained by pre-training to obtain the material surface performance and the surface stress state output by the model; inputting the surface press-in load displacement curve, the surface indentation contour morphology characteristics, the material surface performance and the surface stress state of the steel pipe to be tested into a pre-trained pipe total cross-section performance prediction model; the section indentation load displacement curve, the section indentation contour morphology feature, the material section performance and the section stress state of the to-be-tested steel pipe under the sections corresponding to different pipeline wall thicknesses are obtained. The section indentation load displacement curve, the section indentation contour morphology feature, the material section performance and the section stress state are output by the model.

Description

Technical Field

[0001] The present invention relates to the technical field of material mechanical property testing, and particularly to a method, device, equipment, medium and product for predicting the full-section performance of steel pipes. Background Art

[0002] The non-destructive testing of the mechanical properties and stresses of steel pipe materials is one of the important technologies in the process of pipeline safety inspection. Its non-destructive advantage can ensure that inspectors evaluate the pipeline safety status according to the test results during the pipeline operation.

[0003] At present, the safety testing methods for steel pipe materials can be roughly divided into three categories: flaw detection, mechanical property testing, and stress detection. The existing three testing technologies are diverse, with a large number of types, and the testing process is cumbersome, requiring coordination of a large amount of manpower and material resources. Moreover, the testing standards among the various technologies are not unified, and the results obtained from each other are difficult to ensure direct use, and the testing accuracy is insufficient. Moreover, the above technical means are difficult to simultaneously meet the testing and evaluation of the material mechanical properties and structural stress states of the full cross-section of steel pipe materials. Summary of the Invention

[0004] The present invention provides a method, device, equipment, medium and product for predicting the full-section performance of steel pipes, so as to realize non-destructive prediction of the full-section material mechanical properties and stress states of steel pipes, and improve the prediction accuracy and prediction efficiency.

[0005] According to one aspect of the present invention, there is provided a method for predicting the full-section performance of steel pipes, the method comprising:

[0006] Performing an indentation test on the steel pipe to be tested to determine the surface indentation load-displacement curve and the surface indentation profile feature of the steel pipe to be tested;

[0007] Inputting the surface indentation load-displacement curve and the surface indentation profile feature of the steel pipe to be tested into a pre-trained pipe surface performance prediction model to obtain the material surface performance and surface stress state output by the model;

[0008] Inputting the surface indentation load-displacement curve, the surface indentation profile feature, the material surface performance and the surface stress state of the steel pipe to be tested into a pre-trained pipe full-section performance prediction model to obtain the cross-section indentation load-displacement curve, the cross-section indentation profile feature, the material cross-section performance and the cross-section stress state of the steel pipe to be tested under each cross-section; the pipe wall thickness depths of the respective cross-sections of the steel pipe to be tested are different.

[0009] According to another aspect of the present invention, there is provided a device for predicting the full-section performance of steel pipes, the device comprising:

[0010] Indentation test module, used to perform indentation tests on the steel pipes to be tested, and determine the surface indentation load-displacement curve and the surface indentation profile characteristics of the steel pipes to be tested;

[0011] Surface material property prediction module, used to input the surface indentation load-displacement curve and the surface indentation profile characteristics of the steel pipes to be tested into a pre-trained pipe surface property prediction model, and obtain the material surface properties and surface stress states output by the model;

[0012] Full-section material property prediction module, used to input the surface indentation load-displacement curve, the surface indentation profile characteristics, the material surface properties and the surface stress states of the steel pipes to be tested into a pre-trained pipe full-section property prediction model, and obtain the cross-section indentation load-displacement curve, the cross-section indentation profile characteristics, the material cross-section properties and the cross-section stress states of the steel pipes to be tested under each cross-section; the pipe wall thickness depths of each cross-section of the steel pipes to be tested are different.

[0013] According to another aspect of the present invention, there is provided an electronic device, which includes:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the full-section property prediction method of steel pipes according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, there is provided a computer-readable storage medium, which stores computer instructions for implementing the full-section property prediction method of steel pipes according to any embodiment of the present invention when the computer instructions are executed by a processor.

[0018] According to another aspect of the present invention, there is provided a computer program product, which includes a computer program that implements the above-mentioned full-section property prediction method of steel pipes when the computer program is executed by a processor.

[0019] In the technical solution of the embodiment of the present invention, a surface performance prediction model of a pipe is used to predict the surface performance and surface stress state of a steel pipe to be measured based on the surface indentation load-displacement curve and the surface indentation profile morphology characteristics of the steel pipe to be measured. Then, a comprehensive performance prediction model of the pipe is used to perform the cross-section indentation load-displacement curve, cross-section indentation profile morphology characteristics, material cross-section performance, and cross-section stress state of each cross-section at each pipe wall thickness depth based on the surface indentation load-displacement curve, surface indentation profile morphology characteristics, material surface performance, and surface stress state of the steel pipe to be measured, realizing non-destructive testing of parameters such as the mechanical properties and pressure state of the full cross-section of the pen pipe, reducing the input of detection personnel, and improving the detection efficiency; at the same time, reducing the result error caused by inconsistent detection standards among existing detection technologies, improving the detection accuracy of the material mechanical characteristics of each cross-section of the steel pipe, and further realizing the safety assessment of the cross-section of the steel pipe.

[0020] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0022] Figure 1 is a flowchart of a method for predicting the full cross-section performance of a steel pipe according to Embodiment 1 of the present invention;

[0023] Figure 2 is a schematic diagram of the division of the test specimen area based on the pipeline steel plate according to Embodiment 1 of the present invention;

[0024] Figure 3 is a schematic structural diagram of obtaining an indentation profile by performing an indentation test on an indentation test specimen with a spherical indenter according to Embodiment 1 of the present invention;

[0025] Figure 4 is a schematic diagram showing an indentation test specimen with biaxial stress applied according to Embodiment 1 of the present invention;

[0026] Figure 5 is a schematic diagram of the position selection of a small punch specimen according to Embodiment 1 of the present invention;

[0027] Figure 6It is a flowchart of a method for predicting the full-section performance of steel pipes according to Embodiment 2 of the present invention;

[0028] Figure 7 It is a schematic structural diagram of a device for predicting the full-section performance of steel pipes according to Embodiment 3 of the present invention;

[0029] Figure 8 It is a schematic structural diagram of an electronic device for implementing the method for predicting the full-section performance of steel pipes in the embodiments of the present invention. Detailed implementation manners

[0030] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0032] Embodiment 1

[0033] Figure 1 It is a flowchart of a method for predicting the full-section performance of steel pipes provided in Embodiment 1 of the present invention. This embodiment is applicable to the situation of non-destructively predicting the material mechanical properties and stress states of different cross-sections or different pipe wall thickness depths of steel pipes. This method can be executed by a device for predicting the full-section performance of steel pipes, which can be implemented in the form of hardware and / or software, and the device for predicting the full-section performance of steel pipes can be configured in an electronic device. As Figure 1 shown, the method includes:

[0034] S110. Perform an indentation test on the steel pipe to be tested to determine the surface indentation load-displacement curve and the surface indentation profile feature of the steel pipe to be tested.

[0035] S120. Input the surface indentation load-displacement curve and the surface indentation profile morphological characteristics of the steel pipe to be tested into the pre-trained pipe surface property prediction model, and obtain the material surface properties and surface stress states output by the model.

[0036] S130. Input the surface indentation load-displacement curve, the surface indentation profile morphological characteristics, the material surface properties and the surface stress states of the steel pipe to be tested into the pre-trained pipe full-section property prediction model, and obtain the cross-section indentation load-displacement curve, the cross-section indentation profile morphological characteristics, the material cross-section properties and the cross-section stress states of the steel pipe to be tested under each cross-section; the pipe wall thickness depths of each cross-section of the steel pipe to be tested are different.

[0037] Among them, the steel pipe to be tested can be the steel pipe material to be subjected to pipe safety assessment. It should be noted that the material mechanical properties, stress states, profile morphological characteristics and indentation-load displacement curve characteristics exhibited by the steel pipe on its surface and at the cross-sections corresponding to its different pipe wall thickness depths are different, and the material mechanical properties, stress states, profile morphological characteristics and indentation-load displacement curve characteristics, etc. on the surface of the pipe and at its different cross-sections can be used to evaluate the pipe safety and compliance of the steel pipe.

[0038] Among them, the pipe surface property prediction model is used to predict the material mechanical properties and stress states of the material surface of the steel pipe; the pipe full-section property prediction model is used to predict parameters such as the material mechanical properties and stress states of each surface under different pipe wall thickness depths of the steel pipe.

[0039] This embodiment provides a model training method for the pipe surface property prediction model. The specific implementation method is as follows: perform indentation tests on indentation test specimens of different materials under different stress states to obtain the specimen indentation load-displacement curve and the indentation material properties; the indentation test specimens include indentation profile morphology; perform feature analysis on the indentation profile morphology of the indentation test specimens to obtain the specimen indentation profile morphological characteristics; generate a first training sample including the specimen indentation profile morphological characteristics and the indentation load-displacement curve; among them, the stress state and the indentation material properties are marked as the sample label values of the specimen indentation profile morphological characteristics and the indentation load-displacement curve; input the first training sample into the pre-constructed first network model to obtain the predicted stress and predicted material properties output by the model; according to the predicted stress, predicted material properties, stress state and indentation material properties of the training sample, perform model training on the first network model until the preset model training end condition is met, and obtain the pipe surface property prediction model.

[0040] Among them, the indentation test specimens can be prepared in advance. Specifically, for the indentation test specimens of the same material, the unrolled pipeline steel plate can be divided into regions, such as Figure 2 A schematic diagram of the regional division of test specimens based on pipeline steel plates as shown. The regions marked with numbers are used as indentation test specimens for indentation tests; the regions marked with the symbol "△" are used as uniaxial tensile test specimens for uniaxial tensile tests. The uniaxial tensile test is used to adjust the material mechanical property errors.

[0041] For any indentation test specimen, an indentation test under different stress states is carried out on the indentation test specimen. For example, taking the stress state of zero stress as an example, the indentation test specimen is polished. The surface of the material to be measured is polished to be smooth with 800-mesh sandpaper. The indentation test specimen is subjected to aging heat treatment to eliminate the residual stress introduced by processing or cutting through thermal relaxation, ensuring that the specimen is in a zero-stress state, and an indentation test specimen with zero stress is prepared. An indentation test is carried out on the indentation test specimen in the zero-stress (stress-free) state. Specifically, a pre-selected test device, such as a nano-indentation instrument, etc., is used, and a standard indenter is used to load at a constant rate until the preset maximum load, and then unload after maintaining the peak load for 5 seconds. The load and indenter displacement data are recorded in real time to generate an indentation load-displacement curve.

[0042] Based on the Oliver-Pharr (O-P) method and the energy method, the indentation material properties of the indentation test specimen can be obtained. Among them, the indentation material properties can include material elastic modulus, hardness, yield strength, fracture toughness, etc. Specifically, curve analysis is carried out on the indentation load-displacement curve to extract key curve parameters such as the maximum indentation load, the maximum indentation depth, and the residual indentation depth; the loading section curve and the unloading section curve in the indentation load-displacement curve are respectively fitted, and linear or exponential functions are used to fit to obtain curve fitting parameters such as the loading energy, the unloading energy, and the slope of the unloading section curve. According to the key curve parameters and the curve fitting parameters, based on the energy method and the OP method, the indentation material properties of the indentation test specimen are calculated, including material elastic modulus, hardness, yield strength, fracture toughness, etc.

[0043] It should be noted that since an indentation test is carried out on the indentation test specimen, during the test process, there is an indentation contour morphology left on the indentation test specimen during the pressing process by the indenter. Such as Figure 3 A schematic structural diagram of the indentation contour morphology obtained by performing an indentation test on an indentation test specimen with a spherical indenter as shown.

[0044] Specifically, a high-precision laser scanner is used to extract the indentation degradation morphology of the indentation test specimen under indentation, and the least squares method is used to fit an ellipse to the indentation contour morphology. By calculating the major axis / minor axis ratio and the roundness deviation value, it can be used to evaluate the asymmetry of the indentation. By extracting the gradient change data of the indentation edge, the local height peak of the edge protrusion can be identified, the stacking height ratio and the area of the subsidence area can be calculated. Combining the analysis of the indentation load-displacement curve, the plastic stacking characteristics of the material at the indentation contour edge and the degree of change of the indentation contour ellipse can be obtained. The degree of change of the indentation contour ellipse and the plastic stacking characteristics of the material at the indentation contour edge are used as the indentation contour morphology characteristics of the indentation test specimen under indentation. Among them, the plastic stacking characteristics of the material at the indentation contour edge can be, for example, the edge stacking rate; the degree of change of the indentation contour ellipse can be, for example, the ellipticity index. It should be noted that the indentation contour morphology characteristics of the test specimen can include, but are not limited to, the plastic stacking characteristics of the material at the indentation contour edge and the degree of change of the indentation contour ellipse. For example, it can also include the residual indentation depth, the height of the indentation edge bulge, the indentation diameter, and the ellipticity of the indentation contour, etc. Specifically, it can be obtained by further feature analysis of the indentation contour morphology according to actual needs.

[0045] To reduce the performance error of the indentation material properties obtained based on the indentation test, error correction of the indentation material properties can be performed based on the uniaxial tensile test. In an alternative embodiment, after performing the indentation test on the indentation test specimens of different materials under different stress states to obtain the specimen indentation load-displacement curve and the indentation material properties, it further includes: performing a uniaxial tensile test on the pre-prepared pipeline steel specimen to be tested to obtain the uniaxial tensile material properties of the pipeline steel specimen to be tested; performing an indentation test on the pipeline steel specimen to be tested to obtain the indentation material properties of the pipeline steel specimen to be tested; determining the material property correction error according to the uniaxial tensile material properties and the indentation material properties of the pipeline steel specimen to be tested; using the material property correction error to correct the error of the indentation material properties of the indentation test specimen to obtain the corrected indentation material properties.

[0046] Among them, the materials of the prepared pipeline steel specimens to be tested are different, and specifically can include several material types of pipeline steel to be tested. For the pipeline steel to be tested of the same material type, the unrolled pipeline steel can be divided into regions. For example, as Figure 2 shown in a schematic diagram of the test specimen region division based on pipeline steel plates. The region marked with "△" is used as the uniaxial tensile test specimen for performing the uniaxial tensile test. Among them, the uniaxial tensile test specimen is the pipeline steel specimen to be tested, and the relative position of each specimen in the unrolled pipeline steel has been pre-marked.

[0047] For a test pipe steel specimen at any marked position in the unrolled pipe steel, a uniaxial tensile test is performed on the specimen, the load-displacement curve is recorded, and the engineering stress and engineering strain are collected simultaneously; key parameters in the elastic stage, plastic stage, and fracture stage are collected, and combined with the key parameters, the collected engineering stress-strain curve is converted into a true stress-strain curve. Feature parameters are extracted from the true stress-strain curve to obtain the uniaxial tensile material properties of the test pipe steel specimen, including elastic modulus, yield strength, tensile strength, fracture toughness, etc. For other regions (regions without the "△" mark) in the unrolled pipe steel of the same material, its material mechanical properties can be calculated by taking the average value of the uniaxial tensile material properties of the test pipe steel specimens in the adjacent regions marked with the "△" mark around it.

[0048] However, it should be noted that if there are only two test pipe steel specimens marked with the "△" mark in the adjacent regions around other regions (regions without the "△" mark), then first calculate the average value of the uniaxial tensile material properties of the test pipe steel specimens marked with four "△" marks in the adjacent regions around it, and then calculate the average value of the remaining regions, so as to ensure that there are four test pipe steel specimens marked with the "△" mark around the regions without the "△" mark.

[0049] The determination method of the uniaxial tensile material properties of the test pipe steel specimens of other material types is the same, and this embodiment will not elaborate on this.

[0050] A indentation test is performed on the test pipe steel specimen to obtain the indentation material properties of the test pipe steel specimen; here it should be noted that for pipe steel with uneven material distribution, during the process of error determination, the indentation test specimen and the test pipe steel specimen (uniaxial tensile test specimen) should be the same specimen; while for pipe steel with uniform material distribution, during the process of error determination, the indentation test specimen and the test pipe steel specimen (uniaxial tensile test specimen) can be different specimens.

[0051] The difference in performance parameters between the uniaxial tensile material properties and the indentation material properties of the test pipe steel specimen is used as the material property correction error. If the number of test pipe steel specimens is multiple and the materials are the same, the material property correction error can be the average value of multiple performance parameter differences.

[0052] Based on the material property correction error, the indentation material properties of the indentation test specimen are corrected for error to obtain the corrected indentation material properties, and the corrected indentation material properties are used to participate in the subsequent process of constructing the model training samples.

[0053] By conducting uniaxial tensile tests on steel specimens, the uniaxial tensile material properties are determined, and the calculation of performance correction errors is carried out based on the material properties obtained from the uniaxial tensile tests and the material properties obtained from the indentation tests. Thus, the indentation material properties of the indentation test specimens are corrected based on the performance correction errors, improving the accuracy of determining the indentation material properties, and thus improving the accuracy of constructing the sample data required for subsequent model training.

[0054] An indentation test is carried out on the indentation test specimens by applying different biaxial prestresses to obtain the indentation material properties under different stress states, and the indentation profile morphology of the indentation test specimens under different biaxial prestresses is analyzed for its characteristics to obtain the characteristics of the specimen indentation profile morphology. The specific implementation is the same as that of the above stress-free scenario, and this embodiment will not elaborate on it here. It should be noted that in addition to the above zero stress and biaxial prestress, different stress states may also include uniaxial stress and non-equal biaxial stress, etc. Tests can be carried out under different stress states according to actual needs to obtain the characteristics of the specimen indentation profile morphology and the indentation material properties under different stress states. Exemplarily, as Figure 4 shown in the schematic diagram of an indentation test specimen with biaxial stress applied. Specifically, strain gauges in the X direction and Y direction are pasted on the prepared indentation test specimen, and an indentation test is carried out on the indentation test specimen by applying biaxial stress.

[0055] Taking any indentation test specimen as an example, a first training sample is generated. Among them, the first training sample includes the characteristics of the specimen indentation profile morphology and the indentation load-displacement curve, and the corresponding stress state and indentation material properties are marked as the sample label values of the characteristics of the specimen indentation profile morphology and the indentation load-displacement curve, that is, the sample true values. Optionally, orthogonal combination tests can be carried out on the first training sample for multi-factor orthogonal combination tests and analyses of the indentation material properties and stress states, so as to obtain different combined training samples and realize the improvement of the sample training set.

[0056] The characteristics of the specimen indentation profile morphology, the indentation load-displacement curve, and their corresponding stress states and indentation material properties are input into a pre-constructed first network model to obtain the predicted stress and predicted material properties output by the model. Among them, the first network model can be a neural network model, such as a feedforward neural network (FNN) or a convolutional neural network (CNN), etc., or it can also be a machine learning model, such as a decision tree or a random forest, etc.

[0057] Based on the predicted stress obtained from model prediction and the stress state of the true sample label value, as well as the predicted material properties obtained from model prediction and the indentation material properties of the true sample label value, the current loss value at the current iteration cycle is determined based on a preset loss function; according to the current loss value, the first network model is trained until the preset model training end condition is met, and a pipe surface property prediction model is obtained. Among them, the model training end condition can be preset by relevant technicians. For example, the model training end condition can be that the current loss value reaches a preset loss threshold, or the loss value tends to be stable, or the current number of iterations reaches the set iteration number threshold, etc.

[0058] Among them, the pipe full-section property prediction model can predict the cross-section characteristic data of each cross-section at different pipe wall thickness depths based on the characteristic data on the surface of the pipe, such as the surface indentation load-displacement curve, the surface indentation profile morphology characteristics, the material surface properties, and the surface stress state, such as the cross-section indentation load-displacement curve, the cross-section indentation profile morphology characteristics, the material cross-section properties, and the cross-section stress state under each cross-section.

[0059] This embodiment also provides a training method for the pipe full-section property prediction model. The specific implementation method is: constructing a second training sample of a full-section test specimen; the second training sample includes the surface property parameters of the pipe surface of the full-section test specimen and the cross-section property parameters at different wall thickness depths; the surface property parameters include the surface indentation load-displacement curve, the surface indentation profile morphology characteristics, the material surface properties, and the surface stress state; the cross-section property parameters include the cross-section indentation load-displacement curve, the cross-section indentation profile morphology characteristics, the material cross-section properties, and the cross-section stress state; using the second training sample to train a pre-constructed second network model until the preset model training end condition is met, and a pipe full-section property prediction model is obtained.

[0060] The full-section test specimen is a steel pipe profile at different pipe wall thickness depths of the pipe. The specific preparation method can be: combining the welding process and the characteristics of multi-layer and multi-pass welding of the weld, using the slow wire cutting technology in the electric discharge machining process to cut the full-section test specimen along the generatrix direction, and dividing the pipe cross-section based on the selected position, such as Figure 5 as shown in the schematic diagram of the position selection of a small punch specimen, the pipe is sequentially layered along the thickness direction to prepare small punch specimens. During the preparation process of the small punch specimens, the groove form, the alignment method, the characteristics of the welding consumables, and the material thickness can also be comprehensively considered to achieve the precise preparation of the small punch specimens.

[0061] In an alternative embodiment, constructing a second training sample of full-section test specimens includes: performing indentation tests under different pressure states and analyzing the characteristics of the indentation profile morphology on full-section test specimens of different materials to obtain surface performance parameters of the pipe surface of the full-section test specimens; determining cross-section performance parameters of the punch specimens prepared after cutting the full-section test specimens along the generatrix at different wall thickness depths; generating a second training sample including the surface performance parameters of the pipe surface of the full-section test specimens; wherein, the cross-section performance parameters at different wall thickness depths are labeled as the sample label values of the surface performance parameters.

[0062] The prepared punch specimens are distinguished and specifically divided into pipe base metal specimens and pipe welded joint specimens. For the pipe base metal specimens, considering that the material uniformity in the pipe base metal area is relatively good, indentation tests can be directly performed at four points, namely 12, 3, 6, and 9 on the pipe cross-section. The specific points can be referred to Figure 5 . For the pipe welded joint specimens, indentation tests are directly performed on the cross-section of the specimens. Among them, the cross-section performance parameters include the cross-section indentation load-displacement curve, cross-section indentation profile morphology characteristics, material cross-section performance, and cross-section stress state corresponding to each cross-section at different wall thickness depths.

[0063] Generate a second training sample including the surface performance parameters of the pipe surface of the full-section test specimens; wherein, the cross-section performance parameters at different wall thickness depths are labeled as the sample label values of the surface performance parameters. Input the second training sample into the second network model for model training to obtain the predicted cross-section performance parameters output by the model; based on the true cross-section performance parameters in the label and the predicted cross-section performance parameters predicted by the model, determine the current loss value based on a preset loss function; perform model training on the second network model based on the current loss value in the current iteration cycle until the preset model training end condition is met to obtain the pipe full-section performance prediction model. For example, the model training end condition can be preset by those skilled in the relevant art. For example, the model training end condition can be that the current loss value reaches a preset loss threshold, or the loss value tends to be stable, or the current iteration number reaches the set iteration number threshold, etc.

[0064] Taking an actual usage scenario of the pipe surface performance prediction model and the pipe full-section performance prediction model as an example to illustrate the model usage scenario.

[0065] Obtain the steel pipe to be tested for predicting the full-section performance of the pipe, and conduct an indentation test on the surface of the steel pipe to be tested to obtain the surface indentation load-displacement curve and the surface indentation profile morphology characteristics of the steel pipe to be tested. Input the surface indentation load-displacement curve and the surface indentation profile morphology characteristics of the steel pipe to be tested into the pre-trained pipe surface performance prediction model, and the material surface performance and surface stress state predicted by the model can be obtained. Input the surface indentation load-displacement curve, the surface indentation profile morphology characteristics, the material surface performance and the surface stress state of the steel pipe to be tested into the pre-trained pipe full-section performance prediction model, and obtain the cross-section indentation load-displacement curve, the cross-section indentation profile morphology characteristics, the material cross-section performance and the cross-section stress state of each cross-section of the steel pipe to be tested at different pipe wall thickness depths output by the model.

[0066] In the technical solution of the embodiment of the present invention, by using the pipe surface performance prediction model to predict the material surface performance and surface stress state of the steel pipe to be tested based on the surface indentation load-displacement curve and the surface indentation profile morphology characteristics of the steel pipe to be tested, and then using the pipe comprehensive performance prediction model to perform the cross-section indentation load-displacement curve, the cross-section indentation profile morphology characteristics, the material cross-section performance and the cross-section stress state of each cross-section at different pipe wall thickness depths based on the surface indentation load-displacement curve, the surface indentation profile morphology characteristics, the material surface performance and the surface stress state of the steel pipe to be tested, the non-destructive testing of parameters such as the full-section mechanical properties and pressure state of the pen pipe is realized, the input of detection personnel is reduced, and the detection efficiency is improved; at the same time, the result error caused by the non-uniform detection standards of the existing detection technologies is reduced, and the detection accuracy of the material mechanical characteristics of each cross-section of the steel pipe is improved, so as to further realize the safety assessment of the cross-section of the steel pipe.

[0067] Embodiment 2

[0068] Figure 6 It is a flowchart of a method for predicting the full-section performance of a steel pipe provided in Embodiment 2 of the present invention. Based on the above embodiment, this embodiment provides a preferred example.

[0069] As Figure 6 shown, the method includes the following specific steps:

[0070] Conduct indentation tests on indentation test specimens of different materials under different stress states to obtain the specimen indentation load-displacement curve and the indentation material performance.

[0071] Perform a uniaxial tensile test on a pre-prepared test pipe steel specimen to obtain the uniaxial tensile material properties of the test pipe steel specimen; perform an indentation test on the test pipe steel specimen to obtain the indentation material properties of the test pipe steel specimen; determine the material property correction error based on the uniaxial tensile material properties and indentation material properties of the test pipe steel specimen; use the material property correction error to correct the indentation material properties of the indentation test specimen to obtain the corrected indentation material properties.

[0072] Among them, the indentation test specimen includes the indentation profile morphology. Perform feature analysis on the indentation profile morphology of the indentation test specimen to obtain the specimen indentation profile morphology features; generate a first training sample including the specimen indentation profile morphology features and the indentation load-displacement curve; among them, the stress state and the indentation material properties are labeled as the sample tag values of the specimen indentation profile morphology features and the indentation load-displacement curve; input the first training sample into a pre-constructed first network model to obtain the predicted stress and predicted material properties output by the model; according to the predicted stress, predicted material properties, stress state and indentation material properties of the training sample, perform model training on the first network model until the preset model training end condition is met to obtain a pipe surface property prediction model. Among them, the specimen indentation profile morphology features include the degree of change of the indentation profile ellipse and the material accumulation characteristics at the indentation profile edge, etc.

[0073] Perform an indentation test on full-section test specimens of different materials under different pressure states and perform feature analysis on the indentation profile morphology to obtain the surface property parameters of the pipe surface of the full-section test specimens; determine the cross-section property parameters of the punch specimens prepared after cutting the full-section test specimens along the generatrix at different wall thickness depths; generate a second training sample including the surface property parameters of the pipe surface of the full-section test specimens. Among them, the cross-section property parameters at different wall thickness depths are labeled as the sample tag values of the surface property parameters.

[0074] Among them, the second training sample includes the surface property parameters of the pipe surface of the full-section test specimen and the cross-section property parameters at different wall thickness depths; the surface property parameters include the surface indentation load-displacement curve, the surface indentation profile morphology features, the material surface properties and the surface stress state; the cross-section property parameters include the cross-section indentation load-displacement curve, the cross-section indentation profile morphology features, the material cross-section properties and the cross-section stress state.

[0075] Use the second training sample to perform model training on a pre-constructed second network model until the preset model training end condition is met to obtain a pipe full-section property prediction model.

[0076] Obtain the steel pipe to be tested with test requirements, and conduct indentation tests on the steel pipe to be tested to determine the surface indentation load-displacement curve and the surface indentation profile characteristics of the steel pipe to be tested.

[0077] Input the surface indentation load-displacement curve and the surface indentation profile characteristics of the steel pipe to be tested into the pre-trained pipe surface performance prediction model to obtain the material surface performance and surface stress state output by the model.

[0078] Input the surface indentation load-displacement curve, the surface indentation profile characteristics, the material surface performance, and the surface stress state of the steel pipe to be tested into the pre-trained pipe full-section performance prediction model to obtain the cross-section indentation load-displacement curve, the cross-section indentation profile characteristics, the material cross-section performance, and the cross-section stress state of the steel pipe to be tested under each cross-section; wherein, the pipe wall thickness depths of each cross-section of the steel pipe to be tested are different.

[0079] Embodiment III

[0080] Figure 7 It is a schematic structural diagram of a device for predicting the full-section performance of a steel pipe provided in Embodiment III of the present invention. A device for predicting the full-section performance of a steel pipe provided in an embodiment of the present invention can be applied to the situation of non-destructively predicting the mechanical properties and stress states of materials under different cross-sections or different pipe wall thickness depths of a steel pipe. The device for predicting the full-section performance of a steel pipe can be implemented in the form of hardware and / or software, such as Figure 7 As shown, the device specifically includes: an indentation test module 701, a surface material performance prediction module 702, and a full-section material performance prediction module 703. Among them,

[0081] The indentation test module 701 is used to conduct indentation tests on the steel pipe to be tested to determine the surface indentation load-displacement curve and the surface indentation profile characteristics of the steel pipe to be tested;

[0082] The surface material performance prediction module 702 is used to input the surface indentation load-displacement curve and the surface indentation profile characteristics of the steel pipe to be tested into the pre-trained pipe surface performance prediction model to obtain the material surface performance and surface stress state output by the model;

[0083] The full-section material property prediction module 703 is configured to input the surface indentation load-displacement curve, surface indentation profile morphological features, material surface properties, and surface stress state of the steel pipe to be measured into a pre-trained pipe full-section property prediction model, and obtain the cross-section indentation load-displacement curve, cross-section indentation profile morphological features, material cross-section properties, and cross-section stress state of the steel pipe to be measured at each cross-section output by the model; the pipe wall thickness depths of each cross-section of the steel pipe to be measured are different.

[0084] In the technical solution of the embodiment of the present invention, by using the pipe surface property prediction model to predict the material surface properties and surface stress state of the steel pipe to be measured based on the surface indentation load-displacement curve and surface indentation profile morphological features of the steel pipe to be measured, and then using the pipe comprehensive property prediction model to perform the cross-section indentation load-displacement curve, cross-section indentation profile morphological features, material cross-section properties, and cross-section stress state of each cross-section at each pipe wall thickness depth based on the surface indentation load-displacement curve, surface indentation profile morphological features, material surface properties, and surface stress state of the steel pipe to be measured, the non-destructive testing of parameters such as the mechanical properties and pressure state of the full cross-section of the pen pipe is realized, the input of detection personnel is reduced, and the detection efficiency is improved; at the same time, the result error caused by the inconsistent detection standards of existing detection technologies is reduced, and the detection accuracy of the material mechanical characteristics of each cross-section of the steel pipe is improved, thereby further realizing the safety assessment of the cross-section of the steel pipe.

[0085] Optionally, the device further includes a pipe surface property model training module, and the pipe surface property model training module includes:

[0086] The first indentation test unit is configured to perform an indentation test on indentation test specimens of different materials under different stress states, and obtain the specimen indentation load-displacement curve and indentation material properties; the indentation test specimens include indentation profile morphological features.

[0087] The feature analysis unit is configured to perform feature analysis on the indentation profile morphological features of the indentation test specimens, and obtain the specimen indentation profile morphological features.

[0088] The first sample generation unit is configured to generate a first training sample including the specimen indentation profile morphological features and the indentation load-displacement curve; wherein, the stress state and the indentation material properties are marked as the sample label values of the specimen indentation profile morphological features and the indentation load-displacement curve.

[0089] The first model prediction unit is configured to input the first training sample into a pre-constructed first network model, and obtain the predicted stress and predicted material properties output by the model.

[0090] The first prediction model training unit is used to train the first network model according to the predicted stress, predicted material properties, stress state, and indentation material properties of the training samples until the preset model training end condition is met, and obtain a pipe surface property prediction model.

[0091] Optionally, the pipe surface property model training module further includes:

[0092] The uniaxial tensile test unit is used to perform an indentation test on the indentation test specimens of different materials under different stress states to obtain the specimen indentation load-displacement curve and indentation material properties, and then perform a uniaxial tensile test on the pre-prepared pipe steel specimens to be tested to obtain the uniaxial tensile material properties of the pipe steel specimens to be tested;

[0093] The second indentation test unit is used to perform an indentation test on the pipe steel specimens to be tested to obtain the indentation material properties of the pipe steel specimens to be tested;

[0094] The correction error determination unit is used to determine the material property correction error according to the uniaxial tensile material properties and indentation material properties of the pipe steel specimens to be tested;

[0095] The error correction unit is used to correct the indentation material properties of the indentation test specimens by using the material property correction error to obtain the corrected indentation material properties.

[0096] Optionally, the specimen indentation profile morphology features include the degree of change of the indentation profile ellipse and the material accumulation characteristics at the indentation profile edge.

[0097] Optionally, the device further includes a full-section property model training module; the full-section property model training module includes:

[0098] The second sample generation unit is used to construct a second training sample for the full-section test specimens; the second training sample includes the surface property parameters of the pipe surface of the full-section test specimens and the cross-section property parameters at different wall thickness depths; the surface property parameters include the surface indentation load-displacement curve, the surface indentation profile morphology features, the material surface properties, and the surface stress state; the cross-section property parameters include the cross-section indentation load-displacement curve, the cross-section indentation profile morphology features, the material cross-section properties, and the cross-section stress state;

[0099] The second prediction model training unit is used to train the pre-constructed second network model by using the second training sample until the preset model training end condition is met, and obtain a pipe full-section property prediction model.

[0100] Optionally, the second sample generation unit is specifically used for:

[0101] Perform indentation tests on full-section test specimens of different materials under different pressure states and analyze the characteristics of the indentation profile to obtain the surface performance parameters of the pipe surface of the full-section test specimens.

[0102] Determine the cross-sectional performance parameters of the punch specimens prepared by cutting the full-section test specimens along the busbar at different wall thickness depths.

[0103] Generate a second training sample including the surface performance parameters of the pipe surface of the full-section test specimens; among them, the cross-sectional performance parameters at different wall thickness depths are marked as the sample label values of the surface performance parameters.

[0104] The steel pipe full-section performance prediction device provided by the embodiments of the present invention can execute the steel pipe full-section performance prediction method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0105] Embodiment 4

[0106] Figure 8 FIG. shows a schematic structural diagram of an electronic device 80 that can be used to implement the embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are only examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0107] As Figure 8 shown, the electronic device 80 includes at least one processor 81, and a memory communicatively connected to at least one processor 81, such as a read-only memory (ROM) 82, a random access memory (RAM) 13, etc. Among them, the memory stores a computer program executable by at least one processor, and the processor 81 can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 82 or the computer program loaded from the storage unit 88 into the random access memory (RAM) 83. In the RAM 83, various programs and data required for the operation of the electronic device 80 can also be stored. The processor 81, the ROM 82, and the RAM 83 are connected to each other through a bus 84. The input / output (I / O) interface 85 is also connected to the bus 84.

[0108] Multiple components in the electronic device 80 are connected to the I / O interface 85, including: an input unit 86, such as a keyboard, a mouse, etc.; an output unit 87, such as various types of displays, speakers, etc.; a storage unit 88, such as a disk, an optical disc, etc.; and a communication unit 89, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 89 allows the electronic device 80 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0109] The processor 81 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 81 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 81 executes the various methods and processes described above, such as the method for predicting the full-section performance of steel pipes.

[0110] In some embodiments, the method for predicting the full-section performance of steel pipes can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 88. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 80 via the ROM 82 and / or the communication unit 89. When the computer program is loaded into the RAM 83 and executed by the processor 81, one or more steps of the method for predicting the full-section performance of steel pipes described above can be executed. Alternatively, in other embodiments, the processor 81 can be configured to execute the method for predicting the full-section performance of steel pipes in any other suitable manner (e.g., by means of firmware).

[0111] The various embodiments of the systems and technologies described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs, which can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special or general programmable processor, and can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0112] A computer program for implementing the method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, a special purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer programs can be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine, or entirely on the remote machine or server.

[0113] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0114] In order to provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0115] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected with each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0116] A computing system can include a client and a server. The client and the server are generally far from each other and typically interact through a communication network. The client-server relationship is created by computer programs running on respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system and solves the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0117] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is imposed herein.

[0118] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for predicting the full-section performance of a steel pipe, characterized in that: include: Performing an indentation test on the steel pipe to be tested to determine the surface indentation load displacement curve and surface indentation profile morphology characteristics of the steel pipe to be tested; Inputting the surface indentation load displacement curve and surface indentation profile features of the steel pipe to be tested into a pre-trained pipe surface performance prediction model to obtain the material surface performance and surface stress state output by the model; The surface indentation load displacement curve, surface indentation profile morphology characteristics, material surface properties and surface stress state of the steel pipe to be tested are input into a pre-trained full-section performance prediction model for the pipe, and the model outputs the cross-sectional indentation load displacement curve, cross-sectional indentation profile morphology characteristics, material cross-sectional properties and cross-sectional stress state of the steel pipe to be tested in each cross-section; the pipe wall thickness depth of each cross-section of the steel pipe to be tested is different.

2. The method according to claim 1, characterized in that The training method of the pipe surface performance prediction model is as follows: Performing indentation tests on indentation test specimens of different materials under different stress states to obtain indentation load displacement curves of the specimens and indentation material properties; the indentation test specimens include indentation profile morphology; The indentation profile morphology of the indentation test specimen is analyzed to obtain the indentation profile morphology characteristics of the specimen; Generate a first training sample including the indentation profile morphology characteristics and the indentation load displacement curve of the specimen; wherein the stress state and the indentation material properties are annotated as sample label values ​​of the indentation profile morphology characteristics and the indentation load displacement curve of the specimen; Inputting the first training sample into a pre-built first network model to obtain predicted stress and predicted material properties output by the model; According to the predicted stress, predicted material properties, stress state and indentation material properties of the training samples, the first network model is trained until a preset model training end condition is met to obtain a pipe surface property prediction model.

3. The method according to claim 2, characterized in that After performing the indentation test on the indentation test specimens of different materials under different stress states to obtain the indentation load displacement curve of the specimen and the indentation material properties, the method further includes: Performing a uniaxial tensile test on the pre-prepared pipeline steel specimen to be tested to obtain the uniaxial tensile material properties of the pipeline steel specimen to be tested; Performing an indentation test on the pipeline steel specimen to be tested to obtain the indentation material properties of the pipeline steel specimen to be tested; Determining a material property correction error according to the uniaxial tensile material properties and the indentation material properties of the pipeline steel specimen to be tested; The material property correction error is used to perform error correction on the indentation material property of the indentation test specimen to obtain the corrected indentation material property.

4. The method according to claim 2, characterized in that: The morphological characteristics of the indentation profile of the specimen include the degree of change of the indentation profile ellipse and the material accumulation characteristics at the edge of the indentation profile.

5. The method according to claim 1, characterized in that The training method of the pipe full-section performance prediction model is as follows: Constructing a second training sample of a full-section test specimen; the second training sample includes surface performance parameters of the pipe surface of the full-section test specimen and cross-sectional performance parameters at different wall thickness depths; the surface performance parameters include surface indentation load displacement curve, surface indentation profile morphology characteristics, material surface properties and surface stress state; The cross-sectional performance parameters include cross-sectional indentation load displacement curve, cross-sectional indentation profile morphology, material cross-sectional performance and cross-sectional stress state; The pre-constructed second network model is trained using the second training sample until a preset model training end condition is met, thereby obtaining a full-section performance prediction model of the pipe.

6. The method according to claim 5, characterized in that The second training sample of the full-section test specimen is constructed, comprising: The full-section test specimens of different materials are subjected to indentation tests under different pressure states and the indentation profile morphology is analyzed to obtain the surface performance parameters of the pipe surface of the full-section test specimens; Determine the cross-sectional performance parameters of the punch rod specimen prepared after the full-section test specimen is cut along the generatrix at different wall thickness depths; A second training sample including surface performance parameters of the pipe surface of the full-section test specimen is generated; wherein the cross-sectional performance parameters at different wall thickness depths are annotated as sample label values ​​of the surface performance parameters.

7. A device for predicting the full cross-section performance of a steel pipe, characterized in that: include: An indentation test module is used to perform an indentation test on the steel pipe to be tested, and determine the surface indentation load displacement curve and surface indentation profile morphology characteristics of the steel pipe to be tested; A surface material property prediction module is used to input the surface indentation load displacement curve and surface indentation profile morphology characteristics of the steel pipe to be tested into a pre-trained pipe surface property prediction model to obtain the material surface properties and surface stress state output by the model; The full-section material performance prediction module is used to input the surface compression load displacement curve, surface indentation profile morphology characteristics, material surface performance and surface stress state of the steel pipe to be tested into a pre-trained full-section performance prediction model for the pipe, and obtain the cross-section compression load displacement curve, cross-section indentation profile morphology characteristics, material cross-section performance and cross-section stress state of the steel pipe to be tested in each cross-section output by the model; the pipe wall thickness depth of each cross-section of the steel pipe to be tested is different.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for predicting the full-section properties of a steel pipe according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for predicting the full-section performance of a steel pipe according to any one of claims 1 to 6 when executed.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the computer program implements the method for predicting the full-section performance of a steel pipe according to any one of claims 1 to 6.

Images