Method for evaluating service life of in-service buried gas pipeline

Abstract

The invention discloses a method for evaluating the service life of an in-service buried gas pipeline, and belongs to the technical field of urban gas pipeline special equipment. The evaluation method comprises the following steps: step 1, obtaining mechanical property data of an unserved pipeline material; 2, establishing a pipe-soil nonlinear model, and obtaining training samples of the maximum Von Mises stress of the pipeline under different settlement and slippage actions by using a finite element method; step 3, training the training sample by using a machine learning method, establishing a mathematical model and drawing a stress nephogram; 4, establishing a relation model of pipeline oxidation induction time, stress, temperature and time; and then, measuring actual settlement and slippage, obtaining a stress value through the cloud picture, and predicting the residual life of the pipeline according to the model. According to the method, the service life of the in-service buried gas pipeline is evaluated, and an efficient and scientific evaluation means is provided for guaranteeing the safety of the gas pipeline.

Description

Technical Field

[0001] The present invention relates to a method for assessing the life of an in-service buried gas pipeline, and belongs to the technical field of special equipment for urban gas pipelines, and in particular to a method for assessing the life of an in-service buried gas pipeline based on machine learning and finite element analysis. Background Art

[0002] In the past decade, with the rapid development of the national economy and the transformation of energy consumption, natural gas has become the main source of urban gas in my country. At present, more than 70% of urban natural gas pipelines in my country are polyethylene (PE) pipes, which are mainly used in urban medium and low pressure gas pipelines. Compared with traditional steel pipelines, PE gas pipelines have many advantages such as light weight, corrosion resistance, and low leakage rate, but they also have relatively low strength, prone to large deformation and rupture leakage. Therefore, scientifically evaluating the service safety and service life of buried PE gas pipelines under external loads is the key to ensuring their safe operation. The public patent CN 110749500A proposes a method for predicting the service life of in-service buried pipes, but it is mainly used for the prediction of the life of buried polyethylene gas pipes on site with specific defect types. It is difficult to predict the life of defect-free pipelines. At the same time, since the model does not consider the influence of temperature, it is difficult to quantify the influence of temperature on the life of the pipeline.

[0003] Traditional polyethylene pipe life assessment is mainly based on temperature or ultraviolet accelerated aging experiments, without considering the impact of stress on pipe life. However, this impact cannot be ignored in some areas of soil non-uniform deformation (including non-uniform settlement and non-uniform slip). The pipe stress in this area will suddenly increase due to the non-uniform deformation of the soil. At the same time, the different pipe stress levels caused by different soil non-uniform deformation areas will also significantly affect the life of the pipeline.

[0004] Therefore, there is an urgent need for a method to quickly and accurately evaluate the life of buried gas pipelines in service in areas with non-uniform deformation of soil. This method can not only improve the safety assessment level of buried gas pipelines, but also quickly evaluate the reliability of pipelines in areas with non-uniform deformation of soil, thus ensuring the safety of gas pipelines. Summary of the invention

[0005] The purpose of the present invention is to provide a method for assessing the life of an in-service buried gas pipeline in view of the problems existing in the prior art, which can realize the life assessment of an in-service buried gas pipeline in a soil non-uniform deformation area.

[0006] At the same time, the present invention provides an application of a method for assessing the life of an in-service buried gas pipeline in a medium- and low-pressure gas pipeline network in a city or town.

[0007] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0008] A method for assessing the life of an in-service buried gas pipeline comprises the following steps:

[0009] Step 1: Conduct a tensile test on the unserviced pipeline material to obtain its mechanical data;

[0010] Step 2: Establish a non-uniform linear finite element model between the pipeline and the soil. Use the material mechanical data of the unserviced pipeline obtained in step 1 as the material data of the pipeline, and use its yield strength as the strength criterion. Apply different settlements and slip amounts to the soil as boundary conditions, calculate the maximum Von Mises stress of the pipeline, and use it as a training sample.

[0011] Step 3: Using the soil settlement and slip in step 2 as input variables and the maximum Von Mises stress of the pipeline as output, the machine learning algorithm is used to analyze the samples to obtain a training model, and based on the training model, a cloud diagram of the maximum Von Mises stress of the pipeline under different soil settlement and slip is drawn;

[0012] Step 4: Apply different stresses σ to the unserviced pipeline at different temperatures T, take samples for aging induction test after different times t, obtain the oxidation induction time OIT, and use the least squares method to solve the related constants a, b, c, d of the following life prediction model:

[0013] ln(OIT / OIT0)=a+bt+cσt / T+d*t / T,

[0014] Where OIT0 is the initial oxidation induction time of the pipeline;

[0015] Step 5, measure the settlement and slip of the soil around the in-service pipeline, obtain the maximum Von Mises stress σ1 from the stress cloud map of step 3, and then use the model of step 4 to calculate the time t1 when the stress is σ1 and the ratio of the oxidation induction time to the initial oxidation induction time is 0.01;

[0016] Step six, intercept a part of the in-service pipeline for oxidation induction test to obtain its oxidation induction time OIT1, and use the model in step four to calculate the theoretical in-service time t2 when the stress is σ1. The remaining life of the in-service buried pipeline is t1-t2.

[0017] Preferably, in step 1, the mechanical data of the pipeline material include yield strength, tensile strength, elongation and Poisson's ratio.

[0018] Preferably, in step 2, ANSYS workbench finite element analysis software is used, a static module is selected, a pipeline and soil model is established in the finite element analysis software, and meshing is performed, different settlement boundary conditions are applied using the following formula (1) cubic polynomial, different slip boundary conditions are applied using the formula (3) quartic polynomial, and the maximum Von Mises stress of the pipeline is obtained using an asymmetric solution;

[0019] Z(x)=px 3 +qx+r; (1)

[0020] In formula (1), x is the coordinate value of the comprehensive action area along the x-axis, x0 is the coordinate of the maximum deformation point of the pipeline in the x-axis direction, p, q, and r are dimensionless parameters that need to be confirmed, and their values ​​are confirmed by the following equations:

[0021] Z(0)=0; Z(x0)=-h; Z'(x0)=0; (2)

[0022] In formula (2), h is the maximum settlement value;

[0023] Y(x)=mx 4 +nx 2 +k; (3)

[0024] In formula (3), x is the coordinate value of the comprehensive action area along the x-axis, x0 is the coordinate of the maximum deformation point of the pipeline in the x-axis direction, m, n, k are dimensionless parameters that need to be confirmed, and their values ​​are confirmed by the following equations:

[0025] Y(0)=0; Y(x0)=u; Y'(x0)=0; (4)

[0026] In formula (4), u is the maximum slip value.

[0027] Preferably, in step three, the machine learning algorithm includes BP neural network, decision tree, naive Bayes, KNN or random forest.

[0028] Preferably, the material of the in-service buried gas pipeline is polyethylene.

[0029] Application of a life assessment method for in-service buried gas pipelines in urban medium and low pressure gas pipeline networks.

[0030] The present invention relates to an in-service buried gas pipeline life assessment method and its application in the remaining life assessment of in-service buried gas pipelines under the action of soil non-uniform settlement and non-uniform sliding.

[0031] In the present invention, sedimentation includes uniform sedimentation and non-uniform sedimentation, wherein the non-uniform sedimentation is fitted by a cubic equation (i.e., formula (1)).

[0032] In the present invention, slip includes uniform slip and non-uniform slip, wherein the non-uniform slip is fitted by a quartic equation (ie, formula (3)).

[0033] The life assessment method of the present invention is applicable to in-service buried gas pipelines under the action of non-uniform soil settlement and non-uniform sliding.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] 1. Accurate evaluation: The technical solution of the present invention establishes a quantitative relationship between temperature, stress and pipeline life, which is suitable for the life prediction of pipelines under different temperatures and stress levels. The evaluation results are more accurate and have a wider range of applications, especially for the life evaluation of pipelines in areas with non-uniform deformation of soil at different temperatures.

[0036] 2. Rapid identification: After the evaluation model is established, the maximum Von Mises stress of the pipeline can be quickly identified using the stress cloud map, and then the pipeline life and reliability in different areas can be quickly evaluated.

[0037] The present invention introduces machine learning combined with finite element analysis to draw a stress cloud diagram between the maximum Von Mises stress of the pipeline and the slip and settlement, which can quickly obtain the pipeline stress in the non-uniform settlement area of ​​different soil bodies and evaluate the reliability of the pipeline. At the same time, the influence of temperature and stress during service is introduced into the life assessment, which improves the accuracy of life assessment. This method has broad application prospects and is not only suitable for buried gas polyethylene pipelines in service, but can also be extended to similar applications in other industrial fields. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 is a flow chart of the present invention;

[0039] Figure 2 is the non-uniform linear finite element model mesh between the pipeline and the soil;

[0040] Figure 3 It is the stress cloud diagram between the maximum Von Mises stress of the pipeline and the soil settlement and slip. DETAILED DESCRIPTION

[0041] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. The following embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention.

[0042] Example 1

[0043] like Figure 1 As shown, a method for assessing the life of an in-service buried gas pipeline is provided. To assess the life of an in-service buried gas pipeline, the following steps are mainly taken:

[0044] Step 1: Conduct a tensile test on the unserviced pipeline to obtain its mechanical data.

[0045] Specifically, the stress-strain curve of the pipeline material is obtained, and its yield strength, tensile strength, elongation and Poisson's ratio are obtained.

[0046] Step 2: Establish a non-uniform linear finite element model between the pipeline and the soil. Use the material mechanical data of the unserviced pipeline obtained in step 1 as the material data of the pipeline, and use its yield strength as the strength criterion. Apply different settlements and slip amounts to the soil as boundary conditions, and calculate the maximum Von Mises stress (i.e., Van Mises stress) of the pipeline as a training sample.

[0047] Specifically, Figure 2 As shown, use ANSYS workbench finite element analysis software. Select the static module. Create a pipeline in the finite element software (such as Figure 2 (b)) and soil model (as shown in Figure 2 (a)), and meshing is performed. To ensure the accuracy of the calculation results, the mesh of the contact area is encrypted. Different settlement boundary conditions are applied using the following formula (1) cubic polynomial, and different slip boundary conditions are applied using the formula (3) quartic polynomial. The maximum Von Mises stress of the pipeline is obtained using an asymmetric solution. The training samples obtained are shown in Table 1.

[0048] Z(x)=px 3 +qx+r; (1)

[0049] Where x is the coordinate value of the comprehensive action area along the x-axis, the coordinate of the maximum deformation point of the pipeline in the x-axis direction is -4, p, q, r are dimensionless parameters that need to be confirmed, and their values ​​are confirmed by the following equations:

[0050] Z(0)=0; Z(-4)=-h; Z'(-4)=0; (2)

[0051] Where h is the maximum sedimentation value.

[0052] Y(x)=mx 4 +nx 2 +k; (3)

[0053] Where x is the coordinate value of the comprehensive action area along the x-axis, the coordinate of the maximum deformation point of the pipeline in the x-axis direction is -4, m, n, k are dimensionless parameters that need to be confirmed, and their values ​​are confirmed by the following equation:

[0054] Y(0)=0; Y(-4)=u; Y'(-4)=0; (4)

[0055] Where u is the maximum slip value.

[0056] Table 1 Training samples of maximum Von Mises stress of pipelines and settlement and slip

[0057]

[0058]

[0059]

[0060] Step three, using the soil settlement and slip in step two as input variables, and the maximum Von Mises stress of the pipeline as the output, use the BP neural network to analyze the samples in Table 1 to obtain the training model. The BP model used adopts a three-layer neural network structure, in which the input layer contains two nodes, namely the maximum non-uniform slip and the maximum non-uniform settlement. The output layer has only one node, corresponding to the maximum Von-Mises stress of the pipeline, and the number of hidden layer nodes used is 6. Before training, the input maximum slip and maximum settlement are normalized, and the activation function uses tan-sigmoid and purelin. Set the target number of iterations to 1000, the learning rate to 0.01, and the error threshold to 10 -6 After the training is completed, the training model is used to draw the maximum Von Mises stress cloud diagram of the pipeline under different soil settlement and slippage, such as Figure 3 shown.

[0061] Step 4: Apply different stresses (σ) to the unserviced pipeline at different temperatures (T), and take samples after different times (t) to perform aging induction tests according to GB / T 19466.6-2009 "Plastics Differential Scanning Calorimetry (DSC) Part 6: Determination of Oxidation Induction Time (Isothermal OIT) and Oxidation Induction Temperature (Dynamic OIT)" to obtain the oxidation induction time (OIT), as shown in Table 2, and use the least squares method to solve the following life prediction model (Formula 5) related parameters a, b, c, d,

[0062] ln(OIT / OIT0)=a+bt+cσt / T+d*t / T; (5)

[0063] In formula (5), T represents temperature, t represents time, σ represents stress, OIT represents oxidation induction time, i.e., the oxidation induction time of the sample (in-service pipeline), and OIT0 represents the initial oxidation induction time of the pipeline, i.e., the oxidation induction time of the unin-service pipeline.

[0064] Table 2 Oxidation induction time of PE pipes under different temperatures, stresses and time

[0065]

[0066]

[0067] Step 5: The maximum non-uniform settlement and slip of the soil around the in-service pipeline were measured to be 0.35m and 0.45m respectively. Figure 3 The stress cloud diagram shows that the maximum Von Mises stress is about 19 MPa (i.e., the stress of the unserved pipeline). The model in step 4 is then used to calculate the time when the stress is 19 MPa and the ratio of the oxidation induction time to the initial oxidation induction time is 0.01, which is 2501 days.

[0068] Step six, cut off part of the in-service pipeline for oxidation induction test to obtain its oxidation induction time (OIT1), and use the model in step four to calculate that the theoretical in-service time is 116 days when the stress is σ1, and the remaining life of the in-service pipeline is 2501-116=2385 days.

[0069] Example 2

[0070] The difference between this embodiment and embodiment 1 is only that:

[0071] Step 3: Using the soil settlement and slip in step 2 as input variables and the maximum Von Mises stress of the pipeline as output, naive Bayes is used to analyze the samples in Table 1 to obtain a training model, and the training model is used to draw the maximum Von Mises stress cloud map of the pipeline under different soil settlement and slip.

[0072] Example 3

[0073] The difference between this embodiment and embodiment 1 is that:

[0074] Step 3: Using the soil settlement and slip in step 2 as input variables and the maximum Von Mises stress of the pipeline as output, KNN is used to analyze the samples in Table 1 to obtain the training model, and the training model is used to draw the maximum Von Mises stress cloud map of the pipeline under different soil settlement and slip.

[0075] It should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the intention that the claimed invention requires more features than those expressly recited in each claim. Rather, as reflected in the claims, inventive aspects lie in less than all of the features of the previously disclosed embodiments. Therefore, the claims that follow the detailed description are hereby expressly incorporated into the detailed description, with each claim itself serving as a separate embodiment of the present invention.

[0076] Although the present invention has been described according to a limited number of embodiments, it will be apparent to those skilled in the art, with the benefit of the above description, that other embodiments may be envisioned within the scope of the invention thus described. In addition, it should be noted that the language used in this specification is selected primarily for readability and teaching purposes, rather than for explaining or defining the subject matter of the present invention. Therefore, many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the appended claims. The disclosure of the present invention is illustrative, not restrictive, with respect to the scope of the present invention, which is defined by the appended claims.

[0077] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for assessing the life of an in-service buried gas pipeline, characterized in that: The following steps are involved: Step 1: Conduct a tensile test on the unserviced pipeline material to obtain its mechanical data; Step 2: Establish a non-uniform linear finite element model between the pipeline and the soil. Use the material mechanical data of the unserviced pipeline obtained in step 1 as the material data of the pipeline, and use its yield strength as the strength criterion. Apply different settlements and slip amounts to the soil as boundary conditions, calculate the maximum Von Mises stress of the pipeline, and use it as a training sample. Step 3: Using the soil settlement and slip in step 2 as input variables and the maximum Von Mises stress of the pipeline as output, the machine learning algorithm is used to analyze the samples to obtain a training model, and based on the training model, a cloud diagram of the maximum Von Mises stress of the pipeline under different soil settlement and slip is drawn; Step 4: Apply different stresses σ to the unserviced pipeline at different temperatures T, take samples for aging induction test after different times t, obtain the oxidation induction time OIT, and use the least squares method to solve the related constants a, b, c, d of the following life prediction model: ln(OIT / OIT0)=a+bt+cσt / T+d*t / T, Where OIT0 is the initial oxidation induction time of the pipeline; Step 5, measure the settlement and slip of the soil around the in-service pipeline, obtain the maximum VonMises stress σ1 from the stress cloud map of step 3, and then use the model of step 4 to calculate the time t1 when the stress is σ1 and the ratio of the oxidation induction time to the initial oxidation induction time is 0.01; Step six, intercept a part of the in-service pipeline for oxidation induction test to obtain its oxidation induction time OIT1, and use the model in step four to calculate the theoretical in-service time t2 when the stress is σ1. The remaining life of the in-service buried pipeline is t1-t2.

2. A method for assessing the life of an in-service buried gas pipeline according to claim 1, characterized in that: In step 1, the mechanical data of the pipeline material include yield strength, tensile strength, elongation and Poisson's ratio.

3. The method for assessing the life of an in-service buried gas pipeline according to claim 1, characterized in that: In step 2, ANSYS workbench finite element analysis software is used, the static module is selected, the pipeline and soil models are established in the finite element analysis software, and meshing is performed. Different settlement boundary conditions are applied using the following formula (1) cubic polynomial, and different slip boundary conditions are applied using the formula (3) quartic polynomial. The maximum VonMises stress of the pipeline is obtained using an asymmetric solution; Z(x)=px 3 +qx+r; (1) In formula (1), x is the coordinate value of the comprehensive action area along the x-axis direction, p, q, and r are dimensionless parameters that need to be confirmed, and their values ​​are confirmed by the following equations: Z(0)=0; Z(x0)=-h; Z'(x0)=0; (2) In formula (2), x0 is the coordinate of the maximum deformation point of the pipeline in the x-axis direction, and h is the maximum settlement value; Y(x)=mx 4 +nx 2 +k; (3) In formula (3), x is the coordinate value of the comprehensive action area along the x-axis direction, m, n, and k are dimensionless parameters that need to be confirmed, and their values ​​are confirmed by the following equations: Y(0)=0; Y(x0)=u; Y'(x0)=0; (4) In formula (4), x0 is the coordinate of the maximum deformation point of the pipeline in the x-axis direction, and u is the maximum slip value.

4. The method for assessing the life of an in-service buried gas pipeline according to claim 1, characterized in that: In step 3, the machine learning algorithms include BP neural network, decision tree, naive Bayes, KNN or random forest.

5. The method for assessing the life of an in-service buried gas pipeline according to claim 1, characterized in that: The material of the buried gas pipeline in service is polyethylene.

6. The method for assessing the life of an in-service buried gas pipeline according to claim 1, characterized in that: In step 2, soil settlement includes uniform settlement and non-uniform settlement; soil sliding includes uniform sliding and non-uniform sliding.

7. Application of the method for assessing the life of an in-service buried gas pipeline according to any one of claims 1 to 6 in medium and low pressure gas pipeline networks in cities and towns.

8. Application of the method for life assessment of an in-service buried gas pipeline according to any one of claims 1 to 6 in the remaining life assessment of an in-service buried gas pipeline under the action of non-uniform soil settlement and non-uniform sliding.

Images