Group corrosion defect-containing pipeline safety evaluation method, device, equipment and medium

Abstract

The invention provides a group corrosion defect-containing pipeline safety evaluation method and device, equipment and a medium. The method comprises the following steps: acquiring pipeline data and defect data of a to-be-evaluated pipeline; determining failure pressure of each defect in the to-be-evaluated pipeline based on the pipeline data and the defect data; the pipeline data and the group corrosion defect data are input into a prediction model, the interaction coefficient between group corrosion defects output by the prediction model is obtained, and the prediction model is obtained based on XGBoost model training; and based on the failure pressure of each defect and the interaction coefficient between the defects, determining the interaction failure pressure between the interaction defects, and based on the interaction failure pressure, carrying out safety evaluation on the group corrosion defect-containing pipeline. According to the method, the device, the equipment and the medium provided by the invention, the influence of the interaction between the failure pressure of each defect and the group corrosion defect on the failure pressure of the pipeline is considered, and the accuracy and the reliability of the safety evaluation of the defective pipeline are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of pipeline detection, and in particular to a method, device, equipment and medium for safety evaluation of a pipeline containing group corrosion defects. Background Art

[0002] During the long-term service of oil and gas pipelines, due to the presence of soil media and pollutants in the transported oil and gas, the pipelines are extremely susceptible to corrosion, which seriously affects the safety of the pipelines. Corrosion can be divided into external corrosion and internal corrosion according to the location of the corrosion on the pipeline surface. As the service life of the pipeline increases, the anti-corrosion layer on the outer surface of the pipeline gradually ages and peels off, causing the pipe wall to chemically react with the air and soil, forming external wall corrosion; the corrosive components such as water and sulfide remaining in the transport medium contact the pipe wall to cause internal surface corrosion. When the continuous action of internal and external corrosion of the pipeline causes the pipe wall to become thinner, the pressure bearing capacity of the pipeline will also decrease. When the pipe wall is thinned to a certain extent, it will cause perforation, leakage or rupture of the pipeline, causing economic losses and safety hazards.

[0003] In the prior art, the research on the interaction criteria between pipeline corrosion defects mainly focuses on the regular arrangement of interactive corrosion defects. However, the accuracy of the failure pressure prediction results of pipelines containing group corrosion defects obtained thereby is low, resulting in low reliability of safety evaluation based on the failure pressure prediction results of pipelines containing group corrosion defects. Summary of the invention

[0004] The present invention provides a method, device, equipment and medium for safety evaluation of a pipeline containing group corrosion defects, which are used to solve the problem that the research on the interaction criterion between pipeline corrosion defects in the prior art mainly focuses on the regular arrangement of interactive corrosion defects, and the accuracy of the failure pressure prediction result of the pipeline containing group corrosion defects obtained thereby is low, thereby resulting in the problem that the reliability of safety evaluation based on the failure pressure prediction result of the pipeline containing group corrosion defects is low.

[0005] The present invention provides a method for safety assessment of a pipeline containing group corrosion defects, comprising:

[0006] Obtain pipeline data and group corrosion defect data of the pipeline to be evaluated;

[0007] Determining the failure pressure of each defect in the pipeline to be evaluated based on the pipeline data and the group corrosion defect data;

[0008] The pipeline data and the group corrosion defect data are input into a prediction model to obtain the interaction coefficient between the group corrosion defects output by the prediction model, wherein the prediction model is obtained based on XGBoost model training; based on the failure pressure of each defect and the interaction coefficient between the group corrosion defects, the interaction failure pressure between the group corrosion defects is determined, and based on the interaction failure pressure between the group corrosion defects, a pipeline safety evaluation containing group corrosion defects is performed on the pipeline to be evaluated.

[0009] According to a pipeline safety assessment method containing group corrosion defects provided by the present invention, the formula of the XGBoost model is:

[0010]

[0011] in, is the predicted value of the i-th sample in the model, K is the number of regression trees, and f k (x i ) is the weight of the i-th sample falling on the leaf in the k-th tree, F is the function space composed of all regression trees, and the training data set is D, then D={(x1, y1), (x2, y2), …, (x n ,y n )}, Where R n represents a dataset with n features, x i ∈X represents the i-th sample.

[0012] According to a pipeline safety assessment method containing group corrosion defects provided by the present invention, the objective loss function of the XGBoost model is:

[0013]

[0014] Where Ω(Θ) represents the objective loss function of the XGBoost model, Θ represents the set of feature weights, Θ = {f1, f2, ..., f k}, L(Θ) represents the training error, that is, the degree of match between the model and the training set, and Ω(Θ) represents the regularization term, that is, the sum of the complexity of the regression trees in the model.

[0015] According to a pipeline safety assessment method containing group corrosion defects provided by the present invention, the calculation formulas of the training error and the regularization term are as follows:

[0016]

[0017]

[0018] Where L represents the training error, Ω(fk ) represents the regularization term, γ and λ are the regularization term coefficients, T represents the number of leaf nodes, and w j Represents the weight of the jth leaf node.

[0019] According to a pipeline safety assessment method containing group corrosion defects provided by the present invention, the interaction failure pressure between the group corrosion defects is determined based on the failure pressure of each defect and the interaction coefficient between the group corrosion defects, including:

[0020] Based on the failure pressures of the defects, determining a minimum value of the failure pressures of the defects;

[0021] Based on the minimum value of the failure pressure of each defect and the interaction coefficient between the group of corrosion defects, the interaction failure pressure between the group of corrosion defects is determined.

[0022] According to a pipeline safety assessment method containing group corrosion defects provided by the present invention, the interaction failure pressure between the group corrosion defects is determined based on the minimum value of the failure pressure of each defect and the interaction coefficient between the group corrosion defects, including:

[0023] The interaction failure pressure between the group of corrosion defects is determined based on the following formula:

[0024] If P a <P b , then the interaction failure pressure between group corrosion defects is:

[0025] P ab =f ab ×P a

[0026] If P a >Px, then the interaction failure pressure between the group corrosion defects is:

[0027] P ab =f ab ×P b

[0028] Among them, f ab is the interaction coefficient between defect a and defect b, P a is the failure pressure of defect a, P b is the failure pressure of defect b.

[0029] According to a pipeline safety assessment method containing group corrosion defects provided by the present invention, the pipeline safety assessment containing group corrosion defects is performed on the pipeline to be assessed based on the interaction failure pressure between the group corrosion defects, comprising:

[0030] Based on the following formula, the safety evaluation of the pipeline containing group corrosion defects is performed on the pipeline to be evaluated:

[0031] P double =min{P 12 , P 13 , ..., P nm}(n=1,2,...,N-1,m=n+1,n+2,...,N)

[0032] Where N is the total number of defects, P a is the failure pressure of defect a, P b is the failure pressure of defect b, P nm is the interaction failure pressure between the nth defect and the mth defect.

[0033] The present invention also provides a safety evaluation device for a pipeline containing group corrosion defects, comprising:

[0034] An acquisition unit, used for acquiring pipeline data and group corrosion defect data of the pipeline to be evaluated;

[0035] A determination unit, configured to determine the failure pressure of each defect in the pipeline to be evaluated based on the pipeline data and the group corrosion defect data;

[0036] A prediction unit, used for inputting the pipeline data and the group corrosion defect data into a prediction model to obtain an interaction coefficient between the group corrosion defects output by the prediction model, wherein the prediction model is obtained through training based on an XGBoost model;

[0037] The safety evaluation unit is used to determine the interaction failure pressure between the group of corrosion defects based on the failure pressure of each defect and the interaction coefficient between the group of corrosion defects, and to perform safety evaluation of the pipeline containing group corrosion defects on the pipeline to be evaluated based on the interaction failure pressure between the group of corrosion defects.

[0038] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, any of the above-mentioned methods for evaluating the safety of a pipeline containing group corrosion defects is implemented.

[0039] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method for evaluating the safety of a pipeline containing group corrosion defects as described above is implemented.

[0040] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned methods for evaluating the safety of a pipeline containing group corrosion defects.

[0041] The method, device, equipment and medium for safety assessment of a pipeline containing group corrosion defects provided by the present invention determine the interaction failure pressure between the interaction defects based on the failure pressure of each defect and the interaction coefficient between the defects, and perform defective pipeline safety assessment on the pipeline to be assessed based on the interaction failure pressure between the interaction defects. Therefore, when performing the defective pipeline safety assessment, not only the failure pressure of each defect is considered, but also the influence of the interaction between the group corrosion defects on the pipeline failure pressure is considered, thereby further improving the accuracy and reliability of the defective pipeline safety assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0043] Figure 1 This is one of the flow diagrams of the pipeline safety assessment method containing group corrosion defects provided by the present invention;

[0044] Figure 2 This is the second flow chart of the method for safety assessment of pipelines containing group corrosion defects provided by the present invention;

[0045] Figure 3 It is a structural schematic diagram of a pipeline safety evaluation device containing group corrosion defects provided by the present invention;

[0046] Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] In related technologies, the location and shape of pipeline corrosion are uncertain and irregular. Defects may overlap or be independent of each other. The corrosion shape may be pitting or grooves, etc. In addition, corrosion defects often do not appear independently. According to the number of corrosion defects, they can be divided into single-point corrosion defects and multiple-point corrosion defects. Multiple-point corrosion defects are group corrosion defects.

[0049] The influence of different numbers of defects on pipeline failure pressure also varies. When the number of corrosion defects exceeds one, the failure pressure of multi-point corrosion defect pipelines is still predicted based on the residual strength assessment method of single-point corrosion defect pipelines in the prior art, which ignores the influence of the interaction between defects on the pipeline failure pressure. The accuracy of the failure pressure of the multi-point corrosion defect pipeline is low, which leads to low reliability of safety evaluation based on the failure pressure prediction results of pipelines with group corrosion defects.

[0050] Based on the above problems, the present invention provides a method for safety evaluation of pipelines containing group corrosion defects. Figure 1 This is one of the flow diagrams of the method for safety assessment of pipelines containing group corrosion defects provided by the present invention, such as Figure 1 As shown, the method includes:

[0051] Step 110, obtaining pipeline data and group corrosion defect data of the pipeline to be evaluated.

[0052] Specifically, the pipeline data and group corrosion defect data of the pipeline to be evaluated can be obtained. The pipeline to be evaluated here is a defective pipeline that needs to be subsequently safety evaluated. The pipeline data of the pipeline to be evaluated here may include the pipeline outer diameter, pipeline wall thickness, pipeline tensile strength and pipeline hardening index.

[0053] The defect data of the pipeline to be evaluated here refers to the data of each defect in the pipeline to be evaluated, and the defect data may include the length of the defect, the width of the defect, the depth of the defect, the axial spacing between each defect, and the circumferential spacing between each defect.

[0054] Here, the axial spacing between defects and the circumferential spacing between defects in the group corrosion defect data of the pipeline to be evaluated may be obtained in advance or calculated in real time.

[0055] For example, the combination of each defect is defect a and defect b, where a = 1, 2, ..., N, b = 1, 2, ..., N and a ≠ b. To determine the axial spacing between defects a and b and the circumferential spacing between defects a and b, a coordinate system is established at the center of the geometric size of defect i, and the coordinates of the center point of defect i are (C Xi , C Yi ), C Xi represents the axial coordinate of defect i relative to defect 1 on the outer surface of the pipe, C Yi represents the circumferential coordinates of the circumferential center point of defect i relative to defect 1, then the coordinates of the geometric center positions of defect a and defect b are respectively (C Xa , C Ya ) and (C Xb , C Yb ).

[0056] If CXa <C Xb , then the axial distance S between defects a and b L =(C Xb -L b / 2)-(C Xa +L a / 2), otherwise the axial spacing S L =(C Xa -L a / 2)-(C Xb +L b / 2), where L a Indicates the length of defect a, L b Indicates the length of defect b; if the circumferential coordinate position of the defect C Ya <C Yb , then the annular spacing S between defects a and b C =(C Yb -w b / 2)-(C Ya +w a / 2), otherwise the annular spacing S C =(C Ya -w a / 2)-(C Yb +w b / 2), where w a Indicates the width of defect a, w b Indicates the width of defect b.

[0057] Here, the pipeline data and group corrosion defect data of the pipeline to be evaluated can be stored in the defect table for easy access by users.

[0058] Step 120: determining the failure pressure of each defect in the pipeline to be evaluated based on the pipeline data and the group corrosion defect data.

[0059] Specifically, after the pipeline data and the group corrosion defect data are obtained, the failure pressure of each defect in the pipeline to be evaluated can be determined based on the pipeline data and the group corrosion defect data.

[0060] The failure pressure of each defect in the pipeline to be evaluated here refers to the critical pressure at which pipeline perforation, leakage or rupture may occur at each defect.

[0061] For example, based on pipeline data and group corrosion defect data, the failure pressure of each defect in the pipeline to be evaluated is determined as follows:

[0062]

[0063] Where, f=1,2,......,N,P fis the failure pressure of each defect in the pipeline to be evaluated, MPa; n is the hardening index of the pipe; t0 is the pipe wall thickness, mm; D0 is the outer diameter of the pipe, mm; σ u ' is the nominal tensile strength of the pipeline when it fails, MPa; d is the depth of the defect, mm; L is the length of the defect, mm.

[0064] Step 130, inputting the pipeline data and the group corrosion defect data into a prediction model to obtain the interaction coefficient between the group corrosion defects output by the prediction model, wherein the prediction model is obtained based on XGBoost model training.

[0065] Specifically, after the pipeline data and the group corrosion defect data are obtained, the pipeline data and the group corrosion defect data can be input into the prediction model to obtain the interaction coefficient between the group corrosion defects output by the prediction model.

[0066] It can be understood that by predicting the interaction coefficient between group corrosion defects based on the prediction model, pipeline data and group corrosion defect data, the interaction coefficient between group corrosion defects can be obtained, thereby obtaining the interaction rules between the group corrosion defects of the pipeline to be evaluated, further improving the accuracy and reliability of the subsequent safety evaluation of the pipeline containing group corrosion defects on the pipeline to be evaluated.

[0067] In order to better predict the interaction coefficient between group corrosion defects, it is necessary to obtain a prediction model through the following steps before step 130:

[0068] Sample pipeline data, sample defect data and interaction coefficient labels between group corrosion defects can be collected in advance, and an initial prediction model can be built in advance. The parameters of the initial prediction model here can be pre-set or randomly generated, and the embodiment of the present invention does not specifically limit this.

[0069] Here, an initial prediction model can be built based on finite element software to obtain multiple sets of simulation data results under different feature variables, and based on the machine learning model, the simulation data is trained to build an initial prediction model framework. With the help of test data, the effectiveness of the initial prediction model framework is verified, and 2-10 sets of data are randomly selected as verification sets to verify the accuracy of the initial prediction model. The machine learning model here can be an XGBoost (Extreme Gradient Boosting) model.

[0070] The core idea of ​​the XGBoost model here is the linear fitting of multiple basic models. The XGBoost model breaks through the computing power limit of the boosted tree model and is mainly used to improve the performance of machine learning models and increase computing speed.

[0071] The initial prediction model here may be a double-defect finite element model, where the double-defect finite element model here refers to an interaction model between every two defects.

[0072] The finite element software here may be Ansys software or the like, and the embodiment of the present invention does not specifically limit this.

[0073] Subsequently, the initial prediction model can be trained based on the sample pipeline data, the sample defect data, and the interaction coefficient labels between the defects, and the initial prediction model after training is used as the prediction model.

[0074] First, sample pipeline data and sample defect data can be input into an initial prediction model, and the initial prediction model outputs the interaction coefficients between the defects.

[0075] After obtaining the interaction coefficients between defects based on the initial prediction model, the interaction coefficients between defects can be compared with the pre-collected interaction coefficient labels between defects, and the loss function value is calculated according to the degree of difference between the two. The initial prediction model is iterated based on the loss function value, and the initial prediction model after the parameter iteration is completed is recorded as the prediction model.

[0076] It can be understood that the greater the difference between the interaction coefficient between each defect and the pre-collected interaction coefficient label between each defect, the greater the loss function value; the smaller the difference between the interaction coefficient between each defect and the pre-collected interaction coefficient label between each defect, the smaller the loss function value.

[0077] That is, during the training of the initial prediction model, the ability to predict the interaction coefficients between defects is learned.

[0078] Step 140, based on the failure pressure of each defect and the interaction coefficient between the group of corrosion defects, determine the interaction failure pressure between the group of corrosion defects, and based on the interaction failure pressure between the group of corrosion defects, perform a safety evaluation of the pipeline containing group corrosion defects on the pipeline to be evaluated.

[0079] Specifically, after obtaining the failure pressure of each defect and the interaction coefficient between the group corrosion defects, the interaction failure pressure between the group corrosion defects can be determined based on the failure pressure of each defect and the interaction coefficient between the group corrosion defects. Here, according to the finite element model study, the mutual influence of multiple group corrosion defects mainly depends on the mutual influence between the two defects, so the failure pressure of the group corrosion defects takes the minimum value of the failure pressure between the two defects.

[0080] After determining the interaction failure pressure between the group corrosion defects, the safety assessment of the pipeline containing group corrosion defects can be performed on the pipeline to be assessed based on the interaction failure pressure between the group corrosion defects. Here, the interaction failure pressure between the group corrosion defects can be the minimum value of the interaction failure pressure between each defect.

[0081] The method provided by the embodiment of the present invention determines the interaction failure pressure between the interaction defects based on the failure pressure of each defect and the interaction coefficient between the defects, and performs defective pipeline safety evaluation on the pipeline to be evaluated based on the interaction failure pressure between the interaction defects. Therefore, when performing defective pipeline safety evaluation, not only the failure pressure of each defect is considered, but also the influence of the interaction between group corrosion defects on the pipeline failure pressure is considered, which further improves the accuracy and reliability of defective pipeline safety evaluation.

[0082] Based on the above embodiment, the formula of the XGBoost model is:

[0083]

[0084] in, is the predicted value of the i-th sample in the model, K is the number of regression trees, and f k (x i ) is the weight of the i-th sample falling on the leaf in the k-th tree, F is the function space composed of all regression trees, and the training data set is D, then D={(x1, y1), (x2, y2), …, (x n ,y n )}, Where R n represents a dataset with n features, x i ∈X represents the i-th sample.

[0085] Based on the above embodiment, the objective loss function of the XGBoost model is:

[0086]

[0087] Where Ω(Θ) represents the objective loss function of the XGBoost model, Θ represents the set of feature weights, Θ = {f1, f2, ..., f k}, L(Θ) represents the training error, that is, the degree of match between the model and the training set, and Ω(Θ) represents the regularization term, that is, the sum of the complexity of the regression trees in the model.

[0088] Based on the above embodiment, the calculation formulas for the training error and the regularization term are as follows:

[0089]

[0090]

[0091] Where L represents the training error, Ω(f k ) represents the regularization term, γ and λ are the regularization term coefficients, T represents the number of leaf nodes, and w j Represents the weight of the jth leaf node.

[0092] In addition, the greedy algorithm can be used to obtain the regression tree shape. The specific process is as follows:

[0093]

[0094] in, represents the score of the (th sample after the ith iteration. Substituting it into the training error formula (3) yields:

[0095]

[0096] Where c is a constant. Using Taylor's formula to expand formula (6), we can get:

[0097]

[0098] Omitting the constant term in equation (7), the objective function after the tth iteration is:

[0099]

[0100] Assume that q is the structure of the regression tree, q(x) represents the position of the leaf where the sample falls, then f t (x) = w q(x) ;Use I j Represents all samples in the jth leaf, where I j ={i|q(x i )=j}, combine the objective function in equation (8) according to each leaf and omit the constant term in the equation, then the objective function after the tth iteration is:

[0101]

[0102] In order to obtain the optimal weight value of the leaf node and the extreme value of the objective function, w in formula (9) j Take the derivative and get the optimal weight w of the jth leaf j * And the optimal objective solution is:

[0103]

[0104]

[0105] Obtain the predicted value of the interaction coefficient between the axially arranged double defects under t iterations.

[0106] The results of the double defect interaction coefficients under all the examples of the X52 pipeline are used as the training set, and the XGBoost model is used to predict the interaction coefficients between various defects under different pipeline data and defect data. The ratio of the training set to the test set is set to 7:3.

[0107] When using the XGBoost model to predict the interaction coefficients between defects, some parameters in the model need to be set. The model mainly involves three types of parameters. The first type of parameters are general parameters, which are used to set the macro functions of the model; the second type of parameters are booster parameters, which are used to control the regularization terms in the model; and the last type is learning parameters, which are used to optimize the model and control the performance of the training target. The rationality of the parameter setting determines the accuracy of the model prediction results. The optimal parameters of the model are determined based on the network search (Grid search). The specific parameter adjustment results are shown in Table 1.

[0108] Table 1 Parameter settings of XGBoost model

[0109]

[0110] Among them, "learning_rate" in Table 1 represents the learning rate, which is 0.01-0.2; "max_depth" represents the maximum depth of the regression tree, which is used to control the fitting process of the model. When the max_depth value is larger, the model learns more fully about the local samples, and the more likely it is to overfit, and the value is 3-10; "num_boost_round" represents the number of boosting iterations; "objective" is used to define the loss function, and the regression prediction used in this invention is the mean square error; "gama" represents the required feature splitting. The minimum loss function descent value corresponds to the coefficient γ in the regularization term; "subsample" and "colsample_bytree" are used to control the random sampling ratio of each regression tree, ranging from 0.5 to 1. If the value is too small, the model will be underfitted; "reg_lambda" and "reg_alpha" are used to control the complexity of the model, where "reg_lambda" represents the coefficient of the L2 regularization term; "reg_alpha" represents the number of coefficients of the L1 regularization term; "n_estimators" is used to control the number of weak classifiers.

[0111] Users can select training sets to train the prediction models between various defects, and the system will output the training errors to the display terminal.

[0112] Based on the above embodiment, step 140 includes:

[0113] Step 141, based on the failure pressures of the defects, determining a minimum value of the failure pressures of the defects;

[0114] Step 142: determining the interaction failure pressure between the group of corrosion defects based on the minimum value of the failure pressure of each defect and the interaction coefficient between the group of corrosion defects.

[0115] Specifically, after the failure pressure of each defect is obtained, the minimum value of the failure pressure between the defects can be determined based on the failure pressure of each defect. For example, the failure pressure of defect a is P a , the failure pressure of defect b is P b , if P a <P b , then the minimum failure pressure between defect a and defect b is P a If P a >P b , then the minimum failure pressure between defect a and defect b is P b .

[0116] After the minimum value of the failure pressure between the defects is obtained, the interaction failure pressure between the group of corrosion defects can be determined based on the minimum value of the failure pressure between the defects and the interaction coefficient between the group of corrosion defects.

[0117] The method provided in the embodiment of the present invention not only considers the failure pressure of each defect when conducting the safety evaluation of the defective pipeline, but also refers to the interaction coefficient between the group corrosion defects, thereby further improving the accuracy and reliability of the safety evaluation of the defective pipeline.

[0118] Based on the above embodiment, step 140 includes:

[0119] The interaction failure pressure between group corrosion defects is determined based on the following formula:

[0120] If P a <P b , then the interaction failure pressure between group corrosion defects is:

[0121] P ab =f ab ×P a

[0122] If P a >P b, then the interaction failure pressure between group corrosion defects is:

[0123] P ab =f ab ×P b

[0124] Among them, f ab is the interaction coefficient between defect a and defect b, P a is the failure pressure of defect a, P b is the failure pressure of defect b.

[0125] Based on the above embodiment, step 140 includes:

[0126] Step 210, determining a minimum value of the interaction failure pressure between the group of corrosion defects based on the interaction failure pressure between the group of corrosion defects;

[0127] Step 220: Based on the minimum value of the interaction failure pressure between the group of corrosion defects, a safety assessment of the pipeline containing group corrosion defects is performed on the pipeline to be assessed.

[0128] Specifically, after the interaction failure pressure between the group of corrosion defects is obtained, the minimum value of the interaction failure pressure between the group of corrosion defects may be determined based on the interaction failure pressure between the group of corrosion defects.

[0129] Then, based on the minimum value of the interaction failure pressure between the group corrosion defects, the safety assessment of the pipeline containing group corrosion defects can be carried out.

[0130] For example, the safety assessment of the pipeline containing group corrosion defects can be carried out on the pipeline to be assessed based on the following formula:

[0131] P double =min{P 12 ,P 13 ,…,P nm}(n=1,2,…,N-1, m=n+1,n+2,…,N)

[0132] Where N is the total number of defects, P a is the failure pressure of defect a, P b is the failure pressure of defect b, P nm is the interaction failure pressure between the nth defect and the mth defect.

[0133] It can be understood that based on the minimum value of the interaction failure pressure between group corrosion defects, defective pipeline safety evaluation of the pipeline to be evaluated can ensure the safety of pipelines containing group corrosion defects, reduce the possibility of pipeline perforation, pipeline leakage or pipeline rupture, and improve the safety of the pipeline.

[0134] Based on the above embodiment, the prediction model is a double defect interaction coefficient prediction model;

[0135] Step 131 includes:

[0136] The defect spacing and pipeline wall thickness in the pipeline data, as well as the defect size of each defect in the defect data are input into the double defect interaction coefficient prediction model to obtain the interaction coefficient of each two defect combinations in each defect output by the double defect interaction coefficient prediction model.

[0137] Specifically, the prediction model may be a prediction model for the interaction coefficient between two defects, where the prediction model for the interaction coefficient between two defects refers to a prediction model for the interaction coefficient between every two defects.

[0138] Specifically, the defect spacing, pipeline wall thickness, pipeline tensile strength, pipeline hardening index and other data in the pipeline data, as well as the defect size of each defect in the defect data can be input into the double defect interaction coefficient prediction model to obtain the interaction coefficient f of each combination of two defects in each defect output by the double defect interaction coefficient prediction model. ab This process is similar to step 130 and will not be repeated here.

[0139] Based on any of the above embodiments, the present invention provides a method for safety assessment of a pipeline containing group corrosion defects. Figure 2 This is the second flow chart of the method for safety assessment of pipelines containing group corrosion defects provided by the present invention, such as Figure 2 As shown, the method includes:

[0140] The first step is to obtain the pipeline data and defect data of the pipeline to be evaluated. The pipeline data of the pipeline to be evaluated here includes the pipeline outer diameter, pipeline wall thickness, pipeline tensile strength and pipeline hardening index; the defect data of the pipeline to be evaluated includes the length of the defect, the width of the defect, the depth of the defect, the axial spacing between each defect and the circumferential spacing between each defect.

[0141] The second step is to determine the failure pressure of each defect in the pipeline to be evaluated based on the pipeline data and group corrosion defect data. The formula is as follows:

[0142]

[0143] Where, f=1,2,......,N,P f is the failure pressure of each defect in the pipeline to be evaluated, MPa; n is the pipeline hardening index; t0 is the pipeline wall thickness, mm; D0 is the pipeline outer diameter, mm; σ′ u is the tensile strength of the pipeline, MPa; d is the depth of the defect, mm; L is the length of the defect, mm.

[0144] In the third step, the pipeline data and group corrosion defect data are input into the prediction model to obtain the interaction coefficient between the group corrosion defects output by the prediction model. The prediction model is trained based on the XGBoost model.

[0145] The fourth step is to determine the minimum value of the failure pressure between defects based on the failure pressure of each defect.

[0146] The interaction failure pressure between the defects is determined based on the minimum value of the failure pressure between the defects and the interaction coefficient between the defects.

[0147] The fifth step is to determine the minimum value of the interaction failure pressure between the group corrosion defects based on the interaction failure pressure between the group corrosion defects.

[0148] The sixth step is to conduct a safety assessment of the pipeline containing group corrosion defects based on the minimum value of the interaction failure pressure between group corrosion defects.

[0149] The following is a description of a pipeline safety assessment device containing group corrosion defects provided by the present invention. The pipeline safety assessment device containing group corrosion defects described below and the pipeline safety assessment method containing group corrosion defects described above can be referenced to each other.

[0150] Based on any of the above embodiments, the present invention provides a pipeline safety assessment device containing group corrosion defects. Figure 3 Schematic diagram of the structure of the pipeline safety evaluation device containing group corrosion defects provided by the present invention. Figure 3 As shown, the device comprises:

[0151] An acquisition unit 310 is used to acquire pipeline data and group corrosion defect data of the pipeline to be evaluated;

[0152] A determination unit 320, configured to determine the failure pressure of each defect in the pipeline to be evaluated based on the pipeline data and the group corrosion defect data;

[0153] A prediction unit 330, configured to input the pipeline data and the group corrosion defect data into a prediction model to obtain an interaction coefficient between the group corrosion defects output by the prediction model, wherein the prediction model is obtained based on XGBoost model training;

[0154] The safety evaluation unit 340 is used to determine the interaction failure pressure between the group of corrosion defects based on the failure pressure of each defect and the interaction coefficient between the group of corrosion defects, and perform safety evaluation of the pipeline containing group corrosion defects on the pipeline to be evaluated based on the interaction failure pressure between the group of corrosion defects.

[0155] The device provided by the embodiment of the present invention determines the interaction failure pressure between the interaction defects based on the failure pressure of each defect and the interaction coefficient between the defects, and performs defective pipeline safety evaluation on the pipeline to be evaluated based on the interaction failure pressure between the interaction defects. Therefore, when performing the defective pipeline safety evaluation, not only the failure pressure of each defect is considered, but also the influence of the interaction between group corrosion defects on the pipeline failure pressure is considered, which further improves the accuracy and reliability of the defective pipeline safety evaluation.

[0156] Based on any of the above embodiments, the formula of the XGBoost model is:

[0157]

[0158] in, is the predicted value of the i-th sample in the model, K is the number of regression trees, and f k (x i ) is the weight of the i-th sample falling on the leaf in the k-th tree, F is the function space composed of all regression trees, and the training data set is D, then D={(x1, y1), (x2, y2), …, (x n ,y n )}, Where R n represents a dataset with n features, x i ∈X represents the i-th sample.

[0159] Based on any of the above embodiments, the objective loss function of the XGBoost model is:

[0160]

[0161] Where Ω(Θ) represents the objective loss function of the XGBoost model, Θ represents the set of feature weights, Θ = {f1, f2, ..., f k}, L(Θ) represents the training error, that is, the degree of match between the model and the training set, and Ω(Θ) represents the regularization term, that is, the sum of the complexity of the regression trees in the model.

[0162] Based on any of the above embodiments, the calculation formulas of the training error and the regularization term are as follows:

[0163]

[0164]

[0165] Where L represents the training error, Ω(f k) represents the regularization term, γ and λ are the regularization term coefficients, T represents the number of leaf nodes, and w j Represents the weight of the jth leaf node.

[0166] Based on any of the above embodiments, the safety evaluation unit 340 is specifically used for:

[0167] A failure pressure minimum value determining unit, used to determine the minimum value of the failure pressure of each defect based on the failure pressure of each defect;

[0168] The interaction failure pressure determination unit is used to determine the interaction failure pressure between the group of corrosion defects based on the minimum value of the failure pressure of each defect and the interaction coefficient between the group of corrosion defects.

[0169] Based on any of the above embodiments, determining the interaction failure pressure unit is specifically used for:

[0170] The interaction failure pressure between the group of corrosion defects is determined based on the following formula:

[0171] If P a <P b , then the interaction failure pressure between group corrosion defects is:

[0172] P ab =f ab ×P a

[0173] If P a >P b , then the interaction failure pressure between group corrosion defects is:

[0174] P ab =f ab ×P b

[0175] Among them, f ab is the interaction coefficient between defect a and defect b, P a is the failure pressure of defect a, P b is the failure pressure of defect b.

[0176] Based on any of the above embodiments, the safety evaluation unit 340 is specifically used for:

[0177] Based on the following formula, the safety evaluation of the pipeline containing group corrosion defects is performed on the pipeline to be evaluated:

[0178] P double =min{P 12 , P 13 , ..., P nm}(n=1,2,...,N-1,m=n+1,n+2,...,N)

[0179] Where N is the total number of defects, P a is the failure pressure of defect a, P b is the failure pressure of defect b, P nm is the interaction failure pressure between the nth defect and the mth defect.

[0180] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4 As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430 and a communication bus 440, wherein the processor 410, the communication interface 420 and the memory 430 communicate with each other through the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute the safety evaluation method of a pipeline containing group corrosion defects, the method comprising: obtaining pipeline data and group corrosion defect data of the pipeline to be evaluated; determining the failure pressure of each defect in the pipeline to be evaluated based on the pipeline data and the group corrosion defect data; inputting the pipeline data and the group corrosion defect data into a prediction model to obtain the interaction coefficient between the group corrosion defects output by the prediction model, wherein the prediction model is obtained based on the training of the XGBoost model; determining the interaction failure pressure between the group corrosion defects based on the failure pressure of each defect and the interaction coefficient between the group corrosion defects, and performing a safety evaluation of the pipeline containing group corrosion defects on the pipeline to be evaluated based on the interaction failure pressure between the group corrosion defects.

[0181] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0182] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the pipeline safety assessment method containing group corrosion defects provided by the above methods, the method comprising: obtaining pipeline data and group corrosion defect data of the pipeline to be evaluated; determining the failure pressure of each defect in the pipeline to be evaluated based on the pipeline data and the group corrosion defect data; inputting the pipeline data and the group corrosion defect data into a prediction model to obtain the interaction coefficient between the group corrosion defects output by the prediction model, wherein the prediction model is obtained based on XGBoost model training; based on the failure pressure of each defect and the interaction coefficient between the group corrosion defects, determining the interaction failure pressure between the group corrosion defects, and based on the interaction failure pressure between the group corrosion defects, performing a pipeline safety assessment containing group corrosion defects on the pipeline to be evaluated.

[0183] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the processor executes the method for safety assessment of a pipeline containing group corrosion defects provided by the above methods, the method comprising: obtaining pipeline data and group corrosion defect data of the pipeline to be evaluated; determining the failure pressure of each defect in the pipeline to be evaluated based on the pipeline data and the group corrosion defect data; inputting the pipeline data and the group corrosion defect data into a prediction model to obtain the interaction coefficient between the group corrosion defects output by the prediction model, wherein the prediction model is obtained based on XGBoost model training; determining the interaction failure pressure between the group corrosion defects based on the failure pressure of each defect and the interaction coefficient between the group corrosion defects, and performing a pipeline safety assessment containing group corrosion defects on the pipeline to be evaluated based on the interaction failure pressure between the group corrosion defects.

[0184] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0185] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0186] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for safety assessment of pipelines containing group corrosion defects, characterized in that: include: Obtain pipeline data and group corrosion defect data of the pipeline to be evaluated; Determining the failure pressure of each defect in the pipeline to be evaluated based on the pipeline data and the group corrosion defect data; Inputting the pipeline data and the group corrosion defect data into a prediction model to obtain an interaction coefficient between the group corrosion defects output by the prediction model, wherein the prediction model is obtained based on XGBoost model training; Based on the failure pressure of each defect and the interaction coefficient between the group of corrosion defects, the interaction failure pressure between the group of corrosion defects is determined, and based on the interaction failure pressure between the group of corrosion defects, the safety evaluation of the pipeline containing group corrosion defects is performed on the pipeline to be evaluated.

2. The method for safety assessment of pipelines containing group corrosion defects according to claim 1 is characterized in that: The formula of the XGBoost model is: in, is the predicted value of the i-th sample in the model, K is the number of regression trees, and f k (x i ) is the weight of the i-th sample falling on the leaf in the k-th tree, F is the function space composed of all regression trees, and the training data set is D, then D={(x1,y1),(x2,y2),…,(x n ,y n )}, Where R n represents a dataset with n features, x i ∈X represents the i-th sample.

3. The method for safety assessment of pipelines containing group corrosion defects according to claim 2 is characterized in that: The objective loss function of the XGBoost model is: Among them, Ω(Θ) represents the target loss function of the XGBoost model, Θ represents the set of feature weights, Θ={f1,f2,…,f k }, L(Θ) represents the training error, that is, the degree of match between the model and the training set, and Ω(Θ) represents the regularization term, that is, the sum of the complexity of the regression trees in the model.

4. The method for safety assessment of pipelines containing group corrosion defects according to claim 3 is characterized in that: The calculation formulas of the training error and the regularization term are as follows: Where L represents the training error, Ω(f k ) represents the regularization term, γ and λ are the regularization term coefficients, T represents the number of leaf nodes, and w j Represents the weight of the jth leaf node.

5. The method for safety assessment of pipelines containing group corrosion defects according to claim 1, characterized in that: The determining the interaction failure pressure between the group of corrosion defects based on the failure pressure of each defect and the interaction coefficient between the group of corrosion defects includes: Based on the failure pressures of the defects, determining a minimum value of the failure pressures of the defects; Based on the minimum value of the failure pressure of each defect and the interaction coefficient between the group of corrosion defects, the interaction failure pressure between the group of corrosion defects is determined.

6. The method for safety assessment of pipelines containing group corrosion defects according to claim 5 is characterized in that: The determining of the interaction failure pressure between the group of corrosion defects based on the minimum value of the failure pressure of each defect and the interaction coefficient between the group of corrosion defects includes: The interaction failure pressure between the group of corrosion defects is determined based on the following formula: If P a <P b , then the interaction failure pressure between group corrosion defects is: P ab =f ab ×P a If P a >P b , then the interaction failure pressure between group corrosion defects is: P ab =f ab ×P b Among them, f ab is the interaction coefficient between defect a and defect b, P a is the failure pressure of defect a, P b is the failure pressure of defect b.

7. The method for safety assessment of pipelines containing group corrosion defects according to claim 1 is characterized in that: The method of performing a safety assessment of a pipeline containing group corrosion defects on the pipeline to be assessed based on the interaction failure pressure between the group corrosion defects includes: Based on the following formula, the safety evaluation of the pipeline containing group corrosion defects is performed on the pipeline to be evaluated: P double =min{P 12 ,P 13 ,…,P nm }(n=1,2,…,N-1,m=n+1,n+2,…,N) Where N is the total number of defects, P a is the failure pressure of defect a, P b is the failure pressure of defect b, P nm is the interaction failure pressure between the nth defect and the mth defect.

8. A safety assessment device for pipelines containing group corrosion defects, characterized in that: include: An acquisition unit, used for acquiring pipeline data and group corrosion defect data of the pipeline to be evaluated; A determination unit, configured to determine the failure pressure of each defect in the pipeline to be evaluated based on the pipeline data and the group corrosion defect data; A prediction unit, used for inputting the pipeline data and the group corrosion defect data into a prediction model to obtain an interaction coefficient between the group corrosion defects output by the prediction model, wherein the prediction model is obtained based on XGBoost model training; The safety evaluation unit is used to determine the interaction failure pressure between the group of corrosion defects based on the failure pressure of each defect and the interaction coefficient between the group of corrosion defects, and to perform a safety evaluation of the pipeline containing group corrosion defects on the pipeline to be evaluated based on the interaction failure pressure between the group of corrosion defects.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method for safety assessment of a pipeline containing group corrosion defects as described in any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for safety assessment of a pipeline containing group corrosion defects as described in any one of claims 1 to 7 is implemented.

Images