CN114091320B - Method and device for predicting corrosion failure time of natural gas pipeline - Google Patents
Method and device for predicting corrosion failure time of natural gas pipeline Download PDFInfo
- Publication number
- CN114091320B CN114091320B CN202111121980.7A CN202111121980A CN114091320B CN 114091320 B CN114091320 B CN 114091320B CN 202111121980 A CN202111121980 A CN 202111121980A CN 114091320 B CN114091320 B CN 114091320B
- Authority
- CN
- China
- Prior art keywords
- parameters
- pipeline
- corrosion failure
- corrosion
- failure time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/14—Pipes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/04—Ageing analysis or optimisation against ageing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Mathematical Analysis (AREA)
- Data Mining & Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Geometry (AREA)
- Algebra (AREA)
- Computer Hardware Design (AREA)
- Databases & Information Systems (AREA)
- Testing Resistance To Weather, Investigating Materials By Mechanical Methods (AREA)
Abstract
The invention provides a method and a device for predicting corrosion failure time of a natural gas pipeline. The method comprises the following steps: determining pipeline parameters influencing the pipeline corrosion failure time by establishing a pipeline corrosion failure equation; selecting environmental parameters affecting the corrosion failure time of the pipeline; screening the pipeline parameters and the environment parameters based on correlation; and constructing a prediction model by taking the screened parameters as input variables and the corrosion failure time as output variables, and predicting the corrosion failure time of the pipeline by using the trained model. According to the method, the pipeline corrosion failure equation is established to determine the pipeline parameters influencing the corrosion failure time, the environment parameters of the pipeline are increased, and the parameters which are screened based on the correlation are used as the input variables of the prediction model, so that the prediction accuracy of the prediction model can be obviously improved.
Description
Technical Field
The invention relates to the technical field of natural gas pipeline corrosion prediction, in particular to a natural gas pipeline corrosion failure time prediction method and device.
Background
Natural gas pipelines are an integral part of the natural gas pipeline network. Because the natural gas product contains corrosive gases such as hydrogen sulfide, carbon dioxide and the like and the influence of environmental factors on the pipeline, the pipeline is easy to corrode to cause damage and failure. The problem of natural gas pipeline in the aspect of corrosion is one of main factors influencing the gas safety of China, urban gas is related to national life, pipeline corrosion not only can influence the service life of the natural gas pipeline (from the time of being buried underground to the time of failure caused by corrosion, namely, corrosion failure time), potential safety hazards are formed, and safety accidents can be caused when the potential safety hazard is serious. Therefore, in order to prolong the service life of the natural gas pipeline and ensure the safe, economical and efficient operation of the pipeline, the corrosion monitoring work of the natural gas pipeline must be carried out.
At present, an online detection method is widely applied to corrosion monitoring of pipelines. This technique requires frequent assessment of the pipe condition by high-tech equipment such as magnetic flux and ultrasonic tools, however, this approach is too expensive and time consuming due to the high frequency of on-line inspection and resolution requirements required. In recent years, researchers have focused more on the development of predictive models that can be used to predict corrosion failure. However, these existing models do not consider environmental factors such as soil temperature and the like of corrosion damage, and thus the prediction accuracy of the models is not high.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a method and a device for predicting the corrosion failure time of a natural gas pipeline.
In order to achieve the above object, the present invention adopts the following technical scheme.
In a first aspect, the invention provides a method for predicting corrosion failure time of a natural gas pipeline, comprising the following steps:
determining pipeline parameters influencing the pipeline corrosion failure time by establishing a pipeline corrosion failure equation;
selecting environmental parameters affecting the corrosion failure time of the pipeline;
screening the pipeline parameters and the environment parameters based on correlation;
and constructing a prediction model by taking the screened parameters as input variables and the corrosion failure time as output variables, and predicting the corrosion failure time of the pipeline by using the trained model.
Further, the method for establishing the pipeline corrosion failure equation comprises the following steps:
assuming that the corrosion defect of the pipe is rectangular, the failure pressure is:
wherein p is f For failure pressure, sigma b For minimum yield strength, D, delta are the diameter and wall thickness of the pipeline, D (t) is the function of the change of defect depth with time t, beta is the bulge coefficient, and L (t) is the function of the change of defect length with time;
assuming that pipe corrosion is a quasi-steady state process, then:
d(t)＝d 0 +v r (t-t 0 )
L(t)＝L 0 +v a (t-t 0 )
in the formula, v r 、v a The corrosion rate in the radial direction, i.e. the depth direction, and the corrosion rate in the axial direction, i.e. the length direction, d 0 、L 0 Respectively the last detection time t 0 Defect depth and defect length at the time.
Still further, the method for screening the pipeline parameters and the environment parameters comprises the following steps:
calculating the correlation coefficient of each parameter and corrosion failure time, and sequencing the parameters according to the sequence from the high correlation coefficient to the low correlation coefficient;
deleting parameters with the correlation coefficient smaller than a first threshold value;
and calculating a correlation coefficient between any two parameters in the remaining parameters, and deleting one parameter with a later sequence for the two parameters with the correlation coefficient larger than the second threshold value.
Still further, the predictive model is:
wherein t is s For corrosion failure time, T is the average temperature of the soil in months, h is the depth of coverage of the soil, p f P is the maximum allowable pressure for the failure.
Further, the method further comprises a model correction step:
constructing a test data set, substituting the data set into a prediction model to obtain predicted corrosion failure time;
calculating the standard deviation of the predicted corrosion failure time and the fitting degree of a prediction model;
if the standard deviation is larger than the set threshold value and the fitting degree is smaller than the set threshold value, the accuracy of the prediction model does not meet the requirement, and the prediction model is modified until the accuracy meets the requirement.
In a second aspect, the present invention provides a natural gas pipeline corrosion failure time prediction apparatus, comprising:
the pipeline parameter selection module is used for determining pipeline parameters influencing the pipeline corrosion failure time by establishing a pipeline corrosion failure equation;
the environment parameter selection module is used for selecting environment parameters affecting the corrosion failure time of the pipeline;
the parameter screening module is used for screening the pipeline parameters and the environment parameters based on correlation;
the modeling prediction module is used for constructing a prediction model by taking the screened parameters as input variables and the corrosion failure time as output variables, and predicting the corrosion failure time of the pipeline by using the trained model.
Further, the method for establishing the pipeline corrosion failure equation comprises the following steps:
assuming that the corrosion defect of the pipe is rectangular, the failure pressure is:
wherein p is f For failure pressure, sigma b For minimum yield strength, D, delta are the diameter and wall thickness of the pipeline, D (t) is the function of the change of defect depth with time t, beta is the bulge coefficient, and L (t) is the function of the change of defect length with time;
assuming that pipe corrosion is a quasi-steady state process, then:
d(t)＝d 0 +v r (t-t 0 )
L(t)＝L 0 +v a (t-t 0 )
in the formula, v r 、v a The corrosion rate in the radial direction, i.e. the depth direction, and the corrosion rate in the axial direction, i.e. the length direction, d 0 、L 0 Respectively the last detection time t 0 Defect depth and defect length at the time.
Still further, the method for screening the pipeline parameters and the environment parameters comprises the following steps:
calculating the correlation coefficient of each parameter and corrosion failure time, and sequencing the parameters according to the sequence from the high correlation coefficient to the low correlation coefficient;
deleting parameters with the correlation coefficient smaller than a first threshold value;
and calculating a correlation coefficient between any two parameters in the remaining parameters, and deleting one parameter with a later sequence for the two parameters with the correlation coefficient larger than the second threshold value.
Still further, the predictive model is:
wherein t is s For corrosion failure time, T is the average temperature of the soil in months, h is the depth of coverage of the soil, p f P is the maximum allowable pressure for the failure.
Further, the apparatus comprises a model correction module for,
constructing a test data set, substituting the data set into a prediction model to obtain predicted corrosion failure time;
calculating the standard deviation of the predicted corrosion failure time and the fitting degree of a prediction model;
if the standard deviation is larger than the set threshold value and the fitting degree is smaller than the set threshold value, the accuracy of the prediction model does not meet the requirement, and the prediction model is modified until the accuracy meets the requirement.
Compared with the prior art, the invention has the following beneficial effects.
According to the method, a pipeline corrosion failure equation is established, pipeline parameters influencing the pipeline corrosion failure time are determined, environment parameters influencing the pipeline corrosion failure time are selected, the pipeline parameters and the environment parameters are screened based on correlation, the screened parameters are taken as input variables, the corrosion failure time is taken as output variables, a prediction model is constructed, the trained model is used for predicting the pipeline corrosion failure time, and automatic prediction of the pipeline corrosion failure time is realized. According to the method, the pipeline corrosion failure equation is established to determine the pipeline parameters influencing the corrosion failure time, the environment parameters of the pipeline are increased, and the parameters which are screened based on the correlation are used as the input variables of the prediction model, so that the prediction accuracy of the prediction model can be obviously improved.
Drawings
FIG. 1 is a flow chart of a method for predicting corrosion failure time of a natural gas pipeline according to an embodiment of the invention.
FIG. 2 is a diagram showing the comparison of a predicted value obtained by applying a predictive model with a true value.
FIG. 3 is a block diagram of a natural gas pipeline corrosion failure time prediction device according to an embodiment of the invention.
Detailed Description
The present invention will be further described with reference to the drawings and the detailed description below, in order to make the objects, technical solutions and advantages of the present invention more apparent. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Fig. 1 is a flowchart of a method for predicting corrosion failure time of a natural gas pipeline according to an embodiment of the present invention, including the following steps:
102, selecting environmental parameters affecting the corrosion failure time of a pipeline;
and 104, constructing a prediction model by taking the screened parameters as input variables and the corrosion failure time as output variables, and predicting the corrosion failure time of the pipeline by using the trained model.
In this embodiment, step 101 is mainly used to determine the parameters of the pipeline that affect the corrosion failure time of the pipeline. The pipe parameters refer to parameters related to the structure of the pipe, such as pipe diameter, wall thickness, etc. The pipe parameters determined here are to be used as input variables for the prediction model of the corrosion failure time, which should be relatively sensitive to changes in these parameters in order to improve the prediction accuracy of the prediction model. According to the method, the pipeline corrosion failure equation is established, pipeline parameters contained in the equation are used as pipeline parameters influencing corrosion failure time, so that compared with the prior art, the method is more convincing to determine the pipeline parameters according to experience or subjective imagination, and the prediction accuracy is also more beneficial to improvement. The method for establishing the corrosion failure equation of the pipeline is more, the specific equation establishment method is not limited in this embodiment, and a specific technical scheme will be provided in the following embodiment.
In this embodiment, step 102 is mainly used to select environmental parameters affecting the corrosion failure time of the pipeline. Environmental parameters refer to weather around the pipeline, geographical factors such as temperature, humidity, depth of burial, etc. Practice shows that the prediction result hardly meets the precision requirement by taking the pipeline parameters as the input variables of the prediction model; and the prediction precision is obviously improved after the environmental factors are increased. If the pipeline parameter is regarded as an internal factor, the environmental parameter can be regarded as an external factor, and the embodiment improves the prediction accuracy by increasing the environmental parameter, and is an application of the philosophy principle that the external factor acts by the internal factor.
In this embodiment, step 103 is mainly used for screening the pipeline parameters and the environmental parameters. The factors influencing the corrosion failure time of the pipeline are numerous, or the number of the pipeline parameters and the environment parameters selected before are numerous, if the parameters are used as input variables of a prediction model in an unselected mode, the prediction accuracy cannot be improved, and the method can be the opposite. Therefore, the present embodiment filters these parameters before constructing the prediction model, and deletes those parameters that have no significant effect on the corrosion failure time. In this embodiment, the parameters are screened based on correlation, where the correlation mainly refers to the correlation between the parameters and the corrosion failure time, and the stronger the correlation, the more obvious the influence of the parameters on the corrosion failure time. The correlation strength can be obtained by calculating the correlation coefficient. The correlation coefficient has positive and negative components, the positive correlation coefficient represents positive correlation, and when one quantity is increased, the other quantity is also increased; the correlation coefficient being negative indicates a negative correlation, one increasing in magnitude and the other decreasing in magnitude. Thus, the larger the absolute value of the correlation coefficient, the stronger the correlation. The following examples will give a specific screening method.
In this embodiment, step 104 is mainly used for constructing a prediction model and predicting with a trained model. In the embodiment, the screened parameters are taken as input variables, and the corrosion failure time is taken as output variables, so that a prediction model is constructed. The prediction model can adopt a regression model or an artificial neural network. The regression model may be a multiple linear model or a multiple quadratic model, i.e. a multiple primary or multiple quadratic function with the corrosion failure time as input parameter. The latter is of higher complexity but also of higher precision. The artificial neural network can be regarded as a black box, and a specific function expression is not known, and only input and output are known. The artificial neural network has the characteristics of high precision, complex internal structure of the model, more internal parameters needing to be learned and large calculated amount. And constructing a training data set by collecting historical data, and training a prediction model by using the data set to obtain model parameters. Substituting the values of the screened pipeline parameters and the environmental parameters into a trained prediction model, and outputting the model to obtain the predicted value of the corrosion failure time.
As an alternative embodiment, the method for establishing the pipeline corrosion failure equation comprises the following steps:
assuming that the corrosion defect of the pipe is rectangular, the failure pressure is:
wherein p is f For failure pressure, sigma b For minimum yield strength, D, delta are the diameter and wall thickness of the pipeline, D (t) is the function of the change of defect depth with time t, beta is the bulge coefficient, and L (t) is the function of the change of defect length with time;
assuming that pipe corrosion is a quasi-steady state process, then:
d(t)＝d 0 +v r (t-t 0 )
L(t)＝L 0 +v a (t-t 0 )
in the formula, v r 、v a The corrosion rate in the radial direction, i.e. the depth direction, and the corrosion rate in the axial direction, i.e. the length direction, d 0 、L 0 Respectively the last detection time t 0 Defect depth and defect length at the time.
The embodiment provides a technical scheme for establishing a pipeline corrosion failure equation. Because the regularity of the pipeline corrosion is not strong, the pipeline corrosion failure calculation belongs to approximate engineering calculation, an accurate theoretical expression cannot be obtained, and a final result can be obtained only based on a certain approximate assumption. In the embodiment, firstly, the shape of a pipeline corrosion defect (corrosion spot) is assumed to be a rectangle, and then the failure pressure p is obtained according to the mechanical principle f If the pressure of the pipe exceeds p f Corrosion failure occurs. P is p f The expression of (2) includes inherent structural parameters of the pipeline itself which do not change with time, such as pipeline diameter, wall thickness and the like; also included are two unknown functions that vary with time, the defect length and defect depth, respectively, and thus require further processing. The present example further assumes that the pipe corrosion is a quasi-steady stateThe state process, i.e. the defect length and defect depth during two adjacent detections, can be regarded as increasing at a constant speed over time, whereby a recursive formula expressed in terms of the rate of increase can be obtained, see in particular the formula above.
As an alternative embodiment, the method for screening the pipeline parameters and the environment parameters includes:
calculating the correlation coefficient of each parameter and corrosion failure time, and sequencing the parameters according to the sequence from the high correlation coefficient to the low correlation coefficient;
deleting parameters with the correlation coefficient smaller than a first threshold value;
and calculating a correlation coefficient between any two parameters in the remaining parameters, and deleting one parameter with a later sequence for the two parameters with the correlation coefficient larger than the second threshold value.
The embodiment provides a technical scheme of parameter screening. As described above, the present embodiment performs parameter screening based on correlation. The correlation involved in this embodiment is of two types: one is the correlation of the parameters to be screened and the corrosion failure time; the other is the correlation between the parameters to be screened, and because the correlation between the pipeline parameters and the environmental parameters is weak, the correlation between the pipeline parameters and the correlation between the environmental parameters can be calculated practically separately. The method adopted by the embodiment is as follows: firstly, calculating the correlation coefficient of the parameters to be screened and the corrosion failure time, and sorting according to the size of the correlation coefficient, and deleting the parameters with smaller correlation coefficient (smaller than a set threshold value) because the influence of the parameters with smaller correlation coefficient on the corrosion failure time is smaller; then, according to the correlation coefficient between any two parameters left after screening, deleting one parameter of the two parameters with larger correlation coefficient, wherein the two parameters with larger correlation coefficient have repeatability, and only one parameter is reserved. The embodiment eliminates one parameter with a smaller correlation coefficient with the corrosion failure time, namely, the one with the later sequence.
As an alternative embodiment, the prediction model is:
wherein t is s For corrosion failure time, T is the average temperature of the soil in months, h is the depth of coverage of the soil, p f P is the maximum allowable pressure for the failure.
The embodiment gives a specific model after training. The model is a quadratic regression model, 7 input variable parameters of the model are provided, wherein 5 pipeline parameters are respectively pipeline diameter, pipeline wall thickness, pressure during failure, maximum allowable pressure and minimum yield strength; environmental parameters were 2, month average soil temperature and soil coverage depth, respectively. The constant term, the first term coefficient and the second term coefficient in the prediction model are all determined through model training.
As an alternative embodiment, the method further comprises a model correction step:
constructing a test data set, substituting the data set into a prediction model to obtain predicted corrosion failure time;
calculating the standard deviation of the predicted corrosion failure time and the fitting degree of a prediction model;
if the standard deviation is larger than the set threshold value and the fitting degree is smaller than the set threshold value, the accuracy of the prediction model does not meet the requirement, and the prediction model is modified until the accuracy meets the requirement.
The embodiment provides a technical scheme for checking and correcting the prediction model. The test data set is constructed by collecting the historical data first, and can be performed together with the construction of the training data set, and the constructed historical data set is distributed proportionally, for example, 80% of samples are taken as the training data set, and 20% of samples are taken as the test data set. And substituting the sample data in the test data set into a prediction model to obtain a prediction result of the corrosion failure time. Calculating the standard deviation of the prediction result and the fitting degree of the model, wherein the standard deviation reflects the dispersion degree of the prediction result, and the larger the standard deviation is, the more dispersed the data is; the fitness reflects the magnitude of the prediction error of the model. And finally, comparing the standard deviation and the fitting degree with set thresholds respectively, and judging whether the model precision meets the requirement or not according to the standard deviation and the fitting degree. If the requirements are not met, modifying the parameters of the regression model until the standard deviation and the fitting degree are within a threshold range.
In order to verify the effectiveness of the invention, a prediction model is built for part of natural gas pipelines in a certain area, and a comparison diagram of the result of the predicted value and the actual value of the corrosion failure time obtained by applying the prediction model is given in FIG. 2. As can be seen from FIG. 2, the application situation is good, and the accuracy is as high as 87%.
Fig. 3 is a schematic diagram of a device for predicting corrosion failure time of a natural gas pipeline according to an embodiment of the present invention, where the device includes:
the pipeline parameter selection module 11 is used for determining pipeline parameters influencing the pipeline corrosion failure time by establishing a pipeline corrosion failure equation;
an environmental parameter selection module 12 for selecting environmental parameters affecting the corrosion failure time of the pipeline;
a parameter screening module 13, configured to screen the pipeline parameter and the environmental parameter based on correlation;
the modeling prediction module 14 is configured to construct a prediction model by using the filtered parameters as input variables and the corrosion failure time as output variables, and predict the corrosion failure time of the pipeline by using the trained model.
The device of this embodiment may be used to implement the technical solution of the method embodiment shown in fig. 1, and its implementation principle and technical effects are similar, and are not described here again. As well as the latter embodiments, will not be explained again.
As an alternative embodiment, the method for establishing the pipeline corrosion failure equation comprises the following steps:
assuming that the corrosion defect of the pipe is rectangular, the failure pressure is:
in the middle of，p f For failure pressure, sigma b For minimum yield strength, D, delta are the diameter and wall thickness of the pipeline, D (t) is the function of the change of defect depth with time t, beta is the bulge coefficient, and L (t) is the function of the change of defect length with time;
assuming that pipe corrosion is a quasi-steady state process, then:
d(t)＝d 0 +v r (t-t 0 )
L(t)＝L 0 +v a (t-t 0 )
in the formula, v r 、v a The corrosion rate in the radial direction, i.e. the depth direction, and the corrosion rate in the axial direction, i.e. the length direction, d 0 、L 0 Respectively the last detection time t 0 Defect depth and defect length at the time.
As an alternative embodiment, the method for screening the pipeline parameters and the environment parameters includes:
calculating the correlation coefficient of each parameter and corrosion failure time, and sequencing the parameters according to the sequence from the high correlation coefficient to the low correlation coefficient;
deleting parameters with the correlation coefficient smaller than a first threshold value;
and calculating a correlation coefficient between any two parameters in the remaining parameters, and deleting one parameter with a later sequence for the two parameters with the correlation coefficient larger than the second threshold value.
As an alternative embodiment, the prediction model is:
wherein t is s For corrosion failure time, T is the average temperature of the soil in months, h is the depth of coverage of the soil, p f P is the maximum allowable pressure for the failure.
As an alternative embodiment, the apparatus further comprises a model correction module for,
constructing a test data set, substituting the data set into a prediction model to obtain predicted corrosion failure time;
calculating the standard deviation of the predicted corrosion failure time and the fitting degree of a prediction model;
if the standard deviation is larger than the set threshold value and the fitting degree is smaller than the set threshold value, the accuracy of the prediction model does not meet the requirement, and the prediction model is modified until the accuracy meets the requirement.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any changes or substitutions easily contemplated by those skilled in the art within the scope of the present invention should be included in the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (8)
1. The method for predicting the corrosion failure time of the natural gas pipeline is characterized by comprising the following steps of:
determining pipeline parameters influencing the pipeline corrosion failure time by establishing a pipeline corrosion failure equation;
selecting environmental parameters affecting the corrosion failure time of the pipeline;
screening the pipeline parameters and the environment parameters based on correlation, so that the screened parameters are the parameters with the most obvious influence on corrosion failure time;
constructing a prediction model by taking the screened parameters as input variables and the corrosion failure time as output variables, and predicting the corrosion failure time of the pipeline by using the trained model;
the method for establishing the pipeline corrosion failure equation comprises the following steps:
assuming that the corrosion defect of the pipe is rectangular, the failure pressure is:
wherein p is f For failure pressure, sigma b For minimum yield strength, D, delta are the diameter and wall thickness of the pipeline, D (t) is the function of the change of defect depth with time t, beta is the bulge coefficient, and L (t) is the function of the change of defect length with time;
assuming that pipe corrosion is a quasi-steady state process, then:
d(t)＝d 0 +v r (t-t 0 )
L(t)＝L 0 +v a (t-t 0 )
in the formula, v r 、v a The corrosion rate in the radial direction, i.e. the depth direction, and the corrosion rate in the axial direction, i.e. the length direction, d 0 、L 0 Respectively the last detection time t 0 Defect depth and defect length at the time.
2. The method of claim 1, wherein the method of screening the pipeline parameters and the environmental parameters comprises:
calculating the correlation coefficient of each parameter and corrosion failure time, and sequencing the parameters according to the sequence from the high correlation coefficient to the low correlation coefficient;
deleting parameters with the correlation coefficient smaller than a first threshold value;
and calculating a correlation coefficient between any two parameters in the remaining parameters, and deleting one parameter with a later sequence for the two parameters with the correlation coefficient larger than the second threshold value.
3. The method for predicting the corrosion failure time of a natural gas pipeline according to claim 2, wherein the prediction model is:
wherein t is s For corrosion failure time, T is the average temperature of the soil in months, h is the depth of coverage of the soil, p f P is the maximum allowable pressure at the time of failureXu Yali.
4. The method of predicting corrosion failure time of a natural gas pipeline according to claim 1, further comprising the step of model correction:
constructing a test data set, substituting the data set into a prediction model to obtain predicted corrosion failure time;
calculating the standard deviation of the predicted corrosion failure time and the fitting degree of a prediction model;
if the standard deviation is larger than the set threshold value and the fitting degree is smaller than the set threshold value, the accuracy of the prediction model does not meet the requirement, and the prediction model is modified until the accuracy meets the requirement.
5. A natural gas pipeline corrosion failure time prediction device, comprising:
the pipeline parameter selection module is used for determining pipeline parameters influencing the pipeline corrosion failure time by establishing a pipeline corrosion failure equation;
the environment parameter selection module is used for selecting environment parameters affecting the corrosion failure time of the pipeline;
the parameter screening module is used for screening the pipeline parameters and the environment parameters based on correlation, so that the screened parameters are the parameters with the most obvious influence on the corrosion failure time;
the modeling prediction module is used for constructing a prediction model by taking the screened parameters as input variables and the corrosion failure time as output variables, and predicting the corrosion failure time of the pipeline by using the trained model;
the method for establishing the pipeline corrosion failure equation by the pipeline parameter selection module comprises the following steps:
assuming that the corrosion defect of the pipe is rectangular, the failure pressure is:
wherein p is f For failure pressure, sigma b For minimum yield strength, D, delta are the diameter and wall thickness of the pipeline, D (t) is the function of the change of defect depth with time t, beta is the bulge coefficient, and L (t) is the function of the change of defect length with time;
assuming that pipe corrosion is a quasi-steady state process, then:
d(t)＝d 0 +v r (t-t 0 )
L(t)＝L 0 +v a (t-t 0 )
in the formula, v r 、v a The corrosion rate in the radial direction, i.e. the depth direction, and the corrosion rate in the axial direction, i.e. the length direction, d 0 、L 0 Respectively the last detection time t 0 Defect depth and defect length at the time.
6. The natural gas pipeline corrosion failure time prediction apparatus according to claim 5, wherein the method of screening the pipeline parameters and the environmental parameters comprises:
calculating the correlation coefficient of each parameter and corrosion failure time, and sequencing the parameters according to the sequence from the high correlation coefficient to the low correlation coefficient;
deleting parameters with the correlation coefficient smaller than a first threshold value;
and calculating a correlation coefficient between any two parameters in the remaining parameters, and deleting one parameter with a later sequence for the two parameters with the correlation coefficient larger than the second threshold value.
7. The natural gas pipeline corrosion failure time prediction apparatus according to claim 6, wherein the prediction model is:
wherein t is s For corrosion failure time, T is the average temperature of the soil in months, h is the depth of coverage of the soil, p f P is the maximum allowable pressure for the failure.
8. The apparatus for predicting corrosion failure time of a natural gas pipeline according to claim 5, further comprising a model correction module for,
constructing a test data set, substituting the data set into a prediction model to obtain predicted corrosion failure time;
calculating the standard deviation of the predicted corrosion failure time and the fitting degree of a prediction model;
if the standard deviation is larger than the set threshold value and the fitting degree is smaller than the set threshold value, the accuracy of the prediction model does not meet the requirement, and the prediction model is modified until the accuracy meets the requirement.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111121980.7A CN114091320B (en) | 2021-09-24 | 2021-09-24 | Method and device for predicting corrosion failure time of natural gas pipeline |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111121980.7A CN114091320B (en) | 2021-09-24 | 2021-09-24 | Method and device for predicting corrosion failure time of natural gas pipeline |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114091320A CN114091320A (en) | 2022-02-25 |
| CN114091320B true CN114091320B (en) | 2023-05-23 |
Family
ID=80296204
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111121980.7A Active CN114091320B (en) | 2021-09-24 | 2021-09-24 | Method and device for predicting corrosion failure time of natural gas pipeline |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114091320B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115615929B (en) * | 2022-12-13 | 2023-03-14 | 苏州点线空间科技有限公司 | Mechanical part surface defect detection method and system based on laser scanning |
| CN116167313B (en) * | 2023-02-22 | 2023-09-12 | 深圳市摩尔芯创科技有限公司 | Training data generation method and system for integrated circuit design |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109784668B (en) * | 2018-12-21 | 2022-08-23 | 国网江苏省电力有限公司南京供电分公司 | Sample feature dimension reduction processing method for detecting abnormal behaviors of power monitoring system |
| CN111428360B (en) * | 2020-03-23 | 2023-03-28 | 西安建筑科技大学 | Method for predicting residual life of submarine pipeline under different maintenance depth distributions |
| CN112883538B (en) * | 2020-12-29 | 2022-07-22 | 浙江中控技术股份有限公司 | Corrosion prediction system and method for buried crude oil pipeline |
| CN112668206B (en) * | 2021-01-20 | 2022-03-15 | 西南石油大学 | Multi-factor-considered acid gas field corrosion prediction model and parameter determination method |
-
2021
- 2021-09-24 CN CN202111121980.7A patent/CN114091320B/en active Active
Non-Patent Citations (1)
| Title |
|---|
| 引入失效数据的腐蚀管道结构可靠性评价方法;张杰;张佩颖;虞维超;刁逢;王圣洁;宫敬;;安全与环境工程(03);第185-192页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114091320A (en) | 2022-02-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114091320B (en) | Method and device for predicting corrosion failure time of natural gas pipeline | |
| CN109783906B (en) | Intelligent analysis system and method for detecting magnetic flux leakage data in pipeline | |
| CN109086804B (en) | Hydraulic equipment early failure prediction method based on fusion of multi-source state monitoring information and reliability characteristics | |
| CN108225906B (en) | Inhaul cable corrosion monitoring and identifying and fatigue life evaluating method based on computer vision | |
| CN112883538B (en) | Corrosion prediction system and method for buried crude oil pipeline | |
| CN109492708B (en) | LS-KNN-based pipeline magnetic flux leakage internal detection missing data interpolation method | |
| CN113239504A (en) | Pipeline corrosion defect prediction method based on optimized neural network | |
| CN103838931A (en) | Method for evaluating remanufacturing access period of engineering mechanical arm rest class structure | |
| CN113343402B (en) | Pipeline corrosion grade evaluation method based on multilayer convolution sparse coding | |
| CN111428360A (en) | Method for predicting residual life of submarine pipeline under different maintenance depth distributions | |
| CN117233347B (en) | Carbon steel spheroidization grade measuring method, system and equipment | |
| CN115063337A (en) | Intelligent maintenance decision-making method and device for buried pipeline | |
| CN105741184A (en) | Transformer state evaluation method and apparatus | |
| CN109632942B (en) | Inversion method of pipeline defect size based on ensemble learning | |
| CN108709426B (en) | Sintering machine air leakage fault online diagnosis method based on frequency spectrum characteristic bilateral detection method | |
| CN116164241A (en) | Intelligent detection method for leakage faults of gas extraction pipe network | |
| CN115545112A (en) | Method for automatically identifying and processing large amount of sewage real-time automatic monitoring data | |
| CN110895624A (en) | Method for testing consistency of degraded data of accelerated storage and natural storage based on maximum entropy spectrum estimation | |
| CN115482882A (en) | Pipeline corrosion data acquisition and pipeline corrosion rate prediction model construction method | |
| CN115222114A (en) | Automobile part assembly index value prediction method, terminal device and storage medium | |
| CN114970813A (en) | Dissolved oxygen concentration data restoration and prediction method | |
| CN110889187B (en) | Pearson coefficient-based consistency check method for stored degradation data | |
| CN111767323A (en) | Method for predicting length of stratum fracture in real time based on kernel SMO algorithm | |
| Heidary et al. | Fusing more frequent and accurate structural damage information from one location to assess damage at another location with less information | |
| CN111476507A (en) | Multi-parameter coupling safety evaluation method for pipeline vibration response under tunnel blasting effect |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |