Method for predicting service life of buried gas polyethylene pipeline based on mechanical properties

Abstract

The invention relates to a buried gas polyethylene pipeline life prediction method based on mechanical properties, and belongs to the technical field of pipeline life prediction. The method comprises the steps that a creep aging polyethylene sample is obtained through a hydrostatic test according to a fuel gas polyethylene pipe, a polyethylene ultrasonic pulse signal is obtained through ultrasonic detection, and then a polyethylene ultrasonic spectrum coefficient parameter is extracted through ultrasonic signal statistics; performing mechanical detection on the creep aged polyethylene sample to obtain a polyethylene mechanical property parameter, and constructing a polyethylene pipeline creep aging data set in combination with the polyethylene ultrasonic spectrum coefficient parameter, so as to obtain an ultrasonic nondestructive mechanical property prediction model through nonlinear modeling; real-time polyethylene ultrasonic pulse signals are obtained, real-time polyethylene mechanical property parameters are obtained through the ultrasonic lossless mechanical property prediction model, then the remaining life of the gas polyethylene pipeline is obtained through the polyethylene mechanical recession model, and safe operation of the in-service gas polyethylene pipeline is guaranteed.

Description

Technical Field

[0001] The invention belongs to the technical field of pipeline life prediction, and in particular relates to a method for predicting the life of an underground gas polyethylene pipeline based on mechanical properties. Background Art

[0002] Polyethylene pipes are widely used for natural gas transportation due to their strong corrosion resistance, good machinability and long service life. However, polyethylene gas pipelines are buried underground for a long time and are constantly subjected to soil pressure, thermal oxidation aging and internal loads. As the service time increases, the pipe will gradually creep and age, resulting in a decrease in mechanical properties and eventually losing its use value. In order to ensure that the buried gas polyethylene pipeline maintains the integrity of its structure and function throughout its life cycle and achieve the goal of inherent safety of the pipeline, it is extremely urgent to carry out life prediction research on buried gas polyethylene pipelines.

[0003] However, most of the existing life prediction models for buried gas polyethylene pipelines are based on samples obtained under single variable control, and do not fully consider the complex and variable factors faced by the pipeline during actual operation, resulting in deviations between the prediction results and the actual situation. At the same time, due to the hidden characteristics of buried pipelines buried deep underground, it is extremely difficult to obtain their status data. Traditional data processing technology is difficult to effectively extract information that truly reflects the key status of the pipeline from these limited and messy data, which greatly restricts the accuracy of life prediction. In addition, the current research on the aging mechanism of polyethylene pipes is still shallow, especially creep aging caused by internal pressure. As the main aging form of buried gas polyethylene pipes, related life evaluation research is particularly scarce, and it is difficult to perform non-destructive testing on buried gas pipelines.

[0004] Therefore, it is urgent to further study the life prediction model of buried gas polyethylene pipelines to improve the accuracy and reliability of the prediction and provide strong guarantees for the safe operation of gas pipelines. Summary of the invention

[0005] In order to solve the above problems existing in the prior art, the present invention proposes a method for predicting the life of buried polyethylene gas pipelines based on mechanical properties.

[0006] The purpose of the present invention can be achieved through the following technical solutions: A method for predicting the life of buried gas polyethylene pipeline based on mechanical properties, comprising: Acquire a creep-aged polyethylene sample, obtain a polyethylene ultrasonic pulse signal through ultrasonic testing based on the creep-aged polyethylene sample, and obtain a polyethylene ultrasonic spectrum coefficient parameter through ultrasonic signal statistical extraction based on the polyethylene ultrasonic pulse signal; According to the creep-aged polyethylene sample, mechanical property parameters of polyethylene are obtained through mechanical testing, and a polyethylene pipeline creep-aging data set is constructed according to the polyethylene mechanical property parameters and the polyethylene ultrasonic spectrum coefficient parameters; According to the polyethylene pipe creep aging data set, an ultrasonic non-destructive mechanical property prediction model is obtained through nonlinear modeling; A real-time polyethylene ultrasonic pulse signal is obtained, and real-time polyethylene mechanical property parameters are obtained according to the real-time polyethylene ultrasonic pulse signal through the ultrasonic non-destructive mechanical property prediction model, and the remaining life of the gas polyethylene pipeline is obtained according to the real-time polyethylene mechanical property parameters through the polyethylene mechanical decay model.

[0007] Preferably, the extraction of polyethylene ultrasonic spectrum coefficient parameters includes: Acquiring a polyethylene ultrasonic pulse signal by a single probe pulse reflection echo method according to the creep aged polyethylene sample; According to the polyethylene ultrasonic pulse signal, a discrete polyethylene ultrasonic pulse signal sequence is obtained by sampling the polyethylene ultrasonic pulse signal through an analog-to-digital converter; Decomposing the discrete polyethylene ultrasonic pulse signal sequence by lifting wavelet transform to obtain polyethylene pulse signal detail coefficients and polyethylene pulse signal approximation coefficients; Obtaining a polyethylene ultrasonic pulse denoised signal by reconstructing an error compensation according to the polyethylene pulse signal detail coefficient and the polyethylene pulse signal approximation coefficient; Obtaining a polyethylene ultrasonic spectrum by ultrasonic spectrum analysis according to the polyethylene ultrasonic pulse denoising signal; Ultrasonic spectrum coefficient parameters are obtained by statistical extraction of the ultrasonic spectrum according to the polyethylene ultrasonic spectrum.

[0008] Preferably, the mathematical expression of the polyethylene ultrasonic pulse denoising signal is: , Among them, S(n) is the polyethylene ultrasonic pulse denoising signal, S0(n) is the polyethylene ultrasonic pulse original signal, S1(n) is the polyethylene ultrasonic pulse reconstructed signal, n is the discrete index of the polyethylene ultrasonic pulse signal, and α is the reconstruction error compensation coefficient.

[0009] Preferably, the ultrasonic non-destructive mechanical properties prediction model includes: Receiving the polyethylene pipe creep aging dataset via an input layer; According to the polyethylene pipeline creep aging data set, a polyethylene ultrasonic spectrum coefficient parameter sequence feature is obtained through a feature extraction layer; The predicted value of the polyethylene mechanical property parameter is output through the output layer according to the polyethylene ultrasonic spectrum coefficient parameter sequence characteristics, and the output layer is a fully connected layer with three neurons.

[0010] Preferably, the step of calculating the remaining life of the gas polyethylene pipeline includes: Preset polyethylene mechanical properties failure criterion coefficient; Constructing a polyethylene mechanical decay model through comprehensive decay according to the polyethylene mechanical property failure criterion coefficient and polyethylene mechanical property parameters; A polyethylene mechanical multidimensional failure comprehensive index is preset, and the remaining life of the gas polyethylene pipeline is obtained through the polyethylene mechanical decay model according to the polyethylene mechanical multidimensional failure comprehensive index and the real-time polyethylene mechanical performance parameters.

[0011] Preferably, the mathematical expression of the polyethylene mechanical decay model is: , Wherein, D(t) is the mechanical decay index of polyethylene at time t, A1 is the critical threshold of elongation at break, B1 is the critical threshold of tensile yield stress, C1 is the critical threshold of impact strength, β1 is the weight coefficient of elongation at break, β2 is the weight coefficient of tensile yield stress, β3 is the weight coefficient of impact strength, A(t) is the elongation at break decay model, B(t) is the tensile yield stress decay model, C(t) is the impact strength decay model, A0 is the initial value of elongation at break, B0 is the initial value of tensile yield stress, and C0 is the initial value of impact strength.

[0012] Preferably, obtaining the remaining life of the gas polyethylene pipeline by using the polyethylene mechanical decay model comprises: The time value t is obtained by inverting the polyethylene mechanical decay index according to the polyethylene mechanical multidimensional failure comprehensive index; The remaining life of the gas polyethylene pipeline is calculated based on the t time value and the real-time polyethylene mechanical property parameter through the current time value.

[0013] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned method for predicting the life of buried gas polyethylene pipeline based on mechanical properties is implemented.

[0014] A storage medium containing computer executable instructions, wherein the computer executable instructions are used to execute the above-mentioned mechanical property-based buried gas polyethylene pipeline life prediction method when executed by a computer processor.

[0015] The beneficial effects of the present invention are: (1) By fully considering the comprehensive effects of complex factors such as moisture, heat, oxygen and pressure, the remaining life of buried polyethylene pipelines is scientifically estimated, providing an effective evaluation method for accurately assessing the creep aging problem caused by pressure on in-service polyethylene pipelines and the resulting life loss; (2) The noise in the polyethylene ultrasonic pulse signal is effectively removed through analog-to-digital conversion sampling, lifting wavelet transform decomposition, and reconstruction error compensation, reducing the information loss in the reconstruction process during denoising, providing higher quality data for subsequent ultrasonic spectrum analysis, and thus improving the accuracy of mechanical property prediction; (3) A polyethylene pipe creep aging data set was constructed using polyethylene mechanical property parameters and polyethylene ultrasonic spectrum coefficient parameters, and then an ultrasonic non-destructive mechanical property prediction model was obtained through nonlinear modeling. This achieved accurate real-time prediction of polyethylene mechanical property parameters without damaging the polyethylene pipe. (4) A polyethylene mechanical degradation model is constructed through comprehensive degradation, taking into account the degradation of multiple mechanical performance parameters, providing a more comprehensive mechanical performance degradation assessment, allowing the critical threshold to be set according to specific application scenarios and needs, enhancing the adaptability and flexibility of the model, and introducing weight coefficients to adjust the importance of different mechanical performance parameters in the degradation model, making the model more in line with the actual degradation law. Based on real-time mechanical performance parameters, it can accurately predict the remaining life of gas polyethylene pipelines and improve the safety and reliability of polyethylene pipeline operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0017] Figure 1 The present invention is a schematic flow chart of a method for predicting the life of an underground gas polyethylene pipeline based on mechanical properties. DETAILED DESCRIPTION

[0018] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0019] See also Figure 1 , a method for predicting the life of buried gas polyethylene pipeline based on mechanical properties, including: S1: Creep-aged polyethylene specimens were obtained through hydrostatic test of gas polyethylene pipes; S2: obtaining a polyethylene ultrasonic pulse signal by ultrasonic testing the creep aged polyethylene sample, and obtaining a polyethylene ultrasonic spectrum coefficient parameter by ultrasonic signal statistical extraction based on the polyethylene ultrasonic pulse signal; S3: obtaining polyethylene mechanical property parameters through mechanical testing of the creep-aged polyethylene sample, and constructing a polyethylene pipeline creep aging data set according to the polyethylene mechanical property parameters and the polyethylene ultrasonic spectrum coefficient parameters; S4: Obtaining an ultrasonic nondestructive mechanical property prediction model through nonlinear modeling according to the polyethylene pipe creep aging data set; S5: Acquire a real-time polyethylene ultrasonic pulse signal, obtain real-time polyethylene mechanical property parameters according to the real-time polyethylene ultrasonic pulse signal through the ultrasonic non-destructive mechanical property prediction model, and obtain the remaining life of the gas polyethylene pipeline according to the real-time polyethylene mechanical property parameters through the polyethylene mechanical decay model.

[0020] In this embodiment, the creep aging polyethylene sample obtained by the hydrostatic test of the gas polyethylene pipe is specifically implemented by the following steps: The gas polyethylene pipe is a PE100 grade pipe from the same manufacturer and the same batch, with a pipe diameter of DN110×10mm and a pipe length of 650mm. The hydrostatic test is carried out by preparing creep-aged polyethylene specimens using a hydrostatic testing machine; Specifically, by setting three temperature gradients of 90°C, 60°C and 30°C, 30 observations distributed at 10 pressure levels are obtained under the three temperature gradients, and 3 observation records are obtained at each pressure level; the interval distribution of the test data in the failure time is achieved by reasonably selecting the test ring stress; The selection of the pressure level follows the following principles: at least 4 observations have a destruction time of more than 7000 hours, and at least 1 observation has a destruction time of more than 9000 hours; at any temperature, observations with a destruction time within 10 hours are discarded; at a temperature of 30°C, select an observation with a destruction time between 100-1000 hours.

[0021] The determination of the maximum test ring stress follows the following principles: at temperatures of 90°C and 60°C, the minimum internal pressure that makes the test failure time exceed 10h is the upper limit of the test internal pressure; at a temperature of 30°C, the minimum pressure that makes the failure time exceed 100h is the upper limit of the test internal pressure. The maximum test ring stress can be determined in advance through early preliminary tests.

[0022] According to the test temperature and in combination with GB / T15558.2-2023 standard, the other test ring stresses are dynamically adjusted during the hydrostatic test. Specifically, a minimum test ring stress is estimated. Generally, the higher the temperature, the smaller the difference between the maximum test ring stress and the minimum test ring stress. Then a series of ring stresses are selected between the two ring stresses, and the test is carried out under the corresponding pressure. As the test progresses, the test pressure is continuously corrected and the data is supplemented according to the test requirements. The rupture of the polyethylene pipe or the deformation of the outer diameter of the polyethylene pipe reaching 100% is regarded as an indicator of the loss of the pipe's performance. At this time, the test is stopped, so that the system obtains the creep-aged polyethylene specimen for subsequent analysis and detection.

[0023] It should be noted that the mathematical expression of the test pressure is: ,in, is the test pressure, is the ring stress, is the pipe wall thickness; The hydrostatic test is based on the time-temperature equivalence principle and accelerates the aging process of polyethylene pipes by increasing temperature and ring stress. Under the 30°C test condition, online real-time detection is adopted, that is, the ultrasonic probe is fixed at the position of the pipe sample detection, and data is automatically collected and saved locally, and the collected data is sent to the remote end within a certain period; the ultrasonic monitoring workstation works continuously and cannot be powered off, otherwise it may cause the loss of unsaved data; samples under the 90°C and 60°C test conditions are obtained by regular manual sampling and detection methods using a high-temperature ultrasonic probe. During the test, the sample is taken out under pressure and hung on a hanger. The polyethylene ultrasonic pulse signal can be collected only after the sample is stable.

[0024] In this embodiment, the polyethylene ultrasonic pulse signal is obtained by ultrasonic testing of the creep aged polyethylene sample, and the polyethylene ultrasonic spectrum coefficient parameter is obtained by ultrasonic signal statistical extraction according to the polyethylene ultrasonic pulse signal, which is specifically implemented by the following steps: S201: obtaining a polyethylene ultrasonic pulse signal by a single probe pulse reflection echo method according to the creep aged polyethylene sample; It should be noted that in the process of collecting polyethylene ultrasonic pulse signals, in order to ensure the comprehensiveness and accuracy of the data, it is necessary to collect no less than 200 groups of polyethylene ultrasonic pulse signals under various aging conditions.

[0025] S202: obtaining a polyethylene ultrasonic pulse denoised signal by performing signal denoising preprocessing on the polyethylene ultrasonic pulse signal; S202-1: obtaining a discrete polyethylene ultrasonic pulse signal sequence through sampling by an analog-to-digital converter according to the polyethylene ultrasonic pulse signal; S202-2: Decomposing the discrete polyethylene ultrasonic pulse signal sequence by lifting wavelet transform to obtain polyethylene pulse signal detail coefficients and polyethylene pulse signal approximation coefficients; S202-3: Obtaining a polyethylene ultrasonic pulse denoised signal by reconstructing an error compensation according to the polyethylene pulse signal detail coefficient and the polyethylene pulse signal approximation coefficient; Specifically, according to the polyethylene pulse signal detail coefficient and the polyethylene pulse signal approximate coefficient, noise is removed by adaptive threshold segmentation, the coefficients after threshold processing are reconstructed by discrete wavelet inverse transform to obtain a polyethylene ultrasonic pulse reconstructed signal, and according to the polyethylene ultrasonic pulse reconstructed signal, a polyethylene ultrasonic pulse denoised signal is obtained by reconstruction error compensation. The mathematical expression of the polyethylene ultrasonic pulse denoised signal is: , Among them, S(n) is the polyethylene ultrasonic pulse denoising signal, S0(n) is the polyethylene ultrasonic pulse original signal, S1(n) is the polyethylene ultrasonic pulse reconstructed signal, n is the discrete index of the polyethylene ultrasonic pulse signal, and α is the reconstruction error compensation coefficient.

[0026] S202-4: Obtaining a polyethylene ultrasonic spectrum by ultrasonic spectrum analysis according to the polyethylene ultrasonic pulse denoised signal; S202-5: Obtain ultrasonic spectrum coefficient parameters by ultrasonic spectrum statistical extraction according to the polyethylene ultrasonic spectrum, wherein the ultrasonic spectrum coefficient parameters include ultrasonic attenuation spectrum, ultrasonic phase spectrum, ultrasonic sound velocity spectrum, and ultrasonic reflection coefficient phase spectrum.

[0027] Specifically, the polyethylene ultrasonic spectrum is obtained by converting a time domain signal into a frequency domain signal through fast Fourier transform according to the polyethylene ultrasonic spectrum, and ultrasonic spectrum coefficient parameters are extracted from the polyethylene ultrasonic spectrum.

[0028] In this embodiment, the polyethylene mechanical property parameters are obtained by mechanical testing of the creep-aged polyethylene sample, and the polyethylene pipeline creep aging data set is constructed according to the polyethylene mechanical property parameters and the polyethylene ultrasonic spectrum coefficient parameters through the following steps: The mechanical testing includes obtaining polyethylene mechanical property parameters through tensile testing and impact testing, and the polyethylene mechanical property parameters include elongation at break, tensile yield stress, and impact strength; It should be noted that the elongation at break is the maximum elongation that polyethylene can withstand before breaking, the tensile yield stress is the critical point stress at which polyethylene transitions from elastic deformation to plastic deformation during stretching, and the impact strength is the ability of polyethylene to resist breaking under impact load.

[0029] Specifically, the tensile test is carried out by machining the specimen from the middle part of the aged pipe sample, and the impact test is carried out by axial sampling from the center part of the aged pipe sample. The length of the specimen is 100 mm, the width is 10 mm, and the thickness is the wall thickness of the pipe. The specimens are evenly sampled along the periphery of the pipe section, and a single-sided notch is prepared in the center with a notch depth of 2 mm. The sample failure type and impact strength should be recorded in the test.

[0030] A polyethylene pipeline creep aging data set is constructed according to the polyethylene mechanical property parameters and the polyethylene ultrasonic spectrum coefficient parameters through the corresponding relationship of each level of aging degree.

[0031] In this embodiment, the ultrasonic non-destructive mechanical property prediction model is obtained by nonlinear modeling according to the polyethylene pipe creep aging data set, specifically by the following steps: The ultrasonic non-destructive mechanical property prediction model receives the polyethylene ultrasonic spectrum coefficient parameters in the polyethylene pipe creep aging dataset through an input layer, extracts the primary features of the polyethylene ultrasonic spectrum coefficient parameters through a convolution layer with a convolution kernel size of 3×3, and reduces the feature dimension through a maximum pooling layer with a pooling window size of 2×2. After repeating the convolution and pooling operations twice, a fully connected layer is connected to flatten the features and a LSTM layer with 100 hidden units and a fully connected layer are used to extract the sequence features of the polyethylene ultrasonic spectrum coefficient parameters. Finally, a fully connected layer with three neurons is used to output the predicted value of the polyethylene mechanical property parameters.

[0032] Specifically, the ultrasonic non-destructive mechanical property prediction model uses mean square error as the loss function to measure the difference between the model predicted value and the actual value. The learning rate is initialized to 0.001 to provide an initial step size for model parameter updating. The Adam optimizer is used to optimize the learning rate, and its adaptive learning rate adjustment mechanism is used to improve training efficiency and stability. L2 regularization is introduced, and the weight decay coefficient is set to 0.01 to prevent model overfitting and enhance the generalization ability of the model.

[0033] During the model training process, the polyethylene pipe creep aging data set is divided into a polyethylene pipe creep aging training set and a polyethylene pipe creep aging validation set. Iterative training is performed through multiple epochs according to the polyethylene pipe creep aging training set. Each epoch includes forward propagation, loss calculation, back propagation and parameter update steps. After each epoch, the validation set is used to evaluate the model performance and the validation set loss is recorded. When the validation set loss does not improve within 10 consecutive epochs, it is considered that the model has reached the best performance, and the training is stopped to obtain a trained ultrasonic non-destructive mechanical property prediction model.

[0034] In this embodiment, the real-time polyethylene ultrasonic pulse signal is obtained, the real-time polyethylene mechanical property parameters are obtained through the ultrasonic non-destructive mechanical property prediction model according to the real-time polyethylene ultrasonic pulse signal, and the remaining life of the gas polyethylene pipeline is obtained through the polyethylene mechanical decay model according to the real-time polyethylene mechanical property parameters. Specifically, the following steps are implemented: S501: Preset polyethylene mechanical properties failure criterion coefficient; S502: constructing a polyethylene mechanical degradation model through comprehensive degradation according to the polyethylene mechanical property failure criterion coefficient and the polyethylene mechanical property parameter, wherein the polyethylene mechanical property parameter is the polyethylene mechanical property parameter in the polyethylene pipeline creep aging data set; The mathematical expression of the polyethylene mechanical decay model is: , Wherein, D(t) is the mechanical decay index of polyethylene at time t, A1 is the critical threshold of elongation at break, B1 is the critical threshold of tensile yield stress, C1 is the critical threshold of impact strength, β1 is the weight coefficient of elongation at break, β2 is the weight coefficient of tensile yield stress, β3 is the weight coefficient of impact strength, A(t) is the elongation at break decay model, B(t) is the tensile yield stress decay model, C(t) is the impact strength decay model, A0 is the initial value of elongation at break, B0 is the initial value of tensile yield stress, and C0 is the initial value of impact strength; The elongation at break decay model is: , Among them, k a is the elongation at break decay rate coefficient, and n is the elongation at break decay exponent.

[0035] The tensile yield stress decay model is: , Among them, k b is the tensile yield stress decay rate coefficient, and m is the tensile yield stress decay exponent.

[0036] The impact strength decay model is: , Among them, k c is the impact strength decay rate coefficient, and p is the impact strength decay exponent.

[0037] It should be noted that the unknown independent variables of the polyethylene mechanical decay model are determined by data fitting based on multiple groups of polyethylene mechanical property parameters obtained from the experiment; S503: Preset a polyethylene mechanical multidimensional failure comprehensive index, and obtain the remaining life of the gas polyethylene pipeline through the polyethylene mechanical decay model according to the polyethylene mechanical multidimensional failure comprehensive index and the real-time polyethylene mechanical performance parameter; Specifically, the polyethylene mechanical multidimensional failure comprehensive index is used as the result value of the polyethylene mechanical decay model, and the time value t is obtained by reverse calculation. The remaining life of the gas polyethylene pipeline is calculated by the time value t and the current time value of the real-time polyethylene mechanical property parameter.

[0038] The computer storage medium of the embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device.

[0039] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0040] The program code included on the computer readable medium can be transmitted with any appropriate medium, including but not limited to wireless, electric wire, optical cable, RF, etc., or any suitable combination of the above. The computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or their combinations, and the programming language includes object-oriented programming languages-such as Java, Smalltalk, C++, and also includes conventional procedural programming languages-such as "C" language or similar programming languages. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0041] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A method for predicting the life of buried gas polyethylene pipeline based on mechanical properties, characterized in that: include: Acquire a creep-aged polyethylene sample, obtain a polyethylene ultrasonic pulse signal through ultrasonic testing based on the creep-aged polyethylene sample, and obtain a polyethylene ultrasonic spectrum coefficient parameter through ultrasonic signal statistical extraction based on the polyethylene ultrasonic pulse signal; According to the creep-aged polyethylene sample, mechanical property parameters of polyethylene are obtained through mechanical testing, and a polyethylene pipeline creep-aging data set is constructed according to the polyethylene mechanical property parameters and the polyethylene ultrasonic spectrum coefficient parameters; According to the polyethylene pipe creep aging data set, an ultrasonic non-destructive mechanical property prediction model is obtained through nonlinear modeling; A real-time polyethylene ultrasonic pulse signal is obtained, and real-time polyethylene mechanical property parameters are obtained according to the real-time polyethylene ultrasonic pulse signal through the ultrasonic non-destructive mechanical property prediction model, and the remaining life of the gas polyethylene pipeline is obtained according to the real-time polyethylene mechanical property parameters through the polyethylene mechanical decay model.

2. The method for predicting the life of buried gas polyethylene pipeline based on mechanical properties according to claim 1 is characterized in that: The extraction of polyethylene ultrasonic spectrum coefficient parameters includes: Acquiring a polyethylene ultrasonic pulse signal by a single probe pulse reflection echo method according to the creep aged polyethylene sample; According to the polyethylene ultrasonic pulse signal, a discrete polyethylene ultrasonic pulse signal sequence is obtained by sampling the polyethylene ultrasonic pulse signal through an analog-to-digital converter; Decomposing the discrete polyethylene ultrasonic pulse signal sequence by lifting wavelet transform to obtain polyethylene pulse signal detail coefficients and polyethylene pulse signal approximation coefficients; Obtaining a polyethylene ultrasonic pulse denoised signal by reconstructing an error compensation according to the polyethylene pulse signal detail coefficient and the polyethylene pulse signal approximation coefficient; Obtaining a polyethylene ultrasonic spectrum by ultrasonic spectrum analysis according to the polyethylene ultrasonic pulse denoising signal; Ultrasonic spectrum coefficient parameters are obtained by statistical extraction of the ultrasonic spectrum according to the polyethylene ultrasonic spectrum.

3. The method for predicting the life of buried gas polyethylene pipeline based on mechanical properties according to claim 2 is characterized in that: The mathematical expression of the polyethylene ultrasonic pulse denoising signal is: ， Among them, S(n) is the polyethylene ultrasonic pulse denoising signal, S0(n) is the polyethylene ultrasonic pulse original signal, S1(n) is the polyethylene ultrasonic pulse reconstructed signal, n is the discrete index of the polyethylene ultrasonic pulse signal, and α is the reconstruction error compensation coefficient.

4. The method for predicting the life of buried gas polyethylene pipeline based on mechanical properties according to claim 1 is characterized in that: The ultrasonic non-destructive mechanical properties prediction model includes: Receiving the polyethylene pipe creep aging dataset via an input layer; According to the polyethylene pipeline creep aging data set, a polyethylene ultrasonic spectrum coefficient parameter sequence feature is obtained through a feature extraction layer; The predicted value of the polyethylene mechanical property parameter is output through the output layer according to the polyethylene ultrasonic spectrum coefficient parameter sequence characteristics, and the output layer is a fully connected layer with three neurons.

5. The method for predicting the life of buried gas polyethylene pipeline based on mechanical properties according to claim 1 is characterized in that: The steps for calculating the remaining life of the gas polyethylene pipeline include: Preset polyethylene mechanical properties failure criterion coefficient; Constructing a polyethylene mechanical decay model through comprehensive decay according to the polyethylene mechanical property failure criterion coefficient and polyethylene mechanical property parameters; A polyethylene mechanical multidimensional failure comprehensive index is preset, and the remaining life of the gas polyethylene pipeline is obtained through the polyethylene mechanical decay model according to the polyethylene mechanical multidimensional failure comprehensive index and the real-time polyethylene mechanical performance parameters.

6. The method for predicting the life of buried gas polyethylene pipeline based on mechanical properties according to claim 5 is characterized in that: The mathematical expression of the polyethylene mechanical decay model is: ， Wherein, D(t) is the mechanical decay index of polyethylene at time t, A1 is the critical threshold of elongation at break, B1 is the critical threshold of tensile yield stress, C1 is the critical threshold of impact strength, β1 is the weight coefficient of elongation at break, β2 is the weight coefficient of tensile yield stress, β3 is the weight coefficient of impact strength, A(t) is the elongation at break decay model, B(t) is the tensile yield stress decay model, C(t) is the impact strength decay model, A0 is the initial value of elongation at break, B0 is the initial value of tensile yield stress, and C0 is the initial value of impact strength.

7. The method for predicting the life of buried gas polyethylene pipeline based on mechanical properties according to claim 5 is characterized in that: The remaining life of the gas polyethylene pipeline obtained by the polyethylene mechanical decay model includes: The time value t is obtained by inverting the polyethylene mechanical decay index according to the polyethylene mechanical multidimensional failure comprehensive index; The remaining life of the gas polyethylene pipeline is calculated based on the t time value and the real-time polyethylene mechanical property parameter through the current time value.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for predicting the life of buried gas polyethylene pipeline based on mechanical properties as described in any one of claims 1 to 7 is implemented.

9. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions are used to execute the buried gas polyethylene pipeline life prediction method based on mechanical properties as described in any one of claims 1-7 when executed by a computer processor.

Images