CN116011183B - In-service oil and gas pipeline detection method, device, equipment and storage medium - Google Patents
In-service oil and gas pipeline detection method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN116011183B CN116011183B CN202211573822.XA CN202211573822A CN116011183B CN 116011183 B CN116011183 B CN 116011183B CN 202211573822 A CN202211573822 A CN 202211573822A CN 116011183 B CN116011183 B CN 116011183B
- Authority
- CN
- China
- Prior art keywords
- sample data
- data
- pipeline
- response signal
- stress
- 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
Classifications
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Abstract
The application provides an in-service oil gas pipeline detection method, device, equipment and storage medium, wherein the method comprises the following steps: receiving an original vibration response signal of the in-service oil and gas pipeline, and preprocessing the original vibration response signal to obtain a vibration response signal; performing time domain and frequency domain feature analysis on the vibration response signals to obtain feature data; performing feature selection on the feature data to obtain target feature data; and inputting the target characteristic data into a pre-established mapping relation model so as to identify the stress and defect type of the in-service oil and gas pipeline through the mapping relation model. The original vibration response signals of the in-service oil and gas pipelines are processed and then input into a pre-established mapping relation model, so that the stress and defect types of the in-service oil and gas pipelines are identified through the mapping relation model, the high-precision nondestructive detection of the stress of the in-service oil and gas pipelines can be realized, the method is high in applicability, and the pipeline defects can be detected simultaneously.
Description
Technical Field
The application relates to the field of oil and gas pipeline detection, in particular to an in-service oil and gas pipeline detection method, device, equipment and storage medium.
Background
The pipeline is an engineering structure, and the stress in the in-service buried oil and gas pipeline is an important index for determining the strength of the pipeline, particularly the girth weld of the pipeline. The stress of the in-service oil and gas pipeline can be measured only by adopting a nondestructive testing mode.
Currently, the prior art is applicable to non-excavation measurement methods of stress of in-service buried oil and gas pipelines, such as an inertial navigation internal detection method (Inertial Measure Unit, IMU), an internal detection method based on magnetostriction principle (Axiss), and the like, and excavation measurement methods include coercivity measurement methods, ultrasonic measurement methods, and the like.
However, the inventor finds that the existing stress nondestructive testing methods have the defects of poor precision, short application time, no powerful verification and the like in different aspects, and the methods for measuring the stress cannot simultaneously measure whether defects exist in the in-service oil and gas pipeline.
Disclosure of Invention
The application provides a method, a device, equipment and a storage medium for detecting in-service oil and gas pipelines, which are used for solving the defects that the existing stress nondestructive detection method has poor precision in different aspects, has short application time and is not yet verified forcefully, and the methods for measuring the stress can not measure whether defects exist in the in-service oil and gas pipelines at the same time.
In a first aspect, the application provides an in-service oil and gas pipeline detection method, comprising the following steps:
receiving an original vibration response signal of the in-service oil and gas pipeline, and preprocessing the original vibration response signal to obtain a vibration response signal;
performing time domain and frequency domain feature analysis on the vibration response signals to obtain feature data;
performing feature selection on the feature data to obtain target feature data;
and inputting the target characteristic data into a pre-established mapping relation model so as to identify the stress and defect type of the in-service oil and gas pipeline through the mapping relation model.
In one possible design, the process for creating the mapping relation model includes: constructing attribute information sample data, stress sample data and defect sample data of the in-service oil and gas pipeline; establishing a pipeline knocking model according to the attribute information sample data, the stress sample data and the defect sample data so as to simulate knocking vibration through the pipeline knocking model to obtain a simulated vibration response signal; processing the simulated vibration response signal to obtain response signal characteristic data; and constructing the mapping relation model by using a radial basis function neural network according to the attribute information sample data, the stress sample data, the defect sample data and the response signal characteristic data.
In one possible design, the constructing the in-service oil and gas pipeline attribute information sample data, stress sample data, and defect sample data includes: obtaining attribute information sample data of the in-service oil and gas pipeline by constructing one or more of pipeline materials, pipeline structures, pipeline sizes, excavation lengths, conveying media and conveying process parameters; the stress sample data of the in-service oil and gas pipeline are obtained by constructing stress sample data of different stress states; and obtaining the defect sample data of the in-service oil and gas pipeline by constructing defect sample data of different defect types and different defect sizes.
In one possible design, the building a pipe knocking model according to the attribute information sample data, the stress sample data and the defect sample data to simulate knocking vibration by the pipe knocking model to obtain a simulated vibration response signal includes: and establishing a pipeline knocking model according to the attribute information sample data, the stress sample data and the defect sample data so as to simulate knocking vibration and generate knocking vibration signals through the pipeline knocking model, and acquiring the knocking vibration signals to obtain simulated vibration response signals.
In one possible design, the processing the simulated vibration response signal to obtain response signal characteristic data includes: performing time domain and frequency domain feature analysis on the simulated vibration response signals to obtain feature data comprising a mean value, a standard deviation and a maximum value; and performing feature selection and normalization processing on the feature data to obtain response signal feature data.
In one possible design, the constructing a mapping relation model according to the attribute information sample data, the stress sample data, the defect sample data and the response signal characteristic data by using a radial basis function neural network includes: and taking the attribute information sample data, the stress sample data and the defect sample data as input data of the radial basis function neural network, and taking the response signal characteristic data as output data of the radial basis function neural network to construct a mapping relation model.
In a second aspect, the present application provides an in-service oil and gas pipeline detection device, comprising:
the receiving module is used for receiving the original vibration response signal of the in-service oil and gas pipeline, and preprocessing the original vibration response signal to obtain a vibration response signal;
the characteristic analysis module is used for carrying out characteristic analysis of a time domain and a frequency domain on the vibration response signal to obtain characteristic data;
the feature selection module is used for carrying out feature selection on the feature data to obtain target feature data;
the identification module is used for inputting the target characteristic data into a pre-established mapping relation model so as to identify the stress and defect type of the in-service oil and gas pipeline through the mapping relation model.
In one possible design, the in-service oil and gas pipeline inspection device further comprises: the model building module is used for building attribute information sample data, stress sample data and defect sample data of the in-service oil and gas pipeline; establishing a pipeline knocking model according to the attribute information sample data, the stress sample data and the defect sample data so as to simulate knocking vibration through the pipeline knocking model to obtain a simulated vibration response signal; processing the simulated vibration response signal to obtain response signal characteristic data; and constructing the mapping relation model by using a radial basis function neural network according to the attribute information sample data, the stress sample data, the defect sample data and the response signal characteristic data.
In a third aspect, the present application provides an in-service oil and gas pipeline inspection apparatus comprising: the device comprises a pipeline knocking hammer, a vibration sensor, a signal transmission device and a signal processing analysis server;
the pipeline knocking hammer is used for knocking the outside of the in-service oil and gas pipeline to generate an original vibration response signal;
the vibration sensor is used for collecting the original vibration response signal;
the signal transmission device is used for transmitting the original vibration signal acquired by the vibration sensor to the signal processing analysis diagnosis device;
the signal processing analysis server includes: at least one processor and memory; the memory stores computer-executable instructions; the at least one processor executes computer-executable instructions stored by the memory such that the at least one processor performs the in-service oil and gas pipeline detection method of the first aspect and any one of the possible designs of the first aspect.
In a fourth aspect, the present application provides a computer readable storage medium having stored therein computer executable instructions which, when executed by a processor, implement an in-service oil and gas pipeline detection method as in any one of the possible designs of the first aspect and the first aspect.
According to the in-service oil gas pipeline detection method, the device, the equipment and the storage medium, the original vibration response signals of the in-service oil gas pipeline are processed and then input into the pre-established mapping relation model, so that the stress and the defect type of the in-service oil gas pipeline are identified through the mapping relation model, the high-precision nondestructive detection of the stress of the in-service oil gas pipeline can be realized, the method is high in applicability, and the pipeline defects can be detected simultaneously.
Drawings
In order to more clearly illustrate the application or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the application, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a method for in-service oil and gas pipeline detection according to an embodiment of the present application;
FIG. 2 is a second flowchart of an in-service oil and gas pipeline detection method according to an embodiment of the present application;
FIG. 3 is a schematic diagram of an in-service oil and gas pipeline detection device according to an embodiment of the present application;
FIG. 4 is a schematic hardware configuration diagram of an in-service oil and gas pipeline detection device according to an embodiment of the present application;
fig. 5 is a schematic hardware structure of a signal processing analysis server according to an embodiment of the application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The pipeline is an engineering structure, and the stress in the in-service buried oil and gas pipeline is an important index for determining the strength of the pipeline, particularly the girth weld of the pipeline. The stress of the in-service pipeline can be measured only by adopting a nondestructive detection mode. The stress non-excavation measuring method suitable for the in-service buried oil and gas pipeline in the prior art comprises an inertial navigation internal detection method and an internal detection method based on the magnetostriction principle, and the excavation measuring method comprises a coercive force measuring method, an ultrasonic measuring method and the like. In the nondestructive testing method of the stress state of the pipeline, the currently mainly adopted methods include an X-ray testing method, a neutron diffraction method, a metal magnetic memory method, an ultrasonic testing method and the like. The X-ray detection method has high requirements on the surface of the component, is only suitable for detecting thin materials, and has complex equipment operation. Neutron diffraction equipment is expensive to manufacture and has no portability, and engineering field application is difficult to realize. Methods using magnetic characteristics such as metal magnetic memory methods are susceptible to the surrounding environment, and cannot obtain accurate values. During ultrasonic detection, a stress-free standard block is required to be prepared, the acoustic elasticity coefficient is calibrated, and the stress at the welding line can not be measured. Therefore, the existing methods have the defects of poor precision, poor applicability and the like in different aspects of the nondestructive testing technology of the stress, and the methods for measuring the stress cannot measure whether defects exist in the pipeline at the same time.
In view of the above problems, the present application provides an in-service oil and gas pipeline detection method, which processes an original vibration response signal of an in-service oil and gas pipeline and inputs the processed signal into a pre-established mapping relation model, so as to identify stress and defect types of the in-service oil and gas pipeline through the mapping relation model.
The technical scheme of the application is described in detail below by specific examples. The following embodiments may be combined with each other, and some embodiments may not be repeated for the same or similar concepts or processes.
FIG. 1 is a flowchart illustrating an in-service oil and gas pipeline detection method according to an embodiment of the present application, where the execution body of the embodiment may be a server. As shown in fig. 1, the method of the present embodiment may include the following steps:
s101, receiving an original vibration response signal of the in-service oil gas pipeline, and preprocessing the original vibration response signal to obtain a vibration response signal.
In this embodiment, the original vibration response signal of the in-service oil and gas pipeline is obtained by: excavating a buried in-service oil gas pipeline, knocking the exposed outer wall of the pipeline by using a pipeline knocking hammer to enable the pipeline to generate an original vibration response signal, acquiring the original vibration response signal generated by the pipeline by using original vibration response signal acquisition and reading equipment, and transmitting the obtained original vibration signal to a signal processing analysis device in a wired manner through a signal transmission device. The original vibration response signal acquisition and reading device can use a vibration sensor and the like.
Specifically, excavating the pipe section of the in-service oil and gas pipeline to be detected, visually inspecting the appearance of the pipeline, and determining the section of the pipeline to be measured according to the defect or welding seam condition. Meanwhile, in order to grasp the stress and defect conditions of different circumferential positions of the pipeline, the outer anti-corrosion heat-insulating layer of the pipeline is cleaned at the circumferential direction of 4/6/8 of the section of the pipeline to be measured according to the pipe diameter, so that local pipeline metal is exposed, and the pipeline metal can be contacted when the knocking hammer is used for knocking conveniently. Knocking the outer wall of the metal exposed area of each pipeline, adsorbing the vibration sensor on the outer wall of the pipeline by using a magnet in the adjacent metal exposed area, and collecting an original vibration response signal generated by knocking.
The pipeline knocking hammer in the embodiment can also use electric knocking equipment, such as an electric hammer, a modal force hammer and the like, the electric knocking device, the modal force hammer and the like can set knocking frequency, the pipeline is periodically knocked, and power supply equipment can be arranged in the electric knocking equipment to ensure the operation of the electric knocking equipment.
In this embodiment, the step of preprocessing the original vibration response signal is to perform operations such as low-pass filtering and noise reduction on the original vibration response signal.
S102, performing time domain and frequency domain feature analysis on the vibration response signals to obtain feature data.
In this embodiment, the time domain and the frequency domain are basic properties of the signal, and the time domain is a relationship describing the physical signal versus time, for example, a time domain waveform of a signal may express the change of the signal with time. The frequency domain is a coordinate system used to describe the frequency characteristics of a signal, and the frequency domain plot shows the amount of signal in each given frequency band over a range of frequencies. Extracting the characteristic data of the time domain and the frequency domain of the original vibration response signal, namely performing characteristic analysis of the time domain and the frequency domain on the vibration response signal, wherein the analysis method can adopt a Fourier transform, correlation, convolution or power spectrum estimation method for analysis.
And S103, performing feature selection on the feature data to obtain target feature data.
In this embodiment, the method for selecting features of the feature data may select a packing method (Wrapper) and an embedding method (Embedded), or other feature selection methods in the filtering method, for example, a variance selection method, a chi-square test method, etc. to select feature data, where the selected target feature data can clearly and intuitively express features corresponding to stress and defects of the in-service oil and gas pipeline.
S104, inputting the target characteristic data into a pre-established mapping relation model so as to identify the stress and defect type of the in-service oil and gas pipeline through the mapping relation model.
In this embodiment, the pre-established mapping relation model is a radial basis function neural network (Radial Basis Function Neural Network, RBF neural network) model, which is a model established through the radial basis function neural network. The mapping relation model can output the identification result after the identification of the stress and defect type of the in-service oil and gas pipeline is realized.
In this embodiment, besides the identification of the stress and defect type of the in-service oil and gas pipeline by adopting the RBF neural network model, the identification of the stress and defect type can be performed by replacing the RBF neural network model by using models established by typical algorithms such as PNN (probabilistic) neural network, GRNN (generalized regression) neural network, extreme learning machine, gradient lifting tree, convolutional neural network and the like.
In summary, according to the in-service oil and gas pipeline detection method provided by the embodiment, the original vibration response signals of the in-service oil and gas pipeline are processed and then input into the pre-established mapping relation model, so that the stress and defect types of the in-service oil and gas pipeline are identified through the mapping relation model, high-precision nondestructive detection of the stress of the in-service oil and gas pipeline can be realized, the method is high in applicability, and pipeline defects can be detected simultaneously.
FIG. 2 is a second flowchart of an in-service oil and gas pipeline detection method according to an embodiment of the present application. On the basis of the embodiment of fig. 1, fig. 2 shows a process of establishing a mapping relationship model, and as shown in fig. 2, the method of this embodiment may include the following steps:
s201, constructing attribute information sample data, stress sample data and defect sample data of an in-service oil and gas pipeline.
In this embodiment, the attribute information sample data of the in-service oil and gas pipeline is obtained by constructing one or more of pipeline materials, pipeline structures, pipeline dimensions, excavation lengths, conveying media and conveying process parameters. And obtaining stress sample data of the in-service oil and gas pipeline by constructing stress sample data of different stress states. And obtaining the defect sample data of the in-service oil and gas pipeline by constructing the defect sample data of different defect types and different defect sizes.
Specifically, pipeline materials, pipeline structures, pipeline dimensions, excavation length, conveying media and conveying technological parameters can be set according to actual working conditions of in-service oil and gas pipelines, and the pipeline structures comprise straight pipes, elbows or tees and the like. The stress sample data of different stress states comprise stress states possibly existing in the in-service oil gas pipeline in the actual working condition, and the defect sample data of different defect types and different defect sizes comprise defect types and defect sizes possibly existing in the in-service oil gas pipeline in the actual working condition.
S202, a pipeline knocking model is established according to the attribute information sample data, the stress sample data and the defect sample data, so that knocking vibration is simulated through the pipeline knocking model to obtain a simulated vibration response signal.
In this embodiment, a pipe knocking model is built according to the attribute information sample data, the stress sample data and the defect sample data, so as to simulate knocking vibration and generate knocking vibration signals through the pipe knocking model, and the knocking vibration signals are collected to obtain simulated vibration response signals.
Specifically, in this embodiment, nonlinear finite element simulation software is used to perform modeling and knock vibration simulation. And establishing a pipeline knocking model according to the attribute information sample data, the stress sample data and the defect sample data by adopting nonlinear finite element simulation software, knocking the pipeline model in a force excitation mode, and simulating knocking vibration in a mode of applying a vertical downward transient force on the pipeline model. Different following parameters are set, different stress and defect working conditions of the in-service oil and gas pipeline are simulated, and the method comprises the following steps: different pipeline attributes, such as one or more of materials, structures, sizes, excavation lengths, conveying media and conveying process parameters, are set for the established pipeline knocking model, related boundary conditions are set for simulating different stress states, and the pipeline knocking model is meshed according to certain sizes for simulating defects of different types and sizes. And acquiring the knocking vibration signals to obtain simulation vibration response signals, wherein the simulation vibration response signals are used for simulating different stress and defect working conditions of the in-service oil and gas pipeline.
S203, processing the simulated vibration response signal to obtain response signal characteristic data.
In this embodiment, feature analysis of the time domain and the frequency domain is performed on the simulated vibration response signal, so as to obtain feature data including a mean value, a standard deviation and a maximum value. And performing feature selection and normalization processing on the feature data to obtain response signal feature data.
Specifically, the analysis method for performing the time-domain and frequency-domain feature analysis on the simulated vibration response signal in this embodiment is the same as the analysis method in step S102, and will not be described here again. The method for selecting the characteristics and normalizing the characteristic data is a correlation coefficient method, the correlation coefficient method is used for calculating the correlation coefficient of each characteristic to the target value, and the more relevant characteristic is selected through the correlation coefficient, and the process can be realized through a Python program.
S204, constructing a mapping relation model by using a radial basis function neural network according to the attribute information sample data, the stress sample data, the defect sample data and the response signal characteristic data.
In this embodiment, attribute information sample data, stress sample data and defect sample data are used as input data of a radial basis function neural network, and response signal characteristic data are used as output data of the radial basis function neural network to construct a mapping relation model. The mapping relation model is used for identifying the stress and defect type of the in-service oil and gas pipeline and outputting an identification result.
The radial basis function neural network is a three-layer neural network and comprises an input layer, a hidden layer and an output layer. The transformation from the input space to the hidden space is nonlinear, while the transformation from the hidden space to the output layer space is linear. And taking the attribute information sample data, the stress sample data and the defect sample data as input data of the radial basis function neural network, responding to the signal characteristic data as output data of the radial basis function neural network, selecting a basis function center, determining a connection weight from an implicit layer to an output layer to establish a mapping relation model, and carrying out model verification based on the sample data and the characteristic data after the establishment of the mapping relation model is completed.
In summary, according to the in-service oil and gas pipeline detection method provided by the embodiment, attribute information, stress and defect sample data of the in-service oil and gas pipeline are constructed, a pipeline knocking model is built to obtain response signal characteristic data, a mapping relation model is constructed by using a radial basis function neural network according to the data, a perfect stress and defect classification model of the pipeline can be obtained, and accurate identification of the pipeline stress and defect types is further facilitated.
FIG. 3 is a schematic structural diagram of an in-service oil and gas pipeline detection device according to an embodiment of the present application, as shown in FIG. 3, where the in-service oil and gas pipeline detection device according to the present embodiment is configured to implement operations corresponding to a server in any of the above method embodiments, and the in-service oil and gas pipeline detection device according to the present embodiment includes: a receiving module 301, a feature analysis module 302, a feature selection module 303 and an identification module 304.
The receiving module 301 is configured to receive an original vibration response signal of an in-service oil and gas pipeline, and perform preprocessing on the original vibration response signal to obtain a vibration response signal.
The feature analysis module 302 is configured to perform feature analysis of the time domain and the frequency domain on the vibration response signal to obtain feature data.
The feature selection module 303 is configured to perform feature selection on the feature data to obtain target feature data.
The identifying module 304 is configured to input the target feature data into a pre-established mapping relationship model, so as to identify the stress and defect type of the in-service oil and gas pipeline through the mapping relationship model.
In one possible implementation, the in-service oil and gas pipeline inspection device further includes: the model building module 305 is configured to build attribute information sample data, stress sample data and defect sample data of the in-service oil and gas pipeline; establishing a pipeline knocking model according to the attribute information sample data, the stress sample data and the defect sample data so as to simulate knocking vibration through the pipeline knocking model to obtain a simulated vibration response signal; processing the simulated vibration response signal to obtain response signal characteristic data; and constructing a mapping relation model by using a radial basis function neural network according to the attribute information sample data, the stress sample data, the defect sample data and the response signal characteristic data.
In one possible implementation manner, the model building module 305 is specifically configured to obtain attribute information sample data of the in-service oil and gas pipeline by building one or more of pipeline materials, pipeline structures, pipeline dimensions, excavation lengths, conveying media, and conveying process parameters; the stress sample data of the in-service oil and gas pipeline are obtained by constructing stress sample data of different stress states; and obtaining the defect sample data of the in-service oil and gas pipeline by constructing the defect sample data of different defect types and different defect sizes.
In one possible implementation manner, the model building module 305 is further specifically configured to build a pipeline knocking model according to the attribute information sample data, the stress sample data and the defect sample data, so as to simulate knocking vibration and generate a knocking vibration signal through the pipeline knocking model, and collect the knocking vibration signal to obtain a simulated vibration response signal.
In one possible implementation manner, the model building module 305 is further specifically configured to perform a time domain and frequency domain feature analysis on the simulated vibration response signal to obtain feature data including a mean value, a standard deviation and a maximum value; and performing feature selection and normalization processing on the feature data to obtain response signal feature data.
In one possible implementation, the model building module 305 is further specifically configured to use the attribute information sample data, the stress sample data, and the defect sample data as input data of the radial basis function neural network, and respond to the signal feature data as output data of the radial basis function neural network, so as to build a mapping relationship model.
The in-service oil gas pipeline detection device provided by the embodiment of the application can execute the method embodiment, and the specific implementation principle and technical effects of the in-service oil gas pipeline detection device can be seen from the method embodiment, and the detailed description of the embodiment is omitted.
FIG. 4 is a schematic hardware structure of an in-service oil and gas pipeline detection device according to an embodiment of the present application. As shown in fig. 4, the in-service oil and gas pipeline detection apparatus is configured to implement an operation corresponding to the in-service oil and gas pipeline detection apparatus in any of the above method embodiments, where the in-service oil and gas pipeline detection apparatus of this embodiment may include: a pipe striking hammer 401, a vibration sensor 402, a signal transmission device 403, and a signal processing analysis server 404.
Pipeline striking hammer 401 is used to strike the exterior of an in-service oil and gas pipeline to generate a raw vibration response signal.
A vibration sensor 402 for acquiring a raw vibration response signal.
And the signal transmission device 403 is used for transmitting the original vibration signal acquired by the vibration sensor to the signal processing analysis and diagnosis device.
Signal processing analysis server 404 is configured to identify stress and defect types of the in-service oil and gas pipeline based on the original vibration signal.
Specifically, the signal processing analysis server 404 may include: the device comprises an original vibration response signal storage module, an original vibration response signal preprocessing, feature extraction and feature selection module, a mapping relation model construction module, a stress and defect identification module and a result output module. The original vibration response signal storage module is used for storing and backing up the received original vibration response signals. The original vibration response signal preprocessing, feature extraction and feature selection module is used for preprocessing the original vibration response signal such as low-pass filtering noise reduction, extracting the features of the time domain and the frequency domain of the signal, and selecting the features to obtain target feature data. The mapping relation model building module is used for building attribute information sample data, stress sample data and defect sample data of the in-service oil and gas pipeline, building a pipeline knocking model according to the sample data, and simulating knocking vibration through the pipeline knocking model to obtain a simulated vibration response signal; processing the simulated vibration response signal to obtain response signal characteristic data; and constructing a mapping relation model by using a radial basis function neural network according to the attribute information sample data, the stress sample data, the defect sample data and the response signal characteristic data. The stress and defect identification module is used for inputting the target characteristic data into the mapping relation model and identifying the stress and defect type of the in-service oil and gas pipeline. The result output module is used for outputting the identification result.
Fig. 5 is a schematic hardware structure of the signal processing analysis server 404 according to an embodiment of the application. As shown in fig. 5, the signal processing analysis server 404 includes: a memory 4041 and at least one processor 4042. Memory 4041 for storing computer-executable instructions. The Memory 4041 may include a high-speed random access Memory (Random Access Memory, RAM), and may further include a Non-Volatile Memory (NVM), such as at least one magnetic disk Memory, and may also be a U-disk, a removable hard disk, a read-only Memory, a magnetic disk, or an optical disk.
At least one processor 4042 for executing computer-executable instructions stored in memory to implement the in-service oil and gas pipeline detection method of the above embodiments. Reference may be made in particular to the relevant description of the embodiments of the method described above. The processor 4042 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present application may be embodied directly in a hardware processor for execution, or in a combination of hardware and software modules in a processor for execution.
Alternatively, the memory 4041 may be separate or integrated with the processor 4042.
When the memory 4041 is a separate device from the processor 4042, the signal processing analysis server 404 may also include a bus 4043. The bus 4043 is used to connect the memory 4041 and the processor 4042. The bus 4043 may be an industry standard architecture (Industry Standard Architecture, ISA) bus, an external device interconnect (Peripheral Component Interconnect, PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, among others. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, the buses in the drawings of the present application are not limited to only one bus or to one type of bus.
The communication interface 4044 may be coupled to the processor 4042 via a bus 4043. The processor 4042 may control the communication interface 4044 to perform the functions of receiving and transmitting signals.
The in-service oil gas pipeline detection device provided in this embodiment may be used to execute the above-mentioned in-service oil gas pipeline stress and defect detection method, and its implementation manner and technical effect are similar, and this embodiment is not repeated here.
The application also provides a computer readable storage medium, wherein the computer readable storage medium stores computer execution instructions for implementing the methods provided by the various embodiments.
The computer readable storage medium may be a computer storage medium or a communication medium. Communication media includes any medium that facilitates transfer of a computer program from one place to another. Computer storage media can be any available media that can be accessed by a general purpose or special purpose computer. For example, a computer-readable storage medium is coupled to the processor such that the processor can read information from, and write information to, the computer-readable storage medium. In the alternative, the computer-readable storage medium may be integral to the processor. The processor and the computer readable storage medium may reside in an application specific integrated circuit (Application Specific Integrated Circuits, ASIC). In addition, the ASIC may reside in a user device. The processor and the computer-readable storage medium may also reside as discrete components in a communication device.
In particular, the computer readable storage medium may be implemented by any type or combination of volatile or non-volatile Memory devices, such as Static Random-Access Memory (SRAM), electrically erasable programmable Read-Only Memory (EEPROM), erasable programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM), programmable Read-Only Memory (Programmable Read-Only Memory, PROM), read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic or optical disk. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.
The present application also provides a computer program product comprising a computer program/instructions stored in a computer readable storage medium. At least one processor of the device may read the computer program/instructions from a computer-readable storage medium, execution of the computer program/instructions by at least one processor causing the device to perform the methods provided by the various embodiments described above.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of modules is merely a logical function division, and there may be additional divisions of actual implementation, e.g., multiple modules may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or modules, which may be in electrical, mechanical, or other forms.
Wherein the individual modules may be physically separated, e.g. mounted in different locations of one device, or mounted on different devices, or distributed over a plurality of network elements, or distributed over a plurality of processors. The modules may also be integrated together, e.g. mounted in the same device, or integrated in a set of codes. The modules may exist in hardware, or may also exist in software, or may also be implemented in software plus hardware. The application can select part or all of the modules according to actual needs to realize the purpose of the scheme of the embodiment.
When the individual modules are implemented as software functional modules, the integrated modules may be stored in a computer readable storage medium. The software functional modules described above are stored in a storage medium and include instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or processor to perform some of the steps of the methods of the various embodiments of the application.
It should be understood that, although the steps in the flowcharts in the above embodiments are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the figures may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily occurring in sequence, but may be performed alternately or alternately with other steps or at least a portion of the other steps or stages.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same. Although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments may be modified or some or all of the technical features may be replaced with equivalents. Such modifications and substitutions do not depart from the spirit of the application.
Claims (4)
1. An in-service oil and gas pipeline detection method is characterized by comprising the following steps:
receiving an original vibration response signal of the in-service oil and gas pipeline, and preprocessing the original vibration response signal to obtain a vibration response signal;
performing time domain and frequency domain feature analysis on the vibration response signals to obtain feature data;
performing feature selection on the feature data to obtain target feature data;
inputting the target characteristic data into a pre-established mapping relation model so as to identify the stress and defect type of the in-service oil and gas pipeline through the mapping relation model;
the process for establishing the mapping relation model comprises the following steps:
constructing attribute information sample data, stress sample data and defect sample data of the in-service oil and gas pipeline;
establishing a pipeline knocking model according to the attribute information sample data, the stress sample data and the defect sample data so as to simulate knocking vibration through the pipeline knocking model to obtain a simulated vibration response signal;
processing the simulated vibration response signal to obtain response signal characteristic data;
constructing the mapping relation model by using a radial basis function neural network according to the attribute information sample data, the stress sample data, the defect sample data and the response signal characteristic data;
the construction of the attribute information sample data, the stress sample data and the defect sample data of the in-service oil and gas pipeline comprises the following steps:
obtaining attribute information sample data of the in-service oil and gas pipeline by constructing one or more of pipeline materials, pipeline structures, pipeline sizes, excavation lengths, conveying media and conveying process parameters;
the stress sample data of the in-service oil and gas pipeline are obtained by constructing stress sample data of different stress states;
obtaining defect sample data of the in-service oil and gas pipeline by constructing defect sample data of different defect types and different defect sizes;
the processing of the simulated vibration response signal to obtain response signal characteristic data comprises the following steps:
performing time domain and frequency domain feature analysis on the simulated vibration response signals to obtain feature data comprising a mean value, a standard deviation and a maximum value;
performing feature selection and normalization processing on the feature data to obtain response signal feature data;
the step of establishing a pipeline knocking model according to the attribute information sample data, the stress sample data and the defect sample data so as to simulate knocking vibration through the pipeline knocking model to obtain a simulated vibration response signal, comprises the following steps:
establishing a pipeline knocking model according to the attribute information sample data, the stress sample data and the defect sample data so as to simulate knocking vibration and generate knocking vibration signals through the pipeline knocking model, and acquiring the knocking vibration signals to obtain simulated vibration response signals;
the constructing a mapping relation model by using a radial basis function neural network according to the attribute information sample data, the stress sample data, the defect sample data and the response signal characteristic data comprises the following steps:
and taking the attribute information sample data, the stress sample data and the defect sample data as input data of the radial basis function neural network, and taking the response signal characteristic data as output data of the radial basis function neural network to construct a mapping relation model.
2. An in-service oil and gas pipeline detection device, comprising:
the receiving module is used for receiving the original vibration response signal of the in-service oil and gas pipeline, and preprocessing the original vibration response signal to obtain a vibration response signal;
the characteristic analysis module is used for carrying out characteristic analysis of a time domain and a frequency domain on the vibration response signal to obtain characteristic data;
the feature selection module is used for carrying out feature selection on the feature data to obtain target feature data;
the identification module is used for inputting the target characteristic data into a pre-established mapping relation model so as to identify the stress and defect type of the in-service oil and gas pipeline through the mapping relation model;
the model building module is used for obtaining the attribute information sample data of the in-service oil and gas pipeline by building one or more of pipeline materials, pipeline structures, pipeline sizes, excavation lengths, conveying media and conveying process parameters; the stress sample data of the in-service oil and gas pipeline are obtained by constructing stress sample data of different stress states; obtaining defect sample data of the in-service oil and gas pipeline by constructing defect sample data of different defect types and different defect sizes; establishing a pipeline knocking model according to the attribute information sample data, the stress sample data and the defect sample data so as to simulate knocking vibration and generate knocking vibration signals through the pipeline knocking model, and acquiring the knocking vibration signals to obtain simulated vibration response signals; performing time domain and frequency domain feature analysis on the simulated vibration response signals to obtain feature data comprising a mean value, a standard deviation and a maximum value; performing feature selection and normalization processing on the feature data to obtain response signal feature data; and taking the attribute information sample data, the stress sample data and the defect sample data as input data of a radial basis function neural network, and taking the response signal characteristic data as output data of the radial basis function neural network to construct a mapping relation model.
3. An in-service oil and gas pipeline detection device, comprising: the device comprises a pipeline knocking hammer, a vibration sensor, a signal transmission device and a signal processing analysis server;
the pipeline knocking hammer is used for knocking the outside of the in-service oil and gas pipeline to generate an original vibration response signal;
the vibration sensor is used for collecting the original vibration response signal;
the signal transmission device is used for transmitting the original vibration response signal acquired by the vibration sensor to the signal processing analysis diagnosis device;
the signal processing analysis server includes: at least one processor and memory; the memory stores computer-executable instructions; the at least one processor executing computer-executable instructions stored in the memory, causing the at least one processor to perform the in-service oil and gas pipeline detection method of claim 1.
4. A computer readable storage medium having stored therein computer executable instructions which when executed by a processor implement the in-service oil and gas pipeline detection method of claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211573822.XA CN116011183B (en) | 2022-12-08 | 2022-12-08 | In-service oil and gas pipeline detection method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211573822.XA CN116011183B (en) | 2022-12-08 | 2022-12-08 | In-service oil and gas pipeline detection method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116011183A CN116011183A (en) | 2023-04-25 |
| CN116011183B true CN116011183B (en) | 2023-09-15 |
Family
ID=86018408
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211573822.XA Active CN116011183B (en) | 2022-12-08 | 2022-12-08 | In-service oil and gas pipeline detection method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116011183B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107590516A (en) * | 2017-09-16 | 2018-01-16 | 电子科技大学 | Gas pipeline leak detection recognition methods based on Fibre Optical Sensor data mining |
| CN109800627A (en) * | 2018-12-03 | 2019-05-24 | 第四范式（北京）技术有限公司 | The method for detecting abnormality and device of petroleum pipeline signal, equipment and readable medium |
| CN111288303A (en) * | 2020-03-23 | 2020-06-16 | 上海市特种设备监督检验技术研究院 | Pipeline leakage detector, detection system and detection method |
| WO2020133639A1 (en) * | 2018-12-29 | 2020-07-02 | 东北大学 | Intelligent analysis system for magnetic flux leakage detection data in pipeline |
| CN113343402A (en) * | 2021-07-07 | 2021-09-03 | 北京航空航天大学 | Pipeline corrosion grade evaluation method based on multilayer convolution sparse coding |
| CN113607271A (en) * | 2021-07-15 | 2021-11-05 | 国网电力科学研究院武汉南瑞有限责任公司 | GIL defect online monitoring system and method based on vibration signals |
| CN113792585A (en) * | 2021-08-03 | 2021-12-14 | 重庆兆光科技股份有限公司 | Pipeline vibration signal monitoring method and system, electronic equipment and medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100131210A1 (en) * | 2008-11-24 | 2010-05-27 | Fingerhut Martin | Method and system for non-destructive inspection of a colony of stress corrosion cracks |
| WO2014050619A1 (en) * | 2012-09-28 | 2014-04-03 | 日本電気株式会社 | Defect analysis device, defect analysis method, and program |
-
2022
- 2022-12-08 CN CN202211573822.XA patent/CN116011183B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107590516A (en) * | 2017-09-16 | 2018-01-16 | 电子科技大学 | Gas pipeline leak detection recognition methods based on Fibre Optical Sensor data mining |
| CN109800627A (en) * | 2018-12-03 | 2019-05-24 | 第四范式（北京）技术有限公司 | The method for detecting abnormality and device of petroleum pipeline signal, equipment and readable medium |
| WO2020133639A1 (en) * | 2018-12-29 | 2020-07-02 | 东北大学 | Intelligent analysis system for magnetic flux leakage detection data in pipeline |
| CN111288303A (en) * | 2020-03-23 | 2020-06-16 | 上海市特种设备监督检验技术研究院 | Pipeline leakage detector, detection system and detection method |
| CN113343402A (en) * | 2021-07-07 | 2021-09-03 | 北京航空航天大学 | Pipeline corrosion grade evaluation method based on multilayer convolution sparse coding |
| CN113607271A (en) * | 2021-07-15 | 2021-11-05 | 国网电力科学研究院武汉南瑞有限责任公司 | GIL defect online monitoring system and method based on vibration signals |
| CN113792585A (en) * | 2021-08-03 | 2021-12-14 | 重庆兆光科技股份有限公司 | Pipeline vibration signal monitoring method and system, electronic equipment and medium |
Non-Patent Citations (6)
| Title |
|---|
| A Novel Feature Identification Method of Pipeline In-Line Inspected Bending Strain Based on Optimized Deep Belief Network Model;Shucong Liu等;energies;1-19 * |
| 基于IMU 数据的冻土区管道融沉风险段识别方法;方威伦等;油气储运;288-294 * |
| 基于VMD-BP神经网络模型的天然气管道工况检测研究;梁洪卫;张旭;邹岱峰;;化工自动化及仪表(第07期);633-636 * |
| 基于振动测量的在役管道实时应力求取方法;胡本峰;周美凤;李益民;王云香;;农业装备与车辆工程(第03期);47-48 * |
| 基于神经网络的超声导波管道缺陷识别;赵彩萍;王维斌;何存富;吴斌;;传感器与微系统(第11期);19-24 * |
| 油气管道缺陷信号的MR-EMD降噪与特征提取方法研究;王蕊;中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑(第2期);B019-952 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116011183A (en) | 2023-04-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101509604B (en) | Method and device for detecting and assessing deposit in metal pipe | |
| JP7468724B2 (en) | Piping diagnosis device, piping diagnosis method, and program | |
| CN103049608B (en) | Based on load identification system and the method for binding side strain extreme coordinates | |
| CN101122583A (en) | Sheared frame structure damage detection method | |
| TW201640080A (en) | Collection of field measurement data using a pre-defined workflow | |
| CN113124328A (en) | Natural gas pipeline leakage detection method and system | |
| EP3594653B1 (en) | Diagnosis cost output device, diagnosis cost output method, and diagnosis cost output | |
| JP6973377B2 (en) | Analyst, analysis method, and program | |
| Yang et al. | Modal strain energy-based model updating method for damage identification on beam-like structures | |
| EP3605437A1 (en) | Piping diagnostic device, asset management device, piping diagnostic method, and computer-readable recording medium | |
| CN116011183B (en) | In-service oil and gas pipeline detection method, device, equipment and storage medium | |
| CN114676730A (en) | Bent deformed pipe section identification method and device, electronic equipment and storage medium | |
| Allport et al. | Turbocharger blade vibration: Measurement and validation through laser tip-timing | |
| CN109059813B (en) | Method for detecting corrosion strength of steel structure of hoisting machinery | |
| CN116227045B (en) | Local stress strain field construction method and system for structural test piece | |
| CN110411721A (en) | A kind of marine riser damage positioning method and system | |
| CN105004795B (en) | False defect signal is identified and is utilized it to improve the method for pipeline Non-Destructive Testing precision | |
| Soto-Cajiga et al. | FPGA-based architecture for real-time data reduction of ultrasound signals | |
| US10487643B2 (en) | Two-dimensional imaging with multi-stage processing | |
| CN111948286A (en) | Stress detection method, device and equipment based on ultrasonic waves and deep learning | |
| GB2482973A (en) | Evaluating the condition of a collection of similar elongated hollow objects | |
| CN111912897A (en) | Method, device and equipment for acquiring pipeline defect information and storage medium | |
| Hynninen et al. | IC-engine acoustic source characterization in-situ with capsule tube method | |
| CN114964617B (en) | Calibration method for comprehensive stress detection equipment of long oil and gas pipeline | |
| CN116201526B (en) | Micro annular gap detection method, micro annular gap detection device, computing equipment and storage medium |
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 |