CN114638166A - Method, system, equipment and medium for identifying and predicting fatigue damage of process pipeline - Google Patents
Method, system, equipment and medium for identifying and predicting fatigue damage of process pipeline Download PDFInfo
- Publication number
- CN114638166A CN114638166A CN202210288472.6A CN202210288472A CN114638166A CN 114638166 A CN114638166 A CN 114638166A CN 202210288472 A CN202210288472 A CN 202210288472A CN 114638166 A CN114638166 A CN 114638166A
- Authority
- CN
- China
- Prior art keywords
- damage
- process pipeline
- key process
- pipeline
- signal
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/04—Ageing analysis or optimisation against ageing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
The invention relates to a method, a system, equipment and a medium for identifying and predicting fatigue damage of a process pipeline, wherein the method comprises the following steps: calculating failure possibility coefficients of all process pipelines of the offshore oil platform, and determining key process pipelines for multi-mode signal detection; acquiring multimode detection data of a key process pipeline, and performing damage identification based on the acquired multimode detection data to obtain a damage identification result of the key process pipeline; and based on the damage identification result, predicting the fatigue life of the key process pipeline according to the stress-strain measurement data to obtain a fatigue life prediction result of the key process pipeline. The method combines the process flow parameters, the noise level and the vibration parameters to classify and identify the key process pipelines of the ocean platform and carry out corresponding fatigue analysis, and can be widely applied to the technical fields of ocean oil safety assessment, prediction analysis and safety production.
Description
Technical Field
The invention relates to the technical field of marine oil safety assessment, prediction analysis and safety production, in particular to a method, a system, equipment and a medium for identifying and predicting fatigue damage of a process pipeline based on multimode fusion.
Background
The offshore oil platform process treatment media are all inflammable and explosive hydrocarbon substances, certain pressure or even high pressure exists in the process, and once leakage occurs, a large amount of hydrocarbon substances are leaked, so that accident risks such as fire and explosion are caused. According to incomplete statistics, oil gas leakage accounts for more than 1/3 of marine oil accident statistics and is a main reason for causing major accident risks in marine oil development.
The design life of the offshore oil platform is generally more than 20 years, the offshore oil platform reaching the design life usually has the condition of over-service, and the detection and the evaluation of the process pipeline are not involved in the life extension evaluation or the regular special inspection. The strength, structure and the like of the key process pipeline can be weakened or damaged under the long-term oil gas corrosion, vibration effect and time effect, and hidden troubles are buried for the failure and leakage of the key process pipeline.
However, it is difficult to achieve full coverage of process pipeline damage by non-destructive inspection techniques, mainly due to the complex piping arrangement, variable positions, and inability to perform predictive analysis in combination with impact loads. The problem that the accuracy cannot be guaranteed and the data source signal is single exists in the sensing signal identification of the single factor.
Disclosure of Invention
In view of the above problems, the present invention provides a method, a system, a device and a medium for identifying and predicting fatigue damage of a process pipeline based on multimode fusion, which combines various sensing signals to perform fusion analysis, so as to effectively identify and predict fatigue damage of a key process pipeline of a long-term service offshore oil platform, so as to obtain the safety state of the key process pipeline, and facilitate corresponding control and intervention in advance, so as to prevent sudden failure of the process pipeline and further fire explosion accidents.
In order to achieve the purpose, the invention adopts the following technical scheme:
in a first aspect, the invention provides a method for identifying and predicting fatigue damage of a process pipeline, which comprises the following steps:
calculating failure possibility coefficients of all process pipelines of the offshore oil platform, and determining key process pipelines for multi-mode signal detection;
acquiring multimode detection data of a key process pipeline, and performing damage identification based on the acquired multimode detection data to obtain a damage identification result of the key process pipeline;
and based on the damage identification result, predicting the fatigue life of the key process pipeline according to the stress-strain measurement data to obtain a fatigue life prediction result of the key process pipeline.
Further, the method for calculating the failure probability coefficient of each process pipeline of the offshore oil platform and determining the key process pipeline for multimode signal detection comprises the following steps:
respectively carrying out fluid-to-vibration evaluation, fluid pulsation evaluation and high-frequency acoustic vibration evaluation on the marine oil platform process pipelines to obtain failure probability coefficients of the process pipelines;
and determining weak positions of the marine oil platform process pipelines based on the obtained failure possibility coefficients of the process pipelines as key process pipelines for multi-mode signal detection.
Further, the method for obtaining the multimode detection data of the key process pipeline and identifying the damage based on the obtained multimode detection data to obtain the damage identification result of the key process pipeline comprises the following steps:
performing vibration measurement and acoustic emission measurement on the key process pipeline to obtain a vibration signal and an acoustic emission signal of the key process pipeline;
and preprocessing the vibration signal and the acoustic emission signal of the key process pipeline to obtain an input vector, and inputting the input vector into a pre-constructed multimode fusion damage identification model to obtain a multimode fusion damage identification result.
Further, the construction method of the multimode fusion damage identification model comprises the following steps:
preprocessing the vibration signal, and inputting the vibration signal into a BP neural network intelligent model for damage identification to obtain a damage identification result based on the vibration signal;
preprocessing the acoustic emission signals, inputting the acoustic emission signals into a PNN neural network model for damage identification, and obtaining a damage identification result based on the acoustic emission signals;
and training a multi-mode fusion damage identification model, wherein the model takes a fusion vector of the vibration signal and the acoustic emission signal as input, and takes a damage identification result based on the vibration signal and a fusion vector of the damage identification result based on the acoustic emission signal as output.
Further, the method for preprocessing the vibration signal and inputting the vibration signal into a BP neural network intelligent model for damage identification to obtain a damage identification result based on the vibration signal comprises the following steps:
acquiring a vibration signal of a key process pipeline;
preprocessing the acquired vibration signal of the key process pipeline based on a modal theory to obtain a pipeline vibration modal parameter;
and inputting the pipeline vibration modal parameters into a BP neural network model for carrying out damage positioning to obtain the damage condition and position.
Further, the method for preprocessing the acoustic emission signal and inputting the acoustic emission signal into the PNN neural network model for damage identification to obtain the damage identification result based on the acoustic emission signal comprises the following steps:
extracting the characteristics of the obtained acoustic emission signals based on wavelet transformation and EMD decomposition to obtain characteristic vectors;
comparing the extracted characteristic vector with the pattern sample by combining a PNN neural network to obtain a network output classification result;
and obtaining a signal time difference based on the acoustic emission signal, judging a network output classification result by the signal time difference, and determining noise or crack damage during damage identification.
Further, the method for predicting the fatigue life of the key process pipeline according to the stress-strain measurement data based on the damage identification result to obtain the fatigue life prediction result of the key process pipeline comprises the following steps:
acquiring the stress level of the stress concentration part of the key process pipeline through a stress-strain measuring device;
and preprocessing the obtained stress level, compiling a stress spectrum by adopting a rain flow counting method, and evaluating the fatigue life of the key process pipeline by combining a linear damage accumulation theory.
In a second aspect, the present invention provides a system for identifying and predicting fatigue damage of a process pipeline, comprising:
the primary selection position determining module is used for calculating the failure possibility coefficient of the key process pipeline and determining the key process pipeline detected by the multimode signal;
the multimode fusion identification module is used for acquiring multimode detection data of the key process pipeline and identifying damage based on the acquired multimode detection data to obtain a damage identification result of the key process pipeline;
and the fatigue prediction module is used for predicting the fatigue life of the key process pipeline according to the stress-strain measurement data to obtain a fatigue life prediction result of the key process pipeline.
In a third aspect, the present invention provides a processing apparatus comprising at least a processor and a memory, the memory having stored thereon a computer program that, when executed by the processor, performs the steps of implementing the method for identifying and predicting fatigue damage to a process pipeline.
In a fourth aspect, the present invention provides a computer storage medium having computer readable instructions stored thereon which are executable by a processor to perform the steps of the method for identifying and predicting fatigue damage in a process pipeline.
Due to the adoption of the technical scheme, the invention has the following advantages: the invention combines a multimode fusion mode to process and predict detection signals so as to analyze the damage and cracks of the key process pipeline and position the damage and cracks. And predicting the fatigue life of the pipeline through the stress spectrum to determine the safety state of the pipeline, thereby realizing the safety evaluation of the in-service platform process pipeline. Therefore, the method can be widely applied to the technical fields of marine oil safety assessment, prediction analysis and safety production.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Like reference numerals refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a flow chart of a method for fatigue damage and prediction of a process pipeline based on multi-mode fusion according to an embodiment of the present invention;
FIG. 2 is a flow chart of fluid-to-vibration evaluation provided by an embodiment of the present invention;
FIG. 3 is a flow chart of quantitative evaluation of fluid pulsation according to an embodiment of the present invention;
FIG. 4 is a flow chart of the AIV evaluation according to the embodiment of the present invention;
FIG. 5 is a table of comparison LOFs provided by an embodiment of the present invention;
FIG. 6 is a main pipeline quantitative evaluation criterion provided by an embodiment of the present invention;
FIG. 7 is a diagram illustrating a branch pipeline quantitative evaluation criterion according to an embodiment of the present invention;
FIG. 8 illustrates a thermal well pipeline quantitative evaluation criteria provided by an embodiment of the present invention;
FIG. 9 illustrates a method for locating damage based on vibration sensing analysis according to an embodiment of the present invention;
FIG. 10 is a neural network structure based on vibration damage identification provided by an embodiment of the present invention;
FIG. 11 is a flow chart of an acoustic emission damage recognition-based analysis provided by an embodiment of the present invention;
fig. 12 is a multi-mode converged network architecture provided by an embodiment of the present invention;
FIG. 13 is a modal analysis provided by an embodiment of the invention;
FIG. 14 is a flowchart of determining a lesion location by a BP neural network according to an embodiment of the present invention;
15 a-15 d are vibration information recognition BP network neural model and damage fitting results provided by the embodiment of the invention;
fig. 16a and 16b are rain flow counting statistics provided by embodiments of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the drawings of the embodiments of the present invention. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the described embodiments of the invention, are within the scope of the invention.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
Damage and cracking to the process pipeline is often difficult to identify and therefore requires analysis in conjunction with the inspection data to assess the pipeline condition. In order to solve the problem that a single signal error is difficult to control, a multi-mode fusion mode is combined, and prediction analysis is carried out through a neural network model so as to accurately evaluate damage and cracks. The invention takes the field detection signal as the basis input, develops various analyses on the basis of signal preprocessing, and tries to provide identification and analysis on the weak link of the process pipeline on the premise of not influencing the production, thereby taking measures on the weak link of the pipeline in time and preventing various accidents and losses under the condition of sudden failure of the pipeline.
The invention discloses a method for identifying and predicting fatigue damage of a process pipeline based on multimode fusion in some embodiments. And combining the existing database and test data, and positioning the positions of the damage and the crack by acquiring field detection signals and a multimode fusion network model. For damage-free and crack-free pipelines, the fatigue life is predicted by stress spectroscopy in view of the cumulative effect of the oscillating alternating loads. On the basis of theoretical analysis, a multimode fusion process pipeline fatigue damage and prediction software platform is compiled, the analysis is quickly completed by reading detection data, and weak links or residual service life of the pipeline are output, so that a decision basis is provided for the site.
In accordance with other embodiments of the present invention, a system, apparatus and medium for identifying and predicting fatigue damage to a process pipeline are provided.
Example 1
As shown in fig. 1, the present embodiment provides a method for identifying and predicting fatigue damage of a process pipeline, comprising the following steps:
s1, calculating a failure probability coefficient (LOF) of each process pipeline of the offshore oil platform, and determining a key process pipeline for multimode signal detection;
s2, obtaining multimode detection data of the key process pipeline, and performing damage identification based on the obtained multimode detection data to obtain a damage identification result of the key process pipeline;
and S3, based on the damage identification result, carrying out fatigue life prediction on the key process pipeline according to the stress-strain measurement data to obtain a fatigue life prediction result of the key process pipeline.
In a preferred embodiment, in step S1, a method of combining fluid pulsation and high frequency acoustics may be used to calculate the failure probability coefficient of the offshore oil platform process pipeline.
The method can be realized by the following steps:
s1.1, respectively carrying out fluid-to-vibration evaluation, fluid pulsation evaluation and high-frequency acoustic vibration evaluation on the marine oil platform process pipeline to obtain failure possibility coefficients of the process pipelines;
s1.2, determining weak positions of the marine oil platform process pipelines based on the obtained failure possibility coefficients of the process pipelines to serve as key process pipelines for multi-mode signal detection.
In a preferred embodiment, as shown in fig. 2, the method for evaluating the fluid-to-vibration in the offshore oil platform process pipeline in the step S1.1 comprises the following steps:
determining the fluid quality, i.e. rho v, in a certain process pipeline of an offshore oil platform2Wherein ρ is the fluid density and v is the fluid flow rate;
determining the viscosity coefficient FVF of the fluid in the process pipeline;
thirdly, determining the bracket arrangement of the process pipeline and determining the vortex frequency F of the process pipeline according to the determined bracket arrangement modeV；
Fourthly, according to the determined fluid mass, the determined fluid viscosity coefficient and Fv, calculating a disturbed flow LOF coefficient caused by the flow, and correcting the disturbed flow LOF coefficient to obtain a failure probability coefficient; when the failure possibility coefficient is corrected, an advanced screening method is adopted, and specifically, the basic natural frequency of the advanced screening method is set to be 1-3 Hz;
and fifthly, repeating the steps from the first step to the fourth step, and calculating to obtain the failure possibility coefficients of other process pipelines in the offshore oil platform.
Wherein, according to the stent arrangement type, as shown in the following Table 1, FVThe calculation method of (b) is shown in table 2 below.
TABLE 1 Stent arrangement
TABLE 2 Fv calculation method
In a preferred embodiment, as shown in FIG. 3, a method of fluid pulsation assessment for process lines of an offshore oil platform, comprises the steps of:
determining the critical diameter of a certain process pipeline in an offshore oil platform;
wherein, the calculation formula of the critical diameter of a certain process pipeline is as follows:
in the formula (d)critIs the critical diameter.
Determining the size relationship between the diameter of the process pipeline and the critical diameter, if the diameter of the process pipeline is smaller than the critical diameter, the LOF value of the process pipeline is 0.2, and if the diameter of the process pipeline is larger than or equal to the critical diameter, entering the step III;
(iii) determining whether the Reynolds number flowing through the process line is greater than a predetermined value (e.g. 1.6X 10)7) If yes, entering the fourth step, otherwise entering the fifth step;
fourthly, calculating the Strouhal number S of the process pipeline according to the following formula;
wherein d isintIs the branch line inner diameter and DintIs the main pipeline inner diameter.
Calculating according to the following formula, and obtaining the S of the process pipeline after correction:
wherein Re is Reynolds number.
Sixthly, calculating according to the S of the branch pipe to obtain Fv of the process pipeline;
seventhly, comparing the Fv obtained through calculation with the acoustic natural frequency Fs, and obtaining an LOF coefficient of the process pipeline according to a comparison result;
wherein, the calculation formula of Fs is:
when Fv is more than or equal to Fs, the LOF coefficient of the process pipeline is 1, and when Fv is more than Fs, the LOF coefficient of the process pipeline is 0.29.
And (iii) repeating the steps of the first step and the second step, and calculating to obtain the LOF coefficient of each process pipeline.
In a preferred embodiment, as shown in FIG. 4, a high frequency acoustic vibration assessment method includes the steps of:
calculating the noise level at the sound source;
the calculation formula is as follows:
wherein, P1For pressure reducing meansAn inlet pressure value; p2The pressure value is the outlet pressure value of the pressure reduction facility; t iseIs the inlet temperature; mWIs the molar mass of the medium; w is the mass flow rate; SFF is the sonic flow correction coefficient.
Determining whether the valve core adopts a low-noise mode when the valve is an excitation source, if so, entering the step III, and otherwise, entering the step IV;
correcting the noise level of the sound source according to the data provided by the valve manufacturer, and then entering the step (iv);
for example, if the low noise spool is reduced by 15dB, the value should be subtracted from the calculated PWL. When this method is used, the PWL provided by the valve manufacturer must not be used;
comparing whether the noise value is larger than or equal to a preset threshold (for example, 155 decibels) or not, if so, taking the LOF value of the point to be 0.29, otherwise, entering the step (v);
fifthly, turning to the next welding discontinuous point (such as SBC, welded tee or welded support) and calculating the noise value after attenuation;
the calculation formula is as follows:
wherein L isdisThe distance from the excitation source to the weld discontinuity.
Sixthly, judging whether other excitation sources exist or not, if not, entering a step (c), if so, considering all the excitation sources, and entering the step (c) after calculating the noise value after attenuation at discontinuous positions;
and comparing the noise value at the moment with a preset value (for example, 155 decibels), if the noise value is greater than or equal to the preset value, calculating a LOF value at the discontinuous part, if the noise value is less than the preset value, determining that the main line LOF is equal to the maximum discontinuous position LOF from the source to the position, and determining that the LOF of the subsequent length of the pipeline is 0.29.
In a preferred embodiment, in step S1.2, the method for determining the weak point of the offshore oil platform process pipeline based on the obtained failure probability coefficient comprises: and determining weak positions of the offshore oil platform process pipelines as key process pipelines needing to be intensively analyzed based on the calculated failure probability coefficients (LOF) of the process pipelines and by comparing LOF tables (see figure 5) and key evaluation acceptance tables (see figures 6-8).
In a preferred embodiment, in the step S2, the method for obtaining multi-mode detection data of the key process pipeline and performing damage identification based on the obtained multi-mode detection data to obtain a damage identification result of the key process pipeline includes the following steps:
s2.1, performing vibration measurement and acoustic emission measurement on the key process pipeline to obtain a vibration signal and an acoustic emission signal of the key process pipeline;
s2.2, preprocessing the vibration signal and the acoustic emission signal of the key process pipeline to obtain an input vector, and inputting a pre-constructed multimode fusion damage identification model to obtain a multimode fusion damage identification result.
In a preferred embodiment, in step S2.2, the method for constructing the multimodal fusion lesion identification model includes the following steps:
s2.2.1, preprocessing the vibration signal, and inputting the preprocessed vibration signal into a BP neural network intelligent model for damage identification to obtain a damage identification result based on the vibration signal;
s2.2.2, preprocessing the acoustic emission signals, and inputting the acoustic emission signals into the PNN neural network model for damage identification to obtain a damage identification result based on the acoustic emission signals;
s2.2.3, training a multi-mode fusion damage recognition model, wherein the model takes the fusion vector of the vibration signal and the acoustic emission signal as input and takes the fusion vector of the damage recognition result based on the vibration signal and the damage recognition result based on the acoustic emission signal as output.
In a preferred embodiment, in the step S2.2.1, as shown in fig. 9, the method for preprocessing the vibration signal and inputting the preprocessed vibration signal into the intelligent BP neural network model to perform damage identification to obtain a damage identification result based on the vibration signal includes the following steps:
firstly, acquiring a vibration signal of a key process pipeline;
preprocessing the acquired vibration signals of the key process pipeline based on a modal theory to obtain pipeline vibration modal parameters, wherein the pipeline vibration modal parameters mainly comprise natural frequency, mode, damping and the like;
and thirdly, inputting the pipeline vibration modal parameters into a BP neural network model for carrying out damage positioning to obtain the damage condition and position.
The BP neural network is a neural network with error back propagation, and different neurons have different weights and thresholds. The weight value and the threshold value are repeatedly iterated and modified by combining a learning training sample of big data, so that an accurate mapping relation between input and output is established. Specifically, in the embodiment of the invention, the learning training sample of the BP neural network intelligent model is vibration signal big data formed by the previous oil field detection data, test simulation data and the like, and the constructed BP neural network intelligent model is trained based on the vibration signal big data to obtain the trained BP neural network intelligent model for performing damage identification.
As shown in fig. 10, the BP neural network intelligent model in the present embodiment includes an input layer, a hidden layer, and an output layer. The input layer takes a ten-th-order normalized natural frequency change ratio (calculated based on initial natural frequency in each mode, structural natural frequency after damage and the like, and neglected damping) as input, and the output layer takes a damage position as output.
In a preferred embodiment, in the step S2.2.3, as shown in fig. 11, the method for preprocessing the acoustic emission signal and inputting the acoustic emission signal into the PNN neural network model for lesion recognition to obtain a lesion recognition result based on the acoustic emission signal includes the following steps:
firstly, extracting the characteristics of the obtained acoustic emission signals based on wavelet transformation and EMD decomposition to obtain characteristic vectors;
comparing the extracted characteristic vector with a pattern sample (taken from a database and test sample data) by combining a PNN neural network (probabilistic neural network), analyzing the matching relation between the input sample and the pattern sample at a pattern layer, and processing different classification probabilities at a summation layer to obtain a network output classification result;
and thirdly, obtaining signal time difference based on the acoustic emission signals, judging the classification result output by the network according to the signal time difference, and determining noise or crack damage during damage identification.
In a preferred embodiment, in step S2.2, as shown in fig. 12, the acquired and processed vibration and acoustic emission signals are preprocessed to obtain 11-dimensional data, that is, the data after the first ten-order normalized frequency change rate + acoustic emission recognition processing is input into the multimode fusion damage recognition model to perform fatigue crack localization, so as to obtain a multimode fusion damage recognition result.
In a preferred embodiment, the step S3 includes the following steps:
s3.1, acquiring the stress level of the stress concentration position of the primary selection position of the key process pipeline through a stress-strain measuring device;
and S3.2, preprocessing the obtained stress level, including removing zero drift, abnormal signals and filtering, compiling a stress spectrum by adopting a rain flow counting method, and evaluating the fatigue life of the key process pipeline by combining a Palmgren-Miner (linear damage accumulation) theory.
Example 2
In this embodiment, a method for predicting fatigue damage of a process pipeline provided in embodiment 1 is described in detail, and the implementation method mainly includes the following steps:
(1) collecting on-site process flow parameters, noise levels and vibration parameters, performing preliminary analysis on the offshore oil platform process pipeline by combining the flows of figures 2-4, calculating LOF values, and performing preliminary range screening on the offshore oil platform process pipeline according to figures 5-8 to determine key process pipelines.
(2) And arranging vibration measuring points for the screened key process pipelines. After the vibration signal is processed, a measuring point with energy exceeding the standard is selected through an energy method, the modal characteristics of the pipeline are analyzed, and modal parameters are obtained: natural frequencies, modes, damping, etc. (shown in fig. 13).
(3) Analyzing the data after detection processing through a BP network neural model trained by vibration big data, wherein the frequency change rate is related to the damage position and the damage degree, and therefore the frequency change rate is as follows:
FFC＝g(r)f(ΔK，ΔM) (7)
after expansion by taylor series, the change is:
the positioning is defined by the following input parameters:
{input}＝{NFCR1，NFCR2，...，NFCRi，...，NFCRm} (9)
the analysis flow of the BP neural network identification injury position based on genetic algorithm improvement is shown in figure 14.
(4) An acoustic emission detection device is disposed at the critical process pipeline. And signal characteristics are decomposed through EMD and wavelet packets, and characteristic signals are extracted. And analyzing the parameters through a PNN neural network intelligent model on the basis.
(5) As shown in fig. 15a to 15d, the time difference method is used for data obtained by the vibration modal parameters and the acoustic emission, and the BP neural network is combined for fusion analysis, so as to give initial damage location, the PNN neural network is used for further carrying out damage identification on the acoustic emission collected data, and the initial damage location is compared to determine the positions of the damage and the crack.
(6) And (3) when the damage and the crack are not identified in the detection, arranging stress strain measurement on the key process pipeline identified in the step (1).
(7) As shown in fig. 16a and 16b, after the collected data is filtered, the stress amplitude result is counted by using a rain flow counting method, and then the accumulated damage is calculated on the basis, so as to evaluate the remaining life of the critical pipeline in the current working state.
The method for predicting the fatigue damage of the process pipeline based on the multimode fusion, provided by the embodiment of the invention, realizes the identification of the damage and the crack of the key process pipeline and the evaluation of the fatigue life based on the acquisition and the processing of various sensing data, thereby effectively evaluating the safety of the key process pipeline in service for a long time and providing a decision basis for preventing various accidents or events caused by the pipeline failure.
Example 3
The embodiment 1 provides a method for identifying and predicting fatigue damage of a process pipeline, and correspondingly, the embodiment provides a system for identifying and predicting fatigue damage of a process pipeline. The system provided in this embodiment may implement the method for identifying and predicting fatigue damage of a process pipeline in embodiment 1, and the identification system may be implemented by software, hardware, or a combination of software and hardware. For example, the system may comprise integrated or separate functional modules or functional units to perform the corresponding steps in the methods of embodiment 1. Since the identification system of this embodiment is basically similar to the method embodiment, the description process of this embodiment is relatively simple, and reference may be made to the partial description of embodiment 1 for relevant points, and the embodiment of the system of this embodiment is only schematic.
The system for identifying and predicting fatigue damage of a process pipeline provided by the embodiment comprises:
the primary selection position determining module is used for calculating the failure possibility coefficient of the key process pipeline and determining the key process pipeline detected by the multimode signal;
the multimode fusion identification module is used for acquiring multimode detection data of the key process pipeline and identifying damage based on the acquired multimode detection data to obtain a damage identification result of the key process pipeline;
and the fatigue prediction module is used for predicting the fatigue life of the key process pipeline according to the stress-strain measurement data to obtain a fatigue life prediction result of the key process pipeline.
Example 4
This embodiment provides a processing device corresponding to the method for identifying and predicting fatigue damage of a process pipeline provided in embodiment 1, where the processing device may be a processing device for a client, such as a mobile phone, a laptop, a tablet computer, a desktop computer, etc., to execute the method of embodiment 1.
The processing equipment comprises a processor, a memory, a communication interface and a bus, wherein the processor, the memory and the communication interface are connected through the bus so as to complete mutual communication. The memory stores a computer program that can be executed on the processor, and the processor executes the computer program to execute the method for predicting fatigue damage of the process pipeline provided by embodiment 1.
In some implementations, the Memory may be a high-speed Random Access Memory (RAM), and may also include a non-volatile Memory, such as at least one disk Memory.
In other implementations, the processor may be various general-purpose processors such as a Central Processing Unit (CPU), a Digital Signal Processor (DSP), and the like, and is not limited herein.
Example 5
A method for identifying and predicting fatigue damage of a process pipeline according to embodiment 1 may be embodied as a computer program product, which may include a computer readable storage medium having computer readable program instructions for executing the method for identifying and predicting fatigue damage of a process pipeline according to embodiment 1.
The computer readable storage medium may be a tangible device that holds and stores the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination of the foregoing.
It should be noted that the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. Each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s).
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
The foregoing embodiments are merely illustrative of the present invention, and various components, devices, or steps of the embodiments may be changed or eliminated as desired, not all components may be necessarily shown in the drawings, and the general principles defined in the present application may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments described herein, and all equivalent changes and modifications based on the technical solutions of the present invention should not be excluded from the scope of the present invention.
Claims (10)
1. A method for identifying and predicting fatigue damage of a process pipeline is characterized by comprising the following steps:
calculating failure possibility coefficients of all process pipelines of the offshore oil platform, and determining key process pipelines for multi-mode signal detection;
acquiring multimode detection data of a key process pipeline, and performing damage identification based on the acquired multimode detection data to obtain a damage identification result of the key process pipeline;
and based on the damage identification result, predicting the fatigue life of the key process pipeline according to the stress-strain measurement data to obtain a fatigue life prediction result of the key process pipeline.
2. The method for identifying and predicting fatigue damage of process pipelines according to claim 1, wherein the method for calculating the failure probability coefficient of each process pipeline of the offshore oil platform and determining the key process pipeline for detecting the multimode signal comprises the following steps:
respectively carrying out fluid-to-vibration evaluation, fluid pulsation evaluation and high-frequency acoustic vibration evaluation on the marine oil platform process pipelines to obtain failure probability coefficients of the process pipelines;
and determining weak positions of the marine oil platform process pipelines based on the obtained failure possibility coefficients of the process pipelines and a preset criterion, and using the weak positions as key process pipelines for multi-mode signal detection.
3. The method for identifying and predicting fatigue damage of a process pipeline according to claim 1, wherein the method for obtaining multimode detection data of the key process pipeline and identifying damage based on the obtained multimode detection data to obtain damage identification result of the key process pipeline comprises the following steps:
performing vibration measurement and acoustic emission measurement on the key process pipeline to obtain a vibration signal and an acoustic emission signal of the key process pipeline;
and preprocessing the vibration signal and the acoustic emission signal of the key process pipeline to obtain an input vector, and inputting a pre-constructed multimode fusion damage identification model to obtain a multimode fusion damage identification result.
4. The method for identifying and predicting fatigue damage of process pipelines according to claim 3, wherein the method for constructing the multi-mode fusion damage identification model comprises the following steps:
preprocessing the vibration signal, and inputting the vibration signal into a BP neural network intelligent model for damage identification to obtain a damage identification result based on the vibration signal;
preprocessing the acoustic emission signals, inputting the acoustic emission signals into a PNN neural network model for damage identification, and obtaining a damage identification result based on the acoustic emission signals;
and training a multi-mode fusion damage identification model, wherein the model takes a fusion vector of the vibration signal and the acoustic emission signal as input, and takes a damage identification result based on the vibration signal and a fusion vector of the damage identification result based on the acoustic emission signal as output.
5. The method for identifying and predicting the fatigue damage of the process pipeline as claimed in claim 4, wherein the method for preprocessing the vibration signal and inputting the preprocessed vibration signal into the intelligent BP neural network model to identify the damage so as to obtain the damage identification result based on the vibration signal comprises the following steps:
acquiring a vibration signal of a key process pipeline;
preprocessing the acquired vibration signal of the key process pipeline based on a modal theory to obtain a pipeline vibration modal parameter;
and inputting the pipeline vibration modal parameters into a BP neural network model for carrying out damage positioning to obtain the damage condition and position.
6. The method for identifying and predicting the fatigue damage of the process pipeline as recited in claim 4, wherein the acoustic emission signal is preprocessed and input into the PNN neural network model for damage identification, and a damage identification result based on the acoustic emission signal is obtained, comprising the following steps:
extracting the characteristics of the obtained acoustic emission signals based on wavelet transformation and EMD decomposition to obtain characteristic vectors;
comparing the extracted characteristic vector with the pattern sample by combining a PNN neural network to obtain a network output classification result;
and obtaining a signal time difference based on the acoustic emission signal, judging a network output classification result by the signal time difference, and determining noise or crack damage during damage identification.
7. The method of claim 1, wherein the method of predicting fatigue life of a key process pipeline based on stress-strain measurement data based on damage identification results to obtain a predicted fatigue life of the key process pipeline comprises:
acquiring the stress level of the stress concentration part of the key process pipeline through a stress-strain measuring device;
and preprocessing the obtained stress level, compiling a stress spectrum by adopting a rain flow counting method, and evaluating the fatigue life of the key process pipeline by combining a linear damage accumulation theory.
8. A system for identifying and predicting fatigue damage of a process pipeline is characterized by comprising:
the primary selection position determining module is used for calculating the failure possibility coefficient of the key process pipeline and determining the key process pipeline detected by the multimode signal;
the multimode fusion identification module is used for acquiring multimode detection data of the key process pipeline and identifying damage based on the acquired multimode detection data to obtain a damage identification result of the key process pipeline;
and the fatigue prediction module is used for predicting the fatigue life of the key process pipeline according to the stress-strain measurement data to obtain a fatigue life prediction result of the key process pipeline.
9. A processing apparatus comprising at least a processor and a memory, the memory having stored thereon a computer program, wherein the processor, when executing the computer program, performs the steps to implement the method for identifying and predicting fatigue damage to a process pipeline according to any of claims 1 to 7.
10. A computer storage medium having computer readable instructions stored thereon which are executable by a processor to perform the steps of the method for identifying and predicting fatigue damage in a process line according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210288472.6A CN114638166A (en) | 2022-03-23 | 2022-03-23 | Method, system, equipment and medium for identifying and predicting fatigue damage of process pipeline |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210288472.6A CN114638166A (en) | 2022-03-23 | 2022-03-23 | Method, system, equipment and medium for identifying and predicting fatigue damage of process pipeline |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114638166A true CN114638166A (en) | 2022-06-17 |
Family
ID=81950016
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210288472.6A Pending CN114638166A (en) | 2022-03-23 | 2022-03-23 | Method, system, equipment and medium for identifying and predicting fatigue damage of process pipeline |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114638166A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116608419A (en) * | 2023-07-20 | 2023-08-18 | 山东特检科技有限公司 | Pipeline fatigue failure risk assessment method combined with vibration monitoring |
| CN117743949A (en) * | 2024-02-21 | 2024-03-22 | 山东科技大学 | Method and equipment for predicting service life and operating and maintaining submarine oil and gas pipeline |
-
2022
- 2022-03-23 CN CN202210288472.6A patent/CN114638166A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116608419A (en) * | 2023-07-20 | 2023-08-18 | 山东特检科技有限公司 | Pipeline fatigue failure risk assessment method combined with vibration monitoring |
| CN116608419B (en) * | 2023-07-20 | 2023-11-03 | 山东特检科技有限公司 | Pipeline fatigue failure risk assessment method combined with vibration monitoring |
| CN117743949A (en) * | 2024-02-21 | 2024-03-22 | 山东科技大学 | Method and equipment for predicting service life and operating and maintaining submarine oil and gas pipeline |
| CN117743949B (en) * | 2024-02-21 | 2024-05-17 | 山东科技大学 | Method and equipment for predicting service life and operating and maintaining submarine oil and gas pipeline |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xie et al. | A review on pipeline integrity management utilizing in-line inspection data | |
| Khan et al. | Risk-based pipeline integrity management: A road map for the resilient pipelines | |
| Song et al. | Gas leak detection in galvanised steel pipe with internal flow noise using convolutional neural network | |
| CN114638166A (en) | Method, system, equipment and medium for identifying and predicting fatigue damage of process pipeline | |
| Keshtegar et al. | Reliability analysis of corroded pipes using conjugate HL–RF algorithm based on average shear stress yield criterion | |
| WO2020033316A1 (en) | Leak detection with artificial intelligence | |
| US20130332090A1 (en) | System and method for identifying related events in a resource network monitoring system | |
| CN106323385A (en) | Online detection of storage tank, assessment method and device | |
| US20220275610A1 (en) | Method and system to monitor pipeline condition | |
| CN113348349B (en) | Method and system for analyzing pipeline conditions | |
| US11898705B2 (en) | System and method for mechanical failure classification, condition assessment and remediation recommendation | |
| Xiao et al. | A model-based health indicator for leak detection in gas pipeline systems | |
| Kim et al. | Adaptive approach for estimation of pipeline corrosion defects via Bayesian inference | |
| Yan et al. | Reliability-based crack threat assessment and management | |
| CN117233347B (en) | Carbon steel spheroidization grade measuring method, system and equipment | |
| CN114722856A (en) | Pipeline damage monitoring method and device | |
| CN116090322A (en) | Intelligent decision visualization system for pipeline integrity | |
| US20210164941A1 (en) | System and method for analyzing anomalies in a conduit | |
| CN111400927B (en) | Method and device for predicting corrosion growth in pipeline based on generalized additive model | |
| Kurata et al. | A probabilistic model updating algorithm for fatigue damage detection in aluminum hull structures | |
| CN111666684A (en) | Circumferential weld risk estimation method and device for conveying pipeline and readable storage medium | |
| Valizadeh et al. | Leak detection in transportation pipelines using feature extraction and KNN classification | |
| CN117009801A (en) | Traffic prediction model training method, detection method, system and storage medium | |
| Stubelj et al. | Pipeline predictive analitics trough on-line remote corrosion monitoring | |
| Koduru et al. | Review of Quantitative Reliability Methods for Onshore Oil and Gas Pipelines |
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 |