CN113065224A - Deep sea pipeline crack propagation monitoring and reliability evaluation method based on image recognition - Google Patents

Deep sea pipeline crack propagation monitoring and reliability evaluation method based on image recognition Download PDF

Info

Publication number
CN113065224A
CN113065224A CN202110243661.7A CN202110243661A CN113065224A CN 113065224 A CN113065224 A CN 113065224A CN 202110243661 A CN202110243661 A CN 202110243661A CN 113065224 A CN113065224 A CN 113065224A
Authority
CN
China
Prior art keywords
crack
pipeline
deep sea
image
monitoring
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.)
Granted
Application number
CN202110243661.7A
Other languages
Chinese (zh)
Other versions
CN113065224B (en
Inventor
余杨
李昊达
余建星
王华昆
王彩妹
陈佰川
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tianjin University
Original Assignee
Tianjin University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Tianjin University filed Critical Tianjin University
Priority to CN202110243661.7A priority Critical patent/CN113065224B/en
Publication of CN113065224A publication Critical patent/CN113065224A/en
Application granted granted Critical
Publication of CN113065224B publication Critical patent/CN113065224B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2113/00—Details relating to the application field
    • G06F2113/14—Pipes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/04—Ageing analysis or optimisation against ageing

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Evolutionary Computation (AREA)
  • Geometry (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Image Analysis (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)

Abstract

The invention provides a deep sea pipeline crack propagation monitoring and reliability evaluation method based on image recognition, which comprises the steps of firstly utilizing historical crack image sample data of a deep sea pipeline to carry out actual full-scale test or numerical simulation on the deep sea pipeline; establishing a pipeline fatigue life prediction model corresponding to the deep sea pipeline surface crack by using an XFEM method; selecting a pipeline area image with cracks on a monitored pipeline, inputting the pipeline area image into a prediction model, carrying out residual life evaluation under alternating load on the processed crack subunit image, and outputting an evaluation result; and evaluating the reliability of one crack image on the single monitoring pipeline, and evaluating the overall reliability of the single monitoring pipeline to obtain a reliability prediction result of the single monitoring pipeline in a pipeline system. According to the method, an evaluation model is established for the cracks generated in the pipeline through image characteristic identification, the reliability of the pipeline is modeled and evaluated, and finally the crack state identification and reliability evaluation of the actual deep-sea pipeline are completed.

Description

Deep sea pipeline crack propagation monitoring and reliability evaluation method based on image recognition
Technical Field
The invention relates to the field of underwater pipeline monitoring, in particular to a deep sea pipeline crack propagation monitoring and reliability evaluation method based on image recognition.
Background
With the development of oil exploitation in China to deep sea, the application of deep sea pipelines is more and more extensive, and the construction, operation and maintenance of the deep sea pipelines are also important embodiments of national capability. Deep sea petroleum pipelines are in a high-pressure state for a long time due to being located in deep sea, cracks can be generated under the action of axial and circumferential loads, the pipeline system can be out of work due to the fact that the cracks are expanded to a certain degree, petroleum is leaked seriously and even, great economic benefit loss is generated, and destructive and great pollution is caused to the environment. Investigations have shown that material ageing, long-term fatigue effects and foreign body impact are important factors for crack initiation, and there are already many cases of pipeline failure due to crack propagation.
In the prior art, the residual evaluation of the crack propagation of the deep sea pipeline mainly adopts a numerical simulation and a laboratory test mode, so that huge manpower and material resources are consumed. In addition, a deep sea camera is adopted to monitor the deep sea pipeline, and the mode can facilitate operation and maintenance personnel to observe the surface condition of the pipeline and save manpower and material resources.
In order to ensure the safety of a pipeline system, the current petroleum development department generally adopts a mode of regular maintenance and inspection to evaluate the safety of a deep sea pipeline, but the evaluation mode cannot realize real-time evaluation, and the pipeline system is more difficult to inspect when encountering dangerous sea conditions, and in addition, the evaluation mode has great limitation.
Therefore, an efficient and accurate real-time crack propagation residual life evaluation and reliability analysis method is urgently needed to be provided.
Disclosure of Invention
The invention aims to provide a deep sea pipeline crack propagation monitoring and reliability evaluation method based on image recognition, so as to realize instant analysis and influence evaluation on the crack state of a deep sea pipeline.
Specifically, the invention provides a deep sea pipeline crack propagation monitoring and reliability evaluation method based on image recognition, which comprises the following steps:
step 100, firstly, collecting historical crack image sample data of the deep sea pipeline, then determining an added displacement motion amplitude value according to an actual working condition, extracting key points near different cracks according to the crack image sample, endowing each crack image sample with a corresponding actual working life, simultaneously predicting the damage degree of different stages after a new crack appears in the crack image sample, assigning values, and finally carrying out actual full-size test or numerical simulation on the deep sea pipeline according to the data;
200, in the full-scale test or numerical simulation process, drawing crack time-varying graphs under different crack propagation lives by using a DCPD method and taking the crack length as a vertical coordinate and time as a horizontal coordinate, and establishing a pipeline fatigue life prediction model corresponding to the deep sea pipeline surface crack by using an XFEM method;
step 300, selecting a pipeline area image with cracks on a monitoring pipeline, dividing the image part with the cracks into a plurality of crack subunit images with similar sizes, inputting the crack subunit images into a prediction model, processing crack sub-images by using an optical flow method to obtain the motion state of crack characteristic points, evaluating the residual life of the processed crack subunit images under alternating load, and outputting an evaluation result;
and 400, evaluating the reliability of one crack image on a single monitoring pipeline by using a limit state function and a Monte Carlo method, processing all crack images on the single monitoring pipeline by using the same method, evaluating the overall reliability of the single monitoring pipeline, and obtaining a reliability prediction result of the single monitoring pipeline in the pipeline system according to the importance degree of the single monitoring pipeline in the whole pipeline system by using an expert scoring method.
The method comprises the steps of establishing an evaluation model for the expansion cracks generated by various reasons of the historical pipeline by utilizing the pipeline image acquired by the deep water camera through image feature recognition, modeling and evaluating the reliability of the historical pipeline, performing full-scale test matching with the monitoring pipeline, and finally completing crack state recognition and reliability evaluation of the monitored deep water pipeline.
The method adopts an L-K optical flow method to monitor the crack propagation form, can obtain the motion of the crack edge characteristic points of adjacent frames, can improve the intelligent monitoring of the reliability of the deep sea pipeline, and provides a solution for the safe development and unmanned monitoring of the deep sea oil and gas field.
Drawings
FIG. 1 is a schematic process flow diagram of one embodiment of the present invention.
Detailed Description
The detailed structure and implementation process of the present solution are described in detail below with reference to specific embodiments and the accompanying drawings. In the following description, the historical pipeline refers to a pipeline from a used deep sea pipeline to the end of the working life caused by a crack after the crack is generated, and the crack image thereof is photographed and stored during the working process thereof. The monitoring pipeline refers to a deep sea pipeline which is currently used, and a crack image of the deep sea pipeline is acquired in real time.
In one embodiment of the invention, as shown in fig. 1, a deep sea pipeline crack propagation monitoring and reliability evaluation method based on image recognition is provided, which comprises the following steps:
step 100, firstly, collecting historical crack image sample data of the deep sea pipeline, then determining an added displacement motion amplitude value according to an actual working condition, extracting key points near different cracks according to the crack image sample, endowing each crack image sample with a corresponding actual working life, simultaneously predicting the damage degree of different stages after a new crack appears in the crack image sample, assigning values, and finally carrying out actual full-size test or numerical simulation on the deep sea pipeline according to the data;
the method comprises the steps of taking a crack generation process on a historical pipeline as reference data, and establishing a model through full-scale experiments or numerical simulation according to the crack shape and the trend of the historical pipeline and data such as the influence of different crack lengths on the service life of the pipeline, so as to be used as an image crack prediction reference of a later-stage monitoring pipeline.
The longer the crack length is, the greater the influence on the service life of the pipeline is, so that the crack length is influenced on the pipeline from the beginning to the end of the service life of the pipeline caused by the crack length in the step, the crack generation process of the historical pipeline is divided into different stages, and each stage is assigned with a value; the specific division and assignment can be adjusted according to factors such as the material and the use environment of different pipelines, in the embodiment, the length change process of the crack from the crack generation to the pipeline use stopping process is divided into ten stages, and 1-10 are sequentially assigned according to the crack generation sequence, wherein 1 represents the shortest, and 10 represents that the crack seriously threatens the service life of the pipeline or the pipeline cannot be used.
The extraction of the key points is that two side edges in the crack length direction represent points of crack trend and width, and by defining the key points of different cracks, a two-dimensional image can be converted into a numerical image, then different crack shapes and lengths can be defined, and further, a monitoring image input in the later stage can be rapidly identified, and corresponding reference data is introduced.
The relationship between the crack and the service life of the pipeline can be confirmed in the historical image of the pipeline according to different lengths of the pipeline service life, and then the corresponding relationship between the crack length and the pipeline service life is established.
The method comprises the following steps of:
step 101, comparing the extracted key point data with an actual working life result input into a full-scale experiment or numerical simulation, and establishing a life key point fitting function;
102, simultaneously carrying out multiple extraction experiments on key points in the crack image sample by using numerical simulation, and substituting the extraction experiment results into a fitting function for optimization;
and 103, fitting the function dispersion, and then obtaining the prediction results of the new crack at different stages.
Specific assignment types include: and assigning a crack propagation stage, assigning a stable propagation stage and assigning an accelerated propagation stage.
200, in the full-scale test or numerical simulation process, drawing crack time-varying graphs under different crack propagation lives by using a DCPD method and taking the crack length as a vertical coordinate and time as a horizontal coordinate, and establishing a pipeline fatigue life prediction model corresponding to the deep sea pipeline surface crack by using an XFEM method;
by adopting the XFEM method, the grid is independent of the geometric or physical interface in the structure and is independent of the geometric or physical interface, and the calculation of the stress field at the tip of the crack and the calculation of the crack surface expansion are independent of each other, so that the problem of high-density grid division at the tip of the crack and the operation of grid re-division are avoided.
The calculation process of the XFEM method is as follows:
will any function
Figure BDA0002963269130000051
Using local functions in the domain
Figure BDA0002963269130000052
It is shown that,
Figure BDA0002963269130000053
and make it possible to
∑ΓHΓ(x)＝1 (2)
Overlapping slices { theta }iConstitute an overlay of the investigation region M,
Figure BDA0002963269130000054
is a unit decomposition over the coverage. On each slice, the function space ViFor a local approximation of region M, the overall heuristic space V is:
Figure BDA0002963269130000055
the total space V not only has a partial space ViOf approximation, with unit decomposition
Figure BDA0002963269130000056
And a local space ViSmoothness of (2) as long as the unit is decomposed
Figure BDA0002963269130000057
Sufficiently smooth, a sufficiently smooth trial space can be constructed.
Step 300, selecting a pipeline area image with cracks on a monitoring pipeline, dividing the image part with the cracks into a plurality of crack subunit images with similar sizes, inputting the crack subunit images into a prediction model, processing crack sub-images by using an optical flow method to obtain the motion state of crack characteristic points, evaluating the residual life of the processed crack subunit images under alternating load, and outputting an evaluation result;
the finite element method can adopt different plane elements to divide the pipeline area image according to the specific form. The quality of the crack subunits is required to be ensured to be more than 0.6.
The motion state refers to the rate and direction of crack propagation.
The process of obtaining the motion state of the crack characteristic point after processing the crack subunit image by using the optical flow method is as follows:
Figure BDA0002963269130000061
in the formula VxAnd VyIs the propagation rate of the crack in the x and y directions, or called I (x, y, t) luminous flux;
Figure BDA0002963269130000062
and
Figure BDA0002963269130000063
is the image (x, y, t) in the corresponding directionPartial derivatives, the relationship is as follows:
Figure BDA0002963269130000064
next, using the Lucas-Kanade algorithm, the processed crack image flow velocity vectors are satisfied:
Av＝b (6)
wherein the content of the first and second substances,
Figure BDA0002963269130000065
where q is the pixel in the window, Ix(qi)，Iy(qi),It(qi) Is the image at point qiAnd the partial derivatives of the current time with respect to position x, y and time t;
the crack length is then obtained by numerical integration, the formula being:
Figure BDA0002963269130000066
where t is the equivalent crack propagation time and α is the image scale fit coefficient associated with the deep sea camera.
The residual life evaluation is to establish a fatigue life degradation model by utilizing E-N curve parameters, and the calculation process is as follows:
Figure BDA0002963269130000067
in the formula, NfIs the fatigue life,. epsilonaIs the standard Total Strain, σ'fIs the intensity coefficient, b is the intensity index, ε'fIs the ductility factor and c is the ductility index.
And 400, evaluating the reliability of one crack image on a single monitoring pipeline by using a limit state function and a Monte Carlo method, processing all crack images on the single monitoring pipeline by using the same method, evaluating the overall reliability of the single monitoring pipeline, and obtaining a reliability prediction result of the single monitoring pipeline in the pipeline system according to the importance degree of the single monitoring pipeline in the whole pipeline system by using an expert scoring method.
The extreme state function is calculated as follows:
G(x1，x2，…，xn)＝δσfm-PD (10)
where G is the safety margin for pipeline cracking, δ is the correction factor, σfIs the flow stress, m is the wall thickness, P is the internal pressure of the pipe, and D is the diameter of the pipe.
The procedure for calculating reliability using the monte carlo method is as follows:
generating n groups of random number sequences or pseudo-random number sequences which accord with a basic variable probability distribution model according to a crack image of a monitored pipeline, and generating the random number sequences or the pseudo-random number sequences of the basic variable probability distribution model:
Z＝G(x)＝G(x1，x2，…，xn) (11)
and calculating the value of Z, wherein if the number of Z > 0 in the samples with the number of n is m, the residual reliability of the pipeline is as follows:
Figure BDA0002963269130000071
according to the embodiment, a real-time pipeline image is acquired by using a deep water camera, an evaluation model is established for the expansion cracks generated by various reasons of the pipeline through image characteristic identification, then modeling and evaluation are carried out on the reliability of the pipeline, the reliability is matched with a pipeline full-scale test, and finally crack state identification and reliability evaluation of the actual deep sea pipeline are completed.
The crack propagation form is monitored by adopting an L-K optical flow method, the motion of the crack edge characteristic points of adjacent frames is obtained, the intelligent monitoring on the reliability of the deep sea pipeline is improved, and a solution is provided for the safe development and unmanned monitoring of the deep sea oil and gas field.
Thus, it should be appreciated by those skilled in the art that while a number of exemplary embodiments of the invention have been illustrated and described in detail herein, many other variations or modifications consistent with the principles of the invention may be directly determined or derived from the disclosure of the present invention without departing from the spirit and scope of the invention. Accordingly, the scope of the invention should be understood and interpreted to cover all such other variations or modifications.

Claims (10)

1. The deep sea pipeline crack propagation monitoring and reliability evaluation method based on image recognition is characterized by comprising the following steps of:
step 100, firstly, collecting historical crack image sample data of the deep sea pipeline, then determining an added displacement motion amplitude value according to an actual working condition, extracting key points near different cracks according to the crack image sample, endowing each crack image sample with a corresponding actual working life, simultaneously predicting the damage degree of different stages after a new crack appears in the crack image sample, assigning values, and finally carrying out actual full-size test or numerical simulation on the deep sea pipeline according to the data;
200, in the full-scale test or numerical simulation process, drawing crack time-varying graphs under different crack propagation lives by using a DCPD method and taking the crack length as a vertical coordinate and time as a horizontal coordinate, and establishing a pipeline fatigue life prediction model corresponding to the deep sea pipeline surface crack by using an XFEM method;
step 300, selecting a pipeline area image with cracks on a monitoring pipeline, dividing the image part with the cracks into a plurality of crack subunit images with similar sizes, inputting the crack subunit images into a prediction model, processing crack sub-images by using an optical flow method to obtain the motion state of crack characteristic points, evaluating the residual life of the processed crack subunit images under alternating load, and outputting an evaluation result;
and 400, evaluating the reliability of one crack image on a single monitoring pipeline by using a limit state function and a Monte Carlo method, processing all crack images on the single monitoring pipeline by using the same method, evaluating the overall reliability of the single monitoring pipeline, and obtaining a reliability prediction result of the single monitoring pipeline in the pipeline system according to the importance degree of the single monitoring pipeline in the whole pipeline system by using an expert scoring method.
2. The deep sea pipeline crack propagation monitoring and reliability assessment method according to claim 1,
in the step 100, the key points are points at which two sides of the crack in the length direction indicate the crack trend and the crack width.
3. The deep sea pipeline crack propagation monitoring and reliability assessment method according to claim 1,
in the step 100, the process of predicting the damage degree of the new crack at different stages is as follows:
step 101, comparing the extracted key point data with an actual working life result input into a full-scale experiment or numerical simulation, and establishing a life key point fitting function;
102, simultaneously carrying out multiple extraction experiments on key points in the crack image sample by using numerical simulation, and substituting the extraction experiment results into a fitting function for optimization;
and 103, fitting the function dispersion, and then obtaining the prediction results of the new crack at different stages.
4. The deep sea pipeline crack propagation monitoring and reliability assessment method according to claim 1,
the assignment process is as follows: dividing the process of monitoring the end of the service life of the pipeline caused by the crack generation on the pipeline into ten stages, and giving a numerical value from small to large to each stage, wherein the larger the numerical value is, the longer the crack is and the larger the influence on the service life of the pipeline is.
5. The deep sea pipeline crack propagation monitoring and reliability assessment method according to claim 1,
in the step 200, the calculation process of the XFEM method is as follows:
will any function
Figure FDA0002963269120000021
Using local functions in the domain
Figure FDA0002963269120000022
It is shown that,
Figure FDA0002963269120000023
and make it possible to
∑ГHГ(x)＝1 (2)
Overlapping slices { theta }iConstitute an overlay of the investigation region M,
Figure FDA0002963269120000024
is a unit decomposition over the coverage. On each slice, the function space VIFor a local approximation of region M, the overall heuristic space V is:
Figure FDA0002963269120000031
the total space V thus obtained not only has a local space ViOf approximation, with unit decomposition
Figure FDA0002963269120000032
And a local space ViThe smoothness of the surface.
6. The deep sea pipeline crack propagation monitoring and reliability assessment method according to claim 1,
in the step 300, the divided crack subunits have a mass of 0.6 or more.
7. The deep sea pipeline crack propagation monitoring and reliability assessment method according to claim 1,
in the step 300, the process of obtaining the motion state of the crack feature point after processing the crack subunit image by using the optical flow method is as follows:
Figure FDA0002963269120000033
in the formula VxAnd VyIs the propagation rate of the crack in the x and y directions, or called I (x, y, t) luminous flux;
Figure FDA0002963269120000034
and
Figure FDA0002963269120000035
is the partial derivative of the image (x, y, t) in the corresponding direction, the relationship is as follows:
Figure FDA0002963269120000036
next, using the Lucas-Kanade algorithm, the processed crack image flow velocity vectors are satisfied:
Av＝b (6)
wherein the content of the first and second substances,
Figure FDA0002963269120000037
where q is the pixel in the window, Ix(qi)，Iy(qi),It(qi) Is the image at point qiAnd the partial derivatives of the current time with respect to position x, y and time t;
the crack length is then obtained by numerical integration, the formula being:
Figure FDA0002963269120000038
where t is the equivalent crack propagation time and α is the image scale fit coefficient associated with the deep sea camera.
8. The deep sea pipeline crack propagation monitoring and reliability assessment method according to claim 7,
in the step 300, the residual life evaluation is to establish a fatigue life degradation model by using the E-N curve parameters, and the calculation process is as follows:
Figure FDA0002963269120000041
in the formula, NfIs the fatigue life,. epsilonaIs the standard Total Strain, σ'fIs the intensity coefficient, b is the intensity index, ε'fIs the ductility factor and c is the ductility index.
9. The deep sea pipeline crack propagation monitoring and reliability assessment method according to claim 1,
in step 400, the computation process of the extreme state function is as follows:
G(x1，x2，…，xn)＝δσfm-PD (10)
where G is the safety margin for pipeline cracking, δ is the correction factor, σfIs the flow stress, m is the wall thickness, P is the internal pressure of the pipe, and D is the diameter of the pipe.
10. The deep sea pipeline crack propagation monitoring and reliability assessment method according to claim 1,
in step 400, the calculation process of the monte carlo method is as follows:
generating n groups of random number sequences or pseudo-random number sequences which accord with a basic variable probability distribution model according to a crack image of a monitored pipeline, and generating the random number sequences or the pseudo-random number sequences of the basic variable probability distribution model:
Z＝G(x)＝G(x1，x2，…，xn) (11)
and calculating the value of Z, wherein if the number of Z > 0 in the n samples is m, the residual reliability of the monitoring pipeline is as follows:
Figure FDA0002963269120000051
CN202110243661.7A 2021-03-05 2021-03-05 Deep sea pipeline crack propagation monitoring and reliability evaluation method based on image recognition Active CN113065224B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110243661.7A CN113065224B (en) 2021-03-05 2021-03-05 Deep sea pipeline crack propagation monitoring and reliability evaluation method based on image recognition

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110243661.7A CN113065224B (en) 2021-03-05 2021-03-05 Deep sea pipeline crack propagation monitoring and reliability evaluation method based on image recognition

Publications (2)

Publication Number Publication Date
CN113065224A true CN113065224A (en) 2021-07-02
CN113065224B CN113065224B (en) 2022-05-17

Family

ID=76559683

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110243661.7A Active CN113065224B (en) 2021-03-05 2021-03-05 Deep sea pipeline crack propagation monitoring and reliability evaluation method based on image recognition

Country Status (1)

Country Link
CN (1) CN113065224B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114894642A (en) * 2022-07-01 2022-08-12 湖南大学 Fatigue crack propagation rate testing method and device based on deep learning

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140100827A1 (en) * 2012-10-08 2014-04-10 Siemens Corporation Construction of entropy-based prior and posterior probability distributions with partial information for fatigue damage prognostics
US20140229149A1 (en) * 2013-01-04 2014-08-14 Siemens Corporation Probabilistic modeling and sizing of embedded flaws in ultrasonic nondestructive inspections for fatigue damage prognostics and structural integrity assessment
CN109827855A (en) * 2018-08-30 2019-05-31 长沙理工大学 Seasonality corrosion couples down Reinforced Concrete Bridge life-span prediction method with fatigue
CN109884125A (en) * 2019-02-23 2019-06-14 西安科技大学 A kind of caliberating device and scaling method based on DCPD method crack propagation signal
CN110431395A (en) * 2017-03-13 2019-11-08 通用电气公司 Fatigue crack growth prediction
WO2020089402A2 (en) * 2018-11-01 2020-05-07 Siemens Aktiengesellschaft Computer-implemented method for the probabilistic estimation of a probability of failure of a component, a data processing system, a computer program product and a computer-readable storage medium
CN111737901A (en) * 2020-06-23 2020-10-02 石家庄铁道大学 Cutter fatigue life prediction method and application thereof
CN111783243A (en) * 2020-06-18 2020-10-16 东南大学 Metal structure fatigue crack propagation life prediction method based on filtering algorithm
CN111859616A (en) * 2020-06-12 2020-10-30 中国石油天然气集团有限公司 High-pressure natural gas pipeline fracture critical dimension and service life assessment method
US20200394347A1 (en) * 2019-06-12 2020-12-17 Sichuan University Method for assessing fatigue damage and fatigue life based on abaqus

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140100827A1 (en) * 2012-10-08 2014-04-10 Siemens Corporation Construction of entropy-based prior and posterior probability distributions with partial information for fatigue damage prognostics
US20140229149A1 (en) * 2013-01-04 2014-08-14 Siemens Corporation Probabilistic modeling and sizing of embedded flaws in ultrasonic nondestructive inspections for fatigue damage prognostics and structural integrity assessment
CN110431395A (en) * 2017-03-13 2019-11-08 通用电气公司 Fatigue crack growth prediction
CN109827855A (en) * 2018-08-30 2019-05-31 长沙理工大学 Seasonality corrosion couples down Reinforced Concrete Bridge life-span prediction method with fatigue
WO2020089402A2 (en) * 2018-11-01 2020-05-07 Siemens Aktiengesellschaft Computer-implemented method for the probabilistic estimation of a probability of failure of a component, a data processing system, a computer program product and a computer-readable storage medium
CN109884125A (en) * 2019-02-23 2019-06-14 西安科技大学 A kind of caliberating device and scaling method based on DCPD method crack propagation signal
US20200394347A1 (en) * 2019-06-12 2020-12-17 Sichuan University Method for assessing fatigue damage and fatigue life based on abaqus
CN111859616A (en) * 2020-06-12 2020-10-30 中国石油天然气集团有限公司 High-pressure natural gas pipeline fracture critical dimension and service life assessment method
CN111783243A (en) * 2020-06-18 2020-10-16 东南大学 Metal structure fatigue crack propagation life prediction method based on filtering algorithm
CN111737901A (en) * 2020-06-23 2020-10-02 石家庄铁道大学 Cutter fatigue life prediction method and application thereof

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
赵一昭等: "《管道含外表面裂纹时的疲劳寿命预测研究》", 《石油机械》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114894642A (en) * 2022-07-01 2022-08-12 湖南大学 Fatigue crack propagation rate testing method and device based on deep learning
CN114894642B (en) * 2022-07-01 2023-03-14 湖南大学 Fatigue crack propagation rate testing method and device based on deep learning

Also Published As

Publication number Publication date
CN113065224B (en) 2022-05-17

Similar Documents

Publication Publication Date Title
JP6949060B2 (en) Systems and methods for rapid prediction of hydrogen-induced cracking (HIC) in pipelines, pressure vessels and piping systems and for taking action on it.
CN113075065B (en) Deep sea pipeline crack propagation monitoring and reliability evaluation system based on image recognition
US8109150B2 (en) Crack-propagation prediction method and program
Lozovan et al. Forming the toolset for development of a system to control quality of operation of underground pipelines by oil and gas enterprises with the use of neural networks
Blasón et al. A probabilistic analysis of Miner’s law for different loading conditions
Rummel Nondestructive inspection reliability history, status and future path
Shojai et al. Probabilistic modelling of pitting corrosion and its impact on stress concentrations in steel structures in the offshore wind energy
Qvale et al. Digital image correlation for continuous mapping of fatigue crack initiation sites on corroded surface from offshore mooring chain
CN110852001A (en) Bridge structure safety assessment method based on image processing
CN113065224B (en) Deep sea pipeline crack propagation monitoring and reliability evaluation method based on image recognition
Lee et al. Probabilistic flaw assessment of a surface crack in a mooring chain using the first-and second-order reliability method
CN116840135A (en) Steel gate accelerated degradation test bed with simultaneous effects of corrosion and fatigue and post-degradation running state evaluation method
Ghasemzadeh et al. Pitting corrosion identification approach based on inverse finite element method for marine structure applications
Feng et al. Effects of corrosion morphology on the fatigue life of corroded Q235B and 42CrMo steels: Numerical modelling and proposed design rules
Qi et al. A CNN-based method for concreate crack detection in underwater environments
Hamidia et al. Computer vision-based quantification of updated stiffness for damaged RC columns after earthquake
CN115496707A (en) Creep life evaluation method for local low-hardness P91 pipe fitting based on image processing technology
CN109784590B (en) In-service oil and gas pipeline corrosion prediction method based on CAGM (1,1) -BPNN
Pollock Probability of detection for acoustic emission
Keprate et al. Selecting a modeling approach for predicting remnant fatigue life of offshore topside piping
Stefaniuk et al. Preliminary findings from an NDT to FEM mapping software used for assessment of delamination-type damage
Habbal et al. Cracks Detection using Artificial Intelligence to Enhance Inspection Efficiency and Analyze the Critical Defects
Skrynkovskyy et al. V. Lozovan
Senin et al. Reinforced concrete surface cracks length detection and length estimation by using digital image processing approach
CN114943668A (en) Memory, metal pitting process identification method, device and equipment

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