CN113806902B - Artificial intelligent early warning method for pipeline corrosion - Google Patents
Artificial intelligent early warning method for pipeline corrosion Download PDFInfo
- Publication number
- CN113806902B CN113806902B CN202111178474.1A CN202111178474A CN113806902B CN 113806902 B CN113806902 B CN 113806902B CN 202111178474 A CN202111178474 A CN 202111178474A CN 113806902 B CN113806902 B CN 113806902B
- Authority
- CN
- China
- Prior art keywords
- pipeline
- corrosion
- time
- early warning
- wall thickness
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/18—Network design, e.g. design based on topological or interconnect aspects of utility systems, piping, heating ventilation air conditioning [HVAC] or cabling
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06F2119/04—Ageing analysis or optimisation against ageing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Testing Resistance To Weather, Investigating Materials By Mechanical Methods (AREA)
Abstract
The invention discloses an artificial intelligent early warning method for pipeline corrosion, and belongs to the technical field of pipeline safety. The method comprises the following steps: firstly, collecting basic data of the pipeline, judging the condition of the pipeline for continuous service, then predicting the corrosion rate and the ultrasonic side thickness estimation corrosion rate by using a long-time memory neural network, predicting the residual service life of the pipeline, judging the safe service condition of the pipeline and making a targeted warning. The method is based on the prediction of the residual life of the pipeline, adopts an artificial intelligence method to predict the future operating condition of the pipeline, gives a warning to the abnormal condition and adopts a coping method in time, so that the oil and gas field can be prevented from getting ill, and the technology support of a corrosion early warning layer is provided for the construction of the intelligent oil and gas field by applying the medicine according to the symptoms.
Description
Technical Field
The invention belongs to the technical field of pipeline safety, and particularly relates to a method for establishing artificial intelligent early warning of pipeline corrosion.
Background
In the oil gas field pipeline production operation process, pipeline corrosion can make pipe wall defect position attenuation, causes the pipeline bearing capacity to reduce, leads to pipeline corrosion inefficacy, causes the pipeline to leak, and the accident that causes often has proruption nature and disguise, can cause huge loss. Therefore, before a pipeline corrosion accident occurs, the serious corrosion defect part needs to be warned, overhauled and maintained in time, and corresponding protective measures are taken to scientifically guide the safe operation management of the pipeline.
At present, the existing corrosion early warning method still has some problems to be solved: the establishment of the corrosion early warning method usually depends on a severe network infrastructure, a complex database needs to be established as a basis, the data acquisition principle is fuzzy, the difficulty of early warning work is increased, and the operability is low; the corrosion early warning method is mainly based on the pipeline which cannot be continuously used, pipeline leakage data obtained by analysis and detection are mined, probability judgment is carried out on future corrosion conditions, pipeline accidents cannot be effectively prevented, the early warning result accuracy is low, and protection measures are lack of pertinence.
Therefore, in order to reduce the risk of pipeline corrosion accidents, an algorithm needs to be established to predict the residual service life of the pipeline, judge the safety service condition of the pipeline, determine the corrosion early warning level, and actively take corresponding measures in advance.
Disclosure of Invention
The invention aims to provide an artificial intelligent early warning method for pipeline corrosion, which aims to solve the problem of risk early warning caused by reduced pressure resistance after the pipeline is corroded.
An artificial intelligent early warning method for pipeline corrosion is characterized by comprising the following steps:
step 1: collecting basic data of the pipeline:
pipe outside diameter D w Mm; (2) inner diameter D of pipe n Mm; (3) yield strength sigma of pipe material s MPa; (4) the wall thickness d, mm of the pipeline; (5) designing pressure P and MPa of the pipeline; (6) the corrosion allowance C and mm of the pipeline; (7) pipeline production running time T s A; (8) pipeline design service life T u 。
Step 2: dividing a pipeline corrosion defect area:
detecting corrosion defects of the pipeline, and meshing the area according to the axial direction and the annular direction: axially divided into m parts and respectively C 1 、C 2 …C i …C m And n parts are annularly divided into L 1 、L 2 …L j …L n So as to discretely divide the corrosion defect into m × n wall thickness measuring points A ij (i=1、2、3…m;j=1、2、3…n);
Wherein: m is the number of axially delimited regions, C 1 、C 2 …C m Each part of the axially delimited area corresponds to an axial measuring point of one defect; n is the number of the annularly defined areas, L 1 、L 2 …L n Each part of the axially defined area corresponds to a circumferential measuring point of one defect; a. the ij M n wall thickness measurement points discretely divided for corrosion defects.
And step 3: the method comprises the following steps of:
(a) solving for axially required minimum wall thickness by equation (1)Solving the minimum wall thickness required circumferentially by formula (2)Will calculate the resultAndsubstituting formula (3) to determine the minimum required wall thickness t of the pipeline min :
In the formula:the minimum wall thickness is required in the axial direction, mm;the minimum wall thickness is required in the circumferential direction, and is mm; t is t min The minimum required wall thickness of the pipeline is mm;
(b) counting the wall thickness value a of the m multiplied by n wall thickness measuring point of the pipeline corrosion defect area ij Wherein the measurement gives the wall thickness value at the minimum is a min Solving the average value t of the wall thickness of all measured points through the formula (4) am :
In the formula: a is ij The wall thickness values of m multiplied by n measuring points which are discretely divided for corrosion defects are mm; t is t am The average value of the wall thickness of all measured points is mm;
(c) solving the residual wall thickness ratio R of the pipeline by the formula (5) t :
In the formula: r is t The ratio of the remaining wall thickness of the pipeline;
(d) solving the length L of the maximum allowable corrosion defect in the axial direction of the pipeline:
Wherein: l is the length value of the axial maximum allowable corrosion defect, mm;
(e) determining the safe service condition of the pipeline:
if La is less than or equal to L, the pipeline can be continuously in service;
if La is larger than L and tam-C is larger than or equal to 0.9tmin, the pipeline can continue to be in service;
if La is greater than L and tam-C is less than 0.9tmin, the pipeline cannot be in service continuously, the pipeline is judged to be in first-level early warning level, and the early warning mark is displayed in red;
wherein: l is a The axial length of the corrosion defect of the wall thickness section of the pipeline is mm.
And 4, step 4: predicting the residual life of the pipeline:
(a) predicting the residual life of the pipeline based on online monitoring:
1) predicting the corrosion rate of the pipeline, and specifically comprises the following steps:
arranging an on-site corrosion monitoring data set: monitoring time data set alpha (t) of a certain time period 1 、t 2 、t 3 …t n ) (ii) a Monitoring a time-corresponding corrosion rate data set beta (V) 1 、V 2 、V 3 …V n );
Wherein: t is t 1 、t 2 、t 3 …t n Monitoring time of one step length according to time sequence; v 1 、V 2 、V 3 …V n The corrosion rate monitoring value is mm/a corresponding to the monitoring time;
and secondly, observing the corrosion monitoring data set to supplement missing data:
arbitrarily take 3 times t in the corrosion monitoring time data set alpha a 、t b 、t c Taking the corresponding corrosion rate monitoring value V in the corrosion rate data set beta a 、V b 、V c Substituting equation (6) to obtain the missing time t x Corresponding corrosion rate value V x :
In the formula: t is t a 、t b 、t c For monitoring arbitrary in the time data set alphaThree times; v a 、V b 、V c For t in the corrosion rate data set beta a 、t b 、t c Corresponding corrosion rate monitoring value, mm/a; t is t x Monitoring time for absence; v x Is t x Corresponding corrosion rate, mm/a;
constructing a long-time memory neural network:
i complete corrosion monitoring dataset: monitoring time data set alpha' (t) containing missing values of corrosion data 1 、t 2 、t 3 …t x …t n ) And a corresponding corrosion rate data set β' (V) 1 、V 2 、V 3 …V x …V n ) Wherein α 'is an input value and β' is an output value;
II the internal structure of the long-time and short-time memory neural network model comprises a forgetting gate, an input gate and an output gate:
i last time t i-1 Corrosion rate monitoring of i-1 Passing through t i Forgetting gate f (t) of time-interval neural network i ) Update forgetting is performed by equation (7):
in the formula: f (t) i ) Expressed as a forgetting gate function; sigma is a neural network activation function, and a sigmoid function is selected; w is a f And u f Is a forgetting gate weight coefficient matrix; b f Is a network offset value; t is t i Predicting a time for the target;denotes t i Time data corresponding to time; t is t i-1 A certain time for monitoring the time data set α'; v i-1 Represents the corrosion rate in the corresponding corrosion rate dataset β', mm/a;
iit i corresponding time datat i-1 Time-corresponding corrosion monitoring value V i-1 Enter t i Input gate i (t) of time-lapse neural network i ) Equation (8) and alternatives
In the formula: i (t) i ) A decision coefficient representing an input gate; sigma is a neural network activation function, and a sigmoid function is selected; w is a i And u i Determining a coefficient weight coefficient matrix for the input gate; b i An offset value representing the input gate decision coefficient matrix;representing input gate alternative content; w is a c Representing an input gate alternative content weight matrix; b c A bias value representing the input gate alternate content; tanh represents a hyperbolic tangent excitation function;
iii using t i Forgetting door f (t) at time i ) And the input gate determines the coefficient i (t) i ) Alternative contentUpdating the current state of the neuron to obtain t i Temporal neuron update functionFormula (10):
in the formula:denotes t i-1 A neural update function of time;denotes t i A neural update function of time;
ivt i neuron update function of timet i Corresponding time dataAnd last time t i-1 Corrosion rate monitoring value V corresponding to time i-1 Passing through t i Time output gateEquation (11), output predicted value V of corrosion rate i Formula (12):
in the formula:represents an output gate decision coefficient; sigma represents a neural network activation function, and a sigmoid function is selected; w is a o Representing an output gate weight matrix; b is a mixture of o Represents an offset value of the output gate; v i Represents the target time t i The predicted value of the corrosion rate of (2), mm/a;
2) predicting the corrosion rate V obtained by the prediction i Minimum required wall thickness t of corroded pipeline min And the average value t of the wall thickness of all measured points am Substituting equation (13) into solving pipelineResidual Life T' L :
In the formula: t' L In order to monitor the residual service life of the pipeline on line, a;
k is a safety coefficient, and when La is less than or equal to L, the value of K is 1; when La is more than L, K is 0.9;
(b) predicting the residual life of the pipeline based on ultrasonic thickness measurement:
1) estimating pipeline corrosion rate V μ Formula (14):
in the formula: v μ For the corrosion rate estimation, mm/a; delta d is the difference of wall thickness before and after the same point thickness measurement, mm; delta T is the time difference before and after thickness measurement, a;
2) solving the pipeline to calculate the wall thickness epsilon formula (15):
in the formula: epsilon is the calculated wall thickness of the steel pipe, mm; p is design pressure, MPa; sigma s The yield strength of the steel pipe is MPa;
3) estimating the corrosion rate V μ Substituting the calculated wall thickness epsilon of the pipeline into a calculation formula (16) to solve the corrosion residual life T' L :
In the formula: t' L Measuring the residual life of the pipeline based on ultrasonic waves, a;
(b) determining the remaining life T of a pipeline L :
T L =min(T’ L ,T” L ) (17)
In the formula: t is L The remaining life of the pipeline, a.
And 5: judging the safe service condition of the pipeline:
(a) if T L ≥T u -T s If the pipeline can continue to be in service safely, the pipeline is judged to be in a five-level early warning level, and the early warning mark is displayed to be green;
(b) if T L <T u -T s Further judging the corrosion early warning level;
wherein: t is a unit of s Running time for pipeline production, a; t is u Design age, a.
Step 6: setting conditions of corrosion early warning levels:
(a) if T s <T L <T u -T s If so, judging the early warning level as four-level, and displaying the early warning mark as blue;
(b) if 10<T L <T u If so, judging the early warning level to be a third-level early warning level, and displaying the early warning mark to be yellow;
(c) if 3<T L <When 10, judging the early warning level as a secondary early warning level, and displaying an early warning mark as orange;
(d) if T L <And 3, judging as a primary early warning grade, and displaying the early warning identification in red.
And 7: early warning treatment:
(a) for the first-level early warning, the corrosion degree is very serious, and a corrosion pipeline needs to be replaced;
(b) for the secondary early warning, the corrosion degree is serious, and the pipeline needs to stop running and be repaired;
(c) for the third-level early warning, the corrosion degree is relatively heavy, and the pipeline is depressurized, operated and repaired;
(d) for the four-stage early warning, observing the corrosion condition of the pipeline;
(e) for the five-level early warning, the corrosion control condition of the pipeline is better, and the pipeline can be safely produced and operated.
The invention has the following beneficial effects:
(1) the corrosion early warning method collects pipeline basic data which are easy to obtain, establishes a pipeline residual life algorithm on the premise that the pipeline can be continuously used, simplifies corrosion early warning steps and improves system operability.
(2) The corrosion early warning method is based on the prediction of the residual service life of the pipeline, and adopts the methods of artificial intelligent soft measurement and ultrasonic thickness measurement estimation to form redundancy, so that the defect that the calculation condition of the residual service life of the pipeline is incomplete can be overcome, and the corrosion early warning accuracy is improved.
(3) The corrosion early warning method can accurately predict the residual life of the pipeline, judge the corrosion early warning level of the pipeline, is beneficial to the oil and gas field to actively control the corrosion condition of the pipeline in advance, adopts targeted protective measures, promotes the safe, economic and reliable operation of the pipeline, and provides technical support of a corrosion early warning layer for the construction of an intelligent oil and gas field.
Drawings
FIG. 1 is a flow chart of corrosion warning operations;
FIG. 2 is a flow chart of long and short memory neural network information transfer;
FIG. 3 is a schematic view of pipe corrosion defect meshing.
Detailed Description
The invention is described in detail below with reference to the drawings and the specific embodiments.
Example 1:
taking the No. 1 pipeline in the X station as an example, the pipeline is subjected to corrosion early warning. The method comprises the following specific implementation steps:
step 1: the basic data of the pipeline No. 1 are collected as follows: (1) pipe outside diameter D w1 41.3 mm; (2) inner diameter D of pipeline n1 132.5 mm; (3) yield strength sigma of pipe material s1 240 MPa; (4) wall thickness d of pipe 1 8.8 mm; (5) pipeline corrosion allowance C 1 4 mm; (6) design pressure P of pipeline 1 =20MPa。
Step 2: dividing a No. 1 pipeline corrosion defect area: detecting No. 1 pipeline corrosion defects, and meshing the area according to the axial direction and the annular direction: axially divided into 4 parts respectively of C 1 、C 2 、C 3 、C 4 And is divided circumferentially into 5 parts each of L 1 、L 2 、L 3 、L 4 、L 5 So that the corrosion defect is discretely divided into 20 wall thickness measuring points a 1×1 =9.36mm、a 1×2 =9.52mm、a 1×3 =9.12mm、a 1×4 =9.41mm、a 1×5 =9.33mm、a 2×1 =9.15mm、a 2×2 =8.86mm、a 2×3 =9.49mm、a 2×4 =8.81mm、a 2×5 =9.51mm、a 3×1 =9.57mm、a 3×2 =9.71mm、a 3×3 =9.25mm、a 3×4 =9.39mm、a 3×5 =9.26mm、a 4×1 =9.66mm、a 4×2 =9.29mm、 6 a 4×3 =9.50mm、a 4×4 =9.62mm、a 4×5 =9.52mm。
And step 3: and (3) judging the continuous service condition of the No. 1 pipeline:
(a) solving for axially required minimum wall thickness by equation (1)Solving the circumferential required minimum wall thickness by equation (2)Substituting the calculation result into the formula (3) to determine the minimum required wall thickness t of the corroded pipeline min1 =7.67mm;
(b) Counting the wall thickness values of 20 wall thickness measuring points of the No. 1 pipeline corrosion defect area, and determining that a is the smallest measured wall thickness value min1 Substituting the equation (4) for 8.81mm, and solving to obtain the average value t of the wall thickness of all the measured points am1 =9.37mm;
(c) Solving the residual wall thickness ratio R of the pipeline by the formula (5) t1 =0.63mm;
(e) Determining the safe service condition of the No. 1 pipeline: axial length L of corrosion defect on wall thickness section of No. 1 pipeline a1 80mm due to L a1 >L 1 And t is am1 -C 1 =5.37mm<0.9t min And when the pipeline is 6.903mm, the pipeline cannot be in service continuously, the pipeline is judged to be in a first-level early warning grade, and the early warning is displayed in red.
And 4, step 4: carrying out primary early warning treatment on the No. 1 pipeline: the operation is stopped and the pipeline is replaced.
Example 2:
taking the No. 2 pipeline in the X station as an example, the pipeline is subjected to corrosion early warning. The method comprises the following specific implementation steps:
step 1: the basic data of the No. 2 pipeline are collected as follows: (1) pipe outside diameter D w2 168.8 mm; (2) inner diameter D of pipe n2 157.3 mm; (3) yield strength sigma of pipe material s2 360 MPa; (4) wall thickness d of pipe 2 11.5 mm; (5) pipeline design age T u2 20 a; (6) pipeline production running time T s2 10 a; (7) pipeline corrosion allowance C 2 3.0 mm; (8) design pressure P of pipeline 2 =9.6MPa。
And 2, step: dividing a No. 2 pipeline corrosion defect area: detecting No. 2 pipeline corrosion defects, and meshing the area according to the axial direction and the annular direction: are axially divided into 4 parts which are respectively C' 1 、C’ 2 、C’ 3 、C’ 4 And 4 parts are annularly divided into L' 1 、L’ 2 、L’ 3 、L’ 4 Discrete division of corrosion defects into 16 wall thickness measurement points, respectively a' 1×1 =12.55mm、a’ 1×2 =13.58mm、a’ 1×3 =14.87mm、a’ 1×4 =14.38mm、a’ 2×1 =11.84mm、a’ 2×2 =13.48mm、a’ 2×3 =14.33mm、a’ 2×4 =14.35mm、a’ 3×1 =11.76mm、a’ 3×2 =13.78mm、a’ 3×3 =16.50mm、a’ 3×4 =15.10mm、a’ 4×1 =11.27mm、a’ 4×2 =13.44mm、a’ 4×3 =15.92mm、a’ 4×4 =15.28mm。
And 3, step 3: and (3) judging the continuous service condition of the No. 2 pipeline:
(a) solving for axially required minimum wall thickness by equation (1)The minimum wall thickness is required circumferentially by the formula (2)Substituting the calculation result into formula (3) to determine the minimum required wall thickness t of the corrosion pipeline min2 =2.91mm;
(b) Counting the wall thickness values of 16 wall thickness measuring points of No. 2 pipeline corrosion defect area, and determining that a is the smallest measured wall thickness value min2 Substituting the equation (4) to obtain the average value t of the wall thickness of all the measured points am2 =13.90mm;
(c) Solving the residual wall thickness ratio R of the pipeline through the formula (5) t2 =2.84mm;
(d) Due to R t2 Not less than 0.793, the maximum allowable axial corrosion defect length of No. 2 pipeline
(e) Determining the safe service condition of the No. 2 pipeline: axial length L of No. 2 pipeline wall thickness section corrosion defect a2 80mm due to L a1 ≤L 1 The pipeline may continue to be in service.
And 4, step 4: and (3) predicting the residual life of the No. 2 pipeline:
(a) and predicting the residual life of the No. 2 pipeline based on online monitoring:
1) predicting the corrosion rate of the pipeline, and specifically comprises the following steps:
arranging an on-site corrosion monitoring data set: data set alpha of monitoring time from 1/2018 to 1/7/2021 2 (1/2018, 2/1/2018, 3/1/2018, … 2019/4/1/2019, 6/1/2019, … 2021/7/1/2011); monitoring time-corresponding corrosion rate data set beta 2 (0.01367mm/a, 0.04719mm/a, 0.03254mm/a … 0.0423.0423 mm/a, 0.05478mm/a … 0.05718mm/a) are shown in Table 1:
table 12 corrosion monitoring data for pipe 2018, month 1, and year 2021, month 7, and day 1
α 2 Time set | β 2 Set of corrosion rates (mm/a) |
1 month and 1 day in 2018 | 0.01367 |
2.2018, 1 month and 2 days | 0.04719 |
Year 2018, month 3 and |
0.03254 |
… | … |
4 month and 1 day of 2019 | 0.04230 |
6 months and 1 day in 2019 | 0.05478 |
… | … |
|
0.05718 |
(vii) observe table 1 corrosion monitoring dataset replenishment missing data: in Table 1, 2 corrosion rate deletions in total need to be supplemented, which are respectively the corrosion rate values of No. 2 pipeline in 2019 in 5 months and 1 dayV x Corrosion rate V of 1/3/2020 x ′:
First, monitoring time data t of 2019, 4 months and 1 day is extracted a 401 and corresponding etch Rate V a 0.0423 mm/a; monitoring time data t of 6 months and 1 day in 2019 b 601 and corresponding corrosion rate V b 0.05478 mm/a; monitoring time data t of 7 months and 1 day in 2019 c 701 and corresponding etch rate V c 0.02537mm/a, the above numerical substitution formula (7) supplements and calculates the time data t of 2019 in 5 months x Corrosion rate value V of 501 x :
Similarly, extracting data t of monitoring time of 2 months and 1 day of 2020 a ' (201) and corresponding corrosion rate value V a ' -0.0233 mm/a,; monitoring time data t of 2020, 4 months and 1 day b 401 and corresponding corrosion rate value V b ' -0.04523 mm/a; monitoring time data t of 2020, 5 months and 1 day c ' (501) and corresponding corrosion rate value V c ' 0.03754mm/a, the above numerical value is substituted into formula (7) to complement and calculate the monitoring time data t of 3 months in 2020 x Corrosion rate value V corresponding to' 301 x ′=0.0179mm/a;
Constructing a long-time memory neural network, and specifically comprising the following steps:
i complete pipeline No. 2 corrosion monitoring dataset: monitoring time data set alpha 'containing corrosion data missing value' 2 (1/2018/2/1/2018/3/1/… 2019/5/1/20184/… 2020/3/1/… 2021/7/1/2018), monitoring the time-dependent corrosion rate dataset β' 2 (0.01367mm/a、0.04719mm/a、
0.03254mm/a … 0.033.033 mm/a … 0.0179mm/a … 0.05718mm/a) see table 2, where α 'is the input value and β' is the output value;
table 22 complete corrosion monitoring data for conduit No. 2018, month 1, to 2021, month 7, day 1
Input value of alpha' 2 | Output value of beta' 2 (mm/a) |
1 month and 1 day in 2018 | 0.01367 |
2 month and 1 day of 2018 | 0.04719 |
3 month and 1 day of 2018 | 0.03254 |
… | … |
4 month and 1 day of 2019 | 0.04230 |
5 months and 1 day in 2019 | 0.03300 |
6.2019, 1 month | 0.05478 |
… | … |
2020, 3 months and 1 day | 0.01790 |
… | … |
2020, 7 month and 1 day | 0.05718 |
II long-time memory neural network model inner structure contains forgetting gate, input gate, output gate:
iI with 1 month as step length, corrosion rate monitoring value V corresponding to the time data 101 in 2018, 1 month and 1 day 101 0.01367(mm/a) in 2018, 2/1 day and time data x t2 Forgetting gate f (t) of long-time and short-time neural network as 201 201 ) Carry over into (8) and update forgetting:
f(201)=sigmod(w f *0.1367+u f *201+b f ) (8)
ii time data corresponding to 2 month and 1 day of 2018Corrosion monitoring value V corresponding to time data 101 of 1 month and 1 day in 2018 101 Input gate i (201) of long-term neural network with 0.01367(mm/a) entry time data 201, formula (9) and alternative content
i(201)=sigmod(w i *0.1367+u i *201+b i ) (9)
iii forgetting gate f (201) and input gate determination coefficient i (201) using 2018 year 2 month 1 day time data 210, and candidate contentUpdating the current state of the neuron to obtain a neuron updating function C of the data 201 of 2 months and 1 day in 2018 201 Formula (11):
neuron update function C of 2 month and 1 day in IV2018 201 The corrosion rate monitoring value V corresponding to the data 201 of the time 8 of 1 day of 2 months in 2018 and the data 101 of the last time 101 0.01367(mm/a) output gate O of elapsed time data 201 201 Equation (12), the predicted value V of the corrosion rate of 2018, 2 months and 1 day is output 201 0.0028mm/a formula (13):
O 201 =sigmod(w o *0.01367+u o *201+b o ) (12)
V 201 =O 201 ·tanh(C 201 ) (13)
2) predicting the corrosion rate by a value V 201 0.028mm/a, minimum required wall thickness t min2 2.91mm and the average value t of the wall thickness of all measured points am2 Carry-in (14) to solve No. 2 pipeline residual life 13.90mmWherein L is a ≤L,K 2 The value is 1;
(b) and predicting the residual life of the No. 2 pipeline based on ultrasonic thickness measurement:
1) wall thickness d of the pipe 2 11.5mm, minimum wall thickness measurement a min2 11.27mm and production run time T s2 Substitution of 10a into equation (14) estimates the etch rate V μ2 =0.023mm/a;
2) Design pressure P of pipeline 2 Outer diameter of 9.6MPa 10 D w2 168.8mm, yield strength σ s2 360MPa and corrosion allowance C 2 Calculation of wall thickness epsilon by substituting 3.0mm into equation (15) 2 =4.17mm;
3) Calculating the result V μ2 0.023mm/a and epsilon 2 Solving residual life T in equation (16) substituted for 4.17mm " L2 =308.7a;
(c) Determination of No. 2 pipeline residual life T by formula (17) L :T L2 =min(T’ L2 ,T” L2 )=308.7a。
And 5: and (3) judging the safe service condition of the No. 2 pipeline: due to T L2 ≥T u2 -T s2 If the pipeline is 10a, the pipeline can continue to be safely serviced, the pipeline is judged to be in a five-level early warning level, and the early warning mark is displayed to be green.
And 6: the No. 2 pipeline carries out five-stage early warning treatment: the corrosion control condition of the pipeline is better, and the pipeline can be produced and operated safely.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and should not be taken as limiting the scope of the present invention, which is intended to cover any modifications, equivalents, improvements, etc. within the spirit and scope of the present invention.
Claims (1)
1. An artificial intelligent early warning method for pipeline corrosion is characterized by comprising the following steps:
step 1: collecting basic data of the pipeline:
pipe outside diameter D w Mm; (2) inner diameter D of pipeline n Mm; (3) yield strength sigma of pipe material s MPa; (4) the wall thickness d of the pipeline is mm; (5) the design pressure P, MPa of the pipeline; (6) the corrosion allowance C, mm of the pipeline; (7) pipeline production run time T s A; (8) pipeline design service life T u ;
And 2, step: dividing a pipeline corrosion defect area:
detecting corrosion defects of the pipeline, and meshing the areas according to the axial direction and the annular direction: axially divided into m parts respectively of C 1 、C 2 …C i …C m And n parts are divided annularly into L 1 、L 2 …L j …L n So as to discretely divide the corrosion defect into m × n wall thickness measuring points A ij (i=1、2、3…m;j=1、2、3…n);
Wherein: m is the number of axially defined regions, C 1 、C 2 …C m Each part of the axially delimited area corresponds to an axial measuring point of a defect; n is the number of the annularly defined regions, L 1 、L 2 …L n Each part of the axially defined area corresponds to a circumferential measuring point of one defect; a. the ij M x n wall thickness measurement points discretely divided for corrosion defects;
and step 3: the method comprises the following steps of:
(a) solving for axially required minimum wall thickness by equation (1)Solving the circumferential required minimum wall thickness by equation (2)The calculated result is processedAndsubstituting formula (3) to determine the minimum required wall thickness t of the pipeline min :
In the formula:minimum wall thickness, mm, is required for the axial direction;the minimum wall thickness is required in the circumferential direction and is mm; t is t min The minimum required wall thickness of the pipeline is mm;
(b) statistics ofWall thickness value a of m multiplied by n wall thickness measuring point of pipeline corrosion defect area ij Wherein the measurement gives the wall thickness value at the minimum is a min Solving the average value t of the wall thickness of all measured points through the formula (4) am :
In the formula: a is ij The wall thickness values of m multiplied by n measuring points which are discretely divided for corrosion defects are mm; t is t am The average value of the wall thickness of all measured points is mm;
(c) solving the residual wall thickness ratio R of the pipeline through the formula (5) t :
In the formula: r is t The residual wall thickness ratio of the pipeline is used;
(d) solving the length L of the maximum allowable corrosion defect of the axial direction of the pipeline:
Wherein: l is the length value of the axial maximum allowable corrosion defect, and is mm;
(e) determining the safe service condition of the pipeline:
if La is less than or equal to L, the pipeline can be continuously in service;
if La is greater than L and tam-C is more than or equal to 0.9tmin, the pipeline can continue to be in service;
if La is larger than L and tam-C is smaller than 0.9tmin, the pipeline cannot be in service continuously, the pipeline is judged to be in a first-level early warning level, and the early warning mark is displayed in red;
wherein: l is a The axial length of the corrosion defect of the wall thickness section of the pipeline is mm;
and 4, step 4: predicting the residual life of the pipeline:
(a) predicting the residual life of the pipeline based on online monitoring:
1) predicting the corrosion rate of the pipeline, and specifically comprises the following steps:
firstly, arranging an on-site corrosion monitoring data set: monitoring time data set alpha (t) of a certain time period 1 、t 2 、t 3 …t n ) (ii) a Monitoring a time-corresponding corrosion rate data set beta (V) 1 、V 2 、V 3 …V n );
Wherein: t is t 1 、t 2 、t 3 …t n The monitoring time is separated by one step according to time sequence; v 1 、V 2 、V 3 …V n The corrosion rate monitoring value corresponding to the monitoring time is mm/a;
and (5) observing corrosion monitoring data set supplement missing data:
arbitrarily take 3 times t in the corrosion monitoring time data set alpha a 、t b 、t c Taking the corresponding corrosion rate monitoring value V in the corrosion rate data set beta a 、V b 、V c Substituting equation (6) to obtain the missing time t x Corresponding corrosion rate value V x :
In the formula: t is t a 、t b 、t c Monitoring any three times in the time data set alpha; v a 、V b 、V c For t in the corrosion rate data set beta a 、t b 、t c Corresponding corrosion rate monitoring value, mm/a; t is t x Monitoring time for absence; v x Is t x Corresponding corrosion rate, mm/a;
constructing a long-time memory neural network:
i complete corrosion monitoring dataset: involving corrosion data lossMonitoring time data set of values α' (t) 1 、t 2 、t 3 …t x …t n ) And a corresponding corrosion rate data set β' (V) 1 、V 2 、V 3 …V x …V n ) Wherein α 'is an input value and β' is an output value;
II long-time memory neural network model inner structure contains forgetting gate, input gate, output gate:
i last time t i-1 Corrosion rate monitoring of i-1 Passing through t i Forgetting gate f (t) of time-interval neural network i ) Update forgetting is performed by equation (7):
in the formula: f (t) i ) Expressed as a forgetting gate function; sigma is a neural network activation function, and a sigmoid function is selected; w is a f And u f Is a forgetting gate weight coefficient matrix; b f Is the network offset value; t is t i Predicting a time for the target;represents t i Time data corresponding to time; t is t i-1 A certain time for monitoring the time data set α'; v i-1 Represents the corrosion rate in the corresponding corrosion rate dataset β', mm/a;
iit i corresponding time datat i-1 Time-corresponding corrosion monitoring value V i-1 Enter t i Input gate i (t) of time-lapse neural network i ) Equation (8) and alternativesFormula (9):
in the formula: i (t) i ) A decision coefficient representing an input gate; sigma is a neural network activation function, and a sigmoid function is selected; w is a i And u i Determining a coefficient weight coefficient matrix for the input gate; b i An offset value representing the input gate decision coefficient matrix;representing input gate alternative content; w is a c Representing an input gate candidate content weight matrix; b c A bias value representing the input gate alternate content; tanh represents a hyperbolic tangent excitation function;
iii using t i Forgetting door f (t) of time i ) And the input gate determines the coefficient i (t) i ) Alternative contentUpdating the current state of the neuron to obtain t i Temporal neuron update function C ti Formula (10):
in the formula:denotes t i-1 A neural update function of time;denotes t i A neural update function of time;
ivt i neuron update function of timet i Corresponding time dataAnd last time t i-1 Corrosion rate monitoring value V corresponding to time i-1 Passing through t i Time output gateEquation (11), output predicted value V of corrosion rate i Formula (12):
in the formula:representing an output gate decision coefficient; sigma represents a neural network activation function, and a sigmoid function is selected; w is a o Representing an output gate weight matrix; b is a mixture of o A bias value representing an output gate; v i Represents a target time t i The predicted value of the corrosion rate of (1), mm/a;
2) predicting the corrosion rate V obtained by the prediction i Minimum required wall thickness t of corroded pipeline min And the average value t of the wall thickness of all measured points am Substituting formula (13) to solve pipeline residual life T' L :
In the formula: t' L For monitoring the residual life of pipeline on lineMin, a;
k is a safety coefficient, and when La is less than or equal to L, the value of K is 1; when La is more than L, K takes the value of 0.9;
(b) predicting the residual life of the pipeline based on ultrasonic thickness measurement:
1) estimating pipeline corrosion rate V μ Formula (14):
in the formula: v μ For corrosion rate estimation, mm/a; delta d is the difference of wall thickness before and after the same point thickness measurement, mm; delta T is the time difference before and after thickness measurement, a;
2) solving the pipeline to calculate the wall thickness epsilon formula (15):
in the formula: epsilon is the calculated wall thickness of the steel pipe, mm; p is design pressure, MPa; sigma s The yield strength of the steel pipe is MPa;
3) estimating the corrosion rate V μ Substituting the calculated wall thickness epsilon of the pipeline into a calculation formula (16) to solve the corrosion residual life T ″) L :
In the formula: t ″) L Measuring the residual life of the pipeline based on ultrasonic waves, a;
(b) determining the remaining life T of a pipeline L :
T L =min(T′ L ,T″ L ) (17)
In the formula: t is L Residual life of the pipeline, a;
and 5: judging the safe service condition of the pipeline:
(a) if T L ≥T u -T s Then the pipeline can continue to be in service safely and judgeSetting as a five-level early warning grade, and displaying the early warning mark as green;
(b) if T L <T u -T s Further judging the corrosion early warning level;
wherein: t is a unit of s For the pipeline production run time, a; t is u To design age, a;
and 6: setting conditions of corrosion early warning levels:
(a) if T s <T L <T u -T s If so, judging the early warning level as four-level, and displaying the early warning mark as blue;
(b) if 10<T L <T u If so, judging the early warning level to be a third-level early warning level, and displaying the early warning mark to be yellow;
(c) if 3<T L <When 10, judging the early warning level as a secondary early warning level, and displaying an early warning mark as orange;
(d) if T is L <3, judging the early warning level as the first-level early warning level, and displaying the early warning mark as red;
and 7: early warning treatment:
(a) for the first-level early warning, the corrosion degree is very serious, and a corrosion pipeline needs to be replaced;
(b) for the secondary early warning, the corrosion degree is serious, and the pipeline needs to stop running and be repaired;
(c) for the third-level early warning, the corrosion degree is relatively heavy, and the pipeline is depressurized, operated and repaired;
(d) for the four-stage early warning, observing the corrosion condition of the pipeline;
(e) for the five-level early warning, the corrosion control condition of the pipeline is better, and the pipeline can be safely produced and operated.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111178474.1A CN113806902B (en) | 2021-10-10 | 2021-10-10 | Artificial intelligent early warning method for pipeline corrosion |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111178474.1A CN113806902B (en) | 2021-10-10 | 2021-10-10 | Artificial intelligent early warning method for pipeline corrosion |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113806902A CN113806902A (en) | 2021-12-17 |
CN113806902B true CN113806902B (en) | 2022-08-19 |
Family
ID=78939409
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111178474.1A Active CN113806902B (en) | 2021-10-10 | 2021-10-10 | Artificial intelligent early warning method for pipeline corrosion |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113806902B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114278873B (en) * | 2021-12-23 | 2022-09-16 | 天津大学 | Remote monitoring method for pipeline fault |
CN115614678B (en) | 2022-12-16 | 2023-03-10 | 成都秦川物联网科技股份有限公司 | Intelligent gas pipeline electrochemical corrosion assessment method, internet of things system and medium |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103455682B (en) * | 2013-09-12 | 2019-04-26 | 西南石油大学 | A method of prediction hp-ht well corrosion set pipe residue lifetime |
CN107290270B (en) * | 2017-07-01 | 2019-09-06 | 西南石油大学 | A kind of corrosion life prediction technique for casing |
CN110309577B (en) * | 2019-06-26 | 2022-10-11 | 西安建筑科技大学 | Submarine pipeline residual life prediction method based on IM and LMLE-BU algorithm |
CN112184320B (en) * | 2020-10-09 | 2022-07-22 | 焦点科技股份有限公司 | AI-based intelligent operation detection and operation and maintenance method for operation and maintenance data of commercial website |
CN112883538B (en) * | 2020-12-29 | 2022-07-22 | 浙江中控技术股份有限公司 | Corrosion prediction system and method for buried crude oil pipeline |
CN113239504B (en) * | 2021-06-30 | 2022-01-28 | 西南石油大学 | Pipeline corrosion defect prediction method based on optimized neural network |
-
2021
- 2021-10-10 CN CN202111178474.1A patent/CN113806902B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN113806902A (en) | 2021-12-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113806902B (en) | Artificial intelligent early warning method for pipeline corrosion | |
WO2020063819A1 (en) | Real-time data analysis method for pipe network, and device | |
WO2022252505A1 (en) | Device state monitoring method based on multi-index cluster analysis | |
US11488010B2 (en) | Intelligent analysis system using magnetic flux leakage data in pipeline inner inspection | |
CN113239504B (en) | Pipeline corrosion defect prediction method based on optimized neural network | |
CN113588179B (en) | Water supply network leakage detection method and system | |
CN101915728A (en) | Testing method for predicting residual service life of buried metal water supply pipeline | |
CN109815595B (en) | Underground pipe column of oil and gas field and hydrogen sulfide corrosion big data analysis method of wellhead gas transmission pipeline | |
CN117407827B (en) | Abnormal operation data detection method for purification engineering waste gas purification equipment | |
Shaik et al. | Remaining useful life prediction of a piping system using artificial neural networks: A case study | |
CN110689051A (en) | Intelligent identification method for corrosion mode in gas pipeline based on transfer learning | |
CN113468757A (en) | Method for evaluating reliability of corroded natural gas pipeline based on fuzzy random theory | |
CN111312414B (en) | Fatigue evaluation method of nuclear power plant fatigue monitoring and life evaluation system | |
CN115481940A (en) | Oil and gas pipeline area risk monitoring system based on big data | |
CN114638164A (en) | Method for predicting high-temperature creep life of pressure pipeline of power station | |
CN115830812B (en) | Intelligent early warning system and method for abnormal settlement of pump station building | |
CN116266277A (en) | Automatic overflow identification and early warning method | |
CN116452191A (en) | Intelligent rural water supply data collection and analysis system and method based on big data | |
CN115681828A (en) | Method for identifying and positioning pipe network leakage in urban gas based on big data | |
Padhil et al. | Risk Analysis of Water Distribution in PDAM City of Makassar Using the House of Risk (HOR) Method | |
CN103984845A (en) | Method and system for calculating gas pipeline completeness evaluation period | |
Xing et al. | Streaming sensor data validation in networked infrastructure systems through synergic auto and cross similarity discovery and analysis | |
CN111144002B (en) | Method for predicting pipe burst of grey cast iron pipe of water supply pipe network | |
Uruchurtu-Chavarin et al. | Artificial intelligence for the assessment on the corrosion conditions diagnosis of transmission line tower foundations | |
CN117807854B (en) | Bridge monitoring deflection and temperature separation method based on physical constraint neural network |
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 |