CN112729688A - Oil-gas pipeline leakage detection method based on vibration and temperature double parameters - Google Patents
Oil-gas pipeline leakage detection method based on vibration and temperature double parameters Download PDFInfo
- Publication number
- CN112729688A CN112729688A CN202110034057.3A CN202110034057A CN112729688A CN 112729688 A CN112729688 A CN 112729688A CN 202110034057 A CN202110034057 A CN 202110034057A CN 112729688 A CN112729688 A CN 112729688A
- Authority
- CN
- China
- Prior art keywords
- sample
- vibration
- detected
- temperature
- data
- 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
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 46
- 238000012544 monitoring process Methods 0.000 claims abstract description 20
- 239000013598 vector Substances 0.000 claims description 108
- 238000012360 testing method Methods 0.000 claims description 46
- 239000013307 optical fiber Substances 0.000 claims description 33
- 238000012549 training Methods 0.000 claims description 28
- 238000000034 method Methods 0.000 claims description 17
- 238000001228 spectrum Methods 0.000 claims description 9
- 230000003287 optical effect Effects 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 6
- 230000009977 dual effect Effects 0.000 claims description 5
- 238000010801 machine learning Methods 0.000 abstract description 5
- 238000005516 engineering process Methods 0.000 description 9
- 238000002360 preparation method Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 3
- 241000287196 Asthenes Species 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M3/00—Investigating fluid-tightness of structures
- G01M3/002—Investigating fluid-tightness of structures by using thermal means
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17D—PIPE-LINE SYSTEMS; PIPE-LINES
- F17D5/00—Protection or supervision of installations
- F17D5/02—Preventing, monitoring, or locating loss
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17D—PIPE-LINE SYSTEMS; PIPE-LINES
- F17D5/00—Protection or supervision of installations
- F17D5/02—Preventing, monitoring, or locating loss
- F17D5/06—Preventing, monitoring, or locating loss using electric or acoustic means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M3/00—Investigating fluid-tightness of structures
- G01M3/02—Investigating fluid-tightness of structures by using fluid or vacuum
- G01M3/04—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point
- G01M3/24—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point using infrasonic, sonic, or ultrasonic vibrations
- G01M3/243—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point using infrasonic, sonic, or ultrasonic vibrations for pipes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Mechanical Engineering (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Acoustics & Sound (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medical Informatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Examining Or Testing Airtightness (AREA)
Abstract
The invention discloses an oil-gas pipeline leakage detection method based on vibration and temperature double parameters, which is characterized in that effective characteristic values are extracted from data in two aspects of time domain and frequency domain based on vibration data and temperature data of an oil-gas pipeline, a machine learning method is utilized, a proper classifier model is selected from the data, the oil-gas pipeline leakage state is identified according to the extracted characteristic values, and the missing report rate and the false report rate of oil-gas pipeline leakage monitoring are effectively reduced.
Description
Technical Field
The invention relates to the technical field of distributed optical fiber sensing, in particular to an oil and gas pipeline leakage detection method based on vibration and temperature double parameters.
Background
Oil and gas pipelines often have the characteristics of long distance and very complicated laying place and environment, and the pipelines can pass through various terrains and areas such as mountains, rivers, lakes and the like. In such complicated environment, the oil and gas pipeline can receive diversified external influences through long-term operation, like external local corrosion, third party construction destruction, natural disasters etc. the leakage problem appears in the high possibility. Once the oil and gas pipeline leaks, the resulting consequences are very serious. Firstly, oil and gas pipeline leakage can cause loss of oil and gas resources, and secondly, if the oil and gas pipeline leaks near the country or suburb, casualty accidents can also be caused. And a large amount of manpower and financial resources are needed for processing the industrial pollution and casualty accidents, so that the damage degree of the pipeline leakage is further deepened to a certain extent.
At present, the technologies for detecting the leakage of the oil and gas pipeline mainly comprise a distributed optical fiber temperature sensing technology and a distributed optical fiber vibration sensing technology. The temperature measuring device and the temperature measuring method respectively realize the measurement of the pipeline leakage by measuring the temperature or the vibration condition of optical fibers arranged around the pipeline caused by the pipeline leakage. Although distributed optical fiber sensing technology has been used in some engineering applications in such monitoring fields, there are two main problems with this method: the first problem is that the false alarm rate or the false negative rate is high. When the distributed optical fiber temperature sensing technology is used for detection, as the sensing signal is weak, when the leakage amount is small and the temperature change near a leakage pipeline is small, accidents are difficult to find in time and report is missed; on the other hand, when the distributed optical fiber vibration sensing technology is used for detection, the signal is very sensitive to external micro vibration, so that false alarm is very easily caused when strong vibration interference exists near the pipeline. The second problem is that leak event identification accuracy is to be improved. The signal change of the optical fiber sensing system can be caused by various external factors, and the conventional optical fiber sensing system can only accurately obtain the specific change of the corresponding optical signal at present, so that the accurate detection of the leakage of the oil and gas pipeline is difficult to realize.
Disclosure of Invention
Aiming at the problems, the invention provides an oil and gas pipeline leakage detection method based on vibration and temperature double parameters, so that the false alarm rate and the false alarm rate of oil and gas pipeline leakage monitoring are reduced, and the identification accuracy is improved.
In order to realize the purpose of the invention, an oil-gas pipeline leakage detection method based on vibration and temperature double parameters is provided by acquiring temperature data and vibration data simultaneously, extracting temperature data characteristics and vibration data characteristics from the temperature data and vibration data respectively, combining the characteristics, training a classifier model by using a machine learning method, and finally performing event identification by using the trained classifier model to implement leakage monitoring on an oil-gas pipeline, and comprises the following steps:
s10, arranging optical fibers around the oil and gas pipeline, obtaining a plurality of vibration information by using Rayleigh scattering light in the optical fibers, obtaining a plurality of temperature information by using Brillouin scattering light in the optical fibers, and obtaining the current pipeline state of the oil and gas pipeline, so as to obtain sample vibration information, sample temperature information and sample state of the oil and gas pipeline; the pipeline state comprises a leakage state and a non-leakage state;
s20, obtaining a plurality of description features of the sample temperature information, and forming a sample temperature feature vector by the description features of the sample temperature information;
s30, obtaining a plurality of description features of the sample vibration information, and forming a sample vibration feature vector by each description feature of the sample vibration information;
s40, combining the sample temperature characteristic vector and the sample vibration characteristic vector into a sample characteristic vector, and determining a sample label of the sample characteristic vector according to the sample state;
s50, returning to execute the steps S10-S40 until the obtained sample feature vectors exceed the quantity threshold, and dividing all the sample feature vectors and the sample labels corresponding to the sample feature vectors into a training data set and a testing data set; the training data set comprises a plurality of sample characteristic vectors and sample labels corresponding to the sample characteristic vectors; the test data set comprises a plurality of sample characteristic vectors and sample labels corresponding to the sample characteristic vectors;
s60, training an initial classifier by adopting a training data set to obtain an initial detection model, respectively inputting each sample feature vector of a test data set into the initial detection model to obtain a test result of each sample feature vector in the test data set, comparing the test result of each sample feature vector in the test data set with a sample label to obtain a test accuracy, and determining the initial detection model as a leakage detection model if the test accuracy is greater than or equal to an accuracy threshold;
and S70, acquiring temperature data and vibration data in the leakage monitoring operation of the oil-gas pipeline to obtain temperature data to be detected and vibration data to be detected, acquiring a characteristic vector to be detected according to the temperature data to be detected and the vibration data to be detected, inputting the characteristic vector to be detected into the leakage detection model to identify the pipeline state represented by the characteristic vector to be detected, and realizing the detection of the leakage of the oil-gas pipeline.
In one embodiment, after the optical fiber is arranged around the oil and gas pipeline, the method further comprises the following steps:
and collecting optical signals in the optical fiber, and sequentially carrying out frequency division, demodulation and fitting processing on the optical signals to obtain Rayleigh scattered light and Brillouin scattered light.
In one embodiment, the obtaining the feature vector to be measured according to the temperature data to be measured and the vibration data to be measured includes:
acquiring a plurality of description characteristics of temperature data to be detected, and forming a temperature characteristic vector to be detected by using each description characteristic of the temperature data to be detected;
the method comprises the steps of obtaining a plurality of description features of vibration data to be detected, combining the description features of the vibration data to be detected into a vibration feature vector to be detected, and combining a temperature feature vector to be detected and the vibration feature vector to be detected into a feature vector to be detected.
Specifically, the descriptive characteristics of the sample temperature information or the descriptive characteristics of the temperature data to be measured include the range, the standard deviation, the average value, the maximum value, and the third-order origin moment.
Specifically, the description characteristics of the sample vibration information or the description characteristics of the vibration data to be detected include a range, a standard deviation, a strongest frequency, and a ratio of a primary peak to a secondary peak of a frequency spectrum.
The technical scheme of the invention has the following beneficial effects:
by utilizing the distributed optical fiber sensing technology, the distributed measurement of vibration and temperature along the oil-gas pipeline is realized, the variation parameters caused by leakage of the oil-gas pipeline are fully obtained, comprehensive sensing information is provided for leakage state identification, and the report missing rate of leakage monitoring can be effectively reduced.
The characteristic vectors of the temperature and vibration data are respectively extracted from the time domain and the frequency domain, and the leakage monitoring of the oil and gas pipeline is implemented by using a machine learning method, so that the false alarm rate of the leakage monitoring can be effectively reduced.
Drawings
FIG. 1 is a flow chart of an embodiment of a vibration and temperature dual parameter based oil and gas pipeline leak detection method;
FIG. 2 is a flow chart of a vibration and temperature dual parameter based oil and gas pipeline leak detection method according to another embodiment;
FIG. 3 is a diagram of a confusion matrix for a trained classifier model under test in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
Referring to fig. 1, fig. 1 is a flowchart of an embodiment of a method for detecting leakage of an oil and gas pipeline based on vibration and temperature dual parameters, including the following steps:
s10, arranging optical fibers around the oil and gas pipeline, obtaining a plurality of vibration information by using Rayleigh scattering light in the optical fibers, obtaining a plurality of temperature information by using Brillouin scattering light in the optical fibers, and obtaining the current pipeline state of the oil and gas pipeline, so as to obtain sample vibration information, sample temperature information and sample state of the oil and gas pipeline; the pipeline state comprises a leakage state and a non-leakage state;
in one embodiment, after the optical fiber is arranged around the oil and gas pipeline, the method further comprises the following steps:
and collecting optical signals in the optical fiber, and sequentially carrying out frequency division, demodulation and fitting processing on the optical signals to obtain Rayleigh scattered light and Brillouin scattered light.
The optical fibers can be arranged around the oil and gas pipeline, vibration information is obtained by utilizing Rayleigh scattering light in the optical fibers through processing processes of data acquisition, frequency division, demodulation, fitting and the like, and temperature information is obtained by utilizing Brillouin scattering light in the optical fibers, so that the vibration and temperature information of the pipeline can be measured simultaneously. The vibration and temperature information of the pipeline can be measured, and meanwhile, the oil and gas pipeline can be subjected to exploration and other processing, so that the current pipeline state of the oil and gas pipeline can be determined.
And S20, acquiring a plurality of description features of the sample temperature information, and forming the description features of the sample temperature information into a sample temperature feature vector.
The descriptive characteristics are independently observable attributes or characteristics of observed data (such as sample temperature information or sample vibration information), represent complex observed objects or data through an abstract and simplified mathematical concept, and are characterized by information quantity, distinctiveness and independence. Specifically, the description features of the observed data can be extracted from a plurality of aspects such as time domain, frequency domain, time-space domain, time-frequency domain and the like, and generally take other forms such as numerical values rather than characters and the like, and the inherent and inherent properties of the data can be embodied. The single feature information of the observed data can be called a description feature, and a plurality of description features can be combined into a feature vector of the observed data and characterize the data. Specifically, if the observed data is sample temperature information, each description feature of the sample temperature information may include a range, a standard deviation, an average value, a maximum value, and a third-order origin moment, and in this case, the above step may extract 5 features of the data range, the standard deviation, the average value, the maximum value, and the third-order origin moment from the extracted temperature data (sample temperature information). The 5 features are all based on time domain features of temperature, and the obtained 5 feature values are combined into a one-dimensional vector form.
And S30, acquiring a plurality of description features of the sample vibration information, and forming the plurality of description features of the sample vibration information into a sample vibration feature vector.
Specifically, if the observed data is sample vibration information, each description feature of the sample temperature information may include a range, a standard deviation, a strongest frequency, and a ratio of a primary peak to a secondary peak of a frequency spectrum, and in this case, the above step may extract 4 features of the range, the standard deviation, the strongest frequency, and the ratio of the primary peak to the secondary peak of the frequency spectrum from the extracted vibration data (sample vibration information). The data range and standard deviation are based on the time domain data of vibration, the strongest frequency and the ratio of the main peak to the secondary peak of the frequency spectrum are based on the frequency spectrum data of vibration, and the obtained 4 characteristic values form a one-dimensional vector form.
And S40, combining the sample temperature characteristic vector and the sample vibration characteristic vector into a sample characteristic vector, and determining a sample label of the sample characteristic vector according to the sample state.
This step may combine the one-dimensional vectors of S20 and S30 from left to right to form a new one-dimensional vector containing 9 data feature values.
S50, returning to execute the steps S10-S40 until the obtained sample feature vectors exceed the quantity threshold, and dividing all the sample feature vectors and the sample labels corresponding to the sample feature vectors into a training data set and a testing data set; the training data set comprises a plurality of sample characteristic vectors and sample labels corresponding to the sample characteristic vectors; the test data set includes a plurality of sample feature vectors and sample labels corresponding to the respective sample feature vectors.
The number threshold may be set to a large value such as 800. This step repeats steps S10 to S40, and constructs a data set with the result in step S40 until the amount of data in the data set is sufficient. The determination of the data amount is empirically determined, and typically several hundred groups are selected, and then may be continuously adjusted according to the result of the subsequent step S60.
S60, training the initial classifier by adopting the training data set to obtain an initial detection model, inputting each sample feature vector of the test data set into the initial detection model respectively to obtain a test result of each sample feature vector in the test data set, comparing the test result of each sample feature vector in the test data set with the sample label to obtain a test accuracy, and determining the initial detection model as the leakage detection model if the test accuracy is greater than or equal to an accuracy threshold value.
The test accuracy may be set according to the corresponding detection accuracy, for example, to 90% equivalent. The initial classifier may include a bayesian classifier, a decision tree, a neural network, etc.
This step may scale the data set in step S50 into a training data set and a testing data set for training and testing, respectively. Firstly, selecting several or one classifier model (an initial classifier, such as a Bayes classifier, a decision tree, a neural network and the like) as a model to be trained according to a machine learning method, sequentially inputting sample feature vectors and sample labels in a training data set into the model to be trained until all samples in the training data set are input, and continuously optimizing parameters in the classifier model in the period to obtain the trained model, wherein the training process is carried out. And then, sequentially inputting the sample characteristic vectors in the test data set into the trained model to obtain an output result, and comparing the output result with the sample label to obtain an error (or test accuracy), which is a test process. And determining a classifier model with a good effect according to the test error and the time consumption condition of the model, generally requiring small test error and less time consumption, and storing the trained model.
And S70, acquiring temperature data and vibration data in the leakage monitoring operation of the oil-gas pipeline to obtain temperature data to be detected and vibration data to be detected, acquiring a characteristic vector to be detected according to the temperature data to be detected and the vibration data to be detected, inputting the characteristic vector to be detected into the leakage detection model to identify the pipeline state represented by the characteristic vector to be detected, and realizing the detection of the leakage of the oil-gas pipeline.
In one embodiment, the obtaining the feature vector to be measured according to the temperature data to be measured and the vibration data to be measured includes:
acquiring a plurality of description characteristics of temperature data to be detected, and forming a temperature characteristic vector to be detected by using each description characteristic of the temperature data to be detected;
the method comprises the steps of obtaining a plurality of description features of vibration data to be detected, combining the description features of the vibration data to be detected into a vibration feature vector to be detected, and combining a temperature feature vector to be detected and the vibration feature vector to be detected into a feature vector to be detected.
In this embodiment, step S20, step S30, and step S40 are sequentially performed on temperature data and vibration data in the leakage monitoring operation of the oil and gas pipeline to obtain a data feature value in a one-dimensional vector form, and the leakage state of the oil and gas pipeline is identified according to the stored classifier model (leakage detection model) in step S60, so as to achieve the purpose of leakage monitoring.
Specifically, the descriptive characteristics of the sample temperature information or the descriptive characteristics of the temperature data to be measured include the range, the standard deviation, the average value, the maximum value, and the third-order origin moment.
Specifically, the description characteristics of the sample vibration information or the description characteristics of the vibration data to be detected include a range, a standard deviation, a strongest frequency, and a ratio of a primary peak to a secondary peak of a frequency spectrum.
The oil-gas pipeline leakage detection method based on vibration and temperature double parameters comprises the steps of arranging optical fibers around an oil-gas pipeline, obtaining a plurality of vibration information by Rayleigh scattering light in the optical fibers, obtaining a plurality of temperature information by Brillouin scattering light in the optical fibers, obtaining the current pipeline state of the oil-gas pipeline, thus obtaining sample vibration information and sample temperature information of the oil-gas pipeline, obtaining a plurality of description characteristics of the sample temperature information, forming the description characteristics of the sample temperature information into a sample temperature characteristic vector, obtaining a plurality of description characteristics of the sample vibration information, forming the description characteristics of the sample vibration information into a sample vibration characteristic vector, forming the sample temperature characteristic vector and the sample vibration characteristic vector into a sample characteristic vector, determining a sample label of the sample characteristic vector according to the current pipeline state of the oil-gas pipeline, and obtaining a large number of sample characteristic vectors and corresponding sample labels by adopting the scheme, dividing all sample characteristic vectors and sample labels corresponding to the sample characteristic vectors into a training data set and a testing data set, training an initial classifier by adopting the training data set to obtain an initial detection model, respectively inputting the sample characteristic vectors of the testing data set into the initial detection model to obtain a testing result of each sample characteristic vector in the testing data set, comparing the testing result of each sample characteristic vector in the testing data set with the sample labels to obtain testing accuracy, and determining the initial detection model as a leakage detection model if the testing accuracy is greater than or equal to an accuracy threshold. The method comprises the steps of obtaining temperature data and vibration data in the leakage monitoring operation of the oil-gas pipeline, obtaining temperature data to be detected and vibration data to be detected, obtaining a characteristic vector to be detected according to the temperature data to be detected and the vibration data to be detected, inputting the characteristic vector to be detected into the leakage detection model, identifying the pipeline state represented by the characteristic vector to be detected, achieving accurate detection of leakage of the oil-gas pipeline, and having high detection efficiency.
In one embodiment, since the actual application of the distributed optical fiber sensing technology in the aspect of oil and gas pipeline monitoring is generally based on only temperature data or vibration data, a false alarm or a false alarm is easily caused. In order to solve the problem, referring to fig. 3, in the oil and gas pipeline leakage detection method based on vibration and temperature dual parameters, the whole scheme can be divided into a preparation stage and a monitoring implementation stage, both of which include feature extraction and feature combination of temperature data and vibration data, and the difference is that the preparation stage needs training and testing of a classifier model, and the monitoring implementation stage directly utilizes the prepared classifier model for identification.
First, if the temperature data length is N, the temperature data (sample temperature information) is recorded as X ═ X1,x2,x3,...,xi,...xNAnd f, wherein i is less than or equal to N, extracting the range of the temperature data according to the formula (1) and recording the range as t1：
t1＝max(X)-min(X) (1)
The standard deviation of the temperature data is extracted according to the formula (2) and is recorded as t2：
Extracting the maximum value t of the temperature data according to equation (3)3：
t3＝max(X) (3)
Extracting the average value t of the temperature data according to equation (4)4：
Extracting a third-order origin moment t of the temperature data according to formula (5)5：
Then 5 temperature characteristic values are combined into a one-dimensional vector form and recorded as
In the second step, if the vibration data length (sample vibration information) is M, the vibration data is recorded as Y ═ Y1,y2,y3,...,yj,...yMAnd j is less than or equal to M, extracting the range of the vibration data according to a formula (6) and recording the range as v1：
v1＝max(Y)-min(Y) (6)
The standard deviation of the vibration data is extracted according to equation (7) and recorded as v2：
Then, the frequency spectrum of the vibration data is obtained by Fourier transform of the vibration data, and is recorded as F ═ F1,f2,f3,..,fkWhere k is a frequency component, fkIs the frequency intensity corresponding to frequency k. The strongest frequency of the vibration data is extracted according to equation (8) and designated as v3：
The ratio of the major peak to the minor peak of the frequency spectrum of the vibration data is extracted according to equation (9) and is designated v4：
Combining the 4 vibration characteristic values into a one-dimensional vector form, and recording the one-dimensional vector form as
Thirdly, the vector is processed
Sum vector
Combine to form a new one-dimensional feature vector, denoted as
Then can obtain
Fourthly, repeating the first step to the third step according to different enough data to obtain a data set which is recorded as
Then can obtain
Where L is the data set
The number of data of (2).
The fifth step, the data set
Scaled to be subsequently partitioned into training data sets
And test data set
Training data set
The number of data of (2) is L1Training data set
The number of data of (2) is L2In this example, take L1:L29: 1. Using training data sets
Training the classifier model, in the embodiment, selecting a random forest model as the classifier model, and then utilizing the training data set
The trained classifier model is tested to obtain a confusion matrix diagram as shown in fig. 3, 0 represents a non-leakage class, and 1 represents a leakage class, so that the trained classifier model has a good classification effect on data and overall data of each condition, and therefore, the model can be stored and used as an actual leakage detection model. The preparation phase is now complete.
And sixthly, entering a monitoring implementation phase from the preparation phase. And similarly, extracting feature vectors of the data from different temperature data and vibration data by using the methods from the first step to the third step, identifying the feature vectors by using the classifier model stored in the fifth step, and judging whether the oil-gas pipeline is leaked currently.
The technical scheme of the invention has the following beneficial effects:
by utilizing the distributed optical fiber sensing technology, the distributed measurement of vibration and temperature along the oil-gas pipeline is realized, the variation parameters caused by leakage of the oil-gas pipeline are fully obtained, comprehensive sensing information is provided for leakage state identification, and the report missing rate of leakage monitoring can be effectively reduced.
The characteristic vectors of the temperature and vibration data are respectively extracted from the time domain and the frequency domain, and the leakage monitoring of the oil and gas pipeline is implemented by using a machine learning method, so that the false alarm rate of the leakage monitoring can be effectively reduced.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
It should be noted that the terms "first \ second \ third" referred to in the embodiments of the present application merely distinguish similar objects, and do not represent a specific ordering for the objects, and it should be understood that "first \ second \ third" may exchange a specific order or sequence when allowed. It should be understood that "first \ second \ third" distinct objects may be interchanged under appropriate circumstances such that the embodiments of the application described herein may be implemented in an order other than those illustrated or described herein.
The terms "comprising" and "having" and any variations thereof in the embodiments of the present application are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product, or device that comprises a list of steps or modules is not limited to the listed steps or modules but may alternatively include other steps or modules not listed or inherent to such process, method, product, or device.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (5)
1. A vibration and temperature double-parameter-based oil and gas pipeline leakage detection method is characterized by comprising the following steps:
s10, arranging optical fibers around the oil and gas pipeline, obtaining a plurality of vibration information by using Rayleigh scattering light in the optical fibers, obtaining a plurality of temperature information by using Brillouin scattering light in the optical fibers, and obtaining the current pipeline state of the oil and gas pipeline, so as to obtain sample vibration information, sample temperature information and sample state of the oil and gas pipeline; the pipeline state comprises a leakage state and a non-leakage state;
s20, obtaining a plurality of description features of the sample temperature information, and forming a sample temperature feature vector by the description features of the sample temperature information;
s30, obtaining a plurality of description features of the sample vibration information, and forming a sample vibration feature vector by each description feature of the sample vibration information;
s40, combining the sample temperature characteristic vector and the sample vibration characteristic vector into a sample characteristic vector, and determining a sample label of the sample characteristic vector according to the sample state;
s50, returning to execute the steps S10-S40 until the obtained sample feature vectors exceed the quantity threshold, and dividing all the sample feature vectors and the sample labels corresponding to the sample feature vectors into a training data set and a testing data set; the training data set comprises a plurality of sample characteristic vectors and sample labels corresponding to the sample characteristic vectors; the test data set comprises a plurality of sample characteristic vectors and sample labels corresponding to the sample characteristic vectors;
s60, training an initial classifier by adopting a training data set to obtain an initial detection model, respectively inputting each sample feature vector of a test data set into the initial detection model to obtain a test result of each sample feature vector in the test data set, comparing the test result of each sample feature vector in the test data set with a sample label to obtain a test accuracy, and determining the initial detection model as a leakage detection model if the test accuracy is greater than or equal to an accuracy threshold;
and S70, acquiring temperature data and vibration data in the leakage monitoring operation of the oil-gas pipeline to obtain temperature data to be detected and vibration data to be detected, acquiring a characteristic vector to be detected according to the temperature data to be detected and the vibration data to be detected, inputting the characteristic vector to be detected into the leakage detection model to identify the pipeline state represented by the characteristic vector to be detected, and realizing the detection of the leakage of the oil-gas pipeline.
2. The dual vibration and temperature parametric-based oil and gas pipeline leak detection method of claim 1, further comprising, after laying optical fibers around the oil and gas pipeline:
and collecting optical signals in the optical fiber, and sequentially carrying out frequency division, demodulation and fitting processing on the optical signals to obtain Rayleigh scattered light and Brillouin scattered light.
3. The vibration and temperature dual-parameter-based oil and gas pipeline leakage detection method according to claim 1, wherein the step of obtaining the feature vector to be detected according to the temperature data to be detected and the vibration data to be detected comprises the steps of:
acquiring a plurality of description characteristics of temperature data to be detected, and forming a temperature characteristic vector to be detected by using each description characteristic of the temperature data to be detected;
the method comprises the steps of obtaining a plurality of description features of vibration data to be detected, combining the description features of the vibration data to be detected into a vibration feature vector to be detected, and combining a temperature feature vector to be detected and the vibration feature vector to be detected into a feature vector to be detected.
4. The vibration and temperature dual-parameter-based oil and gas pipeline leakage detection method according to claim 3, wherein the descriptive characteristics of the sample temperature information or the descriptive characteristics of the temperature data to be detected comprise range, standard deviation, average value, maximum value and third-order origin moment.
5. The vibration and temperature bi-parametric based oil and gas pipeline leak detection method of claim 3, wherein the descriptive characteristics of the sample vibration information or the descriptive characteristics of the vibration data to be detected include range, standard deviation, strongest frequency, ratio of primary peak to secondary peak of frequency spectrum.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110034057.3A CN112729688B (en) | 2021-01-12 | 2021-01-12 | Oil-gas pipeline leakage detection method based on vibration and temperature double parameters |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110034057.3A CN112729688B (en) | 2021-01-12 | 2021-01-12 | Oil-gas pipeline leakage detection method based on vibration and temperature double parameters |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112729688A true CN112729688A (en) | 2021-04-30 |
| CN112729688B CN112729688B (en) | 2022-08-19 |
Family
ID=75590567
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110034057.3A Active CN112729688B (en) | 2021-01-12 | 2021-01-12 | Oil-gas pipeline leakage detection method based on vibration and temperature double parameters |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112729688B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113792585A (en) * | 2021-08-03 | 2021-12-14 | 重庆兆光科技股份有限公司 | Pipeline vibration signal monitoring method and system, electronic equipment and medium |
| CN114234055A (en) * | 2021-12-28 | 2022-03-25 | 国家石油天然气管网集团有限公司 | Oil and gas pipeline optical fiber vibration alarm signal rechecking method and system |
| CN114576566A (en) * | 2022-04-28 | 2022-06-03 | 高勘(广州)技术有限公司 | Gas pipeline early warning method, device, equipment and storage medium |
| WO2023125586A1 (en) * | 2021-12-29 | 2023-07-06 | 北京辰安科技股份有限公司 | Training method and apparatus for urban underground gas leakage identification model |
| CN117108939A (en) * | 2023-10-23 | 2023-11-24 | 华清安泰能源股份有限公司 | Online monitoring method, system and device for ground temperature field and storage medium |
| CN117450413A (en) * | 2023-12-25 | 2024-01-26 | 江西铜业集团铜板带有限公司 | Engine oil leakage detection method of copper plate and strip cold rolling mill |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102589620A (en) * | 2012-03-07 | 2012-07-18 | 杭州安远科技有限公司 | Distributed-type optical fiber sensing device and method for simultaneously measuring vibration and temperature |
| CN102997062A (en) * | 2011-09-14 | 2013-03-27 | 中国石油天然气集团公司 | Optical fiber sensor-based natural gas pipeline leakage monitoring method and system and installation method for system |
| CN103727968A (en) * | 2013-12-31 | 2014-04-16 | 宁波诺驰光电科技发展有限公司 | Distributed type optical fiber sensing device and method for simultaneously measuring temperature, strain and vibration |
| CN104919295A (en) * | 2012-12-11 | 2015-09-16 | 管道监控公司 | System and method for supervising, managing, and monitoring the structural integrity of a fluid- transportation pipeline network, for locating the leaking point, and for evaluating the extent of the failure |
| WO2016174410A1 (en) * | 2015-04-27 | 2016-11-03 | Fotech Solutions Limited | Distributed optical fibre sensor |
| CN107917784A (en) * | 2017-11-16 | 2018-04-17 | 武汉理工大学 | A kind of pipeline road Oil Leakage Detecting system and its method of work based on fiber grating |
| CN107917341A (en) * | 2016-10-09 | 2018-04-17 | 中国石油天然气股份有限公司 | A kind of Oil Pipeline Leakage Detection and device |
| CN109186895A (en) * | 2018-08-08 | 2019-01-11 | 太原理工大学 | Distributed passive gas transmission line leakage multi-parameter fusion early warning detection device and method |
| CN110131486A (en) * | 2019-04-17 | 2019-08-16 | 北京百世通管道科技有限公司 | Optical fiber compound pipeline complex pipeline and its monitoring system and method for early warning |
| CN211315808U (en) * | 2019-12-02 | 2020-08-21 | 鞍山睿科光电技术有限公司 | Oil gas pipeline fault early warning and leakage monitoring system |
-
2021
- 2021-01-12 CN CN202110034057.3A patent/CN112729688B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102997062A (en) * | 2011-09-14 | 2013-03-27 | 中国石油天然气集团公司 | Optical fiber sensor-based natural gas pipeline leakage monitoring method and system and installation method for system |
| CN102589620A (en) * | 2012-03-07 | 2012-07-18 | 杭州安远科技有限公司 | Distributed-type optical fiber sensing device and method for simultaneously measuring vibration and temperature |
| CN104919295A (en) * | 2012-12-11 | 2015-09-16 | 管道监控公司 | System and method for supervising, managing, and monitoring the structural integrity of a fluid- transportation pipeline network, for locating the leaking point, and for evaluating the extent of the failure |
| CN103727968A (en) * | 2013-12-31 | 2014-04-16 | 宁波诺驰光电科技发展有限公司 | Distributed type optical fiber sensing device and method for simultaneously measuring temperature, strain and vibration |
| WO2016174410A1 (en) * | 2015-04-27 | 2016-11-03 | Fotech Solutions Limited | Distributed optical fibre sensor |
| CN107917341A (en) * | 2016-10-09 | 2018-04-17 | 中国石油天然气股份有限公司 | A kind of Oil Pipeline Leakage Detection and device |
| CN107917784A (en) * | 2017-11-16 | 2018-04-17 | 武汉理工大学 | A kind of pipeline road Oil Leakage Detecting system and its method of work based on fiber grating |
| CN109186895A (en) * | 2018-08-08 | 2019-01-11 | 太原理工大学 | Distributed passive gas transmission line leakage multi-parameter fusion early warning detection device and method |
| CN110131486A (en) * | 2019-04-17 | 2019-08-16 | 北京百世通管道科技有限公司 | Optical fiber compound pipeline complex pipeline and its monitoring system and method for early warning |
| CN211315808U (en) * | 2019-12-02 | 2020-08-21 | 鞍山睿科光电技术有限公司 | Oil gas pipeline fault early warning and leakage monitoring system |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113792585A (en) * | 2021-08-03 | 2021-12-14 | 重庆兆光科技股份有限公司 | Pipeline vibration signal monitoring method and system, electronic equipment and medium |
| CN113792585B (en) * | 2021-08-03 | 2023-06-27 | 重庆兆光科技股份有限公司 | Pipeline vibration signal monitoring method, system, electronic equipment and medium |
| CN114234055A (en) * | 2021-12-28 | 2022-03-25 | 国家石油天然气管网集团有限公司 | Oil and gas pipeline optical fiber vibration alarm signal rechecking method and system |
| CN114234055B (en) * | 2021-12-28 | 2024-04-23 | 国家石油天然气管网集团有限公司 | Method and system for rechecking optical fiber vibration alarm signal of oil and gas pipeline |
| WO2023125586A1 (en) * | 2021-12-29 | 2023-07-06 | 北京辰安科技股份有限公司 | Training method and apparatus for urban underground gas leakage identification model |
| CN114576566A (en) * | 2022-04-28 | 2022-06-03 | 高勘(广州)技术有限公司 | Gas pipeline early warning method, device, equipment and storage medium |
| CN114576566B (en) * | 2022-04-28 | 2022-07-29 | 高勘(广州)技术有限公司 | Gas pipeline early warning method, device, equipment and storage medium |
| CN117108939A (en) * | 2023-10-23 | 2023-11-24 | 华清安泰能源股份有限公司 | Online monitoring method, system and device for ground temperature field and storage medium |
| CN117108939B (en) * | 2023-10-23 | 2024-01-02 | 华清安泰能源股份有限公司 | Online monitoring method, system and device for ground temperature field and storage medium |
| CN117450413A (en) * | 2023-12-25 | 2024-01-26 | 江西铜业集团铜板带有限公司 | Engine oil leakage detection method of copper plate and strip cold rolling mill |
| CN117450413B (en) * | 2023-12-25 | 2024-03-15 | 江西铜业集团铜板带有限公司 | Engine oil leakage detection method of copper plate and strip cold rolling mill |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112729688B (en) | 2022-08-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112729688B (en) | Oil-gas pipeline leakage detection method based on vibration and temperature double parameters | |
| CN107590516B (en) | Gas transmission pipeline leakage detection and identification method based on optical fiber sensing data mining | |
| Lloyd et al. | Testing an improved index for analysing storm discharge–concentration hysteresis | |
| CN100552668C (en) | Leakage detecting and locating method based on pressure and sound wave information fusion | |
| De Cáceres | How to use the indicspecies package (ver. 1.7. 1) | |
| CN106706119B (en) | Vibration source identification method and system based on signal frequency domain characteristics | |
| CN105067101A (en) | Fundamental tone frequency characteristic extraction method based on vibration signal for vibration source identification | |
| CN112766301A (en) | Similarity judgment method for indicator diagram of oil extraction machine | |
| CN112836719A (en) | Indicator diagram similarity detection method fusing two classifications and three groups | |
| CN116805061A (en) | Leakage event judging method based on optical fiber sensing | |
| CN115987386A (en) | Optical cable same-route detection device and method | |
| CN116108202A (en) | Mining system data attack behavior modeling method based on relational graph | |
| CN110046651A (en) | A kind of pipeline conditions recognition methods based on monitoring data multi-attribute feature fusion | |
| CN111898134B (en) | Intelligent contract vulnerability detection method and device based on LSTM and BiLSTM | |
| CN105722129A (en) | Wireless sensing network event detection method and system based on FSAX-MARKOV model | |
| CN110808947B (en) | Automatic vulnerability quantitative evaluation method and system | |
| CN105046859A (en) | Optical fiber intrusion detection method based on vibration signal space-time two-dimensional sparse representation K-S detection | |
| CN115470524B (en) | Method, system, equipment and medium for detecting leakage of confidential documents | |
| CN115221963B (en) | Data-driven nuclear-grade pipeline resonance fault detection method and system | |
| CN104819382A (en) | Self-adaptive constant false alarm rate vibration source detection method for optical fiber early warning system | |
| Favenza et al. | A machine learning approach to GNSS scintillation detection: Automatic soft inspection of the events | |
| CN116244699A (en) | Vulnerability risk assessment system based on interactive application security detection | |
| CN112381697B (en) | Automatic recognition method for false behavior of water pollution source on-line monitoring data falsification | |
| Gao et al. | Acoustic Emission‐Based Small Leak Detection of Propulsion System Pipeline of Sounding Rocket | |
| Lloyd et al. | Testing an improved index for analysing storm nutrient hysteresis |
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 |