CN118016082B - Pipeline leakage filtering method and system based on automatic variation modal decomposition - Google Patents
Pipeline leakage filtering method and system based on automatic variation modal decomposition Download PDFInfo
- Publication number
- CN118016082B CN118016082B CN202410424127.XA CN202410424127A CN118016082B CN 118016082 B CN118016082 B CN 118016082B CN 202410424127 A CN202410424127 A CN 202410424127A CN 118016082 B CN118016082 B CN 118016082B
- Authority
- CN
- China
- Prior art keywords
- pipeline
- signal
- mode
- filtering
- modal decomposition
- 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
- 238000000354 decomposition reaction Methods 0.000 title claims abstract description 86
- 238000000034 method Methods 0.000 title claims abstract description 74
- 238000001914 filtration Methods 0.000 title claims abstract description 48
- 238000001514 detection method Methods 0.000 claims abstract description 30
- 238000010276 construction Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000005070 sampling Methods 0.000 claims description 3
- 238000011946 reduction process Methods 0.000 claims description 2
- 241001081179 Litsea Species 0.000 abstract description 4
- 235000012854 Litsea cubeba Nutrition 0.000 abstract description 4
- 230000007613 environmental effect Effects 0.000 abstract description 4
- 230000000694 effects Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 238000005457 optimization Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000003190 augmentative effect Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 238000001228 spectrum Methods 0.000 description 3
- 238000006467 substitution reaction Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- RZVAJINKPMORJF-UHFFFAOYSA-N Acetaminophen Chemical compound CC(=O)NC1=CC=C(O)C=C1 RZVAJINKPMORJF-UHFFFAOYSA-N 0.000 description 1
- 208000025531 adult-onset foveomacular vitelliform dystrophy Diseases 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
Landscapes
- Examining Or Testing Airtightness (AREA)
Abstract
The invention discloses a pipeline leakage filtering method, a detection method and a detection system based on automatic variation modal decomposition, relates to the technical field of pipeline leakage detection, and aims to solve the problem that detection accuracy of pipeline leakage signals is reduced due to noise interference. The filtering method comprises the following steps: constructing an objective function of automatic variation modal decomposition by utilizing a concept added constraint criterion of residual signals on the basis of variation modal decomposition, thereby obtaining a formula of updating modal and center frequency; utilizing the power concept of the mode to provide an updated bandwidth formula and automatically searching iteration conditions of the target modulus; and reconstructing the obtained pure mode by using the Litsea distance to achieve the denoising purpose. The detection method comprises the following steps: and filtering the pipeline acoustic wave signal to be detected by using a pipeline leakage filtering method, and then further detecting. The method provided by the invention is simple, high in accuracy and low in detection cost, and effectively solves the problem of interference caused by environmental noise on pipeline leakage detection.
Description
Technical Field
The invention relates to the technical field of pipeline leakage signal detection, in particular to a pipeline leakage filtering method and system based on automatic variation modal decomposition, and a detection method and system.
Background
Today, the pipeline transportation industry is also evolving vigorously as oil and gas reserves increase. Compared with other transportation modes, the pipeline transportation has higher transportation efficiency, can realize continuous, automatic and high-capacity logistics transportation, does not need to wait for the loading and unloading process, and greatly saves time and labor cost. However, there are also some limitations to the transportation of pipes. The construction and maintenance costs of the pipeline system are high, and the transportation path cannot be flexibly adjusted. Moreover, as the problem of aging of the pipeline is gradually increased, sudden accidents such as explosion, fire and the like caused by pipeline leakage cause serious losses and disasters. Therefore, in order to reduce the occurrence of leakage accidents, it is very necessary to perform leakage detection on oil and gas pipelines.
However, the signals collected in actual pipeline detection are often polluted by environmental factors, so that the detection accuracy is reduced, and the problems of false alarm and false alarm exist. Thus, denoising the acquired leakage signal at an early stage of detection is critical to ensure success of the detection technique. The recently developed Variational Modal Decomposition (VMD) algorithm has unique advantages in the aspect of pipeline leakage detection, can decompose the acquired signals into a plurality of single-component signals, is beneficial to selection of effective components, and greatly improves the denoising effect.
However, the VMD parameters are difficult to be manually selected, so that the resolution precision of the VMD is insufficient, and a certain error exists in the accurate selection of the effective modes in the multi-modes by means of manual judgment after the resolution. Therefore, research on how to optimize parameters in the VMD, select effective components and improve the accuracy of judging leakage is an important research direction, and has certain theoretical significance and practical value.
Disclosure of Invention
Therefore, the invention provides a pipeline leakage filtering method and system based on automatic variation modal decomposition, and a detection method and system, which are used for solving the problem that detection accuracy is reduced due to noise interference of a pipeline leakage signal.
According to an aspect of the present invention, there is provided a pipe leakage filtering method based on automatic variation modal decomposition, the method comprising the steps of:
collecting a pipeline acoustic wave signal;
And filtering the pipeline acoustic wave signal, wherein the filtering comprises the following steps: and carrying out variation modal decomposition on the pipeline acoustic wave signal, constructing an objective function of the variation modal decomposition by utilizing a residual signal concept, and carrying out iterative solution on the objective function to obtain a plurality of intrinsic modes and corresponding center frequencies thereof.
Further, the objective function of constructing the variational modal decomposition by using the residual signal concept is as follows: the constraint criterion is added on the basis of the original construction criterion, which is that the energy of the residual signal should be minimized at frequencies with significant components.
Further, the objective function is expressed as:
Wherein α represents a bandwidth; u k＝uk (t) denotes the kth modality; omega k represents the center frequency corresponding to the kth mode; λ=λ (t) represents a double rise parameter; delta (t) represents dirac distribution; j represents a complex structure, j 2＝-1;βk (t) represents a filter; f (t) represents an input pipeline acoustic signal; f r(t)＝f(t)-uk (t) is a residual signal of the input pipeline acoustic signal except the mode obtained by decomposition; t represents the time.
Further, the updated formula for each eigenmode and its corresponding center frequency in each iteration is expressed as:
In the method, in the process of the invention, Representing a kth modality in an n+1th iteration of the frequency domain space; /(I)An input pipeline acoustic signal representing a frequency domain space; ω represents the center frequency of the input signal; /(I)Representing a mode obtained by kth decomposition of the frequency domain space; Representing the center frequency corresponding to the kth mode in the nth iteration;
In the method, in the process of the invention, Representing the center frequency corresponding to the kth mode in the n+1th iteration of the frequency domain space.
Further, in the process of carrying out iterative solution on the objective function to obtain a plurality of eigenmodes and corresponding center frequencies thereof, an updated formula of the bandwidth alpha is improved so that the obtained modes and center frequencies are more accurate; the formula of the bandwidth alpha update is as follows:
Where T represents the sampling time of the input signal.
Further, in the process of carrying out iterative solution on the objective function to obtain a plurality of eigenmodes and corresponding center frequencies thereof, the following iteration termination conditions are set: judgingIf the stopping condition of the (b) is satisfied, outputting the eigenmodes and the corresponding center frequencies; wherein/>And/>Respectively representing the power parameters corresponding to the kth-1 mode and the kth mode, wherein the calculation formula is as follows:
In the method, in the process of the invention, Representing a transposed version of the modality.
Further, after a plurality of eigenmodes and corresponding center frequencies are obtained, noise reduction processing is carried out on the plurality of eigenmodes, and noise-reduced pipeline signals are obtained; the noise reduction process comprises the following steps: calculating the Lith distance between each mode and the original input signal; calculating the slope values of two adjacent Lees, and taking the mode number corresponding to the maximum slope value as a jump point; and carrying out phase reconstruction on all modes positioned in front of the jump points to obtain the noise-reduced pipeline signal.
According to another aspect of the present invention, a system for filtering pipeline leakage based on automatic variation modal decomposition is provided, which has program modules corresponding to the steps of the above-mentioned pipeline leakage filtering method, and which executes the steps of the above-mentioned pipeline leakage filtering method in operation.
According to still another aspect of the present invention, there is provided a pipe leakage detection method based on automatic variation modal decomposition, the method comprising the steps of: after the pipeline leakage filtering method is used for filtering the pipeline acoustic wave signal to be detected, the pipeline acoustic wave signal is input into a trained classifier for recognition, so that a recognition result of whether the pipeline is leaked or not is obtained.
According to a further aspect of the present invention, a system for detecting pipeline leakage based on automatic variation modal decomposition is presented, the system having program modules corresponding to the steps of the pipeline leakage filtering method described above, the steps of the pipeline leakage detecting method described above being executed at run-time.
The beneficial technical effects of the invention are as follows:
The invention provides a pipeline leakage filtering method and a system based on automatic variation modal decomposition, which are characterized in that a constraint criterion is added by utilizing a residual signal concept on the basis of variation modal decomposition, an objective function of the automatic variation modal decomposition is constructed, and the problem that a variation modal decomposition algorithm is inaccurate in finding an objective mode is solved; solving a formula of the mode and the center frequency by using an advanced mathematical solving method, so that the problem of overhigh calculation cost caused by redundancy of solving steps of a variation mode decomposition algorithm is solved; the bandwidth of the automatic variation mode decomposition is automatically updated by utilizing the average power concept of the modes, so that the problem that the bandwidth of the variation mode decomposition algorithm cannot be changed along with the optimization stage so as to not obtain the target mode is solved; an automatic iteration condition is set by utilizing the concept of modal energy, and the problem that the signal decomposition effect is poor due to inaccurate parameter setting of a variation modal algorithm is solved; and evaluating the modal effectiveness obtained by automatic variation modal decomposition by utilizing the Litsea distance, so that the pure signal is reconstructed to obtain the filtering purpose. The filtering method provided by the invention is simple, high in accuracy and low in detection cost, and effectively solves the problem that environmental noise interferes with pipeline leakage detection.
The invention also provides a pipeline leakage detection method and a system based on automatic variation modal decomposition, which are used for further detection processing after filtering processing is carried out on the pipeline acoustic wave signal to be detected by utilizing the pipeline leakage filtering method.
Drawings
The invention may be better understood by reference to the following description taken in conjunction with the accompanying drawings, which are included to provide a further illustration of the preferred embodiments of the invention and to explain the principles and advantages of the invention, together with the detailed description below.
Fig. 1 is a flow chart of a pipeline leakage filtering method based on automatic variation modal decomposition according to an embodiment of the invention.
FIG. 2 is a flow chart diagram of an automatic variation modal decomposition algorithm construction objective function and solution process in an embodiment of the invention.
Fig. 3 is a flow chart of a process for automatically updating rules and iteration conditions in an automatic variation modal decomposition algorithm in an embodiment of the invention.
FIG. 4 is a block flow diagram of a process for filtering a leakage signal using an automatic variation modal decomposition algorithm in combination with Litsea distances in accordance with an embodiment of the present invention.
FIG. 5 is a graph of a pipeline leakage signal collected in an embodiment of the present invention; the left graph in the figure is the time domain waveform of the leakage signal, and the right graph is the frequency domain waveform of the leakage signal.
FIG. 6 is a modal distribution diagram of a leakage signal obtained by an automatic variation modal decomposition model in an embodiment of the invention.
FIG. 7 is a chart of a center frequency Fourier spectrum of a mode obtained by decomposition in an embodiment of the invention; wherein the frequency of the leakage signal is indicated by a dashed line.
Fig. 8 is a diagram showing the denoising effect of a leakage signal according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, exemplary embodiments or examples of the present invention will be described below with reference to the accompanying drawings. It is apparent that the described embodiments or examples are only implementations or examples of a part of the invention, not all. All other embodiments or examples, which may be made by one of ordinary skill in the art without undue burden, are intended to be within the scope of the present invention based on the embodiments or examples herein.
The first embodiment of the invention provides a pipeline leakage filtering method based on automatic variation modal decomposition, which solves the problem that the detection accuracy of a pipeline leakage signal is reduced due to noise interference. The method comprises the following steps: firstly, carrying out variation modal decomposition on a pipeline signal, and adding constraint criteria on the basis of the variation modal decomposition to construct an objective function of automatic variation modal decomposition, thereby obtaining a formula of updating the modal and the center frequency; then, in order to further determine the accuracy of the formula, an updated formula of the bandwidth is designed (considering that the size of the bandwidth is related to the size of the center frequency), mainly through that the size of the bandwidth is smaller and smaller along with the increase of the decomposition times, so that the center frequency is closer and closer to the real frequency; secondly, the iteration condition of automatically searching the target modulus is to enable the whole process to achieve the purpose of 'automatic' decomposition, so that the automatic variation modal decomposition realizes the expectation that decomposition parameters are not required to be set. And finally, acquiring leakage signals by using an acoustic wave sensor, decomposing the leakage signals by using automatic variation mode decomposition, and reconstructing the obtained pure mode by using the developed Lis distance to achieve the denoising purpose.
Fig. 1 is a flow chart of a method of filtering a pipeline leakage based on automatic variation modal decomposition for filtering a pipeline signal. The method comprises the following steps:
S1, collecting a pipeline acoustic wave signal;
s2, filtering the pipeline acoustic wave signal, wherein the filtering comprises the following steps: performing variation modal decomposition on the pipeline acoustic wave signal, constructing an objective function of the variation modal decomposition by utilizing a residual signal concept, and performing iterative solution on the objective function to obtain a plurality of intrinsic modes and corresponding center frequencies thereof;
s3, carrying out noise reduction processing on the plurality of intrinsic modes to obtain a noise-reduced pipeline signal.
In this embodiment, preferably, in the process of iteratively solving the objective function to obtain a plurality of eigenmodes and corresponding center frequencies thereof, an updated formula of the bandwidth α is improved, so that the obtained modes and center frequencies are more accurate.
The method starts at S1.
Firstly, in S1, collecting a pipeline sound wave signal; and then executing S2, and in S2, performing filtering processing on the pipeline acoustic wave signal, wherein the filtering processing comprises the following steps: and carrying out variation modal decomposition on the pipeline acoustic wave signal, constructing an objective function of the variation modal decomposition by utilizing a residual signal concept, and carrying out iterative solution on the objective function to obtain a plurality of intrinsic modes and corresponding center frequencies thereof.
According to an embodiment of the present invention, as shown in fig. 2, first, a criterion of minimum residual energy is used to construct an objective function of the variational modal decomposition: the constraint criterion is added on the basis of the original construction criterion, which is that the energy of the residual signal should be minimized at frequencies with significant components.
The original construction criteria of the objective function of the variational modal decomposition are as follows: each mode should be compact about its center frequency, minimizing the kth decomposed signal mode as follows:
Wherein u k(t),ωk represents the kth mode and the corresponding center frequency; delta (t) represents dirac distribution; j represents a complex structure, j 2 = -1.
The constraint criterion is added on the basis of the original construction criterion, and the constraint criterion is as follows: the energy of the residual signal should be minimized at frequencies with significant components:
Wherein f r(t)＝f(t)-uk (t) represents the residual signal of the input signal f (t) except the mode obtained by decomposition; ω represents the center frequency; f (t) represents an input signal.
Thus, the expression of the objective function constructed is as follows:
Wherein f (t) is an input signal, u k(t),ωk represents a kth mode and a corresponding center frequency, and f r(t)＝f(t)-uk (t) represents a residual signal of the input signal f (t) except modes obtained by decomposition.
The objective function is then further augmented with lagrangian as follows:
Where α is a balance parameter for constraining two criteria, where α represents bandwidth considering that "modal bandwidth is minimized" is assumed in the objective function. u k denotes a modality; beta k (t) represents a filter expression; λ (t) represents a double rise parameter.
In this embodiment, the augmented Lagrangian multiplier method (Augmented Lagrange Method) is used to solve the optimization problem under the constraint of the equation. It increases the robustness of the dual-lifting method and relaxes the strong convex constraint of the function relative to naive lagrangian, enabling the transformed problem to be solved more easily. By improving the objective function of the variation modal decomposition algorithm, the problem that the original algorithm searches for the objective modal inaccuracy can be solved, and meanwhile, the calculation cost is reduced.
Then, after constructing the objective function, a series of mathematical solutions are used to obtain a formula for updating the mode and center frequency. The mathematical solution method comprises the following steps: transferring the minimization problem to a frequency spectrum domain through a Fourier equidistant method and an L 2 norm to solve; the solution is continued by the variable substitution method and the first slope elimination method.
Specifically, 1) update to modality: first, the modality u k (t) is updated according to the following formula:
Wherein n represents a fixed direction and the number of iterations; x represents a natural space. Wherein iteration counters are omitted for simplicity of notation and each counter is implicitly understood as the latest available update.
The above problem was then rewritten as follows using the Parseval/PLANCHEREL Fourier equidistant at L 2 norm and ω++ω - ω k substitution:
In the method, in the process of the invention, Representing a modality; /(I)Representing a filter expression; /(I)Representing the input signal; A modal expression that does not distinguish between iteration numbers is represented.
Finally, by eliminating the first change in positive frequency, a solution to the optimization problem can be obtained, i.e. the updated formula for the modality is:
In the method, in the process of the invention, Representing a kth modality in an n+1th iteration of the frequency domain space; /(I)An input pipeline acoustic signal representing a frequency domain space; ω represents the center frequency of the input signal; /(I)Representing a mode obtained by kth decomposition of the frequency domain space; representing the center frequency corresponding to the kth modality in the nth iteration.
2) For the update of the center frequency, first, the center frequency ω k is updated according to the following formula:
then, using Parseval/PLANCHEREL Fourier equidistant and ω++ω - ω k substitution at L 2 norm, will solve the problems The update formula for the final center frequency is obtained by overwriting and eliminating the first change of the positive frequency as follows:
In the method, in the process of the invention, Representing the center frequency corresponding to the kth mode in the n+1th iteration of the frequency domain space.
Preferably, in the initial stage of finding the target pattern, the estimated intermediate frequency tends to be far away from the actual intermediate frequency, and it is more reasonable to employ a larger bandwidth, as it may contain more target information. In contrast, in the final optimization stage, the currently estimated, i.e. updated, center frequency becomes closer to the true center frequency, so a narrower bandwidth can restore the target modality. Therefore, in this embodiment, the bandwidth update formula is designed by using the concept of average power to further improve the accuracy of the mode and center frequency update formula, so that the automatic variation mode decomposition model is more comprehensive, as shown in fig. 3, and the optimization steps are as follows:
firstly, initializing operation, wherein the average power of an input signal is used as an initial value of a bandwidth;
Wherein T represents the sampling time of the input signal; alpha 1 represents an initial value of the bandwidth, and alpha represents the bandwidth.
Then, calculating the energy percentage difference value of each mode;
Calculating the center frequency difference value of each mode;
Defining a comprehensive bandwidth correction factor;
αAJ＝0.01*αper+αom
The final bandwidth update formula is:
In this embodiment, considering that the AVMD decomposition method is effective, the obtained mode is closer to the target mode, in other words, the difference between the energy of each mode and the original input signal is smaller, so that the bandwidth value is smaller along with the iterative update, and better conforms to the update trend of the analysis bandwidth.
The power ratio concept adopted by bandwidth updating is that the difference value between the energy from each mode and the input signal is smaller and smaller, so that the automatically updated bandwidth value is smaller and smaller along with iteration, and the bandwidth updating trend is more met; meanwhile, the iteration condition can solve the problem of poor signal decomposition effect caused by inaccurate parameter setting of the variation modal algorithm.
Preferably, in the process of performing iterative solution on the objective function to obtain a plurality of eigenmodes and corresponding center frequencies thereof, in order to obtain a target modulus value k, the following automatic iteration conditions are set: judgingIf the stop condition is satisfied, outputting a suitable modulus k value. Wherein the power parameterWhich updates with increasing modulus,/>Representing a transposed version of the modality.
It can be seen that the rule for updating the k value can be approximately expressed as a new constraint condition and index, and the relation between the generated modes and the signals is limited by the energy concept, so that the proper number of modes, namely automatic variation mode decomposition, can be obtained adaptively.
And then executing S3, and in S3, carrying out noise reduction processing on the plurality of intrinsic modes to obtain a noise-reduced pipeline signal. Specifically, the effectiveness of each component obtained by decomposition is evaluated by using the Lee distance, and the pure mode is reconstructed to achieve the purpose of denoising, as shown in FIG. 4, the steps are as follows:
First, for a plurality of signal modes obtained by using an automatic variation mode decomposition algorithm, a Lee distance LD 1,LD2,...,LDk between each mode and an original signal is calculated for evaluating similarity between each mode and the original signal:
Wherein f (t) represents the original signal; u k (t) is the developed modality of automatic variation modality decomposition.
Then, analyzing the numerical value difference and slope comparison to distinguish an effective mode from an ineffective mode; the distribution diagram of the Lis distance values among all modes is intuitively displayed, the slope values of the adjacent distances are calculated, and the mode number corresponding to the maximum slope value is used as a jump point.
Finally, reconstructing an effective mode to obtain a denoised pipeline leakage signal; and performing phase reconstruction on all modes positioned in front of the jump points to obtain the noise-reduced pipeline signal.
In this embodiment, the li distance is used to evaluate the effectiveness degree of each mode obtained by decomposition, and by performing noise reduction pretreatment on the automatic variation mode decomposition model on the leakage signal, the interference of other noise in the pipeline on the effective acoustic wave signal can be reduced, and finally the denoised acoustic wave signal is obtained.
The complete automatic variant modal decomposition algorithm model pseudocode is as follows:
fig. 5 is a time domain and frequency domain waveform of the acquired pipeline leakage signal. The decomposed modal waveforms are shown in fig. 6. To more intuitively demonstrate the reducing power of the auto-change modal decomposition, fig. 7 shows a center frequency fourier spectrum of the resulting modality. The final result is a denoised acoustic signal as shown in fig. 8. As can be seen from fig. 8, the present invention has a superior filtering effect on the channel leakage signal.
In summary, the embodiment of the invention firstly increases constraint criteria by utilizing the residual signal concept on the basis of the variation modal decomposition, constructs an objective function of automatic variation modal decomposition, and solves the problem that the variation modal decomposition algorithm is inaccurate in finding the objective mode; solving a formula of the mode and the center frequency by using an advanced mathematical solving method, so that the problem of overhigh calculation cost caused by redundancy of solving steps of a variation mode decomposition algorithm is solved; the bandwidth of the automatic variation mode decomposition is automatically updated by utilizing the average power concept of the modes, so that the problem that the bandwidth of the variation mode decomposition algorithm cannot be changed along with the optimization stage so as to not obtain the target mode is solved; an automatic iteration condition is set by utilizing the concept of modal energy, and the problem that the signal decomposition effect is poor due to inaccurate parameter setting of a variation modal algorithm is solved; and evaluating the modal effectiveness obtained by automatic variation modal decomposition by utilizing the Litsea distance, so that the pure signal is reconstructed to obtain the filtering purpose. The filtering method is simple, high in accuracy and low in detection cost, and effectively solves the problem that environmental noise interferes with pipeline leakage detection.
A second embodiment of the present invention proposes a pipe leakage filtering system based on automatic variation modal decomposition, the system having program modules corresponding to the steps of the pipe leakage filtering method described above, the steps of the pipe leakage filtering method described above being executed at run-time.
The third embodiment of the invention provides a pipeline leakage detection method based on automatic variation modal decomposition, which comprises the following steps: after the pipeline leakage filtering method is used for filtering the pipeline acoustic wave signal to be detected, the pipeline acoustic wave signal is input into a trained classifier for recognition, so that a recognition result of whether the pipeline is leaked or not is obtained.
A fourth embodiment of the present invention proposes a pipe leakage detection system based on automatic variation modal decomposition, the system having program modules corresponding to the steps of the pipe leakage detection method described above, the steps of the pipe leakage detection method described above being executed at run-time.
While the invention has been described with respect to a limited number of embodiments, those skilled in the art, having benefit of the above description, will appreciate that other embodiments are contemplated within the scope of the invention as described herein. The disclosure of the present invention is intended to be illustrative, but not limiting, of the scope of the invention, which is defined by the appended claims.
Claims (6)
1. The pipeline leakage filtering method based on automatic variation modal decomposition is characterized by comprising the following steps of:
collecting a pipeline acoustic wave signal;
And filtering the pipeline acoustic wave signal, wherein the filtering comprises the following steps: performing variation modal decomposition on the pipeline acoustic wave signal, constructing an objective function of the variation modal decomposition by utilizing a residual signal concept, and performing iterative solution on the objective function to obtain a plurality of intrinsic modes and corresponding center frequencies thereof; the objective function of constructing the variational modal decomposition by using the residual signal concept is as follows: adding a constraint criterion based on the original construction criterion, wherein the constraint criterion is that the energy of the residual signal should be minimized at a frequency with an effective component, and the objective function is expressed as:
Wherein α represents a bandwidth; u k＝uk (t) denotes the kth modality; omega k represents the center frequency corresponding to the kth mode; λ=λ (t) represents a double rise parameter; delta (t) represents dirac distribution; j represents a complex structure, j 2＝-1;βk (t) represents a filter; f (t) represents an input pipeline acoustic signal; f r(t)＝f(t)-uk (t) is a residual signal of the input pipeline acoustic signal except the mode obtained by decomposition; t represents the moment;
the updated formula for each eigenmode and its corresponding center frequency in each iteration is expressed as:
In the method, in the process of the invention, Representing a kth modality in an n+1th iteration of the frequency domain space; /(I)An input pipeline acoustic signal representing a frequency domain space; ω represents the center frequency of the input signal; /(I)Representing a mode obtained by kth decomposition of the frequency domain space; /(I)Representing the center frequency corresponding to the kth mode in the nth iteration;
In the method, in the process of the invention, Representing the center frequency corresponding to the kth mode in the n+1th iteration of the frequency domain space;
After a plurality of eigenmodes and corresponding center frequencies are obtained, carrying out noise reduction treatment on the plurality of eigenmodes to obtain a noise-reduced pipeline signal; the noise reduction process comprises the following steps: calculating the Lith distance between each mode and the original input signal; calculating the slope values of two adjacent Lees, and taking the mode number corresponding to the maximum slope value as a jump point; and carrying out phase reconstruction on all modes positioned in front of the jump points to obtain the noise-reduced pipeline signal.
2. The method for filtering leakage of a pipeline based on automatic variation modal decomposition according to claim 1, wherein in the process of iteratively solving the objective function to obtain a plurality of eigenmodes and their corresponding center frequencies, an updated formula of bandwidth α is improved so that the obtained modes and center frequencies are more accurate; the formula of the bandwidth alpha update is as follows:
Where T represents the sampling time of the input signal.
3. The method for filtering pipeline leakage based on automatic variation modal decomposition according to claim 2, wherein in the process of iteratively solving the objective function to obtain a plurality of eigenmodes and their corresponding center frequencies, the following iteration termination conditions are set: judgingIf the stopping condition of the (b) is satisfied, outputting the eigenmodes and the corresponding center frequencies; wherein/>And/>Respectively representing the power parameters corresponding to the kth-1 mode and the kth mode, wherein the calculation formula is as follows:
In the method, in the process of the invention, Representing a transposed version of the modality.
4. A pipeline leakage filtering system based on automatic variation modal decomposition, characterized in that the system has program modules corresponding to the steps of any of the preceding claims 1-3, the steps of the above pipeline leakage filtering method being executed at run-time.
5. The pipeline leakage detection method based on automatic variation modal decomposition is characterized by comprising the following steps of: the method for filtering the pipeline leakage according to any one of claims 1-3 is used for filtering the pipeline acoustic wave signal to be detected, and then the pipeline acoustic wave signal is input into a trained classifier for recognition so as to obtain a recognition result of whether the pipeline leaks.
6. A system for detecting a pipe leakage based on automatic variation modal decomposition, characterized in that the system has program modules corresponding to the steps of claim 5, wherein the steps of the method for detecting a pipe leakage are executed at run-time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410424127.XA CN118016082B (en) | 2024-04-10 | 2024-04-10 | Pipeline leakage filtering method and system based on automatic variation modal decomposition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410424127.XA CN118016082B (en) | 2024-04-10 | 2024-04-10 | Pipeline leakage filtering method and system based on automatic variation modal decomposition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118016082A CN118016082A (en) | 2024-05-10 |
| CN118016082B true CN118016082B (en) | 2024-06-11 |
Family
ID=90943534
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410424127.XA Active CN118016082B (en) | 2024-04-10 | 2024-04-10 | Pipeline leakage filtering method and system based on automatic variation modal decomposition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118016082B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112013285A (en) * | 2020-08-26 | 2020-12-01 | 辽宁石油化工大学 | Method and device for detecting pipeline leakage point, storage medium and terminal |
| CN115062670A (en) * | 2022-07-14 | 2022-09-16 | 东北石油大学 | Pipeline leakage detection method and system based on MPA-VMD denoising |
| CN116644583A (en) * | 2023-05-30 | 2023-08-25 | 东北石油大学 | Oil and gas pipeline leakage signal preprocessing method and system based on combination of VMD and Frechet distance |
| CN117609702A (en) * | 2023-12-22 | 2024-02-27 | 中国特种设备检测研究院 | Pipeline leakage acoustic emission signal denoising method, system, equipment and medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114742097B (en) * | 2022-03-23 | 2023-05-23 | 大连理工大学 | Optimization method for automatically determining variation modal decomposition parameters based on bearing vibration signals |
-
2024
- 2024-04-10 CN CN202410424127.XA patent/CN118016082B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112013285A (en) * | 2020-08-26 | 2020-12-01 | 辽宁石油化工大学 | Method and device for detecting pipeline leakage point, storage medium and terminal |
| CN115062670A (en) * | 2022-07-14 | 2022-09-16 | 东北石油大学 | Pipeline leakage detection method and system based on MPA-VMD denoising |
| CN116644583A (en) * | 2023-05-30 | 2023-08-25 | 东北石油大学 | Oil and gas pipeline leakage signal preprocessing method and system based on combination of VMD and Frechet distance |
| CN117609702A (en) * | 2023-12-22 | 2024-02-27 | 中国特种设备检测研究院 | Pipeline leakage acoustic emission signal denoising method, system, equipment and medium |
Non-Patent Citations (1)
| Title |
|---|
| 基于VMD-MD的油气管道泄漏信号去噪方法;路敬祎等;《压力容器》;20230530;第40卷(第5期);第44-52页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118016082A (en) | 2024-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111734961B (en) | Natural gas pipeline leakage detection method | |
| CN110671613A (en) | Fluid pipeline leakage signal time delay estimation method based on improved empirical wavelet transform | |
| CN105095912A (en) | Data clustering method and device | |
| Haridy et al. | Optimal average sample number of the SPRT chart for monitoring fraction nonconforming | |
| CN118016082B (en) | Pipeline leakage filtering method and system based on automatic variation modal decomposition | |
| CN115628863A (en) | Fluid pipeline leakage detection method based on parameter optimization variational modal decomposition | |
| CN116644583A (en) | Oil and gas pipeline leakage signal preprocessing method and system based on combination of VMD and Frechet distance | |
| CN117609702A (en) | Pipeline leakage acoustic emission signal denoising method, system, equipment and medium | |
| CN115829157A (en) | Chemical water quality index prediction method based on variational modal decomposition and auto former model | |
| CN117009814A (en) | Engine fault diagnosis method and system based on multi-source information fusion | |
| Chen et al. | A new method for adaptive sequential sampling for learning and parameter estimation | |
| CN117786371A (en) | Temperature monitoring data optimization prediction analysis method and system | |
| CN112013910B (en) | Drainage pipe network flow detection method and device, server and storage medium | |
| CN117541020A (en) | Scheduling management method and system for urban drainage pump station | |
| CN112904412B (en) | Mine microseismic signal P-wave first arrival time extraction method and system | |
| Zhu et al. | Fault feature extraction of rolling element bearing based on EVMD | |
| CN114441111B (en) | Pipeline leakage infrasonic wave signal analysis method and system | |
| Ghosh | Comparative DNN model analysis for detection of various types of optical noise | |
| CN115935797A (en) | Method for realizing engineering optimization based on multi-strategy improved arithmetic optimization algorithm | |
| CN112926147B (en) | Posterior optimization design method for reinforced column shell containing defects | |
| Zhang et al. | Artificial intelligence techniques and cloud computing for wind turbine pitch bearing fault detection | |
| CN113702038B (en) | Fault diagnosis method and system for explosion-proof motor bearing | |
| Huang et al. | Interpretable real-time monitoring of pipeline weld crack leakage based on wavelet multi-kernel network | |
| CN112597425B (en) | Method, device, equipment and medium for detecting abnormal data in flow velocity measurement data | |
| Zhang et al. | 1Department of Electrical and Electronic Engineering, The University of Manchester, Manchester, United Kingdom; 2ETSI Industrial, University of Castilla-La Mancha, Ciudad Real, Spain |
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 |