CN114963030A - Water supply pipeline monitoring method - Google Patents
Water supply pipeline monitoring method Download PDFInfo
- Publication number
- CN114963030A CN114963030A CN202210700812.1A CN202210700812A CN114963030A CN 114963030 A CN114963030 A CN 114963030A CN 202210700812 A CN202210700812 A CN 202210700812A CN 114963030 A CN114963030 A CN 114963030A
- Authority
- CN
- China
- Prior art keywords
- pipeline
- signal
- wavelet
- leakage
- optical cable
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 title claims abstract description 23
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 20
- 230000003287 optical effect Effects 0.000 claims abstract description 43
- 230000008859 change Effects 0.000 claims abstract description 12
- 230000009286 beneficial effect Effects 0.000 claims abstract description 5
- 238000001514 detection method Methods 0.000 claims abstract description 5
- 239000012530 fluid Substances 0.000 claims abstract description 4
- 230000006870 function Effects 0.000 claims description 24
- 238000012545 processing Methods 0.000 claims description 18
- 238000000354 decomposition reaction Methods 0.000 claims description 9
- 238000007635 classification algorithm Methods 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 6
- 239000003292 glue Substances 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 238000013519 translation Methods 0.000 claims description 6
- 238000004804 winding Methods 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 5
- 230000000717 retained effect Effects 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 3
- 230000035772 mutation Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000001228 spectrum Methods 0.000 claims description 3
- 238000010183 spectrum analysis Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 2
- 229910001018 Cast iron Inorganic materials 0.000 description 6
- 229920003023 plastic Polymers 0.000 description 6
- 239000004033 plastic Substances 0.000 description 6
- 238000012706 support-vector machine Methods 0.000 description 4
- 239000002131 composite material Substances 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 229910052751 metal Inorganic materials 0.000 description 2
- 239000002184 metal Substances 0.000 description 2
- 239000004576 sand Substances 0.000 description 2
- 241000894006 Bacteria Species 0.000 description 1
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 229910052782 aluminium Inorganic materials 0.000 description 1
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 1
- 238000005266 casting Methods 0.000 description 1
- 230000003750 conditioning effect Effects 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 238000005034 decoration Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 210000003298 dental enamel Anatomy 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- JEIPFZHSYJVQDO-UHFFFAOYSA-N iron(III) oxide Inorganic materials O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 229920001155 polypropylene Polymers 0.000 description 1
- 229910001220 stainless steel Inorganic materials 0.000 description 1
- 239000010935 stainless steel Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- 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
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A20/00—Water conservation; Efficient water supply; Efficient water use
- Y02A20/15—Leakage reduction or detection in water storage or distribution
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Examining Or Testing Airtightness (AREA)
Abstract
The invention discloses a water supply pipeline monitoring method. The method specifically comprises the following steps: the sensing optical cable on the pipeline is arranged on the pipeline, the signal acquisition host is arranged in the machine room, and the sensing optical cable on the pipeline is connected to the signal acquisition host through a cable; when a leakage event occurs on the pipeline, due to pressure difference inside and outside the pipeline, fluid inside the pipeline rubs with the leakage hole to generate leakage sound waves, and the sound waves are transmitted to the sensing monitoring optical cable through the medium of the pipeline, so that the state of optical signals inside the sensing monitoring optical cable is changed; the signal acquisition host acquires optical signals in the detection optical cable, analyzes the state change of the optical signals through signal analysis processing software, compares the state change with a corresponding event model, and judges whether a leakage event exists or not; when the signal acquisition host detects leakage information, event information is uploaded to the cloud server, and a user can access the cloud server information through the client and check monitoring field event information. The beneficial effects of the invention are: and obtaining a real-time leakage event alarm, and judging the condition of the pipeline leakage event.
Description
Technical Field
The invention relates to the technical field related to pipeline detection, in particular to a water supply pipeline monitoring method.
Background
The water pipe is a water supply pipeline, modern decoration water pipes are constructed in a wall-buried mode, the water pipes are classified into three types, and the first type is a metal pipe, such as a hot-dip cast iron pipe with inner enamel plastics, a copper pipe, a stainless steel pipe and the like. The second type is plastic-clad metal pipes, such as steel-plastic composite pipes, aluminum-plastic composite pipes and the like. The third type is plastic tubes, such as PB tubes, PP-R tubes, etc. In the past, the pipes used for water supply were primarily cast iron pipes. The sand mould cast iron pipe is mainly used outdoors, and the galvanized cast iron pipe is used indoors. But after being used for several years, a large amount of rust scale is easy to generate, bacteria are bred, and the health of a human body is seriously harmed. The state has stipulated that sand mould casting pipe fittings and cold galvanized cast iron pipes are eliminated from 2000, 6, 1, month, the use of hot galvanized cast iron pipes is gradually limited, and aluminum plastic composite pipes, novel plastic pipes and the like are popularized and used.
The existing water supply pipeline monitoring cannot achieve real-time monitoring, and is usually operated after an accident occurs, and great loss is usually caused after the accident occurs.
Disclosure of Invention
The invention provides a water supply pipeline monitoring method capable of monitoring and alarming in real time in order to overcome the defects in the prior art.
In order to achieve the purpose, the invention adopts the following technical scheme:
a water supply pipeline monitoring method specifically comprises the following steps:
(1) the sensing optical cable on the pipeline is arranged on the pipeline, the signal acquisition host is arranged in the machine room, and the sensing optical cable on the pipeline is connected to the signal acquisition host through a cable;
(2) when a leakage event occurs on the pipeline, due to the pressure difference between the inside and the outside of the pipe, fluid in the pipe rubs with the leakage hole to generate leakage sound waves, and the sound waves are transmitted to the sensing monitoring optical cable through the pipe body medium to change the optical signal state in the sensing monitoring optical cable;
(3) the signal acquisition host acquires optical signals in the detection optical cable, analyzes the state change of the optical signals through signal analysis processing software and compares the state change with a corresponding event model to judge whether a leakage event exists or not;
(4) when the signal acquisition host detects the leakage information, the event information is uploaded to the cloud server, and a user can access the cloud server information through the client and check the monitoring field event information.
The water supply pipeline monitoring method comprises a hardware system and a software system, wherein the hardware system comprises the following steps: the system comprises a sensing monitoring optical cable and a signal acquisition host; the software system is composed of signal analysis processing software and a display client; after signal processing is carried out on data collected and transmitted by the hardware system through signal analysis processing software, the software system can obtain classified characteristic signals and then compare the classified characteristic signals with historical actual leakage event characteristic signals to obtain real-time leakage event alarm, judge and detect the pipeline leakage event condition and simultaneously position the specific position of the leakage event in the pipeline (display client).
Preferably, in step (1), the arrangement of the sensing optical cable on the pipeline is as follows: the sensing optical cable is arranged on the pipeline in a winding mode, fixing glue is brushed on the sensing optical cable for fixing after winding, and the fixing glue is fixed on the outer side wall of the pipeline while completely covering the sensing optical cable.
Preferably, in the step (3), after the signal analysis processing software processes the collected and transmitted data, the situation of the pipeline leakage event is judged and detected, and meanwhile, the specific position of the leakage event in the pipeline can also be located, and the specific processing steps are as follows:
(31) signal preprocessing: considering the frequency drift factor of a system laser, the signal can generate slow distortion, and in order to remove the variation trend item, filtering processing is used in advance for the collected signal;
(32) noise screening: performing threshold processing on wavelet domain coefficients of the signals and the noise to realize denoising under the condition that useful signals and the noise are mutually overlapped on a frequency band;
(33) screening of leakage events: and the signals processed before are used as input to carry out characteristic extraction according to events and position parameters, and the extracted signals are used as input of a classification algorithm to carry out event identification and screening and give a final output result.
Preferably, in step (31), the formula of the filtering process is as follows:
the filter used here is a finite-length impulse response filter, H pre (z) is the filter transfer function, N pre Is the order of the filter, a pre (k) Is a coefficient of the k-th order;
such applications are in particular H (z) ═ 1-z -2 The low-frequency part of the collected signal is suppressed by the filter, thereby being beneficial to removing slowly varying interference, flattening the signal and maintaining the signal-to-noise ratio of the signal in the whole frequency spectrum to be consistent so as to be convenient for further frequency spectrum analysis of the signal.
Preferably, in the step (32), specifically: defining the wavelet coefficient by setting a broad value, retaining the main component of the wavelet coefficient greater than the threshold value as an effective signal, removing the main component of the wavelet coefficient smaller than the broad value, and regarding the wavelet coefficient as a noise signal; the operation method comprises the following steps: after f (t) is continuously subjected to wavelet decomposition, wavelet coefficients Cj and k of all scales corresponding to s (t) are obvious in fluctuation, and have larger values at certain positions, and the positions corresponding to the mutation positions of the original signal s (t) contain the change information of the signal; for the noise signal n (t), the distribution of the wavelet coefficients Cj, k corresponding to the noise signal n (t) in each decomposition scale is relatively uniform, and the amplitude of each layer of wavelet coefficients Cj, k tends to become smaller as the decomposition progresses; setting a threshold Th according to different distribution characteristics of respective wavelet coefficients of a useful signal and a noise signal, and when Cj, k is less than Th, considering that the Cj, k at the moment mainly corresponds to the noise signal, and carrying out threshold processing on the noise signal; when Cj, k is greater than Th, considering the Cj, k is corresponding to useful signal, the Cj, k is retained; finally, reconstructing by using the wavelet coefficient subjected to threshold processing and the retained wavelet coefficient to obtain a signal without noise;
wherein the wavelet basis functions are as follows:
in the formula, a is a stretching factor and represents the stretching of the mother wavelet function on a time axis, a >1 represents the stretching, a <1 represents the shrinking, and b is a translation factor and represents the left-right translation of the central position of the mother wavelet function; t is a time variable;
the continuous wavelet transform formula of the arbitrary squared integrable function f (t) is as follows:
W f (a, b) is a function f (t) of continuous wavelet transform, R is the real number domain,. phi. (t) a,b (t) represents the wavelet basis function, t, generated after a, b conditioning of the mother wavelet function t * Representing a complex conjugate operation.
Preferably, in step (33), the classification algorithm is specifically: giving a sample set, wherein samples in the set belong to two types of samples respectively, training an SVM classifier, namely searching a hyperplane, and separating the two types of samples to the maximum extent, so that the samples of the same type with the maximum quantity are separated on the same side of the hyperplane, and the distance between the two types of samples and the hyperplane is maximized; converting the classification problem into an optimization problem by inputting the characteristic data, wherein the optimization problem is represented by the following formula:
wherein, w is characteristic data input in a vector or matrix form; zeta i For the relaxation factor, what is described is the acceptance of individual out-of-plane samples; c is a penalty coefficient used for describing tolerance degree of classification errors; y is i Representing class labels, the value is usually +/-1, x in the case of binary classification i Representing the input data vector, omega and b being the normal vector and intercept, respectively, of the hyperplane; and comparing the obtained classified characteristic signals with historical actual leakage event characteristic signals to obtain real-time leakage event alarm.
The invention has the beneficial effects that: after signal processing is carried out on the collected and transmitted data through signal analysis processing software, classified characteristic signals are obtained and then can be compared with historical and actual leakage event characteristic signals, real-time leakage event alarm is obtained, the condition of a pipeline leakage event is judged and detected, and meanwhile the specific position of the leakage event in the pipeline can be located.
Drawings
FIG. 1 is a diagram of the method architecture of the present invention;
FIG. 2 is a schematic view of a duct cable arrangement according to the present invention;
FIG. 3 is a graph of the amplitude-frequency response of the filter of the present invention;
FIG. 4 is a schematic diagram of the classification algorithm of the present invention.
Detailed Description
The invention is further described with reference to the following figures and detailed description.
In the embodiment shown in fig. 1, a method for monitoring a water supply pipeline specifically includes the following steps:
(1) the sensing optical cable on the pipeline is arranged on the pipeline, the signal acquisition host is arranged in the machine room, and the sensing optical cable on the pipeline is connected to the signal acquisition host through a cable;
as shown in fig. 2, the arrangement of the sensing cables on the pipeline is as follows: the sensing optical cable is arranged on the pipeline in a winding mode, fixing glue is brushed on the sensing optical cable for fixing after winding, and the fixing glue is fixed on the outer side wall of the pipeline while completely covering the sensing optical cable.
(2) When a leakage event occurs on the pipeline, due to pressure difference inside and outside the pipeline, fluid inside the pipeline rubs with the leakage hole to generate leakage sound waves, and the sound waves are transmitted to the sensing monitoring optical cable through the medium of the pipeline, so that the state of optical signals inside the sensing monitoring optical cable is changed;
(3) the signal acquisition host acquires optical signals in the detection optical cable, analyzes the state change of the optical signals through signal analysis processing software and compares the state change with a corresponding event model to judge whether a leakage event exists or not; after the signal analysis processing software processes the collected and transmitted data, the pipeline leakage event condition is judged and detected, and meanwhile, the specific position of the leakage event in the pipeline can be positioned, and the specific processing steps are as follows:
(31) signal preprocessing: considering the frequency drift factor of the system laser, the signal can generate slow distortion, and in order to remove the variation trend item, filtering processing is used in advance for collecting the signal; the formula of the filtering process is as follows:
the filter used here is a finite-length impulse response filter, H pre (z) is the filter transfer function, N pre Is the order of the filter, a pre (k) Is a coefficient of the k-th order;
such applications are in particular H (z) ═ 1-z -2 The amplitude-frequency response curve is shown in fig. 3. The low-frequency part of the collected signal is suppressed by the filter, thereby being beneficial to removing slowly varying interference, flattening the signal and maintaining the signal-to-noise ratio of the signal in the whole frequency spectrum to be consistent so as to be convenient for further frequency spectrum analysis of the signal.
(32) Noise screening: performing threshold processing on wavelet domain coefficients of the signals and the noise to realize denoising under the condition that useful signals and the noise are mutually overlapped on a frequency band; the main idea is as follows: the effective signal and the noise signal have different statistical characteristics after wavelet transformation, generally speaking, the energy of the effective signal corresponds to a wavelet coefficient with a larger amplitude in each scale, and the distribution in each scale is related to the characteristics of the signal; and the wavelet coefficient of the noise is distributed more evenly in all scales and has smaller amplitude.
The method specifically comprises the following steps: defining the wavelet coefficient by setting a broad value, retaining the main component of the wavelet coefficient greater than the threshold value as an effective signal, removing the main component of the wavelet coefficient smaller than the broad value, and regarding the wavelet coefficient as a noise signal; the operation method comprises the following steps: after f (t) is continuously subjected to wavelet decomposition, wavelet coefficients Cj and k of all scales corresponding to s (t) are obvious in fluctuation, and have larger values at certain positions, and the positions corresponding to the mutation positions of the original signal s (t) contain the change information of the signal; for the noise signal n (t), the distribution of the wavelet coefficients Cj, k corresponding to the noise signal n (t) in each decomposition scale is relatively uniform, and the amplitude of each layer of wavelet coefficients Cj, k tends to become smaller as the decomposition progresses; setting a threshold Th according to different distribution characteristics of respective wavelet coefficients of a useful signal and a noise signal, and when Cj, k is less than Th, considering that the Cj, k at the moment mainly corresponds to the noise signal, and carrying out threshold processing on the noise signal; when Cj, k is greater than Th, considering the Cj, k is corresponding to useful signal, the Cj, k is retained; finally, reconstructing by using the wavelet coefficient subjected to threshold processing and the retained wavelet coefficient to obtain a signal without noise;
wherein the wavelet basis functions are as follows:
in the formula, a is a stretching factor and represents the stretching of the mother wavelet function on a time axis, a >1 represents the stretching, a <1 represents the shrinking, and b is a translation factor and represents the left-right translation of the central position of the mother wavelet function; t is a time variable;
the continuous wavelet transform formula of the arbitrary squared integrable function f (t) is as follows:
W f (a, b) is a function f (t) of continuous wavelet transform, R is the real number domain,. phi. (t) a,b (t) represents the wavelet basis functions, ψ, generated after the mother wavelet function ψ (t) has been adjusted by a, b * Representing a complex conjugate operation.
(33) Screening of leakage events: the signals processed before are used as input to extract features according to events and position parameters, and the extracted signals are used as input of a classification algorithm to identify and screen the events and give a final output result;
the classification algorithm adopts a Support Vector Machine (SVM) in the conventional machine learning algorithm, takes two classification problems as an example, and as shown in fig. 4, the classification algorithm specifically includes: a sample set is given, samples in the set belong to two types of samples respectively, a hyperplane is found by training an SVM classifier, the two types of samples are separated to the maximum extent, the same type of samples with the maximum quantity are divided on the same side of the hyperplane, the distance between the two types of samples and the hyperplane is maximized, and the multi-classification problem can be solved by expanding two types of samples.
The core problem of the algorithm is that the classification problem is converted into an optimization problem by inputting feature data, wherein the optimization problem is shown in the following formula:
wherein, w is characteristic data input in a vector or matrix form; zeta i For the relaxation factor, what is described is the acceptance of individual out-of-plane samples; c is a penalty coefficient used for describing tolerance degree of classification errors; y is i Representing class labels, the value is usually +/-1, x in the case of binary classification i Representing the input data vector, omega and b being the normal vector and intercept, respectively, of the hyperplane; and comparing the obtained classified characteristic signals with historical actual leakage event characteristic signals to obtain real-time leakage event alarm.
(4) When the signal acquisition host detects leakage information, event information is uploaded to the cloud server, and a user can access the cloud server information through the client and check monitoring field event information.
After signal processing is carried out on data collected and transmitted by the hardware system through signal analysis processing software, the software system can obtain classified characteristic signals and then compare the classified characteristic signals with historical actual leakage event characteristic signals to obtain real-time leakage event alarm, judge and detect the pipeline leakage event condition and simultaneously position the specific position of the leakage event in the pipeline (display client).
Claims (6)
1. A water supply pipeline monitoring method is characterized by comprising the following steps:
(1) the sensing optical cable on the pipeline is arranged on the pipeline, the signal acquisition host is arranged in the machine room, and the sensing optical cable on the pipeline is connected to the signal acquisition host through a cable;
(2) when a leakage event occurs on the pipeline, due to pressure difference inside and outside the pipeline, fluid inside the pipeline rubs with the leakage hole to generate leakage sound waves, and the sound waves are transmitted to the sensing monitoring optical cable through the medium of the pipeline, so that the state of optical signals inside the sensing monitoring optical cable is changed;
(3) the signal acquisition host acquires optical signals in the detection optical cable, analyzes the state change of the optical signals through signal analysis processing software and compares the state change with a corresponding event model to judge whether a leakage event exists or not;
(4) when the signal acquisition host detects leakage information, event information is uploaded to the cloud server, and a user can access the cloud server information through the client and check monitoring field event information.
2. A method for monitoring a water supply pipeline according to claim 1, wherein in step (1), the sensor cable is arranged on the pipeline in the following manner: the sensing optical cable is arranged on the pipeline in a winding mode, fixing glue is brushed on the sensing optical cable for fixing after winding, and the fixing glue is fixed on the outer side wall of the pipeline while completely covering the sensing optical cable.
3. The method for monitoring the water supply pipeline according to claim 1 or 2, wherein in the step (3), after the signal analysis processing software processes the collected and transmitted data, the situation of the pipeline leakage event is judged and detected, and meanwhile, the specific position of the leakage event in the pipeline can be positioned, and the specific processing steps are as follows:
(31) signal preprocessing: considering the frequency drift factor of a system laser, the signal can generate slow distortion, and in order to remove the variation trend item, filtering processing is used in advance for the collected signal;
(32) noise screening: performing threshold processing on wavelet domain coefficients of the signals and the noise to realize denoising under the condition that useful signals and the noise are mutually overlapped on a frequency band;
(33) screening of leakage events: and the signals processed before are used as input to carry out characteristic extraction according to events and position parameters, and the extracted signals are used as input of a classification algorithm to carry out event identification and screening and give a final output result.
4. A method for monitoring a water supply pipeline according to claim 3, wherein in step (31), the filtering process is formulated as follows:
the filter used here is a finite-length impulse response filter, H pre (z) is the filter transfer function, N pre Is the order of the filter, a pre (k) Is a coefficient of the k-th order;
such applications are in particular H (z) ═ 1-z -2 The low-frequency part of the collected signal is suppressed by the filter, thereby being beneficial to removing slowly varying interference, flattening the signal and maintaining the signal-to-noise ratio of the signal in the whole frequency spectrum to be consistent so as to be convenient for further frequency spectrum analysis of the signal.
5. A method for monitoring water supply pipelines according to claim 3, characterized in that in step (32) it comprises in particular: defining the wavelet coefficient by setting a broad value, retaining the main component of the wavelet coefficient greater than the threshold value as an effective signal, removing the main component of the wavelet coefficient smaller than the broad value, and regarding the wavelet coefficient as a noise signal; the operation method comprises the following steps: after f (t) is continuously subjected to wavelet decomposition, wavelet coefficients Cj and k of all scales corresponding to s (t) are obvious in fluctuation, and have larger values at certain positions, and the positions corresponding to the mutation positions of the original signal s (t) contain the change information of the signal; for the noise signal n (t), the distribution of the wavelet coefficients Cj, k corresponding to the noise signal n (t) in each decomposition scale is relatively uniform, and the amplitude of each layer of wavelet coefficients Cj, k tends to become smaller as the decomposition progresses; setting a threshold Th according to different distribution characteristics of respective wavelet coefficients of a useful signal and a noise signal, and when Cj, k is smaller than Th, considering that the Cj, k at the moment mainly corresponds to the noise signal, and carrying out threshold processing on the noise signal; when Cj, k is larger than Th, considering the Cj, k is corresponding to useful signal, then keeping the Cj, k; finally, reconstructing by using the wavelet coefficient subjected to threshold processing and the retained wavelet coefficient to obtain a signal without noise;
wherein the wavelet basis functions are as follows:
in the formula, a is a stretching factor and represents the stretching of the mother wavelet function on a time axis, a is more than 1 and represents the stretching, a is less than 1 and represents the shrinking, and b is a translation factor and represents the left-right translation of the center position of the mother wavelet function; t is a time variable;
the continuous wavelet transform formula of the arbitrary squared integrable function f (t) is as follows:
W f (a, b) is a function f (t) continuous wavelet transform, R is the real number domain, # a,b (t) represents the wavelet basis functions, ψ, generated after the mother wavelet function ψ (t) has been adjusted by a, b * Representing a complex conjugate operation.
6. A method for monitoring a water supply pipeline according to claim 3, wherein in step (33) the classification algorithm is embodied as: giving a sample set, wherein samples in the set belong to two types of samples respectively, training an SVM classifier, namely searching a hyperplane, and separating the two types of samples to the maximum extent, so that the samples of the same type with the maximum quantity are separated on the same side of the hyperplane, and the distance between the two types of samples and the hyperplane is maximized; converting the classification problem into an optimization problem by inputting the characteristic data, wherein the optimization problem is represented by the following formula:
wherein, w is characteristic data input in a vector or matrix form; zeta i For the relaxation factor, what is described is the acceptance of individual out-of-plane samples; c is a penalty coefficient used for describing tolerance degree of classification errors; y is i Representing class labels, the value is usually +/-1, x in the case of binary classification i Representing the input data vector, omega and b being the normal vector and intercept, respectively, of the hyperplane; and comparing the obtained classified characteristic signals with historical actual leakage event characteristic signals to obtain real-time leakage event alarm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210700812.1A CN114963030A (en) | 2022-06-21 | 2022-06-21 | Water supply pipeline monitoring method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210700812.1A CN114963030A (en) | 2022-06-21 | 2022-06-21 | Water supply pipeline monitoring method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114963030A true CN114963030A (en) | 2022-08-30 |
Family
ID=82964482
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210700812.1A Pending CN114963030A (en) | 2022-06-21 | 2022-06-21 | Water supply pipeline monitoring method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114963030A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115507817A (en) * | 2022-11-22 | 2022-12-23 | 杭州水务数智科技股份有限公司 | Underground pipe gallery duct piece settlement detection method based on distributed optical fiber sensor |
| CN116805061A (en) * | 2023-05-10 | 2023-09-26 | 杭州水务数智科技股份有限公司 | Leakage event judging method based on optical fiber sensing |
| CN117151675A (en) * | 2023-03-16 | 2023-12-01 | 杭州水务数智科技股份有限公司 | Remote operation and maintenance method and system based on video monitoring and encryption |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101551064A (en) * | 2009-05-22 | 2009-10-07 | 重庆大学 | Water supply pipe leakage detection locating signal processing method |
| US20140290343A1 (en) * | 2013-03-28 | 2014-10-02 | Exxonmobil Research And Engineering Company | Method and system for detecting a leak in a pipeline |
| CN107590516A (en) * | 2017-09-16 | 2018-01-16 | 电子科技大学 | Gas pipeline leak detection recognition methods based on Fibre Optical Sensor data mining |
| CN110332466A (en) * | 2019-07-03 | 2019-10-15 | 上海市城市建设设计研究总院（集团）有限公司 | Water supply line leak detection method based on distribution type fiber-optic sonic transducer |
| CN110410684A (en) * | 2019-07-04 | 2019-11-05 | 华中科技大学 | Non-intruding distributed optical fiber pipeline based on acoustic detection monitors system and method |
| CN111623249A (en) * | 2020-05-29 | 2020-09-04 | 承德石油高等专科学校 | Intelligent pipe capable of sensing leakage position and parameters of pipeline |
| CN111911815A (en) * | 2020-07-06 | 2020-11-10 | 天津精仪精测科技有限公司 | Water pipeline safety early warning system based on optical fiber interferometer |
| CN215262312U (en) * | 2021-05-31 | 2021-12-21 | 浙江大学 | Multi-parameter multi-mode high-precision pipeline leakage monitoring and positioning system |
| KR20220071542A (en) * | 2020-11-24 | 2022-05-31 | 주식회사 아리안 | Leakage detection system through sound wave detection in optical cables |
| 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 |
-
2022
- 2022-06-21 CN CN202210700812.1A patent/CN114963030A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101551064A (en) * | 2009-05-22 | 2009-10-07 | 重庆大学 | Water supply pipe leakage detection locating signal processing method |
| US20140290343A1 (en) * | 2013-03-28 | 2014-10-02 | Exxonmobil Research And Engineering Company | Method and system for detecting a leak in a pipeline |
| CN107590516A (en) * | 2017-09-16 | 2018-01-16 | 电子科技大学 | Gas pipeline leak detection recognition methods based on Fibre Optical Sensor data mining |
| CN110332466A (en) * | 2019-07-03 | 2019-10-15 | 上海市城市建设设计研究总院（集团）有限公司 | Water supply line leak detection method based on distribution type fiber-optic sonic transducer |
| CN110410684A (en) * | 2019-07-04 | 2019-11-05 | 华中科技大学 | Non-intruding distributed optical fiber pipeline based on acoustic detection monitors system and method |
| CN111623249A (en) * | 2020-05-29 | 2020-09-04 | 承德石油高等专科学校 | Intelligent pipe capable of sensing leakage position and parameters of pipeline |
| CN111911815A (en) * | 2020-07-06 | 2020-11-10 | 天津精仪精测科技有限公司 | Water pipeline safety early warning system based on optical fiber interferometer |
| KR20220071542A (en) * | 2020-11-24 | 2022-05-31 | 주식회사 아리안 | Leakage detection system through sound wave detection in optical cables |
| CN215262312U (en) * | 2021-05-31 | 2021-12-21 | 浙江大学 | Multi-parameter multi-mode high-precision pipeline leakage monitoring and positioning 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 |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115507817A (en) * | 2022-11-22 | 2022-12-23 | 杭州水务数智科技股份有限公司 | Underground pipe gallery duct piece settlement detection method based on distributed optical fiber sensor |
| CN117151675A (en) * | 2023-03-16 | 2023-12-01 | 杭州水务数智科技股份有限公司 | Remote operation and maintenance method and system based on video monitoring and encryption |
| CN117151675B (en) * | 2023-03-16 | 2024-04-09 | 杭州水务数智科技股份有限公司 | Remote operation and maintenance method and system based on video monitoring and encryption |
| CN116805061A (en) * | 2023-05-10 | 2023-09-26 | 杭州水务数智科技股份有限公司 | Leakage event judging method based on optical fiber sensing |
| CN116805061B (en) * | 2023-05-10 | 2024-04-12 | 杭州水务数智科技股份有限公司 | Leakage event judging method based on optical fiber sensing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114963030A (en) | Water supply pipeline monitoring method | |
| CN112364779B (en) | Underwater sound target identification method based on signal processing and deep-shallow network multi-model fusion | |
| CN108827605B (en) | Mechanical fault feature automatic extraction method based on improved sparse filtering | |
| CN108830127B (en) | Rotary machine fault feature intelligent diagnosis method based on deep convolutional neural network structure | |
| Wang et al. | A new intelligent bearing fault diagnosis method using SDP representation and SE-CNN | |
| CN110245608B (en) | Underwater target identification method based on half tensor product neural network | |
| CN113707176B (en) | Transformer fault detection method based on acoustic signal and deep learning technology | |
| CN107702922B (en) | Rolling bearing fault diagnosis method based on LCD and stacking automatic encoder | |
| CN111933188A (en) | Sound event detection method based on convolutional neural network | |
| CN112418013A (en) | Complex working condition bearing fault diagnosis method based on meta-learning under small sample | |
| CN108630209B (en) | Marine organism identification method based on feature fusion and deep confidence network | |
| CN108648764B (en) | Rainfall measurement system based on rainwater knocking sound identification and measurement method thereof | |
| CN109033632B (en) | Trend prediction method based on deep quantum neural network | |
| CN101984340B (en) | Method for identifying flow type of soft grain two-phase turbulence based on artificial intelligence | |
| CN109538944B (en) | Pipeline leakage detection method | |
| CN109443717B (en) | On-load tap-changer mechanical fault on-line monitoring method | |
| CN113076920B (en) | Intelligent fault diagnosis method based on asymmetric domain confrontation self-adaptive model | |
| CN112686144B (en) | Ore ball milling process load identification method based on grinding sound signals | |
| CN112052712B (en) | Power equipment state monitoring and fault identification method and system | |
| CN115762533A (en) | Bird song classification and identification method and device | |
| CN116935892A (en) | Industrial valve anomaly detection method based on audio key feature dynamic aggregation | |
| CN110458071B (en) | DWT-DFPA-GBDT-based optical fiber vibration signal feature extraction and classification method | |
| CN111508528B (en) | No-reference audio quality evaluation method and device based on natural audio statistical characteristics | |
| CN110865375B (en) | Underwater target detection method | |
| CN116935894A (en) | Micro-motor abnormal sound identification method and system based on time-frequency domain mutation characteristics |
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 |