CN113758627B - Water supply network transient flow event detection method - Google Patents
Water supply network transient flow event detection method Download PDFInfo
- Publication number
- CN113758627B CN113758627B CN202110938339.6A CN202110938339A CN113758627B CN 113758627 B CN113758627 B CN 113758627B CN 202110938339 A CN202110938339 A CN 202110938339A CN 113758627 B CN113758627 B CN 113758627B
- Authority
- CN
- China
- Prior art keywords
- time scale
- time
- frequency
- water supply
- transient flow
- 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
- 230000001052 transient effect Effects 0.000 title claims abstract description 57
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 33
- 238000001514 detection method Methods 0.000 title abstract description 17
- 238000000034 method Methods 0.000 claims abstract description 39
- 238000012544 monitoring process Methods 0.000 claims abstract description 29
- 238000001228 spectrum Methods 0.000 claims abstract description 12
- 238000005070 sampling Methods 0.000 claims description 30
- 238000004364 calculation method Methods 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 9
- 230000001960 triggered effect Effects 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 2
- 238000005457 optimization Methods 0.000 claims description 2
- 238000005259 measurement Methods 0.000 claims 1
- 230000004044 response Effects 0.000 abstract description 4
- 230000036541 health Effects 0.000 abstract description 2
- 101100450325 Arabidopsis thaliana HDG3 gene Proteins 0.000 description 4
- 102100022002 CD59 glycoprotein Human genes 0.000 description 3
- 101000897400 Homo sapiens CD59 glycoprotein Proteins 0.000 description 3
- 101100129496 Arabidopsis thaliana CYP711A1 gene Proteins 0.000 description 2
- 101100129499 Arabidopsis thaliana MAX2 gene Proteins 0.000 description 2
- 101100083446 Danio rerio plekhh1 gene Proteins 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000004880 explosion Methods 0.000 description 2
- 238000011897 real-time detection Methods 0.000 description 2
- 101100382854 Arabidopsis thaliana CCD7 gene Proteins 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004886 process control Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L19/00—Details of, or accessories for, apparatus for measuring steady or quasi-steady pressure of a fluent medium insofar as such details or accessories are not special to particular types of pressure gauges
-
- 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
- G01F—MEASURING VOLUME, VOLUME FLOW, MASS FLOW OR LIQUID LEVEL; METERING BY VOLUME
- G01F1/00—Measuring the volume flow or mass flow of fluid or fluent solid material wherein the fluid passes through a meter in a continuous flow
- G01F1/05—Measuring the volume flow or mass flow of fluid or fluent solid material wherein the fluid passes through a meter in a continuous flow by using mechanical effects
- G01F1/34—Measuring the volume flow or mass flow of fluid or fluent solid material wherein the fluid passes through a meter in a continuous flow by using mechanical effects by measuring pressure or differential pressure
Abstract
The invention discloses a detection method for a transient flow event of a water supply network. Firstly, calculating the daily pressure signal frequency spectrum of a pipe network monitoring point, and determining a time scale grade; secondly, calculating the extremely poor value of the monitoring points of the pipe network under different daily pressure scales; and then calculating the range threshold under different time scales, and finally detecting the transient event of the measured pressure signal. Compared with the traditional water supply network transient flow event detection method, the method provided by the invention has the advantages of wide frequency coverage, timely response and the like, and the method fully utilizes the range index to measure the signal fluctuation, avoids the conventional standard deviation index, has small calculated amount and reduces the calculated power consumption, is a statistical-based lightweight characteristic identification algorithm, is particularly suitable for front-end intelligent node application, and further provides convenience for low-power consumption real-time health monitoring of the water supply network.
Description
Technical Field
The invention belongs to the field of water supply networks, and particularly relates to a detection method for transient flow events of a water supply network.
Background
In the running process of the water supply network, due to water consumption change, pump set start-stop switching, quick valve opening and closing, even accident pump stopping, valve closing and rush repair, the hydraulic load of the network system can be quickly changed, transient working condition change in a pipeline is often caused, a large amplitude of pressure fluctuation is formed, a water hammer is formed in severe cases, the network is damaged, and even a pipe explosion accident is caused.
Advanced low-power-consumption high-precision sensing and processing technology, such as a high-frequency pressure gauge, is utilized to perform transient flow monitoring on a water supply pipe network, so that pipe explosion detection and water hammer protection can be effectively developed, and healthy operation of the pipe network is ensured [1] . Traditional transient event detection methods include accumulation and sum (CUSUM) [2] And wavelet transforms (Wavelet Transform, WT) [3] The method. However, CUSUM has a slow response problem, WTs have a signal transition sensitivity problem, and a more serious bottleneck is: the two detection algorithms have large calculated amount and are not suitable for being applied to the front-end intelligent node.
In actual monitoring, high frequency is often required to collect pressure signal data, and all high frequency data are uploaded not only by the bandwidth limitation of a wireless network [4] And the uploading power consumption is limited by the battery capacity of the front-end intelligent node. In fact, all the high-frequency and high-precision data are periodically sent back to the cloud server for processing, so that the cost is high, the instantaneity is poor, and the practicability is not strong. That is, the detection of the transient flow event is performed on the edge equipment (i.e. the front-end intelligent node) as much as possible, the transient flow process data is uploaded to the cloud server, and the distributed and event-driven data acquisition, transmission and analysis method is adopted, so that the real-time monitoring task of the water supply network can be effectively supported.
Document [4]]A transient flow monitoring method is provided, namely a sensor signal peak trigger recording method: the first sensor signal at the next second detects the absolute value x 1 When the initial threshold value and the absolute difference delta of the previous second are larger than each other, triggering the MCU module to record the signal value of the sensor in the unit time (frequency) of peak value recording; the first sensor signal at the nth second detects the absolute value x N1 When the absolute difference delta and the stop threshold of the previous second are smaller, the peak value recording is stopped, and the sensor signal data is recorded only at set time intervals. The method is effective for online water hammer detection of the water pipe, because the water hammer is generally high-frequency (the sampling frequency is usually 100 Hz-250 Hz, and signals are collected), but is not applicable to transient flow signal detection with concurrent high and low frequency in the water supply pipe network. In addition, the method needs to calculate the average value and standard deviation of the samples every second, and has high calculation cost.
[1]Whittle,A.J.,M.Allen,A.Preis,and M.Iqbal."Sensor Networks for Monitoring and Control of Water Distribution Systems."6th International Conference on Structural Health Monitoring of Intelligent Infrastructure(SHMII 2013),Hong Kong,December 9-11,2013.
[2]Shin Je Lee；Gibaek Lee；Jung Chul Suh；and Jong Min Lee,Online Burst Detection and Location of Water Distribution Systems and Its Practical Applications,Journal of Water Resources Planning and Management,Volume 142Issue 1-January 2016
[3]Seshan Srirangarajan·Michael Allen·Ami Preis·Mudasser Iqbal·Hock Beng Lim·Andrew J.Whittle,Wavelet-based Burst Event Detection and Localization in Water Distribution Systems,Journal of Signal Process System(2013)72:1–16
[4] 202010223297.3A transient flow monitoring method and a multichannel water hammer detector are disclosed in the patent publication No. CN 111442799 A,2020.07.24.
Disclosure of Invention
Aiming at the problems of wide frequency range of transient flow signals of a water supply network and complex calculation and high power consumption of a conventional detection algorithm, the invention adopts a time sequence data multi-scale range statistics process control SPC method to identify the characteristics in pressure signals and realize transient flow event detection.
The method of the invention comprises the following steps:
and step 1, calculating the daily pressure signal frequency spectrum of the monitoring points of the pipe network, and determining the time scale level.
And (3) carrying out frequency spectrum calculation on continuously collected monitoring point pressure signals (not less than 1 week) by adopting a fast Fourier transform algorithm (FFT) to obtain a spectrogram.
Ordering the frequency spectrum which is 3 times larger than the noise amplitude according to the frequency to obtain a transient flow minimum frequency f min And maximum frequency f max 。
According to f min And f max Determining a time scale level: the general time scale is divided into 2-3 stages, stage 1 can analyze the maximum frequency f max Signal, level 2 or 3 analyzable minimum frequency f min A signal.
The frequency range of the transient flow pressure signal of the water supply network is generally between tenths of hertz and several hertz. Preferably, at a sampling period of t=1/f s Is the minimum timing unit (sampling times n=f in1 second) s ) The three-level time scale is defined as: t1=n×t=1 second, t2=10×n×t=10 seconds, and t3=10×10×n×t=100 seconds.
The monitoring point adopts a high-frequency and high-precision intelligent pressure gauge (intelligent node), continuously and rapidly detects water supply pressure, the sampling precision is more than 0.5 level, and the sampling frequency f s (typically. Gtoreq.10 Hz), 7X 24 samples were taken in real time.
And 2, calculating the extreme values of the monitoring points of the pipe network under different time scales.
The polar difference calculation formula at different time scales:
extremely bad at TS1 scale:
R1＝Max(x 1 ,x 2 ,…,x i ,…,x n )-Min(x 1 ,x 2 ,…,x i ,…,x n ) (1)
extremely bad at TS2 scale:
R2＝Max(x 1 ,x 2 ,…,x i ,…,x 10n )-Min(x 1 ,x 2 ,…,x i ,…,x 10n ) (2)
extremely bad at TS3 scale:
R3＝Max(x 1 ,x 2 ,…,x i ,…,x 100n )-Min(x 1 ,x 2 ,…,x i ,…,x 100n ) (3)
wherein x is i For the ith pressure sampling value under a certain scale, max (), min () is the maximum value and the minimum value in the time sequence.
And continuously calculating the continuous range under different scales for the continuously collected monitoring point pressure signals (not less than 1 week).
Under TS1 scale:
obtaining R1 polar difference set { R1 } 1 ,R1 2 ,…,R1 j ,…,R1 J }. Here, xn i And x1 i+1 Is a continuous pressure sampling value, J is a TS1 time scale sequence number, and J is a total sequence number of the TS1 time scale.
Similar calculation can obtain R2 polar difference value set { R2 under TS2 scale 1 ,R2 2 ,…,R2 k ,…,R2 K R3 polar difference set { R3 } and TS3 scale 1 ,R3 2 ,…,R3 m ,…,R3 M K, m are the TS2 and TS3 time scale sequence numbers, K, M is the total sequence number of the TS2 and TS3 time scale sequence numbers.
Step 3, calculating the range threshold under different time scales.
The mean mu and standard deviation sigma of the polar difference value sets of R1, R2 and R3 are respectively calculated, and the calculation formula is as follows:
according to the Laida criterion (3 sigma criterion), taking mu+3 sigma as the upper control limit, the upper limit of the range control under different scales can be determined to form a range threshold value:
under TS1 scale:
under TS2 scale:
under TS3 scale:
preferably, in the steps 1 to 3, except for data collection and uploading at the front-end intelligent node, the rest complex calculation (including frequency spectrum, range, threshold and other calculation) is completed on the cloud server. The front-end intelligent node only needs to receive the optimization parameters of the cloud server, including time scale classification, an extremely poor threshold value and the like.
And 4, detecting transient flow events of the measured pressure signals.
The front-end intelligent node carries out transient flow event real-time detection in the pressure signal acquisition process according to the time scale classification, the range threshold value and other parameters:
4-1, the front-end intelligent node is according to fixed frequency f s Sampling, in which, from the beginning of sampling (generally beginning at the full second), the actual pressure data is recorded normally, and the sample is compared and recordedPressure maxima MAX1/MAX2/MAX3 and minima MIN1/MIN2/MIN3 at different time scales.
4-2, calculating the range R1 according to the formula (1) after every 1 TS1 time scale sampling is completed j The method comprises the steps of carrying out a first treatment on the surface of the Per 1 TS2 time scale sampling, the range R2 is calculated according to the formula (2) k The method comprises the steps of carrying out a first treatment on the surface of the Per 1 TS3 time scale sampling, the range R3 is calculated according to the formula (3) m 。
4-3, the range R1 at 1 TS1 time scale per completion j Comparing the transient event signal with a control upper limit UCL1 threshold value, and triggering a transient event signal if the transient event signal exceeds the control upper limit UCL1 threshold value; extremely poor R2 at 1 TS2 time scale per completion k Comparing the transient event signal with a control upper limit UCL2 threshold value, and triggering a transient event signal if the transient event signal exceeds the control upper limit UCL2 threshold value; extremely poor R3 at 1 TS3 time scale per completion m The transient event signal is triggered if the control upper UCL3 threshold is exceeded.
The comparison method only relates to simple addition and subtraction calculation, is simpler than CUSUM and WT algorithm, overcomes the defects of slow CUSUM response, sensitive WT algorithm signal conversion and the like, reduces the calculation power consumption of the front-end intelligent node, and prolongs the service time of the front-end intelligent node.
Preferably, if the front-end intelligent node detects a transient flow event, high-frequency pressure data of a period of time (1-2 minutes) before and after the triggering moment can be immediately uploaded to the cloud server according to the transient flow characteristics of the water supply network, and the cloud server is triggered to respond to and process the transient flow signal in time; if no transient event is detected, the low-frequency pressure data is uploaded to the cloud server at regular intervals (e.g. 5 minutes), so that the data transmission amount is reduced, and the power consumption is saved.
Compared with the traditional water supply network transient flow event detection method, the method has the advantages of wide frequency coverage, timely response and the like, and the method fully utilizes the range index to measure the signal fluctuation, avoids the conventional standard deviation index, has small calculated amount and reduces the calculated power consumption, is a statistical-based lightweight characteristic identification method, is particularly suitable for front-end intelligent node application, and further provides convenience for low-power consumption real-time health monitoring of the water supply network.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a flow chart of transient event detection in the method of the present invention;
the embodiment of fig. 3 illustrates a transient event detection effect diagram.
Detailed Description
A certain water department monitors high-frequency pressure of a local high-risk pipe network, 10 monitoring points adopt high-frequency and high-precision intelligent pressure gauges (intelligent nodes), water supply pressure is continuously and rapidly detected, sampling precision is above 0.5 level, sampling frequency is 10Hz, and 7 multiplied by 24 real-time sampling is carried out. The embodiment of the present invention will now be described in further detail with reference to the flowchart of the method of the present invention (fig. 1) and the flowchart of the method of the present invention (fig. 2) by taking the example of detecting a transient event at the point 9# as an example, but the method of the present invention is not limited to this example.
And step 1, calculating the daily pressure signal frequency spectrum of the monitoring points of the pipe network, and determining the time scale level.
And continuously acquiring monitoring point pressure signals of the 9# measuring points for 1 week, and performing spectrum calculation by adopting a fast Fourier transform algorithm (FFT) to obtain a spectrogram.
Ordering the frequency spectrum which is 3 times larger than the noise amplitude according to the frequency to obtain a transient flow minimum frequency f min Approximately 0.17Hz and maximum frequency f max ≈2.8Hz。
According to f min And f max Dividing the time scale into 2 levels, wherein the 1 st level can analyze the maximum frequency f max Signal, level 2 analyzable minimum frequency f min A signal.
With sampling period t=1/f s Is the minimum timing unit (sampling times n=f in1 second) s =10 times), the secondary time scale is defined as: t1=n×t=1 second, t2=10×n×t=10 seconds.
And 2, calculating the extreme values of the monitoring points of the pipe network under different time scales.
Continuously acquiring pressure signals of monitoring points for 1 week, and continuously performing range calculation under different scales: calculating according to a formula (4) to obtain an R1 polar difference set { R1 } under TS1 scale 1 ,R1 2 ,…,R1 j ,…,R1 J }. J is the TS1 time scale sequence number, and J is the total sequence number of the TS1 time scale.
Similar calculation can obtain R2 polar difference value set { R2 under TS2 scale 1 ,R2 2 ,…,R2 k ,…,R2 K }. K is the TS2 time scale sequence number, and K is the total sequence number of the TS2 time scale sequence number.
Step 3, calculating the range threshold under different time scales.
According to the formula (5), the mean μ and standard deviation σ of the R1 and R2 polar difference sets are calculated respectively:
determining the upper limit of the range control under the TS1 and TS2 scales, namely a range threshold value according to a formula (6) and a formula (7):
at the scale of TS1, the process is carried out,
at the scale of TS2, the process is carried out,
and 4, detecting transient flow events of the measured pressure signals.
The front-end intelligent node, namely the monitoring point, carries out transient flow event real-time detection in the pressure signal acquisition process according to the time scale classification, the range threshold value and other parameters:
4-1, the front-end intelligent node is according to fixed frequency f s The method comprises the steps of (1) and (2) carrying out (1) sampling at 10Hz, and comparing and recording the maximum value MAX1/MAX2 and the minimum value MIN1/MIN2 of the pressure at different time scales of the round except for normally recording measured pressure data from the beginning of sampling (generally at the moment of whole point second).
4-2, calculating the range R1 according to the formula (1) after every 1 TS1 time scale sampling is completed j The method comprises the steps of carrying out a first treatment on the surface of the Per 1 TS2 time scale sampling, the range R2 is calculated according to the formula (2) k 。
4-3, 1T per completionExtremely poor R1 on S1 time scale j Comparing the transient event signal with a control upper limit UCL1 threshold value, and triggering a transient event signal if the transient event signal exceeds the control upper limit UCL1 threshold value; extremely poor R2 at 1 TS2 time scale per completion k A comparison is made with the upper control limit UCL2 threshold and a transient event signal is triggered if an overrun occurs.
The transient event detection effect of the measuring point 9# is shown in fig. 3, and the transient event is rapidly and accurately detected by using the method.
Claims (5)
1. A method for detecting transient flow events of a water supply network is characterized by comprising the following steps:
step 1, calculating a daily pressure signal frequency spectrum of a pipe network monitoring point, and determining a time scale level;
performing frequency spectrum calculation on continuously acquired pressure signals of monitoring points by adopting a fast Fourier transform algorithm to obtain a spectrogram;
ordering the frequency spectrum which is 3 times larger than the noise amplitude according to the frequency to obtain a transient flow minimum frequency f min And maximum frequency f max ；
According to the instantaneous minimum frequency f min And instantaneous maximum frequency f max Determining a time scale level;
the monitoring point adopts a high-frequency and high-precision intelligent pressure gauge, continuously and rapidly detects the water supply pressure, the sampling precision is above 0.5 level, and the sampling frequency f s Sampling in real time of 7 multiplied by 24, which is not less than 10 Hz;
step 2, calculating the limit value of the monitoring point of the pipe network under different time scales of daily pressure;
taking three-level time scale as an example, the calculation formula of the polar difference value under different time scales is as follows:
extremely poor R1 at first order time scale TS 1:
R1＝Max(x 1 ,x 2 ,…,x i ,…,x n )-Min(x 1 ,x 2 ,…,x i ,…,x n ) (1)
extremely poor R2 at the secondary time scale TS 2:
R2＝Max(x 1 ,x 2 ,…,x i ,…,x 10n )-Min(x 1 ,x 2 ,…,x i ,…,x 10n ) (2)
extremely poor R3 at three-level time scale TS 2:
R3＝Max(x 1 ,x 2 ,…,x i ,…,x 100n )-Min(x 1 ,x 2 ,…,x i ,…,x 100n ) (3)
wherein x is i For the ith pressure sampling value under a certain scale, max (), min () is the maximum value and the minimum value in the time sequence;
and carrying out continuous extremely poor calculation on the continuously acquired monitoring point pressure signals under different time scales to obtain:
r1 polar difference set { R1 } 1 ,R1 2 ,…,R1 j ,…,R1 J }，
R2 polar difference set { R2 1 ,R2 2 ,…,R2 k ,…,R2 K }，
R3 polar difference set { R3 1 ,R3 2 ,…,R3 m ,…,R3 M }
Wherein J is a TS1 time scale sequence number, J is a TS1 time scale total sequence number, K is a TS2 time scale sequence number, K is a TS2 time scale sequence number total sequence number, M is a TS3 time scale sequence number, and M is a TS3 time scale sequence number total sequence number;
step 3, calculating the range threshold under different time scales;
respectively calculating the mean mu and standard deviation sigma of the R1, R2 and R3 polar difference sets; according to the Laida criterion, using mu+3σ as a control upper limit, and determining a very poor control upper limit under different time scales;
step 4, detecting transient flow events of the measured pressure signals;
the monitoring points are classified according to time scales and the limit control upper limit, and the transient flow event is detected in real time in the pressure signal acquisition process, specifically:
4-1, the front-end intelligent node is according to fixed frequency f s Sampling, namely, comparing and recording the maximum value and the minimum value of the pressure under different time scales of the round except for normally recording actual measurement pressure data from sampling;
4-2, calculating the range R1 according to the formula (1) after every 1 TS1 time scale sampling is completed j Every time 1 TS2 time scale sampling is completed, the range R2 is calculated according to the formula (2) k The method comprises the steps of carrying out a first treatment on the surface of the Per 1 TS3 time scale sampling, the range R3 is calculated according to the formula (3) m ；
4-3, the range R1 at 1 TS1 time scale per completion j Comparing the instantaneous flow event signal with the corresponding control upper limit, and triggering the instantaneous flow event signal if the control upper limit exceeds the control upper limit; extremely poor R2 at 1 TS2 time scale per completion k Comparing the instantaneous flow event signal with the corresponding control upper limit, and triggering the instantaneous flow event signal if the control upper limit exceeds the control upper limit; extremely poor R3 at 1 TS3 time scale per completion m The transient event signal is triggered if an overrun is compared to its corresponding upper control limit.
2. The method for detecting a transient flow event of a water supply network according to claim 1, wherein: the time scale is divided into 2 to 3 stages, and the stage 1 analyzes the maximum frequency f max Signal, analysis minimum frequency f of 2 nd or 3 rd min A signal.
3. The method for detecting a transient flow event of a water supply network according to claim 2, wherein: when the tertiary time scale is selected, the primary time scale ts1=1 second, the secondary time scale ts2=10 seconds, and the tertiary time scale ts3=100 seconds.
4. The method for detecting a transient flow event of a water supply network according to claim 1, wherein: step 1-3, except for data acquisition and uploading at a front-end monitoring point, the other complex calculation including frequency spectrum, range and threshold calculation are completed on a cloud server; the front-end monitoring point only needs to receive the optimization parameters of the cloud server, including time scale classification and control upper limit.
5. The method for detecting a transient flow event of a water supply network according to claim 1, wherein: if the front-end monitoring point detects a transient flow event, high-frequency pressure data in a period of time before and after the triggering time can be immediately uploaded to the cloud server according to the transient flow characteristics of the water supply network, and the cloud server is triggered to respond to and process the transient flow signal in time; if no transient event is detected, the low frequency pressure data is uploaded to the cloud server periodically.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110938339.6A CN113758627B (en) | 2021-08-16 | 2021-08-16 | Water supply network transient flow event detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110938339.6A CN113758627B (en) | 2021-08-16 | 2021-08-16 | Water supply network transient flow event detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113758627A CN113758627A (en) | 2021-12-07 |
| CN113758627B true CN113758627B (en) | 2024-01-02 |
Family
ID=78789463
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110938339.6A Active CN113758627B (en) | 2021-08-16 | 2021-08-16 | Water supply network transient flow event detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113758627B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107784799A (en) * | 2016-08-26 | 2018-03-09 | 北京协同创新智能电网技术有限公司 | A kind of multivariable alarm method and system based on online change direction |
| CN110159933A (en) * | 2019-05-29 | 2019-08-23 | 中国水利水电科学研究院 | A kind of controllable constant-pressure low-intensity transient flow exciting bank and method |
| CN110837933A (en) * | 2019-11-11 | 2020-02-25 | 重庆远通电子技术开发有限公司 | Leakage identification method, device, equipment and storage medium based on neural network |
| CN111442799A (en) * | 2020-03-26 | 2020-07-24 | 西安普特流体控制有限公司 | Transient current monitoring method and multi-channel water hammer detector |
| CN112097126A (en) * | 2020-09-18 | 2020-12-18 | 同济大学 | Water supply network pipe burst pipeline accurate identification method based on deep neural network |
| CN112377817A (en) * | 2020-11-11 | 2021-02-19 | 杭州电子科技大学 | Municipal pipe network pipe explosion monitoring system and method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| ES2786129T3 (en) * | 2012-11-30 | 2020-10-08 | Ip2Ipo Innovations Ltd | A device, method and system for monitoring a network of conduits that carry fluid |
-
2021
- 2021-08-16 CN CN202110938339.6A patent/CN113758627B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107784799A (en) * | 2016-08-26 | 2018-03-09 | 北京协同创新智能电网技术有限公司 | A kind of multivariable alarm method and system based on online change direction |
| CN110159933A (en) * | 2019-05-29 | 2019-08-23 | 中国水利水电科学研究院 | A kind of controllable constant-pressure low-intensity transient flow exciting bank and method |
| CN110837933A (en) * | 2019-11-11 | 2020-02-25 | 重庆远通电子技术开发有限公司 | Leakage identification method, device, equipment and storage medium based on neural network |
| CN111442799A (en) * | 2020-03-26 | 2020-07-24 | 西安普特流体控制有限公司 | Transient current monitoring method and multi-channel water hammer detector |
| CN112097126A (en) * | 2020-09-18 | 2020-12-18 | 同济大学 | Water supply network pipe burst pipeline accurate identification method based on deep neural network |
| CN112377817A (en) * | 2020-11-11 | 2021-02-19 | 杭州电子科技大学 | Municipal pipe network pipe explosion monitoring system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113758627A (en) | 2021-12-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022252505A1 (en) | Device state monitoring method based on multi-index cluster analysis | |
| US9797799B2 (en) | Intelligent adaptive system and method for monitoring leakage of oil pipeline networks based on big data | |
| CA2898931C (en) | System and method for enhanced operation of wind parks | |
| US10508974B2 (en) | Storing analytical machine data based on change in scalar machine data indicating alert condition | |
| CN107272651B (en) | A kind of Robust Detection Method of Braking System for Multiple Units interval multiplying property sensor fault | |
| CN106247173A (en) | The method and device of pipeline leakage testing | |
| CN103754718A (en) | System and method for monitoring elevator operation safety | |
| CN112208506B (en) | Intelligent fault detection method for air brake device of railway wagon | |
| CN109063885A (en) | A kind of substation's exception metric data prediction technique | |
| CN112805441A (en) | Method for identifying the source of pressure transients in a water network | |
| CN115792457A (en) | Method and system for diagnosing and analyzing station acquisition fault based on edge calculation | |
| Bakker et al. | Analysis of historic bursts and burst detection in water supply areas of different size | |
| CN113758627B (en) | Water supply network transient flow event detection method | |
| CN108801320B (en) | Diagnosis method of natural gas measurement system | |
| CN115830024B (en) | Bridge guy cable micro-motion vibration detection method based on image segmentation | |
| CN101923605B (en) | Wind pre-warning method for railway disaster prevention | |
| CN114662058A (en) | Wireless station monitoring method and device | |
| CN115858303A (en) | Server performance monitoring method and system based on Zabbix | |
| CN114660378A (en) | Multi-source detection parameter-based contact network comprehensive diagnosis method | |
| CN110516323A (en) | A kind of pressure pipeline damage forecast method based on Time-Series analysis | |
| CN114323412B (en) | Water supply pipe network pressure disturbance event detection method | |
| KR20200113085A (en) | System and method for leakage detection and location estimation of plant applying leakage prediction algorithm | |
| KR102188095B1 (en) | Analasis method for evevt causes of sensor | |
| CN114526915B (en) | Early fault time point identification method based on rolling bearing characteristic distribution | |
| CN116817306B (en) | Gas equipment capable of monitoring and controlling gas flow |
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 |