CN112559969A - Small leakage detection method based on accumulation sum algorithm - Google Patents
Small leakage detection method based on accumulation sum algorithm Download PDFInfo
- Publication number
- CN112559969A CN112559969A CN202011457585.1A CN202011457585A CN112559969A CN 112559969 A CN112559969 A CN 112559969A CN 202011457585 A CN202011457585 A CN 202011457585A CN 112559969 A CN112559969 A CN 112559969A
- Authority
- CN
- China
- Prior art keywords
- water consumption
- leakage
- cusum
- flow data
- range
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 44
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 25
- 238000009825 accumulation Methods 0.000 title claims abstract description 14
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 89
- 238000000034 method Methods 0.000 claims description 33
- 230000002159 abnormal effect Effects 0.000 claims description 13
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000012795 verification Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 2
- 230000006641 stabilisation Effects 0.000 claims description 2
- 238000011105 stabilization Methods 0.000 claims description 2
- 230000000087 stabilizing effect Effects 0.000 claims 1
- 230000008859 change Effects 0.000 abstract description 6
- 230000004044 response Effects 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000002411 adverse Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 238000012937 correction Methods 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 230000002354 daily effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 2
- RAYLUPYCGGKXQO-UHFFFAOYSA-N n,n-dimethylacetamide;hydrate Chemical compound O.CN(C)C(C)=O RAYLUPYCGGKXQO-UHFFFAOYSA-N 0.000 description 2
- 230000003321 amplification Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000012076 audiometry Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000002459 sustained effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Pure & Applied Mathematics (AREA)
- Algebra (AREA)
- General Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Operations Research (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Evolutionary Biology (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- Examining Or Testing Airtightness (AREA)
Abstract
The invention discloses a small leakage detection method based on an accumulation sum algorithm, which comprises the following steps: collecting flow data of a water consumption stable period, then estimating a reference water consumption range of the water consumption stable period through frequency statistics, then verifying the reasonability of the estimated reference water consumption range through setting confidence, eliminating the interference of large low-value fluctuation of the flow data according to the reference water consumption range, and finally detecting small leakage in a DMA (direct memory access) pipe network by utilizing a CUSUM (compute unified basic) algorithm. The invention analyzes the change trend of the flow by the CUSUM algorithm, greatly shortens the discovery time of the small leakage event, enables a manager to make a quick response, guides a leakage detecting person to optimize the priority of leakage detection, realizes purposeful and key leakage detection, has higher application and economic value, and can be used as an effective auxiliary means for implementing the active leakage control of the DMA pipe network.
Description
Technical Field
The invention relates to a water supply network leakage detection method, in particular to a small leakage detection method based on an accumulation sum algorithm.
Background
Pipe network leakage is a common problem in urban water supply systems at home and abroad, and brings adverse effects on the aspects of economy, environment and the like. On the one hand, the lost water resource not only causes great loss of economic benefits of water supply enterprises, but also causes waste of energy and water resource, and is not in accordance with the sustainable development idea advocated by the current state. Therefore, the reduction of the leakage rate of the pipe network has important significance for improving the utilization efficiency of urban water resources and maintaining the sustainable economy.
Pipe network leakage detection methods can be divided into two broad categories, hardware-based methods and software analysis-based methods. The first method relies on hardware devices for detection, such as audiometry, sonography, etc. The method can only be carried out intermittently (for example, the leak detection period is half a month or one month), the labor cost is high, the detection efficiency is low for a water supply system with large urban scale and a complex pipe network structure, and the requirements of 'timely finding and quickly positioning' of a leakage event in the current water supply pipe network management are difficult to meet. The second method mainly achieves the purpose of leak detection by establishing a model or analyzing and processing signals, such as a neural network method, a Kalman filtering method and the like. Due to the strong real-time property of the method, the detection technology related to the method still remains a hot spot and a trend of research due to the rapid development of computer technology, control theory, signal processing, pattern recognition, artificial intelligence and other subjects. However, most of the existing methods based on software analysis focus on the detection of large leaks (the amount of water lost is greater than or equal to 5% of the average flow rate in the same time period), and the detection effect on small leaks (the amount of water lost is less than 5% of the average flow rate in the same time period) is poor. Until now, small leakage detection is still a difficult problem in the field of water supply network leakage detection.
Although the initial leakage water volume of small leakage is small, because the leakage of the pipe network is dynamically and continuously changed, if the leakage water volume is small, the leakage water volume is controlled, and particularly for the pipe network with a large scale, the leakage water volume can be greatly reduced. Therefore, the method has great practical value in the aspects of saving a large amount of water resources, improving the economic benefit of water supply enterprises and the like by effectively and timely detecting the small leakage event.
Disclosure of Invention
The invention aims to solve the technical problem of providing a small leakage detection method based on accumulation and algorithm, which can find small leakage events more quickly aiming at a DMA water supply pipe network system.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
a small leakage detection method based on an accumulation sum algorithm is characterized in that flow data of a water consumption stable period are collected, then a reference water consumption range of the water consumption stable period is estimated through frequency statistics, then the reasonability of the estimated reference water consumption range is verified through setting confidence, then the interference of large and low fluctuation of the flow data is eliminated according to the reference water consumption range, and finally a CUSUM algorithm is utilized to continuously accumulate the difference value between an observed value and a target value so as to accumulate small deviation in the process to achieve small amplification effect, and therefore small leakage of a DMA pipe network is detected.
In this application, the CUSUM algorithm denotes the accumulation sum algorithm, DMA, i.e., the distribution Metering Area, denotes the independent Metering zone.
Specifically, the small leak detection method based on the accumulation sum algorithm includes the following steps:
(1) collecting flow data: collecting flow data of the DMA in a water consumption stable time period according to a set time interval, wherein the flow data refers to net inflow flow data of the DMA, namely the algebraic sum of flow data of a plurality of flowmeters at the same moment, and simultaneously setting inflow DMA as positive and outflow DMA as negative;
(2) estimating a baseline water usage range for a water usage stabilization period, comprising the steps of:
2.1) selecting flow data of a plurality of days;
2.2) setting different flow ranges from small to large, and estimating the reference water consumption range of the water consumption stable time period through frequency analysis;
2.3) setting confidence coefficient and determining a confidence interval [ mu-beta delta ', mu + beta delta ' ], wherein mu is a mean value, beta is a coefficient corresponding to the confidence coefficient, and delta ' is a standard deviation;
2.4) carrying out rationality verification on the reference water consumption range obtained by estimation in the step 2.2), judging that the estimated reference water consumption range is reasonable when the reference water consumption range is in the confidence interval determined in the step 2.3), and returning to the step 2.2) to reset the flow range until the estimated reference water consumption range is reasonable;
(3) data processing: eliminating abnormal data according to the range of the reference water consumption estimated in the step (2), and then calculating the average flow in a stable time period of the daily water consumption;
(4) the method for detecting the leakage by applying the CUSUM algorithm comprises the following steps:
4.1) selecting average flow in a stable period of water consumption for a plurality of days to carry out statistical calculation to determine a target value K and a corrected standard deviation delta, and then calculating CUSUM statistic of each day according to the following formula (1):
Ci＝max[0,Ci-1+Xi-K] (1)
wherein, CiDenotes the CUSUM statistic for day i, its initial value C0＝0；XiThe average flow rate after eliminating the abnormal value on the ith day is represented; k is a target value;
4.2) adding new flow data to continuously update CUSUM statistic, then judging whether CUSUM statistic meets a leakage condition, if yes, judging that leakage occurs, and at the moment, judging that the flow data corresponding to the leakage does not participate in the calculation of the subsequent CUSUM statistic any more;
(5) judging whether the value of i in the latest EWMA statistic is larger than the number of days of a set check period, if so, returning to the step 2); if not, return to step 4.2).
In the step (1) of the method, the set time interval is preferably 1 to 10 minutes, and more preferably 1 to 5 minutes. The water consumption stable period is a time period in which the water consumption approximately obeys normal distribution in one day, and the optimal selection in the application is 2: 00-4: 00.
in step (3) of the above method, the abnormal data is flow data lower than the lower limit of the reference water consumption range estimated in step (2).
In step 4.2) of the above method, the leakage condition is satisfied with any one of the following a) to c):
a) any CUSUM statistic is greater than μ +3 δ;
b) any two consecutive CUSUM statistics are greater than mu +2 delta;
c) any continuous N CUSUM statistics show an increasing trend, wherein N is a positive integer and the value is more than or equal to 3.
In the option c), N is reasonably set after comprehensive consideration according to detection efficiency, false alarm rate and acceptable water leakage amount, and the optimal selection is 3-7 in the application.
In step (5) of the above method, the number of days of the set inspection cycle may be a month number, a quarter number, or the like, and is preferably 30 in the present application. Correspondingly, the target value K and the corrected standard deviation δ also need to be updated in the corresponding period.
Compared with the prior art, the detection method for the small leakage in the DMA pipe network provided by the invention has the advantages that the change trend of the flow is analyzed through the CUSUM algorithm, the discovery time of the small leakage event is greatly shortened, a manager can make a quick response, leak detection personnel are guided to optimize the priority of leak detection, purposeful and important leak detection is realized, the application and economic value are high, and the detection method can be used as an effective auxiliary means for implementing active leak control of the DMA pipe network.
Drawings
FIG. 1 is a flow chart of example 1 of the present invention.
Fig. 2 is a schematic diagram of a DMA pipe network according to an embodiment of the present invention.
Fig. 3 is a diagram illustrating variation trend of CUSUM in the detection process according to the embodiment of the present invention, in which a curve a represents an upper limit cumulative sum and a curve b represents a lower limit cumulative sum.
Detailed Description
The present invention will be better understood from the following detailed description taken in conjunction with the accompanying drawings, but the present invention is not limited to the following embodiments.
Example 1
As shown in fig. 1, the small leak detection method based on accumulation sum algorithm of the present invention includes the following steps:
(1) collecting normal flow data
The DMA water consumption is stable in a time period of 2: 00-4: 00 in the morning, approximately follows normal distribution, and is more favorable for detecting small leakage. In addition, the application mainly collects normal flow data of 2: 00-4: 00 in the morning every day, wherein the flow data recording interval is 1-10 minutes, considering that the pressure change caused by small leakage is small. In the DMA having a plurality of flow ports, the flow data is the net input flow data in the DMA area, that is, the algebraic sum of the flow data of the plurality of flow meters at the same time, and the input DMA is set to be positive and the output DMA is set to be negative.
(2) Estimating nighttime baseline water usage range
The water consumption at night is inevitably fluctuated due to the influence of external factors such as water pressure, randomness of water consumption of users and the like. The small leakage itself causes an increase in flow rate, but the variation is small, and when there is a large low value fluctuation, the flow rate variation information due to the small leakage may be masked. In order to eliminate the adverse effect caused by large low-value fluctuation, the method processes the flow data by estimating the nighttime reference water consumption range.
The specific steps for estimating the night reference water consumption range are as follows:
2.1) selecting flow data of a plurality of days;
2.2) setting different flow ranges from small to large, wherein the first flow range can be properly amplified, the subsequent flow range is set according to a fixed variation amplitude (such as 0.1, 0.5 or 1), and then the night reference water consumption range is estimated through frequency analysis;
2.3) setting a proper confidence coefficient, such as 95% or 99%, and determining a confidence interval [ mu-beta delta ', mu + beta delta ' ], wherein mu is a mean value, beta is a coefficient of the corresponding confidence coefficient (beta is 2 when the confidence coefficient is 95%, beta is 3 when the confidence coefficient is 99%), and delta ' is a standard deviation;
2.4) carrying out rationality verification on the reference water consumption range obtained by estimation in the step 2.2), judging that the estimated reference water consumption range is reasonable when the reference water consumption range is in the confidence interval determined in the step 2.3), and returning to the step 2.2) to reset the flow range until the estimated reference water consumption range is reasonable.
(3) Data processing
Before leakage detection is performed, the flow data all need to utilize the reference water consumption range to eliminate adverse effects caused by large low-value fluctuation. In this application, the flow data below the lower limit of the reference water consumption range estimated in step (2) is regarded as abnormal data and is rejected. Calculating average flow X in stable time of daily water consumption after eliminating abnormal dataiAs data for calculating CUSUM statistics, namely after abnormal data are eliminated, average value X of flow data in 2: 00-4: 00 time periods in the morning every dayiAs data to compute the CUSUM statistic.
(4) Leakage detection using CUSUM algorithm
After a leak event, the flow generally increases, so only the CUSUM statistic needs to be analyzed for upward drift trends in the present application.
The specific steps of applying the CUSUM algorithm to detect the leakage are as follows:
4.1) determining the target value K of the average flow and the standard deviation delta after correction
Selecting the average flow (namely X) in a period of 2: 00-4: 00 a plurality of days in the morning under a normal statei) And performing statistical calculation to determine a target value K and the corrected standard deviation delta. K is determined by the average value of the flow data after the abnormal value is removed, and is mainly used for calculating CUSUM statistic in the follow-up process, and delta is mainly used for setting a control limit. The CUSUM statistic is calculated according to equation (1) below:
Ci＝max[0,Ci-1+Xi-K] (1)
wherein, CiDenotes the CUSUM statistic for day i, its initial value C0＝0；XiIndicating a rejection anomaly on day iMean flow after value; k is the target value.
After K and delta are determined, the leakage detection method can be used for leakage detection for a plurality of subsequent days. However, in a water supply network environment, the flow rate is dynamically changed with time, and the target value is not always in a specific state, but is continuously changed along with the change of the network environment and relevant factors (such as seasons). Therefore, the decision for a leakage event must also be determined based on normal reference values of the network state over a certain period of time, i.e. the K and δ values need to be updated periodically (e.g. a month or a quarter). When K and δ are updated, CUSUM statistic is reset to 0.
4.2) leakage detection
And adding new flow data into the continuously updated CUSUM statistic, and then judging whether leakage occurs according to the leakage condition. Because the flow change caused by small leakage is small, and the flow can fluctuate normally, if only a single judgment rule is adopted, the judgment rule can be met for a long time, so that the detection efficiency is greatly reduced, and the control on the leakage of the water supply network is not favorable. Therefore, in order to improve the detection efficiency and reduce false alarm, on the basis of referring to the idea of westgard multi-rule quality control program, and combining the characteristic that the flow is increased after leakage occurs, the westgard judgment rule is properly improved, and if the rule is specified to meet any one of the following a) -c), the flow is considered to be abnormal, the small leakage event can be judged to occur, otherwise, the water supply network is in a normal operation state:
a) any CUSUM statistic is greater than μ +3 δ;
b) any two consecutive CUSUM statistics are greater than mu +2 delta;
c) any continuous N CUSUM statistics show an increasing trend, wherein N is a positive integer and the value is more than or equal to 3. After comprehensive consideration of detection efficiency, false alarm rate and acceptable water leakage amount, the optimal value is 3-7.
(5) Judging whether the value of i in the latest EWMA statistic is larger than the number of days of a set check period, if so, returning to the step 2); if not, return to step 4.2). The number of days of the set check cycle corresponds to the number of days of update of the target value K and the corrected standard deviation δ, and may be a number of days of one month or a number of days of one quarter, and is generally set to 30 in the present application.
The method described in the present application is described below with an example of a DMA network for a better understanding of the present application by those skilled in the art.
The selected example pipe network has only one flow inlet and no outlet, the number of residents is about 13500, and DN300 water inlet pipe is schematically shown in FIG. 2.
In this example, the method for detecting a small leak based on accumulation and algorithm of the present application includes the following specific steps:
(1) collecting flow data
In the embodiment, flow data of 2: 00-4: 00 in the morning for 35 days are collected, and the recording time interval of the flow data is 5 min. To verify the effectiveness of the method described in the present application, 1 sustained small leak event was simulated by draining the hydrant at 2:00 am on day 31 with an amount of water lost of about 3% of the average flow of the DMA under study over a period of 2:00 to 4:00 (about 0.9 m)3/h)。
(2) Estimating nighttime baseline water usage range
In this example, a total of 336 flow data of the first 14 days were selected for statistical analysis, and the mean μ of these data was 30.2m3H, standard deviation delta' of 0.85m3/s。
Design flow range from small to large, with the first flow range set to [0,28 ]]Subsequent flow rate range is 0.5m3The amplitude/h was designed as shown in table 1 below, and then the frequency analysis was used to estimate the possible range of baseline water usage.
TABLE 1 frequency analysis
From Table 1To see that the flow rate is less than 28.5m3The number of times/h is only 2.09%, the occurrence is more than or equal to 31m3The number of times/h is only 3.28%, which can be considered as a small probability event. Compared with the two cases, the times of the flow in the intervals of [28.5,29) and [30.5,31) respectively account for 16.37 percent and 6.25 percent, and belong to multiple occurrences, so that the reference water consumption range at night is preliminarily estimated to be [28.5, 31%]。
And (3) selecting 95% confidence to verify the range of the reference water consumption, so as to obtain a confidence interval [ 30.2-2X 0.85,30.2+ 2X 0.85], namely [28.5,31.95 ]. The above-described estimated night time reference water usage range [28.5,31] is within the [28.5,31.95] interval, and therefore it can be considered that the previously estimated night time reference water usage range is reasonable.
(3) Data processing
And (3) eliminating abnormal data according to the range of the reference water consumption estimated in the step (2), and then calculating the average flow in a time period of 2: 00-4: 00 every morning. The mean flow will be the data for calculating the CUSUM statistic.
(4) Leakage detection using CUSUM algorithm
4.1) determining the target value K and the standard deviation delta
After abnormal data are eliminated, normal average flow in a time period of 2: 00-4: 00 in the morning of the first 14 days is selected for analysis, a target value K is 30.89, and a standard deviation delta is 0.77 after correction. Therefore, the flow data to be measured can be detected.
4.2) leakage detection
And from the 15 th day, adding new flow data into the sample data to continuously update CUSUM statistics, and comparing the trend change of the CUSUM statistics with the leakage condition so as to judge the running state of the pipe network. By comprehensive consideration, the value of N in the option of the leakage condition c) is 7. The CUSUM variation trend of the whole detection process is shown in FIG. 3.
As can be seen from fig. 3, according to the rule of judgment of leakage, no false alarm occurs from day 15 to day 30. And according to item a) of the leak condition, a small leak event starting on day 31 is detected on day 33 (i.e., the second day after the event occurs). The period of regular leak detection is generally 15 days or 1 month, so that the method can greatly shorten the discovery time of the leakage event and provide important reference for leak detection personnel to carry out targeted leak detection work.
Claims (8)
1. A small leakage detection method based on an accumulation sum algorithm is characterized in that flow data of a water consumption stable period are collected, then a reference water consumption range of the water consumption stable period is estimated through frequency statistics, then the reasonability of the estimated reference water consumption range is verified through setting confidence, then the interference of large and low-value fluctuation of the flow data is eliminated according to the reference water consumption range, and finally a CUSUM algorithm is used for detecting small leakage in a DMA (direct memory access) pipe network.
2. The method of claim 1, comprising the steps of:
(1) collecting flow data: collecting flow data of the DMA in a water consumption stable time period according to a set time interval, wherein the flow data refers to net inflow flow data of the DMA, namely the algebraic sum of flow data of a plurality of flowmeters at the same moment, and simultaneously setting inflow DMA as positive and outflow DMA as negative;
(2) estimating a baseline water usage range for a water usage stabilization period, comprising the steps of:
2.1) selecting flow data of a plurality of days;
2.2) setting different flow ranges from small to large, and estimating the reference water consumption range of the water consumption stable time period through frequency analysis;
2.3) setting confidence coefficient and determining a confidence interval [ mu-beta delta ', mu + beta delta ' ], wherein mu is a mean value, beta is a coefficient corresponding to the confidence coefficient, and delta ' is a standard deviation;
2.4) carrying out rationality verification on the reference water consumption range obtained by estimation in the step 2.2), judging that the estimated reference water consumption range is reasonable when the reference water consumption range is in the confidence interval determined in the step 2.3), and returning to the step 2.2) to reset the flow range until the estimated reference water consumption range is reasonable;
(3) data processing: eliminating abnormal data according to the range of the reference water consumption estimated in the step (2), and then calculating the average flow in a stable time period of the daily water consumption;
(4) the method for detecting the leakage by applying the CUSUM algorithm comprises the following steps:
4.1) selecting average flow in a stable period of water consumption for a plurality of days to carry out statistical calculation to determine a target value K and a corrected standard deviation delta, and then calculating CUSUM statistic of each day according to the following formula (1):
Ci＝max[0,Ci-1+Xi-K] (1)
wherein, CiDenotes the CUSUM statistic for day i, its initial value C0＝0；XiThe average flow rate after eliminating the abnormal value on the ith day is represented; k is a target value;
4.2) adding new flow data to continuously update CUSUM statistic, then judging whether CUSUM statistic meets a leakage condition, if yes, judging that leakage occurs, and at the moment, judging that the flow data corresponding to the leakage does not participate in the calculation of the subsequent CUSUM statistic any more;
(5) judging whether the value of i in the latest EWMA statistic is larger than the number of days of a set check period, if so, returning to the step 2); if not, return to step 4.2).
3. The method for detecting small leakage based on the accumulation sum algorithm as claimed in claim 2, wherein in the step (1), the set time interval is 1-10 minutes.
4. The small leak detection method based on the accumulation sum algorithm as claimed in claim 2, wherein in the step (1), the water consumption stabilizing period is 2: 00-4: 00.
5. the method of claim 2, wherein the abnormal data in step (3) is flow data below the lower limit of the reference water usage range estimated in step (2).
6. The method for detecting small leakage based on accumulation sum algorithm as claimed in claim 2, wherein in step 4.2), the leakage condition is that any one of the following a) to c) is satisfied:
a) any CUSUM statistic is greater than μ +3 δ;
b) any two consecutive CUSUM statistics are greater than mu +2 delta;
c) any continuous N CUSUM statistics show an increasing trend, wherein N is a positive integer and the value is more than or equal to 3.
7. The method of claim 6, wherein in option c), N is 3-7.
8. The method of claim 1, wherein in step (5), the number of inspection cycle days is set to 30.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011457585.1A CN112559969B (en) | 2020-12-10 | 2020-12-10 | Small leakage detection method based on accumulation sum algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011457585.1A CN112559969B (en) | 2020-12-10 | 2020-12-10 | Small leakage detection method based on accumulation sum algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112559969A true CN112559969A (en) | 2021-03-26 |
| CN112559969B CN112559969B (en) | 2022-04-29 |
Family
ID=75062717
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011457585.1A Active CN112559969B (en) | 2020-12-10 | 2020-12-10 | Small leakage detection method based on accumulation sum algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112559969B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114677830A (en) * | 2022-02-25 | 2022-06-28 | 青岛海尔科技有限公司 | Reminding method of water use message, storage medium and electronic device |
| CN116642138A (en) * | 2023-05-25 | 2023-08-25 | 大连智水慧成科技有限责任公司 | New leakage detection method for water supply network |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140149054A1 (en) * | 2011-06-28 | 2014-05-29 | Holger Hanss | Leak Detection Via a Stochastic Mass Balance |
| CN106017729A (en) * | 2016-05-19 | 2016-10-12 | 太原理工大学 | SPC (Statistical Process Control) based motor temperature monitoring method |
| CN107194621A (en) * | 2017-07-14 | 2017-09-22 | 水联网技术服务中心（北京）有限公司 | A kind of Water supply network system and method |
| CN109388904A (en) * | 2018-10-29 | 2019-02-26 | 泰华智慧产业集团股份有限公司 | Method and system based on DMA subregion flow rate calculation ullage |
| CN109932009A (en) * | 2018-08-31 | 2019-06-25 | 滁州市智慧水务科技有限公司 | A kind of distribution tap water pipe network loss monitoring system and method |
-
2020
- 2020-12-10 CN CN202011457585.1A patent/CN112559969B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140149054A1 (en) * | 2011-06-28 | 2014-05-29 | Holger Hanss | Leak Detection Via a Stochastic Mass Balance |
| CN106017729A (en) * | 2016-05-19 | 2016-10-12 | 太原理工大学 | SPC (Statistical Process Control) based motor temperature monitoring method |
| CN107194621A (en) * | 2017-07-14 | 2017-09-22 | 水联网技术服务中心（北京）有限公司 | A kind of Water supply network system and method |
| CN109932009A (en) * | 2018-08-31 | 2019-06-25 | 滁州市智慧水务科技有限公司 | A kind of distribution tap water pipe network loss monitoring system and method |
| CN109388904A (en) * | 2018-10-29 | 2019-02-26 | 泰华智慧产业集团股份有限公司 | Method and system based on DMA subregion flow rate calculation ullage |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114677830A (en) * | 2022-02-25 | 2022-06-28 | 青岛海尔科技有限公司 | Reminding method of water use message, storage medium and electronic device |
| CN116642138A (en) * | 2023-05-25 | 2023-08-25 | 大连智水慧成科技有限责任公司 | New leakage detection method for water supply network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112559969B (en) | 2022-04-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112559969B (en) | Small leakage detection method based on accumulation sum algorithm | |
| CN109932009B (en) | Distributed tap water pipe network loss monitoring system and method | |
| CN107355688B (en) | Urban water supply network leakage control management system | |
| CN110617209A (en) | Online monitoring and diagnosing method and system for pump station unit | |
| CN103186603B (en) | Determine that SQL statement is on the method for the impact of the performance of key business, system and equipment | |
| CN110942137A (en) | Power grid information operation and maintenance monitoring method based on deep learning | |
| CN116418120A (en) | Intelligent early warning method applied to water-cooled power supply | |
| CN106682763A (en) | Power load optimization and prediction method for massive sample data | |
| TW201915622A (en) | Forecasting method for performance | |
| CN111720753A (en) | Cell DMA (direct memory access) leakage detection control method based on noise monitoring technology | |
| CN105740989B (en) | A kind of water supply network anomalous event method for detecting based on VARX model | |
| CN111984930A (en) | Method and system for identifying abnormal value of underground water level monitoring data | |
| CN108414016A (en) | A kind of sewage network monitoring system based on big data technology | |
| CN114323412B (en) | Water supply pipe network pressure disturbance event detection method | |
| CN114462688A (en) | Tube explosion detection method based on LSTM model and dynamic threshold determination algorithm | |
| CN117647143B (en) | Large-scale waste heat recovery control system | |
| CN111930802A (en) | Anti-electricity-stealing analysis method based on Lasso analysis | |
| CN110848578B (en) | PDD model-based existing leakage positioning method for urban water supply pipe network | |
| CN112487364B (en) | Small leakage detection method based on exponential weighted moving average algorithm | |
| KR20220061713A (en) | Method of replacing missing value in smart meter and control system of smart meter using the same | |
| CN108171408A (en) | A kind of sewage water and water yield modeling method | |
| CN113297194B (en) | Method for identifying and cleaning false data of spare capacity of electric automobile aggregator | |
| CN116205360A (en) | Energy consumption prediction method and device for heating ventilation air conditioner | |
| CN114611998B (en) | Factory production line energy efficiency data acquisition and analysis method, system and computer storage medium | |
| Sun et al. | Identifying supply-demand mismatches in district heating system based on association rule mining |
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 |