CN110285330B - Water network pipe burst detection method based on local outlier factor - Google Patents
Water network pipe burst detection method based on local outlier factor Download PDFInfo
- Publication number
- CN110285330B CN110285330B CN201910624754.7A CN201910624754A CN110285330B CN 110285330 B CN110285330 B CN 110285330B CN 201910624754 A CN201910624754 A CN 201910624754A CN 110285330 B CN110285330 B CN 110285330B
- Authority
- CN
- China
- Prior art keywords
- detection
- pipe
- point
- points
- detection data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
Abstract
The invention relates to the technical field of water service network pipe network detection, in particular to a water service network pipe burst detection method based on local outlier factors, which comprises the following steps: s1, collecting the detection data of each detection point in the pipe network to be detected at the current moment and historical detection data of the same moment in the past days; s2, calculating the outlier factor of the detection data of each detection point at the current moment according to the detection data of each detection point at the current moment and the historical detection data; s3, acquiring the spatial adjacent relation of the detection points, and calculating the pipe explosion probability of the pipe section between every two adjacent detection points according to the outlier factors of the two adjacent detection points at the current moment; and S4, judging whether the pipe explosion probability of each pipe section is greater than a set threshold value, if so, judging that the pipe section is subjected to pipe explosion, otherwise, judging that the pipe explosion does not occur. The method does not need to know the label of the data, has practicability and enables pipe network pipe explosion detection to be higher in feasibility.
Description
Technical Field
The invention relates to the technical field of water service network management network detection, in particular to a water service network pipe burst detection method based on local outlier factors.
Background
Water resources are indispensable resources in various countries and indispensable components for human civilization development, people have larger and larger water demands, the pollution condition of the water resources is increased day by day, fresh water resources are few, and therefore the water shortage problem is serious all over the world and is far lower than the average level of the world through relevant research and research. Along with the rapid and continuous development of city construction in China and the general increase of population, the demand of water resources becomes very large. The water resource saving is an important method for effectively relieving the shortage of water resources, and the reduction of the leakage of a water supply network can save the water resources and effectively improve the economic benefit of water supply enterprises. Pipeline leaks are a very common accident. Even if the pipeline is laid to meet the national standards, leakage often occurs due to aging, deformation, corrosion, etc. of the pipeline, with physical leakage being more inevitable. In recent years, the problem of pipe network leakage in China is more and more serious, and particularly, the influence on some water-deficient cities is the greatest, so that long-distance water supply is needed to meet the basic requirements of the areas, but the cost is greatly increased due to the influence of factors such as weather and environment; on the other hand, when the leakage reaches a certain degree, the problem of pipe explosion is easily caused, and then a considerable economic loss is caused. Therefore, the leakage of the pipe network is detected and reduced, and the pipe burst of the water service pipe network is prevented.
At present, the main methods for judging leakage widely are divided into a passive leakage detection method and an active leakage detection method.
The passive leak detection method is widely applied in the past, and the method needs to wait for a period of pipeline leakage, after water gradually overflows from the underground, relevant workers regularly patrol the pipeline to observe whether water overflows from the underground or not, and then judge whether water leakage exists or not. Because the method can be found after a large amount of water leakage is generated, a lot of water resources are wasted, and the loss of the pipe network is very large. In addition, the optimization of the water leakage points and the urban water supply network detection points at the positions of the water leakage points of the pipe sections and the research of a pipe burst positioning model have too large contrast, so that the excavation amount is often too large, and the maintenance time is too long.
Active leak detection is a relatively modern method, and unlike passive leak detection, can be detected by modern instruments without water emerging from the bottom of the ground. With the progress of society, many new technologies for pipe network leak detection and positioning are researched by various countries, including in-pipe detection methods based on magnetic flux, ultrasound and other technologies, and off-pipe leak detection methods such as thermal infrared imaging, meteorological imaging, olfactory sensing, radioactive tracer leak detection, negative pressure wave, pressure gradient, neural network, optical fiber leak detection, mass or volume balance, SCADA (supervisory control and data acquisition system), acoustic wave detection, pressure wave detection and the like.
In the active leak detection method, most methods need a large amount of marked data to generate a prediction model, but because the data is relatively difficult to obtain, especially the data needs to be marked, the work is very difficult to realize in reality, and the time cost and the labor cost are particularly high.
Disclosure of Invention
This patent is difficult to obtain the data of mark in to current initiative leak hunting method, and is very specific to consume this shortcoming of time cost and human cost, has provided a water utilities pipe network pipe explosion detection method based on local outlier factor and has detected whether the pipe network explodes, and the label that the data need not be known to this method has certain practicality for pipe network pipe explosion detection feasibility is higher.
The method comprises the following steps:
s1, collecting the detection data of each detection point in the pipe network to be detected at the current moment and historical detection data of the same moment in the past days;
s2, calculating the outlier factor of the detection data of each detection point at the current moment according to the detection data of each detection point at the current moment and the historical detection data;
s3, acquiring the spatial adjacent relation of the detection points, and calculating the pipe explosion probability of the pipe section between every two adjacent detection points according to the outlier factors of the two adjacent detection points at the current moment;
and S4, judging whether the pipe explosion probability of each pipe section is greater than a set threshold value, if so, judging that the pipe section is subjected to pipe explosion, otherwise, judging that the pipe explosion does not occur.
The method uses the data of the same pipe section at different times as a basis, and calculates the pipe explosion probability by judging the size of the outlier factor of the data of the pipe section at a certain moment and the data of the pipe section at a historical moment, so that whether the pipe section is exploded or not is detected according to the set pipe explosion probability threshold value, time and labor consuming marking on the data is not needed, the practicability is high, and the feasibility of pipe network pipe explosion detection is high.
Further, in step S2, the calculation process of the outlier factor is as follows:
let the detection data set y at the current moment be XojAnd the historical detection data set is X ═ XijI is history time, I is {1,2 … I }, I represents the depth of the history time, J is detection point number, J is {1,2 … J }, J represents the total number of detection points,
the formula for calculating the outlier factor is as follows:
wherein: (1) rhok(Xoj) Represents point XojAll points in the K' th neighborhood of (c) to XojThe formula is as follows:
(2)Nk(Xoj) Is a point XojThe kth distance neighborhood of (c), satisfies:
Nk(Xoj)＝{Xij'∈D\{Xoj}|d(Xoj,Xij')≤dk(Xoj)}；
(3)dk(Xoj,Xij) Is XijPoint to point XojThe Kth reachable distance of
dk(Xoj,Xij)＝max{dk(Xoj),d(Xoj,Xij)}；
(4) Let d (X)oj,Xij) Is two pressure points XojAnd XijThe distance between them;
(5)dk(Xoj) Is a point XojA k-th distance of, and dk(Xoj)＝d(Xoj,Xij) The following conditions are satisfied:
a) at least X is not included in the setijAt the inner k points Xoj,∈C{x≠XijSatisfy d (X)ij,Xoj,)≤d(Xij,Xoj)；
b) At most X is excluded from the setijK-1 points X including poj,∈C{x≠XijSatisfy d (X)ij,Xoj,)<d(Xij,Xoj)。
Further, in step S3, the pipe burst probability of a certain pipe section is calculated as follows:
if the detection point j1 and the detection point j2 are adjacent according to the spatial adjacent relation between the detection points, the tube explosion probability P of a certain section of the connected tube segment is calculated as follows:
wherein s represents the pipe section number, s ═ {1,2 … m }, m represents the maximum number of pipe sections; LOFk(X0j1) Current detection data X representing detection point j10j1Of the outlier factor, LOFk(X0j2) Current detection data X representing detection point j20j2The outlier factor of (a);
max(LOFk(X0j) And Large (LOF)k(X0j) Respectively) represent the largest and second largest outlier factors among all checkpoints.
Further, the detection data is a pressure value in the pipe.
Further, the K value representing the neighborhood size is selected to take 3 in step S2.
Further, the maximum history depth is selected to be 3 in step S1.
Further, the threshold value of the tube explosion probability ranges from 0.85 to 0.95.
Further, the threshold value of the pipe explosion probability is 0.90.
The false alarm occurs on a few adjacent pipe sections, that is, the distance from the pipe section which actually has a pipe burst is short, because the pressure detection data of the adjacent pipe section is influenced certainly after the pipe burst occurs on one pipe section, the influence of the false alarm on the final dispatched worker for checking and repairing is not large, the false alarm is in an acceptable range, however, if a higher threshold value is selected, the false alarm can be accepted to a certain extent, and the loss caused by the false alarm is serious, so that the embodiment selects 0.90 as the threshold value on the basis to ensure that the situation of the false alarm can not occur.
Drawings
Fig. 1 is a schematic diagram of a pipe bursting model of a water supply pipe network established in the first embodiment of the invention.
Fig. 2 is an enlarged view of a point a in fig. 1.
Fig. 3 is a flowchart of a water service network pipe burst detection method based on a local outlier in an embodiment of the present invention.
Detailed Description
The following is further detailed by way of specific embodiments:
example one
In this embodiment, a town-level water supply network hydraulic model is first constructed by EPANET software, and the water supply network hydraulic model includes:
one water source: the total water head is set to be 500, and enters a pipe network through a water supply node;
a water pump: the water pump curve can be selected at will, and the equation of the curve adopted in the embodiment is as follows;
46.67-1.867X 10 of lift-4X (flow rate)2The unit of lift is meter (m) and the unit of flow is liter/second (L/s);
49 pipe network detection points: the elevation is about 49ft, and the basic water demand is set to be 5-10L/s;
number of 63 segments: selecting DN100-DN400 for the pipe diameter, and defaulting the roughness coefficient to 100;
the pipe network topological diagram of the constructed water supply pipe network hydraulic model is basically as shown in figure 1;
there are 3 pipe bursts in the pipe network, 24, 30 and 53 pipe segments, respectively, circled in fig. 2.
In order to implement and simulate the water supply network pipe explosion detection method based on the local outlier, after a water supply network pipe explosion model is built, the built pipe network is imported by means of an MATLAB tool, an inp file exported by EPANET is read through related program codes, data in the EPANET program are exported and stored in an Excel file, and a pressure detection data set under normal conditions and a pressure detection data set during pipe explosion are obtained.
In the operation of a pipe network, the total duration of the pipe network is 24 hours, the hydraulic time step length is 1 hour, namely, pressure data of detection points are collected once every hour, the total number of the detection points is 49, therefore, the data dimension of each group of data is 1 multiplied by 49, and 24 groups of data are obtained in total every day.
Firstly, 24 groups of data under the normal condition of a pipeline within 24 hours are obtained, each group of pressure detection data is respectively subjected to Hadamard product operation (Hadamard product) with a value of [0.99-1.01] and a dimensionality of 1 × 49 random vector, three groups of data similar to the normal condition are obtained through operation with three different random vectors, the three groups of data are used for simulating the pressure detection data at the same time before one day, two days and three days as training samples, and in addition, one group of data under the original normal condition is added, and each time in the training samples has 4 groups of data;
then, the 24, 30 and 53 pipe sections are respectively set as pipe explosion, one pipe section of the three pipe sections is simulated to explode at each time, and pressure detection data of 24 moments in a day under the condition of pipe explosion are obtained as test data, and the test data are called pipe explosion detection data in the following.
The burst detection can then be performed according to the following algorithm:
the detection data set y at the current moment is XojIn this example, the tube explosion detection data at a certain time is obtained, and the historical detection data set is X ═ XijI.e. the pressure detection data of the training sample at the same time before one day, two days and three days in the example, wherein I ═ 1,2 … I, and I representsThe depth of the historical time, which is found by tracing the historical data of the previous three days in this example, is 3, J is the number of the detected points, J is {1,2 … J }, J represents the total number of detected points, and is 49 in this example, the formula for calculating the outlier factor is set as follows:
wherein: (1) rhok(Xoj) Represents point XojAll points in the K' th neighborhood of (c) to XojThe calculation formula is as follows:
(2)Nk(Xoj) Is a point XojThe kth distance neighborhood of (c), satisfies:
Nk(Xoj)＝{Xij'∈D\{Xoj}|d(Xoj,Xij')≤dk(Xoj)}；
(3)dk(Xoj,Xij) Is XijPoint to point XojThe Kth reachable distance of
dk(Xoj,Xij)＝max{dk(Xoj),d(Xoj,Xij)}；
(4) Let d (X)oj,Xij) Detecting data points X for two pressuresojAnd XijThe distance between them;
(5)dk(Xoj) Is a point XojA K-th distance of, and dk(Xoj)＝d(Xoj,Xij) The following conditions are satisfied:
a) at least X is not included in the setijAt inner K points Xoj,∈C{x≠XijSatisfy d (X)ij,Xoj,)≤d(Xij,Xoj)；
b) At most X is excluded from the setijK-1 points X including poj,∈C{x≠XijSatisfy d (X)ij,Xoj,)<d(Xij,Xoj) In this example, the value of K is 3.
And calculating the local outlier factors of each point one by one through an LOF algorithm, and arranging the local outlier factors in ascending order.
The spatial adjacent relation between the detection points is obtained from the network topology structure of the water supply network pipe explosion model, and if the detection point j1 is adjacent to the detection point j2, the pipe explosion probability P of a pipe section s formed by connecting the detection points j1 and the detection point j2 is calculated as follows:
where s represents the pipe section number, s ═ 1,2 … m, where m represents the maximum number of pipe sections, in this case 63; LOFk(X0j1) Current detection data X representing detection point j10j1Of the outlier factor, LOFk(X0j2) Current detection data X representing detection point j20j2The outlier factor of (a);
max(LOFk(X0j) And Large (LOF)k(X0j) Respectively) represent the largest and second largest outlier factors among all checkpoints.
And sequentially calculating the tube explosion probability of each tube section, setting different tube explosion probability thresholds, and obtaining different tube explosion tube section numbers. In this example, the pipe explosion probability calculation is performed at 24 times in total from 0 point to 24 points by using the pipe explosion detection data of the pipe explosion of No. 24, 30 and 53 pipe sections, that is, the pipe explosion probability calculation of each pipe section is performed for 72 rounds in total, screening calculation of the pipe explosion pipe sections is performed for different pipe explosion probability threshold values, and a group of pipe explosion detection results are exemplarily given by using the pipe explosion probability calculated at 12 points as a basis and using 0.85, 0.90 and 0.95 as pipe explosion probability threshold values respectively in table 1.
TABLE 1
The results in table 1 show that the method adopted by the patent can accurately predict the pipe section of the pipe explosion when the pipe explosion probability threshold is set to be 0.95, and has no explosion leakage or false alarm. In addition, false alarms occur on sections adjacent to the section of the booster.
Setting: the false alarm rate is the number of the pipe sections with wrong prediction results/the number of the predicted pipe sections; the missing report rate is the number of times that the pipe burst section does not appear in the prediction result/the total prediction number of times;
by expanding the value range of the tube explosion probability threshold, after the final prediction is carried out on the tube explosion probability calculation results of all 72 rounds in the embodiment by adopting different tube explosion probability thresholds, the false alarm rate and the missing report rate of the prediction result are counted, the higher the tube explosion probability threshold is, the lower the false detection rate is, and when the tube explosion probability threshold is as high as 0.85, the false alarm rate is 6.1%, and the missing report rate is 0; when the pipe explosion probability threshold is up to 0.9, the false alarm rate is reduced to 2.4%, and the false alarm rate is 0; when the tube probability threshold is as high as 0.6%, but the rate of missing reports is increased to 33.3% substantially; on the other hand, the false alarm condition is generated on the pipe section adjacent to the pipe section of the pipe burst, and the distance from the pipe section of the pipe burst is not far, so the influence caused by manual review is within a tolerable range, and therefore, the threshold value of the pipe burst probability is preferably 0.9.
The computer simulation result shows that by setting a proper threshold value, the method can better utilize historical detection data and current monitoring data to predict pipe sections with pipe explosion, and the probability of the false alarm condition and the false alarm condition are in an acceptable range.
Example two
In this embodiment, the scheme of the present invention is applied to actual pipe network detection, and a flow chart of the detection method is shown in fig. 3, which is specifically as follows
S1, collecting the detection data of each detection point in the pipe network to be detected at the current moment and historical detection data of the same moment in the past days;
s2, calculating the outlier factor of the detection data of each detection point at the current moment according to the detection data of each detection point at the current moment and the historical detection data;
s3, acquiring the spatial adjacent relation of the detection points, and calculating the pipe explosion probability of the pipe section between every two adjacent detection points according to the outlier factors of the two adjacent detection points at the current moment;
and S4, judging whether the pipe explosion probability of each pipe section is greater than a set threshold value, if so, judging that the pipe section is subjected to pipe explosion, otherwise, judging that the pipe explosion does not occur.
In the embodiment, the calculation of the outlier factor and the pipe explosion probability is the same as that in the embodiment 1, each detection node in a pipe network is a pressure sensor for collecting water pressure, pressure data collection is carried out all weather, the sampling period is 5 seconds, and the sampling data are collected to a background detection server; similarly, the depth of the historical time is also selected to be 3 days, and the K value representing the size of the field is also taken to be 3, so that the pipe explosion probability P in the embodiment 1 is calculated every 5 seconds by using the data in the past 3 days on the detection server, and the pipe explosion probability threshold is set to be 0.90; when the detection server finds that the pipe explosion probability of the pipe section exceeds the threshold value, the alarm information is sent out, and therefore real-time detection of the pipe network is achieved. By setting the threshold value, the situation that no false alarm is generated can be achieved, but false alarm may occur, as shown in the example in the table i, the false alarm occurs on a few adjacent pipe sections, that is, the distance from the pipe section where pipe explosion actually occurs is short, because the pressure detection data of the adjacent pipe section is certainly influenced after the pipe explosion of one pipe section actually occurs, so that the influence of the false alarm on the final dispatched workers to check and repair is not large, and the false alarm is within an acceptable range. However, if a higher threshold is selected, a false report may occur, and from the perspective of actual operation, a certain degree of false report may be acceptable, and the loss caused by the false report will be serious, so in this embodiment, 0.90 is selected as the threshold on the basis to ensure that the false report does not occur.
The signal connection between the pressure sensor and the detection server adopts a sensor network, data transmission is carried out by utilizing low-power-consumption communication protocols such as LORA or NB-IoT, the corresponding pressure sensor can be clustered, in order to increase the coverage range of a single detection server, a plurality of communication relay stations can be arranged in the sensor network, but the implementation of the detection method in the invention is not influenced no matter how the communication network is arranged.
According to the method in the embodiment, data of the same pipe section at different times are used as a basis, and the pipe explosion probability is calculated by judging the size of the outlier factor between the data of the pipe section at a certain moment and the data of the pipe section at previous historical moments, so that whether the pipe section is exploded or not is detected according to a set pipe explosion probability threshold value, time and labor consuming marking on the data is not needed, high practicability is achieved, and the feasibility of pipe network pipe explosion detection is high. After practical application, the working efficiency of detecting pipe explosion of a water plant when the pipe explosion occurs can be improved, and water resources are saved.
The foregoing are merely exemplary embodiments of the present invention, and no attempt is made to show structural details of the invention in more detail than is necessary for the fundamental understanding of the art, the description taken with the drawings making apparent to those skilled in the art how the several forms of the invention may be embodied in practice with the teachings of the invention. It should be noted that, for those skilled in the art, without departing from the structure of the present invention, several changes and modifications can be made, which should also be regarded as the protection scope of the present invention, and these will not affect the effect of the implementation of the present invention and the practicability of the patent. The scope of the claims of the present application shall be determined by the contents of the claims, and the description of the embodiments and the like in the specification shall be used to explain the contents of the claims.
Claims (8)
1. A water network pipe burst detection method based on local outlier factors is characterized by comprising the following steps: the method comprises the following steps:
s1, collecting the detection data of each detection point in the pipe network to be detected at the current moment and historical detection data of the same moment in the past days;
s2, calculating the outlier factor of the detection data of each detection point at the current moment according to the detection data of each detection point at the current moment and the historical detection data;
s3, acquiring the spatial adjacent relation of the detection points, and calculating the pipe explosion probability of the pipe section between every two adjacent detection points according to the outlier factors of the two adjacent detection points at the current moment;
and S4, judging whether the pipe explosion probability of each pipe section is greater than a set threshold value, if so, judging that the pipe section is subjected to pipe explosion, otherwise, judging that the pipe explosion does not occur.
2. The water service network pipe burst detection method based on the local outlier factor according to claim 1, wherein the method comprises the following steps: in step S2, the calculation process of the outlier factor is as follows:
let the detection data set y at the current moment be XojAnd the historical detection data set is X ═ XijWhere I is the historical time, I is {1,2 … I }, I represents the maximum depth of the historical time, J is the number of detected points, J is {1,2 … J }, and J represents the total number of detected points, the formula for calculating the outlier factor is as follows:
wherein: (1) rhok(Xoj) Represents point XojAll points in the K' th neighborhood of (c) to XojThe formula is as follows:
(2)Nk(Xoj) Is a point XojThe kth distance neighborhood of (c), satisfies:
Nk(Xoj)＝{Xij'∈D\{Xoj}|d(Xoj,Xij')≤dk(Xoj)}；
(3)dk(Xoj,Xij) Is XijPoint to point XojThe Kth reachable distance of
dk(Xoj,Xij)＝max{dk(Xoj),d(Xoj,Xij)}；
(4) Let d (X)oj,Xij) Is two pressure points XojAnd XijThe distance between them;
(5)dk(Xoj) Is a point XojA k-th distance of, and dk(Xoj)＝d(Xoj,Xij) The following conditions are satisfied:
a) at least X is not included in the setijAt the inner k points Xoj,∈C{x≠XijSatisfy d (X)ij,Xoj,)≤d(Xij,Xoj)；
b) At most X is excluded from the setijK-1 points X including poj,∈C{x≠XijSatisfy d (X)ij,Xoj,)<d(Xij,Xoj)。
3. The water service network pipe burst detection method based on the local outlier factor according to claim 2, wherein the method comprises the following steps: in step S3, the pipe bursting probability of a certain pipe section is calculated as follows:
if the detection point j1 and the detection point j2 are adjacent according to the spatial adjacent relation between the detection points, the tube explosion probability P of a certain section of the connected tube segment is calculated as follows:
wherein s represents the pipe section number, s ═ {1,2 … m }, m represents the maximum number of pipe sections; LOFk(X0j1) Current detection data X representing detection point j10j1Of the outlier factor, LOFk(X0j2) Current detection data X representing detection point j20j2The outlier factor of (a);
max(LOFk(X0j) And Large (LOF)k(X0j) Respectively) represent the largest and second largest outlier factors among all checkpoints.
4. The water service network pipe burst detection method based on the local outlier factor according to claim 1, wherein the method comprises the following steps: the detection data is a pressure value in the pipe.
5. The water service network pipe burst detection method based on the local outlier factor according to claim 2, wherein the method comprises the following steps: the K value representing the neighborhood size is selected to be 3 in step S2.
6. The water service network pipe burst detection method based on the local outlier factor according to claim 5, wherein the method comprises the following steps: the history depth of the history detection data sequence is selected to be 3 in step S1.
7. The water service network pipe burst detection method based on the local outlier factor according to claim 1, wherein the method comprises the following steps: the threshold value of the tube explosion probability ranges from 0.85 to 0.95.
8. The water service network pipe burst detection method based on the local outlier factor according to claim 7, wherein the method comprises the following steps: the threshold value of the tube explosion probability is 0.90.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910624754.7A CN110285330B (en) | 2019-07-11 | 2019-07-11 | Water network pipe burst detection method based on local outlier factor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910624754.7A CN110285330B (en) | 2019-07-11 | 2019-07-11 | Water network pipe burst detection method based on local outlier factor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110285330A CN110285330A (en) | 2019-09-27 |
| CN110285330B true CN110285330B (en) | 2021-08-10 |
Family
ID=68022098
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910624754.7A Active CN110285330B (en) | 2019-07-11 | 2019-07-11 | Water network pipe burst detection method based on local outlier factor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110285330B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111367972B (en) * | 2020-02-03 | 2021-04-02 | 重庆特斯联智慧科技股份有限公司 | Community drainage pipeline exploration method and system based on artificial intelligence |
| CN112097125B (en) * | 2020-09-18 | 2021-07-20 | 同济大学 | Water supply pipe network pipe burst detection and positioning method based on self-adaptive checking |
| CN117436845B (en) * | 2023-12-15 | 2024-04-09 | 山东齐芯智控科技有限公司 | Abnormal data monitoring method for intelligent district heating system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102777770A (en) * | 2012-08-07 | 2012-11-14 | 河北农业大学 | Flow monitoring point optimizing arranging method for water supply pipe network leakage fault diagnosis |
| CN104976517A (en) * | 2015-05-25 | 2015-10-14 | 安迅捷集装箱码头（深圳）有限公司 | Wharf water supply pipe network online supervision method |
| CN106874532A (en) * | 2016-12-23 | 2017-06-20 | 武汉智博创享科技有限公司 | A kind of grid method for analyzing cartridge igniter |
| CN108980628A (en) * | 2018-07-27 | 2018-12-11 | 上海航天动力科技工程有限公司 | A kind of water supply network booster alarm method |
| CN109560984A (en) * | 2018-11-13 | 2019-04-02 | 苏宁易购集团股份有限公司 | A kind of network service response time method for detecting abnormality and device |
| CN109681789A (en) * | 2019-03-01 | 2019-04-26 | 重庆邮电大学 | The relevant detection localization method of fluid line leak acoustic signal based on variation mode decomposition |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9104563B2 (en) * | 2012-02-09 | 2015-08-11 | Microsoft Technology Licensing, Llc | Self-tuning statistical resource leak detection |
-
2019
- 2019-07-11 CN CN201910624754.7A patent/CN110285330B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102777770A (en) * | 2012-08-07 | 2012-11-14 | 河北农业大学 | Flow monitoring point optimizing arranging method for water supply pipe network leakage fault diagnosis |
| CN104976517A (en) * | 2015-05-25 | 2015-10-14 | 安迅捷集装箱码头（深圳）有限公司 | Wharf water supply pipe network online supervision method |
| CN106874532A (en) * | 2016-12-23 | 2017-06-20 | 武汉智博创享科技有限公司 | A kind of grid method for analyzing cartridge igniter |
| CN108980628A (en) * | 2018-07-27 | 2018-12-11 | 上海航天动力科技工程有限公司 | A kind of water supply network booster alarm method |
| CN109560984A (en) * | 2018-11-13 | 2019-04-02 | 苏宁易购集团股份有限公司 | A kind of network service response time method for detecting abnormality and device |
| CN109681789A (en) * | 2019-03-01 | 2019-04-26 | 重庆邮电大学 | The relevant detection localization method of fluid line leak acoustic signal based on variation mode decomposition |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110285330A (en) | 2019-09-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109555979B (en) | Water supply pipe network leakage monitoring method | |
| CN110285330B (en) | Water network pipe burst detection method based on local outlier factor | |
| CN108984873B (en) | Water supply network real-time leakage detection method, device, system and storage medium | |
| CN107869653B (en) | Pipeline flow sensitivity matrix leakage detection method | |
| CN106372299B (en) | A kind of pipeline method for predicting residual useful life based on inverse Gaussian process and EM-PF | |
| CN102235575A (en) | Data processing method and system for checking pipeline leakage | |
| CN105930653A (en) | Pipe explosion pre-warning method based on metering zone flow monitoring data | |
| CN105608842A (en) | Nuclear reactor fuel failure online monitoring alarm device | |
| CN105388884A (en) | Alarm system for detecting leakage fault of heat supply network based on identification algorithm driven by data and method | |
| CN112377817A (en) | Municipal pipe network pipe explosion monitoring system and method | |
| CN110119853A (en) | Water supply network leakage loss alarm threshold value choosing method based on time series Analysis on monitoring data | |
| CN111666652B (en) | Steam heating network steam trap inspection emission operation scheduling method and operation scheduling system | |
| CN115654381A (en) | Water supply pipeline leakage detection method based on graph neural network | |
| CN108615098A (en) | Water supply network pipeline burst Risk Forecast Method based on Bayesian survival analysis | |
| CN116341272A (en) | Construction safety risk management and control system for digital distribution network engineering | |
| CN115481940A (en) | Oil and gas pipeline area risk monitoring system based on big data | |
| CN113128709B (en) | Water supply network leakage management system | |
| CN108071941A (en) | A kind of booster identification and localization method based on time series vector similarity analysis | |
| CN111317953B (en) | Intelligent algorithm-based water pipe network water leakage monitoring method for fire fighting | |
| CN113269352A (en) | Urban waterlogging monitoring and early warning method, system and medium based on mobile internet | |
| CN115493093A (en) | Steam heating pipe network leakage positioning method and system based on mechanical simulation | |
| Boatwright et al. | Optimal sensor placement and leak/burst localisation in a water distribution system using spatially-constrained inverse-distance weighted interpolation | |
| CN116484219A (en) | Water supply network water quality abnormal pollution source identification method based on gate control graph neural network | |
| CN112097125B (en) | Water supply pipe network pipe burst detection and positioning method based on self-adaptive checking | |
| CN116010800A (en) | Leakage point analysis method for quantifying candidate leakage node detection priority |
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 |