CN102072409B - Pipe network leakage monitoring method combining leakage probability calculation and recorder monitoring - Google Patents
Pipe network leakage monitoring method combining leakage probability calculation and recorder monitoring Download PDFInfo
- Publication number
- CN102072409B CN102072409B CN200910238226.4A CN200910238226A CN102072409B CN 102072409 B CN102072409 B CN 102072409B CN 200910238226 A CN200910238226 A CN 200910238226A CN 102072409 B CN102072409 B CN 102072409B
- Authority
- CN
- China
- Prior art keywords
- leakage
- recorder
- pipe
- monitoring
- pipe network
- 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.)
- Expired - Fee Related
Links
Abstract
The invention belongs to the field of pipe network leakage monitoring and particularly relates to a pipe network leakage monitoring method combining a leakage probability calculation process and an acoustical signal-based leakage recorder monitoring process. In the invention, a genetic programming process is used to establish a functional relationship between independent variables, such as pipe age, pipe diameter and pipe length, and leakage times, and a pipe network geographic information system (GIS) platform is combined to determine key areas to be monitored; furthermore, the leakage recorder monitoring process is used to clear leakage and position leakage points. The method can greatly improve leakage monitoring efficiency, reduce labor intensity of manual leakage monitoring and improve operation management level of a pipe network. The method is not only suitable for leakage monitoring of urban water supply pipe network, but also the leakage monitoring pipes such as recycled water pipe networks, heat distribution pipe and oil and gas pipes.
Description
Technical field
The present invention relates to a kind of pipe network leakage monitoring method, the particularly pointer leakage monitoring method to public supply mains.
Background technique
Public supply mains are city " lifelines ", and its safe and stable operation is to ensure the normally moving prerequisite turning of city.But in China and even world wide, public supply mains leakages is very serious, therefore, efficiently leakage monitoring method in the urgent need to.
At present, the leakage detection method being most widely used is audition leak detecting, in recent years, both at home and abroad some cities by a kind of leakage recorder of pipe leak noise signal of monitoring for the leakage loss monitoring of water supply network.This recorder is made up of many data loggers and a controller, recorder is laid on pipeline, can catch and record the noise signal that pipeline produces because leaking, by utilizing computer software to analyze these signals, can judge the generation of whether leaking in recorder region.
But this monitoring method does not have specific aim, much time power, efficiency is lower.Therefore, need to set up rational miss probability computation model, formulate rational monitoring scheme with aid decision personnel, improve leak detection efficiency.
The key problem of calculating pipe network miss probability space distribution is to select suitable model, but conventional model can not provide, formula clear and definite, that have physical significance, multivariable, extensive approval calculates the miss probability of pipeline.Conventional model has two large classes: the physical model based on pipeline aging mechanism, the statistical model based on historical missing data.Wherein, the physical model based on aging mechanism need to carry out long-term follow to particular conduit, and obtaining of data is more difficult, and cost is higher; Statistical model based on historical missing data need to screen leakage factor of influence, need to determine the model formation form adopting, and model accuracy is not too high.Utilize the space distribution rule of modeling pipe network miss probability, and in conjunction with the audition leak detecting based on leakage recorder, public supply mains are monitored, can greatly improve leakage loss monitoring efficiency, reduce the working strength of artificial leak detection.
Summary of the invention
The present invention is directed to the inefficient problem of water supply network leakage loss monitoring, and miss probability distribution Traditional calculating methods cost is high, miss factor of influence and model formation form is selected the problems such as difficulty, a kind of miss probability computational methods are provided, utilize genetic programming method automatic mining to go out the rule that historical missing data is followed, evaluate the space distribution of pipe leak probability, and in conjunction with the leakage recorder monitoring method based on sound signal, effectively improve leakage loss monitoring efficiency.
Know-why of the present invention is: will manage 3 key factors pipe leak number of times to significant effects such as age, caliber, pipe range as independent variable, to miss number of times as dependent variable, and utilize genetic programming to set up the function relation between dependent variable and independent variable.In pipe network geographic information system (GIS) platform, application gained function expression calculates the simulation leakage number of times of all pipeline sections, pipeline section simulation leakage number of times, divided by this pipeline section pipe range, can be obtained to simulation leakage density, and the size of this value reflects the size of pipeline section miss probability.Further, the miss probability spatial distribution result obtaining according to modeling, utilizes leakage recorder to carry out emphasis monitoring to the high region of miss probability, thereby significantly improves leakage loss monitoring efficiency.
Concrete technological scheme of the present invention is:
1, for the water supply network of target area to be monitored, utilize GIS statistics pipe network physical property data, collect the missing data in time backtracking from carrying out leakage loss monitoring 10～30 years.Missing data comprises that piping laying time of missing pipeline section is to carrying out year number (managing age), leakage pipeline section diameter (being caliber), the leakage length of pipe section (being pipe range) between time of leakage loss monitoring and missing frequency.In order to obtain statistical significance, all pipeline section data are divided into groups according to 2 factors of caliber and pipe age, be about to have identical caliber and be divided into one group with the pipeline section of managing age.Then, in each group, the pipe range of pipeline section is added to the pipe range sum that obtains dividing into groups, the leakage frequency of pipeline section is added and obtains grouping leakage frequency sum.
2, by caliber, manage age, grouping pipe range sum is as independent variable, to divide into groups leakage frequency sum as dependent variable, according to genetic programming principle, its parameter is set as shown in table 1, utilize PC Tools exploitation genetic programming model, model will utilize operator and the independent variable of parameter in arranging to generate at random representation, and select representation (variance between calculated value and dependent variable and more little more selected) to carry out 2 genetic manipulations of crossover and mutation according to the degree of closeness between the calculated value of representation and dependent variable, when program evolves to after certain algebraically, can obtain describing better the function expression of relation between independent variable and dependent variable.
3, utilize the GIS platform of target area to be monitored water supply network, in pipe network attribute list, add " the leakage number of times analogue value " field, according to the caliber of each pipeline section, pipe age, pipe range information, utilize functional relation obtained in the previous step to calculate the simulation leakage number of times of each pipeline section, the length divided by this pipeline section by its result again, obtain the prediction leakage number of times in unit length, that is the leakage density of pipeline section, set it as new field and insert pipe network attribute list.
4, all pipeline sections are carried out to descending sequence according to " leakage density " field, then to all pipeline sections according to this sequentially, utilize leakage recorder to carry out leakage loss monitoring and leakage points location, concrete grammar is as follows:
Leakage recorder is laid principle: the pipeline that is 75mm～200mm for diameter, and leakage recorder is laid distance between 150m～200m; The pipeline that is 200mm～400mm for diameter, leakage recorder is laid distance between 100m～150m; Be pipeline more than 400mm for diameter, leakage recorder is laid distance between 60m～100m.Definite principle that leakage recorder cloth is set up an office is: be preferentially chosen on pipeline auxiliary construction and lay, auxiliary construction refers to inspection shaft, fire hydrant, exhaust valve, valve, gate etc.
Afterwards, treat monitoring objective regional water supply pipe network and carry out missed signal collection.The 2nd day to the 6th day any one day after leakage recorder is laid, carry signal collection main frame with the speed that is less than 30km/h near process recorder installation position, wherein signal collection main frame and miss between recorder distance in 20m; After being received by main frame, the signal of leakage recorder record determines whether to exist leakage.
5, collect the missed signal of leakage recorder, prompt for the region of " leakage points " and " suspicious leakage points " for missed signal, send workman to go to the pipeline section that occurs to miss manually to listen to omit in printing and look into; Prompt for the region of " normal point " for missed signal, needn't manually investigate.
Table 1 genetic programming parameter arranges
| Independent variable | Caliber, pipe age, grouping pipe range sum |
| Dependent variable | Grouping leakage frequency sum |
| Function | Add, subtract, multiplication and division, ask absolute value, power, index, logarithm |
| Fitness evaluation standard | Variance between the analogue value and actual value and size, variance and little person's fitness are high |
| Population Size | Determine according to data volume size, recommend 4000～6000 |
| Evolutionary generation | Determine according to data volume size, recommend 100～200 |
| Crossover probability | Recommend 0.4～0.5 |
| Variation probability | Recommend 0.001～0.003 |
Compared with existing public supply mains leakage monitoring method, the present invention has following advantage:
1, only need to utilize the historical data of pipe network, and not need particular conduit to carry out tracking test, can complete the exploitation of pipe network miss probability computation model.Therefore, the construction cycle of pipe network miss probability computation model is shorter, and required cost is lower.
2, adopt the algorithm of genetic programming as Formula, do not limit the functional relation structure between number and independent variable and the dependent variable of independent variable, the result that model finally obtains be completely genetic programming according to the fine or not automatic screening of analog result out, so just than adopt fixing equation regression model have higher simulation precision.
3, utilize pipe network miss probability spatial distribution result, can effectively avoid missing merely the blindness of recorder monitoring method, improve leakage loss monitoring efficiency.
Embodiment
For further disclosing technological scheme of the present invention, be described in detail below in conjunction with embodiment.
The present embodiment is certain public supply mains, comprise hundreds thousand of more than of pipeline sections, all pipeline sections are divided into groups according to caliber and pipe age, obtain 500 groups of data, and calculate pipe range sum and 19 years (1987～2005) interior leakage number of times summation in grouping.Only list 30 groups of data signals at this as space is limited,, as shown in table 2.Then set the parameter of genetic programming according to table 1, operation genetic programming program, obtains optimum analog result and is
Wherein B is simulation leakage number of times, and A is for managing age, and L is pipe range, and D is caliber.Partial simulation of the present invention the results are shown in table 2 (the 5th row).
Table 2 pipeline association attributes, leakage number of times and the leakage number of times analogue value
| Caliber/mm | Pipe age/yr | Pipe range and/km | Leakage number of times | The leakage number of times analogue value |
| 75 | 30 | 4.79781 | 2 | 3.67894 |
| 75 | 9 | 1.81055 | 2 | 1.02858 |
| 75 | 14 | 8.05351 | 1 | 4.21558 |
| 75 | 20 | 9.65272 | 4 | 5.81227 |
| 75 | 40 | 6.56455 | 3 | 3.62497 |
| 75 | 1 | 1.81732 | 0 | 0.137627 |
| 75 | 38 | 50.1478 | 25 | 26.5122 |
| 100 | 23 | 16.9644 | 4 | 6.79194 |
| 100 | 51 | 6.32631 | 0 | 0.600464 |
| 100 | 19 | 18.3116 | 9 | 6.47531 |
| 100 | 10 | 41.7153 | 8 | 6.80112 |
| 100 | 24 | 18.4509 | 6 | 7.33709 |
| 100 | 1 | 65.0794 | 1 | 1.00904 |
| 100 | 4 | 27.6847 | 2 | 2.28469 |
| 100 | 22 | 20.8835 | 7 | 7.67958 |
| 150 | 19 | 8.7843 | 2 | 2.66363 |
| 150 | 15 | 18.379 | 2 | 3.71046 |
| 150 | 33 | 1.2322 | 0 | 0.528977 |
| 150 | 36 | 1.9197 | 0 | 0.701808 |
| 150 | 39 | 2.92796 | 0 | 0.878235 |
| 150 | 27 | 5.54141 | 1 | 2.1023 |
| 150 | 42 | 2.43818 | 0 | 0.567053 |
| 200 | 12 | 14.6693 | 0 | 2.05726 |
| 200 | 24 | 3.1706 | 1 | 1.02063 |
| 200 | 40 | 3.48593 | 0 | 0.729373 |
| 200 | 32 | 1.54122 | 0 | 0.502536 |
| 200 | 20 | 8.70315 | 0 | 2.03305 |
| 400 | 45 | 8.09224 | 0 | 0.629765 |
| 400 | 17 | 23.6416 | 1 | 1.78402 |
| 500 | 26 | 3.39706 | 0 | 0.431858 |
Then, based on these public supply mains GIS platform, in pipe network attribute list, add " the leakage number of times analogue value " field, and the formula that utilizes upper step to obtain
Calculate the simulation leakage number of times B of all pipeline sections, and obtain missing density divided by length of pipe section L, and according to missing density value to the descending sequence of all pipeline sections.Fig. 1 is the miss probability spatial distribution map of the embodiment of the present invention, and wherein highlighted demonstration is that leakage density comes front 20% pipeline.Finally, can utilize leakage recorder first to miss investigation for this pipeline section of 20%.
Claims (4)
1. a pipe network leakage monitoring method, is characterized in that miss probability computational methods to be combined and to be applied to pipe network leakage loss monitoring with the leakage recorder monitoring method based on sound signal; Described miss probability computational methods comprise using pipe age, caliber, 3 factors of pipe range as independent variable, to miss number of times as dependent variable, utilize genetic programming method to set up the function relation between dependent variable and independent variable, and utilize pipe network geographic information system platform to calculate simulation leakage density and space distribution rule thereof, and the high emphasis monitored area of definite miss probability;
Wherein, described genetic programming method comprise independent variable be set to caliber, pipe age, grouping pipe range and, dependent variable be set to grouping leakage number of times and, functional operation is set to add, subtracts, multiplication and division, ask absolute value, power, index, logarithm; Population Size is set to 4000～6000, and evolutionary generation is made as 100～200, and crossover probability is made as 0.5, and variation probability is made as 0.001.
2. pipe network leakage monitoring method according to claim 1, is characterized in that in described genetic programming method, individual superior and inferior evaluating standard is variance and the size between the analogue value and actual value, and variance and less individuality are more excellent, otherwise poorer.
3. pipe network leakage monitoring method according to claim 1, is characterized in that utilizing leakage recorder to monitor the high emphasis monitored area of miss probability; The 2nd day to the 6th day any one day after leakage recorder is laid, carry signal collection main frame with the speed that is less than 30km/h near process recorder installation position, wherein signal collection main frame and miss between recorder distance in 20m; After being received by main frame, the signal of leakage recorder record determines whether to exist leakage; Missed signal is prompted for to the region of " leakage points " and " suspicious leakage points ", send workman to go to the pipeline section that occurs to miss manually to listen to omit in printing and look into; Missed signal is prompted for to the region of " normal point ", needn't manually investigate.
4. pipe network leakage monitoring method according to claim 1, is characterized in that, in the leakage recorder monitoring method based on sound signal, take pipe leak sound signal as locating according to carrying out leakage loss monitoring and leakage points; Leakage recorder is laid principle: the pipeline that is 75mm～200mm for diameter, and leakage recorder is laid distance between 150m～200m; The pipeline that is 200mm～400mm for diameter, leakage recorder is laid distance between 100m～150m; Be pipeline more than 400mm for diameter, leakage recorder is laid distance between 60m～100m; Definite principle that leakage recorder cloth is set up an office is: be preferentially chosen on pipeline auxiliary construction and lay, auxiliary construction refers to inspection shaft, fire hydrant, exhaust valve, valve, gate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200910238226.4A CN102072409B (en) | 2009-11-23 | 2009-11-23 | Pipe network leakage monitoring method combining leakage probability calculation and recorder monitoring |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200910238226.4A CN102072409B (en) | 2009-11-23 | 2009-11-23 | Pipe network leakage monitoring method combining leakage probability calculation and recorder monitoring |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102072409A CN102072409A (en) | 2011-05-25 |
| CN102072409B true CN102072409B (en) | 2014-05-21 |
Family
ID=44031069
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN200910238226.4A Expired - Fee Related CN102072409B (en) | 2009-11-23 | 2009-11-23 | Pipe network leakage monitoring method combining leakage probability calculation and recorder monitoring |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102072409B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101447925B1 (en) * | 2013-08-22 | 2014-10-08 | 주식회사 엘지씨엔에스 | Leakage signal analysis method |
| CN104697908A (en) * | 2015-03-12 | 2015-06-10 | 国家海洋局天津海水淡化与综合利用研究所 | Method for monitoring drifting salt deposition of seawater cooling tower |
| CN104866899A (en) * | 2015-06-17 | 2015-08-26 | 山东省环境保护科学研究设计院 | Leakage detection method based on hydraulic model calibration of urban water supply network |
| CN105605429A (en) * | 2015-12-29 | 2016-05-25 | 安徽海兴泰瑞智能科技有限公司 | Method for managing urban water supply pipes |
| CN106874575B (en) * | 2017-01-19 | 2020-03-27 | 北京工业大学 | Method for establishing pipe network leakage prediction model based on EPR evolutionary polynomial regression |
| CN106869247B (en) * | 2017-02-16 | 2019-04-23 | 中国科学院生态环境研究中心 | A kind of method and system improving pipe network leakage control efficiency |
| CN109002590B (en) * | 2018-06-26 | 2023-07-14 | 清华大学 | Method for determining leakage point growth function |
| CN109737308B (en) * | 2018-12-26 | 2021-04-20 | 成都熊谷油气科技有限公司 | LBS and big data based oil and gas pipeline punching and oil stealing monitoring analysis method |
| CN110108328B (en) * | 2019-04-03 | 2021-03-26 | 同济大学 | Method for acquiring water leakage amount of leakage area of water supply pipe network |
| CN110984302B (en) * | 2019-12-11 | 2020-11-03 | 浙江嘉科信息科技有限公司 | Water pipe network sensor deployment positioning system and positioning method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101329012A (en) * | 2007-06-23 | 2008-12-24 | 富士地探株式会社 | Leakage detector |
| CN101409941A (en) * | 2008-11-21 | 2009-04-15 | 冶金自动化研究设计院 | System and method for analyzing coal gas pipe net present status |
| CN101493186A (en) * | 2009-02-27 | 2009-07-29 | 保定市金迪科技开发有限公司 | Groundwater supply pipe network water leakage detecting method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3070590B2 (en) * | 1998-12-14 | 2000-07-31 | 株式会社エヌ・ティ・ティ ファシリティーズ | Engine power generation equipment |
| JP2002310840A (en) * | 2001-04-10 | 2002-10-23 | Noriyuki Uto | Control system for water pipe |
-
2009
- 2009-11-23 CN CN200910238226.4A patent/CN102072409B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101329012A (en) * | 2007-06-23 | 2008-12-24 | 富士地探株式会社 | Leakage detector |
| CN101409941A (en) * | 2008-11-21 | 2009-04-15 | 冶金自动化研究设计院 | System and method for analyzing coal gas pipe net present status |
| CN101493186A (en) * | 2009-02-27 | 2009-07-29 | 保定市金迪科技开发有限公司 | Groundwater supply pipe network water leakage detecting method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102072409A (en) | 2011-05-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102072409B (en) | Pipe network leakage monitoring method combining leakage probability calculation and recorder monitoring | |
| CN110108328B (en) | Method for acquiring water leakage amount of leakage area of water supply pipe network | |
| Li et al. | Development of systems for detection, early warning, and control of pipeline leakage in drinking water distribution: A case study | |
| CN107355688B (en) | Urban water supply network leakage control management system | |
| CN108984873B (en) | Water supply network real-time leakage detection method, device, system and storage medium | |
| CN102235575B (en) | Data processing method and system for checking pipeline leakage | |
| KR100973662B1 (en) | Water leakage position estimating system | |
| CN110866974A (en) | Hydraulic monitoring system based on three-dimensional display | |
| CN102890792A (en) | Municipal drainage pipe network decision evaluation method | |
| CN104930355A (en) | Online nondestructive detection method and device applicable to urban water supply pipeline system | |
| CN103953098A (en) | Pipe network loss monitoring method | |
| CN109886506B (en) | Water supply network pipe explosion risk analysis method | |
| CN108615098B (en) | Bayesian survival analysis-based water supply network pipeline pipe burst risk prediction method | |
| CN103559399A (en) | Water transportation pipe network leakage positioning method based on Bayesian decision theory and genetic algorithm | |
| CN105653791A (en) | Data mining based corrosion failure prediction system for on-service oil pipe column | |
| CN102072404A (en) | Optimizing layout method for leakage monitoring points of urban water supply pipe network | |
| Zhang et al. | Optimization monitoring distribution method for gas pipeline leakage detection in underground spaces | |
| Hou et al. | Optimization of the gas leak monitoring points distributed underground | |
| CN115127037A (en) | Water supply pipe network leakage positioning method and system | |
| CN106874575A (en) | A kind of pipe network based on EPR evolution polynomial regressions misses the method for building up of forecast model | |
| CN112785141A (en) | Comprehensive pipe gallery whole life cycle planning design intrinsic safety risk assessment method | |
| CN109027700B (en) | Method for evaluating leakage detection effect of leakage point | |
| CN116796473A (en) | Gas pipe network monitoring point position layout method based on improved greedy algorithm | |
| CN115493093A (en) | Steam heating pipe network leakage positioning method and system based on mechanical simulation | |
| CN115127036B (en) | Municipal gas pipe network leakage positioning method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20140521 Termination date: 20191123 |