CN111210083A - Pipe network abnormity analysis method - Google Patents
Pipe network abnormity analysis method Download PDFInfo
- Publication number
- CN111210083A CN111210083A CN202010033118.XA CN202010033118A CN111210083A CN 111210083 A CN111210083 A CN 111210083A CN 202010033118 A CN202010033118 A CN 202010033118A CN 111210083 A CN111210083 A CN 111210083A
- Authority
- CN
- China
- Prior art keywords
- pipe
- pipe section
- value
- time
- abnormal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 33
- 238000012544 monitoring process Methods 0.000 claims abstract description 82
- 230000002159 abnormal effect Effects 0.000 claims abstract description 75
- 238000004364 calculation method Methods 0.000 claims abstract description 18
- 238000000034 method Methods 0.000 claims abstract description 18
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 29
- 238000004880 explosion Methods 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000005474 detonation Methods 0.000 claims 1
- 238000001514 detection method Methods 0.000 abstract description 4
- 230000005856 abnormality Effects 0.000 description 12
- 238000012423 maintenance Methods 0.000 description 7
- 230000009172 bursting Effects 0.000 description 4
- 239000000463 material Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 230000000246 remedial effect Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Images
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Pipeline Systems (AREA)
Abstract
The invention discloses a pipe network anomaly analysis method which can obtain an abnormal value of each pipe section according to the pipe section characteristics of the pipe sections related to abnormal points and a pre-trained calculation model and judge whether the pipe sections burst or not according to the abnormal values. According to the technical scheme, a calculation model is trained in advance according to massive historical data, the burst pipe section can be judged and predicted reasonably and efficiently according to monitoring data, meanwhile, the situation of simultaneous burst of multiple points is further optimized and judged, and therefore active prediction and technical early warning of pipeline burst are achieved. By adopting the technical scheme, the growth of the small leak can be prevented to the maximum extent, the management period and the labor consumption of leak detection are greatly shortened, and the method has high economic value.
Description
Technical Field
The invention relates to the field of water service pipe network safety monitoring, in particular to a pipe network abnormity analysis method.
Background
Municipal water pipe network is the life line engineering in city, and the main pipe explosion in city often brings very serious consequence. With the advance of information and intelligent water affairs of pipe networks, real-time online monitoring of pipe explosion accidents is an important component of safety guarantee of water affair enterprises and is also paid more and more attention. At present, after pipe explosion is mainly found by field personnel, the pipe explosion is remotely fed back to an operation enterprise through hot-wire telephones and other modes so as to take corresponding measures, the mode is extremely low in efficiency and cannot reflect the situation in time, at most, the mode is a remedial measure after the occurrence of large pipe explosion, and therefore a mode capable of autonomously analyzing and judging the abnormality of a pipe network is urgently needed.
Disclosure of Invention
Aiming at the problems in the prior art, a pipe network abnormity analysis method is provided, and the specific technical scheme is as follows:
a pipe network anomaly analysis method is applied to a water service pipe network, a plurality of monitoring terminals are arranged in the water service pipe network, and each monitoring terminal collects and outputs real-time pipe network data once every preset time interval;
recording a water service pipe network between every two adjacent monitoring terminals as a pipe section;
the method for analyzing the pipe network abnormality comprises the following steps:
step S1, according to the real-time pipe network data, continuously generating and outputting the real-time monitoring value corresponding to each monitoring terminal;
step S2, determining whether each real-time monitoring value is less than or equal to a first preset threshold:
if each real-time monitoring value is less than or equal to the first preset threshold value, returning to the step S2;
if any real-time monitoring value is greater than the first preset threshold value, recording the monitoring terminal corresponding to the real-time monitoring value greater than the first preset threshold value as an abnormal point, and turning to the step S3;
step S3, recording all pipe sections containing abnormal points as pipe sections to be analyzed, and acquiring the pipe section characteristics of all pipe sections to be analyzed;
step S4, obtaining the abnormal value of each pipe section to be analyzed according to the characteristics of the pipe section and a calculation model obtained by pre-training, and judging whether each abnormal value is less than or equal to a second preset threshold value:
if each abnormal value is less than or equal to the second preset threshold, returning to the step S2;
if any abnormal value is larger than the second preset threshold, the process goes to step S5;
and step S5, marking the pipe section corresponding to the abnormal value larger than the second preset threshold value as a burst pipe section and outputting the burst pipe section, and then returning to the step S2.
Preferably, in the pipe network abnormality analysis method, the preset time is in a value range of [30ms, 50ms ].
Preferably, the method for analyzing pipe network anomaly, wherein the real-time pipe network data includes pressure values.
Preferably, in the pipe network abnormality analysis method, step S1 further includes:
step S11, for each monitoring terminal, performing linear fitting according to real-time pipe network data, and outputting a real-time trend curve corresponding to each monitoring terminal;
and step S12, calculating the slope value of the real-time trend curve at preset time intervals according to the real-time trend curve and recording the slope value as a real-time monitoring value.
Preferably, in the pipe network anomaly analysis method, a monitoring terminal at one end of a pipe section is recorded as a first monitoring terminal, and a monitoring terminal at the other end of the pipe section is recorded as a second monitoring terminal;
recording the time corresponding to the real-time monitoring value larger than the first preset threshold as an abnormal time;
the pipe section characteristics comprise all real-time pipe network data corresponding to the first monitoring terminal in a preset time period before and after the abnormal time, all real-time pipe network data corresponding to the second monitoring terminal in a preset time period before and after the abnormal time, the pipe length and the pipe diameter of the pipe section and the water flow direction in the pipe section.
Preferably, the pipe network anomaly analysis method, wherein the pipe segment characteristics comprise a plurality of characteristic quantities;
the calculation model comprises a plurality of weighting coefficients, each weighting coefficient corresponds to a characteristic quantity, and an abnormal value is obtained by weighting and adding the plurality of characteristic quantities.
Preferably, in the method for analyzing the pipe network anomaly, before step S1, a plurality of sets of historical pipe section characteristic data are preset;
each group of historical pipe section characteristic data comprises a plurality of groups of pipe section characteristics, and each group of pipe section characteristics corresponds to one pipe section;
each set of historical pipe segment characteristic data comprises pipe segment characteristics of at least one burst pipe segment and pipe segment characteristics of at least one non-burst pipe segment;
before step S1, the method includes the following steps:
step A1, extracting a group of historical pipe section characteristic data in sequence, and respectively obtaining abnormal values corresponding to each pipe section in the group of historical pipe section characteristic data according to a calculation model;
step A2, sorting the abnormal values in the order from high to low;
step A3, marking an interval composed of the minimum value of the abnormal value corresponding to the burst pipe section and the maximum value of the abnormal value corresponding to the non-burst pipe section as a critical interval;
step A4, repeating the steps A1 to A3 until a plurality of groups of historical pipe section characteristic data all obtain a corresponding critical interval;
and step A5, taking intersection of all critical intervals, recording the intersection as a critical value set of pipe explosion, and outputting.
Preferably, in the pipe network anomaly analysis method, the second preset threshold belongs to a pipe bursting critical value set.
Preferably, in the method for analyzing the pipe network abnormality, the pipe sections are numbered according to a preset rule;
the preset rule is that the numbers of the adjacent pipe sections are similar.
Preferably, in the pipe network abnormality analysis method, step S5 further includes:
step S51, determining whether the number of abnormal values greater than the second preset threshold is equal to 1:
if so, marking the pipe section corresponding to the abnormal value as a burst pipe section and outputting the burst pipe section;
if not, go to step S52;
step S52, acquiring the numbers of the pipe sections corresponding to all abnormal values, sequencing the numbers in the order from big to small, and outputting a number sequence;
step S53, determining whether the absolute values of the differences of the numbers in the number sequence are all less than or equal to a third preset threshold:
if the absolute values are less than or equal to a third preset threshold, marking the pipe section corresponding to the maximum value in the abnormal values as a burst pipe section and outputting the burst pipe section;
if any absolute value is greater than the third preset threshold, go to step S54;
step S54, dividing the numbering sequence according to two numbers corresponding to the absolute value to obtain at least two numbering subsequences;
in step S55, each of the numbered subsequences is output.
This technical scheme has following advantage or beneficial effect:
according to the technical scheme, a calculation model is trained in advance according to massive historical data, the burst pipe section can be judged and predicted reasonably and efficiently according to monitoring data, meanwhile, the situation of simultaneous burst of multiple points is further optimized and judged, and therefore active prediction and technical early warning of pipeline burst are achieved. By adopting the technical scheme, the growth of the small leak can be prevented to the maximum extent, the management period and the labor consumption of leak detection are greatly shortened, and the method has high economic value.
Drawings
Fig. 1 is a schematic flow chart of a pipe network anomaly analysis method according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
The invention is further described with reference to the following drawings and specific examples, which are not intended to be limiting.
A pipe network anomaly analysis method is applied to a water service pipe network, a plurality of monitoring terminals are arranged in the water service pipe network, and each monitoring terminal collects and outputs real-time pipe network data once every preset time interval;
recording a water service pipe network between every two adjacent monitoring terminals as a pipe section;
as shown in fig. 1, the pipe network anomaly analysis method includes the following steps:
step S1, according to the real-time pipe network data, continuously generating and outputting the real-time monitoring value corresponding to each monitoring terminal;
step S2, determining whether each real-time monitoring value is less than or equal to a first preset threshold:
if each real-time monitoring value is less than or equal to the first preset threshold value, returning to the step S2;
if any real-time monitoring value is greater than the first preset threshold value, recording the monitoring terminal corresponding to the real-time monitoring value greater than the first preset threshold value as an abnormal point, and turning to the step S3;
step S3, recording all pipe sections containing abnormal points as pipe sections to be analyzed, and acquiring the pipe section characteristics of all pipe sections to be analyzed;
step S4, obtaining the abnormal value of each pipe section to be analyzed according to the characteristics of the pipe section and a calculation model obtained by pre-training, and judging whether each abnormal value is less than or equal to a second preset threshold value:
if each abnormal value is less than or equal to the second preset threshold, returning to the step S2;
if any abnormal value is larger than the second preset threshold, the process goes to step S5;
and step S5, marking the pipe section corresponding to the abnormal value larger than the second preset threshold value as a burst pipe section and outputting the burst pipe section, and then returning to the step S2.
In a preferred embodiment of the present invention, the method for analyzing pipe network anomaly firstly analyzes the real-time acquisition value of each monitoring terminal, when the real-time monitoring value is greater than a first preset threshold, it indicates that the monitoring point location corresponding to the monitoring terminal has a pipe network anomaly, at this time, all pipe sections related to the monitoring point location are marked as pipe sections to be analyzed, an anomaly value of each analyzed pipe section is obtained through a pre-trained calculation model, and whether the pipe section bursts or not is determined by the anomaly value.
As a preferred embodiment, the pipe network abnormality analysis method is characterized in that the preset time is in a value range of [30ms, 50ms ].
In another preferred embodiment of the present invention, the monitoring terminals are all installed in the secondary water supply pump room of the water service pipe network to meet the related requirements of high frequency acquisition. In present prior art, traditional pipe network data acquisition point often directly sets up in the pipeline section of pipe network, want to repair, upgrade and replace and often need dig out whole pipeline section and reset, can consume a large amount of manpower, materials and financial resources, in above-mentioned preferred embodiment, will regard as the monitor terminal 1 of data acquisition point and all set up in the junction of existing secondary water supply pump house and municipal water pipe network, can reflect the whole situation of change of water pipe network more effectively: the number of pump rooms in a city is large, so that collection points can be greatly increased, and the consumed manpower, material resources and financial resources are greatly saved compared with the situation that collection points are directly arranged in a pipe network; the secondary water supply pump house is generally relatively perfect in data acquisition, transmission, power supply, control mode and other configurations, and can support high-frequency data acquisition, pressure change of a pipe network generally occurs in a millisecond-level extremely short time, and the monitoring frequency must be guaranteed to be high enough to effectively monitor fine pressure fluctuation of the pipe network, so that the acquisition frequency needs to be limited between [30ms and 50ms ], and meanwhile, operation and maintenance personnel can properly adjust the acquisition frequency according to actual needs.
As a preferred embodiment, the pipe network anomaly analysis method includes that real-time pipe network data includes pressure values.
In another preferred embodiment of the present invention, the real-time pipe network data includes the pipe network pressure value flowing through the installation location of the monitoring terminal, which is most closely related to the pressure state of the pipe network, and of course, other water affair related parameters such as flow rate may be included in the real-time pipe network data and may be set by the operation and maintenance personnel.
As a preferred embodiment, in the pipe network abnormality analysis method, the step S1 further includes:
step S11, for each monitoring terminal, performing linear fitting according to real-time pipe network data, and outputting a real-time trend curve corresponding to each monitoring terminal;
and step S12, calculating the slope value of the real-time trend curve at preset time intervals according to the real-time trend curve and recording the slope value as a real-time monitoring value.
In another preferred embodiment of the present invention, the specific process in step S1 is further described in detail: the real-time pipe network data uploaded by the monitoring terminals are subjected to linear fitting according to a time axis, a real-time trend curve corresponding to each detection terminal is output, a slope value at a certain moment is calculated according to the real-time trend curve, the larger the slope value is, the more obvious the change and fluctuation of the real-time trend curve are, the more the reflected real-time monitoring value conforms to the characteristic of pipe network burst, and therefore when the real-time detection value is larger than a first preset threshold value, the pipe section near the monitoring point is judged to have burst risks and needs to be further evaluated.
Particularly, the technical scheme aims at monitoring and preventing pipe network bursting, so that the pressure value data in the real-time pipe network data are usually fitted in a pressure-time coordinate system to obtain a real-time pressure trend curve, and the real-time pressure trend curve can be output outwards for operation and maintenance personnel to check.
In a preferred embodiment, the pipe network anomaly analysis method includes recording a monitoring terminal at one end of a pipe section as a first monitoring terminal, and recording a monitoring terminal at the other end of the pipe section as a second monitoring terminal;
recording the time corresponding to the real-time monitoring value larger than the first preset threshold as an abnormal time;
the pipe section characteristics comprise all real-time pipe network data corresponding to the first monitoring terminal in a preset time period before and after the abnormal time, all real-time pipe network data corresponding to the second monitoring terminal in a preset time period before and after the abnormal time, the pipe length and the pipe diameter of the pipe section and the water flow direction in the pipe section.
In another preferred embodiment of the present invention, the characteristic quantity included in the pipe segment characteristics is further described, including all real-time pipe network data corresponding to the first monitoring terminal in a preset time period before and after the abnormal time, all real-time pipe network data corresponding to the second monitoring terminal in a preset time period before and after the abnormal time, the pipe length and the pipe diameter of the pipe segment, and the water flow direction in the pipe segment, so that main characteristics related to pipe segment bursting can be summarized relatively comprehensively, and operation and maintenance personnel can also appropriately delete and supplement the characteristic quantity according to actual needs.
In a preferred embodiment, the pipe network anomaly analysis method includes a step of analyzing pipe segment characteristics including a plurality of characteristic quantities;
the calculation model comprises a plurality of weighting coefficients, each weighting coefficient corresponds to a characteristic quantity, and an abnormal value is obtained by weighting and adding the plurality of characteristic quantities.
In another preferred embodiment of the present invention, the calculation model includes a plurality of weighting coefficients, each weighting coefficient corresponds to a feature quantity, and an abnormal value is obtained by performing weighted addition on the plurality of feature quantities, and in combination with the above preferred embodiment, the feature quantities include all real-time pipe network data corresponding to the first monitoring terminal in a preset time period before and after the abnormal time, all real-time pipe network data corresponding to the second monitoring terminal in a preset time period before and after the abnormal time, the pipe length, the pipe diameter, and the water flow direction in the pipe section, and an evaluable specific abnormal value is obtained by a weighting algorithm, so as to facilitate determination of whether the abnormal value represents a pipe section burst.
In the above preferred embodiment, the determination of the weighting coefficients in the calculation model is performed by pre-training a large amount of historical data, and the weighting is specifically set according to the importance of the characteristic quantities and the correlation of the water pipe burst.
In particular, the calculation model is not invariable, the burst judgment standard of the water service pipe section is not invariable, and the calculation model has certain self-learning capability and can optimize the weight setting standard among all characteristic quantities according to data obtained during daily operation.
As a preferred embodiment, in the pipe network abnormality analysis method, before step S1, a plurality of sets of historical pipe segment characteristic data are preset;
each group of historical pipe section characteristic data comprises a plurality of groups of pipe section characteristics, and each group of pipe section characteristics corresponds to one pipe section;
each set of historical pipe segment characteristic data comprises pipe segment characteristics of at least one burst pipe segment and pipe segment characteristics of at least one non-burst pipe segment;
before step S1, the method includes the following steps:
step A1, extracting a group of historical pipe section characteristic data in sequence, and respectively obtaining abnormal values corresponding to each pipe section in the group of historical pipe section characteristic data according to a calculation model;
step A2, sorting the abnormal values in the order from high to low;
step A3, marking an interval composed of the minimum value of the abnormal value corresponding to the burst pipe section and the maximum value of the abnormal value corresponding to the non-burst pipe section as a critical interval;
step A4, repeating the steps A1 to A3 until a plurality of groups of historical pipe section characteristic data all obtain a corresponding critical interval;
and step A5, taking intersection of all critical intervals, recording the intersection as a critical value set of pipe explosion, and outputting.
As a preferred embodiment, in the pipe network abnormality analysis method, the second preset threshold belongs to a pipe bursting critical value set.
In another preferred embodiment of the present invention, the setting manner of the second preset threshold is further described in detail:
as a preferred embodiment, in the method for analyzing pipe network abnormality, pipe sections are numbered according to a preset rule;
the preset rule is that the numbers of the adjacent pipe sections are similar.
As a preferred embodiment, in the pipe network abnormality analysis method, the step S5 further includes:
step S51, determining whether the number of abnormal values greater than the second preset threshold is equal to 1:
if so, marking the pipe section corresponding to the abnormal value as a burst pipe section and outputting the burst pipe section;
if not, go to step S52;
step S52, acquiring the numbers of the pipe sections corresponding to all abnormal values, sequencing the numbers in the order from big to small, and outputting a number sequence;
step S53, determining whether the absolute values of the differences of the numbers in the number sequence are all less than or equal to a third preset threshold:
if the absolute values are less than or equal to a third preset threshold, marking the pipe section corresponding to the maximum value in the abnormal values as a burst pipe section and outputting the burst pipe section;
if any absolute value is greater than the third preset threshold, go to step S54;
step S54, dividing the numbering sequence according to two numbers corresponding to the absolute value to obtain at least two numbering subsequences;
in step S55, each numbered subsequence is output.
A specific embodiment is now provided to further describe and explain the present technical solution:
in the specific embodiment of the invention, the situation of multipoint burst of the water service pipe network is further defined and optimized: firstly, numbering each pipe section, wherein due to the irregularity of the monitoring terminal, no specific literary rule exists for numbering the pipe sections, and only the condition that the numbers of the adjacent pipe sections are similar is met; then, the number of the abnormal values which are larger than the second preset threshold is judged, if only one abnormal value exists, the water service pipe network only has one burst pipe section, and at the moment, the operation and maintenance personnel only need to be dispatched to the pipe section; if there are multiple outliers that are all greater than the second predetermined threshold, further consideration is needed:
considering that the pipe sections are not independent but communicated with each other, the burst of one pipe section may cause the fluctuation of abnormal values of other adjacent pipe sections, so when a plurality of abnormal values meet the burst condition, it is necessary to judge whether the abnormal values belong to the adjacent fluctuation condition and discharge the abnormal values correspondingly.
In the above embodiment, because the numbers of the adjacent pipe segments are similar, according to the actual application situation, the operation and maintenance personnel sets a suitable third preset threshold, sorts the numbers of the pipe segments whose abnormal values meet the burst condition, and if the absolute value of the difference between two adjacent numbers is greater than the third preset threshold, it indicates that the two numbers do not belong to the adjacent fluctuation, at least two burst points exist in the pipe network, and accordingly, the number sequence of the pipe network is divided into a plurality of subsequences, and one corresponding pipe segment may exist in each subsequence or a plurality of corresponding pipe segments may exist in each subsequence; if a plurality of corresponding pipe sections exist, it is indicated that adjacent pipe sections are mistakenly brought into the sequence of the burst pipe section, and at the moment, each subsequence is only required to be output from large to small according to abnormal values, and operation and maintenance personnel carry out corresponding investigation according to corresponding alarm information.
In conclusion, according to the technical scheme, a calculation model is trained in advance according to mass historical data, the burst pipe section can be judged and predicted reasonably and efficiently according to monitoring data, and meanwhile, the situation of simultaneous multipoint burst is further optimized and judged, so that active prediction and technical early warning of pipeline burst are achieved. By adopting the technical scheme, the growth of the small leak can be prevented to the maximum extent, the management period and the labor consumption of leak detection are greatly shortened, and the method has high economic value.
While the invention has been described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention.
Claims (10)
1. A method for analyzing abnormity of a pipe network is applied to a water service pipe network and is characterized in that a plurality of monitoring terminals are arranged in the water service pipe network, and each monitoring terminal collects and outputs real-time pipe network data once every preset time interval;
the water service pipe network between every two adjacent monitoring terminals is marked as a pipe section;
the pipe network anomaly analysis method comprises the following steps:
step S1, according to the real-time pipe network data, continuously generating and outputting a real-time monitoring value corresponding to each monitoring terminal;
step S2, determining whether each of the real-time monitoring values is less than or equal to a first preset threshold:
if each real-time monitoring value is less than or equal to the first preset threshold value, returning to the step S2;
if any one of the real-time monitoring values is greater than the first preset threshold, recording the monitoring terminal corresponding to the real-time monitoring value greater than the first preset threshold as an abnormal point, and turning to step S3;
step S3, recording all the pipe sections containing the abnormal points as pipe sections to be analyzed, and acquiring the pipe section characteristics of all the pipe sections to be analyzed;
step S4, obtaining an abnormal value of each pipe section to be analyzed according to the characteristics of the pipe section and a calculation model obtained by pre-training, and judging whether each abnormal value is less than or equal to a second preset threshold value:
if each abnormal value is less than or equal to the second preset threshold, returning to the step S2;
if any one of the abnormal values is greater than the second preset threshold, the process goes to step S5;
and step S5, marking the pipe section corresponding to the abnormal value larger than the second preset threshold value as a burst pipe section and outputting the burst pipe section, and then returning to the step S2.
2. The pipe network anomaly analysis method according to claim 1, wherein the preset time is in a value range of [30ms, 50ms ].
3. The pipe network anomaly analysis method according to claim 1, wherein said real-time pipe network data comprises pressure values.
4. The pipe network anomaly analysis method according to claim 1, wherein said step S1 further comprises:
step S11, for each monitoring terminal, performing linear fitting according to the real-time pipe network data, and outputting the real-time trend curve corresponding to each monitoring terminal;
and step S12, calculating the slope value of the real-time trend curve every preset time according to the real-time trend curve and recording the slope value as the real-time monitoring value.
5. The pipe network anomaly analysis method according to claim 1, wherein a monitoring terminal at one end of the pipe section is marked as a first monitoring terminal, and a monitoring terminal at the other end of the pipe section is marked as a second monitoring terminal;
recording the time corresponding to the real-time monitoring value larger than the first preset threshold as an abnormal time;
the pipe section characteristics comprise all real-time pipe network data corresponding to the first monitoring terminal in a preset time period before and after the abnormal time, all real-time pipe network data corresponding to the second monitoring terminal in the preset time period before and after the abnormal time, the pipe length and the pipe diameter of the pipe section, and the water flow direction in the pipe section.
6. The pipe network anomaly analysis method according to claim 1, wherein said pipe segment characteristics include a plurality of characteristic quantities;
the calculation model comprises a plurality of weighting coefficients, each weighting coefficient corresponds to one characteristic quantity, and the abnormal value is obtained by weighting and adding the plurality of characteristic quantities.
7. The pipe network anomaly analysis method according to claim 1, wherein before step S1, a plurality of sets of historical pipe segment characteristic data are preset;
each group of historical pipe section characteristic data comprises a plurality of groups of pipe section characteristics, and each group of pipe section characteristics corresponds to one pipe section;
each set of historical pipe segment characteristic data includes the pipe segment characteristics of at least one burst pipe segment and the pipe segment characteristics of at least one non-burst pipe segment;
before the step S1, the method includes the following steps:
step A1, extracting a group of historical pipe section characteristic data in sequence, and respectively obtaining the abnormal value corresponding to each pipe section in the group of historical pipe section characteristic data according to the calculation model;
step A2, sorting the abnormal values in the order from high to low;
step A3, recording an interval composed of the minimum value of the abnormal value corresponding to the burst pipe section and the maximum value of the abnormal value corresponding to the non-burst pipe section as a critical interval;
step A4, repeating the steps A1 to A3 until a plurality of groups of historical pipe section characteristic data obtain a corresponding critical interval;
and A5, taking an intersection of all the critical intervals, recording the intersection as a critical value set of the pipe explosion, and outputting.
8. The pipe network anomaly analysis method according to claim 7, wherein said second preset threshold value belongs to said set of detonation threshold values.
9. The pipe network anomaly analysis method according to claim 1, wherein said pipe sections are numbered according to a preset rule;
the preset rules are that the numbers of the adjacent pipe sections are similar.
10. The pipe network anomaly analysis method according to claim 9, wherein said step S5 further comprises:
step S51, determining whether the number of abnormal values greater than the second preset threshold is equal to 1:
if so, recording the pipe section corresponding to the abnormal value as the burst pipe section and outputting the burst pipe section;
if not, go to step S52;
step S52, acquiring the numbers of the pipe sections corresponding to all the abnormal values, sequencing the numbers in the order from big to small, and outputting a number sequence;
step S53, determining whether the absolute values of the differences of the numbers in the number sequence are all less than or equal to a third preset threshold:
if the absolute values are all smaller than or equal to the third preset threshold value, recording the pipe section corresponding to the maximum value in the abnormal values as the burst pipe section and outputting the burst pipe section;
if any of the absolute values is greater than the third preset threshold, the process goes to step S54;
step S54, dividing the numbering sequence according to the two numbers corresponding to the absolute value to obtain at least two numbering subsequences;
step S55, outputting each of the numbered sub-sequences.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010033118.XA CN111210083A (en) | 2020-01-13 | 2020-01-13 | Pipe network abnormity analysis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010033118.XA CN111210083A (en) | 2020-01-13 | 2020-01-13 | Pipe network abnormity analysis method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111210083A true CN111210083A (en) | 2020-05-29 |
Family
ID=70785481
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010033118.XA Pending CN111210083A (en) | 2020-01-13 | 2020-01-13 | Pipe network abnormity analysis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111210083A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113239447A (en) * | 2021-06-11 | 2021-08-10 | 重庆电子工程职业学院 | Indoor pipeline abnormity detection system and method |
| CN113362200A (en) * | 2021-07-02 | 2021-09-07 | 上海天麦能源科技有限公司 | Anomaly detection method and system of space-time dimension combination |
| CN117370906A (en) * | 2023-08-21 | 2024-01-09 | 长江生态环保集团有限公司 | Tube explosion detection and performance evaluation method based on single-point and time sequence anomaly detection |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106960126A (en) * | 2017-03-28 | 2017-07-18 | 联想(北京)有限公司 | Data early warning method and equipment |
| CN107143750A (en) * | 2017-04-13 | 2017-09-08 | 浙江大学 | A kind of pipe burst monitors the space method for arranging of network |
| CN108167653A (en) * | 2017-12-23 | 2018-06-15 | 浙江大学 | Public supply mains booster detection method based on dynamic neural network prediction |
| CN108278491A (en) * | 2017-12-18 | 2018-07-13 | 苏州航天系统工程有限公司 | A kind of method and system finding drainage pipeline networks operation exception |
| CN108360608A (en) * | 2018-03-21 | 2018-08-03 | 浙江大学 | A kind of booster identification of water system water-supply-pipe and localization method |
| CN108730775A (en) * | 2018-05-25 | 2018-11-02 | 山东锋士信息技术有限公司 | A kind of tree pipe network method for analyzing cartridge igniter and device |
| CN108981803A (en) * | 2018-07-02 | 2018-12-11 | 宁波水表股份有限公司 | A kind of water utilities monitoring management system |
| CN109578816A (en) * | 2018-12-14 | 2019-04-05 | 中冶京诚工程技术有限公司 | Water supply network booster detection method and device, control method and device |
-
2020
- 2020-01-13 CN CN202010033118.XA patent/CN111210083A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106960126A (en) * | 2017-03-28 | 2017-07-18 | 联想(北京)有限公司 | Data early warning method and equipment |
| CN107143750A (en) * | 2017-04-13 | 2017-09-08 | 浙江大学 | A kind of pipe burst monitors the space method for arranging of network |
| CN108278491A (en) * | 2017-12-18 | 2018-07-13 | 苏州航天系统工程有限公司 | A kind of method and system finding drainage pipeline networks operation exception |
| CN108167653A (en) * | 2017-12-23 | 2018-06-15 | 浙江大学 | Public supply mains booster detection method based on dynamic neural network prediction |
| CN108360608A (en) * | 2018-03-21 | 2018-08-03 | 浙江大学 | A kind of booster identification of water system water-supply-pipe and localization method |
| CN108730775A (en) * | 2018-05-25 | 2018-11-02 | 山东锋士信息技术有限公司 | A kind of tree pipe network method for analyzing cartridge igniter and device |
| CN108981803A (en) * | 2018-07-02 | 2018-12-11 | 宁波水表股份有限公司 | A kind of water utilities monitoring management system |
| CN109578816A (en) * | 2018-12-14 | 2019-04-05 | 中冶京诚工程技术有限公司 | Water supply network booster detection method and device, control method and device |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113239447A (en) * | 2021-06-11 | 2021-08-10 | 重庆电子工程职业学院 | Indoor pipeline abnormity detection system and method |
| CN113239447B (en) * | 2021-06-11 | 2023-08-15 | 重庆电子工程职业学院 | Indoor pipeline abnormality detection system and method |
| CN113362200A (en) * | 2021-07-02 | 2021-09-07 | 上海天麦能源科技有限公司 | Anomaly detection method and system of space-time dimension combination |
| CN113362200B (en) * | 2021-07-02 | 2024-02-23 | 上海天麦能源科技有限公司 | Abnormality detection method and system for space-time dimension combination |
| CN117370906A (en) * | 2023-08-21 | 2024-01-09 | 长江生态环保集团有限公司 | Tube explosion detection and performance evaluation method based on single-point and time sequence anomaly detection |
| CN117370906B (en) * | 2023-08-21 | 2024-05-10 | 长江生态环保集团有限公司 | Tube explosion detection and performance evaluation method based on single-point and time sequence anomaly detection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111210083A (en) | Pipe network abnormity analysis method | |
| CN111260087A (en) | Management system for pipe network abnormity | |
| US8046180B2 (en) | Model-based determination of power source replacement in wireless and other devices | |
| US20230175652A1 (en) | Safety monitoring methods and internet of things systems of pipe network reliability degree based on intelligent gas | |
| US20230243132A1 (en) | Fluid delivery system | |
| US20150241304A1 (en) | Method for the computer-assisted monitoring of the operation of a technical system, particularly of an electrical energy-generating installation | |
| CN113341813B (en) | Urban gas medium-low pressure pipe network detection method and system | |
| CN111401582A (en) | Abnormity identification method and monitoring platform for domestic sewage treatment facility | |
| CN113962439A (en) | Cloud platform data management system based on industrial big data and construction method thereof | |
| CN116976557A (en) | Energy-saving and carbon-reducing park energy control method and system | |
| CN111522864B (en) | Enterprise production mode recognition and transfer production early warning method based on electricity consumption data | |
| CN113326585A (en) | Energy efficiency abnormity early warning method and device for gas-fired boiler and computer equipment | |
| CN111317953B (en) | Intelligent algorithm-based water pipe network water leakage monitoring method for fire fighting | |
| CN117057608A (en) | Enterprise safety production risk early warning system | |
| CN116488351A (en) | Low-voltage distribution box remote monitoring method and system based on Internet of things | |
| CN116187980A (en) | Visual intelligent management system for environmental protection equipment based on data transmission | |
| CN113324181B (en) | Intelligent air supply management method and system | |
| CN114969068A (en) | Method and system for analyzing real-time flow monitoring data of urban pressure pipe network | |
| CN112947611A (en) | Scheduling method and system based on pressure monitoring | |
| CN112432307A (en) | Water pump evaluation method and device, air conditioning system, storage medium and electronic equipment | |
| CN108092824B (en) | Control system diagnosis method based on complex dynamic network | |
| CN115425734B (en) | Operation and maintenance box with automatic energy-saving operation program | |
| US12008883B2 (en) | Alarm-based prevention and control method, internet of things system, and medium for safety risk of smart gas | |
| CN117150415B (en) | Communication equipment state monitoring method and system based on artificial intelligence | |
| US20230419811A1 (en) | Alarm-based prevention and control method, internet of things system, and medium for safety risk of smart gas |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200529 |