CN117649752B - Monitoring, early warning and disposing method, device, equipment and medium for water supply network - Google Patents
Monitoring, early warning and disposing method, device, equipment and medium for water supply network Download PDFInfo
- Publication number
- CN117649752B CN117649752B CN202410122212.0A CN202410122212A CN117649752B CN 117649752 B CN117649752 B CN 117649752B CN 202410122212 A CN202410122212 A CN 202410122212A CN 117649752 B CN117649752 B CN 117649752B
- Authority
- CN
- China
- Prior art keywords
- alarm
- instruction
- generating
- monitoring data
- monitoring
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 342
- 238000000034 method Methods 0.000 title claims abstract description 60
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 57
- 230000008859 change Effects 0.000 claims abstract description 112
- 230000000007 visual effect Effects 0.000 claims abstract description 48
- 238000002372 labelling Methods 0.000 claims abstract description 33
- 230000002159 abnormal effect Effects 0.000 claims description 98
- 238000011084 recovery Methods 0.000 claims description 82
- 238000004458 analytical method Methods 0.000 claims description 28
- 238000009825 accumulation Methods 0.000 claims description 25
- 238000004590 computer program Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 11
- 238000003860 storage Methods 0.000 claims description 8
- 238000012423 maintenance Methods 0.000 description 23
- 230000007246 mechanism Effects 0.000 description 21
- 230000005856 abnormality Effects 0.000 description 17
- 230000008569 process Effects 0.000 description 17
- 238000013461 design Methods 0.000 description 15
- 230000035772 mutation Effects 0.000 description 15
- 230000004044 response Effects 0.000 description 13
- 238000004140 cleaning Methods 0.000 description 9
- 238000010276 construction Methods 0.000 description 9
- 238000009826 distribution Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 9
- 238000007689 inspection Methods 0.000 description 9
- 238000007726 management method Methods 0.000 description 7
- 230000009286 beneficial effect Effects 0.000 description 5
- 230000035945 sensitivity Effects 0.000 description 5
- 238000001914 filtration Methods 0.000 description 4
- 238000013178 mathematical model Methods 0.000 description 4
- 239000002245 particle Substances 0.000 description 4
- ZAMOUSCENKQFHK-UHFFFAOYSA-N Chlorine atom Chemical compound [Cl] ZAMOUSCENKQFHK-UHFFFAOYSA-N 0.000 description 3
- 239000000460 chlorine Substances 0.000 description 3
- 229910052801 chlorine Inorganic materials 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000008520 organization Effects 0.000 description 3
- 230000001960 triggered effect Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 230000003111 delayed effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 241000192700 Cyanobacteria Species 0.000 description 1
- 206010063385 Intellectualisation Diseases 0.000 description 1
- PWHULOQIROXLJO-UHFFFAOYSA-N Manganese Chemical compound [Mn] PWHULOQIROXLJO-UHFFFAOYSA-N 0.000 description 1
- 230000004931 aggregating effect Effects 0.000 description 1
- XKMRRTOUMJRJIA-UHFFFAOYSA-N ammonia nh3 Chemical compound N.N XKMRRTOUMJRJIA-UHFFFAOYSA-N 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000009960 carding Methods 0.000 description 1
- 238000013070 change management Methods 0.000 description 1
- 229930002875 chlorophyll Natural products 0.000 description 1
- 235000019804 chlorophyll Nutrition 0.000 description 1
- ATNHDLDRLWWWCB-AENOIHSZSA-M chlorophyll a Chemical compound C1([C@@H](C(=O)OC)C(=O)C2=C3C)=C2N2C3=CC(C(CC)=C3C)=[N+]4C3=CC3=C(C=C)C(C)=C5N3[Mg-2]42[N+]2=C1[C@@H](CCC(=O)OC\C=C(/C)CCC[C@H](C)CCC[C@H](C)CCCC(C)C)[C@H](C)C2=C5 ATNHDLDRLWWWCB-AENOIHSZSA-M 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005474 detonation Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 229910052748 manganese Inorganic materials 0.000 description 1
- 239000011572 manganese Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 230000036632 reaction speed Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012384 transportation and delivery Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Landscapes
- Testing And Monitoring For Control Systems (AREA)
Abstract
The application relates to a monitoring and early-warning treatment method, a device, equipment and a medium of a water supply network, wherein the monitoring and early-warning treatment method of the water supply network comprises the steps of generating a visual layer based on a map service source and underground pipeline service; acquiring equipment data, and generating corresponding marking points on a visual layer; acquiring monitoring data, generating a confidence interval according to historical monitoring data of a first preset period day in the past, generating a corresponding intelligent alarm instruction, comparing and analyzing the monitoring data with a preset pressure data threshold value, generating a corresponding abrupt change alarm instruction, and generating a corresponding association alarm instruction according to the intelligent alarm instruction, the abrupt change alarm instruction and a maximum clustering distance to be used for converting the labeling state of a labeling point.
Description
Technical Field
The invention relates to the technical field of the Internet, in particular to a monitoring, early warning and disposing method, a device, equipment and a medium of a water supply network.
Background
With the expansion of urban scale and population growth, the complexity and scale of urban water supply network systems are also increasing. The traditional water supply network monitoring method mainly relies on manual inspection and periodic detection, has the problems of low monitoring frequency, low reaction speed, limited monitoring range and the like, and is difficult to meet the safe operation requirement of a modern urban water supply network system, and the research and the application of a few water supply network monitoring and early warning systems are available at home and abroad. The system comprises a monitoring center, a water supply network, a monitoring system and a control system, wherein the monitoring system adopts a sensor technology to monitor parameters such as pressure, flow, water quality and the like of the water supply network in real time, and transmits data to the monitoring center for analysis and processing;
however, although the systems can realize real-time monitoring and early warning of the running state of the water supply network, the early warning threshold value set by the systems is unreasonable, false alarm and missing alarm are easy to occur, for example, the threshold value setting is too sensitive, the system can frequently generate false alarm, normal fluctuation or noise is wrongly interpreted as abnormality, or the threshold value setting is too conservative, the system can miss real abnormal signals, and the discovery and processing of potential problems are delayed, so that a monitoring system which is difficult to generate false alarm and missing alarm is lacking.
Disclosure of Invention
In order to solve the problems that the prior monitoring system is easy to misreport and miss report because the early warning threshold value is unreasonable, the application provides a monitoring early warning treatment method, a device, equipment and a medium for a water supply network.
The first object of the present invention is achieved by the following technical solutions:
the monitoring, early-warning and disposing method of the water supply network comprises the following steps:
generating a visual layer based on the map service source and the underground pipeline service;
acquiring equipment data, and generating corresponding marking points on a visual layer;
acquiring monitoring data, and generating a confidence interval according to historical monitoring data of the first preset period days in the past;
comparing and analyzing the monitoring data with the confidence interval to generate a corresponding intelligent alarm instruction;
comparing and analyzing the monitoring data with a preset pressure data threshold value to generate a corresponding abrupt change alarm instruction;
and determining the maximum clustering distance for generating the associated alarm event, and generating a corresponding associated alarm instruction according to the intelligent alarm instruction, the abrupt change alarm instruction and the maximum clustering distance, wherein the intelligent alarm instruction, the abrupt change alarm instruction and the associated alarm instruction are all used for converting the labeling state of the labeling point.
By adopting the technical scheme, the method can dynamically adjust the threshold value and the monitoring strategy by generating the confidence interval based on the historical monitoring data and combining the intelligent alarm mechanism, the abrupt change alarm mechanism and the associated alarm mechanism, thereby effectively avoiding the problems of false alarm and false alarm caused by improper setting of the threshold value. The intelligent alarm mechanism can accurately analyze the monitoring data in the first preset period days according to the confidence interval generated by the historical data, so that erroneous judgment on normal fluctuation is avoided. The abrupt change alarm mechanism can timely respond to abrupt change conditions within a first threshold time, and the quick change of the false alarm conditions is prevented. The association alarm mechanism avoids the problem that global abnormality is ignored due to local abnormality by setting the maximum clustering distance, and effectively reduces the risks of false alarm and missing alarm. Comprehensively, the intelligent adjustment of the method in the aspect of early warning threshold setting obviously improves the accuracy of an alarm system, reduces the occurrence probability of false alarm and missing alarm, and further ensures the reliability of the safe operation of a pipe network.
The present application may be further configured in a preferred example to: the step of comparing and analyzing the monitoring data and the confidence interval and generating the corresponding intelligent alarm instruction comprises the following steps:
Judging whether the monitoring data exceeds a confidence interval, if so, executing an operation of adding one to a count value of an alarm count, executing an operation of increasing a weight level of a level accumulation sum, judging whether the alarm count is larger than or equal to an alarm frequency threshold value, and judging whether the level accumulation sum is larger than or equal to an alarm buffer zone, if not, generating an alarm delay instruction, if so, generating an intelligent alarm instruction, and executing an operation of restoring the count value assignment of the count to zero;
and judging whether the monitoring data exceeds a confidence interval, if not, executing the operation of adding one to the count value of the recovery count, judging whether the recovery count is larger than or equal to a recovery count threshold value, if not, generating a recovery delay instruction, if so, generating a recovery instruction, executing the operation of assigning zero to the count value of the alarm count and assigning zero to the weight level of the level accumulation sum, and generating an intelligent alarm record.
By adopting the technical scheme, the monitoring and early warning system successfully generates the confidence interval of the day by acquiring the real-time monitoring data and the historical monitoring data of the days of the past first preset period, thereby realizing the comprehensive analysis of the monitoring data. And when judging whether the monitored data exceeds the confidence interval, the system flexibly executes the operation of alarm counting and level accumulation, and accurately judges the weight level increment of the abnormal condition. By generating the intelligent alarm instruction, the system achieves timely response to the abnormality, and effectively filters smaller-amplitude fluctuation through the alarm delay instruction, so that the false alarm risk is reduced. When the monitoring data is recovered to be normal, the system executes a recovery instruction, clears the alarm count and the level accumulation sum, and ensures the timely recording of the normal state. The generation of the resume delay instruction further avoids false alarms caused by short-time fluctuations. Through the design, the system not only can accurately alarm under abnormal conditions, but also can effectively process the recovery condition of the normal state, and the accuracy and the stability of monitoring and early warning are improved.
The present application may be further configured in a preferred example to: the step of comparing and analyzing the monitoring data with a preset pressure data threshold value and generating a corresponding abrupt change alarm instruction comprises the following steps:
determining alarm delay time length, and acquiring a plurality of monitoring data sets containing two monitoring data with time intervals being the alarm delay time length;
judging whether the difference value of two monitoring data in all the monitoring data sets is larger than a preset pressure data threshold value, and if not, generating an alarm delay instruction;
if so, judging whether the distance between the monitoring data before the alarm delay time and the confidence interval center is greater than the distance between the monitoring data after the alarm delay time and the confidence interval center, and if not, generating an alarm delay instruction;
if yes, judging whether the monitoring data after the alarm delay time is greater than zero, if not, generating an alarm delay instruction, if yes, generating a sudden change alarm instruction, and recording the monitoring data before the alarm delay time;
determining a recovery delay time length, acquiring monitoring data in the recovery delay time length, judging whether the monitoring data in the recovery delay time length is all greater than the monitoring data before the alarm delay time length minus a preset pressure data threshold value, if not, generating a recovery delay instruction, if so, generating a recovery instruction, and generating a sudden change alarm record.
By adopting the technical scheme, the monitoring and early warning system successfully realizes accurate judgment of abnormal conditions and effective treatment of normal conditions by setting alarm delay and recovery delay time and acquiring the monitoring data set in the corresponding time interval. When judging whether to generate the alarm delay instruction, the system ensures that the alarm instruction is generated only when the monitoring data is changed substantially by analyzing the difference value of the monitoring data, and effectively reduces the false alarm risk. By comparing the distance between the monitoring data and the confidence interval center before and after the alarm delay time and the change trend of the monitoring data, the system further refines the alarm condition and avoids the sensitive response to the instantaneous fluctuation. When a mutation alarm instruction is generated, the system considers the directionality and trend of the monitoring data, and the abnormal situation is judged more comprehensively. When judging whether to generate a recovery instruction, the system successfully records and processes the normal recovery condition of the monitoring data by comparing the relative changes of the monitoring data. The design not only improves the sensitivity of the monitoring and early warning system to abnormal conditions, but also keeps the stability when the fluctuation in a normal state is processed, and comprehensively improves the accuracy and the stability of the system.
The present application may be further configured in a preferred example to: the step of determining the alarm delay time length and acquiring a plurality of monitoring data sets including two monitoring data with time intervals of the alarm delay time length includes:
judging whether a sudden change alarm record is generated on the second preset period days, if not, setting the alarm delay time to be 5 minutes;
if yes, generating an alarm duration average value according to the abrupt change alarm record, judging whether the alarm duration average value is smaller than 20 minutes, if yes, setting the alarm delay time to be 10 minutes, and if not, setting the alarm delay time to be 5 minutes;
based on the alarm delay time length, a plurality of monitoring data sets containing two monitoring data with time intervals being the alarm delay time length are obtained.
By adopting the technical scheme, when acquiring the data set containing the two monitoring data with the time interval being the alarm delay time length, the system flexibly adjusts the alarm delay time length by judging whether the abrupt change alarm record is generated on the second preset period days in the past. If no abrupt change alarm record is generated in the past period, the system sets a shorter alarm delay time to be 5 minutes so as to quickly respond to the abnormal condition. If abrupt change alarm records exist, the system generates an average value of alarm duration time according to the records and judges whether the average value is smaller than 20 minutes, so that the alarm delay time is intelligently set to be 10 minutes or 5 minutes. The design fully considers the history mutation situation, so that the system can sensitively and accurately adjust the alarm delay time under the abnormal situation, and the timely response and the intelligent regulation and control capability of the system to the abnormal situation are improved.
The present application may be further configured in a preferred example to: the determining of the maximum clustering distance for generating the associated alarm event, and generating a corresponding associated alarm instruction according to the intelligent alarm instruction, the abrupt change alarm instruction and the maximum clustering distance, wherein the intelligent alarm instruction, the abrupt change alarm instruction and the associated alarm instruction are all used for converting the labeling state of the labeling point location, and the steps comprise:
determining a maximum cluster distance for generating an associated alarm event;
determining abnormal monitoring points in a user selected area according to the intelligent alarm instruction and the abrupt change alarm instruction, and acquiring coordinate information of the abnormal monitoring points;
judging whether the distance between every two abnormal monitoring points is smaller than the maximum clustering distance according to the coordinate information, classifying the two abnormal monitoring points as the same associated alarm event if the distance between the two abnormal monitoring points is smaller than the maximum clustering distance, and pushing corresponding associated alarm state information in a visual image layer according to each associated alarm event in a user selection area;
judging whether the associated alarm state information at different moments is the same, if not, pushing the converted associated alarm state information, and generating a corresponding associated alarm instruction.
By adopting the technical scheme, through the comprehensive application of intelligent alarm and mutation alarm instructions, the system not only successfully locates abnormal monitoring points in the user selection area, but also merges adjacent abnormal monitoring points into the same event through distance judgment and clustering of associated alarm events, thereby realizing more visual and clearer abnormal state presentation. Associated alarm state information is pushed in time, and by combining a dynamic monitoring mechanism, the user is ensured to obtain accurate and real-time pipe network state information, and the practicability and the credibility of the user to the system are improved.
The present application may be further configured in a preferred example to: the determining of the maximum clustering distance for generating the associated alarm event, and generating a corresponding associated alarm instruction according to the intelligent alarm instruction, the abrupt change alarm instruction and the maximum clustering distance, wherein the intelligent alarm instruction, the abrupt change alarm instruction and the associated alarm instruction are all used for converting the labeling state of the labeling point location, and then the steps of:
determining an abnormal monitoring point, and acquiring alarm parameters of the abnormal monitoring point, wherein the alarm parameters comprise pressure drop conditions before closing a valve, flow change before closing the valve, a valve to be closed, a pipe section and a user influenced after closing the valve, and pressure drop conditions after closing the valve, and corresponding statistical data are generated according to the alarm parameters;
And drawing the affected valve, the affected pipe section, the affected user and the pressure change point positions on the visual layer according to the statistical data.
By adopting the technical scheme, the key information is clearly displayed on the visual layer, so that quick and comprehensive pipe network state change understanding is provided for operators, and quick and accurate decision support is provided for the operators in emergency. Through timely and clear information display, the system not only realizes quick response and control on abnormal conditions, but also comprehensively improves the emergency processing capability and the operation efficiency.
The second object of the present invention is achieved by the following technical solutions:
the monitoring, early-warning and disposing device of the water supply network comprises:
the first generation module is used for generating a visual layer based on the map service source and the underground pipeline service;
the second generation module is used for acquiring equipment data and generating corresponding marking points on the visual layer;
the third generation module is used for acquiring monitoring data and generating a confidence interval according to historical monitoring data of the first preset period days in the past;
the first comparison analysis module is used for comparing and analyzing the monitoring data and the confidence interval and generating a corresponding intelligent alarm instruction;
The second comparison analysis module is used for comparing and analyzing the monitoring data with a preset pressure data threshold value and generating a corresponding abrupt change alarm instruction;
and the fourth generation module is used for determining the maximum clustering distance for generating the associated alarm event, and generating a corresponding associated alarm instruction according to the intelligent alarm instruction, the abrupt change alarm instruction and the maximum clustering distance, wherein the intelligent alarm instruction, the abrupt change alarm instruction and the associated alarm instruction are all used for converting the labeling state of the labeling point.
The third object of the present application is achieved by the following technical solutions:
the computer equipment comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the processor realizes the steps of the monitoring, early warning and treating method of the water supply network when executing the computer program.
The fourth object of the present application is achieved by the following technical solutions:
a computer readable storage medium storing a computer program which when executed by a processor implements the steps of the monitoring and early warning treatment method of a water supply network described above.
In summary, the present application includes at least one of the following beneficial technical effects:
1. according to the system, through intelligent alarm and mutation alarm mechanisms, efficient and accurate abnormality identification and response are achieved in pipe network monitoring. The intelligent alarm mechanism is combined with the confidence interval generated by the historical data to accurately judge the abnormal state of the monitored data, so that the oversensitivity to short-time fluctuation is avoided, and the possibility of false alarm is remarkably reduced. The comprehensive technical optimization not only improves the monitoring accuracy, but also ensures the real-time response to the real abnormal condition, and comprehensively improves the reliability and practicability of the system in the aspect of monitoring the pipe network abnormality;
2. according to the method and the system, through the association alarm mechanism, the system successfully clusters adjacent abnormal monitoring points into the same association alarm event, and visual and clear map layer display is provided for operators. The visual display mode effectively simplifies complex abnormal information, so that operators can clearly know related abnormal conditions at a glance, and the operability and user experience of the system are greatly improved. The technical effect of the method is that the abnormality monitoring is more visual and understandable, and a more convenient and efficient pipe network state analysis and processing means is provided for users;
3. According to the method and the system, after the abnormal monitoring points are confirmed, the system can intelligently analyze related data, determine the valve to be closed, and clearly present the information such as the affected valve, the pipe section, the user and the pressure change. The system has the advantages that operators can quickly know the state change of the pipe network under the emergency condition, make quick and accurate decisions, and comprehensively improve the emergency treatment capacity and the operation efficiency of the system.
Drawings
Fig. 1 is a flow chart of a method for monitoring, pre-warning and disposing of a water supply network according to an embodiment of the present application.
FIG. 2 is a flowchart illustrating implementation of step S40 in a method for monitoring, pre-warning and disposing of a water supply network according to an embodiment of the present application;
FIG. 3 is another implementation flowchart of step S50 in a method for monitoring and pre-warning treatment of a water supply network according to another embodiment of the present application;
FIG. 4 is a flowchart of another implementation of step S501 in a method for monitoring, pre-warning and disposing of a water supply network according to an embodiment of the present application;
fig. 5 is a flowchart illustrating implementation of step S60 in a method for monitoring, pre-warning and disposing of a water supply network according to other embodiments of the present application;
FIG. 6 is a flow chart of another implementation of a method for monitoring, pre-warning and disposing of a water supply network in an embodiment of the present application;
FIG. 7 is a schematic block diagram of a monitoring, early warning and disposing device of a water supply network according to an embodiment of the present application;
Fig. 8 is a schematic view of an apparatus in an embodiment of the present application.
Detailed Description
The present application is described in further detail below with reference to the accompanying drawings.
In an embodiment, as shown in fig. 1, the application discloses a method for monitoring, early-warning and disposing of a water supply network, which specifically includes the following steps:
s10, generating a visual layer based on a map service source and underground pipeline service;
in this embodiment, the map service source provides support for geospatial data for the system, while the underground pipeline service provides rich information for the pipe network structure and the equipment data, and the system can display the multi-level data such as the geographic layout, the pipeline structure and the related equipment information of the pipe network on the map layer in a visual form. The method enables operators to intuitively know the spatial distribution and equipment layout of the pipe network, and provides visual and effective visual support for real-time monitoring, anomaly identification and pipe network maintenance.
Specifically, the relevant information of the device state is supplemented in the visual layer, wherein the relevant information comprises the distribution of the map where the device is located, and each device displays different color distinction according to the current state.
S20, acquiring equipment data, and generating corresponding marking points on the visual layer;
In this embodiment, after acquiring the device data, the system maps the data onto the visual layer to generate the corresponding labeling point positions. This process exposes the location information of the device on the map layer in the form of labels by associating the geographic coordinates of the device with the corresponding location on the map. The visual presentation enables operators to intuitively know the distribution condition of equipment in the pipe network, and visual and effective space information is provided for real-time monitoring, abnormality identification and pipe network maintenance.
Specifically, the device data refers to related information of each device in the pipe network, and the labeling point positions are geographic position marks generated according to the device data on the visual layer, wherein the corresponding device data, such as a device account function in a software platform, can be directly observed through a remote device management platform, and the device account is used for displaying all the device data. The fields include status, station code, station name, station classification, organization architecture, basic information (construction source, monitoring purpose, address, construction time, power supply mode, equipment model, coordinates, elevation, well depth, caliber, ground high level, manhole code), data information (data source, acquisition frequency, uploading frequency, communication mode, IP address, RTU brand, SIM card number), maintenance information (user, maintainer), and equipment ledger support the conditional query of organization, status, type, name, number, etc.
Preferably, the equipment account information further provides maintenance or new functions, the new equipment is divided into three steps, basic information (station name, station monitoring, organization structure, station number, administrative division, station type, monitoring purpose, user number, equipment manufacturer, water classification, virtual point, elevation, well depth, ground elevation, caliber, check code, rainfall site, coordinates, address, available state, importance, all elements, business office, sea-going canal, sequencing, construction source, construction time, brand, model), data information (data source, collection frequency, uploading frequency, stream address, ip, communication mode), operation and maintenance information (responsible person, power supply mode, contact person, user side, maintenance side) can be respectively input, in addition, the equipment maintenance record is used for checking the historical operation and maintenance record of a specific certain equipment, the state change management function can enable the state of each equipment to be one of normal, fault maintenance, planned maintenance and permanent 4 states, the state can be set through a manual mode, the single-off state can be completed through the functions of equipment management, equipment management and automatic equipment and the like, and the single-off-business state can be completed after the single-business maintenance module is changed and the equipment is changed. The maintenance dispatch automatically completes the dispatch function when the equipment alarms such as offline faults or unchanged data for a long time, and then performs equipment evaluation, so that 5 dimensions of the equipment, such as accuracy, operation and maintenance completion degree, equipment effective rate, equipment alarm and service life of the equipment, are used for scoring the equipment, and the conditions of each core index are counted according to months.
Preferably, the system also provides data restoration and data cleaning functions, and due to the problem of data accuracy of the Internet of things, manual restoration is required for some error data affecting the service. Therefore, the monitoring and early warning platform provides a data repairing function, a certain repairing algorithm can be selected for data in a certain time interval to carry out rapid data repairing, meanwhile, the original data is still reserved, an intelligent algorithm is provided for analyzing historical data, missing data and abnormal data can be found conveniently and rapidly, a rapid repairing scheme is provided, the monitoring and early warning platform comprises a time sequence model data cleaning algorithm, a period of continuous time data is input, the periodicity rule of the data is analyzed according to a time sequence model, then the data violating the periodicity rule is removed, and the missing data is filled with the counted regular data. The method is mainly suitable for data cleaning with periodicity rules, such as flow data, pressure data and the like, or a moving average data cleaning algorithm, namely, data input for a period of continuous time, firstly, extremely abnormal data are cleaned according to a normal distribution algorithm, and then, data missing time is filled according to the running states of the data before and after the data missing time by using a moving average method. The method is mainly suitable for cleaning data without periodicity or with weak periodicity, such as water quality data, pump running state data and the like, and also comprises a historical same period data average cleaning algorithm, namely, selecting historical data similar to the time to be cleaned, such as data of a working day or holiday or the same weather condition, taking an average value according to time sequence, and then filling missing data of the time to be cleaned. The method is mainly suitable for data cleaning at a time with a periodicity rule but a special running state, and finally a cubic spline difference value data cleaning algorithm is also provided, namely data of a continuous time is input, firstly extremely abnormal data is cleaned according to a normal distribution algorithm, and then cubic spline interpolation is carried out on the data missing time. The method is mainly suitable for data cleaning of short-time data missing samples.
Furthermore, the method and the device can also make a plan for inspection and maintenance to form a work order, namely making the plan for inspection and maintenance, and generating a specific work order according to the set period and time after making the plan, wherein the steps are as follows: newly-built plan: the remote transmission equipment manager can define different periodic service schemes according to different equipment types and different monitoring points, wherein the schemes comprise a patrol range, patrol frequency, patrol period and service type. The inspection business types are inspection, maintenance and checking according to the operation and maintenance requirements of the equipment; planning dispatch: after the inspection task is defined, the system automatically generates a corresponding inspection, maintenance and check task list according to the period; work order management: all work orders associated with the equipment are displayed, including maintenance, inspection and maintenance work orders for the equipment. And displaying the execution flow of each work order; device overview: and displaying the key data of the KPI of the equipment. The equipment key indexes are used for counting the quantity, state, type, integrity rate, data accuracy rate, maintenance time rate, inspection completion rate, maintenance completion rate, work order completion rate, check completion rate and the like of the equipment and the operation and maintenance indexes.
S30, acquiring monitoring data, and generating a confidence interval according to historical monitoring data of the first preset period days in the past;
In this embodiment, the process determines the trusted range of the monitored data by analyzing the distribution characteristics of the historical monitored data, thereby forming the expected range of the current day monitored data, and further being used for subsequent anomaly identification and intelligent alarm mechanisms. The method can help the system to judge whether the monitoring data deviate from the normal range or not more accurately, and improves the accuracy of pipe network monitoring.
Specifically, according to historical data of past 30 days of the monitoring points, a confidence interval of all days is calculated, updated once a day and stored, and 30 days is the first preset period.
S40, comparing and analyzing the monitoring data with the confidence interval to generate a corresponding intelligent alarm instruction;
s50, comparing and analyzing the monitoring data with a preset pressure data threshold value to generate a corresponding abrupt change alarm instruction;
s60, generating corresponding association alarm instructions according to the intelligent alarm instructions, the mutation alarm instructions and the maximum clustering distance, wherein the intelligent alarm instructions, the mutation alarm instructions and the association alarm instructions can be used for converting the labeling states of labeling points.
In this embodiment, the system implements multi-level anomaly identification and processing by acquiring the monitoring data and applying the confidence interval generated by the history data. The intelligent alarm instruction accurately judges whether the monitored data is abnormal or not by utilizing confidence interval comparison, and the sudden change alarm instruction accurately identifies the short-time pressure sudden change through comparison analysis of the monitored data and a preset pressure data threshold value. And the associated alarm instruction is used for aggregating adjacent abnormal monitoring points into associated events based on the maximum clustering distance. The comprehensive design enables the system to comprehensively and accurately identify and respond to pipe network anomalies of different types, and provides multi-dimensional and multi-layer pipe network monitoring and processing guidance for operators, so that the intellectualization and practicability of the monitoring system are improved.
Specifically, the monitoring data refers to real-time monitoring values obtained from pipe network equipment; the first preset period is a time period of monitoring data history record preset by the system; the historical monitoring data is a monitoring data record in a certain time range; the confidence interval is defined by a credible range of monitoring data generated by historical monitoring data, and the first threshold time is a time threshold set by a system and used for triggering intelligent alarm in the time; the preset pressure data threshold value is a threshold value of an abnormal pressure value of monitoring data, which is preset by the system, the maximum clustering distance is a maximum distance limit which is set by the system and used for clustering adjacent abnormal monitoring points into related events, and the labeling state is a visual mark used for marking the abnormal state of the monitoring points on the visual layer.
More specifically, by generating a confidence interval based on historical monitoring data and combining an intelligent alarm mechanism, a sudden change alarm mechanism and an associated alarm mechanism, the method can dynamically adjust the threshold value and the monitoring strategy, and effectively avoids the problems of false alarm and false alarm caused by improper threshold value setting. The intelligent alarm mechanism can accurately analyze the monitoring data in the first preset period days according to the confidence interval generated by the historical data, so that erroneous judgment on normal fluctuation is avoided. The abrupt change alarm mechanism can timely respond to abrupt change conditions within a first threshold time, and the quick change of the false alarm conditions is prevented. The association alarm mechanism avoids the problem that global abnormality is ignored due to local abnormality by setting the maximum clustering distance, and effectively reduces the risks of false alarm and missing alarm. Comprehensively, the intelligent adjustment of the method in the aspect of early warning threshold setting obviously improves the accuracy of an alarm system, reduces the occurrence probability of false alarm and missing alarm, and further ensures the reliability of the safe operation of a pipe network.
In one embodiment, as shown in fig. 2, in step S40, that is, comparing and analyzing the monitored data and the confidence interval, the step of generating the corresponding intelligent alarm instruction includes:
s401, judging whether the monitored data exceeds a confidence interval, if so, executing the operation of adding one to the count value of the alarm count, executing the operation of increasing the weight level of the level accumulation sum, judging whether the alarm count is greater than or equal to an alarm frequency threshold value and whether the level accumulation sum is greater than or equal to an alarm buffer zone, if not, generating an alarm delay instruction, if so, generating an intelligent alarm instruction and executing the operation of restoring the count value assignment of zero;
in this embodiment, when the monitored data exceeds the confidence interval, the system performs the weight level increment operation of the increment sum of the alarm count and the level accumulation sum, and determines whether the alarm triggering condition is reached. If the alarm count exceeds the set alarm frequency threshold value and the level accumulation sum is greater than or equal to the alarm buffer zone, the system generates an intelligent alarm instruction, and accurately identifies and responds to the abnormal condition. On the basis, the system also realizes the generation of an alarm delay instruction, effectively filters short-time anomalies, and ensures the accuracy of alarm and the stability of the system. The intelligent alarm mechanism is beneficial to timely and accurately judging and processing the abnormal event by the system.
Specifically, the alarm count is a counter that records the number of times the monitored data exceeds the confidence interval; the level accumulation sum is a value for carrying out weight increment accumulation on the alarm event level; the alarm frequency threshold value is a counting threshold value for triggering alarm; the alarm buffer zone is a buffer zone threshold value for setting the level accumulation sum triggering the alarm; the alarm delay instruction is a delay instruction generated after the alarm condition is triggered and is used for filtering short-time abnormality, wherein the operation of performing the assignment of zero to the count value of the recovery count is to refresh the value of the recovery times of not alarming for recovering the normal state when judging the next moment, for example, when the monitoring data does not exceed the confidence interval at each moment, the state of judging whether to recover the normal state and not alarming is entered, at this moment, the recovery count is also to be subjected to the operation of increasing 1, but the value of the recovery count is refreshed as long as the alarm is generated, so that the state of judging whether to recover the normal state and not alarming is more reasonable.
And S402, judging whether the monitored data exceeds a confidence interval, if not, executing the operation of adding one to the count value of the recovery count, judging whether the recovery count is larger than or equal to the recovery count threshold value, if not, generating a recovery delay instruction, if so, generating a recovery instruction, executing the operation of assigning zero to the count value of the alarm count and assigning zero to the weight level of the level accumulation sum, and generating an intelligent alarm record.
In this embodiment, the system performs an increment operation of the recovery count when the monitored data is restored to the normal state, and determines whether the recovery count threshold is reached. If the threshold is not reached, a resume delay instruction is generated for filtering short term fluctuations. Once the recovery count exceeds the set threshold, the system will generate a recovery instruction, perform the alarm count clearing and level accumulation and weight level clearing operations, and generate an intelligent alarm record. The intelligent alarm mechanism effectively reduces false alarm caused by instantaneous fluctuation, ensures the stability and accuracy of the system, and simultaneously provides detailed intelligent alarm record, thereby facilitating subsequent analysis and improvement.
Specifically, the recovery count is a counter that records the recovery normal state of the monitoring data; the recovery count threshold is a count threshold that sets a trigger recovery operation; the recovery delay instruction is a delay instruction generated in the process of monitoring data recovery and is used for filtering short-time fluctuation; the recovery instruction is an instruction generated when the monitored data completely recovers to normal, and the recovery instruction executes zero clearing operation and generates intelligent alarm records; the intelligent alarm record is the detailed information of the intelligent alarm event recorded by the system, so that the subsequent analysis and improvement are convenient.
Preferably, the confidence interval of the whole day is calculated according to the historical data of the past 30 days of the monitoring point, updated once a day and stored, then the real-time uploading data is compared with the upper limit and the lower limit of the confidence interval of the corresponding time point, if obvious abnormality occurs at a plurality of continuous moments, an alarm is triggered to generate an alarm event until the monitoring data is restored to the confidence interval, the alarm is ended, namely whether the abnormality occurs is judged for the monitoring data uploaded in real time, after the monitoring data exceeds the confidence interval, whether the alarm is needed is judged, and an alarm event is generated only after the monitoring data exceeds the confidence interval obviously and lasts for a period of time, so that the false alarm is reduced. The algorithm filters out short-time overrun alarms or alarms exceeding the limit value but with unobvious amplitude by setting the alarm delay times and the alarm buffer area, and prevents the early recovery of the alarms caused by jump data by setting the recovery delay times.
More specifically, the monitoring and early warning system successfully generates the confidence interval of the day by acquiring real-time monitoring data and historical monitoring data of the days of the first preset period in the past, so that comprehensive analysis of the monitoring data is realized. And when judging whether the monitored data exceeds the confidence interval, the system flexibly executes the operation of alarm counting and level accumulation, and accurately judges the weight level increment of the abnormal condition. By generating the intelligent alarm instruction, the system achieves timely response to the abnormality, and effectively filters smaller-amplitude fluctuation through the alarm delay instruction, so that the false alarm risk is reduced. When the monitoring data is recovered to be normal, the system executes a recovery instruction, clears the alarm count and the level accumulation sum, and ensures the timely recording of the normal state. The generation of the resume delay instruction further avoids false alarms caused by short-time fluctuations. Through the design, the system not only can accurately alarm under abnormal conditions, but also can effectively process the recovery condition of the normal state, and the accuracy and the stability of monitoring and early warning are improved.
In one embodiment, as shown in fig. 3, in step S50, that is, comparing the analysis monitoring data with the preset pressure data threshold, the step of generating the corresponding abrupt change alarm instruction includes:
s501, determining alarm delay time length, and acquiring a plurality of monitoring data sets containing two monitoring data with time intervals being the alarm delay time length;
in this embodiment, by determining the alarm delay time length, the system acquires a monitoring data set including two monitoring data whose time interval is the alarm delay time length. The design is beneficial to the system to select proper monitoring data before the alarm is triggered so as to perform more accurate analysis and judgment, improves the filtering effect of the system on short-time abnormality, and effectively reduces the false alarm condition caused by instantaneous fluctuation, thereby improving the accuracy and stability of the alarm.
Specifically, the alarm delay time is a set time period for delaying alarm triggering; the monitoring data set is a data set containing two monitoring data with a time interval being an alarm delay time length, for example, the alarm delay time length is set to be t, namely, the monitoring data required to be acquired at the current moment is A1, the monitoring data before t minutes is A2, the A1 and the A2 are the same monitoring data set, in addition, the monitoring data B1 at the next moment is acquired, the monitoring data before t minutes at the next moment is B2, at the moment, the B1 and the B2 are the same monitoring data set, and the like, so as to acquire a plurality of monitoring data sets.
S502, judging whether the difference value of two monitoring data in all monitoring data sets is larger than a preset pressure data threshold value, and if not, generating an alarm delay instruction;
in this embodiment, the system determines the difference between two monitoring data in all the monitoring data sets, and if the difference is not greater than a preset pressure data threshold, that is, 0.05MPa, generates an alarm delay instruction. The step is helpful for the system to carry out sensitive judgment on the change of the monitoring data, short-time small fluctuation is effectively filtered, false alarm caused by instantaneous fluctuation is reduced, and the accuracy and stability of alarm are improved.
S503, if so, judging whether the distance between the monitoring data before the alarm delay time and the confidence interval center is greater than the distance between the monitoring data after the alarm delay time and the confidence interval center, and if not, generating an alarm delay instruction;
in this embodiment, the system further determines, when the difference is greater than 0.05MPa, whether the distance between the monitored data before the alarm delay time and the center of the confidence interval is greater than the distance between the monitored data after the alarm delay time and the center of the confidence interval. If this condition is not met, an alarm delay instruction is generated. The design effectively avoids short-time false alarm caused by instantaneous fluctuation, improves the reliability and accuracy of alarm, ensures the sensitivity of the system to pipe network state change and has enough robustness.
Specifically, the distance of the confidence interval center refers to the distance between the monitoring data and the center value of the confidence interval. In a monitoring system, a confidence interval is a range that measures the fluctuation of monitored data, and a center value represents the center position of the range. Therefore, the distance between the monitoring data and the confidence interval center before and after the alarm delay time is judged, and the distance can be used for evaluating the deviation degree of the monitoring data relative to the normal range, so that whether an alarm delay instruction needs to be generated or not is judged more accurately.
S504, if yes, judging whether the monitoring data after the alarm delay time is greater than zero, if not, generating an alarm delay instruction, if yes, generating a sudden change alarm instruction, and recording the monitoring data before the alarm delay time;
in this embodiment, the purpose of judging whether the monitored data after the alarm delay period is greater than zero is to further confirm the trend of the monitored data. In the system design, there may be a sudden change, that is, the monitored data fluctuates greatly in a short time, and this fluctuation may be caused by a device fault, an abnormal event or other reasons, and if the monitored data after the alarm delay period is greater than zero, it indicates that the monitored data still has an upward trend in the alarm delay period, which may be an indication of a sudden change. Therefore, the generation of the abrupt change alarm instruction and the recording of the monitoring data before the alarm delay time are beneficial to the timely response and recording of the system to the abnormal event, and the sensitivity and the accuracy of the system are improved.
S505, determining a recovery delay time length, acquiring monitoring data in the recovery delay time length, judging whether the monitoring data in the recovery delay time length is all greater than the monitoring data before the alarm delay time length minus a preset pressure data threshold value, if not, generating a recovery delay instruction, if so, generating a recovery instruction, and generating a sudden change alarm record.
In this embodiment, the response of the system to the abnormal state is effectively delayed to prevent false alarms caused by short-time fluctuations. By continuing to monitor the data for the recovery delay period, the system ensures that the monitoring state is stable during the recovery period, thereby more accurately determining whether a recovery instruction needs to be generated. Meanwhile, the generation of the mutation alarm record is beneficial to the system record and analysis of mutation events, and data support is provided for subsequent pipe network health analysis.
More specifically, the monitoring and early warning system successfully realizes accurate judgment of abnormal conditions and effective treatment of normal conditions by setting alarm delay and recovery delay time length and acquiring monitoring data sets in corresponding time intervals. When judging whether to generate the alarm delay instruction, the system ensures that the alarm instruction is generated only when the monitoring data is changed substantially by analyzing the difference value of the monitoring data, and effectively reduces the false alarm risk. By comparing the distance between the monitoring data and the confidence interval center before and after the alarm delay time and the change trend of the monitoring data, the system further refines the alarm condition and avoids the sensitive response to the instantaneous fluctuation. When a mutation alarm instruction is generated, the system considers the directionality and trend of the monitoring data, and the abnormal situation is judged more comprehensively. When judging whether to generate a recovery instruction, the system successfully records and processes the normal recovery condition of the monitoring data by comparing the relative changes of the monitoring data. The design not only improves the sensitivity of the monitoring and early warning system to abnormal conditions, but also keeps the stability when the fluctuation in a normal state is processed, and comprehensively improves the accuracy and the stability of the system.
In one embodiment, as shown in fig. 4, in step S501, that is, determining an alarm delay time, the step of obtaining a plurality of monitoring data sets including two monitoring data with a time interval being the alarm delay time includes:
s5011, judging whether a sudden change alarm record is generated on the second preset period days, if not, setting the alarm delay time to be 5 minutes;
in this embodiment, the alarm delay time is dynamically adjusted according to the history abrupt change alarm condition so as to adapt to the change of the pipe network operation state. If no abrupt warning occurs within the past cycle days, the system selects a relatively short warning delay period to increase the sensitivity of the system to abnormal conditions and quickly respond to potential abnormal events.
Specifically, the number of days of the second preset period refers to a time period preset in the design, and may be a number of days for reviewing past monitoring data and analyzing. The specific period days are determined according to the system design and the requirement, and can be 30 days, 60 days and the like; the abrupt change alarm record refers to the condition that the system analyzes the pressure monitoring data in the period of monitoring the past period days and records the event of abrupt change. This record includes information about the instant, magnitude, duration, etc. of the abrupt change.
S5012, if yes, generating an average value of the alarm duration according to the abrupt change alarm record, judging whether the average value of the alarm duration is smaller than 20 minutes, if yes, setting the alarm delay time to be 10 minutes, and if not, setting the alarm delay time to be 5 minutes.
In this embodiment, the purpose of the average is to comprehensively consider the duration of multiple alarm events in the past abrupt change alarm records, thereby obtaining a more comprehensive and smooth metric value. By calculating the average value, the system can better know the overall trend of the abrupt change alarm, avoid excessively depending on the extreme value of a specific event and improve the grasp of the network state change of the pipe.
More specifically, when acquiring a data set including two monitoring data having a time interval of an alarm delay period, the system flexibly adjusts the alarm delay period by determining whether a sudden change alarm record is generated on the past second preset cycle days. If no abrupt change alarm record is generated in the past period, the system sets a shorter alarm delay time to be 5 minutes so as to quickly respond to the abnormal condition. If abrupt change alarm records exist, the system generates an average value of alarm duration time according to the records and judges whether the average value is smaller than 20 minutes, so that the alarm delay time is intelligently set to be 10 minutes or 5 minutes. The design fully considers the history mutation situation, so that the system can sensitively and accurately adjust the alarm delay time under the abnormal situation, and the timely response and the intelligent regulation and control capability of the system to the abnormal situation are improved.
S5013, based on the alarm delay time, acquiring a plurality of monitoring data sets containing two monitoring data with time intervals being the alarm delay time.
In one embodiment, as shown in fig. 5, in step S60, that is, determining the maximum clustering distance for generating the associated alarm event, generating the corresponding associated alarm instruction according to the intelligent alarm instruction and the abrupt change alarm instruction and the maximum clustering distance, where the intelligent alarm instruction, the abrupt change alarm instruction and the associated alarm instruction are all used for converting the labeling state of the labeling point, the method includes:
s601, determining a maximum clustering distance for generating an associated alarm event;
s602, determining abnormal monitoring points in a user selected area according to the intelligent alarm instruction and the abrupt change alarm instruction, and acquiring coordinate information of the abnormal monitoring points;
in this embodiment, the system determines an abnormal monitoring point in the user-selected area according to the intelligent warning instruction and the abrupt change warning instruction. The system then obtains coordinate information of these abnormal monitoring points to accurately identify the locations of these points on the map. According to the design, the alarm is related to a specific monitoring point and the coordinate information of the specific monitoring point is acquired, so that an operator can intuitively know the occurrence position of an abnormal event, and the visualization and operability of the system are improved.
Specifically, the user selection area refers to that a user can select a specific area for monitoring, and the area may include a plurality of monitoring points, and an abnormal monitoring point is usually a monitoring device or a sensor point with abnormal data, and coordinate information may include position information such as longitude and latitude, so as to accurately locate the position of each monitoring point on a map.
S603, judging whether the distance between every two abnormal monitoring points is smaller than the maximum clustering distance according to the coordinate information, if so, classifying the two abnormal monitoring points into the same associated alarm event, and pushing corresponding associated alarm state information in a visual image layer according to each associated alarm event in a user selection area;
in this embodiment, the system determines whether or not they are sufficiently close by comparing the distance between every two abnormal monitoring points with the set maximum clustering distance. If the distance between two abnormal monitoring points is smaller than the maximum clustering distance, the system classifies the abnormal monitoring points as the same associated alarm event. This associated alarm event may be understood as a single alarm event that is commonly initiated by a plurality of adjacent abnormal monitoring points within a user selected area. The system then pushes associated alarm state information corresponding to each associated alarm event within the user-selected area on the visualization layer. This design enables the system to present associated alarm events for multiple adjacent monitoring points in an intuitive manner, helping operators to better understand anomalies.
S604, judging whether the associated alarm state information at different moments is the same, if not, pushing the converted associated alarm state information, and generating a corresponding associated alarm instruction.
In this embodiment, the system compares the associated alarm state information at different times and if they are found to be different, it is indicated that the associated alarm event has changed at different points in time. In this case, the system pushes updated associated alarm state information and generates a corresponding associated alarm instruction. This step aims at informing the operator in time about the change of the status of the associated alarm event so that they can take corresponding measures.
Specifically, the associated alarm state information refers to a state description related to an associated alarm event within the user-selected area. Such information may include the time of occurrence of the associated alarm event, the abnormal monitoring point involved in the event, the current state of the event, e.g., whether the event is in an alarm state, a processed state, etc., e.g., the user selected area includes five monitoring points, a, b, c, d, e altogether, where the alarm state is a non-0 value of 1,2, etc., the non-alarm state is 0, in one embodiment the initial state is displayed as {0,1, 0}, the next time the state is displayed as {0,0,1,1,2}, then c, d is said to be classified as alarm event 1 based on the minimum cluster distance, while e generates new alarm event 2, but because the minimum cluster distance is too far, c, d, e cannot be consolidated as new alarm event 1, in another embodiment, the initial state is shown as {0,0,1,1,2}, the next time the state is shown as {0, 1}, then it is stated that b between c, d and e is because an alarm event also occurs, and because the minimum cluster distance between c, d and b merges the three into the same alarm event, and because the minimum cluster distance between b and e, again causes b, c, d, e are all combined into the same alarm event 1, in other embodiments, the initial state is {0, 1}, the next time the state is {0, 0}, which means that the alarm events of b, c, d, e are all solved and become the corresponding non-alarm state 0, wherein the monitoring points contained in the alarm event can only be increased but not decreased. I.e., if one monitoring point in the event is restored, but the alarms of other monitoring points are not restored, the monitoring point is not removed from the alarm event. The alarm event is not ended until all monitoring points in the alarm event have been restored.
More specifically, through the comprehensive application of intelligent alarm and mutation alarm instructions, the system not only successfully locates abnormal monitoring points in a user selected area, but also merges adjacent abnormal monitoring points into the same event through distance judgment and clustering of associated alarm events, thereby realizing more visual and clearer abnormal state presentation. Associated alarm state information is pushed in time, and by combining a dynamic monitoring mechanism, the user is ensured to obtain accurate and real-time pipe network state information, and the practicability and the credibility of the user to the system are improved.
Furthermore, besides the situation that the intelligent alarm algorithm library is constructed to eliminate the strain false alarm and the false alarm, basic alarm rule construction is also indispensable, and in a monitoring system, the alarm rule construction is based on predefined rules and thresholds, so that the method is applicable to static and common situations. The intelligent alarm algorithm library processes complex and dynamic system behaviors by means of advanced data analysis and machine learning technologies, and accuracy and adaptability are improved. The common abnormal situation and the complex unknown situation can be effectively processed by comprehensively using the two, and the comprehensiveness and the instantaneity of the monitoring system are improved;
therefore, the mathematical model of the whole-flow water quality association alarm establishes association and time difference relation for delivery, pipe network and two water supply particles, and turbidity alarm rules are as follows: after residual chlorine and pH are used, when 1 water particle is over-limited, yellow alarm is given; when the time difference range of 2 associated water particles exceeds the limit, orange alarm is given; when the time difference range of 3 associated water particles exceeds the limit, red alarm is given;
The mathematical model of factory water quality alarm of the water factory is yellow alarm when turbidity is ultra-low limit (0.2 NTU, other 0.3NTU of the advanced treatment process water factory); red alarm when the limit is ultra-high (advanced treatment process water factory: 0.3NTU, other 0.5 NTU); yellow alarm when residual chlorine exceeds limit (advanced treatment process water plant: free residual chlorine <0.5 or >1.0, other water plants <0.4 or > 1.0); yellow alarm when pH exceeds limit (advanced treatment process water factory: <7.2 or >8.5, other <7.0 or > 8.0);
the raw water quality alarm rule is yellow alarm when turbidity is ultra-low (40 NTU); red alarm at the ultra-high limit (80 NTU); yellow alarm is given when ammonia nitrogen is at an ultra-low limit (0.1 mg/L); red alarm when the limit is ultra-high (0.3 mg/L); yellow alarm when the conductivity exceeds the limit; yellow alarm when chlorophyll is at ultra-low limit (20 ug/L); red alarm at the ultra-high limit (30 ug/L); red alarm when CODMn exceeds the limit; yellow alarm when the dissolved oxygen is at the ultra-low limit (6); red alarm when the limit is ultrahigh (5); yellow alarm when the pH exceeds the limit; yellow alarm when manganese exceeds the limit; red alarm when blue-green algae exceeds the limit;
the mathematical model of the pipe network pressure correlation alarm is the maximum and minimum value 15 days before rejection, and a pressure alarm band is set. Namely, when 1 pipe network pressure point exceeds the low limit, alarming to be yellow; when the 2 pipe network associated pressure points exceed the low limit, the alarm is orange; when 3 or more pipe network associated pressure points exceed the low limit, alarming to be red;
The mathematical model of the factory pressure alarm is based on the factory pressure zone to set a pressure alarm zone. When the instantaneous pressure drop of the factory pressure exceeds 2 meters, the flow rate is increased by more than 5%, and the alarm is orange when the flow rate exceeds the low limit; when the instantaneous pressure drop of the factory pressure exceeds 3 meters, the flow rate is increased by more than 15 percent, and the alarm is red when the flow rate exceeds the low limit; when the alarms are generated simultaneously, the system can be combined into one alarm event.
The mechanism model of the pressure and flow coupling analysis alarm is based on a real-time online water supply hydraulic model to develop flow and pressure simulation error alarm, the real-time error distribution of each monitoring point is analyzed, and the position of the detonation tube is pre-judged according to the error condition. Namely, when the error of 1 pipe network pressure point suddenly changes by 1 meter, yellow is reported; when the error of the 2 pipe network associated pressure points suddenly changes by 1 meter, the alarm is orange; and when the error of the pressure points associated with 3 or more pipe networks suddenly changes by 1 meter, the color is red.
In one embodiment, as shown in fig. 6, after step S30, that is, after determining the maximum clustering distance for generating the associated alarm event, generating the corresponding associated alarm instruction according to the intelligent alarm instruction and the abrupt change alarm instruction and the maximum clustering distance, the steps of using the intelligent alarm instruction, the abrupt change alarm instruction and the associated alarm instruction to change the labeling state of the labeling point position include:
S70, determining an abnormal monitoring point, acquiring alarm parameters of the abnormal monitoring point, wherein the alarm parameters comprise pressure drop conditions before closing the valve, flow change before closing the valve, a valve to be closed, a pipe section and a user influenced after closing the valve, and pressure drop conditions after closing the valve, and generating corresponding statistical data according to the alarm parameters;
in this embodiment, after the system determines the abnormal monitoring point, comprehensive analysis is performed by acquiring data such as pressure drop condition and flow change before closing the valve. Based on this data, the system determines the valve that needs to be closed and evaluates the impact on the pipe section and the user after closing the valve, while calculating the pressure drop after closing the valve. The process generates detailed statistical data, provides comprehensive and accurate pipe network state change information for operators, and enables the operators to quickly formulate proper management and control measures. The design not only enables operators to quickly and comprehensively know the change of the pipe network state, but also provides quick and accurate decision support for the operators.
And S80, drawing affected valves, affected pipe sections, affected users and pressure change points on the visual layer according to the statistical data.
In the embodiment, the system realizes visual display of the pipeline network by pushing the detailed information of the affected valve, the pipeline section and the user and the pressure change position on the visual image layer according to the information generated by the statistical data. Operators can quickly and comprehensively know the abnormal conditions in the pipe network, including affected equipment, pipe sections and users and related pressure change positions, so that the speed and accuracy of emergency response are improved, and the efficiency of monitoring and managing the pipe network is comprehensively improved.
Specifically, assuming an abnormal monitoring point in the water supply network, a sudden increase in pressure drop is detected, and the system finds that this is due to an abnormality of a certain valve according to statistical data analysis. The system can push specific information of the valve on the visual image layer, including the position of the valve, pressure drop change before and after closing the valve, affected pipe sections, users and the like. Operators can quickly know the root cause of the problem through the information, and are helped to quickly take corresponding measures to repair, so that the emergency treatment efficiency is improved.
More specifically, the key information is clearly presented on the visual layer, so that the operator is provided with quick and comprehensive pipe network state change knowledge, and quick and accurate decision support is provided for the operator in emergency situations. Through timely and clear information display, the system not only realizes quick response and control on abnormal conditions, but also comprehensively improves the emergency processing capability and the operation efficiency.
Furthermore, after risk determination, alarm closed-loop treatment management is performed, namely, in order to promote construction of a group operation plate safety risk monitoring and early warning system, surrounding production and pipe network business risk monitoring and early warning application scenes, comprehensive carding of risk source management, event monitoring, risk pre-alarm and risk treatment system construction requirements of each scene are performed, and operation safety risk monitoring and early warning command system construction work is pushed to be divided into the following steps:
The alarm marking state, namely, when a site alarms, the state of the equipment information ledger can be automatically updated under the alarm state and under an alarm dispatch list, so that a system user can know the latest state of the measuring point;
alarm tracing analysis, namely, water quality alarm can call a hydraulic model to realize tracing and diffusion analysis;
the alarm dispatch is that after confirming the condition, the alarm dispatch can be sent to an outside industry work order through the dispatch, and the history dispatch record, the history alarm record, the basic information of the dispatch and the position of a measuring point map can be seen during dispatch;
and inquiring the alarm work orders, namely inquiring and tracking the disposal records of the alarm work orders through the alarm work orders and the accounts.
Preferably, after the alarm is processed, the method further comprises the following steps:
analyzing work order feedback information, manually inputting or collecting the work order feedback information by a system, wherein the work order feedback information comprises relevant details such as alarm reasons, alarm places and the like, and relates to word description, image data or other forms of information provided by users or operators;
based on the work order feedback information, the system executes alarm accuracy checking operation, extracts content related to an alarm reason and an alarm place from the work order feedback information, compares the extracted information with actual monitoring data, verifies whether the alarm reason and the alarm place are consistent with the condition recorded by the monitoring system, if the alarm reason and the alarm place are inconsistent with the condition recorded by the monitoring system, the system classifies problems, including false alarm, missing report or other conditions inconsistent with the actual condition, and the system detects abnormal conditions, such as whether abnormal monitoring data exist or whether the work order information is inconsistent or not, through further analysis;
Based on the monitoring data of the normal and abnormal conditions of the work order feedback information, operations are performed to pre-process the monitoring data, including removing outliers, processing missing data, normalizing data, etc., selecting and extracting key features for problem resolution, marking data indicating whether each data point is normal or abnormal, selecting an appropriate machine learning model, typically including but not limited to support vector machines, decision trees, neural networks, etc., training the selected model using the marked data set. Through repeated iteration, the model can adjust parameters of the model to adapt to known data distribution to the greatest extent, so that the model can be better generalized to unknown data, the performance of the trained model is evaluated by using another verification data set, fine adjustment of model parameters is performed or different feature sets are selected according to the result of performance evaluation, and the trained abnormal correction model is deployed into an actual system;
based on the abnormality correction model, detecting the abnormal condition in the data stream in real time, and making proper adjustment to optimize the alarm instruction so as to reduce the false alarm rate or false alarm rate.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic of each process, and should not limit the implementation process of the embodiment of the present application in any way.
In an embodiment, a monitoring and early-warning treatment device of a water supply network is provided, where the monitoring and early-warning treatment device of the water supply network corresponds to the monitoring and early-warning treatment method of the water supply network in the above embodiment one by one. As shown in fig. 7, the monitoring and early-warning treatment device of the water supply network comprises a first generation module, a second generation module, a third generation module, a first contrast analysis module, a second contrast analysis module and a fourth generation module. The functional modules are described in detail as follows:
the first generation module is used for generating a visual layer based on the map service source and the underground pipeline service;
the second generation module is used for acquiring equipment data and generating corresponding marking points on the visual layer;
the third generation module is used for acquiring monitoring data and generating a confidence interval according to historical monitoring data of the first preset period days in the past;
the first comparison analysis module is used for comparing and analyzing the monitoring data and the confidence interval and generating a corresponding intelligent alarm instruction;
the second comparison analysis module is used for comparing and analyzing the monitoring data with a preset pressure data threshold value and generating a corresponding abrupt change alarm instruction;
and the fourth generation module is used for determining the maximum clustering distance for generating the associated alarm event, and generating a corresponding associated alarm instruction according to the intelligent alarm instruction, the abrupt change alarm instruction and the maximum clustering distance, wherein the intelligent alarm instruction, the abrupt change alarm instruction and the associated alarm instruction are all used for converting the labeling state of the labeling point.
Optionally, the first contrast analysis module includes:
the first judging unit is used for judging whether the monitored data exceeds the confidence interval, if so, executing the operation of adding one to the count value of the alarm count, executing the operation of increasing the weight level of the level accumulation sum, judging whether the alarm count is greater than or equal to the alarm frequency threshold value, and judging whether the level accumulation sum is greater than or equal to the alarm buffer area, if not, generating an alarm delay instruction, if so, generating an intelligent alarm instruction, and executing the operation of restoring the count value assignment of zero;
the second judging unit is used for judging whether the monitored data exceeds the confidence interval, if not, executing the operation of adding one to the count value of the recovery count, judging whether the recovery count is larger than or equal to the recovery count threshold value, if not, generating a recovery delay instruction, if so, generating a recovery instruction, executing the operation of assigning zero to the count value of the alarm count and assigning zero to the weight level of the level accumulation sum, and generating an intelligent alarm record;
optionally, the second contrast analysis module includes:
the acquisition unit is used for determining the alarm delay time length and acquiring a plurality of monitoring data sets containing two monitoring data with time intervals being the alarm delay time length;
The third judging unit is used for judging whether the difference value of two monitoring data in all the monitoring data sets is larger than a preset pressure data threshold value or not, and if not, generating an alarm delay instruction;
a fourth judging unit, configured to judge if the distance between the monitoring data before the alarm delay time and the confidence interval center is greater than the distance between the monitoring data after the alarm delay time and the confidence interval center if the distance between the monitoring data before the alarm delay time and the confidence interval center is greater than the distance between the monitoring data before the alarm delay time and the confidence interval center, and generate an alarm delay instruction if the distance between the monitoring data before the alarm delay time and the confidence interval center is greater than the distance between the monitoring data after the alarm delay time and the confidence interval center is greater than the distance between the monitoring data before the alarm delay time and the confidence interval center;
a fifth judging unit, configured to judge whether the monitored data after the alarm delay time is greater than zero if yes, if no, generate an alarm delay instruction, if yes, generate a sudden change alarm instruction, and record the monitored data before the alarm delay time;
a sixth judging unit, configured to determine a recovery delay duration, obtain monitoring data in the recovery delay duration, and judge whether all monitoring data in the recovery delay duration is greater than monitoring data before the alarm delay duration minus a preset pressure data threshold, if not, generate a recovery delay instruction, if so, generate a recovery instruction, and generate a sudden change alarm record;
optionally, the acquiring unit includes:
the first judging subunit is used for judging whether the number of days of the second preset period is larger than the number of days of the first preset period, if not, the alarm delay time is set to be 5 minutes;
The second judging subunit is used for generating an average value of the alarm duration according to the abrupt change alarm record if yes, judging whether the average value of the alarm duration is smaller than 20 minutes, setting the alarm delay time to be 10 minutes if yes, and setting the alarm delay time to be 5 minutes if no;
an acquisition subunit, configured to acquire a plurality of monitoring data sets including two monitoring data with a time interval being an alarm delay duration based on the alarm delay duration;
optionally, the fourth generating module includes:
a first determining unit, configured to determine a maximum cluster distance for generating an associated alarm event;
the second determining unit is used for determining abnormal monitoring points in the user selection area according to the intelligent alarm instruction and the abrupt change alarm instruction and acquiring coordinate information of the abnormal monitoring points;
a seventh judging unit, configured to judge, according to the coordinate information, whether a distance between each two abnormal monitoring points is smaller than a maximum clustering distance, if so, classify the two abnormal monitoring points as the same associated alarm event, and push corresponding associated alarm state information at the visual layer according to each associated alarm event in the user selection area;
the eighth judging unit is used for judging whether the associated alarm state information at different moments is the same, if not, pushing the converted associated alarm state information, and generating a corresponding associated alarm instruction;
Optionally, the monitoring and early warning treatment device further includes:
the determining module is used for determining abnormal monitoring points, acquiring alarm parameters of the abnormal monitoring points, wherein the alarm parameters comprise pressure drop conditions before closing the valve, flow change before closing the valve, a valve to be closed, a pipe section and a user influenced after closing the valve, and pressure drop conditions after closing the valve, and generating corresponding statistical data according to the alarm parameters;
and the drawing module is used for drawing the affected valve, the affected pipe section, the affected user and the pressure change point positions on the visual layer according to the statistical data.
The specific limitation of the monitoring and early-warning treatment device of the water supply network can be referred to the limitation of the monitoring and early-warning treatment method of the water supply network, and is not repeated herein. All or part of the modules in the monitoring and early-warning treatment device of the water supply network can be realized by software, hardware and a combination of the software and the hardware. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, and the internal structure of which may be as shown in fig. 8. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program when executed by the processor is used for realizing a monitoring, early warning and disposing method of the water supply network.
In one embodiment, a computer device is provided comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the steps of when executing the computer program:
s10, generating a visual layer based on a map service source and underground pipeline service;
s20, acquiring equipment data, and generating corresponding marking points on the visual layer;
s30, acquiring monitoring data, and generating a confidence interval according to historical monitoring data of the first preset period days in the past;
s40, comparing and analyzing the monitoring data with the confidence interval to generate a corresponding intelligent alarm instruction;
s50, comparing and analyzing the monitoring data with a preset pressure data threshold value to generate a corresponding abrupt change alarm instruction;
s60, generating corresponding association alarm instructions according to the intelligent alarm instructions, the mutation alarm instructions and the maximum clustering distance, wherein the intelligent alarm instructions, the mutation alarm instructions and the association alarm instructions can be used for converting the labeling states of labeling points.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
S10, generating a visual layer based on a map service source and underground pipeline service;
s20, acquiring equipment data, and generating corresponding marking points on the visual layer;
s30, acquiring monitoring data, and generating a confidence interval according to historical monitoring data of the first preset period days in the past;
s40, comparing and analyzing the monitoring data with the confidence interval to generate a corresponding intelligent alarm instruction;
s50, comparing and analyzing the monitoring data with a preset pressure data threshold value to generate a corresponding abrupt change alarm instruction;
s60, generating corresponding association alarm instructions according to the intelligent alarm instructions, the mutation alarm instructions and the maximum clustering distance, wherein the intelligent alarm instructions, the mutation alarm instructions and the association alarm instructions can be used for converting the labeling states of labeling points.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions.
The above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.
Claims (4)
1. The monitoring and early-warning treatment method for the water supply network is characterized by comprising the following steps of:
generating a visual layer based on the map service source and the underground pipeline service;
Acquiring equipment data, and generating corresponding marking points on a visual layer;
acquiring monitoring data, and generating a confidence interval according to historical monitoring data of the first preset period days in the past;
comparing and analyzing the monitoring data with the confidence interval to generate a corresponding intelligent alarm instruction;
comparing and analyzing the monitoring data with a preset pressure data threshold value to generate a corresponding abrupt change alarm instruction;
determining the maximum clustering distance for generating the associated alarm event, and generating a corresponding associated alarm instruction according to the intelligent alarm instruction, the abrupt change alarm instruction and the maximum clustering distance, wherein the intelligent alarm instruction, the abrupt change alarm instruction and the associated alarm instruction are all used for converting the labeling state of the labeling point position;
the step of comparing and analyzing the monitoring data and the confidence interval and generating the corresponding intelligent alarm instruction comprises the following steps:
judging whether the monitoring data exceeds a confidence interval, if so, executing an operation of adding one to a count value of an alarm count, executing an operation of increasing a weight level of a level accumulation sum, judging whether the alarm count is larger than or equal to an alarm frequency threshold value, and judging whether the level accumulation sum is larger than or equal to an alarm buffer zone, if not, generating an alarm delay instruction, if so, generating an intelligent alarm instruction, and executing an operation of restoring the count value assignment of the count to zero;
Judging whether the monitoring data exceeds a confidence interval, if not, executing the operation of adding one to the count value of the recovery count, judging whether the recovery count is larger than or equal to a recovery count threshold value, if not, generating a recovery delay instruction, if so, generating a recovery instruction, executing the operation of assigning zero to the count value of the alarm count and assigning zero to the weight level of the level accumulation sum, and generating an intelligent alarm record;
the step of comparing and analyzing the monitoring data with a preset pressure data threshold value and generating a corresponding abrupt change alarm instruction comprises the following steps:
determining alarm delay time length, and acquiring a plurality of monitoring data sets containing two monitoring data with time intervals being the alarm delay time length;
judging whether the difference value of two monitoring data in all the monitoring data sets is larger than a preset pressure data threshold value, and if not, generating an alarm delay instruction;
if so, judging whether the distance between the monitoring data before the alarm delay time and the confidence interval center is greater than the distance between the monitoring data after the alarm delay time and the confidence interval center, and if not, generating an alarm delay instruction;
if yes, judging whether the monitoring data after the alarm delay time is greater than zero, if not, generating an alarm delay instruction, if yes, generating a sudden change alarm instruction, and recording the monitoring data before the alarm delay time;
Determining a recovery delay time length, acquiring monitoring data in the recovery delay time length, judging whether the monitoring data in the recovery delay time length is all greater than the monitoring data before the alarm delay time length minus a preset pressure data threshold value, if not, generating a recovery delay instruction, if so, generating a recovery instruction, and generating a sudden change alarm record;
the step of determining the alarm delay time length and acquiring a plurality of monitoring data sets including two monitoring data with time intervals of the alarm delay time length includes:
judging whether a sudden change alarm record is generated on the second preset period days, if not, setting the alarm delay time to be 5 minutes;
if yes, generating an alarm duration average value according to the abrupt change alarm record, judging whether the alarm duration average value is smaller than 20 minutes, if yes, setting the alarm delay time to be 10 minutes, and if not, setting the alarm delay time to be 5 minutes;
acquiring a plurality of monitoring data sets containing two monitoring data with time intervals being the alarm delay time length based on the alarm delay time length;
the determining of the maximum clustering distance for generating the associated alarm event, and generating a corresponding associated alarm instruction according to the intelligent alarm instruction, the abrupt change alarm instruction and the maximum clustering distance, wherein the intelligent alarm instruction, the abrupt change alarm instruction and the associated alarm instruction are all used for converting the labeling state of the labeling point location, and the steps comprise:
Determining a maximum cluster distance for generating an associated alarm event;
determining abnormal monitoring points in a user selected area according to the intelligent alarm instruction and the abrupt change alarm instruction, and acquiring coordinate information of the abnormal monitoring points;
judging whether the distance between every two abnormal monitoring points is smaller than the maximum clustering distance according to the coordinate information, classifying the two abnormal monitoring points as the same associated alarm event if the distance between the two abnormal monitoring points is smaller than the maximum clustering distance, and pushing corresponding associated alarm state information in a visual image layer according to each associated alarm event in a user selection area;
judging whether the associated alarm state information at different moments is the same, if not, pushing the converted associated alarm state information, and generating a corresponding associated alarm instruction;
the determining of the maximum clustering distance for generating the associated alarm event, and generating a corresponding associated alarm instruction according to the intelligent alarm instruction, the abrupt change alarm instruction and the maximum clustering distance, wherein the intelligent alarm instruction, the abrupt change alarm instruction and the associated alarm instruction are all used for converting the labeling state of the labeling point location, and then the steps of:
determining an abnormal monitoring point, and acquiring alarm parameters of the abnormal monitoring point, wherein the alarm parameters comprise pressure drop conditions before closing a valve, flow change before closing the valve, a valve to be closed, a pipe section and a user influenced after closing the valve, and pressure drop conditions after closing the valve, and corresponding statistical data are generated according to the alarm parameters;
And drawing the affected valve, the affected pipe section, the affected user and the pressure change point positions on the visual layer according to the statistical data.
2. The utility model provides a monitoring early warning processing apparatus of water supply network, its characterized in that, monitoring early warning processing apparatus of water supply network includes:
the first generation module is used for generating a visual layer based on the map service source and the underground pipeline service;
the second generation module is used for acquiring equipment data and generating corresponding marking points on the visual layer;
the third generation module is used for acquiring monitoring data and generating a confidence interval according to historical monitoring data of the first preset period days in the past;
the first comparison analysis module is used for comparing and analyzing the monitoring data and the confidence interval and generating a corresponding intelligent alarm instruction;
the second comparison analysis module is used for comparing and analyzing the monitoring data with a preset pressure data threshold value and generating a corresponding abrupt change alarm instruction;
the fourth generation module is used for determining the maximum clustering distance for generating the associated alarm event, and generating a corresponding associated alarm instruction according to the intelligent alarm instruction, the abrupt change alarm instruction and the maximum clustering distance, wherein the intelligent alarm instruction, the abrupt change alarm instruction and the associated alarm instruction are all used for converting the labeling state of the labeling point position;
The first contrast analysis module includes:
the first judging unit is used for judging whether the monitoring data exceeds a confidence interval, if yes, executing the operation of adding one to the count value of the alarm count, executing the operation of increasing the weight level of the level accumulation sum, judging whether the alarm count is greater than or equal to an alarm frequency threshold value, and judging whether the level accumulation sum is greater than or equal to an alarm buffer zone, if not, generating an alarm delay instruction, if yes, generating an intelligent alarm instruction, and executing the operation of assigning zero to the count value of the recovery count;
the second judging unit is used for judging whether the monitoring data exceeds the confidence interval, if not, executing the operation of adding one to the count value of the recovery count, judging whether the recovery count is larger than or equal to the recovery count threshold, if not, generating a recovery delay instruction, if so, generating a recovery instruction, executing the operation of assigning zero to the count value of the alarm count and assigning zero to the weight level of the level accumulation sum, and generating an intelligent alarm record;
the second contrast analysis module includes:
the acquisition unit is used for determining the alarm delay time length and acquiring a plurality of monitoring data sets containing two monitoring data with time intervals being the alarm delay time length;
The third judging unit is used for judging whether the difference value of two monitoring data in all the monitoring data sets is larger than a preset pressure data threshold value or not, and if not, generating an alarm delay instruction;
a fourth judging unit, configured to judge if the distance between the monitoring data before the alarm delay time and the confidence interval center is greater than the distance between the monitoring data after the alarm delay time and the confidence interval center if the distance between the monitoring data before the alarm delay time and the confidence interval center is greater than the distance between the monitoring data before the alarm delay time and the confidence interval center, and generate an alarm delay instruction if the distance between the monitoring data before the alarm delay time and the confidence interval center is greater than the distance between the monitoring data after the alarm delay time and the confidence interval center is greater than the distance between the monitoring data before the alarm delay time and the confidence interval center;
a fifth judging unit, configured to judge whether the monitored data after the alarm delay time is greater than zero if yes, if no, generate an alarm delay instruction, if yes, generate a sudden change alarm instruction, and record the monitored data before the alarm delay time;
a sixth judging unit, configured to determine a recovery delay duration, obtain monitoring data in the recovery delay duration, and judge whether all monitoring data in the recovery delay duration is greater than monitoring data before the alarm delay duration minus a preset pressure data threshold, if not, generate a recovery delay instruction, if so, generate a recovery instruction, and generate a sudden change alarm record;
the acquisition unit includes:
the first judging subunit is used for judging whether the number of days of the second preset period is larger than the number of days of the first preset period, if not, the alarm delay time is set to be 5 minutes;
The second judging subunit is used for generating an average value of the alarm duration according to the abrupt change alarm record if yes, judging whether the average value of the alarm duration is smaller than 20 minutes, setting the alarm delay time to be 10 minutes if yes, and setting the alarm delay time to be 5 minutes if no;
an acquisition subunit, configured to acquire, based on the alarm delay duration, a plurality of monitoring data sets including two monitoring data with a time interval being the alarm delay duration;
the fourth generation module includes:
a first determining unit, configured to determine a maximum cluster distance for generating an associated alarm event;
the second determining unit is used for determining abnormal monitoring points in the user-selected area according to the intelligent alarm instruction and the abrupt change alarm instruction and acquiring coordinate information of the abnormal monitoring points;
a seventh judging unit, configured to judge, according to the coordinate information, whether a distance between every two abnormal monitoring points is smaller than a maximum clustering distance, if so, classify the two abnormal monitoring points as the same associated alarm event, and push corresponding associated alarm state information in a visual layer according to each associated alarm event in a user selection area;
The eighth judging unit is used for judging whether the associated alarm state information at different moments is the same, if not, pushing the converted associated alarm state information, and generating a corresponding associated alarm instruction;
the monitoring, early warning and disposing device further comprises:
the system comprises a determining module, a judging module and a judging module, wherein the determining module is used for determining an abnormal monitoring point and acquiring alarm parameters of the abnormal monitoring point, the alarm parameters comprise pressure drop conditions before closing a valve, flow change before closing the valve, a valve to be closed, a pipe section and a user influenced after closing the valve and pressure drop conditions after closing the valve, and corresponding statistical data are generated according to the alarm parameters;
and the drawing module is used for drawing the affected valve, the affected pipe section, the affected user and the pressure change point positions on the visual layer according to the statistical data.
3. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor, when executing the computer program, implements the steps of the method for monitoring and pre-warning treatment of a water supply network according to claim 1.
4. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the monitoring and pre-warning treatment method of a water supply network according to claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410122212.0A CN117649752B (en) | 2024-01-30 | 2024-01-30 | Monitoring, early warning and disposing method, device, equipment and medium for water supply network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410122212.0A CN117649752B (en) | 2024-01-30 | 2024-01-30 | Monitoring, early warning and disposing method, device, equipment and medium for water supply network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117649752A CN117649752A (en) | 2024-03-05 |
| CN117649752B true CN117649752B (en) | 2024-04-09 |
Family
ID=90045511
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410122212.0A Active CN117649752B (en) | 2024-01-30 | 2024-01-30 | Monitoring, early warning and disposing method, device, equipment and medium for water supply network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117649752B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1266211A (en) * | 1999-03-04 | 2000-09-13 | 沈阳市航天供水设备厂 | Fire-fighting water supply monitoring system and control method |
| CN112185072A (en) * | 2020-09-22 | 2021-01-05 | 广州珠江建设发展有限公司 | Deep foundation pit automatic monitoring method, device, equipment and medium based on Internet of things |
| CN115345568A (en) * | 2021-09-02 | 2022-11-15 | 浙江浙安数智环境工程有限公司 | Monitoring and early warning method and system based on drainage pipe network GIS |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150009031A1 (en) * | 2013-07-03 | 2015-01-08 | Honeywell International Inc. | Multilayer perimeter instrusion detection system for multi-processor sensing |
-
2024
- 2024-01-30 CN CN202410122212.0A patent/CN117649752B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1266211A (en) * | 1999-03-04 | 2000-09-13 | 沈阳市航天供水设备厂 | Fire-fighting water supply monitoring system and control method |
| CN112185072A (en) * | 2020-09-22 | 2021-01-05 | 广州珠江建设发展有限公司 | Deep foundation pit automatic monitoring method, device, equipment and medium based on Internet of things |
| CN115345568A (en) * | 2021-09-02 | 2022-11-15 | 浙江浙安数智环境工程有限公司 | Monitoring and early warning method and system based on drainage pipe network GIS |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117649752A (en) | 2024-03-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111784140A (en) | Wisdom water affairs management and control scheduling platform based on internet of things | |
| US20120185184A1 (en) | System and method for identifying likely geographical locations of anomalies in a water utility network | |
| CN117010863A (en) | Municipal pipe network health degree online monitoring system and method based on Internet of things technology | |
| US20230167950A1 (en) | Methods for safety management of compressors in smart gas pipeline network and internet of things systems thereof | |
| CN116503975B (en) | Intelligent gas GIS-based potential safety hazard disposal method and Internet of things system | |
| CN111538643B (en) | Alarm information filtering method and system for monitoring system | |
| CN110359919B (en) | Shield tunneling machine construction risk prevention and control method and system | |
| CN115358155A (en) | Power big data abnormity early warning method, device, equipment and readable storage medium | |
| CN115018343A (en) | System and method for recognizing and processing abnormity of mass mine gas monitoring data | |
| CN116934262A (en) | Construction safety supervision system and method based on artificial intelligence | |
| CN115204583A (en) | Method, system and device for hierarchical management, control, evaluation and analysis of regional risks in chemical industry park | |
| CN117370818B (en) | Intelligent diagnosis method and intelligent environment-friendly system for water supply and drainage pipe network based on artificial intelligence | |
| CN113762445B (en) | Identification analysis system based on assembled building | |
| CN117649752B (en) | Monitoring, early warning and disposing method, device, equipment and medium for water supply network | |
| CN116777085B (en) | Coal mine water damage prediction system based on data analysis and machine learning technology | |
| CN116579601B (en) | Mine safety production risk monitoring and early warning system and method | |
| CN113128803A (en) | Oil and gas pipeline risk determination method and device and computer equipment | |
| CN116271930A (en) | Remote control system for alcohol refining process | |
| CN113361730B (en) | Risk early warning method, device, equipment and medium for maintenance plan | |
| CN114969068A (en) | Method and system for analyzing real-time flow monitoring data of urban pressure pipe network | |
| CN110878692A (en) | Fault alarm method and device | |
| CN115130692A (en) | Equipment cloud monitoring system | |
| CN110455370B (en) | Flood-prevention drought-resisting remote measuring display system | |
| CN113837408A (en) | Traffic facility operation and maintenance management system based on equipment full-life-cycle supervision | |
| CN111586612A (en) | Water affair management method, device and system based on wireless sensor network |
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 |