KR102747356B1 - Water pipe network intelligent system using water digital twin abd apparatus performing thereof - Google Patents

Abstract

The water pipe network intelligence server according to the present invention includes a data receiving unit which receives data from a waterworks headquarters server and an open information acquisition server, a leakage prediction data processing unit which processes a sensitivity status value of a leakage meter among the data to generate and provide leakage prediction processed data, a pipe life data processing unit which processes a pressure value and a flow rate value of a pipe among the data to generate and provide pipeline life prediction processed data, a water quality data processing unit which processes a water quality value of the pipe among the data to generate and provide water quality prediction processed data, a leakage prediction unit which determines whether a leakage is possible using the leakage prediction processed data generated by the leakage prediction data processing unit, a pipe life prediction unit which predicts the pipe life using the pipe life prediction processed data generated by the pipe life data processing unit, and a water quality prediction unit which determines the water quality status of the pipe using the water quality prediction processed data generated by the water quality data processing unit.

Description

Water pipe network intelligent system using water digital twin and its execution method {WATER PIPE NETWORK INTELLIGENT SYSTEM USING WATER DIGITAL TWIN ABD APPARATUS PERFORMING THEREOF}

The present invention relates to a water pipe network intelligence system through application of a water supply digital twin and a method for implementing the same, and more specifically, to a water pipe network intelligence system through application of a water supply digital twin and a method for implementing the same, which develops an artificial intelligence-based control system for water pipes by incorporating digital twin technology that supports the life cycle and enables a strategic approach to maintenance through prediction of accident occurrence and prediction of the life of the pipes.

The water supply network is an essential urban infrastructure, and water pipes form its basic framework. However, due to the nature of water pipes, which are mostly buried underground, there is a problem in that it is difficult to accurately determine the damage status or aging.

When water pipes break due to external factors or aging, it not only causes economic losses due to water leaks, but also causes pollutants to infiltrate the damaged area, and causes many other problems, large and small, such as rust caused by aging pipes. Here, the breakage of water pipes is not necessarily proportional to the aging of water pipes, and therefore, it is difficult to see it as desirable in terms of economy or efficiency to replace water pipes in order of aging.

Therefore, it is required to accurately diagnose water pipes in order to apply them to calculating the priority for replacing water pipes.

Previously proposed technologies for diagnosing water supply networks are disclosed in the following <Patent Document 1> to <Patent Document>.

The prior art disclosed in <Patent Document 1> includes a pipeline model automatic generation module for automatically generating a pipeline model for pipeline diagnosis, a pipeline analysis module for analyzing a pipeline by considering water pressure, flow rate, and water leakage information, a pipe condition evaluation module for automatically evaluating a pipe condition using a predetermined evaluation factor, a hydraulic/water quality diagnosis module for analyzing hydraulic/water quality information including leakage amount and water quality information by section of a pipeline, and a facility improvement decision-making module for determining a pipeline improvement priority using collected data.

This configuration supports decision-making on priority for pipeline maintenance by using automatic analysis results for water pipe networks calculated based on repair, water quality and facility diagnosis results.

In addition, the prior art disclosed in <Patent Document 2> includes an acoustic detection unit for detecting the sound of a target object, a storage unit, a transmitter unit, and a water leak detection module, and enables more precise and easy identification of the presence or absence of a water leak and the location of the leak, thereby minimizing waste of time and manpower for exploration in areas where there is no water leak, thereby maximizing work efficiency.

In addition, the prior art disclosed in <Patent Document 3> includes a detection sensor unit for detecting the sound of a target object through which a fluid flows, a storage unit for storing acoustic data, a water leak detection device, and a calculation unit for analyzing the acoustic data, and analyzes the part of the target object where noise is generated using the noise level and noise distribution, thereby enabling the identification of whether there is a water leak and the location of the leak to be performed more precisely and easily, thereby minimizing waste of time and manpower for exploration in an area without a leak, thereby maximizing work efficiency.

In addition, the prior art disclosed in <Patent Document 4> connects and installs both ends of a special-shaped pipe between cut drain pipes, and connects both ends of the special-shaped pipe to drain pipes on both sides, forms an access flange portion on the top of the special-shaped pipe so that an endoscopic device can be inserted inside, and provides a plug flange that can be opened and closed on the access flange portion, so that an endoscopic device can be inserted without cutting the drain pipe, thereby reducing construction costs and shortening the water outage time due to the construction time.

At the current technological level, underground water pipe networks are managed primarily using GIS, but there is a limit to the level of fragmentary information displayed on a two-dimensional plane regarding facility specifications.

Although the smart water supply project is underway, it is limited to installing sensors to monitor the current status of the water supply and collecting information rather than predicting aging and accidents, and complex prediction analysis using a large amount of measurement information is difficult.

Previously, only the domains and objects belonging to each domain, such as manufacturing, city, home, energy, medical, and education, to which digital twins were applied, were targeted as digital twins, and the movement of digital twin objects between domains or the linkage between digital twin systems in different domains were not considered. Therefore, information sharing and management of digital twin objects scattered across each domain were not performed.

Republic of Korea Patent No. 10-1283828 (registered on July 2, 2013) (water pipe network diagnosis system) Republic of Korea Patent No. 10-1382231 (registered on April 1, 2014) (leakage diagnosis system using negative continuity) Republic of Korea Publication Patent No. 10-2014-0063380 (Published on May 27, 2014) (Permanent water leak diagnosis system using noise level and distribution) Republic of Korea Public Utility Model No. 20-2010-0003282 (Published on March 25, 2010 (Deformed pipe for drainage pipe diagnosis))

The purpose of the present invention is to provide a water pipe network intelligence system and an implementation method thereof by applying a water supply digital twin capable of performing a strategic approach to maintenance through prediction of accident occurrence and prediction of pipeline lifespan by developing an artificial intelligence-based control system for water pipes by incorporating digital twin technology that supports the life cycle.

In addition, the present invention aims to provide a water pipe network intelligence system and an execution method thereof through the application of a water pipe digital twin that can develop a deep learning model for water leakage prediction based on acquisition of pipe installation information and operation information measured from water pipes, verification of the reliability of the acquired information, and combination of time series and non-time series information, thereby increasing the possibility and reliability of water leakage prediction.

The purposes of the present invention are not limited to the purposes mentioned above, and other purposes and advantages of the present invention which are not mentioned can be understood by the following description, and will be more clearly understood by the embodiments of the present invention. In addition, it will be easily understood that the purposes and advantages of the present invention can be realized by the means and combinations thereof indicated in the claims.

In order to achieve these objectives, a water pipe network intelligence server includes a data receiving unit which receives data from a waterworks headquarters server and an open information acquisition server, a leakage prediction data processing unit which processes a sensitivity status value of a leakage meter among the data to generate and provide leakage prediction processed data, a pipe life data processing unit which processes a pressure value and a flow rate value of a pipe among the data to generate and provide pipeline life prediction processed data, a water quality data processing unit which processes a water quality value of the pipe among the data to generate and provide water quality prediction processed data, a leakage prediction unit which determines whether a leakage is possible using the leakage prediction processed data generated by the leakage prediction data processing unit, a pipe life prediction unit which predicts the pipe life using the pipe life prediction processed data generated by the pipe life data processing unit, and a water quality prediction unit which determines the water quality status of the pipe using the water quality prediction processed data generated by the water quality data processing unit.

In addition, a method for intelligentizing a water pipe network to achieve these purposes includes the steps of receiving data from a waterworks headquarters server and an open information acquisition server, the step of processing a sensitivity status value of a water leak meter among the data to generate water leak prediction processed data, the step of processing a pressure value and a flow rate value of a pipe among the data to generate water leak life prediction processed data, the step of processing a water quality value of the pipe among the data to generate water quality prediction processed data, and the steps of determining whether a water leak is possible using the generated water leak prediction processed data, predicting the pipe life using the pipe life prediction processed data, and determining the water quality status of the pipe using the water quality prediction processed data.

According to the present invention as described above, there is an advantage in that an artificial intelligence-based control system for water pipelines can be developed by incorporating digital twin technology that supports the life cycle, thereby enabling a strategic approach to maintenance through prediction of accident occurrence and prediction of pipeline lifespan.

In addition, according to the present invention, there is an advantage in that it is possible to develop a deep learning model for water leakage prediction based on acquisition of pipe installation information and operation information measured from water pipes, verification of the reliability of the acquired information, and combination of time series and non-time series information, thereby increasing the possibility and reliability of water leakage prediction.

Figure 1 is a drawing for explaining a water pipe network intelligence system through application of a water supply digital twin according to one embodiment of the present invention.
FIG. 2 is a block diagram illustrating the internal structure of a water pipe network intelligence server according to one embodiment of the present invention.
Figure 3 is a flow chart for explaining one embodiment of a water pipe network intelligence method according to the present invention.

The above-mentioned objects, features and advantages will be described in detail below with reference to the attached drawings, so that those with ordinary skill in the art to which the present invention pertains can easily practice the technical idea of the present invention. In describing the present invention, if it is judged that a detailed description of a known technology related to the present invention may unnecessarily obscure the gist of the present invention, a detailed description thereof will be omitted. Hereinafter, a preferred embodiment according to the present invention will be described in detail with reference to the attached drawings. In the drawings, the same reference numerals are used to indicate the same or similar components.

Figure 1 is a drawing for explaining a water pipe network intelligence system through application of a water pipe digital twin according to one embodiment of the present invention. A digital twin according to the present invention means expressing a corresponding water pipe as a virtual object in software.

Referring to Fig. 1, the water supply network intelligence system through application of water supply digital twin includes a water supply headquarters server (100), an open information acquisition server (200), and a water supply network intelligence server (300).

The waterworks headquarters server (100) is connected to each of a plurality of water meters and receives remote metering information (i.e., water usage) from a remote metering water meter that measures the water meter. At this time, the water meter means a meter installed in an existing waterworks user, and the remote metering water meter is installed to be connected to the water meter via wires or wirelessly.

The water supply headquarters server (100) provides water supply flow rate information, water quality information, pressure information, remote metering information, vibration information, etc. to the water supply network intelligence server (300).

The open information acquisition server (200) provides soil information, precipitation information, slope information, road information, temperature information, pipe simulation information, use area information, earthquake information, subway information, soil map information, soil distribution grade information, land use plan information, etc. to the water pipe network intelligence server (300).

The water supply network intelligence server (300) receives water supply flow rate information, water quality information, pressure information, remote metering information, vibration information, etc. from the water supply headquarters server (100).

The water pipe network intelligence server (300) receives the measured water usage from the water supply headquarters server (100) through a remote metering water meter that is connected to each of a plurality of water meters and checks the corresponding water meter.

The water pipe network intelligence server (300) receives soil information, precipitation information, slope information, road information, temperature information, pipe simulation information, use area information, earthquake information, subway information, soil map information, soil distribution grade information, land use plan information, etc. from the open information acquisition server (200).

Thereafter, the water supply network intelligence server (300) can provide control services, remote metering services, water leakage metering result provision services, water supply information provision services, etc. using information received from the water supply headquarters server (100) and the open information acquisition server (200).

In one embodiment, when a zone is selected by a user in the process of providing a control service, the water supply network intelligence server (300) provides the selected zone and remote metering information of the zone on a map.

In another embodiment, the water pipe network intelligence server (300) provides the location of the selected area and water leak meter on the map when the area is selected by the user in the process of providing a water leak detection result provision service. At this time, when a specific water leak meter is selected by the user, the water pipe network intelligence server (300) provides the sensitivity status, water leak trend, and water leak meter property information of the corresponding water leak meter.

In the above embodiment, the water pipe network intelligence server (300) displays the sensitivity status of the water leak meter as a first graph, divides the first graph into specific units, and then groups them to create multiple groups.

In one embodiment, the water pipe network intelligence server (300) divides the first graph into specific units and then groups them to create multiple groups.

In another embodiment, the water pipe network intelligence server (300) analyzes the first graph, divides it into periodic units if a waveform exists, and groups the groups to create multiple groups.

After that, the water pipe network intelligence server (300) compresses the sensitivity status value of each group for each of the multiple groups.

In one embodiment, the water pipe network intelligence server (300) divides the first graph into specific units and then groups the graphs to create multiple groups, and for each of the multiple groups, averages the sensitivity status values of the corresponding groups to calculate an average value.

At this time, the water pipe network intelligence server (300) can divide the sensitivity status values in the first graph into a specific number of units to create multiple groups.

After that, the water pipe network intelligence server (300) compresses the sensitivity status values of each of the multiple groups and displays them as a second graph, and then extracts a specific sensitivity status value from the second graph corresponding to each group to determine whether there is a possibility of a water leak.

In one embodiment, the water pipe network intelligence server (300) averages the bio-impedance values of each of the plurality of groups and displays the average value as a second graph at a location corresponding to the group. At this time, the second graph displays the sensitivity status value corresponding to the average value after averaging a specific number of sensitivity status values in each group.

As described above, the water pipe network intelligence server (300) averages the sensitivity status values of each group for each of a plurality of groups and displays them as a second graph, then analyzes the second graph to extract the largest slope value and uses this to determine whether there is a possibility of a water leak.

In one embodiment, the water pipe network intelligence server (300) compares the slope values extracted from each group, calculates a slope difference value by comparing the slope values, and merges the groups according to the slope difference value to extract only one slope value and uses this to determine whether there is a possibility of a water leak.

As described above, the water pipe network intelligence server (300) averages the sensitivity status values of each group for each of a plurality of groups and displays them as a second graph, then analyzes the second graph to extract the largest slope value and uses this to determine whether there is a possibility of a water leak.

In one embodiment, the water pipe network intelligence server (300) compares the slope values extracted from each group, calculates a slope difference value by comparing the slope values, and merges the groups according to the slope difference value to extract only one slope value and uses this to determine whether there is a possibility of a water leak.

In the above embodiment, the water pipe network intelligence server (300) compares the slope values extracted from each of the first group and the second group to calculate a slope difference value, and if the slope difference value is less than or equal to a specific value, the first group and the second group are merged, and then a larger slope value is extracted between the largest slope value extracted from the first group and the largest slope value extracted from the second group, and this can be used to determine whether there is a possibility of a water leak.

Through the above process, the water pipe network intelligence server (300) extracts the sensitivity status value, expresses the sensitivity status value in a third graph, and analyzes the third graph to determine whether there is a possibility of a water leak.

In one embodiment, the water pipe network intelligence server (300) can analyze the third graph and determine that no leak has occurred if the sensitivity status value falls within the normal range.

In another embodiment, the water pipe network intelligence server (300) can analyze the third graph and determine that a leak has occurred if the sensitivity status value is outside the normal range.

In the above embodiment, the water pipe network intelligence server (300) analyzes the third graph, and if the sensitivity status value is out of the normal range, compares the sensitivity status value immediately before it is out of the normal range and the sensitivity status value immediately after it is out of the normal range, and if the difference sensitivity status value is greater than a specific value, determines that a leak has occurred and provides a notification message to the administrator terminal.

In another embodiment, the water pipe network intelligence server (300) provides the location of the selected area and flow meter on the map when the area is selected by the user in the process of providing a remote metering service. At this time, when a specific flow meter is selected by the user, the water pipe network intelligence server (300) may include information such as pressure flow rate, accumulated flow rate, water quality, and attribute information of the corresponding pipe.

More specifically, the water pipe network intelligence server (300) displays each of the pressure value and flow rate value of the pipe as a first graph, divides the first graph into specific units, and then groups them to create multiple groups.

After that, the water pipe network intelligence server (300) averages the pressure value, flow rate value, and water quality value of the pipes of each group for each of the multiple groups to calculate the average value and information on the relationship between elements.

FIG. 2 is a block diagram illustrating the internal structure of a water pipe network intelligence server according to one embodiment of the present invention.

Referring to FIG. 2, the water pipe network intelligence server (300) includes a data receiving unit (310), a water leak prediction data processing unit (320), a pipe life data processing unit (330), a water quality data processing unit (340), a water leak prediction unit (350), a pipe life prediction unit (360), and a water quality prediction unit (370).

The data receiving unit (310) receives water supply flow rate information, water quality information, pressure information, remote metering information, vibration information, etc. from the water supply headquarters server (100).

The data receiving unit (310) receives the water usage measured through a remote metering water meter that is connected to each of a plurality of water meters from the waterworks headquarters server (100) and checks the water meter.

The data receiving unit (310) receives soil information, precipitation information, slope information, road information, temperature information, pipe simulation information, use area information, earthquake information, subway information, soil map information, soil distribution grade information, land use plan information, etc. from the open information acquisition server (200).

The water leak prediction data processing unit (320) processes the sensitivity information of the water leak measuring device.

First, the water leak prediction data processing unit (320) displays the sensitivity status of the water leak measuring device as a first graph, divides the first graph into specific units, and then groups them to create multiple groups.

In one embodiment, the leak prediction data processing unit (320) divides the first graph into specific units and then groups them to create multiple groups.

In another embodiment, the leak prediction data processing unit (320) analyzes the first graph, divides it into periodic units if a waveform exists, and groups it to create multiple groups.

After that, the water leak prediction data processing unit (320) compresses the sensitivity status value of each group for each of the multiple groups.

In one embodiment, the water leak prediction data processing unit (320) divides the first graph into specific units and then groups the graphs to create multiple groups, and for each of the multiple groups, averages the sensitivity status values of the corresponding groups to calculate an average value.

At this time, the water leak prediction data processing unit (320) can divide the sensitivity status values in the first graph into a specific number of units to create multiple groups.

After that, the water leak prediction data processing unit (320) compresses the sensitivity status values of each of the multiple groups and displays them as a second graph, and then extracts a specific sensitivity status value from the second graph corresponding to each group to determine whether a water leak is possible.

In one embodiment, the water leak prediction data processing unit (320) averages the bio-impedance values of each of the plurality of groups and displays the average value as a second graph at a location corresponding to the group. At this time, the second graph displays the sensitivity status value corresponding to the average value after averaging a specific number of sensitivity status values in each group.

As described above, the water leak prediction data processing unit (320) averages the sensitivity status values of each of the multiple groups and displays them as a second graph, then analyzes the second graph to extract the largest slope value and uses this to determine whether or not there is a possibility of a water leak.

In one embodiment, the leak prediction data processing unit (320) compares the slope values extracted from each group, compares the slope values, calculates a slope difference value, merges the groups according to the slope difference value, extracts only one slope value, and provides it to the leak prediction unit (350), so that the leak prediction unit (350) can determine whether or not a leak is possible using only the slope value.

As described above, the water leak prediction data processing unit (320) averages the sensitivity status values of each group for each of the multiple groups and displays them as a second graph, then analyzes the second graph to extract the most sensitive status value and provides it to the water leak prediction unit (350), so that the water leak prediction unit (350) can determine whether or not a leak is possible using only the slope value.

In one embodiment, the leak prediction data processing unit (320) compares the slope values extracted from each group, compares the slope values, calculates a slope difference value, merges the groups according to the slope difference value, extracts only one slope value, and provides it to the leak prediction unit (350), so that the leak prediction unit (350) can determine whether or not a leak is possible using only the slope value.

In the above embodiment, the water leak prediction data processing unit (320) compares the slope values extracted from each of the first group and the second group to calculate a slope difference value, and if the slope difference value is less than or equal to a specific value, the first group and the second group are merged, and then the larger slope value is extracted between the largest slope value extracted from the first group and the largest slope value extracted from the second group and provided to the water leak prediction unit (350), so that the water leak prediction unit (350) can determine whether or not a leak is possible using only the slope value.

The pipeline life data processing unit (330) displays each of the pipeline pressure value and flow rate value as a first graph, divides the first graph into specific units, and then groups them to create multiple groups.

After that, the pipe life data processing unit (330) divides the first graph into specific units and groups them to create multiple groups, and calculates an average value of the pressure value and flow rate value of each of the multiple groups.

At this time, the pipeline life data processing unit (330) can divide the pressure values and flow rate values in the first graph into a specific number of units to create multiple groups.

In one embodiment, the water leak prediction data processing unit (320) averages the pressure values and flow rates of each of the plurality of groups and displays the average value as a second graph at a location corresponding to the group. At this time, the second graph displays the pressure values and flow rates corresponding to the average values after averaging a specific number of pressure values and flow rates in each group.

As described above, the water leak prediction data processing unit (320) averages the pressure and flow rate values of each of the multiple groups and displays them as a second graph, then analyzes the second graph to extract the largest slope value and provides it to the water quality prediction unit (370), so that the water quality prediction unit (370) can determine whether or not a water leak is possible using only the slope values of each of the pressure and flow rate values.

The water quality data processing unit (340) displays the water quality values in a first graph, divides the first graph into specific units, and then groups them to create multiple groups.

In one embodiment, the water quality data processing unit (340) divides the first graph into specific units and then groups them to create multiple groups.

In another embodiment, the water quality data processing unit (340) analyzes the first graph, divides it into periodic units if a waveform exists, and groups it to create multiple groups.

After that, the water quality data processing unit (340) compresses the water quality values of each of the multiple groups.

In one embodiment, the water quality data processing unit (340) divides the first graph into specific units and then groups the divided graphs to create multiple groups, and for each of the multiple groups, averages the water quality values of the corresponding groups to calculate an average value.

At this time, the water quality data processing unit (340) can divide the water quality values in the first graph into a specific number of units to create multiple groups.

Thereafter, the water quality data processing unit (340) compresses the water quality values of each of the multiple groups and displays them as a second graph, and then extracts a specific water quality value from the second graph corresponding to each group to determine the water quality status.

In one embodiment, the water quality data processing unit (340) averages the water quality values of each of the plurality of groups and displays the average value as a second graph at a location corresponding to the group. At this time, the second graph displays the water quality value corresponding to the average value after averaging a specific number of water quality values in each group.

As described above, the water quality data processing unit (340) averages the water quality values of each group for each of the multiple groups and displays them as a second graph, then analyzes the second graph to extract the largest slope value and provides it to the water quality prediction unit (370), so that the water leakage prediction unit (350) can determine whether or not there is a possibility of a water leakage using only the slope value.

In one embodiment, the water quality data processing unit (340) compares the slope values extracted from each group, compares the slope values, calculates a slope difference value, merges the groups according to the slope difference value, extracts only one slope value, and provides it to the water leak prediction unit (350), so that the water leak prediction unit (350) can determine whether or not there is a possibility of a leak using only the slope value.

As described above, the water quality data processing unit (340) averages the sensitivity status values of each group for each of the multiple groups and displays them as a second graph, then analyzes the second graph to extract the largest slope value and provides it to the water quality prediction unit (370), so that the water leakage prediction unit (350) can determine whether or not there is a possibility of a water leakage using only the slope value.

In one embodiment, the water quality data processing unit (340) compares the slope values extracted from each group, compares the slope values to calculate the slope difference value, merges the groups according to the slope difference value, extracts only one slope value, and provides it to the water quality prediction unit (370) so that the water quality prediction unit (370) can determine the water quality condition using only the slope value.

In the above embodiment, the water quality data processing unit (340) compares the slope values extracted from each of the first group and the second group to calculate a slope difference value, and if the slope difference value is less than or equal to a specific value, the first group and the second group are merged, and then a larger slope value is extracted between the largest slope value extracted from the first group and the largest slope value extracted from the second group and provided to the water quality prediction unit (370), so that the water quality prediction unit (370) can determine the water quality condition using only the slope value.

The water leak prediction unit (350) expresses the slope of the sensitivity status value received from the water leak prediction data processing unit (320) as a third graph, and analyzes the third graph to determine whether a water leak is possible.

In one embodiment, the leak prediction unit (350) may analyze the third graph and determine that no leak has occurred if the sensitivity status value falls within the normal range.

In another embodiment, the leak prediction unit (350) may analyze the third graph and determine that a leak has occurred if the sensitivity status value is out of the normal range.

In the above embodiment, the leak prediction unit (350) analyzes the third graph, and if the sensitivity status value is out of the normal range, compares the sensitivity status value immediately before it is out of the normal range and the sensitivity status value immediately after it is out of the normal range, and if the difference sensitivity status value is greater than a specific value, determines that a leak has occurred and provides a notification message to the administrator terminal.

The pipe life prediction unit (360) receives the slope values of each of the pressure values and the flow rate values from the pipe life data processing unit (330), expresses each of the slope values of each of the pressure values and the flow rate values as a third graph, and analyzes the third graph to predict the pipe life.

In one embodiment, the pipe life prediction unit (360) can determine that the pipe life remains for a predetermined lifespan if the slope values of each of the pressure value and the flow rate value on the third graph fall within a normal range.

In another embodiment, the pipe life prediction unit (360) may determine that the pipe life has been reduced if each of the pressure value and the flow rate value on the third graph is outside the normal range.

In the above embodiment, if the slope values of each of the pressure value and the flow rate value on the third graph are out of the normal range, the pipe life prediction unit (360) can predict and provide a reduced pipe life based on the difference between the pressure value and the flow rate value immediately before they are out of the normal range and the pressure value and the flow rate value immediately after they are out of the normal range.

The water quality prediction unit (370) receives the slope value of each water quality value received from the pipeline life data processing unit (330), expresses the slope value of the water quality value as a third graph, and analyzes the third graph to determine the water quality status.

In one embodiment, the water quality prediction unit (370) can determine that the water quality condition is normal if the slope value of the water quality value on the third graph falls within the normal range.

In another embodiment, the water quality prediction unit (370) may determine that the water quality condition is not normal if the slope value of the water quality value on the third graph is out of the normal range.

In the above embodiment, if the slope value of the water quality value on the third graph is out of the normal range, the water quality prediction unit (370) can predict and provide a water quality grade indicating how bad the water quality is based on the difference between the water quality value just before it goes out of the normal range and the water quality value immediately after it goes out of the normal range.

Figure 3 is a flow chart for explaining one embodiment of a water pipe network intelligence method according to the present invention.

Referring to FIG. 3, the water supply network intelligence server (300) receives data from the water supply headquarters server and the open information acquisition server (step S310).

The water pipe network intelligence server (300) processes the sensitivity status value of the water leak measuring device among the above data to generate water leak prediction processed data (step S320).

The water pipe network intelligence server (300) processes the pressure and flow values of the pipe among the data to generate pipe life prediction processing data (step S330).

The water pipe network intelligence server (300) processes the water quality values of the pipes among the data to generate water quality prediction processing data (step S340).

The water pipe network intelligence server (300) uses the water leak prediction processing data to determine whether there is a possibility of a water leak, uses the pipe life prediction processing data to predict the pipe life, and uses the water quality prediction processing data to determine the water quality status of the pipe (step S350).

Although the invention has been described by way of limited embodiments and drawings, it is not limited to the above embodiments, and various modifications and variations are possible from this description by those skilled in the art to which the invention pertains. Accordingly, the spirit of the invention should be understood only by the scope of the claims set forth below, and all equivalent or equivalent variations thereof will be deemed to fall within the scope of the spirit of the invention.

100: Waterworks Headquarters Server,
200: Open Information Acquisition Server,
300: Water Supply Network Intelligence Server
310: Data receiving unit,
320: Leakage prediction data processing department,
330: Pipe life data processing department,
340: Water quality data processing department,
350: Leakage Prediction Unit,
360: Pipeline Life Prediction Department
370: Water Quality Prediction Department

Claims (2)

A data receiving unit that receives data from the waterworks headquarters server and the open information acquisition server;
A water leak prediction data processing unit which displays the sensitivity status of a water leak meter in a first graph, divides the first graph into specific units and groups them to create multiple groups, or analyzes the first graph, divides it into cycle units if a waveform exists, groups it, and creates multiple groups, and averages the bio-impedance values of each of the multiple groups and displays the calculated average value in a second graph at a position corresponding to the group, analyzes the second graph to compare the slope values extracted from the first and second groups, and calculates a slope difference value, and if the slope difference value is less than a specific value, merges the first and second groups, and then extracts and provides a larger slope value between the largest slope value extracted from the first group and the largest slope value extracted from the second group.
A pipeline life data processing unit that displays each of the pressure value and the flow rate value of a pipeline as a first graph, divides the pressure value and the flow rate value of the first graph into a specific number of units to create a plurality of groups, averages the pressure value and the flow rate value of each of the plurality of groups, and displays the calculated average value as a second graph at a location corresponding to the group, and analyzes the second graph to extract and provide the largest slope value;
A water quality data processing unit which generates a plurality of groups by dividing the first graph, which displays water quality values as a first graph, into specific units and then grouping the first graph, and for each of the multiple groups, the water quality values of the corresponding group are averaged and displayed as a second graph, and then compares the slope values extracted from each of the first group and the second group of the second graph to calculate a slope difference value, and if the slope difference value is lower than a specific value, merges the first group and the second group, and then extracts and provides a larger slope value between the largest slope value extracted from the first group and the largest slope value extracted from the second group;
A leak prediction unit that expresses the slope of the sensitivity status value received from the above leak prediction data processing unit as a third graph, analyzes the third graph, and if the sensitivity status value deviates from the normal range, compares the sensitivity status value immediately before deviating from the normal range and the sensitivity status value immediately after deviating from the normal range, and determines that a leak has occurred if the difference sensitivity status value is greater than a specific value, and provides a notification message to the administrator terminal;
A pipe life prediction unit which receives the slope values of each of the pressure values and the flow rate values from the pipe life data processing unit, expresses each of the slope values of each of the pressure values and the flow rate values as a third graph, and if the slope values of each of the pressure values and the flow rate values on the third graph are out of the normal range, predicts and provides a reduced pipe life based on the difference between the pressure values and the flow rate values immediately before they are out of the normal range and the pressure values and the flow rate values immediately after they are out of the normal range;
A water quality prediction unit characterized in that it includes a water quality prediction unit that receives the slope value of each water quality value received from the pipe life data processing unit, expresses the slope value of the water quality value as a third graph, and, if the slope value of the water quality value on the third graph is out of the normal range, predicts and provides a water quality grade indicating how bad the water quality is based on the difference between the water quality value immediately before it is out of the normal range and the water quality value immediately after it is out of the normal range.
Water supply network intelligence server.
In a water pipe network intelligence method executed on a water pipe network intelligence server,
A step of receiving data from a waterworks headquarters server and an open information acquisition server;
Step 1: Processing the sensitivity status value of the water leak meter among the above data to generate water leak prediction processing data;
A step of processing the pressure value and flow rate value of the pipeline among the above data to generate pipeline life prediction processing data;
A step of processing the water quality value of the pipeline among the above data to generate water quality prediction processing data;
It includes a step of determining whether there is a possibility of a leak using the generated leak prediction processing data, predicting the life of the pipeline using the pipeline life prediction processing data, and determining the water quality status of the pipeline using the water quality prediction processing data.
The sensitivity status value of the water leak meter among the above data is processed to generate water leak prediction processing data.
A step of displaying the sensitivity status of a water leak meter as a first graph, dividing the first graph into specific units and then grouping them to create multiple groups, or analyzing the first graph, dividing it into periodic units if a waveform exists, and then grouping them to create multiple groups;
A step of averaging the bio-impedance values of each of the above multiple groups, displaying the average value calculated as a second graph at a location corresponding to the group, analyzing the second graph, comparing the slope values extracted from each of the first group and the second group, and calculating the slope difference value; and
If the difference in slope value is less than or equal to a specific value, the step of merging the first group and the second group and then extracting and providing a larger slope value among the largest slope value extracted from the first group and the largest slope value extracted from the second group,
The step of generating pipeline life prediction processing data by processing the pipeline pressure and flow rate values among the above data is
A method of producing a ...
The step of processing the water quality value of the pipe among the above data to generate water quality prediction processing data
A step of dividing the first graph, which displays the water quality values as a first graph, into specific units and then grouping them to create multiple groups, averaging the water quality values of each group for each of the multiple groups and displaying them as a second graph, and then comparing the slope values extracted from each of the first group and the second group of the second graph to calculate a slope difference value; and
If the above-mentioned difference in slope value is less than or equal to a specific value, the step of merging the first group and the second group and then extracting and providing a larger slope value among the largest slope value extracted from the first group and the largest slope value extracted from the second group,
The step of determining whether there is a possibility of a leak using the generated leak prediction processing data, predicting the life of the pipeline using the pipeline life prediction processing data, and determining the water quality status of the pipeline using the water quality prediction processing data is provided.
A step of expressing the slope of the sensitivity status value as a third graph, analyzing the third graph, and if the sensitivity status value deviates from the normal range, comparing the sensitivity status value immediately before deviating from the normal range and the sensitivity status value immediately after deviating from the normal range, and determining that a leak has occurred if the difference sensitivity status value is greater than a specific value, and providing a notification message to the administrator terminal;
A step of receiving a slope value of each of the pressure value and the flow rate value, expressing each of the slope values of each of the pressure value and the flow rate value as a third graph, and if the slope value of each of the pressure value and the flow rate value on the third graph is out of the normal range, predicting and providing a reduced pipe life based on the difference between the pressure value and the flow rate value immediately before going out of the normal range and the pressure value and the flow rate value immediately after going out of the normal range;
A method for receiving a slope value of each water quality value, expressing the slope value of the water quality value as a third graph, and, if the slope value of the water quality value on the third graph is out of the normal range, predicting and providing a water quality grade indicating how bad the water quality is based on the difference between the water quality value immediately before it is out of the normal range and the water quality value immediately after it is out of the normal range.
Method for making water supply networks intelligent.