KR20210091863A - Deep learning based intelligent water management system for leak diagnosis prediction - Google Patents

Abstract

The present invention relates to a deep learning-based intelligent water management system for leak diagnosis prediction. According to the present invention, since a sound generated in a water and a sewer pipe is analyzed using a leak analysis algorithm, it is possible to capture a leak phenomenon occurring deep underground. In addition, it is possible to accurately identify a leak point through a source of the sound. The deep learning-based intelligent water management platform for the leak diagnosis prediction of the present invention comprises: a leak sound collection sensor; and a cloud server.

Description

Deep learning based intelligent water management system for leak diagnosis prediction}

For predicting leak diagnosis of the present invention, and more particularly, to a deep learning-based intelligent water management system for leak diagnosis prediction.

The water and sewage industry occupies a very important part in city operation and development.

These water and sewer pipes are naturally aging over time, and in order to prevent and solve the damage to the amount of tap water that occurs due to aging, it is necessary to accurately identify the location of the leakage and deal with it. are experiencing great difficulty.

This is because, due to the nature of the water and sewer pipes, it is difficult to determine whether a leak has occurred because they are buried deep underground, and replacing a water and sewage pipe buried deep underground simply because a leak is suspected leads to a huge waste of money.

Accordingly, the applicant of the present invention intends to solve this problem by using an algorithm that analyzes the sound characteristic of leaks occurring in the water and sewer pipes.

The present invention for solving the above-described problems is to install a leak sound collecting sensor at a plurality of different locations, collect the sound generated in the water and sewer pipe, and analyze it using a leak analysis algorithm.

The problems to be solved by the present invention are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the following description.

A deep learning-based intelligent water management platform for predicting leak diagnosis according to an embodiment of the present invention for solving the above-described problems includes: a leak sound collecting sensor installed in the field to collect sounds generated in water and sewage; and receiving the sound collected from the leak sound collection sensor, analyzing the sound with a leak analysis algorithm to analyze whether there is a leak, and when a leak is detected, the leak location information and the degree of leak are measured using the integrated leak control system It includes a cloud server, which is provided to a management server and a terminal in charge.

In addition to this, another method for implementing the present invention, another system, and a computer-readable recording medium for recording a computer program for executing the method may be further provided.

According to the present invention as described above, since the sound generated in the water and sewer pipe is analyzed using the leak analysis algorithm, it is possible to capture the leak phenomenon that occurs deep underground, and accurately grasp the leak point through the source of the sound. It has the advantage of being able to

Effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

1 is an exemplary diagram of a deep learning-based intelligent water management platform for leak diagnosis prediction according to an embodiment of the present invention.
2 is a view showing the specifications of the leak sound collection sensor according to an embodiment of the present invention as an example.

Advantages and features of the present invention and methods of achieving them will become apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only these embodiments allow the disclosure of the present invention to be complete, and those of ordinary skill in the art to which the present invention pertains. It is provided to fully understand the scope of the present invention to those skilled in the art, and the present invention is only defined by the scope of the claims.

The terminology used herein is for the purpose of describing the embodiments and is not intended to limit the present invention. As used herein, the singular also includes the plural unless specifically stated otherwise in the phrase. As used herein, “comprises” and/or “comprising” does not exclude the presence or addition of one or more other components in addition to the stated components. Like reference numerals refer to like elements throughout, and "and/or" includes each and every combination of one or more of the recited elements. Although "first", "second", etc. are used to describe various elements, these elements are not limited by these terms, of course. These terms are only used to distinguish one component from another. Accordingly, it goes without saying that the first component mentioned below may be the second component within the spirit of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used herein will have the meaning commonly understood by those of ordinary skill in the art to which this invention belongs. In addition, terms defined in a commonly used dictionary are not to be interpreted ideally or excessively unless specifically defined explicitly.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

The water and sewage industry occupies a very important part in city operation and development.

These water and sewer pipes are naturally aging over time, and in order to prevent and solve the damage to the amount of tap water that occurs due to aging, it is necessary to accurately identify the location of the leakage and deal with it. are experiencing great difficulty.

This is because, due to the nature of the water and sewer pipes, it is difficult to determine whether a leak has occurred because they are buried deep underground, and replacing a water and sewage pipe buried deep underground simply because a leak is suspected leads to a huge waste of money.

In the past, various attempts have been made to detect water leakage using various sensors. For example, there have been attempts to use fresh food, gas, and electronic sensors, but these sensors have a problem in that it is difficult to measure each time period, and the price is quite high, so it is impossible to detect leaks occurring in water and sewage pipes in large urban areas. was close to

And, in the case of the correlation sensor, different from the above, it is possible to measure by time period and the two-channel correlation non-excavation method is possible, so it can be measured on the ground. There is a problem.

Recently, as the performance of the robot has been developed, an attempt has been made to detect and diagnose a water leak using a robot. As a result of using the robot, the leak point can be accurately identified and there are various advantages, but the problem that the robot must be put directly into the water pipe Therefore, it was concluded that it is not suitable for detecting water leaks in large urban areas.

Hereinafter, the configurations of the leak detection platform according to an embodiment of the present invention will be described with reference to the drawings, and in the case of the present invention, how to solve the problems that could not be solved in the above other sensors will be described in detail.

1 is an exemplary diagram of a deep learning-based intelligent water management platform for leak diagnosis prediction according to an embodiment of the present invention, and FIG. 2 is a diagram illustrating specifications of a leak sound collection sensor according to an embodiment of the present invention. .

With reference to FIG. 1, a deep learning-based intelligent water management platform for leak diagnosis prediction according to an embodiment of the present invention will be described.

A leak sound collecting sensor is installed on site and collects sounds from water and sewage.

For example, the leak sound collection sensor may be installed in a pipe, a manhole, a fire hydrant, a ground surface, etc. to collect the sound generated in the water and sewage system.

The leak sound collecting sensor can transmit sound data to the cloud server by having a communication function in the sensor itself.

In addition, the leak sound collection sensor is connected to a user terminal (eg, a terminal device having a communication function such as a smartphone) through wired or short-distance communication, and transmits the collected sound to the user terminal, and transmits sound data from the user terminal to the cloud server. can be transmitted

Transmitting the sound data collected through the leak sound collecting sensor to the cloud server in this way uses a general communication method, and thus the inventor of the present invention can easily select it.

The cloud server receives the sound collected from the leak sound collection sensor, and analyzes the sound with the leak analysis algorithm to analyze the leak.

Then, when a leak is detected, the cloud server uses the location where the corresponding sound is generated to capture the point of occurrence of the leak, and provides location information and leak information where the leak occurred to the management server, the terminal in charge, the field, and the like.

At this time, the NUGU information may be transmitted and provided from the cloud server itself, or if only a leak analysis algorithm is built in the cloud server, it may be provided to the outside using an integrated leak control system.

In one embodiment, the sound detection sensor is installed in the field and collects sound, but is designed to be rotated at a predetermined angle, so that the angle can be remotely controlled by a cloud server or a person in charge/manager terminal.

In this case, it is to accurately detect the leak location, and since the sound has a directionality due to the nature of the sound, it is possible to accurately determine the leak location by rotating the sound sensor by a predetermined angle.

For example, if only the leak point is generally determined and reported, the site manager, who has to construct and solve the leak, conducts an inspection over a large area and proceeds with the construction/repair after the inspection.

However, if the leak point is identified in more detail as above, it provides convenience to the site by providing a more accurate point.

In addition, the leak analysis algorithm used in the embodiment of the present invention learns by inputting numerous leak sounds, as well as various sounds that can be received from the outside, such as vehicle sounds, people's sounds, wind sounds, etc. along with leak sounds. By inputting and learning together and optimizing to distinguish the leak sound from other sounds, there is an effect that the accuracy of judging the leak is guaranteed.

In addition, the leak analysis algorithm can also determine the degree of leak by analyzing the size and pattern of the leak sound.

In addition, detailed information about the location, depth, etc. of the water and sewer pipes installed in the city are stored in the cloud server, so that the leak sound collection sensor can calculate how far apart the water and sewage pipes are. can be used to

Accordingly, the cloud server can provide various information such as a leak point and the degree of leak to the outside.

In this case, being provided to the outside means providing a leak notification to facilities and personnel in charge of managing and managing water leakage, such as an office, a field, a terminal in charge, and the like.

Referring to Figure 2, the specification of the leak sound collection sensor according to the embodiment of the present invention is exemplified.

The mobile leak sound collecting sensor collects leak sound from the ground and transmits the collected sound data to the cloud server.

The fixed water leakage sound collecting sensor is installed in manholes, fire hydrants, water pipes, etc. to collect sound at all times and transmit it to the cloud server.

Such a leak sound collecting sensor may be provided with a device and a sensor for amplifying and filtering sound, and in the case of a fixed type, it is preferable to have its own communication means to transmit sound data at all times.

In addition, it is preferable that the water leak collecting sensor is waterproof in order to prevent sound errors and mechanical defects due to moisture.

When the deep learning-based intelligent water management platform for leak diagnosis prediction according to the embodiment of the present invention described above is used, the following effects are exhibited compared to the conventional sensors described above.

The leak sound collection sensor collects sound and transmits it to the cloud server to determine whether there is a leak in the cloud server, so it is possible to detect a leak at a low cost.

In particular, if a fixed water leakage sound collecting sensor is designed at a low cost and installed in a large area of the city, damage caused by water leakage can be minimized by detecting water leakage throughout the city and solving the water leakage problem early.

Since the installation is not limited to a specific place, a leak sound collection sensor can be installed directly in or near a water and sewer pipe, and a location where leak sound can be collected even when no sub-construction is performed, such as a manhole or the ground surface. If it is installed anywhere, it is possible to collect the leak sound and determine whether there is a leak.

As mentioned above, although embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art to which the present invention pertains can realize that the present invention can be embodied in other specific forms without changing its technical spirit or essential features. you will be able to understand Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive.

Claims (1)

a water leak sound collection sensor that is installed in the field and collects sounds generated from water and sewage;
Receives the sound collected from the leak sound collection sensor, analyzes the sound with a leak analysis algorithm to analyze the leak, and when a leak is detected, the leak location information and the degree of leak are managed using the leak detection system A deep learning-based intelligent water management platform for leak diagnosis prediction, including a cloud server, provided to the server and the person in charge terminal.

Images