Search

KR-102963408-B1 - METHOD FOR DETECTING DEFECTS IN WATER AND SEWAGE FACILITIES AND A DEFECT DETECTION SYSTEM SUPPORTING THE SAME

KR102963408B1KR 102963408 B1KR102963408 B1KR 102963408B1KR-102963408-B1

Abstract

A defect detection system for water and sewage facilities is disclosed, comprising: a defect detection data set storage unit storing at least one defect prediction data and at least one defect history data related to water and sewage facilities; an image conversion unit generating at least one prediction image data based on 3D model data corresponding to the at least one defect prediction data; a neural network generation unit performing machine learning by associating the at least one prediction image data with the at least one defect history data; and a defect detection module determining whether a defect is included in real-time image data obtained from the water and sewage facilities. In addition to this, various embodiments identified through this document are possible.

Inventors

  • 최영환
  • 도재혁
  • 박동채
  • 문현철
  • 노우승
  • 유현승

Assignees

  • 경상국립대학교산학협력단

Dates

Publication Date
20260512
Application Date
20220325

Claims (12)

  1. In a water supply and sewage facility defect detection system, A defect detection data set storage unit storing at least one defect prediction data related to a water supply and sewage facility and at least one defect history data related to the water supply and sewage facility; An image conversion unit that generates at least one predicted image data based on 3D model data corresponding to the above at least one defect prediction data; A neural network generation unit that performs machine learning by associating the above at least one prediction image data with the above at least one defect history data; and Based on the above neural network generation unit, it includes a defect detection module that determines whether the real-time image data obtained from the water and sewage facilities contains defects, and The above prediction image data is generated through a preprocessing process in which the above 3D model data is input into a 3D printer to input the object coordinates of the actually printed 3D model, and The image conversion unit generates at least one predicted image data to include at least one region of interest (ROI), and A water supply and sewage defect detection system, wherein the defect detection module compares the region of interest between the real-time image data and the predicted image data and determines whether the real-time data contains a defect when the specified similarity is exceeded.
  2. In Article 1, A water supply and sewage defect detection system, wherein at least one defect prediction data is stored in the defect detection data set storage unit as at least one data set based on the risk level associated with defects in the water supply and sewage facilities.
  3. delete
  4. In Article 1, A water supply and sewage defect detection system in which the above neural network generation unit performs the above machine learning based on a convolutional neural network.
  5. In Article 1, The above defect history data is data including defect image data of the water and sewage facilities detected from the water and sewage facilities during a specified period of time, and A water supply and sewage defect detection system, wherein the above real-time image data is data obtained from the water supply and sewage facility after the above defect history data is stored in the defect detection data set storage unit.
  6. delete
  7. In a method for detecting defects in water supply and sewage facilities based on a water supply and sewage facility defect system described in claim 1, A step of storing at least one defect prediction data related to a water supply and sewage facility and at least one defect history data related to the water supply and sewage facility; A step of generating at least one prediction image data based on 3D model data corresponding to at least one defect prediction data; A step of machine learning by associating the above at least one prediction image data with the above at least one defect history data; and Based on the above neural network generation unit, the method includes a step of determining whether the real-time image data obtained from the water and sewage facilities contains defects, and The step of generating the above-mentioned predicted image data generates the predicted image data through a preprocessing process in which the 3D model data is applied to a 3D printer and the object coordinates of the actually printed 3D model are input. The above generating step generates at least one prediction image data to include at least one region of interest (ROI), and A method for detecting defects in water supply and sewage systems, wherein the determining step compares the region of interest between the real-time image data and the predicted image data and determines whether the real-time data contains defects when the specified similarity is exceeded.
  8. In Article 7, The above-mentioned storage step is a method for detecting water and sewage defects, wherein the at least one defect prediction data is stored as at least one data set based on the risk level associated with the defect of the water and sewage facility.
  9. delete
  10. In Article 7, The machine learning step described above is a method for detecting water and sewage defects, which performs the machine learning based on a convolutional neural network.
  11. In Article 7, The above defect history data is data including defect image data of the water and sewage facilities detected from the water and sewage facilities during a specified period of time, and A method for detecting defects in a water supply and sewage system, wherein the above real-time image data is data obtained from the above water supply and sewage facility after the above defect history data is stored.
  12. delete

Description

Method for detecting defects in water and sewage facilities and a defect detection system supporting the same The embodiments disclosed in this document relate to a method for detecting defects in water and sewage facilities and a defect detection system supporting the same. Water supply and sewage facilities refer to facilities that supply water to buildings such as houses and factories, or treat water discharged from said buildings. Such water supply and sewage facilities may include pipes separated according to the type of water supplied or discharged. For example, water supply and sewage facilities may include water pipes that are part of a facility supplying water suitable for drinking, and sewage pipes that are part of a facility discharging domestic sewage, factory wastewater, rainwater, etc. Water supply and sewage facilities may include various components, such as water pipes and sewer pipes, to supply water or discharge sewage. Water supply and sewage facilities containing such components may be buried and not exposed to the outside. Due to the functional characteristics of water and sewage facilities, such as their buried form and the passage of water or wastewater through numerous pipes, it can be difficult for managers to detect internal structural defects. One method for detecting defects in water and sewage facilities involves, for instance, switching the system from a water supply and/or drainage state to a water cutoff or non-cutoff state and then detecting defects such as cracks through images taken of the interior of water and/or sewer pipes. However, this method carries the inconvenience of requiring managers to manually inspect each pipe even after images of the interior are obtained, as well as the potential for managerial misjudgment. Such a method can further delay the time required to detect defects in water and sewage facilities. FIG. 1 is a block diagram of a water supply and sewage facility defect detection system according to one embodiment. FIG. 2 is a flowchart illustrating a method for detecting defects in water supply and sewage facilities according to one embodiment. FIG. 3 is a diagram illustrating a method for detecting defects in water and sewage facilities according to various embodiments, based on the data transmission and reception relationships between the components. FIG. 4 is a diagram exemplarily illustrating a series of processes related to a method for detecting defects in water supply and sewage facilities according to various embodiments. In relation to the description of the drawings, the same reference number may be assigned to identical or corresponding components. Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the attached drawings. The advantages and features of the present invention, and the methods for achieving them, will become clear by referring to the embodiments described below in detail together with the attached drawings. However, the present invention is not limited to the embodiments disclosed below but may be implemented in various different forms. These embodiments are provided merely to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the invention, and the present invention is defined only by the scope of the claims. In the following, the same reference numerals refer to the same components. Although terms such as "first," "second," etc. are used to describe various elements, components, and/or sections, it goes without saying that these elements, components, and/or sections are not limited by these terms. These terms are used merely to distinguish one element, component, or section from another. Accordingly, it goes without saying that the first element, first component, or first section mentioned below may be a second element, second component, or second section within the technical scope of the present invention. The terms used herein are for describing embodiments and are not intended to limit the invention. In this specification, the singular form includes the plural form unless specifically stated otherwise in the text. As used herein, "comprises" and/or "made of" do not exclude the presence or addition of one or more other components, steps, actions, and/or elements to the mentioned components, steps, actions, and/or elements. Unless otherwise defined, all terms used in this specification (including technical and scientific terms) may be used in a meaning commonly understood by those skilled in the art to which the present invention pertains. Additionally, terms defined in commonly used dictionaries are not to be interpreted ideally or excessively unless explicitly and specifically defined otherwise. Hereinafter, the configuration of the present invention will be described in detail with reference to the attached drawings. FIG. 1 is a block diagram of a water supply and sewage facility defect detectio