KR-102962731-B1 - METHOD AND DEVICE FOR PERFORMING CIRCULAR AGGREGATE FOREIGN MATTER SORTING OPERATION BASED ON DEEP LEARNING ALGORITHM

KR102962731B1KR 102962731 B1KR102962731 B1KR 102962731B1KR-102962731-B1

Abstract

A method for sorting aggregates and a control device for performing the same are disclosed. According to one embodiment of the present disclosure, the method for sorting aggregates performed by the control device may include: a step of acquiring a first image of a first recycled aggregate through at least one camera; a step of acquiring information regarding foreign substances in the first recycled aggregate by inputting a data set related to the first image into a first artificial intelligence (AI) model; and a step of controlling an opening and closing device related to the movement of the first recycled aggregate so that the first recycled aggregate is loaded into a first area based on the information regarding foreign substances in the first recycled aggregate, wherein the amount of foreign substances in the first recycled aggregate is less than a first threshold value.

Inventors

송호재

Assignees

주식회사 에코리믹스

Dates

Publication Date: 20260511
Application Date: 20250731
Priority Date: 20240806

Claims (7)

In an aggregate sorting method performed by a control device, the method comprises: A step of acquiring a first image of the first recycled aggregate through at least one camera; A step of inputting a dataset related to the first image into a first artificial intelligence (AI) model to obtain information about foreign substances in the first recycled aggregate; and The method includes the step of controlling an opening and closing device related to the movement of the first recycled aggregate so that the first recycled aggregate is loaded into a first area, based on the fact that the amount of foreign matter contained in the first recycled aggregate among the information regarding foreign matter of the first recycled aggregate is less than a first threshold value. The data set associated with the first image includes the first image and first lighting information associated with the first image, and The first lighting information includes the intensity of the light source at the time when the first image is captured, the angle of incidence of light incident on the first recycled aggregate, and the type of light source. method.
In paragraph 1, The method further includes the step of controlling the opening and closing device related to the movement of the first recycled aggregate so that the first recycled aggregate is loaded into a second area based on the fact that the amount of foreign matter contained in the first recycled aggregate is greater than or equal to the first threshold value. A method in which a filter screen for removing foreign substances of a size greater than or less than x mm is placed within the second area.
delete
In paragraph 1, The above-mentioned first AI model includes a classifier and a plurality of sub-models, and The above classifier is trained to determine the submodel to input the first image based on the first lighting information among the plurality of submodels, and A method in which each of the above plurality of sub-models is trained to output information about foreign substances from an image input from the classifier.
In paragraph 4, A method in which, based on the fact that the type of light source at the time when the first image is captured is not natural light, the first image is input to the first sub-model among the plurality of sub-models by the classifier.
In paragraph 5, Based on the fact that the type of light source at the time when the first image is captured is natural light, the illuminance intensity of the light source is greater than or equal to a second threshold, and the angle of incidence is greater than or equal to a third threshold, the first image is input to the second sub-model among the plurality of sub-models by the classifier, and Based on the fact that the type of light source at the time when the first image is captured is natural light, the illuminance intensity of the light source is greater than or equal to a second threshold, and the angle of incidence is less than a third threshold, the first image is input to the third sub-model among the plurality of sub-models by the classifier, and Based on the fact that the type of light source at the time when the first image is captured is natural light, the illuminance intensity of the light source is less than a second threshold value, and the angle of incidence is greater than or equal to a third threshold value, the first image is input to the fourth sub-model among the plurality of sub-models by the classifier, and A method in which, based on the fact that the type of light source at the time when the first image is captured is natural light, the illuminance intensity of the light source is less than a second threshold value, and the angle of incidence is less than a third threshold value, the first image is input to the fifth sub-model among the plurality of sub-models by the classifier.
In a control device, At least one memory; and It includes at least one processor, The above at least one processor is: Acquire a first image of the first recycled aggregate through at least one camera; Inputting a dataset related to the first image into a first artificial intelligence (AI) model to obtain information on foreign substances in the first recycled aggregate; and Based on the information regarding foreign substances in the first recycled aggregate, that the amount of foreign substances contained in the first recycled aggregate is less than a first threshold value, the opening and closing device related to the movement of the first recycled aggregate is configured to be controlled so that the first recycled aggregate is loaded into a first area. The data set associated with the first image includes the first image and first lighting information associated with the first image, and The first lighting information includes the intensity of the light source at the time when the first image is captured, the angle of incidence of light incident on the first recycled aggregate, and the type of light source. controller.

Description

Method and device for performing circular aggregate foreign matter sorting operation based on a deep learning algorithm The present disclosure relates to a foreign substance sorting technology, and more specifically, to a method and apparatus for performing a foreign substance sorting operation on recycled aggregate based on a deep learning algorithm. This invention is a result carried out with support from the 'Eco-Startup Support Program' promoted by the Ministry of Environment and operated by the Korea Environmental Industry & Technology Institute. (Project No.: RT2025020828) In conventional construction waste intermediate treatment processes, a method is generally adopted in which construction waste of various characteristics collected from demolition work and other sources is mixed and fed into a single plant for crushing and sorting. In this process, waste is crushed to a size smaller than a certain threshold using a large crusher, and then recyclable resources are extracted by sequentially performing manual sorting, specific gravity separation by wind power, metal separation by magnetic force, and sieve separation based on particle size differences. However, the conventional processing method described above has fundamental limitations. Fine foreign substances of 25 mm or less generated during the crushing process are difficult to accurately separate using only the physical sorting method described above, and this results in problems such as the mixing of impurities into the final sorted material or the deterioration of the quality of recycled resources. In particular, fine particles generated from mixtures of concrete, synthetic resins, vinyl, wood, and fibers often have similar properties and densities, making them difficult to effectively remove using conventional wind or magnetic separation equipment. Due to these limitations, there were problems that hindered the resource circulation rate, such as the low quality of final recycled products and the re-landfilling or incineration of some unsorted waste. FIG. 1 is a drawing for explaining a system that performs a sorting operation of foreign substances in recycled aggregate based on a deep learning algorithm according to one embodiment of the present disclosure. FIG. 2 is a diagram illustrating the configuration of a control device that performs a sorting operation of foreign substances in recycled aggregate based on a deep learning algorithm according to one embodiment of the present disclosure. FIGS. 3 and 4 are drawings for explaining a method of performing a sorting operation of foreign substances in recycled aggregate based on a deep learning algorithm according to one embodiment of the present disclosure. The advantages and features of the present disclosure and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present disclosure 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 is complete and to fully inform those skilled in the art of the scope of the present disclosure, and the present disclosure is defined only by the scope of the claims. The terms used herein are for describing the embodiments and are not intended to limit the disclosure. In this specification, the singular form includes the plural form unless specifically stated otherwise in the text. As used herein, "comprises" and/or "comprising" do not exclude the presence or addition of one or more other components in addition to the components mentioned. Throughout the specification, the same reference numerals refer to the same components, and "and/or" includes each of the mentioned components and all combinations of one or more thereof. Although terms such as "first," "second," etc., are used to describe various components, they are not limited by these terms. These terms are used merely to distinguish one component from another. Accordingly, the first component mentioned below may be the second component within the technical scope of this disclosure. Unless otherwise defined, all terms used herein (including technical and scientific terms) may be used in a meaning commonly understood by those skilled in the art to which this disclosure pertains. Additionally, terms defined in commonly used dictionaries are not to be interpreted ideally or excessively unless explicitly and specifically defined otherwise. Spatially relative terms such as "below," "beneath," "lower," "above," and "upper" may be used to easily describe the relationship between one component and another, as illustrated in the drawings. Spatially relative terms should be understood as encompassing the different directions of the components during use or operation, in addition to the directions depicted in the drawings. For example, if a component depicted in a drawing is inverted, a componen