KR-20260063639-A - Foreign matter detection system in mold

KR20260063639AKR 20260063639 AKR20260063639 AKR 20260063639AKR-20260063639-A

Abstract

The present invention relates to a mold foreign substance detection system capable of detecting a dent defect in a molded product by detecting a foreign substance located in a press mold during press forming of a metal sheet. The system may include at least one of a first mold and a second mold installed facing each other with the metal sheet in between to enable press forming of the metal sheet, a load sensor unit for measuring a load value applied to a molding mold including the first mold and the second mold during press forming of the metal sheet, and a control unit for detecting a foreign substance between the first mold and the second mold by comparing the change in the load value applied to the molding mold from the load sensor unit in real time during press forming of the metal sheet, a mold load pattern signal patterned in the form of a graph of the change in the load value applied in real time, and a reference pattern signal stored in advance with the mold load pattern signal.

Inventors

배기현
송정한
이종섭
박남수
김민기

Assignees

한국생산기술연구원

Dates

Publication Date: 20260507
Application Date: 20241030

Claims (15)

A load sensor unit for measuring a load value applied to a forming mold including the first mold and the second mold, wherein at least one is installed in either a first mold and a second mold installed facing each other with the metal plate in between so as to press-form the metal plate, and during press-forming of the metal plate; and A control unit that, during press forming of the metal plate, receives the load value applied to the forming mold from the load sensor unit in real time, calculates a mold load pattern signal by patterning the change of the load value received in real time into a graph form, and detects foreign matter between the first mold and the second mold by comparing the mold load pattern signal with a previously stored reference pattern signal; A mold foreign substance detection system including
In Article 1, The above control unit is, A mold foreign substance detection system that pre-calculates and stores a pattern signal, which is a graph-shaped pattern of the change in load value when there is no foreign substance between the first mold and the second mold in a normal state, as a reference pattern signal.
In Article 2, The above control unit is, A mold foreign substance detection system that determines whether a foreign substance exists between the first mold and the second mold used for press forming the metal sheet by comparing the mold load pattern signal calculated in real time with the reference pattern signal during press forming of the metal sheet.
In Paragraph 3, The above control unit is, A mold foreign substance detection system that determines the size of a foreign substance existing between the first mold and the second mold based on the difference between the peak value of the reference pattern signal and the peak value of the mold load pattern signal.
In Article 4, The above control unit is, A mold foreign substance detection system that determines the location of a foreign substance existing between the first mold and the second mold based on the difference between the time when the peak value of the reference pattern signal occurs and the time when the peak value of the mold load pattern signal occurs.
In Article 5, The location of the foreign substance determined by the above control unit is, A mold foreign substance detection system, wherein the distance information from the load sensor unit to the foreign substance existing between the first mold and the second mold.
In Article 2, The above control unit is, A mold foreign substance detection system that stores in advance a foreign substance detection algorithm calculated by mechanically learning by artificial intelligence the pattern characteristics of the above reference pattern signal and the pattern characteristics of pattern signals that are patterned in a graph form, which represent changes in load values that may occur differently depending on the size and location of the foreign substance existing between the first mold and the second mold.
In Article 7, The above control unit is, A pattern signal collection unit that, during press forming of the metal plate, collects the load value applied in real time from the load sensor unit, outputs the mold load pattern signal by patterning the change in strength of the collected load value into a graph form, and extracts the pattern characteristics of the mold load pattern signal; and A foreign substance detection unit that determines the presence of foreign substances and the size and location of foreign substances by applying the foreign substance detection algorithm to the pattern characteristics of the mold load pattern signal extracted from the pattern signal collection unit; A mold foreign substance detection system including
In Article 8, The above pattern signal collection unit is, A Fast Fourier Transform (FFT) is applied to the mold load pattern signal, which patterns the change in strength of the load value over time in the form of a graph, to obtain an FFT transformed image that represents the frequency components and magnitudes occurring over time in the form of an image map, and pattern characteristics are extracted from the FFT transformed image. The above foreign substance detection unit is, A mold foreign substance detection system that determines the presence of foreign substances and the size and location of foreign substances by applying the foreign substance detection algorithm to the pattern characteristics of the above FFT transformed image.
In Article 9, The above foreign substance detection algorithm is, A mold foreign substance detection system that is calculated by learning the pattern characteristics of FFT learning images obtained by the Fast Fourier Transform, using the above reference pattern signal and pattern signals that are patterned in a graph form of the change in load value that may occur differently depending on the size and location of the foreign substance existing between the first mold and the second mold.
In Article 10, The above foreign substance detection algorithm is, A foreign substance detection system for a mold, comprising an algorithm in which a Prince Component Analysis (PCA) algorithm and a Support Vector Machine (SVM) algorithm are sequentially executed to reduce the dimensionality of a dataset of FFT training images to extract pattern features, and to classify and distinguish the extracted pattern features.
In Article 5, The above load sensor unit is, A plurality of load sensors arranged along the perimeter of the forming area of the metal plate in the first mold or the second mold; A mold foreign substance detection system including
In Article 12, The above control unit is, A mold foreign substance detection system that determines the size and location of a foreign substance existing between the first mold and the second mold through correlation analysis of mold load pattern signals, which are each calculated in real time by load values applied from each of the plurality of load sensors during press forming of the metal plate.
In Article 12, The above plurality of load sensors are, A foreign substance detection system for a mold, wherein four units are arranged radially with respect to the center of the forming area of the metal plate so as to be arranged along the perimeter of the forming area of the metal plate.
In Article 1, The above load sensor unit is, A bolt-type load sensor formed in the shape of a bolt and coupled to the first mold or the second mold; A mold foreign substance detection system including

Description

Foreign matter detection system in mold The present invention relates to a foreign substance detection system for a mold, and more specifically, to a foreign substance detection system for a mold capable of detecting a foreign substance located in a press mold during press forming of a metal sheet and detecting a dent defect in a molded product. Press processing is a type of plastic processing that can form a product having a predetermined shape by using a press forming device to cut or change the shape of the material, mainly in the form of a plate, thereby deforming the shape of the material. For example, it can be processed into various forms of material such as shearing, punching, trimming, bending, burring, curling, and drawing. In such a press forming device, raw materials such as sheet metal are placed between the upper and lower molds of the internally mounted molding die, and the upper mold is pressed against the lower mold and then pressed to form a product. Due to the characteristics of this press forming device, once mass production conditions are set, the device operates continuously under consistent conditions; however, if foreign substances enter between the molding dies during press forming, dent defects may occur in the molded product, which can lead to quality variations in mass-produced products. As such, conventional press forming devices had the problem that it was impossible to check in real time during the mass production process whether foreign substances had entered between the forming dies. Consequently, the presence of foreign substances had to be confirmed by visually inspecting the final product to check for dents, or the process had to be stopped periodically to inspect the inside of the press dies. FIG. 1 is a cross-sectional view schematically illustrating a foreign substance detection system of a mold according to one embodiment of the present invention. FIGS. 2 and FIGS. 3 are cross-sectional views schematically showing a load sensor unit installed in the molding die of the press forming device of FIG. 1. Figure 4 is an image schematically showing the algorithm configuration of the foreign substance detection system of a mold. Figure 5 is a block diagram schematically showing the configuration of the control unit of the foreign substance detection system of a mold. FIG. 6 is a graph showing various embodiments of a mold load pattern signal in which the change in load value applied from the load sensor unit is patterned in the form of a graph. Figure 7 is a graph showing various embodiments of mold load pattern signals calculated according to the location of foreign substances present in the molding die. FIG. 8 is a graph and images showing an example of converting a mold load pattern signal into an FFT transformed image. FIG. 9 shows images representing various embodiments of FFT transformed images calculated according to the location of foreign substances present in the molding die. Figure 10 is an image schematically showing the configuration of a foreign substance detection algorithm. FIGS. 11 and 12 are images and graphs showing embodiments for determining the size and location of foreign substances through correlation analysis of mold load pattern signals calculated from a plurality of load sensors installed in a molding mold. Hereinafter, several preferred embodiments of the present invention will be described in detail with reference to the attached drawings. The embodiments of the present invention are provided to more fully explain the invention to those skilled in the art, and the following embodiments may be modified in various different forms, and the scope of the invention is not limited to the following embodiments. Rather, these embodiments are provided to make the disclosure more faithful and complete and to fully convey the spirit of the invention to those skilled in the art. In addition, the thickness or size of each layer in the drawings is exaggerated for convenience and clarity of explanation. Hereinafter, embodiments of the present invention are described with reference to drawings that schematically illustrate ideal embodiments of the present invention. In the drawings, variations of the illustrated shapes may be expected, for example, depending on manufacturing techniques and/or tolerances. Accordingly, embodiments of the inventive concept should not be interpreted as being limited to specific shapes of the areas illustrated herein, but should include, for example, variations in shape resulting from manufacturing. FIG. 1 is a cross-sectional view schematically showing a foreign substance detection system (1000) of a mold according to an embodiment of the present invention, FIG. 2 and FIG. 3 are cross-sectional views schematically showing a load sensor unit (100) installed in a molding mold (M) of a press molding device of FIG. 1, FIG. 4 is an image schematically showing the overall algorithm configuration of the foreign substance detection system (10