System, device and method for controlling the welding of a secondary battery based on artificial intelligence

Abstract

The present disclosure provides a system, apparatus, and method for controlling welding based on artificial intelligence. The artificial intelligence-based welding control system according to an embodiment of the present disclosure may include a machine vision system configured to photograph at least a part of a welding object through a camera and transmit the photographed image (hereinafter, "photographic image") to a relay system;The relay system is configured to receive the photographic image from the machine vision system, detect a welding position of the welding object from the received photographic image based on a pre-trained first artificial intelligence model, determine whether the detected welding position is included in a specific position range, and, if the detected welding position is included in the specific position range, transmit the detected welding position to a welding system; and the welding system is configured to receive the welding position from the relay system and perform welding at the received welding position.

Claims

[1] A welding control system based on artificial intelligence, the system comprising: a machine vision system configured to photograph at least part of a welding object through a camera and transmit the photographed image (hereinafter ‘photographic image’) to a relay system; the relay system is configured to receive the photographic image from the machine vision system, detect a welding position of the welding object from the received photographic image based on a pre-trained first artificial intelligence model, determine whether the detected welding position is included in a designated position range, and, if the detected welding position is included in the designated position range, transmit the detected welding position to a welding system; and the welding system is set up to receive the welding position from the relay system and perform the welding at the received welding position. [2] The system according to claim 1, wherein the relay system triggers an alarm when the detected welding position is not included in the designated position range or the welding position is not detected from the photographic image. [3] The system according to claim 1, wherein the relay system requests the machine vision system to identify a welding position when the detected welding position is not included in the designated position range or the welding position is not recognized from the photographic image, and when identification of the welding position is requested, the machine vision system identifies the welding position from the photographic image, determines whether the identified welding position is included in the designated position range, and if the identified welding position is included in the designated position range, transmits the identified welding position to the welding system. [4] The system of claim 3, wherein the machine vision system triggers an alarm if the identified welding position is not included in the designated position range or the welding position is not identified from the photographic image. [5] The system according to any one of claims 1 to 4, wherein the machine vision system attempts to identify a welding position from the photographic image after photographing at least a part of the welding object, and, if the welding position is not identified from the photographic image or the identified welding position is not included in the designated position range, transmits the photographic image to the relay system. [6] The system of claim 5, wherein the machine vision system communicates the identified welding position to the welding system if the identified welding position is included in the designated position range. [7] The system of any one of claims 1 to 4, wherein the relay system extracts a region of interest from the photographic image based on a pre-trained second artificial intelligence model and transmits information about the extracted region of interest to the machine vision system, and the machine vision system identifies a welding position within the region of interest of the photographic image and transmits the identified welding position to the welding system. [8] The system according to any one of claims 1 to 4, further comprising a checking system configured to check whether a welding defect exists after the welding is performed and, if the welding defect exists, to transmit welding defect information to the relay system, wherein the relay system updates the first artificial intelligence model based on the welding defect information. [9] System according to one of claims 1 to 4, wherein the relay system comprises: an artificial intelligence server comprising the first artificial intelligence model; and a relay server configured to relay communication between the machine vision system, the welding system, and the artificial intelligence server. [10] The system according to any one of claims 1 to 4, wherein the welding object comprises a secondary battery, and the welding position comprises an edge of an electrode of the secondary battery. [11] A method for controlling welding based on artificial intelligence, the method comprising: Photographing at least part of the welding object by a camera and transmitting the photographed image (hereinafter “photographic image”) to a relay system by a machine vision system; Receiving the photographic image from the machine vision system, recognizing a welding position of the welding object from the received photographic image based on a pre-trained first artificial intelligence model, determining whether the recognized welding position is included in a designated position range, and if the recognized welding position is included in the designated position range, transmitting the recognized welding position to a welding system through the relay system; Receiving the welding position from the relay system and performing welding at the received welding position by the welding system. [12] The method of claim 11, further comprising the relay system triggering an alarm when the detected welding position is not included in the designated position range or the welding position is not detected from the photographic image. [13] The method of claim 11, further comprising: If the detected welding position is not included in the designated position range or the welding position is not recognized from the photographic image, request the machine vision system to identify a welding position through the relay system; and if identification of the welding position is requested, identifying the welding position from the photographic image, determining whether the identified welding position is contained within the intended position range, and if the identified welding position is contained within the intended position range, communicating the identified welding position to the welding system through the machine vision system. [14] The method of claim 13, further comprising generating an alarm by the machine vision system when the detected welding position is not within the intended position range or the welding position is not recognized from the photographic image. [15] A method according to any one of claims 11 to 14, further comprising attempting to identify a welding position from the photographic image after at least part of the welding object has been photographed by the machine vision system, wherein the step of transmitting the photographic image to the relay system is performed when the welding position is not identified from the photographic image or the identified welding position is not included in the designated position range. [16] The method of claim 15, further comprising transmitting the identified welding position to the welding system through the machine vision system when the identified welding position is within the designated position range. [17] A method according to any one of claims 11 to 14, further comprising: Extracting a region of interest from the photographic image based on a pre-trained second artificial intelligence model, and transmitting information about the extracted region of interest to the machine vision system through the relay system; and Identifying a welding position within the area of interest of the photographic image and transmitting the identified welding position to the welding system through the machine vision system. [18] A method according to any one of claims 11 to 14, further comprising: Verification of the presence of a welding defect by a testing system after welding has been carried out; if the welding defect is present, transmitting welding defect information to the relay system; and Updating the first artificial intelligence model based on the welding defect information by the relay system. [19] Device for controlling welding based on artificial intelligence, the device comprising: a camera; a memory containing a pre-trained artificial intelligence model; a welding module; and a processor configured to control the camera to photograph at least a part of a welding object, to detect a welding position from the image photographed by the camera (hereinafter "photographic image") based on the artificial intelligence model, to determine whether the detected welding position is included in a designated position range, and, if the detected welding position is included in the designated position range, to control the welding module to weld the detected welding position. [20] The apparatus according to claim 19, further comprising a checking module, wherein the processor determines through the checking module whether a welding defect exists after performing the welding, and if the welding defect exists, updates the artificial intelligence model based on the welding defect information

Images