# US 2020/0348660 A1 · System and method for managing welding gun

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2020/0348660 A1
- Document ID: US20200348660A1
- Status: Published application
- Kind: A1
- Application number: 16/667,493
- Filed: 2019-10-29
- Published: 2020-11-05
- Earliest claimed: 2019-05-03
- Assignees: Hyundai Motor Company; Kia Motors Corporation
- Applicants: Hyundai Motor Company; Kia Motors Corporation
- Inventors: Daewon LEE
- Web page: https://patentgrep.com/patent/US20200348660A1

## CPC

- B23K 11/3063: {Electrode maintenance, e.g. cleaning, grinding}
- B23K 9/0953: {using computing means}
- B23K 11/252: {using digital means}
- B23K 11/3072: {Devices for exchanging or removing electrodes or electrode tips}
- B23K 11/314: {Spot welding guns, e.g. mounted on robots}
- B23K 31/006: {relating to using of neural networks}
- G05B 23/024: {Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks}
- G06F 18/2413: based on distances to training or reference patterns
- B23K: SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A system managing a polishing state of tips of a welding gun of each welding robot installed in a production line of a vehicle includes: a robot controller storing tip polishing data including the number of polishing of the tips and a polishing amount of the tips generated after each tip dressing of the welding gun; and a server collecting the tip polishing data from the robot controller to store the collected data according to robot identification information of the robot and learning the store data through artificial neural network to generate reference data determining the polishing state of the tips corresponding to the robot identification information. The robot controller sets artificial neural network of the robot based on the reference data and determines whether a polishing state of the tips according to the number of polishing and the polishing amount of the tips is normal.

## Claims

### Claim 1

A system for managing a polishing state of tips of a welding gun of each welding robot installed in a production line of a vehicle, comprising:
a robot controller configured to store tip polishing data including a number of polishing the tips and a polishing amount of the tips that are generated after each tip dressing of the welding gun in a table; and
a server configured to:
collect the tip polishing data from the robot controller;
store the collected tip polishing data based on robot identification information of the welding robot; and
learn the stored tip polishing data through an artificial neural network to generate reference data that determines the polishing state of the tips corresponding to the robot identification information,
wherein the robot controller is further configured to:
set an artificial neural network of the robot based on the reference data; and
determine whether the polishing state of the tips based on the number of polishing the tips and the polishing amount of the tips is normal.

### Claim 2 (depends on 1)

The system of claim 1, wherein:
the reference data includes an artificial neural network setting parameter information that determines the polishing state of the tips based on a space between the tips corresponding to the number of polishing and an increase amount of the space between the tips as normal, excessive, or insufficient, and
the space between the tips and the increase amount of the space is determined based on a start position of replaced tips of the welding gun measured in a state where the tips are in contact with a measurement plate between the tips.

### Claim 3 (depends on 1)

The system of claim 1, wherein the welding gun comprises:
a gun arm installed on one surface of a bracket that is mounted on an end-effector of the welding robot;
a fixed tip that is an electrode that is in contact with one side of a base material and that is fixedly mounted on a holder of the gun arm;
a moving tip that is an electrode that is in contact with another side of the base material and that is mounted on an adaptor formed on another side of the gun arm such that the moving tip is capable of moving in a forward direction and a backward direction; and
a servo motor that is operated based on an applied control signal and configured to:
move the moving tip in the forward direction or the backward direction and;
measure a moving distance of the moving tip based on an amount of rotation of the servo motor.

### Claim 4 (depends on 1)

The system of claim 1, wherein the robot controller further comprises:
a communication device configured to:
match the tip polishing data with the robot identification information;
transmit, to the server, the matched tip polishing data; and
receive, from the server, the reference data;
a data collection device configured to collect the tip polishing data of the tips measured in the state where the tips are in contact with a measurement plate between the tips;
an artificial intelligence device configured to:
calculate the collected tip polishing data using the artificial neural network to which the reference data is applied; and
determine whether the polishing amount of the tips is normal, insufficient, or excessive;
a storage device configured to cumulatively store the collected tip polishing data in the table; and
a control device configured to reduce a pressure and a time of polishing the tips performed by the welding robot when it is determined that the polishing amount of the tips is excessive.

### Claim 5 (depends on 4)

The system of claim 4, wherein the data collection device is configured to:
collect a start position of replaced tips of the welding gun when a moving tip of the tips is moved to an upper surface of the measurement plate by a servo motor in a state where a fixed tip of the tips is fixed to a lower surface of the measurement plate after the tips are replaced; and
store the collected position in the table.

### Claim 6 (depends on 5)

The system of claim 5, wherein the tip polishing data includes at least one of the start position of both ends of the tips, the number of polishing of the replaced tips, a space between the tips due to polishing of the replaced tips measured at a current position of the tips, or an increase amount of the space between the tips.

### Claim 7 (depends on 6)

The system of claim 6, wherein the current position is a position of a currently polished tips of the welding gun and has the space between the tips increased as much as the polishing amount of the tips in a state where the welding robot is set to the same attitude control as attitude control for the start position.

### Claim 8 (depends on 5)

The system of claim 5, wherein:
a polishing amount of the moving tip is a moving distance that the moving tip moves to the upper surface of the measurement plate, and
a polishing amount of the fixed tip is a value obtained by subtracting the polishing amount of the moving tip from the polishing amount of the tips.

### Claim 9 (depends on 4)

The system of claim 4, wherein the control device is configured to:
generate an emergency event to stop the welding robot; and
transmit the emergency event to the server to alert an operator of the system of the emergency event when underestimation of the polishing amount of the tips is repeated over a predetermined number of times.

### Claim 10 (depends on 4)

The system of claim 4, wherein the control device is configured to:
calculate a remaining length of a fixed tip of the tips and the moving tip of the tips based on each tip dressing; and
alert the server of replacement time of the tips when the remaining length is less than a valid reference value.

### Claim 11 (depends on 1)

The system of claim 1, wherein the server comprises:
a communicator configured to:
receive the tip polishing data periodically collected by the robot controller; and
transmit the reference data to the robot controller;
a data manager configured to generate classification data for artificial intelligence based the collected tip polishing data;
an artificial intelligence learning device configured to:
calculate the classification data through the the artificial intelligence; and
generate the reference data to determine the polishing state of the tips of each welding robot;
a database configured to store the tip polishing data, the classification data, and the reference data corresponding to the robot identification information;
a graphic generation device configured to display the polishing state of the tips of each welding robot based on data stored in the database through a graph so that an operator of the system checks the polishing state of the tips of each welding robot; and
a controller configured to:
transmit a weight and a bias of the reference data to each robot controller corresponding to the robot identification information; and
update a state of the artificial neural network.

### Claim 12 (depends on 11)

The system of claim 11, wherein the data manager is configured to:
generate abnormal data equivalent to the number of normal data corresponding to the tip polishing data by using accumulated abnormal data or setting information of the operator.

### Claim 13 (depends on 11)

The system of claim 11, wherein the artificial intelligence learning device is configured to:
set the reference data as two layers using open-source software used for machine learning; and
adjust parameter values set in the weight and the bias of each of the layers.

### Claim 14

A method for managing a polishing state of tips of a welding gun of each welding robot installed in a production line of a vehicle, comprising:
a) setting, by a robot controller, an artificial neural network for determining the polishing state of the tips of the welding gun based on reference data received from the server;
b) setting, by the robot controller, a space between replaced tips of the welding gun measured in a state where the replaced tips are in contact with a measurement plate between the tips as a start position;
c) measuring, by the robot controller, tip polishing data including a number of polishing the tips and a polishing amount of the tips that are generated after each tip dressing of the welding gun in a state where the tips are in contact with the measurement plate, wherein the polishing amount of the tips is determined based on the start position; and
d) computing, by the robot controller, the measured tip polishing data through the set artificial neural network to determine whether the polishing state of the tips is normal.

### Claim 15 (depends on 14)

The method of claim 14, wherein the method further comprises:
matching, by the robot controller, the polishing data regarding the tips accumulated in a table for a predetermined amount of time with robot identification information of the welding robot to transmit the matched tip polishing data to the server; and
receiving, by the robot controller, the reference data derived by learning the polishing data regarding the tips though an artificial intelligence of the server.

### Claim 16 (depends on 14)

The method of claim 14, wherein the step c) comprises:
measuring, by the robot controller, the tip polishing data based on a moving distance of a moving tip of the tips.

### Claim 17 (depends on 14)

The method of claim 14, wherein the step d) comprises:
determining, by the robot controller, whether the polishing amount of the tips is normal, excessive, or insufficient.

### Claim 18 (depends on 17)

The method of claim 17, wherein the step d) comprises:
adjusting, by the robot controller, the excessive polishing amount to a normal range by reducing a pressure and a time of polishing of the tips when the polishing amount of the tips is determined to be excessive.

### Claim 19 (depends on 17)

The method of claim 17, wherein the step d) comprises:
adjusting, by the robot controller, a deficient polishing amount of the tips to a normal range through a re-polishing when the polishing amount of the tips is determined to be insufficient; and
generating, by the robot controller, an emergency event to stop the production line and to transmit the emergency event to the server to alert an operator of the emergency event when the polishing amount of the tips is determined to be insufficient over a predetermined number of times.

### Claim 20 (depends on 17)

The method of claim 17, wherein the step d) comprises:
when the polishing amount of the tips is within a normal range, recording, by the robot controller, the polishing amount of the tips in a table;
calculating, by the robot controller, current positions of both ends of the tips to calculate a remaining tip length of the tips as compared to a new product; and
alerting, by the robot controller, the server of replacement time of the tips when the remaining tip length is less than a valid reference value.
