Unlock instant, AI-driven research and patent intelligence for your innovation.

A real-time intelligent detection method and system for universal welding arc initiation

An intelligent detection and real-time detection technology, which is applied in manufacturing computing systems, testing dielectric strength, machine learning, etc., can solve problems such as inability to detect arcing, welding consistency problems, and potential defects, so as to avoid signal Communication and cloud processing, high accuracy, high universality effect

Active Publication Date: 2022-05-31
苏芯物联技术(南京)有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In terms of welding quality, frequent arcing will cause welding consistency problems, resulting in too many welded joints, and more likely to have hidden defects; on the other hand, the arcing process can reflect the ability of welders, and has important implications for process and personnel performance evaluation. very important
[0004] The current arc detection methods generally rely on welding machines or robot-specific hardware, and the middle and low-end welding machines with a huge stock of low-end welding machines cannot achieve accurate arc detection if they do not have similar hardware.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A real-time intelligent detection method and system for universal welding arc initiation
  • A real-time intelligent detection method and system for universal welding arc initiation
  • A real-time intelligent detection method and system for universal welding arc initiation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The preferred embodiments of the present invention will be described below in conjunction with the accompanying drawings, and the present invention will be described more clearly and completely.

[0044] Step 1.1: The high-frequency current collected is constructed by a sliding window according to 1s (sampling frequency is F), and passes the threshold

[0046] Step 1.3: randomly shuffle (out of order) all the samples generated, and set the proportion of training samples train_

[0057] D, the maximum value of the current at the last K points in the previous second, preferably K=200 in the embodiment.

[0062] welding_before: the welding state of the previous second, the existence of welding is 1, and the standby is 0;

[0064] c_200point_last_max: the maximum value of the last 200 point currents in the previous second;

[0070] After the model is deployed, real-time detection of arcing events is performed on the new high-frequency current data.

[0075] 2) The feature calcul...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a real-time intelligent detection method and system for universal welding arc starting. The method includes: firstly, performing sliding window sampling and sample screening on collected high-frequency current data, and marking the selected samples with arc starting state; Thereby, a data sample set is generated; feature construction is performed on the generated data samples to obtain the feature set of each sample; combined with the constructed feature set, the machine learning classification algorithm is used for model training, and the detection model of the arcing event is obtained; The detection model of the new high-frequency current data performs real-time detection of arcing events. The invention adopts a low-cost current sensor to collect the current data in the welding process in real time, and based on the meticulous research on the real industrial welding arc starting data, a characteristic algorithm based on the arc starting signal mechanism is designed, which can realize more than one hundred kinds of welding machines. It has high universality, accuracy and practicability to accurately describe the arcing state in the complex state.

Description

A real-time intelligent detection method and system for universal welding arc starting technical field The present invention relates to a kind of universal welding arc starting real-time intelligent detection method and system, belonging to the field of intelligent welding technology. area. Background technique [0002] Intelligent welding is one of the most important research topics in the field of intelligent manufacturing. Sensing technology and its information processing It is the key element to realize the intelligence and automation of the welding process. In recent years, with miniaturization, non-contact and large transmission capacity Sensing technologies with characteristics such as these are more applied to the welding process and real-time quality control, but more attention is focused on the welding process. In terms of welding defect detection, there is currently no detection technology for welding arcing events through sensor data. In real industrial...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06N20/00G01R31/12
CPCY02P90/30
Inventor 田慧云李波朱毛赛姚志豪王祖明
Owner 苏芯物联技术(南京)有限公司