Pipe Welding Seam Tracking With Vision-Based Stitch Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for tracking welding seams in pipe welding, such as those using laser scanners, lack precision and require improved monitoring and automatic adjustment of welding parameters.

Innovation Solution

A robotic welding system with a camera attached to a torch arm continuously captures and processes frames to detect seam positions, stitch starts, and stitch ends, adjusting welding parameters accordingly to ensure precise tracking and quality control during spool welding operations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If laser scanners are used for seam tracking, then the welding operation can be automated, but the precision of seam tracking is limited

Engineering Contradiction:
Improveseam tracking precisionVSAvoidimaging system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces traditional mechanical laser scanners with a vision-based system using cameras and image processing algorithms. The camera captures images of the weld seam, and software processes these images to determine seam position and guide the welding torch, substituting mechanical scanning with optical detection and computational analysis.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system creates a visual copy (image) of the weld seam and processes this copy to determine seam position. Instead of directly measuring with mechanical sensors, the system captures an optical replica of the seam and uses image processing to extract positioning information from this copy.

Inventive Principle:
Principle #26Copying

2Device complexity

If passive vision systems are used for seam tracking, then device complexity is reduced, but measurement precision may be insufficient for thin plate closed-gap welding

Engineering Contradiction:
Improvevision system complexityVSAvoidseam tracking precision
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The system performs preliminary positioning by detecting the weld seam before actual welding begins. The vision system captures images and processes them to determine the seam position in advance, allowing the welding torch to be accurately positioned before the welding operation starts, which is particularly important for thin plate closed-gap welding.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system continuously monitors the weld seam position during welding and provides real-time feedback to adjust the torch position. The vision system captures images throughout the welding process, processes them to determine current seam position, and uses this information to correct any deviations from the intended weld path.

Inventive Principle:
Principle #23Feedback

3Extent of automation

If real-time image processing is implemented for seam tracking, then welding parameter adjustment can be automated, but processing time and computational resources increase

Engineering Contradiction:
Improvewelding parameter automationVSAvoidimage processing time
Core Design Contradiction:
Extent of automationVSLoss of time

Solution Approach 1:

The system processes only the necessary portions of the captured images to determine seam position and welding parameters. Rather than analyzing entire images or all possible features, the system focuses on extracting only the critical seam position information needed for control, reducing computational burden while maintaining automation.

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The vision system captures and processes images at periodic intervals during welding rather than continuously. This periodic sampling provides sufficient information for parameter adjustment while reducing the total computational load and processing time required compared to continuous real-time analysis.

Inventive Principle:
Principle #19Periodic action

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This method enhances precision in seam tracking and welding parameter adjustment, achieving accurate and consistent welds with improved precision and efficiency in pipe welding operations.

Implementation Method 1

a camera positioned to capture images of an area around a welding arc

Methodology Applied
Scientific EffectLight reflection: Reflection

Data Source

PatentEP3749475B1Method for seam tracking in pipe welding
Publication Date: 2023.11.01 NOVARC TECH INC
  • EP3749475B1 patent drawingFigure 1~2
  • EP3749475B1 patent drawingFigure 2A
  • EP3749475B1 patent drawingFigure 3

AI summary

The present disclosure provides a method for controlling a robotic welding system to weld pipe sections wherein the pipe sections are held in fixed relation to each other by a plurality of stitches at a seam between the pipe sections. The method comprises rotating the pipe sections so a camera may determine the seam position, moving a torch arm and welding torch so that the torch is over one of the plurality of stitches, adjusting welding parameters and determining stitch start when welding torch is over a stitch and further adjusting welding parameters and determining stitch end when welding torch moves past one of the plurality of stitches.