Weld Pool Ripple Detection for Stable Welding Parameter Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional welding technologies face challenges in suppressing defects such as sputtering and pits, particularly due to the formation of ripples in the weld pool, which indicate an unstable welding state.
Innovation Solution
A processing device determines the stability of the weld pool by analyzing images using pixel value fluctuations or machine learning models, correcting welding parameters such as voltage, current, and shielding gas flow rate when ripples are detected, to maintain a more stable weld state.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If welding parameters are continuously adjusted based on real-time monitoring, then weld quality and stability are improved, but system complexity and processing time increase
Solution Approach 1:
The system implements real-time feedback by monitoring weld pool images during welding and automatically adjusting welding parameters based on detected ripple states. The control unit receives image data, determines ripple conditions, and modifies welding parameters accordingly, creating a closed-loop control system that improves weld quality while managing complexity through automated decision-making algorithms.
Solution Approach 2:
The welding system performs self-diagnosis and self-adjustment by automatically detecting weld pool instability through image analysis and correcting its own welding parameters without external intervention. The system monitors its own performance in real-time and makes autonomous corrections to maintain optimal welding conditions.
2Stability of the object's composition
If real-time image analysis is performed to detect weld pool ripples, then weld stability is improved, but processing speed and time consumption increase
Solution Approach 1:
The system performs partial image analysis by focusing only on critical features of the weld pool (such as ripple detection in specific regions) rather than analyzing the entire image in detail. This selective approach allows real-time detection of instability conditions while maintaining welding speed, applying excessive action only where necessary for quality control.
Solution Approach 2:
The system establishes predetermined thresholds and decision criteria for ripple detection before welding begins. By pre-programming the conditions that indicate instability and the corresponding parameter adjustments, the system eliminates complex real-time calculations and enables rapid automated responses that maintain both weld stability and production speed.
Data Source
AI summary
According to one embodiment, a processing device performs at least determination processing of determining a state of a weld by using a first image of at least a portion of a weld pool. The state includes a first state, and a second state that is more unstable than the first state. The determination processing determines the weld to be in the second state when ripples exist in the weld pool. The processing device corrects a condition of the weld when the weld is determined to be in the second state. The processing device does not correct the condition of the weld when the weld is determined to be in the first state.