Nondestructive Evaluation (NDE) and Quality Monitoring of Resistant Spot Welding Based on Quantitative Ultrasonic Technique

2001 ◽  
Author(s):  
Roman Gr. Maev
Keyword(s):  
Nondestructive Evaluation ◽  
Spot Welding ◽  
Quality Monitoring ◽  
Ultrasonic Technique

scholarly journals Correlation between Peel Test and Real Time Ultrasonic Test for Quality Diagnosis in Resistance Spot Welding

2016 ◽  
Vol 21 (3) ◽  
pp. 282-289 ◽  
Author(s):  
Angelo F. Andreoli ◽  
Andriy M. Chertov ◽  
Roman Gr. Maev
Keyword(s):  
Nondestructive Evaluation ◽  
Real Time ◽  
Spot Welding ◽  
Peel Test ◽  
Ultrasonic Test ◽  
Welding Time ◽  
Test Results ◽  
Industrial Environment ◽  
Quality Diagnosis ◽  
Potential Use

Abstract: This paper aimed to study the correlation between Real Time Integrated Weld Analyzer measurements and peel test results. The experiment involved study of weld nuggets for different combinations of sheet thicknesses, welding time and current of mild steel samples. The intent was to assess the potential use of a real time integrated ultrasonic system in the industrial environment allowing nondestructive evaluation of 100% of the spot welds produced. The results showed high correlation between nugget penetration into the sheets and nugget size measured ultrasonically and destructively, for all evaluated parameters.

Quality monitoring of spot welding with advanced signal processing and data-driven techniques

2017 ◽  
Vol 40 (7) ◽  
pp. 2291-2302 ◽  
Author(s):  
Xing-Jue Wang ◽  
Jun-Hong Zhou ◽  
Heng-Chao Yan ◽  
Chee Khiang Pang
Keyword(s):  
Signal Processing ◽  
Heat Affected Zone ◽  
Spot Welding ◽  
Quality Monitoring ◽  
Self Organizing Map ◽  
Size Estimation ◽  
Welding Quality ◽  
Quality Estimation ◽  
Quality Classification ◽  
Self Organizing

As resistance spot welding is a crucial and widely used metal joining technique nowadays, a cheap and highly accurate online quality monitoring scheme is strongly demanded in industry. In this paper, a novel framework for welding quality examination is proposed by using advanced signal processing and artificial intelligence techniques. Our proposed framework consists of two objective schemes, a general welding quality classification scheme and a more detailed and advanced welding quality estimation scheme. To achieve a fast, convenient and cheap monitoring strategy, only the easily obtained electrical signals are monitored for data acquisition. For the welding quality classification, a self-organizing map under a windowed feature extraction is applied. Results of the spot welding experiment from a portable welding machine show that the classification accuracy can be 92.9%. For welding quality estimation, variation of the welding time and detailed aspects of welding quality are introduced. In particular, a modified recurrent neural network is utilized for the size estimation of the heat affected zone, while a novel self-organizing map type classifier is used to detect the expulsion condition along with its occurrence time. During the spot welding experiments, the average error percentage of the heat affected zone size estimation is around 6.7% and the accuracy on expulsion detection reaches 93.3%.

Sign in / Sign up

Export Citation Format

Share Document