Use of Machine Learning Algorithms for Weld Quality Monitoring using Acoustic Signature

Sumesh, A.; Rameshkumar, K.; Mohandas, K.; Babu, Rosebin

doi:10.1016/j.procs.2015.04.042

Cited by 99 publications

(25 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although the different methods are tested here for mitigating defect formation in FSW, they are generic in nature and can be extended for any other multifactorial manufacturing issues. [42][43][44][45][46][47][48][49][50][51][52][53][54][55][56]…”

Section: Introductionmentioning

confidence: 99%

Conditions for void formation in friction stir welding from machine learning

Mukherjee

DebRoy

2019

npj Comput Mater

View full text Add to dashboard Cite

Friction stir welded joints often contain voids that are detrimental to their mechanical properties. Here we investigate the conditions for void formation using a decision tree and a Bayesian neural network. Three types of input data sets including unprocessed welding parameters and computed variables using an analytical and a numerical model of friction stir welding were examined. One hundred and eight sets of independent experimental data on void formation for the friction stir welding of three aluminum alloys, AA2024, AA2219, and AA6061, were analyzed. The neural network-based analysis with welding parameters, specimen and tool geometries, and material properties as input predicted void formation with 83.3% accuracy. When the potential causative variables, i.e., temperature, strain rate, torque, and maximum shear stress on the tool pin were computed from an approximate analytical model of friction stir welding, 90 and 93.3% accuracies of prediction were obtained using the decision tree and the neural network, respectively. When the same causative variables were computed from a rigorous numerical model, both the neural network and the decision tree predicted void formation with 96.6% accuracy. Among these four causative variables, the temperature and maximum shear stress showed the maximum influence on void formation.

show abstract

Section: Introductionmentioning

confidence: 99%

Conditions for void formation in friction stir welding from machine learning

Mukherjee

DebRoy

2019

npj Comput Mater

View full text Add to dashboard Cite

show abstract

“…There are several studies in literature correlating welding parameters with weld defects, as well as online monitoring of the welding process. Some of these studies correlated the effects of weld current, voltage, travel speed, heat input, and shielding gas with the weld defects (lack of fusion, burn-through, weld size, lack of strength) using audio (microphone) data by linear correlation [ 1 ] and machine learning [ 2 ]. Atabaki et al [ 3 ] identified the factors causing porosity in hybrid laser/arc welding in relation to the stand-off distance between the laser and arc, and the heat input.…”

Section: Introductionmentioning

confidence: 99%

The Detection of Burn-Through Weld Defects Using Noncontact Ultrasonics

et al. 2018

View full text Add to dashboard Cite

Nearly all manufactured products in the metal industry involve welding. The detection and correction of defects during welding improve the product reliability and quality, and prevent unexpected failures. Nonintrusive process control is critical for avoiding these defects. This paper investigates the detection of burn-through damage using noncontact, air-coupled ultrasonics, which can be adapted to the immediate and in-situ inspection of welded samples. The burn-through leads to a larger volume of degraded weld zone, providing a resistance path for the wave to travel which results in lower velocity, energy ratio, and amplitude. Wave energy dispersion occurs due to the increase of weld burn-through resulting in higher wave attenuation. Weld sample micrographs are used to validate the ultrasonic results.

show abstract

“…The signatures are based on acquired signals of the welding current and arc voltage [27,28]. Some examples of methods using acoustic signals to monitor lack of fusion, burn through and welding arc length can be found in [5,6,30]. Other interesting examples employ the use of temperature field monitoring by infrared cameras for monitoring of the heat input [11,12].…”

Section: Introductionmentioning

confidence: 99%

Prediction of penetration in one-sided fillet welds by in-process joint gap monitoring—an experimental study

Sikström

Öberg

2017

Weld World

View full text Add to dashboard Cite

The challenge to predict variations in penetration depth in one-sided fillet welds during robotized gas metal arc welding has been addressed by a pilot investigation of technical possibilities and limitations. The main cause for the variation in penetration depth is considered to be variation in joint gap size. Special attention has been paid in order to adopt the experimental conditions to conform to industrial welding conditions. The employed method uses in-process monitoring of joint gap size together with an empirical model relating penetration depth to gap size in order to predict this depth. The gap size estimates are based on image information from two cameras, one visual and one infrared. The results, that are evaluated off-line, confirm the development of a real-time method providing technical solutions that are industrially tractable. The results also pinpoint areas of further improvements towards increased robustness and reduced estimation uncertainties.

show abstract

Use of Machine Learning Algorithms for Weld Quality Monitoring using Acoustic Signature

Cited by 99 publications

References 10 publications

Conditions for void formation in friction stir welding from machine learning

Conditions for void formation in friction stir welding from machine learning

The Detection of Burn-Through Weld Defects Using Noncontact Ultrasonics

Prediction of penetration in one-sided fillet welds by in-process joint gap monitoring—an experimental study

Contact Info

Product

Resources

About