Journal ArticleDOI
Quality assessment of resistance spot welding process based on dynamic resistance signal and random forest based
TLDR
In this article, a scheme for online quality monitoring of resistance spot welding (RSW) process is proposed to effectively determine the rate of spot weld quality, where a random forest (RF) classification featuring with dynamic resistance (DR) signals which were collected and processed in the production environment was carried out.Abstract:
A scheme for online quality monitoring of resistance spot welding (RSW) process is proposed to effectively determine the rate of spot weld quality. In this work, the random forest (RF) classification featuring with dynamic resistance (DR) signals which were collected and processed in the production environment was carried out. The obtained results demonstrated that the constructed RF model based on DR profile features adequately distinguished high-quality welds from the other unacceptable welds such as inadequate sized welds and expulsions. Variable importance evaluation of RF was implemented against the input features. It showed that two DR slopes for nugget nucleation and growth (v
2
, v
3
) and dynamic resistance (R
γ
) in the final half cycle play the most significant roles in achieving more accurate results of classification, while absolute gradient ∇
max
is useful in detecting minor expulsion from pull-out failure. In addition, shunting effect in consecutive welds was tentatively investigated via the DR curves, accounting for noticeable declines in the stage I of DR. The results revealed that shunted welds beyond minimum weld spacing do not significantly undermine the accuracy of classification. The implementation of RF based on the combination of welding parameters and DR features improves the accuracy of classification (98.8%) with ntree = 1000 and mtry = 4, as weld current significantly distinguished situations where DR features solely achieve accuracy (93.6%). The incorporation of the RF technique into online monitoring system attains a satisfying RSW quality classification accuracy and reduces the workload on destructive tests.read more
Citations
More filters
Journal ArticleDOI
Overview of recent advances of process analysis and quality control in resistance spot welding
Kang Zhou,Ping Yao +1 more
TL;DR: The establishment of general models to online process analysis, quality estimation and real time control system design for obtaining welds with satisfactory quality still remains a big challenge in reality.
Journal ArticleDOI
Performances of regression model and artificial neural network in monitoring welding quality based on power signal
TL;DR: In this paper, the authors compared the performances of regression model and artificial neural network in predicting the nugget diameter of spot-welded joints by monitoring the dynamic power signature.
Journal ArticleDOI
Characteristics of shunting effect in resistance spot welding in mild steel based on electrode displacement
Bobin Xing,Yi Xiao,Qing H. Qin +2 more
TL;DR: Shunting effect of resistance spot welding is evaluated based on the electrode displacement signals in this article, which showed that the weld spacing and nugget diameter were polynomial-correlated, and the minimum welding spacing of 20 mm can be derived from the results.
Journal ArticleDOI
Investigation of feed-forward back propagation ANN using voltage signals for the early prediction of the welding defect
TL;DR: The research paper investigates the prediction capability of the artificial neural network for weld quality assessment from the captured voltage signals in a gas metal arc welding process and proves that the developed method is promising for the immediate and early prediction of the weld quality.
Journal ArticleDOI
Prediction of residual stress in electron beam welding of stainless steel from process parameters and natural frequency of vibrations using machine-learning algorithms:
TL;DR: In this article, machine learning algorithms have been used to predict residual stress during electron beam welding of stainless steel using the information of input process parameters and natural language processing (NLP).
References
More filters
Journal ArticleDOI
Random Forests
TL;DR: Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the forest, and are also applicable to regression.
Classification and Regression by randomForest
Andy Liaw,Matthew C. Wiener +1 more
TL;DR: random forests are proposed, which add an additional layer of randomness to bagging and are robust against overfitting, and the randomForest package provides an R interface to the Fortran programs by Breiman and Cutler.
Journal ArticleDOI
Assessment of resistance spot welding quality based on ultrasonic testing and tree-based techniques
TL;DR: In this article, classification and regression tree (CART) and random forest techniques were proposed as pattern recognition tools for classification of ultrasonic oscillograms of resistance spot welding (RSW) joints.
Journal ArticleDOI
A novel quality evaluation method for resistance spot welding based on the electrode displacement signal and the Chernoff faces technique
TL;DR: In this article, Chen et al. developed a visual and reliable weld quality assessment method for resistant spot welding, the electrode displacement signal was measured and analyzed, and some statistical features closely related to the weld quality were extracted.
Journal ArticleDOI
Real Time Monitoring Weld Quality of Resistance Spot Welding for Stainless Steel
TL;DR: In this article, the effects of various process conditions in spot welded stainless steel on quality by using dynamic resistance were explored. But the results showed that dynamic resistance responds well to the variations of process conditions and can serve as an important indicator of weld quality.