Learning quality characteristics for plastic injection molding processes using a combination of simulated and measured data

et al. 2022

IEEE Access

Resistance spot welding (RSW) is a widespread manufacturing process in the automotive industry. There are different approaches for assessing the quality level of RSW joints. Multi-input-singleoutput methods, which take as inputs either the intrinsic parameters of the welding process or ultrasonic nondestructive testing variables, are commonly used. This work demonstrates that the combined use of both types of inputs can significantly improve the already competitive approach based exclusively on ultrasonic analyses. The use of stacking of tree ensemble models as classifiers dominates the classification results in terms of accuracy, F-measure and area under the receiver operating characteristic curve metrics. Through variable importance analyses, the results show that although the welding process parameters are less relevant than the ultrasonic testing variables, some of the former provide marginal information not fully captured by the latter.

Section: ) Stackingmentioning

confidence: 99%

Comparative Study of Classification Algorithms for Quality Assessment of Resistance Spot Welding Joints From Pre- and Post-Welding Inputs

Martín¹,

et al. 2022

IEEE Access

“…Apart from bagging and boosting [52] -the two most common ensemble techniques for classification-there is a third methodology for combining classifiers on the same dataset known This document is a preprint. Do not cite this document, please cite instead: Martín, O., Ahedo, V., Santos, J.I., Galán, J.M.…”

Section: Stackingmentioning

confidence: 99%

Comparative Study of Classification Algorithms for Quality Assessment of Resistance Spot Welding Joints From Pre- and Post-Welding Inputs

Martín

et al. 2022

Preprint

Resistance spot welding (RSW) is a widespread manufacturing process in the automotiveindustry. There are different approaches for assessing the quality level of RSW joints. Multiinput‐single‐output methods, which take as inputs either the intrinsic parameters of the weldingprocess or ultrasonic nondestructive testing variables, are commonly used. This workdemonstrates that the combined use of both types of inputs can significantly improve thealready competitive approach based exclusively on ultrasonic analyses. The use of stacking oftree ensemble models as classifiers dominates the classification results in terms of accuracy, Fmeasureand area under the receiver operating characteristic curve metrics. Through variableimportance analyses, the results show that although the welding process parameters are lessrelevant than the ultrasonic testing variables, some of the former provide marginal informationnot fully captured by the latter.

“…Apart from bagging and boosting [52] -the two most common ensemble techniques for classification-there is a third methodology for combining classifiers on the same dataset known as stacked generalization or stacking [53]. This approach is giving excellent and, in some cases, close to optimal results [54][55][56], and it is also recently starting to be successfully applied in manufacturing-related fields [57,58].…”

Section: Stackingmentioning

confidence: 99%

Quality Prediction of Resistance Spot Welding Joints From Pre- and Post-Welding Inputs Using Stacking of Tree Ensemble Models

Martín

et al. 2021

Preprint

Resistance spot welding (RSW) is a widespread manufacturing process in the automotive industry. There are different approaches for assessing the quality level of RSW joints. Multi-input-single-output methods, which take as inputs either the intrinsic parameters of the welding process or ultrasonic nondestructive testing variables, are commonly used. This work demonstrates that the combined use of both types of inputs can significantly improve the already competitive approach based exclusively on ultrasonic analyses. The use of stacking of tree ensemble models as classifiers dominates the classification results in terms of accuracy, F-measure and area under the receiver operating characteristic curve metrics. Through variable importance analyses, the results show that although the welding process parameters are less relevant than the ultrasonic testing variables, some of the former provide marginal information not fully captured by the latter.