Using data mining techniques to investigate the correlation between surface cracks and flange lengths in deep drawn sheet metals
Research output: Journal contributions › Conference article in journal › Research › peer-review
Standard
In: IFAC-PapersOnLine, Vol. 52, No. 13, 01.09.2019, p. 851-856.
Research output: Journal contributions › Conference article in journal › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - JOUR
T1 - Using data mining techniques to investigate the correlation between surface cracks and flange lengths in deep drawn sheet metals
AU - Heger, Jens
AU - Zein El Abdine, Mazhar
N1 - Conference code: 9
PY - 2019/9/1
Y1 - 2019/9/1
N2 - A problem during manufacturing of body parts in the automobile industry is the frequent occurrence of surface cracks in sheet metal cold forming processes. In this paper, we compare different supervised data mining techniques to predict cracks in deep-drawn sheet metals using their flange lengths as correlating features. Inline images of sheet metals are taken during the deep drawing process through cameras that are installed in every stage of a six-stage press line. A commercial software is used to label the images as defective and non-defective. Additionally, flange lengths, which generally correlate with forces set at the machines, are measured along the periphery of the sheets. The results are promising, as the models achieved satisfactory accuracy rates, albeit with some margin for improvement. This paper aims to choose a binary classification algorithm that is best suitable for the given dataset. Furthermore, the results provide an insight on the correlation of flange lengths with the occurrence of cracks, which can be used for online parameter adjustments of the machines in the future.
AB - A problem during manufacturing of body parts in the automobile industry is the frequent occurrence of surface cracks in sheet metal cold forming processes. In this paper, we compare different supervised data mining techniques to predict cracks in deep-drawn sheet metals using their flange lengths as correlating features. Inline images of sheet metals are taken during the deep drawing process through cameras that are installed in every stage of a six-stage press line. A commercial software is used to label the images as defective and non-defective. Additionally, flange lengths, which generally correlate with forces set at the machines, are measured along the periphery of the sheets. The results are promising, as the models achieved satisfactory accuracy rates, albeit with some margin for improvement. This paper aims to choose a binary classification algorithm that is best suitable for the given dataset. Furthermore, the results provide an insight on the correlation of flange lengths with the occurrence of cracks, which can be used for online parameter adjustments of the machines in the future.
KW - Classifier evaluation
KW - Cold forming
KW - Computer vision
KW - Data mining
KW - Deep drawing
KW - Quality control
KW - Surface inspection
KW - Engineering
UR - http://www.scopus.com/inward/record.url?scp=85078894989&partnerID=8YFLogxK
U2 - 10.1016/j.ifacol.2019.11.236
DO - 10.1016/j.ifacol.2019.11.236
M3 - Conference article in journal
AN - SCOPUS:85078894989
VL - 52
SP - 851
EP - 856
JO - IFAC-PapersOnLine
JF - IFAC-PapersOnLine
SN - 2405-8971
IS - 13
T2 - 9th International Federation of Automatic Control Conference on Manufacturing Modelling, Management and Control - 2019
Y2 - 28 August 2019 through 30 August 2019
ER -