A new model to distinguish welds performed by short-circuit GMAW based on FRESH algorithm and MLP ANN
- 16 Downloads
The short-circuit gas metal arc welding has been continuously studied over the years, due to its important role in manufacturing processes. Concerning the process, many kinds of research are carried out aiming to understand the influence of the shielding gas in welds quality. In this context, this work treats the voltage and current welding signals as time series and applies a feature extraction based on scalable hypothesis tests, which is called FRESH algorithm, in order to obtain the signal features. After that, these features are applied in a multilayer perceptron artificial neural network, trained by the scaled conjugate gradient method, which classifies the welds according to the flow rate and type of shielding gas used in the process. The model presented excellent performance, which shows that the proposal is suitable to be used in welding quality monitoring.
KeywordsGas metal arc welding (GMAW) Shielding gas FRESH algorithm Artificial neural network
The authors would like to acknowledge FAPEMIG, CAPES, CNPq and Federal University of Juiz de Fora for financial support.
Compliance with ethical standards
Conflict of interest
The authors declare that they have no conflict of interest.
This article does not contain any studies with human participants or animals performed by any of the authors.
- 4.Uttrachi GD (2007) GMAW shielding gas flow control systems. Weld J 86(4):22Google Scholar
- 11.Panda BN, Babhubalendruni MR, Biswal B, Rajput DS (2015) Application of artificial intelligence methods to spot welding of commercial aluminum sheets (BS 1050). In: Proceedings of fourth international conference on soft computing for problem solving. Springer, Berlin, pp 21–32Google Scholar
- 12.Campbell S, Galloway A, McPherson N (2012) Artificial neural network prediction of weld geometry performed using GMAW with alternating shielding gases. Weld J 91(6):174SGoogle Scholar
- 15.Christ M, Kempa-Liehr AW, Feindt M (2016) Distributed and parallel time series feature extraction for industrial big data applications. arXiv preprint arXiv:1610.07717
- 18.Nanopoulos A, Alcock R, Manolopoulos Y (2001) Feature-based classification of time-series data. Int J Comput Res 10(3):49Google Scholar
- 19.Geurts P (2001) in Pattern extraction for time series classification. In: European conference on principles of data mining and knowledge discovery. Springer, Berlin, pp 115–127Google Scholar
- 21.Radivojac P, Obradovic Z, Dunker AK, Vucetic S (2004) Feature selection filters based on the permutation test. In: European conference on machine learning. Springer, Berlin, pp 334–346Google Scholar
- 24.Stehman S (1996) Estimating the kappa coefficient and its variance under stratified random sampling. Photogram Eng Remote Sens 62(4):401Google Scholar
- 25.Sokolova M, Japkowicz N, Szpakowicz S (2006) Beyond accuracy, F-score and ROC: a family of discriminant measures for performance evaluation. Springer, BerlinGoogle Scholar