ANFIS estimation of optimal parameters for dross formation in plasma arc cutting process. (November 2022)

• Record Type: Journal Article
• Authors: Denic, Nebojsa; Cirkovic, Bogdan; Stevanovic, Vesna; Stevanovic, Malilsa; Petković, Dalibor
• Is Part Of: Advances in engineering software. Volume 173(2022)
• Publication Date: 2022-11
• Subjects: Plasma arc cutting -- Optimization -- Dross formation -- ANFIS; Computer-aided engineering -- Periodicals; Engineering -- Computer programs -- Periodicals; Engineering -- Software -- Periodicals; Periodicals; 620.0028553
• DOI: 10.1016/j.advengsoft.2022.103270
• Languages: English
• ISSNs: 0965-9978

Abstract

Highlights: Plasma arc cutting process based on a data driven optimization approach. The three output parameters represent the dross formation. To employ an adaptive neural fuzzy inference system (ANFIS). Abstract: In this study was optimized plasma arc cutting process based on a based-on dross formation. The three output parameters represent the dross formation. The input factors are thickness, current, arc gap voltage, speed and cutting time. The output responses are: weight after cutting with dross, weight after cutting without dross and dross formation rate (DFR). Since the process is very complex due the different processing parameters and there is need to establish an optimization model in order to obtain the undeformed structures. In this article the main aim was to identify the most influential attributes for optimal conditions for the dross formation in plasma arc cutting. The purpose of this research is to employ an adaptive neural fuzzy inference system (ANFIS) to classify the different input parameters for the optimization of the dross formation in plasma arc cutting. Combination of thickness and current has the highest influence on the all three output factors. In other words, the combination of thickness and current is the optimal combination for prediction of weight after cutting with dross (RMSE: 2.9535), weight after cutting without dross (RMSE: 3.0965) and dross formation rate (DFR) (RMSE: 0.0382). The study also considering different input parameters simultaneously is believed to be the first on a small scale and to attract the interest of everyone.