Evaluation of different approach for WEDM process optimization. (2022)

• Record Type: Journal Article
• Authors: Patel, Sandip; Prajapati, J.M.; Patel, Deepak; Patel, Mitesh; Patel, Kaushik
• Is Part Of: Materials today. Volume 66:Part 4(2022)
• Page Start: 1988
• Page End: 1993
• Publication Date: 2022
• Subjects: BPNN -- CCD -- MRR -- WEDM -- Data Point; CCD Central Composite Design -- WEDM Wire Electric Discharge machining -- RSM Response Surface Methodology -- MRR Material Removal Rate -- BPNN Back Propagation Neural Network -- GRA Gray Relation Analysis -- ANN Artificial Neural Network -- SR Surface Roughness -- WWR Wire Wear Ratio -- PSO Particle Swarm Optimization; Materials science -- Congresses -- Periodicals; 620.1
• DOI: 10.1016/j.matpr.2022.05.438
• Languages: English
• ISSNs: 2214-7853

Abstract

Abstract: In this paper, an effective process optimization approach based on artificial neural networks with a backpropagation and response surface methodology including central composite design is presented for the modeling and prediction of material removal rate in the wire electrical discharge machining process. In the development of predictive models, cutting parameters of pulse on time, pulse off time, peak current, spark gap set voltage, wire tension, and wire feed rate are considered as model variables. After experiments are carried out, the BPNN model was developed using six process parameters. The performance of the developed artificial neural networks and response surface methodology predictive models is tested for prediction accuracy in terms of the coefficient of determination and root mean square error metrics. MRR's CCD statistical models were compared to the performance of the created BPNN models. On 52 investigative data points, the training of a neural network model based on back-propagating was evaluated. The results indicate that an artificial neural networks model provides a more accurate prediction than the response surface methodology model.