Genetic programming approach to predict the performance characteristics of WEDM taper cutting process

Created by W.Langdon from gp-bibliography.bib Revision:1.7615

@Article{NAYAK:2022:matpr,

• author = "Bijaya Bijeta Nayak and Nitish Kumar and Abhishek Singh and Sasmita Sahu and Shiv Sankar Das and Debashree Debadatta Behera and Rita Kumari Sahu",
• title = "Genetic programming approach to predict the performance characteristics of {WEDM} taper cutting process",
• journal = "Materials Today: Proceedings",
• volume = "62",
• pages = "4504--4508",
• year = "2022",
• note = "International Conference on Materials, Processing \& Characterization (13th ICMPC)",
• ISSN = "2214-7853",
• DOI = "doi:10.1016/j.matpr.2022.04.948",
• URL = "https://www.sciencedirect.com/science/article/pii/S2214785322031522",
• keywords = "genetic algorithms, genetic programming, Genetic programming (GP), WEDM, Taper cutting, Angular error, Prediction model",
• abstract = "One of the unique applications of the wire electrical discharge machining (WEDM) method is taper cutting process. This process is ideal for numerous intricate, difficult to machine materials with complex profiles, deep slots with tight corners and features at different angles, those are basically used in defense and aerospace applications. According to the literature, numerous mathematical models based on physics and data may be created to identify the optimum parameter settings throughout the taper cutting process. However, it is a challenging process since it necessitates extensive understanding of how to do tapering operations with WEDM. As a result, a genetic programming (GP) model is created in this study to anticipate the angle inaccuracy during WEDM taper cutting. Six process parameters including workpiece thickness, taper angle, pulse duration, discharge current, wire speed and wire tension were considered at three level each for minimizing the angular error and surface roughness during WEDM taper cutting process. The L27 orthogonal array of Taguchi's design of experiment is used to collect data on the procedure. Three assessing criteria are used to assess the correctness of the suggested model: root mean square error (RSME), mean absolute percentage error (MAPE) and co-efficient of determination (R2). In compared to typical prediction approaches, the results suggest that MGGP is a successful strategy. The model is cost effective and time saving way to investigate angular error and surface roughness in taper cutting before performing the actual machining process",

}

Genetic Programming entries for Bijaya Bijeta Nayak Nitish Kumar Abhishek Singh Sasmita Sahu Shiv Sankar Das Debashree Debadatta Behera Rita Kumari Sahu

Citations