Mathematical modeling to estimate machining time during milling of Inconel 718 workpiece using ANN. (2023)

• Record Type: Journal Article
• Authors: Kalra, Gourav; Kumar Gupta, Arun
• Is Part Of: Materials today. Volume 78(2023)Part 3
• Page Start: 546
• Page End: 554
• Publication Date: 2023
• Subjects: Inconel 718 -- RSM -- BBD -- Operational parameters -- Machine Time -- Artificial Neural network; Materials science -- Congresses -- Periodicals; 620.1
• DOI: 10.1016/j.matpr.2022.11.314
• Languages: English
• ISSNs: 2214-7853

Abstract

Abstract: For the manufacturing of thin walled-complex shape components used in complex dies and moulds it is important to manufacture these kinds of components with hard, tough and heat resistant material such as Income 718. During the end milling of such type of components there are many challenges related to machine time, surface roughness, tool wear etc identified in the recent past. Therefore, in this study a prediction model for machining time with respect to the input parameters such as cutting speed, Depth of Cut, Feed rate and nose radius has been developed. The prediction model with high accuracy is very important for the optimization problems usually faced during machining. For prediction of machining time many of the researchers have applied Statistical, Analytical as well as artificial network (AI) techniques and as per the recent literature review it has been observed that the AI techniques are most accurate and reliable. Inconel 718 used for making components in aerospace, marine, automobile, steam turbines etc is difficult to machine due to its physical and chemical properties. Therefore, in the present work an attempt has been made to develop a prediction model of machine time during milling of Inconel 718 with the help of BBD-RSM-Regression (statistical techniques) as well as Artificial Neural network (AI techniques). Beside this a comparative analysis has been made among these techniques and it has been observed that AI technique provide better prediction as compare to the BBD-RSM-Regression. The ANOVA technique is also applied to find the estimate the percentage contribution of each machine parameter with respect to machine time.