Prediction of machining performance using RSM and ANN models in hard turning of martensitic stainless steel AISI 420

Abstract

The purpose of this experimental work is to study the impact of the machining parameters ( Vc, ap, and f) on the surface roughness criteria ( Ra, Rz, and Rt) as well as on the cutting force components ( Fx, Fy, and Fz), during dry turning of martensitic stainless steel (AISI 420) treated at 59 hardness Rockwell cone. The machining tests were carried out using the coated mixed ceramic cutting-insert (CC6050) according to the Taguchi design (L25). Analysis of the variance (ANOVA) as well as Pareto graphs made it possible to quantify the contributions of ( Vc, ap, and f) on the output parameters. The response surface methodology and the artificial neural networks approach were used for output modeling. Finally, the optimization of the machining parameters was performed using desirability function (DF) minimizing the surface roughness and the cutting forces simultaneously. The results indicated that the roughness is strongly affected by the feed rate ( f) with contributions of (80.71%, 80.26%, and 81.80%) for ( Ra, Rz, and Rt) respectively, and that the depth of cut ( ap) is the factor having the major influence on the cutting forces ( Fx = 53.76%, Fy = 50.79%, and Fz = 65.31%). Furthermore, artificial neural network and response surface methodology models correlate very well with experimental data. However, artificial neural network models show better accuracy. The optimum machining setting for multi-objective optimization is Vc = 80 m/min, f = 0.08 mm/rev and ap = 0.141 mm.

Optimization and Modeling of Process Parameters in Multi-Hole Simultaneous Drilling Using Taguchi Method and Fuzzy Logic Approach

“…The percent contribution in ANOVA is used to describe how much influence each process parameters has on the output responses. The P-value can confirm the effect of process parameters on responses and shows that values less than 0.05 have no effect [35]. Another statistical tool is F-value, which is used to check the design parameters with a significant impact on the quality characteristic [2].…”

Prediction the Influence of Machining Parameters for CNC Turning of Aluminum Alloy Using RSM and ANN

“…The Artificial Neural Network can be defined as a computational model that inspired its design schematically from the actual neuron (human, animal) functioning. Statistical learning methods are utilized to optimize neural networks so that they are positioned with statistical applications group on one hand, which they enriched with a group of models allowing generating large functional spaces that are flexible and partially structured [6]. In this paper, Hebbian learning rule in Neural Network model consists of three input neurons and one output corresponding to (tool diameter (d), feed-rate (f), cutting speed (v)), and (Ra) respectively.…”

“…Recently, various scientific studies according to ANN have been carried out because of its good predictive ability. [6] Alagarsamy and Rajakumar presented an effective method for the optimization of turning conditions according to Taguchi's approach with RSM. This work examines the employ of Taguchi's method to minimize desired Ra and maximize MRR during machining Al-7075 alloy using tungsten carbide (TNMG 115 100) insert.…”

“…Finally, process parameters optimization was done utilizing desirability function (DF) minimizing Ra and cutting forces simultaneously. An output result was present that Ra is robustly affected by feed-rate (f), and that cutting forces is influenced by the depth of cut (ap) [6]. In this paper, the influence of machining parameters (Cutting speed (mm/ min), feed rate (mm/rev) and depth of cut (mm)) was studied to determine the influence of them on the Surface Roughness (Ra) values based on Response Surface Methodology (RSM) with (3 factors, 3 levels) and Artificial Neural Network (ANN).…”

Parameter optimization of double‐blade normal milk processing and mixing performance based on RSM and BP‐GA

“…In addition, some scholars used the response surface method and the artificial neural network to finish the research on the machining performance of martensitic stainless steel, surface roughness of keyway milling, surface finish analysis of wire electric discharge machined specimens and cutting parameters in turning of gray cast iron. On the basis of modeling, the machining performance of mechanical materials was analyzed and optimized, and the experimental verification was carried out (Bhupinder & Misra, 2019;Ghosh, Mandal, & Mondal, 2019;Laouissi, Yallese, Belbah, Belhad, & Haddad, 2019;Zerti, Yallese, Zerti, Nouioua, & Khettabi, 2019). Tang, Huang, and Fang (2011) did optimal design on face plate structure of the numerical control rotary table by applying genetic algorithm and BP neural network.…”