Application of GONNS to predict constrained optimum surface roughness in face milling of high-silicon austenitic stainless steel

Artificial intelligence for automatic prediction of required surface roughness by monitoring wear on face mill teeth

“…Grzenda and Bustillo (2013) focused on the initial data transformation and its effect on the prediction of surface roughness in hightorque face milling operations. Elhami et al (2013) suggested a genetically optimized neural network system for the prediction of constrained optimal cutting conditions in the face milling of a high-silicon austenitic stainless steel, in order to minimize surface roughness. Saric et al (2013) presented a study of the prediction of machined surface roughness in the face milling of steel at various numbers of revolutions, cutting speeds, feeds, and depths.…”

“…Many researchers have developed surface roughness prediction models in face milling using AI (Srinivasa Pai et al 2002;Vosniakos 2002, 2003;Saglam and Unuvar 2003;Bruni et al 2008;El-Sonbaty et al 2008;Lela et al 2009;Muñoz-Escalona and Maropoulos 2010;Razfar et al 2011;Bharathi Raja and Baskar 2012;Grzenda et al 2012;Bajić et al 2012;Kovac et al 2013;Simunovic et al 2013;Grzenda and Bustillo 2013;Elhami et al 2013;Saric et al 2013;Rodríguez et al 2017;Simunovic et al 2016;Selaimia et al 2017;Svalina et al 2017). Srinivasa Pai et al (2002 presented an estimation of flank wear in face milling based on the radial basis function (RBF) of neural networks using acoustic emission signals, surface roughness, and cutting conditions (cutting speed and feed).…”

Prediction of surface roughness in end face milling based on Gaussian process regression and cause analysis considering tool vibration

“…From this analysis, we can conclude that depth of cut is the most influential factor in the three parameters. While in [8] and [17], the authors drew that the feed rate is the most influential parameter. In Elhami's work [8], the material is high-silicon austenitic stainless steel and most importantly, the cutting speed is very small, the largest value is 78.5 rpm, much smaller than the 6,000 rpm used in this report.…”

“…Bozdemir et al [7] developed an artificial neural network (ANN) modeling technique with the results obtained from the experiments, in this way, average surface roughness could be estimated without performing actual application for those values. Elhami et al [8] arranged an experimental scheme by using Taguchi method and proposed a genetically optimized neural network system (GONNS) to predict the constrained optimal cutting conditions in face milling of high-silicon austenitic stainless steel, found that the feed is the dominant factor affecting the surface roughness. Fuh and Wu [9] used RSM to study the influence of tool geometries and cutting parameters on surface roughness in end milling of Al alloy; the result showed that the surface roughness is affected by the tool nose radius and feed rate.…”

Use of Neural Networks in Prediction and Simulation of Steel Surface Roughness

“…The authors first conduct designed experiments. The Taguchi design of experiment is often used to reduce the time and cost of the experiments [12,13], but the central composite [14] and the full factorial design of experiments [1] are also used. The main purpose of designed experiments is to monitor the influence of controlled parameters on surface roughness [1,[15][16][17][18], but some authors also add other parameters like chip's characteristics [12], pre-tool wear vibrations [19], workpiece-tool vibration [20], lubrication-cooling condition [21] etc.…”