Modeling of the Influence of Cutting Parameters on the Surface Roughness, Tool Wear and Cutting Force in Face Milling in Off-Line Process Control

Abstract

Off-line process control improves process efficiency. This paper examines the influence of three cutting parameters on surface roughness, tool wear and cutting force components in face milling as part of the off-line process control. The experiments were carried out in order to define a model for process planning. Cutting speed, feed per tooth and depth of cut were taken as influential factors. Two modeling methodologies, namely regression analysis and neural networks have been applied to experimentally determined data. Results obtained by the models have been compared. Both models have a relative prediction error below 10%. The research has shown that when the training dataset is small neural network modeling methodologies are comparable with regression analysis methodology and can even offer better results, in which case an average relative error of 3.35%. Advantages of off-line process control which utilizes process models by using these two modeling methodologies are explained in theory.

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

“…Grzenda et al (2012) presented a new strategy for improving the AI models for predicting surface roughness using small datasets tested in high-torque milling operations. Bajić et al (2012) examined the impact of various cutting speeds, cutting depth, and tool wear on surface roughness and the cutting force components. Kovac et al (2013) studied the influence of machining parameters on surface roughness in face milling, comparing prediction models based on fuzzy logic and RA.…”

“…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).…”

Deep Stacked Auto-Encoder Network Based Tool Wear Monitoring in the Face Milling Process

“…Machine learning techniques have been researched and applied in many fields of science and technology, such as computer vision, automatic diagnostics systems and pattern recognition. These techniques are often based on artificial intelligence methods such as k-nearest neighbour (K-NN) [8], support vector machines (SVM) [9] and [10], and the artificial neural network (ANN) [11] to [13]. These methods have been effectively applied to identify tool wear status.…”

Experimental research of face mill wear effect to flat surface roughness

“…In the articles from [9,10], the models of roughness prediction are given, though without the assumption of tool wear. In [11][12][13][14][15][16], the effect of the machining parameters on the roughness of finished surfaces by face milling were studied; for example, the quality of machined surface vs. milling and cooling conditions are given; the studies were per formed with the use of Taguti method and others. However, the aforementioned works do not consider the essential component, namely, the change of the roughness of finished flat surfaces due to the growth of the flank of wear on the back surface of face mill teeth.…”