Surface roughness assessing based on digital image features

Abstract

The paper gives an account of the machined surface roughness investigation based on the features of a digital image taken subsequent to the technological operation of milling of aluminium alloy Al6060. The data used for investigation were obtained by mixed-level factorial design with two replicates. Input variables (factors) are represented by the face milling basic machining parameters: spindle speed (at five levels: 2000; 3500; 5000; 6500; 8000 rev/min, respectively), feed per tooth (at six levels: 0.025; 0.1; 0.175; 0.25; 0.325; 0.4 mm/tooth, respectively) and depth of cut (at two levels: 1; 2 mm, respectively). Output variable or response is the most frequently used surface roughness parameter -arithmetic average of the roughness profile, Ra. Digital image of the machined surface is provided for every test sample. Based on experimental design and obtained results of roughness measuring, a base has been created of input data (features) extracted from digital images of the samples' machined surfaces. This base was later used for generating the fuzzy inference system for prediction of the surface roughness using the adaptive neuro-fuzzy inference system (ANFIS). Assessing error, i.e. comparison of the assessed value Ra provided by the system with real Ra values, is expressed with the normalized root mean square error (NRMSE) and it is 0.0698 (6.98 %).

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

“…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).…”

“…Rodríguez et al (2017) presented an AI-based decision-making tool for selection of the right cutting tools for face milling, one of the criteria for which is the roughness of the machined surface. Simunovic et al (2016) presented a machined surface roughness investigation based on the features of a digital image such as spindle speed, feed per tooth, and cutting depth, but without considering tool wear; the digital image was produced following a milling operation of an aluminum alloy Al6060. Selaimia et al (2017) modeled the output responses, namely: surface roughness (Ra), cutting force (FC), cutting power (PC), specific cutting force (KS) and metal removal rate (MRR) during the face milling of the austenitic stainless steel X2CrNi18-9 with coated carbide inserts (GC4040).…”

Increasing Stiffness of Constructions through Application of Enhancing Elements

“…This causes displacements and deformations of the elements of the machining system, which, consequentially, leads to deviations from nominal tolerances and reduces machining accuracy [2]. Deformations of machining system components, as well as their contact interfaces, significantly impact system stability, i.e., machine tool [3], cutting tool [4], fixture [5], and workpiece [6]. During the process, clamping forces and torques are being transferred onto all other elements of the machining system.…”

Untitled

“…Anodizing is one of the most important processes in corrosion protection and colour finishes for aluminium [6]. Design of experiments (DoE) is one of the basic tools which help us to show the influence of input factors on outputs [7][8][9][10]. The optimum selection of process conditions is an extremely important issue as these determine surface quality of the manufactured components [11][12][13].…”