Characterization of wear and prediction of wear zone locations on the rake face using Mamdani fuzzy inference system

Abstract

In order to improve the performance of the cutting tool, third-generation tools with multi-layered nanocoatings on the rake face are used. During machining, the chip-tool interactions depict that although the tool wear on the rake face is located in the close proximity of the cutting edge, that is, within 800 mm, all the commercially available cutting tools have the coatings on the entire rake face. Taking into account the tribological properties required by the rake face close to the cutting edge, that is, high wear resistance and low friction, this study makes an attempt to identify, characterize and locate the actual wear zones/regions in terms of hard and soft zones in the chip contact area of tungsten carbide (WC) inserts close to the cutting edge in turning. Mamdani fuzzy inference system model was developed, trained with the sample experimental data and tested with the test data. The simulated results showed that the average error values of edge chipping (in X-and Y-directions), nose damage and crater wear (in X-and Y-directions) are about 2.37%, 3.01%, 2.86%, 2.66% and 1.89%, respectively. The fuzzy model developed in this study showed remarkable prediction of the wear zone locations and is also helpful for the researchers to decide the type of coating (hard and soft) along the specified zones for reducing the cost of production.

Modeling of Nanolubricant-Assisted Machining Process by using Multiple Regression Analysis

“…The interpolated results from the fuzzy model are used to model the various responses the multiple regression approach employing a nonlinear fit between the response and the pertinent significant parameters [48]. Multiple regression analysis was frequently utilized for modeling and interpreting experimental results because it is useful, affordable, and generally simple to use [67][68][69][70][71]. Using analysis of variance (ANOVA), it was possible to determine the importance of the parameters on the outcomes.…”

Correlating tool wear and surface integrity of a CNC turning process using Naïve based classifiers

“…Ma et al 6 developed a theoretical model for tool wear mechanism and identified most influential factors during milling of Inconel 718. Pavani et al 7 developed a Mamdani fuzzy inference system model, which is able to predict the wear zones in the form of hard and soft zones in place of contact of tungsten carbide inserts and the work piece during the machining process. Karandikar et al 8 applied naı¨ve based classifiers for tool condition monitoring in end milling of 1018 steel using carbide insert.…”

“…Conditional independence assumption simplifies equation (3) as follows. Again, considering the Bayes rule and naı¨ve conditional independence assumption can be rewritten as equation (7) as follows. It is to be noted here, that denominator of equation ( 5) is a normalizing constant and it is not shown in equation (7).…”

Tool strain–based wear estimation in micro turning using Bayesian networks

“…The interrogator measures the shift in nominal wavelength for the FBG sensors. Strain values were obtained from the wavelength shifts of the FBG sensors using equations (1) and (2). 23 The strain value obtained in a sample was subtracted from the next sample to get De (difference in strain between the samples) values as in equation (3) Dl…”

“…Estimation of tool wear in micro machining operations, as compared to conventional scale machining, proves to be a daunting task due to varying process physics, cutting mechanism and miniature sizes of tools. 1,2 In contact-based micro machining processes such as micro turning, micro milling and micro drilling, tool wear is influenced by a number of factors such as type of tool, tool morphology, tool strain, machining conditions and work materials. 3 Unlike conventional scale processes where machining primarily occurs by cutting at the tool edge, micro-scale material removal processes involve three different mechanisms, namely, cutting, slipping and plowing that makes the tool–work interaction complex and therefore drawing proper inference regarding tool wear using machine parameters becomes a difficult task.…”