a fuzzy logic-based prediction model for kerf width in laser beam machining

7/24/2019 A Fuzzy Logic-Based Prediction Model for Kerf Width in Laser Beam Machining

1/7

Full Terms & Conditions of access and use can be found athttp://www.tandfonline.com/action/journalInformation?journalCode=lmmp20

Download by:[King Faisal University] Date:16 February 2016, At: 01:

Materials and Manufacturing Processes

ISSN: 1042-6914 (Print) 1532-2475 (Online) Journal homepage: http://www.tandfonline.com/loi/lmmp20

A Fuzzy Logic-Based Prediction Model for KerfWidth in Laser Beam Machining

Anamul Hossain, Altab Hossain, Y. Nukman, M. A. Hassan, M. Z. Harizam, A.M. Sifullah & P. Parandoush

To cite this article:Anamul Hossain, Altab Hossain, Y. Nukman, M. A. Hassan, M. Z. Harizam,A. M. Sifullah & P. Parandoush (2016) A Fuzzy Logic-Based Prediction Model for Kerf Width

in Laser Beam Machining, Materials and Manufacturing Processes, 31:5, 679-684, DOI:10.1080/10426914.2015.1037901

To link to this article: http://dx.doi.org/10.1080/10426914.2015.1037901

Accepted author version posted online: 05Jun 2015.Published online: 05 Jun 2015.

Submit your article to this journal

Article views: 170

View related articles

View Crossmark data


2/7

A Fuzzy Logic-Based Prediction Model for Kerf Width

in Laser Beam Machining

Anamul Hossain1, Altab Hossain1, Y. Nukman1,2, M. A. Hassan1,2, M. Z. Harizam1,

A. M. Sifullah1

, and P. Parandoush1

1Department of Mechanical Engineering, Faculty of Engineering, University of Malaya, Kuala, Lumpur, Malaysia2Department of Mechanical Engineering, Faculty of Engineering, Assiut University, Assiut, Egypt

In laser beam machining, the main concern is the machining quality as kerf width of the end product. It is essential for industrialapplications to cut the workpiece with minimum kerf width. However, it is difficult to develop a precise functional relationship between

input and output variables in laser machining. Therefore, an effort has been conducted to build up an intelligent fuzzy expert system(FES) model to predict the kerf width in CO2laser cutting. The employed input parameters were assisting gas pressure, laser power, cutting

speed, and standoff distance. The fuzzy logic was performed on fuzzy toolbox in MATLAB R2009b by employing Mamdani technique. Intotal, 81 experiments were carried out and experimental results were used for training and testing of the developed fuzzy model. Relative

error and goodness of fit were used to investigate the accuracy of the prediction ability and the values of 3.852%and 0.994, respectively, werefound to be satisfactory. This paper will extend knowledge about the prediction of kerf width by using FES model.

Keywords Fuzzy; Kerf; Laser; Model; PMMA.

INTRODUCTION

The applications of laser in the industry have beengrowing up significantly because of its outstanding bene-fits, such as machining quality, productivity, saving ofthe pre- and post-processing of the materials, and mini-mum loss of the parent workpiece as well as technicalbenefits [1,2]. In laser cutting processes, a kerf width isformed through the relative movement of the workpieceand laser beam. This movement allows creating an intri-cate shape on a flat workpiece. Mechanism of laser cut-

ting is one kind of thermal process that depends onlaser power which is divided into conduction, energy ofmelting, and vaporization and energy losses to theenvironment to balance the input laser energy. The objec-tive of this research to investigate kerf width for differentinput parameters such as assisting gas pressure, laserpower, cutting speed, and standoff distance onto 3 mmthickness of polymethylmethacrylate (PMMA) and aneffort has been carried out to establish a fuzzy expert sys-tem (FES) model in order to predict the kerf width.

Laser machining quality is strongly dependent on inputparameters. In laser machining process, laser beam hitson workpiece which can be restrained by the adjustmentof the assisting gas pressure, laser power, scanning speed,

beam mode (continuous wave (CW) or pulsed), and beam

frequency [3]. Goeke et al. [4] presented the application ofCO2 laser cutting on carbon fiber-reinforced plastics(CFRPs). They observed that radiation of laser andabsorption into material have an indicative influence onheat-affected zone and kerf width. Quintero et al. [5]applied CO2 laser cutting on phenolic resin boards(PRBs) and particleboard plates that were covered witha melamine sheet imitating beechwood. They used adesign of experiment (DOE) and found the output lasercutting quality as kerf width and surface roughness.

Dubey et al. [6] applied a combined method of TaguchiMethod and Response Surface Method (TMRSM) forthe optimization of silicon alloy steels width of kerfand material removal rate (MRR). They also developeda mathematical model of kerf width and MRR, accordingto the laser input parameters such as gas pressure, pulsewidth, cutting speed, and frequency of the pulse. Pandeyet al. [7] analyzed the kerf quality of Ti alloy in pulsedlaser cutting by an intelligent FES. Sheng et al. [8] pro-posed an analytical prediction model of kerf width as arelation to erosion front. Pandey et al. [9] developedFES model for duralumin sheet to get minimum kerfwidth and also deviations on top and bottom sides. Synet al. [10] analyzed surface quality of Incoloy alloy by

an intelligent FES model. It has not been found in litera-ture that artificial intelligent (AI) such as an FES isapplied on nonmetal like PMMA to predict kerf width.Therefore, an effort has been carried out to build up amodel of kerf width in CO2 laser cutting by FES. The usesof PMMA are being increased not only for as a substituteof glass but also for bone cement, prostheses, intraocularlens, dentures, biosensors, and biomechanical device [11].This research will be helpful to find the optimum cutting

Received December 15, 2014; Accepted March 8, 2015

Address correspondence to Altab Hossain, Department ofMechanical Engineering, Faculty of Engineering, University of Malaya,50603 Kuala Lumpur, Malaysia; E-mail: [email protected],[email protected]

Color versions of one or more of the figures in the article can befound online atwww.tandfonline.com/lmmp.

Materials and Manufacturing Processes, 31: 679684, 2016Copyright# Taylor & Francis Group, LLCISSN: 1042-6914 print=1532-2475 onlineDOI: 10.1080/10426914.2015.1037901

679


3/7

conditions and take decisions for adjusting the inputparameters of PMMA material in laser machiningindustry with minimum loss of the parent material.

MATERIALS AND METHODS

All the experiments have been performed by a Zechlaser machine that can provide up to 500W CW CO2laser with the mode structure of TEM01. It consists of

two parts: a laser generation system (ZLX5) and a lasercutting workstation (ZL 1010). In this experiment, lasermachine was associated with a computer system to con-trol the operation. AutoCAD software was used fordrawing. C-Cut software was applied to synchronizemovements of the laser head with cutting direction.The material used for this experiment was PMMA withthickness of 3.0mm. A digital caliper, resolution of0.01 mm and range from 0 to 150 mm, was employedto get the measurement of the lengths H1 and H2 asshown in Fig.1. Corners power, nozzle diameter, anddelay time were constant in this experiment. Table 1shows the list of the input parameters with differentlevels. Linear rectangular cuts were made on a PMMA

workpiece. A schematic of the cutting nozzle and opticsis shown in Fig.2. A converging lens (thickness 6 mm)with a fixed focal length (127 mm) was installed alongthe beam path. Standoff distance was varying from 1to 10 mm to produce laser spot on the workpiece. Tomeasure the upper kerf width, H1 and H2 side lines werepicked out three times at several locations and werecomputed by the following equation:

KerfwidthH1H2

2 1

The interaction of the laser beam and material is a com-plex phenomenon. It can be classified as absorption,

reflection, conduction, convection, melting, vaporiza-tion, radiation, scattering, and transmission [12]. Butlaser machining of PMMA is different from other metalbecause CO2 laser interaction with PMMA beginsvaporization while it is subjected to melt shearing [13,14]. Hence, the statement of the laser machining ofPMMA is vague information. The principle of FEShas been vindicated as an efficient tool to manage this

kind of information [9, 15]. Generally, researchers usestatistical analysis for evaluation and investigation ofthe laser parameters [16,17] based on experimental resultonly. On the other hand, the fuzzy logic model is amulti-input multi-output modeling technique which com-bines different heterogeneous data (such as experimentaldata, numerical data, mathematical data, recommen-dation, and suggestions). Also, we have found relativeerror in regression analysis for the experimental dataalone was 9.38% (R2 0.907), which is greater than fuzzymodel relative error 3.852% (R2 0.989). This paper con-centrates on fuzzy logic because our further implication isfuzzy controller for autolaser cutting process.

Generally the variables are defined as linguistic vari-ables. Each linguistic variable has linguistic values thatmay be expressed as synthetic language, words, and sen-tences. In this study, 3 linguistic values were used forinput variable (Low, Medium, and High) and 15 linguisticvalues were used for the kerf width (kw1, kw2, kw3, kw4,kw5, kw6, kw7, kw8, kw9, kw10, kw11, kw12, kw13,kw14, and kw15). PMMAs kerf width prediction ofFES was implemented on MATLAB R2009b software.For getting more precise results, more membershipfunctions were used in output. For fuzzification, twomembership functions are common: triangle andtrapezoidal membership function [18]. Triangle member-ship function was used because it is defined as a simplest

membership function [19]. In this research, IFTHENrules have been built up by a set of 64 experimental data,which is called as training data. Rules are built up in theMATLAB rule editor and can be accessed in the ruleviewer. In this CO2 laser study fuzzification of the

FIGURE 1.Kerf width measurement.

TABLE 1.Input variables and their levels

Input parameters Level 1 Level 2 Level 3 Units

Assist gas pressure: A 0.5 2.5 4.5 BarsLaser power: B 100 300 500 WattCutting speed: C 0.2 0.7 1.2 m=min

Standoff distance: D 1 5 10 Mm

FIGURE 2.A schematic of the cutting nozzle and optics.

680 A. HOSSAIN ET AL.


4/7

linguistic parameters were made by the following func-tion:

GPi1 i1; 0:5 i1 4:5

0; otherwise

2

LPi2 i2; 100 i2 500

0; otherwise 3

CSi3 i3 0:2 i3 1:2

0; otherwise

4

SDi4 i4; 1 i4 10

0; otherwise

5

KWo1 o1; 0 o1 1:9

0; otherwise

6

wherei1,i2,i3, and i4are input variables as assisting gaspressure, laser power, cutting speed, and standoff

distance, respectively, and o1 is the output variable kerfwidth.

By the implication process, fuzzy rules were evaluated.Mamdani implication was used because there were threemembership functions for each input linguistic variableswhich were taken into consideration. The implicationresults were analyzed by an aggregation process. In thisprocess, output results of the rules were aggregated intoa single fuzzy set. The fuzzification process, membershipfunction, and the linguistic fuzzy sets of assisting gaspressure (GP), laser power (LP), cutting speed (SD),standoff distance (SD), and kerf width (KW) intervalcan be deduced from Eqs. (2)(6) as follows:

lMediumGP

i10:52:50:5 ; 0:5 i1 2:54:5i1

4:52:5 ; 2:5 i1 4:50; i1 > 4:5

9=;

8 500

9=;

8 0:7

9=

;

8 10

9=;

8

a fuzzy logic-based prediction model for kerf width in laser beam machining

Documents