INTERNATIONAL JOURNAL OF MECHANICAL ENGINEERING AND TECHNOLOGY (IJMET)

Similar documents
Predetermination of Surface Roughness by the Cutting Parameters Using Turning Center

The Importance Of 3D Profilometry & AFM Integration

An Experimental Analysis of Surface Roughness

Central Manufacturing Technology Institute, Bangalore , India,

Comparison between 3D Digital and Optical Microscopes for the Surface Measurement using Image Processing Techniques

MODELLING AND OPTIMIZATION OF WIRE EDM PROCESS PARAMETERS

MetroPro Surface Texture Parameters

SURFACE TEXTURE *INTRODUCTION:

Volume 1, Issue 3 (2013) ISSN International Journal of Advance Research and Innovation

Key Words: DOE, ANOVA, RSM, MINITAB 14.

Basic Components & Elements of Surface Topography

Evaluation of Surface Roughness of Machined Components using Machine Vision Technique

Ch 22 Inspection Technologies

A.M.Badadhe 1, S. Y. Bhave 2, L. G. Navale 3 1 (Department of Mechanical Engineering, Rajarshi Shahu College of Engineering, Pune, India)

UNIT IV - Laser and advances in Metrology 2 MARKS

3D Surface Metrology on PV Solar Wafers

MACHINING SURFACE FINISH QUALITY USING 3D PROFILOMETRY

Development of an Artificial Neural Network Surface Roughness Prediction Model in Turning of AISI 4140 Steel Using Coated Carbide Tool

Optimization of Process Parameter for Surface Roughness in Drilling of Spheroidal Graphite (SG 500/7) Material

Keywords: Turning operation, Surface Roughness, Machining Parameter, Software Qualitek 4, Taguchi Technique, Mild Steel.

[Rao* et al., 5(9): September, 2016] ISSN: IC Value: 3.00 Impact Factor: 4.116

Volume 3, Issue 3 (2015) ISSN International Journal of Advance Research and Innovation

Condition Monitoring of CNC Machining Using Adaptive Control

CHAPTER 3 SURFACE ROUGHNESS

Optimization of Surface Roughness in End Milling of Medium Carbon Steel by Coupled Statistical Approach with Genetic Algorithm

RESEARCH ABOUT ROUGHNESS FOR MATING MEMBERS OF A CYLINDRICAL FINE FIT AFTER TURNING WITH SMALL CUTTING FEEDS

This presentation focuses on 2D tactile roughness measurements. Three key points of the presentation are: 1. Profiles are simply a collection of

SURFACE ROUGHNESS MONITORING IN CUTTING FORCE CONTROL SYSTEM

Measurements using three-dimensional product imaging

SURFACE TEXTURE PARAMETERS FOR FLAT GRINDED SURFACES

Surface Texture Parameters

PLASTIC FILM TEXTURE MEASUREMENT USING 3D PROFILOMETRY

Parametric Investigation of Single Point Incremental Forming For Al 8011A H-14

Optimization of Milling Parameters for Minimum Surface Roughness Using Taguchi Method

A Generic Framework to Optimize the Total Cost of Machining By Numerical Approach

Optimization of turning parameters for machinability using Taguchi method An experimental investigation

CNC Milling Machines Advanced Cutting Strategies for Forging Die Manufacturing

APPLICATION OF GREY BASED TAGUCHI METHOD IN MULTI-RESPONSE OPTIMIZATION OF TURNING PROCESS

BALKANTRIB O5 5 th INTERNATIONAL CONFERENCE ON TRIBOLOGY JUNE Kragujevac, Serbia and Montenegro

Application of Taguchi Method in the Optimization of Cutting Parameters for Surface Roughness in Turning on EN-362 Steel

Introduction to Image Processing and Analysis. Applications Scientist Nanotechnology Measurements Division Materials Science Solutions Unit

Surface Texture Measurement Fundamentals

Analysis and Optimization of Parameters Affecting Surface Roughness in Boring Process

Volume 4, Issue 1 (2016) ISSN International Journal of Advance Research and Innovation

Surface roughness parameters determination model in machining with the use of design and visualization technologies

Evaluation of Optimal Cutting Parameters in CNC Milling Of NIMONIC 75 Using RSM

Pradeep Kumar J, Giriprasad C R

Experimental Study of the Effects of Machining Parameters on the Surface Roughness in the Turning Process

Optimisation of Quality and Prediction of Machining Parameter for Surface Roughness in CNC Turning on EN8

Available online at ScienceDirect. Procedia Materials Science 6 (2014 )

INTELLIGENT LATHE TURNING COMPUTER CONTROL SYSTEM MODEL

Analyzing the Effect of Overhang Length on Vibration Amplitude and Surface Roughness in Turning AISI 304. Farhana Dilwar, Rifat Ahasan Siddique

FUEL CELL GAS DIFFUSION LAYER INSPECTION WITH 3D PROFILOMETRY

Optimizing Turning Process by Taguchi Method Under Various Machining Parameters

Multiple Regression-Based Multilevel In-Process Surface Roughness Recognition System in Milling Operations Mandara D. Savage & Joseph C.

A Comparative Study of Using Spindle Motor Power and Eddy Current for the Detection of Tool Conditions in Milling Processes

Surface Roughness Prediction of Al2014t4 by Responsive Surface Methodology

EVALUATION OF OPTIMAL MACHINING PARAMETERS OF NICROFER C263 ALLOY USING RESPONSE SURFACE METHODOLOGY WHILE TURNING ON CNC LATHE MACHINE

An objective method to measure and evaluate the quality of sanded wood surfaces

PROBE RADIUS COMPENSATION AND FITTING ERRORS IN CAD-BASED MEASUREMENTS OF FREE-FORM SURFACE: A CASE STUDY

SURFACE QUALITY & MACHINIG SYMBOLS Introduction Types of surfaces Nomenclature of surface texture Surface roughness value Machining symbols Roughness

CALCULATION OF 3-D ROUGHNESS MEASUREMENT UNCERTAINTY WITH VIRTUAL SURFACES. Michel Morel and Han Haitjema

CORRELATION AMONG THE CUTTING PARAMETERS, SURFACE ROUGHNESS AND CUTTING FORCES IN TURNING PROCESS BY EXPERIMENTAL STUDIES

TOOL WEAR CONDITION MONITORING IN TAPPING PROCESS BY FUZZY LOGIC

[Mahajan*, 4.(7): July, 2015] ISSN: (I2OR), Publication Impact Factor: 3.785

Optimization of Process Parameters of CNC Milling

EFFECT OF CUTTING SPEED, FEED RATE AND DEPTH OF CUT ON SURFACE ROUGHNESS OF MILD STEEL IN TURNING OPERATION

Machining and metrology systems for free-form laser printer mirrors

Experimental accuracy assessment of different measuring sensors on workpieces with varying properties

CHAPTER 4. OPTIMIZATION OF PROCESS PARAMETER OF TURNING Al-SiC p (10P) MMC USING TAGUCHI METHOD (SINGLE OBJECTIVE)

Multi-Objective Optimization of Milling Parameters for Machining Cast Iron on Machining Centre

Analysis and Effect of Process Parameters on Surface Roughness and Tool Flank Wear in Facing Operation

Optimization of Turning Process during Machining of Al-SiCp Using Genetic Algorithm

Application of laser optical displacement sensor to foundry processes control and research

Optimization of End Milling Process Parameters for Minimization of Surface Roughness of AISI D2 Steel

Multi-Objective Optimization of End-Milling Process Parameters Using Grey-Taguchi Approach

Study & Optimization of Parameters for Optimum Cutting condition during Turning Process using Response Surface Methodology

Simulation Approach And Optimization Of Machining Parameters In Cnc Milling Machine Using Genetic Algorithm.

Experimental Investigation of Material Removal Rate in CNC TC Using Taguchi Approach

OPTIMIZATION OF CNC END MILLING OF BRASS USING HYBRID TAGUCHI METHOD USING PCA AND GREY RELATIONAL ANALYSIS

Cutting Force Simulation of Machining with Nose Radius Tools

COMPRESSION SET IN SITU MEASUREMENT USING 3D PROFILOMETRY. Compression Set time: 1 min 10 min 30 min 60 min. Prepared by Duanjie Li, PhD

Improving Productivity in Machining Processes Through Modeling

PREDICTION AND OPTIMIZATION OF SURFACE ROUGHNESS BY COUPLED STATISTICAL AND DESIRABILITY ANALYSIS IN DRILLING OF MILD STEEL

Use of Artificial Neural Networks to Investigate the Surface Roughness in CNC Milling Machine

Saurabh GUPTA and Prabhu RAJAGOPAL *

Measurement of Surface Roughness Using Image Processing

Thickness of the standard piece: 10 mm The most important calibration data are engraved in the side face of the specimen.

NUMERICAL METHOD TO ESTIMATE TOLERANCES COMBINED EFFECTS ON A MECHANICAL SYSTEM

CHAPTER 5 SINGLE OBJECTIVE OPTIMIZATION OF SURFACE ROUGHNESS IN TURNING OPERATION OF AISI 1045 STEEL THROUGH TAGUCHI S METHOD

Optimization of Roughness Value by using Tool Inserts of Nose Radius 0.4mm in Finish Hard-Turning of AISI 4340 Steel

Analysis of Image and Video Using Color, Texture and Shape Features for Object Identification

SOFTWARE POST-PROCESSING OF DATA STRUCTURE OBTAINED FROM MEASURING DEVICE BALLBAR QC20

SERBIATRIB th International Conference on Tribology. Kragujevac, Serbia, May 2011

Micro Cutting Tool Measurement by Focus-Variation

Empirical Modeling of Cutting Forces in Ball End Milling using Experimental Design

FULLY AUTOMATIC ROUGHNESS MEASUREMENT "IN MINIATURE"

OPTIMIZATION OF MACHINING PARAMETERS FROM MINIMUM SURFACE ROUGHNESS IN TURNING OF AISI STEEL

ROUNDTEST RA-2200 SERIES

OPTIMIZATION OF TURNING PARAMETERS FOR SURFACE ROUGHNESS USING RSM AND GA

Transcription:

INTERNATIONAL JOURNAL OF MECHANICAL ENGINEERING AND TECHNOLOGY (IJMET) International Journal of Mechanical Engineering and Technology (IJMET), ISSN 0976 ISSN 0976 6340 (Print) ISSN 0976 6359 (Online) Volume 3, Issue 1, January- April (2012), pp. 332-341 IAEME: www.iaeme.com/ijmet.html Journal Impact Factor (2011): 1.2083 (Calculated by GISI) www.jifactor.com IJMET I A E M E MEASUREMENT OF CUTTING TOOL CONDITION BY SURFACE TEXTURE ANALYSIS BASED ON IMAGE AMPLITUDE PARAMETERS OF C-SIC MACHINED SURFACE AN EXPERIMENTAL APPROACH 1 Pallavi.H.Agarwal, 2 Dr.P.M.George and 3 Dr.L.M.Manocha 1 Research Scholar, S.P.University, Vallabh-Vidyanagar, Gujarat,India Email :pallavi_ruhi@yahoo.co.in 2 Professor and Head Mechanical Engineering Department, Birla Vishwakarma Mahavidyalaya, Vallabh-Vidyanagar, Gujarat,India 3 Professor, Material Science Department, S.P.University, Vallabh-Vidyanagar, Gujarat,India ABSTRACT In this paper an experimental investigation is presented for accomplishing surface texture analysis using machine vision based system for measuring the condition of the cutting tool. Texture of the machined surface provides reliable information regarding the extent of the tool wear because tool wear affects the surface roughness dramatically. Analysis of the machined surface images of C-SiC material is done by grabbing the image using a scanning electron microscope, amplitude parameters based approach for analysis of machined surface is used. Machined surfaces are investigated using surface metrology software TRUEMAP. Since the machined surface is a negative replica of the shape of the cutting tool and reflects the volumetric changes in the cutting edge shape, it is more suitable to analyze the machined surface than to look at the cutting tool. However, no work has been performed on the development of surface texture of machined work piece that provide information on the condition of cutting tool employed for machining C-SiC composite material. In this paper, a non-contact method using machine vision with surface metrology software is presented for inspecting surface roughness of machined surfaces. Machined surfaces produced under different cutting conditions are studied to measure the cutting tool condition. A strong correlation is found between tool wear and surface texture of the machined surfaces. Results prove that the approach is effective in measuring the condition of the cutting tool through amplitude parameters. Keywords: surface texture, surface roughness, tool wear, C-SiC (carbon silicon carbide), amplitude parameters 332

1. INTRODUCTION In earlier days, the tool condition was determined by using three basic methods. They are, monitoring of specific machine tool parameters in order to infer the tool condition, direct observations made on the cutting tool and information taken from the chips produced by the cutting tool. However no work has been reported on the development of surface texture that provides information on the condition of the tool employed in machining the carbon silicon carbide composite. An overview of the various methods employed for monitoring tool condition by work piece texture analysis has been done. Most of the methods used for tool condition monitoring involve processing information such as acoustic emission (AE), measurement of cutting forces, etc. Even though all these techniques perform reasonably well, the implementation usually requires specially designed equipment. On line process monitoring has been an active area of research because it is recognised as an essential part of fully automated manufacturing systems. One of the important parameters to be controlled in machining is surface finish. Surface finish is an important attribute of quality in any machining operation. Many researchers have studied the influence of various factors that can improve surface finish of a work piece. The simplest procedure is visual comparison with an established standard. This procedure is simple and can be accomplished in real time as it is independent of the machining process. Machining can be continued as the images of work piece are captured and analyzed. Zhong et al [6] presented the relation between surface roughness with machining parameters like feed rate, nose radius and cutting speed and also discussed limitations of the stylus instrument. The texture of the machined surface is closely related to the cutting tool condition (tool wear) and the arithmetic average roughness (Ra) of the machined surfaces [5]. C.Bradley et al [2] showed that the machined surface texture can be used to estimate tool wear. The above literature review clearly indicates that surface texture of the work piece is in good relation with the condition of the tool. The high spatial resolution, measurement flexibility and good accuracy of the present machine vision system, has made this easier. The computer vision system provides three dimensional roughness values of the surfaces such as RMS Surface Roughness (Sq), Skewness (Ssk) and Kurtosis (Sku) etc. The stylus methods are popular in contact measurement category but the major limitation with this measurement is, it requires direct contact with the machined surface and resolution of this instrument is influenced by the diameter of the measuring probe tip, which restricts the speed of measurement. In addition, the Ra value is measured along a single line of a cut surface and fails to capture the overall features of a machined surface. In this paper, a non contact method using machine vision for inspecting surface roughness of machined C-SiC surfaces produced by drilling holes and varying the cutting conditions is studied to analyse the cutting tool condition. This paper also illustrates the application of image amplitude parameters [5] in predicting the condition of the cutting tool. Image processing and machine vision technology improves productivity and quality management and provides a competitive advantage to industries that employ this technology. The surface metrology software TRUEMAP offers image processing functions, which simplify calculations of amplitude parameters like RMS, skewness, kurtosis etc. And also plots the machined surfaces in 3D exploded view. With the help of this software we can extract information that relates to the extent of tool wear at various conditions of different machining processes. 333

1.1 Surface Texture of a Machined surface as a Basis for Cutting Tool Condition Monitoring Measurement of workpiece surface texture provides a spatial signature of the interaction between the cutting tool and the work piece surface. For a given tool and workpiece, many factors can influence the form of this spatial signature such as feedrate, spindle speed, machine tool alingment and tool setup. It is assumed here that the surface features generated by the wear of the tool can be seperated from the other factors. The surface texture of a part is indicative of all the machine tool performance factors present during machining : examples are tool wear, machine tool rigidity, bearing wear, chatter and sideway errors. The objective is to extract the surface texture signature component, due to tool wear, from the other texture components and employ it as an indication of the tool condition. This technique is a direct tool condition measurement method, in contrast to the indirect measures, employing intermediary phenomena, such as cutting force or acoustic emission. Researchers have studied the influence of various factors that can improve the surface finish of a work piece, in this work cutting speed, feed rate and drill size are included. 1.2 Amplitude Parameters used for Surface Texture Analysis The surface texture parameters describe the amplitude related properties of the machined surface and their significance are given in Table 1. Table 1 Amplitude parameters considered for surface texture analysis Skewness( Ssk) Kurtosis(Sku) RMS roughness (Sq) Result Positive Value>3 Low value Good surface finish Negative Value<3 High value High surface roughness Reason Few number of peaks than valleys in 3D view plots, more number of peaks More number of peaks than valleys in 3D view plots, well spread distribution 1.3 Experimental Set up and Procedure To establish the relation between the surface texture of the machined surface roughness and the tool condition, various experiments were conducted on the carbon silicon carbide composite by varying the machining conditions. The images of the machined work are grabbed using the SEM microscope and analysed using the software TRUEMAP and the values of different amplitude parameters were obtained. In this research work the machine used is Denford CNC machine with Fanuc controller with a six station automatic tool changer. The spindle speed range available is 0-4000 rpm and the feed range available 0-1000 mm/min. The factorial 334

approach [16] is used for experimentation as it is very effective in dealing with multi variables. This method is a powerful design of experiment tool, which provides a simple, effective and systematic approach to experimentation. This method reduces the number of experiments that are required to model the response functions. Traditional experimentation is one factor at a time experiment, where one variable is changed while the rest are held constant. The process parameters considered in this experiment are spindle speed, feed rate and drill size. The experiments are planned according to 2 3 with 4 centre points. The design matrix used in shown in Table.2. Table 2 Design matrix for experimentation Experiment No Run. No Experimental Factors A(speed) B(feed) C(drill dia) 1 6 - - - 2 9 + - - 3 4 - + - 4 8 + + - 5 12 - - + 6 10 + - + 7 2 - + + 8 11 + + + 9 5 0 0 0 10 1 0 0 0 11 3 0 0 0 12 7 0 0 0 According to the capability of the commercial machine available for machining this material the range and the number of levels of the parameters selected are as given in Table 3. Table 3 Machining Parameters and their levels Parameter Unit -1 0 1 Spindle speed rpm 1500 2250 3000 Feed rate mm/min 30 35 40 Drill size mm 1 2 3 (HSS) A sub image of the original image of size 512x512 is used for further processing with the image metrology software TRUEMAP and all the amplitude parameters are obtained with the help of this software. This system is faster than the stylus based system. 335

2. Analysis of Machined Surfaces Machined surface roughness measurement can be done in two ways. One direct measurement of average surface roughness (Ra) with stylus instrument. This method requires direct contact of work piece with measuring probe tip. The second method, being non-contact captures the images of work piece surfaces after machining with SEM and then these images are analyzed to obtain amplitude parameters used for surface roughness estimation of machined surfaces. Hence the procedure adopted for the current research work is shown in Figure.1 2.1 Surface Roughness Measuring techniques Direct Measurement [Stylus instrument] The average roughness Ra of the machined surface is obtained directly by the stylus instrument. The surfaces of the work pieces which were machined by different machining processes are subjected to this test. The roughness values thus obtained from this instrument compared with the amplitude parameter values 2.2 Machine vision system The basic steps in machine vision system are shown in Figure 2. A machine vision system analyses images and procedures description of the images. Fig.2 Basic vision system 336

Figure 1 Procedure adopted for current work Machine vision as applied to manufacturing extracts information from visual sensors to make intelligent decisions. Such decisions are needed in quality control (detection of defects), process monitoring (prevention of defects), product routing (parts acquisition and sorting) and statistical reporting (performance evaluation). The three main industrial application categories are inspection, identification and machine guidance. Inspection by visual means is a very obvious and potentially beneficial application area, which can be used as a powerful tool in automating quality control procedures and in obtaining specific quantitative measurements of important parameters in manufacturing process. Image capturing and analysis was done with Hitachi S-3000 scanning electron microscope image processing can mean quality enhancement, coding and analysis and processing, which includes image formation to comprehension. Image analysis implies the description and measurement of image properties. By using the surface metrology software TRUEMAP, the surface roughness amplitude parameters and spatial parameters are calculated. These values are then analysed for giving an indication on the cutting tool condition. The parameters evaluated with the software are as follows: Kurtosis it is a measure of the peakedness or sharpness of the surface. A Gaussian surface has kurtosis value of 3. A surface that is centrally distributed has a kurtosis value greater than 3. A surface that has a well spread out distribution has a kurtosis value of less than 3. By using a combination of the skewness and kurtosis values, it is possible to identify plateau honed surfaces that have relatively flat top, but contains deep valleys. Skewness measures the symmetry of the variation of a surface about its mean plane. A Gaussian surface, having a symmetrical shape for the height distribution, has a skewness of zero. A plateau honed surface with predominant plateau and deep valleys will tend to 337

have a negative skew, whereas a surface comprised of disproportionate number of peaks will have positive skew. The Root Mean Square (RMS) roughness parameter, Sq, is the root mean square of the surface departures from the mean plane within the sampling area. The Power Spectrum image is computed directly from the results of passing the surface data through a Fast Fourier Transform (FFT) algorithm. The FFT algorithm outputs real and imaginary components which can be used to obtain amplitude and phase information of the surface. The low frequency components of the surface are displayed in the centre of this image. The power spectrum image displays repeated patterns as narrow peaks, the co-ordinates of which describe their periodicity and direction. The Autocorrelation image is obtained by performing a cross correlation of a surface with itself. The general shape of the autocorrelation image is often used to determine some meaningful information regarding the surface. For example, for a surface with a predominant lay (anisotropic surface), the autocorrelation image will have a central lobe that extends along one axis. 3. RESULT AND DISCUSSION The images of the machined surface obtained with different machining conditions are shown in Fig.3. The images are then analysed using the TRUEMAP software and the amplitude parameters obtained are shown in Table 4. Figure 3 Images of the machined surface 338

Table 4: Result table for amplitude parameters Experiment No Run. No & Image No. Experimental Factors Amplitude Parameters for surface texture analysis A(speed) B(feed) C(drill dia) Sq Sku Ssk 1 6 - - - 83.24 2.130 0.750 2 9 + - - 63.11 2.678 0.795 3 4 - + - 64.72 2.905 0.858 4 8 + + - 77.81 2.107 0.616 5 12 - - + 61.73 2.311 0.076 6 10 + - + 44.43 4.089 0.524 7 2 - + + 45.11 6.145 1.090 8 11 + + + 45.62 4.343 0.489 9 5 0 0 0 65.67 3.705 1.275 10 1 0 0 0 58.11 3.937 1.168 11 3 0 0 0 59.81 3.381 1.046 12 7 0 0 0 50.55 4.293 1.060 From the Table 4 it is clear that the RMS roughness values (Sq) are less for experiment no.6, 7 and 8 and the values for kurtosis (Sku) are more than 3 and skewness (Ssk) is positive, these values suggest that the surface finish produced is good. For the surface finish to be good the tool should be relatively new, the speed should be high as can be observed from experiments 6 and 8 as the run for these experiments has been 10 and 11. For experiment 7 even at low speed the surface finish obtained is good as the experiment has been conducted second when the tool was relatively new. As the speed decreases and the tool wear occurs the composite shows pitting as can be interpreted from the values of high RMS roughness and skewness value less than 3 from experiment no. 5 which was conducted twelfth. Experiments 9,10,11 and 12 have been conducted at low speeds and feed so,inspite of these runs been conducted earlier when the tool was a 2mm diameter tool not used before the values of RMS roughness are high and skewness values are approximately equal to 3, indicating that the surface finish achieved was not good. Experiments 1, 2, 3 and 4 have been conducted with 1mm diameter drill, as can be observed the values of RMS roughness are high and skewness value less than 3, when the speed is low and feed is low generating a poor surface finish. It is clearly indicated that as the wear on the tool increases and the speed decreases the surface finish deteriorates. Hence it can be seen that the surface textures vary significantly as the tool wears. When the tool is sharp, the surface textures are very regular along the direction of the machining process. However, when the tool becomes dull, the surface texture becomes irregular. In the absence of severe cutting tool vibrations, the cut surface is almost a negative imprint of the tool. As the tool wears, the general orientation of the line texture can also change. It is easier to analyse the machined surface than to look at certain portions of the cutting tool. This system provides sufficient information about the machined surface and is much faster than the stylus based system. Fig.4 gives the 3D plots of the images and gives the three dimensional view of the peaks and valleys of 339

varying heights and depths which also correlates with the tool condition which was interpreted using amplitude parameters. Figure 4 3D plots of images 4. CONCLUSION In the present work experiments have been conducted on carbon silicon carbide using HSS drills with different machining parameters. Factorial design method is used to conduct the experiments. The images have been analysed with image metrology software TRUEMAP. Various amplitude parameters have been obtained. In this work it has been shown that with the application of machine vision technique it is possible to effectively measure the tool condition by analysing the machined surfaces. In this work, image of the machined surface was used in experimental investigation for measuring the condition of the tool instead of capturing directly the image of the cutting tool and hence this feature saves a lot of time. This methodology ensures that the machining process is not interrupted for measurements. Experiments prove that the machine vision system is independent of the machining process and can be adapted to any kind of surface roughness investigation. Hence the condition of the HSS tool while machining carbon silicon carbide can be assessed using surface texture as a basis with amplitude parameters. 340

5. REFERENCES [1] M.A.Manna, Zhu Mian and A.A.Kassim, Tool Wear Monitoring Using a Fast Hough transform of Images of Machined Surfaces, (2004) Machine Vision and Applications. Vol.15, pp.156-163 [2] C.Bradley and Y.S.Wong, Surface Texture Indicating Tool Wear- A Machine Vision Approach. International Journal of Advanced Manufacturing Technology (2001), Vol. 17, pp. 435-443 [3] B.Y.Lee, H.Juan and S.F.Yu, A Study of Computer Vision for Measuring Surface Roughness in the Turning Process, International Journal of Advanced Manufacturing Technology,(2002)Vol.19,pp 295-301 [4] Kjeld Bruno Pedersen, Wear Measurement of Cutting Tools by Computer Vision, Journal Mech. Tools Manufacturing, (1990),Vol.30,pp.131-139 [5] B.S.Prasad and M.M.M.Sarcar, Measurement of Cutting Tool condition by Surface Texture Analysis Based on Image Amplitude Parameters of Machined Surfaces-An Experimental Approach, MAPAN-Journal of Metrology Society of India, (2008),Vol.23,pp.39-54 [6] Z.W.Zhong, L.P.Khoo and S.T.Hao, Prediction of Surface Roughness of Turned Surfaces Using Neural Networks, International Journal of Advanced Manufacturing Technology, (2006), Vol.28, pp. 688-693 [7] B.Dhanashekar and B.Ramamoorthy, Evaluation of Surface Roughness Using a Image Processing and Machine Vision System, MaPAN-Journal of Metrology Society of India, (2006), pp. 9-15 [8] C.Milton Shaw, Metal Cutting principles, Oxford University Press, New York (2005) 341