International Journal of Mechanical Engineering and Technology (IJMET), ISSN 0976 6340(Print), ISSN 0976 6359(Online) Volume 2, Issue

ue 2, August- December (2011), IAEME

INTERNATIONAL JOURNAL OF MECHANICAL ENGINEERING AND TECHNOLOGY (IJMET)

ISSN 0976 6340 (Print) ISSN 0976 6359 (Online) Volume 2, Issue 2, August- December (2011), pp. 126-137 IAEME: www.iaeme.com/ijmet.html Journal Impact Factor (2011) - 1.2083 (Calculated by GISI) www.jifactor.com

IJMET
IAEME

EVALUATION OF MACHINABILITY CHARACTERISTICS OF INDUSTRIAL CERAMIC COATINGS USING GENETIC PROGRAMMING BASED APPROACH
Mohammed Yunus1, Dr. J. Fazlur Rahman2 and S.Ferozkhan3

1. Research scholar, Anna University of Technology Coimbatore Professor, Department of Mechanical Engineering H.K.B.K.C.E., Bangalore, India. yunus.mohammed@rediffmail.com Mobile: +919141369124 2. Supervisor, Anna University of Technology Coimbatore Professor Emeritus, Department of MechanicalEngineering H.K.B.K.C.E., Bangalore, India. jfazlu2003@yahoo.co.in Mobile: +919845350742 3. Lecturer, Department of Mechanical Engineering, H.K.B.K.C.E., Bangalore, India. feroz_deen@yahoo.co.in ABSTRACT Ceramic coated components have the advantage features of both metal and ceramics, i.e. good toughness, high hardness and wear resistance. Despite their outstanding characteristics, ceramic materials are not used in many cases due to high cost of machining. A major drawback to engineering applications of ceramic is due to their brittleness and fracture toughness, which makes them difficult and costly to machine. In order to study the precision machining processes of ceramics like grinding and lapping, number of trial experiments were conducted to find out the influence of various cutting parameters on surface quality production as well as grinding and lapping performances. Surface grinding of ceramic coating materials was done on samples specimens coated with Alumina (Al2O3), Alumina-Titania (Al2O3-TiO2) and Partially stabilized zirconia (PSZ )using diamond and CBN (cubic boron nitride)

126

International Journal of Mechanical Engineering and Technology (IJMET), ISSN 0976 6340(Print), ISSN 0976 6359(Online) Volume 2, Issue 2, August- December (2011), IAEME

grinding wheels. Based on the experimental results, the influence of cutting parameters, namely, cutting force, surface roughness and bearing area characteristics were evaluated and optimum machining conditions have been suggested for better performance in precision machining of ceramic coating materials. Genetic programming (GP) has proved to be a highly versatile and useful tool for identifying relationships in data for which a more precise theoretical construct is unavailable. The prediction of machinability of ceramic oxide coatings, depending on input parameters (type of grinding wheels, type of coatings, depth of cut, grinding speed, lapping duration etc.), was made by means of genetic programming using data values on the outputs ( normal and tangential forces, surface roughness Ra, Rt etc.) of grinding and lapping operations of experimental results already made. This paper highlights how one can use GP technique in the prediction of output parameters. Commercial Genetic Programming (GP) software-Discipulus is used to derive a mathematical modelling of relations for various input and output parameters used in characterisation. A special genetic approach for the modelling of Machinability characteristics in coated components is proposed on the basis of a training data set. Different types of genetic models for prediction of different machinability properties with greater accuracy (less than 1%) were also proposed by simulated evolution. Keywords: Evolutionary computation; Genetic programming; Cutting force; Diamond and CBN grinding wheel; Precision machining; Grinding and Lapping; Optimizations of Cutting parameters; Precision Machining Processes; Surface roughness.
.

1. INTRODUCTION With the projected wide spread applications of ceramic coating materials, it is necessary to develop an appropriate technology for their efficient and cost effective machining processes [5] & [8-[10 ]. Grinding of ceramics is a difficult task, as it is generally associated with cracking, splintering and delamination of surfaces. Conventional processes and tools are not generally suited for the machining of ceramics. Standard machining tools can be used with optimization of machining parameters in operating conditions [ 7-10 ]. Various precision machining techniques that could be adopted for efficient machining of ceramic materials, namely grinding and lapping processes are studied in detail for the parametric influence of various cutting parameters of precision machining of ceramic coating materials [12-13]. Ceramic coated components used in industrial applications, generally require post treatments like heat treatment and surface finishing by precision machining [1-5]. Good surface finish and high efficiency in machining to meet the demands of tight tolerances are generally achieved by grinding, lapping and polishing like precision machining processes [3]. Grinding of ceramics is a difficult task, as it is generally associated with
127

International Journal of Mechanical Engineering and Technology (IJMET), ISSN 0976 6340(Print), ISSN 0976 6359(Online) Volume 2, Issue 2, August- December (2011), IAEME

cracking of surface. In order to study the effect of precision machining processes[14-15], experiments were conducted to check the machining parameters like surface quality, grinding forces etc. on ceramic coated components for different machining conditions. The main object of this study is to evaluate the behavior of A, AT, PSZ, Super-Z alloy and ZTA ceramic coating materials subjected to different grinding conditions. The performance was evaluated by measuring grinding force [14], surface finish [8-9] and bearing area characteristics and also using oil film retainability characteristics. 1.2 Genetic Programming (GP) GP works with a large population of candidate programs and uses the Darwinian principle of survival of the fittest to produce successively better programs for a given problem and evolves a program that predicts the target output from a data file of inputs and outputs [17-19]. The programs evolved by GP software Discipulus [20], in this case Java, C/C++ and assembly interpreter programs represents a mapping of input to output data. This is done by Machine Learning that maps a set of input data to known output data. The aims of using the machine learning technique on engineering problems are to determine data mining and knowledge discovery. GP provides a significant benefit in many areas of science and industry [21-25]. The Discipulus GP [20] system uses AIM Learning Technology. AIM stands for Automatic Induction of Machine Code. AIM Learning and Discipulus deal with the machine learning speed problem. This speed allows the analyst to able to make many more runs to investigate relationships between data and output, assess information content of data streams, uncover bad data or outliers, assess time lag relationships between inputs and outputs, and the like. The evolved models have been used to develop process prediction or to control algorithms. Hence GP technology has been selected for the present work. GP solutions are computer programs that can be easily inspected, documented, evaluated, and tested. The GP solutions are easy to understand the nature of the derived relationship between input and output data and to examine the uncover relationships that were unknown before. Genetic Programming evolves both the structure and the constants to the solution simultaneously. Discipulus GP strongly discriminates between relevant input data and inputs that have no bearing on a solution [20]. In other words, Discipulus performs input variable selection as a by-product of its learning algorithm. The following step by step procedure will be implemented for a steady state GP algorithm [17-19]. 1. Initialization of population: Generate an initial population of random compositions of the functions and terminals of the problem (computer programs). 2. Fitness evaluation: Execute each program in the population, randomly it selects some programs and assign it a fitness value according to how well it
128

International Journal of Mechanical Engineering and Technology (IJMET), ISSN 0976 6340(Print), ISSN 0976 6359(Online) Volume 2, Issue 2, August- December (2011), IAEME

solves the problem by mapping input data to output data. Some programs are selected as best programs (winner programs) 3. Create a new population of computer programs by exchanging parts of the best programs with each other (called crossover). 4. Copy the best existing programs. 5. Create new computer programs by randomly changing each of the tournament winners to create two new programs mutation. 6. Iterate Until Convergence. Repeat steps two through four until a program is developed that predicts the behavior sufficiently. GP has been successfully used to solve problems in a wide range of broad categories [17-26]: 1. Systems Modelling, Curve Fitting, Data Modelling, and Symbolic Regression 2. Industrial Process Control 3. Financial Trading, Time Series Prediction and Economic Modelling 4. Optimisation and scheduling 5. Medicine, Biology and Bioinformatics 6. Design 7. Image and Signal processing 8. Entertainment and Computer games 2. EXPERIMENTAL PROCEDURE Three different commercially available ceramic coating powder materials namely, Alumina (Al2O3), Alumina-Titania (Al2O3-TiO2), Partially Stabilized Zirconia (PSZ) were used for the preparation of coatings [3] &[7]. A 40 KW Sulzer, Metco plasma spray system with 7MB gun is used for this plasma spraying of coatings. Mild steel plates of 50x50x6 mm were used as substrate to spray the ceramic oxides. They were grit blasted, degreased and spray coated with a 50 to 100 microns Ni Cr Alumel bond coat. The above ceramic materials were then plasma sprayed using optimum spray parameters. 2.1 Precision Machining of Ceramic Coating Grinding: Using diamond and CBN grinding wheels [20] with the surface grinding trials were conducted with the grinding conditions mentioned below in table 1. Machining trials were conducted on different ceramic coated specimens (A, AT and PSZ ceramic coatings).
Table1. Grinding specifications Type of grinding Surface grinding Grinding wheel used Wheel speed used Depth of grinding Work feed Diamond of 185 grit size CBN of 120 grit size 5 to 30m/sec 10 to 40m 0.5 mm/sec Table2. Lapping specifications Type of Machine Flat surface hand lapping Lapping medium Diamond size Lapping speed Lapping pressure Lapping time duration Abrasive and diamond compound paste. 2-10 m 0.2 m/sec 0.05 MPa 25 minutes

The main object of this study is to evaluate the behavior of A, AT and PSZ ceramic coatings subjected to different grinding conditions. The performance [14] was evaluated by measuring

129

International Journal of Mechanical Engineering and Technology (IJMET), ISSN 0976 6340(Print), ISSN 0976 6359(Online) Volume 2, Issue 2, August- December (2011), IAEME

1. Grinding force ( both normal and tangential forces) 2. Surface finish produced which also includes the bearing area characteristics 2.2 Force Measurement The normal grinding force (Fn) and the tangential force (Ft) were measured using grinding dynamometer [14].The ground samples were measured for different surface finish parameters such as Ra, Rt, and tp values using Taylor Hobsons stylus tracing profilometer. 2.3 Lapping A circular disc of 50 mm in diameter made of bright steel was coated with NiCrAlumel bond coat of thickness 75m and subsequently coated with different ceramic coating materials namely, Alumina (A), Alumina-Titania (AT), Partial Stabilized Zirconia (PSZ), Super-Z alloy and ZTA [19-20]. Samples were initially ground to achiev pre lapping finish and then further lapped under the conditions mentioned above in table 2. The process variables chosen were lapping time (ranging 5 to 25 minutes) and size of the diamond abrasives in lapping [5]. The lapped discs were thoroughly cleaned and measurement in respect of surface finish was made using Taylor Hobsons surface finish profilometer. 3. Genetic Programming Methodology: Genetic programming can be the most general approach among evolutionary computation methods in which the coatings subjected to different precision machining operations and cutting parameters variation adaptation are those hierarchically organized computer programs whose size and form dynamically change during simulated evolution. The initial population in GP is obtained by the creation of random computer programs consisting of available function genes from set F and available terminal genes from set T. In Genetic programming modelling, it is necessary to select suitable terminal from set F and available terminal genes from set f (0)[17-25]. From these, the evolutionary process will try to build as fit an organism (i.e. mathematical model) as possible for machinability characteristics prediction. The organisms consist of both terminal and function genes and have the nature of computer programs which differ in form and size. In our case the set of terminal genes f (0) is: f (0) = {Process inputs}.The selected set of function genes F is: F = {+, -, *, /}, where +,-,*, / are the mathematical operation of addition, subtraction, multiplication and division. The quality of the individual organism (i.e. prediction) is found out using fitness function. In our case, four different functions are used. Process Inputs: Depth of cut (m), Hardness of a wheel, Hardness of coatings (HV),

130

International Journal of Mechanical Engineering and Technology (IJMET), ISSN 0976 6340(Print), ISSN 0976 6359(Online) Volume 2, Issue 2, August- December (2011), IAEME

Grinding speed (m/sec), Toughness (MPam) Thermal conductivity (W/m K) Thermal Diffusivity (10-7m2/sec) Measured Process Outputs f(0) Normal Grinding force Fn (N) Tangential Grinding force Ft (N) Surface roughness Ra (m)
Table 3. Experimental Results of evaluating the Surface Roughness Ra during surface grinding for different coatings Experimental results Depth Grinding of cut speed in m (V0) (V1) 10 10 10 10 20 20 20 20 30 30 30 30 40 40 40 40 5 10 15 30 5 10 15 30 5 10 15 30 5 10 15 30 Ra in m for PSZ ground with Diamond wheel 1 0.9 0.85 0.8 1.3 1.1 0.95 0.7 1.1 0.98 1 0.62 0.89 0.75 0.68 0.63 Ra in m for AT ground with Diamond wheel 0.82 0.82 0.95 0.9 0.9 0.84 0.8 0.85 0.95 0.77 0.78 0.73 1 0.75 0.9 0.6 Ra in m for AT ground with CBN wheel 1.9 1.7 1.65 1.7 1.6 1.6 1.5 1.4 1.8 1.5 1.4 1.3 1.1 0.9 0.82 0.73 Ra in m for A ground with Diamond wheel Ra in m for A ground with CBN wheel 1 0.8 0.65 0.64 1.4 1.3 1.2 1.1 1.5 1.4 1.2 1.15 1.7 1.6 1.5 1.4 Ra in m for PSZ ground with CBN wheel 1.5 1.4 1.25 1.15 1.5 1.35 1.05 1.2 1.4 1.2 1.1 1.25 1.1 1 0.98 0.93 GP Output PSZ using CBN wheel

0.85 0.8 0.82 0.81 1.1 1 0.95 0.79 1.2 1.1 1 0.71 1.1 1 0.8 0.7

1.620467 1.449796 1.360538 1.253909 1.357232 1.348581 1.032365 1.209249 1.291292 1.209249 1.130757 1.360538 1.003651 1.000821 0.971932 0.891324

Table 4. Experimental Results of evaluating Normal force Fn during surface grinding for different coatings Experimental results Depth of cut in m (V1) 10 20 30 40 10 20 30 40 10 20 30 40 10 20 30 40 Grinding speed in m/sec (V0) 5 10 15 30 5 10 15 30 5 10 15 30 5 10 15 30 Fn in N for PSZ using diamond wheel 0.5 1.7 0.7 1.1 1.25 2 1.3 1.8 1.3 2.2 1.5 1.8 1.7 3 1.8 2 Fn in N for AT using diamond wheel 2.5 0.42 0.55 0.7 2.5 2.1 0.6 0.75 3 2.8 0.7 0.81 3.8 3.1 0.9 1.3 Fn in N for AT using CBN wheel 4 5.2 5 4.8 4.1 5.4 5.8 5.2 4.8 5.6 6.2 5.2 5 5.7 6.5 6.2 Fn in N for A using diamond wheel 2.8 0.5 0.6 0.65 2.7 2.2 0.7 0.72 3.3 3.1 0.78 0.825 3.9 3.5 1.1 1.2 Fn in N for A using CBN wheel 4.2 5.2 5.5 5.4 4.6 5.9 6.5 6.4 5.3 6 6.6 6.4 5.6 6.2 7 6.8 Fn in N for PSZ using CBN wheel 3.9 5.2 5.5 5.4 4.1 5.5 6 5.6 4.7 5.9 6.4 5.6 4.9 6.1 6.75 6.4 GP Output PSZ using CBN wheel

4.074322 5.414451 5.40726 5.333083 3.996253 5.40726 5.923153 5.607811 4.746202 5.73641 6.407451 5.670387 4.962764 5.923153 6.853525 6.407451

131

International Journal of Mechanical Engineering and Technology (IJMET), ISSN 0976 6340(Print), ISSN 0976 6359(Online) Volume 2, Issue 2, August- December (2011), IAEME
Table 5. Experimental Results of evaluating Tangential force Ft during surface grinding for different coatings Experimental results Depth Grinding of cut speed in in m m/sec ( V1) (V0) 10 5 20 10 30 15 40 30 10 5 20 10 30 15 40 30 10 5 20 10 30 15 40 30 10 5 20 10 30 15 40 30

Ft in N for PSZ using diamond wheel 0.2 0.215 0.24 0.29 0.24 0.29 0.35 0.4 0.35 0.38 0.54 0.5 0.45 0.5 0.67 0.62

Ft in N for PSZ using CBN wheel 0.3 0.5 0.6 0.55 0.4 0.65 0.71 0.69 0.56 0.8 1 0.98 0.75 1 1.4 1.2

Ft in N for AT using diamond wheel 0.18 0.25 0.14 0.255 0.145 0.33 0.31 0.41 0.21 0.34 0.21 0.46 0.22 0.52 0.23 0.55

Ft in N for AT using CBN wheel 0.4 0.62 0.8 0.75 0.6 0.85 1 0.95 0.8 1.2 1.4 1.3 1 1.5 1.8 1.6

Ft in N for A using diamond wheel 0.2 0.35 0.3 0.21 0.3 0.4 0.35 0.24 0.44 0.47 0.45 0.4 0.53 0.57 0.53 0.68

Ft in N for A using CBN wheel 0.6 0.8 0.9 0.85 0.42 0.65 0.75 0.7 0.95 1.5 1.8 1.6 0.4 0.62 0.8 0.75

Table 6. Experimental Results of evaluating surface roughness Ra after lapping for different coatings Experimental results Depth of cut in m ( V4) 0.25 0.25 0.25 0.25 0.25 0.25 8 8 8 8 8 8 14 14 14 14 14 14 Lapping time in minutes ( V1) 5 10 15 20 25 30 5 10 15 20 25 30 5 0 15 20 25 30 Ra in m for PSZ using diamond wheel 0.5 0.35 0.28 0.2 0.18 0.175 0.75 0.47 0.33 0.24 0.21 0.2 0.82 0.55 0.45 0.4 0.33 0.28 Ra in m for AT using diamond wheel 0.38 0.28 0.22 0.18 0.15 0.14 0.49 0.39 0.29 0.24 0.2 0.195 0.65 0.5 0.4 0.3 0.28 0.26 Ra in m for AT using CBN wheel Ra in m for A using diamond wheel 0.72 0.41 0.33 0.24 0.23 0.2 0.8 0.52 0.44 0.34 0.31 0.295 0.905 0.82 0.62 0.52 0.46 0.38 Ra in m for A using CBN wheel Ra in m for PSZ using CBN wheel 0.53 0.38 0.3 0.21 0.18 0.18 0.7 0.5 0.36 0.28 0.22 0.2 0.88 0.6 0.51 0.45 0.38 0.32 GP Output PSZ using CBN wheel

0.4 0.31 0.24 0.18 0.16 0.14 0.5 0.42 0.31 0.26 0.205 0.2 0.68 0.52 0.43 0.32 0.3 0.28

0.72 0.42 0.35 0.27 0.25 0.21 0.8 0.58 0.48 0.38 0.35 0.32 0.98 0.85 0.65 0.58 0.5 0.4

0.54021 0.383549 0.293363 0.209842 0.186963 0.183273 0.681086 0.482033 0.36672 0.27575 0.224667 0.209842 0.847382 0.601887 0.507382 0.456926 0.383549 0.310341

4. GENETIC MODELS RESULTS AND DISCUSSION Using GP simulation, During Grinding operation, the Normal force Fn is given by, Where V2= Hardness of coatings, V3=Toughness of coatings and V4=Hardness of Grinding wheels (refer table 4.)

132

International Journal of Mechanical Engineering and Technology (IJMET), ISSN 0976 6340(Print), ISSN 0976 6359(Online) Volume 2, Issue 2, August- December (2011), IAEME

Using GP simulation, During Grinding operation, the Tangential force Ft is given by,

Where V2= Hardness of coatings, V3=Toughness of coatings and V4=Hardness of Grinding wheels (refer table 5.)

Using GP simulation, During Grinding operation, the surface roughness Ra is given by,

Where V2= Hardness of coatings, V3=Toughness of coatings and V4=Hardness of Grinding wheels (Refer table3.)

Using GP simulation, During Lapping operation, the surface roughness Ra is given by

Where V0= Hardness of coatings, V3=Toughness of coatings and V2=Hardness of Grinding wheels (refer table 6.)

The percentage deviation of GP (expected) and experimental results for Normal grinding forces simulation of the Grinding Machining process are shown on Figure 1 and the Tangential grinding forces are presented in Figure 2. Whereas results of surface roughness Ra during grinding and lapping operations are shown in figure 3 and figure 4 respectively. The Discipulus GP technique was able to simulate these output variables within an average of 1.9% of their measured value, with no value exceeding a 5% deviation.

133

International Journal of Mechanical Engineering and Technology (IJMET), ISSN 0976 6340(Print), ISSN 0976 6359(Online) Volume 2, Issue 2, August- December (2011), IAEME
Figure 1. Percentage deviation curve between the best models regarding individual generation and experimental results of Fn

Figure 2. Percentage deviation curve between the best models regarding individual generation and experimental results of Ft

Figure 3. Percentage deviation curve between the best models regarding individual generation and experimental results of Ra value during Grinding

134

International Journal of Mechanical Engineering and Technology (IJMET), ISSN 0976 6340(Print), ISSN 0976 6359(Online) Volume 2, Issue 2, August- December (2011), IAEME

Figure 4. Percentage deviation curve between the best models regarding individual generation and experimental results of Ra value during Lapping

4 CONCLUSION Oxide ceramics such as Alumina (A), Alumina-Titania (AT) and Partial stablized zirconia (PSZ), have been widely used for many industrial applications by deposition of thick film of hard materials on a relatively softer substrate of the engineering components. Before deciding on the selection of coatings, it is essential to look into its characteristics which also includes its machinability for control of size and shape of end products. The above work was taken up as product development of ceramic coated surfaces are having immense value for industrial applications. In this paper, the genetic programming was used for predicting the machinability of ceramic materials. In the proposed concept the mathematical models for verifying the machinability are subject to adaptation. After many trials, with the help of validation and testing data, the fittest model reliability is 98%. Thus, in this case the reliability was almost 100%. Some of genetically developed models of cutting parameters of precision machining of ceramic oxide coatings, out of many successful solutions are presented here. The accuracies of solutions obtained by GP depend on applied evolutionary parameters and also on the number of measurements and the accuracy of measurement. In general, more measurements supply more information to evolution which improves the structures of models and we have provided enough data. In this paper, the genetic programming was used for predicting the Machinabiliy characteristics for verifying the experimental results of Cutting parameters which are subject to adaptation. Its reliability is approximately 98% in the prediction of various outputs of results. In the testing phase, the genetically produced model gives the same result as actually found out during the experiment, with the reliability of almost cent percent. It is inferred from our research findings that the genetic programming approach could be well used for the prediction of Machinability characteristics of ceramic coatings
135

International Journal of Mechanical Engineering and Technology (IJMET), ISSN 0976 6340(Print), ISSN 0976 6359(Online) Volume 2, Issue 2, August- December (2011), IAEME

without conducting the experiments. This helps to establish efficient planning and optimizing of process for the quality production of ceramic coatings depending upon the functional requirements. Further work is on progress, for the prediction/optimization of mechanical and tribological characteristics of Industrial ceramic coatings by developing a mathematical model. REFERENCES [1] Erry Yulian T. Adesta, Muhammad Riza, Muataz Hazza,Delvis Agusman, Rosehan Tool Wear and Surface Finish Investigation in High Speed Turning Using Cermet Insert by Applying Negative Rake Angles European Journal of Scientific Research,Vol.38 (2), 2009, pp.180-188. [2] Thamizhmanii S., Kamarudin K., Rahim E.A., Saparudin A., Hassan S., 2007. Tool Wear andSurface Roughness inn Turning AISI 8620 using Coated Ceramic Tool, Proceedings of The World Congress on Engineering Vol. II WCE, 2007, London, UK. [3] Senthilkumar A., Rajadurai A., and Sornakumar A., 2003. Machinability of hardened steel using alumina based ceramic cutting tools, International Journal o Refractory Metals and HardMaterials, 21 pp. 109-117. [4] Ms. Shruti Mehta, Mr. Avadhoot Rajurkar, Mr. Jignesh Chauhan, A Review on Current Research Trends in Die-Sinking Electrical Discharge Machining of Conductive Ceramics, International Journal of Recent Trends in Engineering, Vol. 1(5), 2009, pp.100-104. [5] M. Wakuda, Y. Yamauchi and S. Kanzaki Effect of work piece properties on machinability in abrasive jet machining of ceramic materials, Publication: Precision Engineering, Volume 26 (2), 2002, pp. 193-198. [6] Konig W., Popp M., Precision Machining of Advanced Ceramics, Ceramic Bulletin, Vol.68 ( 3), 1989, pp.550-553. [7] Mohammed yunus, Dr.J. Fazlur rahman, Optimization of process parameters of wear and hardness characterization of industrial ceramic coatings using Taguchi design approach , Int. J. of Advanced Engineering Sciences and Technologies, Vol.9(2), 2011, pp.193- 198. [8] S. Gowri, K. Narayana, Precision Grinding of Sprayed Ceramic coatings, 7th Annual Conference, ASPE, USA, october 1992. [9] S. Gowri, K. Narayana, Study on Flat Lapping Characteristics of Plasma sprayed Ceramic Coatings, International Conference on surface Modification Technologies, Nagsaka, Japan, october 1993. [10] Caveney, R.J., Theil N.W., Grinding Alumina with Dioamond Abrasive, NBS special publicationb,1972, pp. 99. [11] Chen. C., Saki.S., InasakiI, Lapping advanced ceramics, Journal of Materials and Manufacturing processes, vol 6(2), pp.211-226. [12] Davis. C.E., A study of theinfluence of flat Lapping with Diamond microabrasivraying, Diamond Information Series 1.32, De beersIndustrial diamond diviionU.K. [13] Krishnamurhy R, annachalam L.M.,GokulRatnam. C.V., Grinding Transformation of toughned Y-ZTP ceramics, Annals of CIRP, Vol40(1),1991, pp.331-337.

136

International Journal of Mechanical Engineering and Technology (IJMET), ISSN 0976 6340(Print), ISSN 0976 6359(Online) Volume 2, Issue 2, August- December (2011), IAEME

[14] Marshell, Shaw M.C., Forces in Dry Surface Grinding, ASME, pp. 51. [15] Malkim S., Current Trend in CBN Technology, Annals of CIRP vol 34, 1985, Pp. 557-563. [16] Nordin, J.P. and Banzhaf, W. (1996) Controlling an Autonomous Robot with Genetic Programming.In: Proceedings of 1996 AAAI fall symposium on Genetic Programming, Cambridge, USA. [17] Koza, J.R., (1992) Genetic Programming: On the Programming of Computers by Natural Selection.MIT Press, Cambridge, MA. [18] J. R. Koza, Genetic programming II, The MIT Press, Massachusetts, 1994. [19] Koza, Bennett, Andre, & Keane, (1999) GENETIC PROGRAMMING III Darwinian Invention and Problem Solving, Morgan Kaufmann Publishers, Inc. pp. 1154. [20] Francone, F., (1998-2000) Discipulus Owners Manual and Discipulus Tutorials, Register Machine Learning Technologies, Inc. [21] Spector, L., Langdon, W., B., OReilly, U., Angeline, P.J. (1999) Advances in Genetic Programming Volume 3, MIT Press, pp. 476. [22] M. Kovacic, J. Balic and M. Brezocnik, Evolutionary approach for cutting forces prediction in milling, Journal of materials processing technology, 155/156, 2004, pp.1647-1652. [23] Gusel L., Brezocnik M. Modeling of impact toughness of cold formed material by genetic programming, Comp. Mat. Sc. 37 (2006), pp.476 482. [24] Brezocnik M., Gusel L. (2004), Predicting stress distribution in coldformed material with genetic programming, International Journal of Advanced Manufacturing Technology, Vol 23, pp.467-474. [25] M. Brezocnik, M. Kovacic and M. Ficko (2004), Prediction of surface roughness with genetic programming, Journal of materials processing technology, 157/158, 28-36. [26] M. Brezocnik and M. Kovacic (2003), Integrated genetic programming and genetic algorithm approach to predict surface roughness, Materials and manufacturing processes,18(4), pp.475491.

137