Prediction of Material Removal Rate using Artificial … of Material Removal Rate using Artificial...

International Journal of Engineering Technology, Management and Applied Sciences

www.ijetmas.com February 2015, Volume 3 Issue 2, ISSN 2349-4476

12 Karanam Krishna , Ch.Siva Ramakrishna

Prediction of Material Removal Rate using Artificial Neural

Network in CNC Turning Process on Aluminum

Karanam Krishna Department of Mechanical Engineering,

Vignan’s Institute of Information Technology

Visakhapatnam, India.

Ch.Siva Ramakrishna Department of Mechanical Engineering,

Vignan’s Institute of Information Technology

Visakhapatnam, India

ABSTRACT

Present work deals with prediction of MRR of CNC turning using back propagation neural

network (BPNN). Machining operations have been performed in aluminum work piece by carbide insert over a range of cutting parameters. Important process parameters have been used as input for

BPNN and MRR, spindle load has been used as output of the network. Inclusion of cutting speed, feed rate, depth of cut as an input parameters leads to better training of the network. Performance of the Neural Network has been found to be satisfactory while validated with experimental result.

Keywords : Spindle speed, Depth of Cut, Feed rate, Material removal rate, Artificial neural network, spindle load, CNC Lathe.

1.INTRODUCTION

CNC (Computer Numeric Control) machining is one of the most popular approaches of conventional machining by tools with defined geometry. Computer control of machining program

brings significant advantages in comparison to human unpredictable machining. What is more, the CNC machining leads to a unique possibility to process planning. Knowledge of the machining

process and optimal settings of the input parameters are essential for the quality and accuracy of the machined parts.Despite the fact that the machining process is affected by large amount of factors and the process itself is time-variant the modeling of the output process parameters is currently becoming

more available. The paper presents modeling and prediction of technological parameters of CNC turning using artificial neural networks (ANN), while back propagation neural network(BPNN) was applied. The studied input parameters of the turning process are as follows: Spindle speed, depth of

cut , feed . The obtained results are verified on the experimental measurement.

1.1 Why Aluminum

The main properties which make aluminum a valuable material are is lightweight, strength, recyclability, corrosion resistance, durability, ductility, formability and conductivity. Due to this unique combination of properties, the variety of applications of aluminum continues to increase. It is

essential in our daily lives. We cannot fly; go by high performance car or fast ferry without it. We cannot get heat and light into our homes and office without it. We depend on it to preserve our food,

our medicine and to provide electronic components for our computers. Physically, chemically and mechanically aluminum is a metal like steel, brass, copper, zinc, lead or titanium. It can be melted,

http://www.ijetmas.com/




cast, formed and machined much like these metal and it conducts electric current. In fact often the equipment and fabrication methods are used for steel.

1.2 Cutting parameters

In turning, the speed and motion of the cutting tool is specified through several parameters. Out of

the many parameters affecting the surface roughness of a metal these parameters are selected for each operation based upon the work-piece material, tool material, tool size, and more. Spindle speed(N-rpm)

The rotational speed of the spindle and tool in revolutions per minute (RPM). The spindle speed is equal to the cutting speed divided by the circumference of the tool.

Depth of cut (mm) Cutting speed and feed rate come together with depth of cut to determine the material removal rate, which is the volume of work-piece material (metal, wood, plastic, etc.) that can be removed per time

unit. Feed rate (mm/rev)

The speed of the cutting tool's movement relative to the work-piece as the tool makes a cut. The feed rate is measured in inches per minute (IPM) and is the product of the cutting feed (IPR) and the spindle speed (RPM).

2.LITRATURE REVIEW

The performance of hard turning is measured in terms of surface finish, cutting forces, power

consumed and tool wear. Surface finish influences functional properties of machined components.





Surface finish, in hard turning, has been found to be influenced by a number of factors such as feed rate, cutting speed, work material characteristics, work hardness, cutting time, tool nose radius and

tool geometry, stability of the machine tool and the work piece set-up, the use of cutting fluids, etc. [1].Sujit Das attempts to study the machine ability issues of aluminum-silicon carbide (Al-

SiC) metal matrix composites (MMC) in turning using HSS cutting tool. SiCp-reinforced metal matrix composites (MMCs) containing SiC particles (5wt%-20wt %) of 400mesh size were prepared by powder metallurgy (P/M) route and used as work material for turning. Experiments were

conducted at various cutting speeds and depth of cuts at constant feed rate and parameters, such as cutting forces and surface roughness were measured. It was found that higher weight percentage of

SiCp reinforcement produced a higher surface roughness and needs high cutting forces during machining operation of MMCs. It was also observed that surface roughness and the cutting forces are also depending upon the depth of cut and the cutting speed at constant feed rate.[2].Ilhan Asiltürk ,

Süleyman Nes eli has studied the Multi response optimization of CNC turning parameters via Taguchi method-based response surface analysis.[3].Ojel, T. et al. (2005) has studied the effects of

cutting edge geometry, work piece hardness, feed rate and cutting speed on surface roughness and resultant forces in the finish hard turning of AISI H13 steel. Cubic Boron Nitrite inserts with two distinct edge preparations (chamfered and honed) and through hardened AISI H13 steel bars were

used. The honed Edge geometry and lower work piece surface hardness resulted in better surface roughness. [4].Krishna and Bharathi suggested an approach for finding the best cutting parameters

leading to minimum surface roughness and maximum Material Removal Rate7. The material used was Cast Iron and the experiment was done on a machining Centre. Experimental attributes were obtained from MATLAB. The researcher used genetic algorithm coupled with artificial neural

network which leads to find out the minimum value of Ra and Rz [5].Tugrul Ozel et al. (2007) has conducted an experimental study on turning of AISI D2 steels (60 HRC) using ceramic wiper tool.

The cutting parameters considered in this work are cutting speed, feed rate and depth of cut and the response are tool wear, surface roughness. Tool wear analysis using Neural Network Modeling. He suggested that for high feed rate maintaining good surface finish and best tool life was obtained in

lowest feed rate and lowest cutting speed combinations.[6]. Kagade and Deshmukh (2011) has investigated an experimental study on turning of High Carbon High Chromium steel (HCHC) using CNMG 09 03 08-PF carbide insert tool. The cutting parameters focused in this work are cutting

speed, depth of cut, feed rate and the outcomes considered are surface roughness, spindle load. This work has revealed a conclusion that speed has maximum effect and depth of cut has minimum effect

on surface roughness[7]. D. Rahul Davis 2013 The present work is associated with turning operation of En-19 steel. The paper represents the influences of five different cutting parameters like pressurized coolant jet, rake angle, depth of cut, spindle speed and feed rate on the surface roughness

of the En-19 steel. In the experiment Taguchi technique was used to calculate the various readings by using MINITAB15 software. Orthogonal L16 array was used and signal to noise ratio and the

analysis of variance (ANOVA) are employed to interpret the cutting parameters. The carbide t ipped tool having negative and positive rake angle according to the combination of the experiment was used. The experiment setup included spindle speed of 780 and 1560 rev/min, pressurized coolant jet

of 0.5 and 1 bar, rake angle 4 and 7 degrees, depth of cut of 0.5 and 1 mm and feed rate 0.16 and 0.8 mm/rev. At last confirmation test was done to compare the value with final outcome to confirm the

effectiveness of the surface roughness of En-19 steel.[8]. Mohammad Reza Soleymani Yazdi and Saeed Zare Chavoshi (2010) studied the effect of cutting parameters and cutting forces on rough and





finish surface operation and material removal rate (MRR) of AL6061 in CNC face milling operation. The objective was to develop the multiple regression analysis and artificial neural network models

for predicting the surface roughness and material removal rate. According to them, in rough operation, the feed rate and depth of cut are the most significant effect parameters on Ra and MRR

and increases with the increase of the cutting forces.[9].Krishnamurthy and Venkatesh (2013) determined the optimum cutting factors for surface roughness and MRR on TiB2 particles reinforced Al6063 metal matrix composites. From the experimental results it was found that feed is the most

significant process parameter on surface roughness followed by cutting speed. The MRR results showed that the speed and the feed are the most significant parameters.[10].Neeraj et al (2012)

applied the Taguchi technique through a case study in turning of mild steel bar using HSS tool for optimizing the process parameters. Influence of turning process parameters on surface roughness on mild steel has been studied. The results show that the cutting speed and depth of cut are the

significant parameters to influence the surface roughness of mild steel[11].Durai et al (2012) studied the cutting parameters that ensure less power consumption in high tare CNC machines. The data

acquisition system was used to measure the output characteristics. From the results, it was concluded that the feed rate and the depth of cut significantly influence the energy consumption. [12].Kamal Hassan and Anish Kumar also used taguchi technique to find the optimal set of process

parameters while turning of medium brass alloy.

3.METHODOLOGY AND EXPERIMENTATION

To investigate the process parameters for MRR on aluminum the following experimental procedure is carried out .STEP 1: The raw material (metal rods) is fed into the CNC Turning lathe Machine. STEP 2: The Metal rods are magnetically clamped in the machine STEP 3: The program is written in

the computer console according to the required cutting parameters i.e. Cutting Speed, Depth of Cut and Feed Rate. STEP 4: The process of turning has been done in the following three cases. i. Varying

speed while keeping the Depth of Cut and Feed Rate constant .ii.Varying Feed Rate and keeping the Spindle Speed and Depth of Cut constant. Iii. Varying Depth of Cut while keeping the Spindle Speed and Feed Rate constant.

Fig 3.1 CNC Machine Fig. 3.2 Principle of machining

3.1 Axes of CNC Turning Machine





The axis along machine spindle axis of turning machine is Z axis and along the cross traverse is X axis. There is no traverse along the Y axis derived from the right hand coordinate system

Fig 3.3 Co-ordinate system of CNC Lathe Fig 3.4 spindle load axis

The direction of Z axis away from the machine headstock is positive and towards the lathe headstock is negative. The direction of X axis from traverse (X axis) towards the center axis is

negative and away from the center axis is positive. 3.2 Adjustable Process Parameters

Cutting speed and cutting feed

The process of metal cutting or machining of metal work-piece is influenced greatly by the relative velocity between the work-piece and the edge of the cutting tool. The relative movement in the

machining operations is produced by the combination of rotary and translator movement either of the work-piece or of the cutting tool or both. The translator displacement of the cutting edge of the tool along the work surface during a given period of time is called 'feed', while the rate of traverse of the

work surface past the cutting edge is designated as 'cutting speed'. The presence of these motions e.g., feed and cutting speed permits the exertion of the process of cutting continuously. In machine

tools with rotary priming cutting motion, A. Cutting Speed: Speed (v) is the peripheral speed of the cutter in m/min.

Cutting speed(V) = πDN/1000, Where,

D = work piece diameter in mm, N = spindle speed in rpm. B. Feed: It is the distance moved by the tool in an axial direction at each revolution of the work. It is

usually expressed in mm/rev. C. Depth of cut: It is the thickness of metal removed from the work piece, measured in a radial

direction or It is the perpendicular distance measured from the machining surface to the un machined surface of the work piece or It is the depth of penetration of the tool into the work piece during machining process.

3.3 Material Removal Rate: The material removal rate has been calculated from the difference of weight of work before and after

machining by using following formula. MRR = Wi-Wf/ρat mm3//sec Where, Wi = Initial weight of





work piece in gm, Wf = Final weight of work piece in gm, t = Machining time in seconds, ρs= Density of Aluminum (2.7 g/mm3).

3.4 Parameter and levels Reason for selection

1. Feed rate (0.08, 0.1, 0.12 mm/rev): It is known from the fundamentals of metal cutting that feed

rate influences pitch of the machined surface profile. Various researchers have observed the effect of feed rate on the surface roughness and tool wear during machining of composites. Thus, these feed rates are chosen based on the earlier findings in the literature.2. Cutting speed (1500, 1600, 1700

rpm): Previous studies have indicated that the surface roughness is influenced by the cutting speed. Therefore, to study the effect of cutting speed in detail, these values of cutting speed has been

considered here.3. Depth of cut (0.6, 0.8, 1 mm): The depth of cut influences the surface roughness, which in turn influences the tolerance and fit of the components. 3.5 Design of Experiments (DOE)

The experiments were conducted on a high precision CNC Turning centre. Aluminum is taken as the work piece material for investigation. The specimen is prepared with the dimensions of 71mm length

and 32mm diameter for turning and carbide insert is used for experimentation. The control factors considered for experiments are spindle speed, feed and depth of cut while Metal removal rate and surface roughness are considered as the output responses. The ranges of the process control variables

are given in table 1. Table 1. Control factors and their levels

Table 4.1 Levels of Control Factors Table 4.2 Design of Experiments

S.No Control Factor

Symbol

-1

Level

0 Level

+1 Level

Units

1 speed N 1500 1600 1700 rpm

2 Feed F 0.08 0.1 0.12 mm/min

3 Depth of cut

DOC 0.6 0.8 1 mm

w/s No.

Speed (rpm)

Feed

(mm/rev)

Depth of Cut

(mm)

1 1500 0.08 0.6

2 1500 0.1 0.8

3 1500 0.12 1

4 1600 0.08 0.8

5 1600 0.1 1

6 1600 0.12 0.6

7 1700 0.08 1

8 1700 0.1 0.6

9 1700 0.12 0.8

After conducting the experiments as per the design of experiments, the output responses were

measured and recorded. Another response, MRR is calculated as the ratio of volume of material removed from work piece to the machining time. In order to determine the volume of material

removed after machining, the weights of work piece before machining and after machining are measured. Machining time taken for each cut is automatically displayed by the machine. The output responses recorded for each set of process control variables are listed.





Table 4.3 DOE with Material removal rate Table 4.4 net weight of work piece

w/s

No.

Speed

(rpm)

Feed

(mm/rev.)

D.OC

(mm)

MRR

(mm3/s)

1 1500 0.8 0.6 0.0132

2 1500 0.1 0.8 0.0213

3 1500 0.12 1 0.0480

4 1600 0.8 0.8 0.0284

5 1600 0.1 1 0.0586

6 1600 0.12 0.6 0.0176

7 1700 0.8 1 0.0306

8 1700 0.1 0.6 0.0233

9 1700 0.12 0.8 0.0499

10 1600 0.1 0.8 0.0297

11 1700 0.1 0.8 0.0297

12 1600 0.12 0.8 0.0441

13 1600 0.1 0.6 0.0208

14 1500 0.08 0.8 0.0224

15 1500 0.1 0.6 0.0214

16 1700 0.1 1.0 0.0283

17 1600 0.08 0.6 0.0154

18 1600 0.12 1.0 0.0441

S.

No.

Weight

Before

turning

(gm)

Weight

after

turning

(gm)

cycle

Time

(sec.)

Means of

MRR

(mm³/sec)

1 154.00 146.00 223 0.0132

2 150.70 142.00 139 0.0213

3 154.00 140.00 108 0.0480

4 152.00 142.00 130 0.0284

5 154.05 138.00 101 0.0586

6 152.98 148.00 84 0.0176

7 154.00 140.00 169 0.0306

8 148.00 142.00 95 0.0233

9 154.00 142.00 89 0.0499

10 154.00 138.00 199 0.0297

11 152.00 136.00 199 0.0297

12 152.00 135.00 176 0.0441

13 156.00 142.00 213 0.0208

14 154.00 137.00 280 0.0224

15 154.00 141.00 224 0.0214

16 154.00 139.00 196 0.0283

17 154.00 143.00 263 0.0154

18 156.00 135.00 176 0.0441

4.RESULTS AND GRAPHS

4.1. Direct and interaction effect of process parameters on output response, MRR

The main effects of the process variables on MRR and surface roughness are studied after plotting the graphs by using Design Expert software. The cutting variables Speed, feed and depth of cut have a major effect upon the material removal rate, which has a major role in determining the power

requirements.The effect of cutting parameters on MRR is as shown in Fig. 1 to 6. Table 4.5 Effect of process parameters on MRR

w/s No. Speed (rpm) Feed (mm/rev.) D.OC

(mm)

MRR

(mm3/s)

1 1500 0.8 0.6 0.0132

2 1500 0.1 0.8 0.0213

3 1500 0.12 1 0.0480

4 1600 0.8 0.8 0.0284

5 1600 0.1 1 0.0586

6 1600 0.12 0.6 0.0176

7 1700 0.8 1 0.0306

8 1700 0.1 0.6 0.0233





9 1700 0.12 0.8 0.0499

10 1600 0.1 0.8 0.0297

11 1700 0.1 0.8 0.0297

12 1600 0.12 0.8 0.0441

13 1600 0.1 0.6 0.0208

14 1500 0.08 0.8 0.0224

15 1500 0.1 0.6 0.0214

16 1700 0.1 1.0 0.0283

17 1600 0.08 0.6 0.0154

18 1600 0.12 1.0 0.0441

0100200300400500

MR

R

Speed

Speed vs MRR

mrr2

speed

mrr

0

100

200

300

400

500

0.060.08 0.1 0.120.14

MR

R

Feed

Feed vs MRR

Column2

Column1

mrr

Fig.4.1Effect of spindle speed on MRR

Fig4.2. Effect of feed rate on MRR

0100200300400500600

0.4 0.6 0.8 1 1.2

MR

R

Depth of Cut

Depth of Cut vs MRR

0

0.2

0.4

0.6

0.8

1

1.2

1500 1600 1700

MR

R

Speed & Depth of cut VS MRR

MRR

Depth of cut

Fig 4.3. Effect of depth of cut on MRR Fig.4.4 Effect of Spindle speed & DOC on MRR





0.760.78

0.80.820.840.86

1500 1600 1700

MR

R

Speed,Feed VS MRR

0

0.5

1

1.5

1600 1600 1600

MR

R

Depth of Cut,Feed VS MRR

Fig 4.5 Effect of Speed, Feed on MRR Fig 4.6 Effect of Depth of Cut, Feed on MRR

1. As the spindle speed increases, the removal of material per unit time also increases as shown in Figure 1.

2.As the feed rate is increased, the material removal per unit time also becomes more as shown in Figure 2. As the tool movement per unit time increases, the greater amount of material is removed 3.The more the depth of cut, the more the material removal rate as shown in Figure 3. The chips

removed per unit time will be more and thereby quantity of material removed is also high. As the depth of cut increases, the cutting force increases Thereby increase in removal of material.

Table 4.2Effect of cycle time and spindle load on MRR

w/s

No.

Speed

(rpm)

Feed

(mm/rev.)

D.OC

(mm)

Cycle

time

in

(sec)

Spindle

load

MRR

(mm3/s)

1 1500 0.8 0.6 223 17.4 0.0132

2 1500 0.1 0.8 139 18 0.0213

3 1500 0.12 1 108 18.6 0.0480

4 1600 0.8 0.8 130 19.8 0.0284

5 1600 0.1 1 101 19.2 0.0586

6 1600 0.12 0.6 84 19.2 0.0176

7 1700 0.8 1 169 19.8 0.0306

8 1700 0.1 0.6 95 18 0.0233

9 1700 0.12 0.8 89 19.8 0.0499

10 1600 0.1 0.8 199 19.2 0.0297

11 1700 0.1 0.8 199 19.2 0.0297

12 1600 0.12 0.8 176 18 0.0441

13 1600 0.1 0.6 213 18 0.0208

14 1500 0.08 0.8 280 18.6 0.0224

15 1500 0.1 0.6 224 18 0.0214





16 1700 0.1 1.0 196 18.6 0.0283

17 1600 0.08 0.6 263 18 0.0154

18 1600 0.12 1.0 176 18 0.0441

The spindle speed and depth of cut increases cycle time decreases, if the feed decreases cycle time increases, the spindle load is maintain constant according to the above design parameters.

4.3 Type of Chip Because of the types of chips produced significantly influence the surface finish of the work piece and the overall cutting operation. For example, vibration, and chatter, etc. The type of chips are

divided as following four types.1.Continuous Chips: Usually, continuous chips are formed with ductile materials at high cutting speeds and high rake angles. Although they generally produce good

surface finish, continuous chips are not always desirable, particularly in the CNC manufacturing widely used today. Continuous chips tend to become tangled around the too l holder, the fixtureing, and the work piece, as well as chip-disposal system, and the operation has to be stopped to clear

away the chips. This problem can be alleviated with chip breakers and by changing machining parameters, such as cutting speed, feed, and cutting fluids. 2. Built-up Edge Chips:A built-up edge

(BUE), consisting of layers of material from the work piece that are gradually deposited on the tool, may form at the tip of the tool during cutting. As it becomes larger, the BUE becomes unstable and eventually breaks up. Part of the BUE material is carried away by the tools side of the chip, the rest

is deposited randomly on the work piece surface. The process of BUE formation and destruction is repeated continuously during cutting operation unless measures are taken to eliminate it.

3. Serrated Chips: Serrated chips are semi continuous chips with zones of low and high shear strain. This type of chips often has a saw tooth like appearance.4.Discontinuous Chips: Discontinuous chips consist of segments that may be firmly or loosely attached to each other.

4.4. Results and discussion by ANN

A feed-forward three layered back propagation neural Network is constructed in fig 4.7The network

is constructed with three layers including with input, output and hidden layers.. The input neurons are cutting speed, feed, depth of cut, output neurons are MRR,. Neurons in the hidden layers were determined by examining different neural networks. Easy NN plus software was used for training of

this network and the ANN was trained with back propagation algorithm. Weights of network connections are randomly selected by the software. The learning of neural network is shown in fig

4.8 The red line is the maximum example error, the blue line is the minimum example error and the green line is the average example error. The orange line is the average validating error. Learning progress graph shows the maximum, average and minimum training error. The average validating

error is shown if any validating examples rows are included. The neural network was trained with 18 examples and validated with 7 examples and tested for 8

examples. Predicted values of MRR are given In table 4.3 Percentage of error between experimental values and predicted values for the MRR, of work piece is calculated.,. From fig 4.13 it was found that the predicted values are very close to the experimental values. From these results, it can be

deemed that the proposed network model is capable of predicting the MRR of the work piece.





Fig 4.7. Neural network architecture (3-12-2)

Fig. 4.8. Learning progress graph with maximum, average and minimum training error.

Fig 4.9 easy NN results average training error

Fig 4.10 easy NN results average training error





4.11 easy NN results average training error







4.3 predicted value of MRR

Trail

No

Experimental

Value

Predicted

Value

Error of

measurement

1 0.0132 0.01319 0.001373

2 0.0213 0.02129 0.047071

3 0.0480 0.04799 0.005039

4 0.0284 0.02839 0.058081

5 0.0586 0.05859 0.013240

6 0.0176 0.01759 0.000474

7 0.0306 0.03057 0.283276

8 0.0233 0.02329 0.000055

9 0.0499 0.04989 0.011131

10 0.0297 0.02969 0.000004

11 0.0297 0.02967 0.265543

12 0.0441 0.04409 0.006721

13 0.0208 0.02077 0.000003

14 0.0224 0.02239 0.478111

15 0.0214 0.02139 0.000082

16 0.0283 0.02829 0.000011

17 0.0154 0.01539 0.005242

18 0.0441 0.04409 0.002655





0

0.02

0.04

0.06

0.08

0.1

0.12

0.14

1 2 3 4 5 6 7 8 9

predicted

experimental

Fig. 4.13. ANN model for MRR

In this work, eighteen experiments were conducted according to a proposed design of experiments with three levels of cutting parameters such as cutting speed, depth of cut and feed. In each trial of

experiment, a strong correlation among the dependent and independent variables was found. A neural network (3-12-2) was used to learn the collected experimental data. The ANN was trained with18 examples, validated with 7 examples and tested with 8 examples. The trained ANN was used

to predict the MRR and spindle load. It was found that there is agreement between experimental dataand predicted values for MRR(4.5185% of error), spindle load (4.2568% of error) Then it is possible

to change the cutting tool at correct time in order to get good quality of products. The neural network can help in selection of proper cutting parameters to increase MRR and reduce machining time.

5.CONCLUSIONS & FUTURE SCOPE OF WORK

The present study was carried out to the effect of input parameters on the material removal rate The

following conclusions have been drawn from the study: 1. The Material removal rate is mainly affected by cutting speed and feed rate. With the increase in cutting speed the material removal rate is increases & as the feed rate increases the material removal

rate is increases. 2. The parameters considered in the experiments are optimized to attain maximum material removal

rate. The best setting of input process parameters for defect free turning (maximum material removal rate) within the selected range is as follows: Cutting speed=1700rpm, Feed=0.1, Depth of cut=0.8 3. As the spindle speed increases, the removal of material per unit time also increases.

4. As the feed rate is increased, the material removal per unit time also becomes more 5.The more the depth of cut, the more the material removal rate as The chips removed per unit time

will be more and thereby quantity of material removed is also high . As the depth of cut increases, the cutting force increases thereby increase in removal of material. 8. The Material removal could be effectively predicted by using spindle speed, feed rate, and depth

of cut as the input variables. Considering the individual parameters, had been found that depth of cut and cutting speed to be the most influencing parameter, followed by and feed rate. Maximum material removal rate is achieved at cutting speed 1600rpm, feed rate of 0.1 mm/rev and

at a depth of 1mm.





9.the experimental results are compared with ANN the results are validate, so above parameters are optimized parameters for better Material Removal rate.

5.1Future Scope of Work The machining was done on Aluminum to study the effect of the independent process parameters on

process output parameters. Performance evaluation was done on material removal rate and machining time and spindle load. Performance characteristic was analyzed using Taguchi’s Technique. There is scope for extending the study with various work materials like brass,

magnesium, nickel, steel, thermo set plastic, titanium and zinc. The material of cutting tool used in the present project was carbide. The experiment can be performed with different cutting tools

including Tungsten carbide electrode to assess the machining performance of CNC machine. The present project work was carried out by considering Aluminum as work material of 25mm diameter & 75mm length and carbide inside as tool material. and the results of MRR and cycle time

compared with ANN(Artificial Neural Network)using EASY NN software. The results of Further this project can be extended for different diameter and length of work materials and by varying tool

nose radius and the much more harder tool material like ceramic, cubic boron nitride etc of suitable nose radius.

REFERENCES

[1]. S.Das, Rabindra Behera, D. Chatterjee, G. Sutradhar, (2011) “Forge ability and Machine ability of Stir Cast

Aluminum Alloy Metal Matrix Composites”, Journal of Minerals & Materials Characterizat ion & Engineering, Vol. 10,

No.10, pp.923-939,

[2] Ilhan Asiltürk , Süleyman Nes_eli, Mult i response optimizat ion of CNC turning parameters via Taguchi method-

based response surface analysis,doi:10.1016/j.measurement.2011.12.004, Journal of Measurement 45 (2012) 785–794.

[3]. Ojel, T. et al. (2005), “Effects of cutting edge geometry, work piece hardness, feed rate and cutting speed on surface

roughness and forces in finish turning of hardened AISI H13 steel” International Journal of Advance Manufacturing and

Technology, vol. 25, pp. 262-269.

[4]. D.V.V. Krishna Prasad and K. Bharathi, Multi-Objective Optimizat ion of Milling Parameters for Machining

CastIron on Machining Centre, Research Journal of Engineering Sciences, 2(5), 35-39 (2013)

[5]. Tugrul Ozel, Yig it Karpat, Luýs Figueira and Paulo Davim J (2007), “Modeling of Surface Fin ish and Tool Flank

Wear in Turning of AISI D2 Steel with Ceramic Wiper Inserts”, Journal of Materials Processing Technology, Vol.

189,pp. 192-198

[6]. Kagade V R and Deshmukh R R (2011),“Experimental Investigation of Turning Operation Using Carb ide Inserts”,

International Journal of Applied Research in Mechanical Engineering, Vol. 1, No. 1, pp. 87-90.

[7]. Rahul Davis, Vivek John, Vivek Kumar Lomga & Raja Paul Horo “The Applications Of Taguchi’s Optimization

Method In Wet Turning Operation Of EN 19 Steel”, Faculty of Mechanical Engineering, Uttar Pradesh, 2013

[8]. Helen Coldwell, Richard Woods, Martin Paul, Philip Koshy, Richard Dewes, David Aspinwall. 2003. Rapid

machining of hardened AISI H13 and D2 moulds dies and press tools. J. Mat. Proc. Tech. Vol.135, pp. 301–311.

[9]. Krishna murthy. K and Venkatesh. J. (2013), “Assessment of Surface Roughness and Material Removal Rate on

Machining of TiB2Reinforced Aluminum 6063: A Taguchi’s Approach” International Journal of Scientific and Research

Publications, Vol. 3, Issue 1, pp.1-6.7.

[10]. Neerajsharma and Renusharma, (2012), “Optimization of Process Parameters of Turn ing Parts: A Taguchi

Approach” Journal of Engineering, Computers and Applied Sc iences, Vol. 1, No.1, pp. 32-36.

[11]. DuraiMatinsureshBabu, Mouleeswaran Senthilkumar, and Jothiprakashvishnuu (2012),“Optimizat ion of Cutting

Parameters for CNC Turned parts using Taguchi’s Technique”, International Journal of Engineering, Vol. 3, pp.493 -496.

.[12].Kamal Hassan, Anish Kumar, M.P.Garg, “Experimental Investigation of Material Removal Rate in CNC turning

using Taguchi Method”, International Journal of Engineering Research and Applications 2,(2012), Issue 2, 1581-1590


Prediction of Material Removal Rate using Artificial … of Material Removal Rate using Artificial...

Documents

Transcript of Prediction of Material Removal Rate using Artificial … of Material Removal Rate using Artificial...