Microsoft Word 14 Material Removal

International Journal of Mechanical Engineering and Technology (IJMET), ISSN 0976 – 
6340(Print), ISSN 0976 – 6359(Online) Volume 3, Issue 2, May-August (2012), © IAEME 
132 
The transfer function in the hidden layer and the output layer is tan-sigmoid. The 
training function is trainlm which updates weight and the bias values according to the 
Levenberg-Marquadrt optimization rule. 
 
 
 
 
 
 
 
 
 
 
Fig 2 Effect of number of nodes in the hidden layer 
 
Network learning function is learngdm which is the gradient descent with momentum 
weight and bias learning function. The data is divided as training data to train the neural 
network. The testing data is used to test the model; it does not take part in the training of 
the model. The mean squared error (MSE) is the criterion for selecting the network 
structure. Here the error is calculated as the difference between the target output and the 
network output 
The experimental data is used to train and validate the ANN. The prediction of the MRR 
by neural network is shown in Table 3. 
B.FUZZY SYSTEM 
 
Fuzzy logic has lot of application in the real world. Basically the system will accept the 
input or some inputs and pass the inputs to a process called fuzzification. In the 
fuzzification process, the input data will undergo some translation into the linguistic 
quantity as low, medium, high of the physical properties. The translated data will be sent 
to an inference mechanism that will apply the predefined rules. The inference engine 
generates the results in the linguistic form. The linguistic output will go through 
defuzzification process to be in numerical form. Defuzzification is defined as the 
conversion of a fuzzy membership function to precise or crisp quantity [9], [10]. Fuzzy 
modeling and approximation are the most interesting fields where the fuzzy theory can 
be effectively applied. As far as modeling and approximation is concerned one can say 
that the main interest is towards the applications when we intend to apply fuzzy 
modeling and approximation to an industrial process. One of the key problems to be 
solved is to find the fuzzy rules.

Sugeno – Type fuzzy inference
The most commonly known or used fuzzy inference methodology is Mamdani. But this 
paper discussed the Sugeno or Takagi-Sugeno-Kang, method of fuzzy inference. The 
main difference between Mamdani and Sugeno is that the Sugeno output membership 
functions are either linear or constant but can be excellently suited for modeling non-
linear systems by interpolating between multiple linear models. 
A typical rule in a Sugeno fuzzy model has the form: 
If Input 1=x, Input 2=y, then output z=ax+by+c. 

---