2013 5th International Conference on Computer Science and Information Technology 2013
DOI: 10.1109/csit.2013.6588751
|View full text |Cite
|
Sign up to set email alerts
|

Modeling of ANFIS in predicting TiN coatings roughness

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
5
0

Year Published

2015
2015
2016
2016

Publication Types

Select...
4
1

Relationship

0
5

Authors

Journals

citations
Cited by 6 publications
(5 citation statements)
references
References 17 publications
0
5
0
Order By: Relevance
“…The ANFIS rules based contains fuzzy if‐then rules of Sugeno type that can be expressed as Rule 1: if V is A 1 and V reated is B 1 and V ref is C 1 and T is D 1 and DF is E 1 then f is f 1 ( V , V rated , V ref , T , DF). Rule 2: if V is A 2 and V reated is B 2 and V ref is C 2 and T is D 2 and DF is E 2 then f is f 2 ( V , V rated , V ref , T , DF). Here V , V rated , V ref , T and DF are the ANFIS inputs, A i , B i , C i , D i and, E i states the fuzzy sets and f i ( V , V rated , V ref , T , DF) represents the outputs of the first‐order Sugeno fuzzy inference system. As (6), every node in first layer has been denoted with a node function [25] μAifalse(x,σ,cfalse)=efalse(xcfalse)2/2σ2 where x is the input data to node i , A i the linguistic tag associated with this node, c is the central of membership function (MF), σ is the standard deviation and μAi is the MF of A i . In the second layer, every node is a fixed node which computes the firing strength w i of a fuzzy rule.…”
Section: Proposed Methodsmentioning
confidence: 99%
“…The ANFIS rules based contains fuzzy if‐then rules of Sugeno type that can be expressed as Rule 1: if V is A 1 and V reated is B 1 and V ref is C 1 and T is D 1 and DF is E 1 then f is f 1 ( V , V rated , V ref , T , DF). Rule 2: if V is A 2 and V reated is B 2 and V ref is C 2 and T is D 2 and DF is E 2 then f is f 2 ( V , V rated , V ref , T , DF). Here V , V rated , V ref , T and DF are the ANFIS inputs, A i , B i , C i , D i and, E i states the fuzzy sets and f i ( V , V rated , V ref , T , DF) represents the outputs of the first‐order Sugeno fuzzy inference system. As (6), every node in first layer has been denoted with a node function [25] μAifalse(x,σ,cfalse)=efalse(xcfalse)2/2σ2 where x is the input data to node i , A i the linguistic tag associated with this node, c is the central of membership function (MF), σ is the standard deviation and μAi is the MF of A i . In the second layer, every node is a fixed node which computes the firing strength w i of a fuzzy rule.…”
Section: Proposed Methodsmentioning
confidence: 99%
“…To train the model, a hybrid method included the least‐squares method and the back propagation gradient descent has been used as optimization technique to emulate a given training dataset. The linear output MFs have been used to create the electrical power loss values [27,28]. Power loss estimated based on ANFIS for low current region has been shown in Figure .…”
Section: Electrical Parameters Of Mosa: Measurement Computation Andmentioning
confidence: 99%
“…ANFIS commonly includes a five‐layer feed forward neural network to make the inference system as depicted in Figure . To demonstrate the process of the ANFIS, a system with three inputs ( U,T,DF ) which are applied voltage, temperature, and degradation factor was used.…”
Section: Power Loss Estimationmentioning
confidence: 99%
“…To train the model, a hybrid approach included the least‐squares method and the back propagation gradient descent was used as optimization technique to emulate a given training dataset. Eventually, the MF linear output was used to create the electrical power loss curve .…”
Section: Power Loss Estimationmentioning
confidence: 99%