Scribd
Upload
281 views4 pages

Fuzzy Logic Example

1) The document describes a hydroponic system that uses nutrient film technique (NFT) without a timer to pump nutrients dissolved in water. Fuzzy logic control is used to control the EC and pH levels in the nutrient solution. 2) Fuzzy logic control involves defining input (pH and EC) and output (pump activation time) variables, mapping inputs to fuzzy sets using membership functions, creating fuzzy rules, and using defuzzification to determine crisp output values. 3) The design of the fuzzy logic control system includes six variables, membership functions for pH, EC and pump activation, and rules relating pH, EC levels to pump activation times. Defuzzification uses a weighted average to determine crisp pump activation

Uploaded by

Tri Awan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
281 views4 pages

Fuzzy Logic Example

1) The document describes a hydroponic system that uses nutrient film technique (NFT) without a timer to pump nutrients dissolved in water. Fuzzy logic control is used to control the EC and pH levels in the nutrient solution. 2) Fuzzy logic control involves defining input (pH and EC) and output (pump activation time) variables, mapping inputs to fuzzy sets using membership functions, creating fuzzy rules, and using defuzzification to determine crisp output values. 3) The design of the fuzzy logic control system includes six variables, membership functions for pH, EC and pump activation, and rules relating pH, EC levels to pump activation times. Defuzzification uses a weighted average to determine crisp pump activation

Uploaded by

Tri Awan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 4

A.

Hydroponic
Hydroponic is plant cultivation that use water and without use soil as a planting medium (soilless). Nutrient Film Technique (NFT)
system is one of the form of cultivation hydroponic. NFT is a system that constantly to flow nutrient dissolved in water without use
timer to pump. This nutrition flow into gully through plant root and therefore returning to shelter water, so on. In this study, the system
implemented in urban agriculture with hydroponic NFT model.
B. Fuzzy Logic Control Method
Fuzzy system was first conceived in 1965 by Lotfi Zadeh, a professor at the California University, Berkley. Fuzzy logic is a
method has ability to process variable that ambiguous or cannot be described in exact or definitely. Basic of fuzzy logic is fuzzy set
theory [14]. Fuzzy logic control is a methodology to presented and implement human knowledge or intelligence about how to control
a system [15]. In this research, fuzzy logic control used to control the EC and pH condition on the providing of plant nutrition. PH
value and EC value as input and pump activation time (actuator) as output. The design of fuzzy logic control in this research can be
seen in fig. 1.

Fig. 1 Design of fuzzy logic control method

Steps the application of fuzzy logic control consist of:


1. The first step is define variable involve in process that will be determined and according to fuzzification functions. In this case,
there is six variables that will be modeled, namely:
Input variable : pH and EC
Output variable: pump A, pump B, pump C and pump D.
2. The second step (Fuzzification) is step mapping input crisp into fuzzy sets that presented in form membership function. The
purpose of fuzzification is get degree of membership. The following computation of value membership functions ( ) for each
input variable and output variable.
a. PH Acid (x), consist of two linguistic values, namely: High and Low. The membership function was formulated as follows :

Value degree of membership:

1x a
bx
phAcid HIGH [ x ] =
a xb
ba
0 xb

1 xb
phAcid LOW [ x ] = xa a x b
ba
0xa
b.

PH Alkaline (x), consist of two linguistic values, namely: Low and High. The membership function was formulated as
follows :

Value degree of membership:

1 xc
phAlkaline HIGH [ x ]= dx c x d
d c
0 x d

1 x c
phAlkaline LOW [ x ] = dx c x d
dc
0 xd
c.

EC (x), consist of three linguistic values, namely: Low, Optimal and High. The membership function was formulated as
follows :

Value degree of membership:

1x a
ecLOW [ x ] = bx a x b
ba
0 xb

0 x 1 a atau x 4 d
ecOPTIMAL [ x ] = (xa)/(ba) a x b
1bx c
(dx )/(d c) c x d

1 xd
xc
ecHIGH [ x ] =
c xd
dc
0 xc
d.

Pump A (z), Pump B (z), Pump C (z) and Pump D (z), each consist of two linguistic value, namely: OFF and ON. The
membership function was formulated as follows :

Value degree of membership:

{
{

}
}

1 za
bz
pump OFF [ z ]=
a z b
ba
0 zb

1 zb
za
pump ON [ z ] =
a z b
ba
0 z a

3.

The third step (Fuzzy Inference Engine) is set rules fuzzy use Tsukamoto model, which is by counting value -predicate for each
rule with using implication system MIN function and value of z in pump variable value for each rule fuzzy. The following rulebased in this system :
The first rules :
IF-THEN

pH Acid High

pH Acid Low

EC Low

pump A ON AND pump


C ON AND pump D ON

pump A OFF AND pump


C ON AND pompa D ON

pump A ON AND pump


C OFF AND pump D
OFF
pump A ON AND pump
C OFF AND pump D
OFF

pump A OFF AND pump


C OFF AND pump D
OFF
pump A OFF AND pump
C OFF AND pump D
OFF

EC
Optimal
EC High

The second rules :


IF-

pH Alkaline Low

pH Alkaline High

THEN

4.

EC
Low

pump B OFF AND pump


C ON AND pump D ON

pump B ON AND pump C


ON AND pump D ON

EC
Optima
l

pump B OFF AND pump


C OFF AND pump D
OFF

pump B ON AND pump C


OFF AND pump D OFF

EC
High

pomp B OFF AND pump


C OFF AND pump D
OFF

pump B ON AND pump C


OFF AND pump D OFF

The fourth step (Defuzzification) is convert fuzzy sets into a firm number. The method used in defuzzification process in
composition rule Tsukamoto that is weighted average. Calculate crisp value Z using formula the following:
n

Pump activation time (Z) =

u i . zi

u i . zi

u i . zi

ui

ui

ui

i=1
n

i=1

i=1
n

i=1

i=1
n

i=1

You might also like