You are on page 1of 5

UNIVERSITI TUN HUSSEIN ONN MALAYSIA

JABATAN KEJURUTERAAN MEKATRONIK & ROBOTIK FAKULTI KEJURUTERAAN ELEKTRIK & ELEKTRONIK SKEMA PEMARKAHAN QUIZ 1 SEMESTER 1 SESI 2011/12

SULIT
HANYA UNTUK KEGUNAAN PEMERIKSA SAHAJA

NAMA MATAPELAJARAN

: NEURAL NETWORK AND FUZZY LOGIG FUZZY CONTROL SYSTEM : BEM 4233 / BER 4233 : 4 BEM / 4BER : SOALAN QN : 45 MARKAH SOALAN QF : 55 MARKAH

KOD MATAPELAJARAN KURSUS KANDUNGAN SKEMA

BEM 4233 /BER 4233 ) Q1 MISO Fuzzy Logic Control (FLC) is applied to control water tank level system as shown in Figure 1. FLC has function to keep the water level in tank (h) and the water outlet flow rate (Q) are constant on Average and Medium respectively. These requirements are fulfilled by controlling the water inlet valve opening. Water level (h) and outlet water flow rate (Q) are FLC input variables and have memberships are minimum, average, maximum and soft, medium, hard respectively. On the other hand, inlet water valve opening is the FLC output variable and has memberships are open fast, open slow, steady, close slow, close fast. Membership functions for each variable are as below:

Figure 1: Water Tank Level System Derive rule tabulation and all rule for this Fuzzy Logic Control. (100 marks) Answer: (a) Design table of rule related with above problem. Flow rate (Q) Water inlet Valve (V) Minimum Water level (h) Average Maximum Soft Open Fast Open Slow Close Slow Medium Open Slow Steady Close Slow Hard Close Slow Close Slow Close Fast (45 marks) Q2 (a) Draw a fuzzy controller block and briefly explain each element of the block Answer: The block of fuzzy control system can draw as below:

BEM 4233 /BER 4233

Figure: A fuzzy controller block (5 marks) Explain each element definition Answer: a. Fuzzification The first block inside the controller is fuzzification, which converts each piece of input data to degrees of membership by a lookup in one or several membership functions. The fuzzification block thus matches the input data with the conditions of the rules to determine how well the condition of each rule matches that particular input instance. There is a degree of membership for each linguistic term that applies to that input variable. (3 marks) b. Inference Mechanism / Engine Inference Mechanism or Engine is the processing program in a fuzzy control system. It derives a conclusion from the facts and rules contained in the knowledge base using various human expert techniques. (3 marks) c. Rule-base A group of rules may use several variables both in the condition and the conclusion of the rules. They are based on a set of rules that a human expert would follow in diagnosing a problem. Rulebase also where the knowledge is stored. (3 marks) d. Defuzzification Defuzzification is a process that maps a fuzzy set to a crisp set. Defuzzification has attracted far less attention than other processes involved in fuzzy systems and technologies. Defuzzification is sometimes not seen as a part of the core of a fuzzy system; fuzzy system ends where uncertainty and imprecision end. Defuzzification is just the last step; it is an interface with crisp models of the world. Defuzzification is a model of synthesis; therefore it is completely opposite to the main concept of fuzzy set theory. (3 marks)

BEM 4233 /BER 4233 (b) Answer: Differentiate between crisp and fuzzy logic Fuzzy Fuzzy, qualitative, vague Uses knowledge (i.e. rules) Requires fuzzy data Nonlinear method No traditional modeling, inferences based on knowledge Can handle incomplete information to some degree Linguistic (14 marks)

Crisp Crisp, exact based on models (i.e. differential equations) Requires complete set of data Typically linear Complex systems hard to model incomplete information leads to inaccuracy numerical

(c) Answer:

Create the equality, union, intersection and compliment equation for fuzzy set A and B with universe of discourse U

Equality:

A (u ) = B (u )

for all u U (3 marks) for all u U (3 marks)

Union:

A B (u ) = A+ B (u ) = max{ A (u ), B (u )} A B (u ) = min{ A (u ), B (u )}

Intersection:

for all u U (3 marks)

Complement: A (u ) = 1 A (u )

for all u U (3 marks)

(d) Answer:

Describe the step of Mamdani Fuzzy Inference? The Mamdani-style fuzzy inference process is performed in four steps: 1. Fuzzification of the input variables (3 marks) 2. Rule evaluation (inference) (3 marks) 3. Aggregation of the rule outputs (composition) (3 marks) 4

BEM 4233 /BER 4233 4. Defuzzification. (3 marks)

You might also like