rr411301 neural networks and fuzzy logic control

Code No: RR411301 Set No. 1

IV B.Tech I Semester Regular Examinations, November 2007NEURAL NETWORKS AND FUZZY LOGIC CONTROL

( Common to Electronics & Control Engineering and Instrumentation &Control Engineering)

Time: 3 hours Max Marks: 80Answer any FIVE Questions

All Questions carry equal marks

1. (a) Explain what is supervised and unsupervised learning with examples.

(b) Explain the logic functional using truth tables performed by the followingnetworks with mp neurons. figure 1(b)i,figure 1(b)ii,figure 1(b)iii,

i.

Figure 1(b)i

ii.

Figure 1(b)ii

iii.

Figure 1(b)iii[7+9]

2. (a) Explain the Hopfield network algorithm and its limitations.

(b) Explain the Energy analysis of Discrete Hopfield Network. [8+8]

3. (a) Explain the architecture of self-organizing map network.

(b) Explain the training algorithm of Kohonens layer training algorithm. [8+8]

4. (a) What are the major issues arise in plant inverse identification. Explain.

(b) Explain the neural network configuration for plant inverse identification.[8+8]

1 of 2


5. Let X = {1, 2, 3, . . . , 10}. Determine the cardinalities and relative cardinalitiesof the following fuzzy sets.

(a) A = {(3, 10), (4, 0.2), (5, 0.3), (6, 0.4), (7, 0.6), (8, 0.8), (10, 1), (12, 0.8), (14, 0.6)}.

(b) B = {(2, 0.4), (3, 0.6), (4, 0.8), (5, 1.0), (6, 0.8), (7, 0.6), (8, 0.4)}

(c) C = {(2, 0.4), (4, 0.8), (5, 1.0), (7, 0.6)} [6+5+5]

6. What are the main components of fuzzy logic controller? Explain each of them indetail. [16]

7. Explain the step-by-step procedure in designing of a fuzzy logic controller. [16]

8. The interior temperature of an electrically heated oven is to be controlled by varyingthe heat input, u, to the jacket. The oven is shown in figure 8. below. Let theheat capacities of the oven interior and of the jacket be c1 and c2, respectively.Let the interior and the exterior jacket surface areas be a1 and a2, respectively.Let the radiation coefficients of the interior and exterior jacket surfaces be r1 andr2, respectively. Assume that there is uniform and instantaneous distribution oftemperature throughout, and the rate of loss of heat is proportional to area and theexcess of temperature over that of the surroundings. If the external temperature isT0, the jacket temperature is T1, and the oven interior temperature is T2, then wehavec1

T1

= a2r2(T1 T0) a1r1(T1 T2 ) + u

c2

T2

= a1r1(T1 T2)

Figure 8

Formulate the FAM table using the initial conditions of x1(0) = 80O, and x2(0) =

85O. [16]

2 of 2






1. With suitable diagram, derive the weight update equations in backpropagationalgorithm for a multilayer feedforward neural network and explain the effect oflearning rate, and momentum terms in weight update equations. [16]

2. What are the modes of operation of a Hopfield network?. Explain the algorithm forstorage of information in a Hopfield network. Similarly explain the recall algorithm.

[16]

3. (a) Explain ART network algorithm.

(b) Explain the following terms with respect to Neural networks.

i. Stability

ii. Plasticity

iii. Learning

iv. Architecture. [8+8]

4. Define the problem of control of dynamical system and explain how to achieve themthrough neural networks. [16]

5. (a) Consider the following matrix defining a fuzzy relation R on A B

y1 y2 y3 y4 y5x1 .5 0 1 .9 .9

R : x2 .1 .4 .5 .3 .1x3 .7 .8 0 .2 .6x4 .1 .3 .7 1 0

Give the first and the second projection with R(1)(x) and R(2)(y) and the

cylindrical extensions of the projection relations with R(1)L and R(2)L

(b) Given that A=0.2/3 + 0.5/4 + 0.8/5 and B=0.8/5 + 0.2/8, determine theCartesian product of the two sets; AB. [8+8]

R1 y1 y2 y3 y4x1 .3 0 .7 .3x2 0 1 .2 0

1 of 2


R2 z1 z2 z3y1 1 0 1y2 0 .5 .4y3 .7 .9 .6y4 0 0 0

6. List the main components of fuzzy logic controller. Explain each of them in detail.[16]

7. Explain the design procedure of a fuzzy logic controller. Illustrate it with an ex-ample. [16]

8. Design a fuzzy controller for a temperature control system of a room. Assume yourown control actions due to which the temperature of the room may vary. Designin fuzzy rule-based system to keep the room at a comfortable temperature. [16]

2 of 2






1. (a) What are the three models of artificial neuron. Explain them in detail.

(b) Compare and contrast artificial neural networks with conventional computersystem. [10+6]



3. Explain architecture of Konen?s self-organizing network. Explain the training al-gorithm of Kohonen?s layer. [16]

4. (a) What are the major issues arise in plant inverse identification. Explain.

(b) Explain the neural network configuration for plant inverse identification.[8+8]


(a) A = {(3, 10), (4, 0.2), (5, 0.3), (6, 0.4), (7, 0.6), (8, 0.8), (10, 1), (12, 0.8), (14, 0.6)}.

(b) B = {(2, 0.4), (3, 0.6), (4, 0.8), (5, 1.0), (6, 0.8), (7, 0.6), (8, 0.4)}

(c) C = {(2, 0.4), (4, 0.8), (5, 1.0), (7, 0.6)} [6+5+5]

6. Draw a block diagram of a possible fuzzy logic control system. Explain about eachblock. [16]

7. Describe the design of fuzzy logic control with a case study. [16]

8. A printer drum is driven by a brushless DC motor. The moment of inertia ofthe drum is J = 0.00185kg.m2. The motor resistance is R = 1.12. The torqueconstant for the motor is KT = 0.0363Nm/A. The back EMF constant is k =0.0363 V/(rad/s). The equation of the system is

j =KT (V k)

R

where = (V k)R

= I = motor current = rotational angleV = motorcontrol voltageUsing the initial conditions of x1 = 7.5

o and x2 =?150rad/s and forming thedifference equations, design the fuzzy controller. [16]

1 of 1






1. (a) What is the significance of momentum term in back propagation learning.

(b) Why convergence is not guaranteed for the back propagation-learning algo-rithm. [8+8]



3. Explain architecture of Konen?s self-organizing network. Explain the training al-gorithm of Kohonen?s layer. [16]

4. Define the problem of process identification. What are the possible neural networkconfigurations for plant identification? Explain each of them. [16]


(a) A = {(3, 10), (4, 0.2), (5, 0.3), (6, 0.4), (7, 0.6), (8, 0.8), (10, 1), (12, 0.8), (14, 0.6)}.

(b) B = {(2, 0.4), (3, 0.6), (4, 0.8), (5, 1.0), (6, 0.8), (7, 0.6), (8, 0.4)}

(c) C = {(2, 0.4), (4, 0.8), (5, 1.0), (7, 0.6)} [6+5+5]

6. Write short notes on the following

(a) Knowledge base in fuzzy logic control system.

(b) Decision making logic in fuzzy logic control system. [8+8]

7. Explain the step-by-step procedure in designing of a fuzzy logic controller. [16]

8. Design a fuzzy controller for a temperature control system of a room. Assume yourown control actions due to which the temperature of the room may vary. Designin fuzzy rule-based system to keep the room at a comfortable temperature. [16]

1 of 1

rr411301 neural networks and fuzzy logic control

Documents