1 artificial neural networks for structural vibration control ju-tae kim: graduate student, kaist,...

27
1 Artificial Neural Networks for Structural Vibration Control Ju-Tae Kim: Graduate Student, KAIST, Korea Ju-Won Oh: Professor, Hannam University, Korea In-Won Lee: Professor, KAIST, Korea Aug. 23, 1999.

Upload: harry-daniel

Post on 19-Jan-2016

212 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: 1 Artificial Neural Networks for Structural Vibration Control Ju-Tae Kim: Graduate Student, KAIST, Korea Ju-Won Oh: Professor, Hannam University, Korea

1

Artificial Neural Networks for

Structural Vibration Control

Ju-Tae Kim: Graduate Student, KAIST, Korea

Ju-Won Oh: Professor, Hannam University, Korea

In-Won Lee: Professor, KAIST, Korea

Aug. 23, 1999.

Page 2: 1 Artificial Neural Networks for Structural Vibration Control Ju-Tae Kim: Graduate Student, KAIST, Korea Ju-Won Oh: Professor, Hannam University, Korea

2

CONTENTS

1. Introduction

2. Neural Networks for Control

3. Numerical Examples

4. Conclusions

Page 3: 1 Artificial Neural Networks for Structural Vibration Control Ju-Tae Kim: Graduate Student, KAIST, Korea Ju-Won Oh: Professor, Hannam University, Korea

3

1. Introduction

required

impossible/hard

impossible/hard

Response based ANN control

Model based conventional control

Mathematicalmodel

Parametric uncertainty

Parametric variation

not required

simple/easy

simple/easy

Conventional Control vs. ANN Control

Page 4: 1 Artificial Neural Networks for Structural Vibration Control Ju-Tae Kim: Graduate Student, KAIST, Korea Ju-Won Oh: Professor, Hannam University, Korea

4

Previous Works on ANN Control in CE

H. M. Chen et al. (1995), J. Ghaboussi et al. (1995) - pioneering research in civil engineering

K. Nikzad (1996) - delay compensation

K. Bani-Hani et al. (1998) - nonlinear structural control

Condition : desired response is to be pre-determined.

Page 5: 1 Artificial Neural Networks for Structural Vibration Control Ju-Tae Kim: Graduate Student, KAIST, Korea Ju-Won Oh: Professor, Hannam University, Korea

5

• Training rule of controller neural network

• SDOF linear/nonlinear structural control

Scope

Page 6: 1 Artificial Neural Networks for Structural Vibration Control Ju-Tae Kim: Graduate Student, KAIST, Korea Ju-Won Oh: Professor, Hannam University, Korea

6

• Emulator neural network

- trained to imitate responses of unknown structures.

- used for training of controller neural network.

• Controller neural network - trained to make control force.

- used for controller.

2. Neural Networks for Control

Two Neural Networks

Page 7: 1 Artificial Neural Networks for Structural Vibration Control Ju-Tae Kim: Graduate Student, KAIST, Korea Ju-Won Oh: Professor, Hannam University, Korea

7

Controller(ANN)

Minimize error(E)

Emulator(ANN)

Structure

Load

Z-1

+

_

D (desired response)

E=D-X

Previous Studies

Weights of controller neural network(W) are updated

to minimize error function(E).

U X

Page 8: 1 Artificial Neural Networks for Structural Vibration Control Ju-Tae Kim: Graduate Student, KAIST, Korea Ju-Won Oh: Professor, Hannam University, Korea

8

Controller(ANN)

Minimize cost(J)

Emulator(ANN)

Structure

Load

Z-1

Proposed Method

Weights of controller neural network(W) are updated

to minimize cost function(J) instead of error function(E).

UX

Page 9: 1 Artificial Neural Networks for Structural Vibration Control Ju-Tae Kim: Graduate Student, KAIST, Korea Ju-Won Oh: Professor, Hannam University, Korea

9

n

nTnnTn

n

n

tRUUQXX

JJ

2

1

ˆˆ

(1)

RQ,

nn UX , : response, control force vector

: weighting matrices

• Cost function

where

Page 10: 1 Artificial Neural Networks for Structural Vibration Control Ju-Tae Kim: Graduate Student, KAIST, Korea Ju-Won Oh: Professor, Hannam University, Korea

10

• Controller neural network

)( jj netfh

L

iijij IWnet

1

)( kk netgu

L

ijkjk hWnet

1

hidden layer

Output layer

(2)

(3)

(4)

(5)

Ii uk

Wji Wkj

i=1~Lj=1~M

k=1~N

Page 11: 1 Artificial Neural Networks for Structural Vibration Control Ju-Tae Kim: Graduate Student, KAIST, Korea Ju-Won Oh: Professor, Hannam University, Korea

11

kj

nTn

n

nTn

kj

n

n

n

kj

n

n

n

n

n

kj

nn

kj

W

URU

U

XQXt

W

U

U

J

W

U

U

X

X

J

W

JW

ˆˆ

ˆ

• Learning rule: weights of output-hidden layer

11 nkj

nkj

nkj

nkj WWWW (6)

(7)

Page 12: 1 Artificial Neural Networks for Structural Vibration Control Ju-Tae Kim: Graduate Student, KAIST, Korea Ju-Won Oh: Professor, Hannam University, Korea

12

jknkkn

k

nTn

kj

nkn

kknk

nTnn

kj

hnetguru

XQXt

W

uur

u

XQXtW

)(

(8)

nj

nk

nkj hW

)( knkkn

k

nTnn

k netguru

XQXt

(9)

(10)where

Page 13: 1 Artificial Neural Networks for Structural Vibration Control Ju-Tae Kim: Graduate Student, KAIST, Korea Ju-Won Oh: Professor, Hannam University, Korea

13

(11)

(12)

• Learning rule: weights of hidden-input layer

11 nji

nji

nji

nji WWWW

ji

nTn

n

nTn

ji

n

n

n

ji

n

n

n

n

n

ji

nnji

W

URU

U

XQXt

W

U

U

J

W

U

U

X

X

J

W

JW

ˆˆ

ˆ

Page 14: 1 Artificial Neural Networks for Structural Vibration Control Ju-Tae Kim: Graduate Student, KAIST, Korea Ju-Won Oh: Professor, Hannam University, Korea

14

ni

nj

nji IW

)()(

)()(

)()( 11

jn

NjN

jn

kjk

jnj

Tnn

nTnn

j

netfWnetg

netfWnetg

netfWnetg

RUU

XQXt

(13)

(14)

where

Page 15: 1 Artificial Neural Networks for Structural Vibration Control Ju-Tae Kim: Graduate Student, KAIST, Korea Ju-Won Oh: Professor, Hannam University, Korea

15

k

c

m

uxmkxxcxm g

u

x

x

g

3. Numerical Examples

Control of Linear Structure

• Equation of motion

: mass

: damping

: stiffness

: displacement

: ground acceleration

: control force

(15)

Page 16: 1 Artificial Neural Networks for Structural Vibration Control Ju-Tae Kim: Graduate Student, KAIST, Korea Ju-Won Oh: Professor, Hannam University, Korea

16

TxxX

gxFBuAXX

1

0,

/1

0,

10F

mB

mcmkA

gxumx

x

mcmkx

x

1

0

/1

010

• State-space form

Let , then

(16)

(17)

Page 17: 1 Artificial Neural Networks for Structural Vibration Control Ju-Tae Kim: Graduate Student, KAIST, Korea Ju-Won Oh: Professor, Hannam University, Korea

17

017.00

01Q

41076.5 R

kgm 1

mNc sec25.1

mNk 39

• Parameters

• Controller neural network

)1( nx

)1( nx

)1( nxg

)(nu

Page 18: 1 Artificial Neural Networks for Structural Vibration Control Ju-Tae Kim: Graduate Student, KAIST, Korea Ju-Won Oh: Professor, Hannam University, Korea

18

(a) El Centro earthquake(1940) (b) California earthquake(1952)

(c) Northridge earthquake(1994)

• Ground accelerations( )

TRAINED UNTRAINED

UNTRAINED

gx

0 10 20 30 40Time (sec)

-4 .0

-2 .0

0.0

2.0

4.0

Acc

eler

atio

n (

m/s

ec 2 )

0 10 20 30 40Time (sec)

-2 .0

-1 .0

0.0

1.0

2.0

Acc

eler

atio

n (

m/s

ec 2 )

0 10 20 30 40Time (sec)

-4 .0

-2 .0

0.0

2.0

4.0

Acc

eler

atio

n (

m/s

ec 2 )

Page 19: 1 Artificial Neural Networks for Structural Vibration Control Ju-Tae Kim: Graduate Student, KAIST, Korea Ju-Won Oh: Professor, Hannam University, Korea

19

0 10 20 30 40 500.0

0.5

1.0

1.5

2.0

epoch

<

Cos

t fun

ctio

n(J)

• Minimization of cost function

Page 20: 1 Artificial Neural Networks for Structural Vibration Control Ju-Tae Kim: Graduate Student, KAIST, Korea Ju-Won Oh: Professor, Hannam University, Korea

20

(a) El Centro earthquake(trained)

(b) California earthquake(untrained)

• Control results

0 5 10 15 20T im e (sec)

-10.0

-5.0

0.0

5.0

10.0

Dis

plac

emen

t (cm

) uncontro lledcontro lled

0 5 10 15 20T im e (sec)

-80

-40

0

40

80

Dis

plac

emen

t (cm

) uncontro lledcontro lled

0 5 10 15 20T im e (sec)

-6 .0

-3.0

0.0

3.0

6.0

Dis

plac

emen

t (cm

) uncontro lledcontro lled

0 5 10 15 20T im e (sec)

-40

-20

0

20

40

Vel

ocity

(cm

/sec

) uncontro lledcontro lled

Page 21: 1 Artificial Neural Networks for Structural Vibration Control Ju-Tae Kim: Graduate Student, KAIST, Korea Ju-Won Oh: Professor, Hannam University, Korea

21

(c) Northridge earthquake(untrained)

0 5 10 15 20T im e (sec)

-10.0

-5.0

0.0

5.0

10.0

Dis

plac

emen

t (cm

) uncontro lledcontro lled

0 5 10 15 20T im e (sec)

-80

-40

0

40

80

Vel

ocity

(cm

/sec

) uncontro lledcontro lled

Page 22: 1 Artificial Neural Networks for Structural Vibration Control Ju-Tae Kim: Graduate Student, KAIST, Korea Ju-Won Oh: Professor, Hannam University, Korea

22

uxmxxfxcxm g ),(

kdwkxxxf )1(),(

)(1 1 pp

wxwwxxad

w

5.0

5.0

6.0

5.0

04.0

0.1

p

d

a

Control of Nonlinear Structure

(18)

(19)

(20)

• Equation of motion

• Parameters

Page 23: 1 Artificial Neural Networks for Structural Vibration Control Ju-Tae Kim: Graduate Student, KAIST, Korea Ju-Won Oh: Professor, Hannam University, Korea

23

-0 .10 -0.05 0.00 0.05 0.10D isplacem ent (m )

-4 .0

-2.0

0.0

2.0

4.0R

esto

ring

forc

e (N

)

-0 .10 -0.05 0.00 0.05 0.10D isplacem ent (m )

-4 .0

-2.0

0.0

2.0

4.0

Res

torin

g fo

rce

(N)

-0 .10 -0.05 0.00 0.05 0.10D isplacem ent (m )

-4 .0

-2.0

0.0

2.0

4.0

Res

torin

g fo

rce

(N)

-0 .10 -0.05 0.00 0.05 0.10D isplacem ent (m )

-4 .0

-2.0

0.0

2.0

4.0

Res

torin

g fo

rce

(N)

3.0

6.0 60k

39k

Page 24: 1 Artificial Neural Networks for Structural Vibration Control Ju-Tae Kim: Graduate Student, KAIST, Korea Ju-Won Oh: Professor, Hannam University, Korea

24

(a) El Centro earthquake(trained)

(b) California earthquake(untrained)

• Control results-1

0 5 10 15 20T im e (sec)

-10.0

-5.0

0.0

5.0

10.0

Dis

plac

emen

t (cm

) uncontro lledcontro lled

0 5 10 15 20T im e (sec)

-60

-30

0

30

60

Vel

ocity

(cm

/sec

) uncontro lledcontro lled

0 5 10 15 20T im e (sec)

-6 .0

-3.0

0.0

3.0

6.0

Dis

plac

emen

t (cm

) uncontro lledcontro lled

0 5 10 15 20T im e (sec)

-40

-20

0

20

40

Vel

ocity

(cm

/sec

) uncontro lledcontro lled

Page 25: 1 Artificial Neural Networks for Structural Vibration Control Ju-Tae Kim: Graduate Student, KAIST, Korea Ju-Won Oh: Professor, Hannam University, Korea

25

(c) Northridge earthquake(untrained)

0 5 10 15 20T im e (sec)

-10.0

-5.0

0.0

5.0

10.0

Dis

plac

emen

t (cm

) uncontro lledcontro lled

0 5 10 15 20T im e (sec)

-60

-30

0

30

60

Vel

ocity

(cm

/sec

) uncontro lledcontro lled

Page 26: 1 Artificial Neural Networks for Structural Vibration Control Ju-Tae Kim: Graduate Student, KAIST, Korea Ju-Won Oh: Professor, Hannam University, Korea

26

-0 .10 -0.05 0.00 0.05 0.10D isplacem ent (m )

-4 .0

-2.0

0.0

2.0

4.0

Res

torin

g fo

rce

(N)

-0 .10 -0.05 0.00 0.05 0.10D isplacem ent (m )

-4 .0

-2.0

0.0

2.0

4.0

Res

torin

g fo

rce

(N)

-0 .10 -0.05 0.00 0.05 0.10D isplacem ent (m )

-4 .0

-2.0

0.0

2.0

4.0

Res

torin

g fo

rce

(N)

-0 .10 -0.05 0.00 0.05 0.10D isplacem ent (m )

-4 .0

-2.0

0.0

2.0

4.0R

esto

ring

forc

e (N

)

-0.14 -0.07 0.00 0.07 0.14D isplacem ent (m )

-4 .0

-2.0

0.0

2.0

4.0

Res

torin

g fo

rce

(N)

-0.14 -0.07 0.00 0.07 0.14D isplacem ent (m )

-4 .0

-2.0

0.0

2.0

4.0

Res

torin

g fo

rce

(N)

(a) El Centro earthquake (b) California earthquake (c) Northridge earthquake

• Control results-2 c

ontr

olle

d

u

ncon

trol

led

Page 27: 1 Artificial Neural Networks for Structural Vibration Control Ju-Tae Kim: Graduate Student, KAIST, Korea Ju-Won Oh: Professor, Hannam University, Korea

27

4. Conclusions

• Training rule of neural network for optimal

control is proposed.

• Not only linear but nonlinear structure is

controlled successfully.