You are on page 1of 8

U

f.alihoseini@math.iut.ac.ir


.
.
U . .
: - U - - -


. ) (. . .
t

.

.

.
.

.
.
.
.
- ) (
)(1

) F(t ) = 1 F(t ) = P (T t

- : .
1
) f (t
)= lim P (t < T < t + t | T > t ) (2
t
) F (t
- ) ( MRL .

= ) h(t

F ( x)dx

t
(t ) = E (T t | T > t ) =
)(3
) F (t
) (

.
U
.

U .

U .

U
F U )) (h(t
.
.
: .
.
.
: .

: .

U . U . U
.

. U


U .
) Mi(1995 .
F U < 0 t1 t 2 ) h(t 0 t t1
. t 1 t t 2 t t 2 .
.
t t1

)(4

t1 t t 2
t t2

) h1 (t

h(t ) =
) h (t
2

) h(t ] [0, t1 t t 2 .
.

. ) (
U .

U
.
) (TTT Campo, Barlow .
TTT
)(5

) H F1 (t
(t ) = 1
) H F (t
1
F


)(6

0 u 1

R (u )du

) F 1 ( t

= ) H F1 (t

)( TTT)( . U TTT
)( )( S .

. F t



. .

.
: t , , 0
.
)(7

t >0
, , > 0

) )

(F (T ) = 1 exp(


.
.
.
] Chen[4
.
.

}] ) R (t ) = exp{ [1 e ( t /
, , > 0 t 0
)(8

.

U .
t
t
] r (t ) = ( ) 1 exp[( )

)(9

}] ) F (t ) = 1 R (t ) = 1 exp{ [1 e ( t /

)(10
.
)(11

t
t
]) ) f (t ) = ( ) 1 exp[( ) + (1 e ( t /

])(t / ) 1 exp[(t / ) ][ (t / ) + ( 1
)(12

) ( .
.
= ) r (t

1 :
t > 0 r (t ) > 0 ) r (t .
> 1 r (0) = 0 = 1 r (0) =
r (t ) as t
< 1 :
1

r (t * ) = 0

)(13

) 1

(t =
*

* t . * r (t ) < 0 t < t
* r (t ) > 0 t > t . U .
t 0 or t

)( * t .

if

) r (t


) (MTTF ) (Mean Time To Failure_
.
)]}dt (14

t
( )

= tdF (t ) = R(t )dt = exp{ [1 e

. .
.

t 2 dF ( t ) 2 = 2 tR ( t ) dt 2
0

]}dt 2

)(15

) (

= ) Var (T

= 2 t exp{ [1 e
0


.
:

)(16

t
t
1 [1 + ( ) + (t ) ] ( )

t
( )

1 e

)(17

} ]} exp{ 1 t

1
= 1

) (

R (t ) = exp{ [1 e

U .


.
.

n .

] Lawless [5 T1 , T2 ...Tn L1 , L2 ...Ln


t i = min{Ti , Li } i = 1,2...n .

)(18

n
t
t
t
}] L( , , ) = k k ( i ) 1 exp{ ( i ) + [1 exp( i )

iD

t i = Ti i = 1 t i = Li i = 0 } 1 j n

iD

D = { j , j = 1

k n .

. . .

) WPP(weibull probability plot
.
) ( = 1
. .
t
( )

R (t ) = exp{(1 e

)(19
.
x = ln t
y = ln t ln = x ln
for < x < +
)(20

.
})

) (
) t t ( .
t .

)(21

as t 0

t
( )

t
( )

1 e

:
}) y = ln{ ln R (t

)(22

x = ln t

y x .
) y = x + ln( 1

)(23
) ln( 1
.
}]

t
( )

ln[ ln R (t )] = ln{ [1 e

= ln{ [e

t
( )

1]} = ln( ) + ln{e

t
( )

1}

(24)
t

t
ln{exp[( ) ] 1}

t
t
= ln{1 exp[( ) ]} ln{exp[( ) ]}

(25)

t
t
= exp[( ) ] + ( )

t
) ( t

.
.


. U
( ) .
.
.

[1] Xie M, Tang Y, Goh TN. A modified Weibull extension with bathtub shaped failure rate function. Reliability
Engineering and System Safety 2002; 76:279-285.
[2] Lai CD, Xie M, Murthy DNP. Bathtub-shaped failure rate life distributions. Handbook of statistics. Advances
in reliability, vol. 20.London: Elsevier, 2001 p. 69-104
[3]Tang Y, Xie M, Goh TN. Statistical analysis of a weibull extension model. Communication in Statistics 2003;
Vol. 32, No. 5, pp. 913-928
[4]Chen Z. A new two-parameter lifetime distribution with bathtub shape or increasing failure rate function.
Statistics & Probability Letters.2000; 49: 155-161.
[5]Lawless JF. Statistical Models and Methods for life time data.1982; Wiley, New York
[6]Mi J. Bathtub failure rate and upside-down bathtub mean residual life. IEEE Transaction on Reliability. 1995;
Vol. 44, No.3, pp. 388-397