reliability {smmR}R Documentation

Reliability Function

Description

Consider a system SystemS_{ystem} starting to function at time k=0k = 0. The reliability or the survival function of SystemS_{ystem} at time kNk \in N is the probability that the system has functioned without failure in the period [0,k][0, k].

Usage

reliability(x, k, upstates = x$states, level = 0.95, klim = 10000)

Arguments

x

An object of S3 class smmfit or smm.

k

A positive integer giving the period [0,k][0, k] on which the reliability should be computed.

upstates

Vector giving the subset of operational states UU.

level

Confidence level of the asymptotic confidence interval. Helpful for an object x of class smmfit.

klim

Optional. The time horizon used to approximate the series in the computation of the mean sojourn times vector mm (cf. meanSojournTimes function) for the asymptotic variance.

Details

Consider a system (or a component) SystemS_{ystem} whose possible states during its evolution in time are E={1,,s}E = \{1,\dots,s\}. Denote by U={1,,s1}U = \{1,\dots,s_1\} the subset of operational states of the system (the up states) and by D={s1+1,,s}D = \{s_1 + 1,\dots, s\} the subset of failure states (the down states), with 0<s1<s0 < s_1 < s (obviously, E=UDE = U \cup D and UD=U \cap D = \emptyset, U, DU \neq \emptyset,\ D \neq \emptyset). One can think of the states of UU as different operating modes or performance levels of the system, whereas the states of DD can be seen as failures of the systems with different modes.

We are interested in investigating the reliability of a discrete-time semi-Markov system SystemS_{ystem}. Consequently, we suppose that the evolution in time of the system is governed by an E-state space semi-Markov chain (Zk)kN(Z_k)_{k \in N}. The system starts to work at instant 00 and the state of the system is given at each instant kNk \in N by ZkZ_k: the event {Zk=i}\{Z_k = i\}, for a certain iUi \in U, means that the system SystemS_{ystem} is in operating mode ii at time kk, whereas {Zk=j}\{Z_k = j\}, for a certain jDj \in D, means that the system is not operational at time kk due to the mode of failure jj or that the system is under the repairing mode jj.

Let TDT_D denote the first passage time in subset DD, called the lifetime of the system, i.e.,

TD:=inf{nN; ZnD} and inf :=.T_D := \textrm{inf}\{ n \in N;\ Z_n \in D\}\ \textrm{and}\ \textrm{inf}\ \emptyset := \infty.

The reliability or the survival function at time kNk \in N of a discrete-time semi-Markov system is:

R(k):=P(TD>k)=P(ZnU,n=0,,k)R(k) := P(T_D > k) = P(Zn \in U,n = 0,\dots,k)

which can be rewritten as follows:

R(k)=iUP(Z0=i)P(TD>kZ0=i)=iUαiP(TD>kZ0=i)R(k) = \sum_{i \in U} P(Z_0 = i) P(T_D > k | Z_0 = i) = \sum_{i \in U} \alpha_i P(T_D > k | Z_0 = i)

Value

A matrix with k+1k + 1 rows, and with columns giving values of the reliability, variances, lower and upper asymptotic confidence limits (if x is an object of class smmfit).

References

V. S. Barbu, N. Limnios. (2008). Semi-Markov Chains and Hidden Semi-Markov Models Toward Applications - Their Use in Reliability and DNA Analysis. New York: Lecture Notes in Statistics, vol. 191, Springer.


[Package smmR version 1.0.3 Index]