INFORMS Journal on Computing
Artificial Intelligence: A Modern Approach
Artificial Intelligence: A Modern Approach
Hi-index | 0.00 |
When conducting an availability analysis we cannot verify an assigned probability, as it expresses the analyst's uncertain prior observation. We only review the background information used as the rationale for the assignment but, generally, it will not be possible to explicitly document all the transformation steps from this background information to the assigned probability. There are various algorithms that have been used to perform this task. This paper explores Markov chains techniques for searching a given problem probability for a particular target. The work in this paper has two parts. In the first part, a theoretical approach for determining the availability of interacting system man-machine is presented. In the second part an illustrative example of the presented approach is given. Results have shown that this approach allows the estimation of availability for complex systems, such as those involved in railway transport, without performing laborious calculus, e.g. large Markov chains.