Abstract
This thesis studies the statistical analysis of expert
judgements and
prediction of wear. The point of view adopted is the one
of
information theory and Bayesian statistics. A general
Bayesian
framework for analyzing both the expert judgements and
wear
prediction is presented. Information theoretic
interpretations are
given for some averaging techniques used in the
determination of
concensus distributions. Further, information theoretic
models
are compared with a Bayesian model. The general Bayesian
framework is then applied in analyzing expert judgements
based on
ordinal comparisons. In this context, the value of
information
lost in the ordinal comparison process is analyzed by
applying
decision theoretic concepts. As a generalization of the
Bayesian
framework, stochastic filtering models for wear
prediction are
formulated. These models utilize the information from
condition
monitoring measurements in updating the residual life
distribution
of mechanical components. Finally, the application of
stochastic
control models in optimizing operational strategies for
inspected
components are studied. Monte-Carlo simulation methods,
such as
the Gibbs sampler and the stochastic quasi-gradient
method, are
applied in the determination of posterior distributions
and in the
solution of stochastic optimization problems.
Original language | English |
---|---|
Qualification | Doctor Degree |
Awarding Institution |
|
Supervisors/Advisors |
|
Award date | 27 May 1994 |
Place of Publication | Espoo |
Publisher | |
Print ISBNs | 951-38-4419-6 |
Publication status | Published - 1994 |
MoE publication type | G5 Doctoral dissertation (article) |
Keywords
- statistical models
- bayes theorem
- comparison
- modelling
- stochastic processes
- filtering
- optimization
- theses