Abstract
| 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) |
Fingerprint
Keywords
- statistical models
- bayes theorem
- comparison
- modelling
- stochastic processes
- filtering
- optimization
- theses
Cite this
}
Statistical models for expert judgement and wear prediction : Dissertation. / Pulkkinen, Urho.
Espoo : VTT Technical Research Centre of Finland, 1994. 152 p.Research output: Thesis › Dissertation › Collection of Articles
TY - THES
T1 - Statistical models for expert judgement and wear prediction
T2 - Dissertation
AU - Pulkkinen, Urho
N1 - Project code: aut9412
PY - 1994
Y1 - 1994
N2 - 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.
AB - 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.
KW - statistical models
KW - bayes theorem
KW - comparison
KW - modelling
KW - stochastic processes
KW - filtering
KW - optimization
KW - theses
M3 - Dissertation
SN - 951-38-4419-6
T3 - VTT Publications
PB - VTT Technical Research Centre of Finland
CY - Espoo
ER -