Statistical models for expert judgement and wear prediction: Dissertation

Urho Pulkkinen

Research output: ThesisDissertation

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 languageEnglish
QualificationDoctor Degree
Awarding Institution
  • Helsinki University of Technology
Supervisors/Advisors
  • Hämäläinen, Raimo, Supervisor, External person
Award date27 May 1994
Place of PublicationEspoo
Publisher
Print ISBNs951-38-4419-6
Publication statusPublished - 1994
MoE publication typeG5 Doctoral dissertation (article)

Fingerprint

Wear of materials
Gradient methods
Information theory
Condition monitoring
Statistical methods
Statistical Models
Statistics

Keywords

  • statistical models
  • bayes theorem
  • comparison
  • modelling
  • stochastic processes
  • filtering
  • optimization
  • theses

Cite this

Pulkkinen, U. (1994). Statistical models for expert judgement and wear prediction: Dissertation. Espoo: VTT Technical Research Centre of Finland.
Pulkkinen, Urho. / Statistical models for expert judgement and wear prediction : Dissertation. Espoo : VTT Technical Research Centre of Finland, 1994. 152 p.
@phdthesis{1e4e80350cc3456ba42f2a89f596d637,
title = "Statistical models for expert judgement and wear prediction: Dissertation",
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.",
keywords = "statistical models, bayes theorem, comparison, modelling, stochastic processes, filtering, optimization, theses",
author = "Urho Pulkkinen",
note = "Project code: aut9412",
year = "1994",
language = "English",
isbn = "951-38-4419-6",
series = "VTT Publications",
publisher = "VTT Technical Research Centre of Finland",
number = "181",
address = "Finland",
school = "Helsinki University of Technology",

}

Pulkkinen, U 1994, 'Statistical models for expert judgement and wear prediction: Dissertation', Doctor Degree, Helsinki University of Technology, Espoo.

Statistical models for expert judgement and wear prediction : Dissertation. / Pulkkinen, Urho.

Espoo : VTT Technical Research Centre of Finland, 1994. 152 p.

Research output: ThesisDissertation

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 -

Pulkkinen U. Statistical models for expert judgement and wear prediction: Dissertation. Espoo: VTT Technical Research Centre of Finland, 1994. 152 p.