Dependability Modelling under Uncertainty: An Imprecise Probabilistic Approach

✍ Scribed by Philipp Limbourg

• Publisher: Springer
• Year: 2008
• Tongue: English
• Leaves: 148
• Series: Studies in Computational Intelligence; 148
• Category: Library

✦ Synopsis

Mechatronic design processes have become shorter and more parallelized, induced by growing time-to-market pressure. Methods that enable quantitative analysis in early design stages are required, should dependability analyses aim to influence the design. Due to the limited amount of data in this phase, the level of uncertainty is high and explicit modeling of these uncertainties becomes necessary.

This work introduces new uncertainty-preserving dependability methods for early design stages. These include the propagation of uncertainty through dependability models, the activation of data from similar components for analyses and the integration of uncertain dependability predictions into an optimization framework. It is shown that Dempster-Shafer theory can be an alternative to probability theory in early design stage dependability predictions. Expert estimates can be represented, input uncertainty is propagated through the system and prediction uncertainty can be measured and interpreted. The resulting coherent methodology can be applied to represent the uncertainty in dependability models.

✦ Table of Contents

Title Page
Preface
Contents
Acronyms
Introduction
Thesis Aims
Overview
Dependability Prediction in Early Design Stages
The Mechatronic Project Cycle and Its Demand on Dependability Prediction
The V-Model: A Mechatronic Process Model
The Mechatronic Dependability Prediction Framework and the Integration of Dependability into the V-Model
Dependability in an Early Design Stage
Definitions on Dependability, Reliability and Safety
Basic Definitions of Elements in Dependability Modeling
Dependability and Its Attributes
Means to Attain Dependability
Boolean System Models
Representation and Propagation of Uncertainty Using the Dempster-Shafer Theory of Evidence
Types and Sources of Uncertainty
The ESReDA Framework on Uncertainty Modeling
The Dempster-Shafer Theory of Evidence
Dempster-Shafer Theory in Dependability Modeling
Foundations
An Illustrative Example
Aggregation
Dependency
The Concept of Copulas
Copula Types
Applying Copulas to Model Joint Imprecise Distributions
Propagation through System Functions
Measures of Uncertainty
Sensitivity Analysis Using Uncertainty Measures
Comparing Dempster-Shafer Theory and Probabilistic Settings
The Decision between Dempster-Shafer Theory and Probability
Predicting Dependability Characteristics by Similarity Estimates – A Regression Approach
Related Work: The Transformation Factor
Estimation Procedure
Elicitation
Inherent Sources of Prediction Uncertainty
Formulating Similarity Prediction as a Regression Problem
Regression
Implementing the Regression Problem
Learning Similarity Prediction
Neural Networks
Gaussian Processes
Test Sets
Scalable Test Suite
Real Test Set
Results
Scalable Test Suite
Real Test Set
Conclusion
Design Space Specification of Dependability Optimization Problems Using Feature Models
The Redundancy Allocation Problem
Feature Models
Basic Feature Set Types
Feature Models Defining Optimization Problems
Generating Reliability Block Diagrams and Fault Trees from Realizations
Conclusion
Evolutionary Multi-objective Optimization of Imprecise Probabilistic Models
Pareto-Based Multi-objective Optimization
Deterministic Multi-objective Functions
Imprecise Multi-objective Functions
Pareto Evolutionary Algorithms for Multi-objective Optimization Problems
Evolutionary Algorithms: Overview and Terminology
An Evolutionary Algorithm forMulti-objective Optimization under Uncertainty
Dominance Criteria on Imprecise Objective Functions
Probabilistic Dominance
Imprecise Probabilistic Dominance
Density Estimation for Imprecise Solution Sets
Illustrative Examples
RAP
Complex Design Space
Conclusion
Case Study
Background
System under Investigation
Fault Tree Model
Quantifying Reliability According to the IEC 61508 and the ESReDA Uncertainty Analysis Framework
Quantification of the Input Sources
Practical Implementation Characteristics and Results of the Uncertainty Study
Specifying Design Alternatives
Optimizing System Reliability
Summary, Conclusions and Outlook
Summary and Main Contributions
Outlook
References
Index