Sequential Estimation of Age Replacement Policies

Abstract

Optimal maintenance policies are designed to reduce the number of system failures and minimize the cost of repair by scheduling planned replacements. In this area the problem of updating the maintenance policy using the past maintenance history has not been adequately solved. In this thesis we study a sequential estimation procedure in a nonparametric setting to estimate the age replacement policy that minimizes long run expected maintenance costs. This thesis begins with the discussion of the concepts of preventive maintenance, age replacement policies, the settings of our simulation model, and a detailed description of the sequential estimation procedure. We include examples using actual replacement data which demonstrate the usefulness of the sequential procedure. Monte-Carlo methods are used to study the behavior of estimated optimal age replacement policy for different sample sizes, costs and underlying system life distributions. We also make comparison with Frees and Ruppert's (1985) sequential procedure is competitive and for large sample sizes performs better than the Frees and Ruppert's procedure. Finally, we sill introduce a graphical method to estimate the optimal age replacement policy. Thesis.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 01, 1990
Accession Number
ADA226614

Entities

People

  • Yang-huang Wu

Organizations

  • Naval Postgraduate School

Tags

Communities of Interest

  • C4I

DTIC Thesaurus Topics

  • Data Science
  • Estimators
  • Information Science
  • Maintenance
  • Maintenance Costs
  • Monte Carlo Method
  • Operations Research
  • Preventive Maintenance
  • Probability
  • Random Variables
  • Sampling
  • Scheduling (Production)
  • Simulations
  • Statistical Analysis
  • Statistics
  • Tractor Engines

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Logistics and Supply Chain Management.
  • Regression Analysis.