Accession Number : ADA294515

Title :   Forecasting Overhaul or Replacement Intervals Based on Estimated System Failure Intensity.

Descriptive Note : Master's thesis,

Corporate Author : NAVAL POSTGRADUATE SCHOOL MONTEREY CA

Personal Author(s) : Gannon, James M.

PDF Url : ADA294515

Report Date : DEC 1994

Pagination or Media Count : 117

Abstract : System reliability can be expressed in terms of the pattern of failure events over time. Assuming a nonhomogeneous Poisson process, and Weibull intensity function for complex repairable system failures, the degree of system deterioration can be approximated. Maximum likelihood estimators (MLEs) for the system Rate of Occurrence of Failure (ROCOF) function are presented. Evaluating the integral of the ROCOF over annual usage intervals yields the expected number of annual system failures. By associating a cost of failure with the expected number of failures, budget and program policy decisions can be made based on expected future maintenance costs. Monte Carlo simulation is used to estimate the range and the distribution of the net present value and intemal rate of return of alternative cash flows based on the distributions of the cost inputs and confidence intervals of the MLEs. (AN)

Descriptors :   *WEIBULL DENSITY FUNCTIONS, *MILITARY VEHICLES, *MAINTENANCE MANAGEMENT, *SYSTEMS ANALYSIS, DATA BASES, MATHEMATICAL MODELS, SIMULATION, TIME INTERVALS, MILITARY REQUIREMENTS, POLICIES, DECISION MAKING, LIFE EXPECTANCY(SERVICE LIFE), TIME DEPENDENCE, COST ANALYSIS, MAXIMUM LIKELIHOOD ESTIMATION, FORECASTING, FAILURE, THESES, MONTE CARLO METHOD, RELIABILITY, REPAIR, MARINE CORPS EQUIPMENT, TRUCKS, DETERIORATION, CONFIDENCE LIMITS, POISSON DENSITY FUNCTIONS.

Subject Categories : Operations Research
      Surface Transportation and Equipment
      Logistics, Military Facilities and Supplies

Distribution Statement : APPROVED FOR PUBLIC RELEASE