Date of Award

2014

Publisher

North Dakota State University

Document Type

Thesis

Degree Awarded

Master of Science (MS)

Program

Industrial and Manufacturing Engineering

Department

Industrial and Manufacturing Engineering

College

Engineering

Faculty Advisor

Yadav, Om Prakash

Description

Providing more realistic reliability prediction based on small proportion of failed population or test data has always been a challenging task. Manufacturers rely heavily on reliability prediction for designing warranty plan. Further, to predict warranty claims for the remaining warranty period, it is important to have more realistic reliability assessment by considering a larger proportion of the population or the maximum possible information on the remaining population. However, generally this information is not readily available and is very difficult to gather on the scattered population. In this work, we propose to use customer usage rate profile to generate censored usage data on the remaining population that do not have any failure and warranty claim yet. We intend to use field data available such as warranty claims, field failures, recall data, and maintenance data to develop usage rate profile and subsequently estimate censored usage time. Finally, reliability estimation methodology is developed considering both censored data and field failure data to provide more reasonable reliability prediction for the remaining warranty period. The proposed methodology is demonstrated considering real life data from a big manufacturing company.

Rights

NDSU Policy 190.6.2

Rights Link

https://www.ndsu.edu/fileadmin/policy/190.pdf

Handle Identifier

https://hdl.handle.net/10365/27510

Download

Share

COinS