Reliability estimation considering usage rate profile and warranty claims

Abstract

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. Furthermore, 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 claims 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.

Big data and reliability applications: The complexity dimension

“…Liu and Tang (2015) presented a description of reliability analysis and spares provisioning for repairable systems with dependent failure processes and a time-varying installed base. Limon et al (2016) presented reliability estimation considering use rate profiles and warranty claims. King, Hong, and Meeker (2017) used product component genealogy information, which is readily available in production databases, to improve prediction accuracy.…”

Two-dimensional warranty: A literature review

“…A vast amount of literature on warranty can be found from monographs, 2–8 review papers, 1,9–17 and many other journal and conference papers. Interested readers are referred to Xie and Ye, 18 Lee et al, 19 Limon et al, 20 Tseng et al, 21 Park and Pham, 22 Darghouth et al, 23 Zhao and Xie, 24 and Murthy and Jack 25 for recent progresses on product warranty.…”