Author(s)

D. I. De Souza, D. R. Fonseca & D. Kipper

Abstract

In a previous paper we applied a sequential life testing approach to a low alloy-high strength steel part used in highway overpasses in Brazil. The data was collected over a period of a few years with the steel parts working under normal use conditions. In this paper we decided to use a combined approach of accelerated life testing with sequential life testing to verify if the test results obtained under accelerated conditions could be translated to the results verified under normal use conditions with a certain degree of accuracy. To accomplish this we will apply the \“Maxwell Distribution Law”. We elected as sampling distribution the three-parameter Weibull model. To estimate the three parameters of the Weibull underlying sampling distribution we will use a maximum likelihood approach for censored failure data. We will be assuming a linear acceleration condition. To evaluate the accuracy (significance) of the parameter values obtained under normal conditions for the underlying three-parameter Weibull model we will apply to the expected normal failure times sequential life testing using a truncation mechanism developed previously by De Souza. An example will illustrate the application of this procedure. Keywords: three-parameter Weibull model, low allot-high strength steel parts, sequential life testing, maximum likelihood approach. www.witpress.com, ISSN 1743-3517 (on-line) WIT Transactions on Information and Communication Technologies, Vol 43, ©2010 WIT Press doi: Risk Analysis VII PI-105

Keywords

three-parameter Weibull model, low allot-high strength steel parts, sequential life testing, maximum likelihood approach