Article ID: | iaor201112639 |
Volume: | 27 |
Issue: | 6 |
Start Page Number: | 781 |
End Page Number: | 793 |
Publication Date: | Oct 2011 |
Journal: | Quality and Reliability Engineering International |
Authors: | Quan Sun, Kvam Paul H |
Keywords: | statistics: regression |
At the core of satellite rubidium standard clocks is the rubidium lamp, which is a critical piece of equipment in a satellite navigation system. There are many challenges in understanding and improving the reliability of the rubidium lamp, including the extensive lifetime requirement and the dearth of samples available for destructive life tests. Experimenters rely on degradation experiments to assess the lifetime distribution of highly reliable products that seem unlikely to fail under the normal stress conditions, because degradation data can provide extra information about product reliability. Based on recent research on the rubidium lamp, this article presents a multi-cause degradation path model, including its application background, model description, modeling method, and parameter estimation method. Using the available data from degradation tests, we construct point estimates and interval estimates for rubidium lamp lifetimes using regression techniques.