Reliability and Bathtub Curve
Abstract
Carl and Fred discussing the origin and meaning of the reliability “bathtub” curve, and why it is not useful as a visual analogy.
Key Points
Join Carl and Fred as they discuss the elements that make up full-life failure distributions, and the consequences of making wrong assumptions.
Topics include:
- What is the actual shape of the “bathtub” curve?
- Why don’t system failure distributions follow a “bathtub” curve?
- What are the different elements that make up the “bathtub” curve?
- Early field failures due to manufacturing defects, later field failures due to design deficiencies
- What about service-generated failures or initial customer dissatisfaction?
- Discussion of actual field failures over time for vehicles, showing a “check-mark” curve
- We are seeing “check-mark” or “V” curves, why?
- What do the presence of early failure mechanisms have to do with the type of curve that is seen in practice?
- Why are people attracted to assumption of constant failure rate? Is it wishful thinking?
- Listener quiz: reliability allocation of the metric “Defects Per Thousand Vehicles”
- How to include “out-of-box” failures
- Look at actual data rather than forcing to a math model that doesn’t fit
- What visual representation reflects the failure rate of your product?
Enjoy an episode of Speaking of Reliability. Where you can join friends as they discuss reliability topics. Join us as we discuss topics ranging from design for reliability techniques to field data analysis approaches.
SOR 720 Reliability and Bathtub CurveCarl S. Carlson
- Social:
- Link:
- Embed:
“The Bathtub Curve Doesn’t Always Hold Water,” ASQC Reliability Review, Vol. 15, No. 3, Sept. 1994 pp 5-7. Attrition and retirement make failure rate functions decrease in old age, perhaps even despite (premature?) wearout like this…. \____/\
Another reason for nonparametric failure rate function estimators. Is there reality in reliability?