JUROJIN – Statistics for Fatigue Testing and Reliability Analysis

Challenge: Reliability Demonstration is Expensive!

Before components enter production only few and expensive prototypes are available for reliability demonstration. Especially for safety relevant components, this demonstration is crucial.

In order to plan the verification efficiently, many questions have to be answered

How many prototypes need to be tested? At what test duration?
Either many short or few long tests?
How to analyse the test results?
Required statistical confidence level?
Are different suppliers producing the same quality?
Is it possible to expand a components homologation to a modified version?
etc.

With the help of statistical reliability theory, one could answer the questions in principle. Unfortunately, this theory is almost always formulated only for larger sample sizes. Additionally, it is difficult to find an access to the thought patterns of statistics.

Our Mission

Jurojin is the Software product for engineers who occasionally have to statistically evaluate fatigue strength data and who value easy-to-generate, correct evaluations whose interpretation does not have to be laboriously worked out.

Unlike common statistics packages, you don't need any expertise in statistics while digging through huge menu structures.

Solution in Jurojin

The implementation of these advanced algorithms has produced the software package JUROJIN. Leading guidelines have been:

Approach 1: The correct statistic

Our algorithms use all the information in a sample; in particular, run-throughs (tests with no observed failure) can also be evaluated correctly. In addition, Jurojin specializes in small sample sizes.

Approach 2: Consider load

You can perform reliability verification against a defined test scenario or design customer, or even import or create a model of customer load. This makes it even easier to predict failures in the field and helps you control the risk of oversizing.

Approach 3: Use of prior knowledge

Store your evaluation results in a structured way in the connected database. You can fall back on this prior knowledge for future reliability verifications. With the help of clever Bayesian statistics, the testing effort can be noticeably reduced. Optionally, you can also have this prior knowledge derived from warranty data.