Design of Experiments Guide  • Prospective Sample Size and Power • Reliability Test Plan and Demonstration • Reliability Demonstration
Previous
 • 
Next
Reliability Demonstration
A reliability demonstration consists of testing a specified number of units for a specified period of time. If fewer than k units fail, you pass the demonstration, and conclude that the product reliability meets or exceeds a reliability standard.
The Reliability Demonstration feature computes required sample sizes and experimental run-times for demonstrating that a product meets or exceeds a specified reliability standard.
To launch the Reliability Demonstration calculator, select DOE > Design Diagnostics > Sample Size and Power, and then select Reliability Demonstration. Reliability Demonstration Window shows the Reliability Demonstration window.
Reliability Demonstration Window
The Reliability Demonstration window has the following options:
Alpha
is the alpha level.
Distribution
is the assumed failure distribution. After selecting a distribution, specify the associated scale parameter in the text field under the Distribution menu.
Max Failures Tolerated
is the maximum number of failures you want to allow during the demonstration. If we observe this many failures or fewer, then we say we passed the demonstration.
Time
is the time component of the reliability standard you want to meet.
Probability of Surviving
is the probability component of the reliability standard you want to meet.
Time of Demonstration
is the required time for the demonstration.
Number of Units Tested
is the required number of units for the demonstration.
Continue
click here to make the calculations.
Back
click here to go back to the Power and Sample Size window.
After the Continue button is clicked, a plot appears (see Reliability Demonstration Plot).
Reliability Demonstration Plot
The true probability of a unit surviving to the specified time is unknown. The Y axis of the plot gives the probability of passing the demonstration (concluding the true reliability meets or exceeds the standard) as a function of the true probability of a unit surviving to the standard time. Notice the line is increasing, meaning that the further the truth is above the standard, the more likely you are to detect the difference.
Example
A company wants to get the required sample size for assessing the reliability of a new product against an historical reliability standard of 90% survival after 1000 hours. From prior studies on similar products, it is believed that the failure distribution is Weibull, with a β parameter of 3. The company can afford to run the demonstration for 800 hours, and wants the experiment to result in no more than 2 failures.
To compute the required sample size, do the following steps:
1.
Select DOE > Design Diagnostics > Sample Size and Power.
2.
Select Reliability Demonstration.
3.
Select Weibull from the Distribution list.
4.
Enter 3 for the Weibull β.
5.
Enter 2 for Max Failures Tolerated.
6.
Enter 1000 for Time.
7.
Enter 0.9 for Probability of Surviving.
8.
Enter 800 for Time of Demonstration.
9.
Click Continue. Reliability Demonstration Results shows the results.
Reliability Demonstration Results
The company needs to run 118 units in the demonstration. Furthermore, if they observe 2 or fewer failures by 800 hours, we can conclude that the new product reliability is at least as reliable as the standard.

Previous
 • 
Next
Help created on 9/19/2017