105374_en-US

liliconcom

Reliability: Estimating failure time under special testing conditions

Hi,

 

a customer has the following scenario:

They get from their customers motor testing data from a test rig (not field data). There they test under various conditions and always the full test time (which can vary between the tests, too). With this kind of data their customer expects them to estimate the failure probability in the field. So far so wierd 

 

test no.	stage	valve present	hours	test type	engine
5278	1	yes	465	Nardo	M9
5278	2	yes	465	Nardo	M9
6088	1	no	300	SHES+NC	M9
6088	2	yes	300	SHES+NC	M9
6117	1	yes	187	endurance	M9
6117	2	no	187	endurance	M9
6126	1	no	214	several	M9
6126	2	yes	214	several	M9
7291	1	yes	300	SHES+NC	M9
7291	2	yes	300	SHES+NC	M9
6107	1	no	392	Hot/ Cold	M9
6107	2	yes	392	Hot/ Cold	M9
7324	1	no	417	Hot/ Cold	M9
7324	2	yes	417	Hot/ Cold	M9
6917	1	no	416	SHES+NC	M9
6917	2	yes	416	SHES+NC	M9
6108	1	yes	562	Cmax/ Pmax	M9
6108	2	yes	562	Cmax/ Pmax	M9
1801	2	yes	314	Cmax/ Pmax	R9
1839	2	no	229	Hot/ Cold	R9
1839	2	no	400	Hot/ Cold	R9
1020	2	yes	435	SHES+NC	R9
833	2	no	388	SHES+NC	R9
1903	2	yes	357	spark end.	R9
1025	2	yes	279	Laquage	R9

Inn the data you see the test scenarious, two engines (M9 and R9). Their parts will be within the engines of the OEM who do the test with their engines (not in the field). Their parts include two rubber valves, listed as "stage". M9 has two, R9 only the second. A test run is a failure if at the end of the test at one valve is missing ("no" in valve present).

I've made some analysis (attached file), but I have some questions if this is at all an analysis one can trust.

 

1. As the test scenarios and the run times of the test are different does this impact the life distribution taking all observations into account? I guess yes.

2. Using test type as competing cause one could see that some test types are not included as there is just one or none failure in the data. This of course results in a huge confidence interval. If one would like at least to know when the a failure is to be expected they would have more information as of today. I guess this can be done already with that analysis, do I miss anything?

3. Is it a problem if they just detect a failure when the run is over? I compare it with repairable systems, and maintenance intervals, where you just detect there was a failure before that date, but not exactly to what time before that maintenance date. I'd expect that the uncertainty increases but probably not that much that the results cannot be used. Is that a too optimistic view?

 

How would you treat this problem if you cannot change the way the tests are run by the OEMs?

 

Thanks a lot,

Martin

 

Re: Reliability: Estimating failure time under special testing conditions

Based on what you described, I concur with Don that you fit a parametric survival: Hours as the time-to-event, Valve Present as a censoring indicator and Test Type and Engine as model effects. Then the question is: how to deal with Stage. If, for M9 engines, one of the two valves is lost then it is considered a failure then I'd combine the rows and recode Valve Present to reflect the change, and create a new failure mode to indicate if the failure is due to Stage 1 or Stage 2 failure. In other words, you'd run a competing-cause parametric survival model. 

  

Re: Reliability: Estimating failure time under special testing conditions

I'd go with Fit Parametric (or Generalized Regression if the customer has Pro). Not sure how you might use the effects, maybe the customer can offer some insight into how to do that. Worse case, you can average over the conditions for the significant effects.

Re: Reliability: Estimating failure time under special testing conditionsAh and yes they usually don’t repair but exchange, so non-repairable.Re: Reliability: Estimating failure time under special testing conditionsTo give some more background:
Customer is producing eg oil filters for car engines. These will be tested by their customers eg oem’s Within their engines. One test is running under certain stress conditions eg hot/cold or high touring or ... the test runs for a specific time eg 348h. Then they look if the filter is still ok , in the data there is a part with two valves which have to be still in the part and should not be lost. The next test might be under different conditions. They test in the lab so to say and not in the field. At the end of the run they check is the part ok or not. So it is not run until failure occurs. This is the data the oem sends to my customer and ask them to specify probability to failure in the field.
Hope this makes it more clear.Re: Reliability: Estimating failure time under special testing conditions

Martin,

What is being tested? When you say they run the test for the full time, I assume that whatever is being tested is tested to failure (i.e., its a  nonrepairable system). At first glance, I would think that using Fit Parametric Survival would be the way to go, but I'd have to know a bit more before saying for sure.

Don