How to do MSA when a single part also varies.
Six Sigma – iSixSigma › Forums › Old Forums › General › How to do MSA when a single part also varies.
- This topic has 68 replies, 18 voices, and was last updated 13 years, 3 months ago by
Mikel.
-
AuthorPosts
-
February 17, 2009 at 8:57 pm #51872
I have a couple of applications where people are trying to quantify their measurement system variation with parts that are not constant i.e. the measured value of each single part also changes from measurement to measurement.
Does anyone have experience with similar cases? How do you sort out the true MS variation from the part variation?0February 17, 2009 at 9:06 pm #181341
luke skywalkerParticipant@luke-skywalkerInclude @luke-skywalker in your post and this person will
be notified via email.Can you share what the parts are, or what they are made of? Also has anyone checked to ensure the measuring device is not broken?
0February 17, 2009 at 9:06 pm #181342
Ken FeldmanParticipant@DarthInclude @Darth in your post and this person will
be notified via email.Typically, a MSA study would consist of say 10 parts measured 2 times by 3 people. What I am about to say is a generality in the absence of a lot of detail in your post. Since the parts are the same, the variation could be attributable to the Repeatability of each operator and the Reproducibility between the operators. This is called a crossed study since the parts are measured across the operators. If the parts also vary then you have a different situation much as you would have if the test you were measuring was a destructive one thus making repeated measurements impossible. In this case you would analyze as a nested study. The Reproducibility issue becomes moot but the part to part variation and the repeatability remain. The big challenge is to get parts that are similar enough in nature to allow the Repeatability to become valid should there be an issue.
0February 17, 2009 at 9:10 pm #181343The parts are various optical components. An example of a specific measurement is Polarization Mode Dispersion. The problem is that both the parts and the measurement systems are leading edge and both introduce variation.
0February 17, 2009 at 9:15 pm #181345Darth,
Yeah, that’s the big challenge. How do you sort out part variation from measurement system variation in this case.0February 17, 2009 at 9:53 pm #181347
Ken FeldmanParticipant@DarthInclude @Darth in your post and this person will
be notified via email.How are you doing the part selection and why must they be different? No real secret solution here. If you select different parts from a single batch and all operators can measure from the same batch then you might make the assumption of “likeness”. If only one operator can measure the batch and the others must measure different batches then you can easily mask the ms variation with the part to part variation. Provide more detail on your parts and part selection process and others will jump in. There is considerable MSA experience on the Forum.
0February 17, 2009 at 10:13 pm #181353Darth,
Thanks, the problem is not the selection of parts, but that any one part will vary each time it is measured. That is, the measurement parameter of a single part is not constant, but also exhibits variation itself from measurement to measurement. The problem: how to sort this out from the gauge variation.0February 17, 2009 at 10:28 pm #181355It is interesting that you think you know the variation is coming
from the parts – you don’t.That the parts and measurements are “leading edge” is a nonsense
excuse.Your problem will be fixed with one or both of the following -1) Learn to present or fixture the part to give a consistent
presentation to the measurement.2) Take multiple readings and average them. This may be multiple
readings at different locations or it may be multiple presentations
for measurement.Let me know if you need further help. I could solve this problem in
two hours or less.0February 17, 2009 at 10:31 pm #181356
luke skywalkerParticipant@luke-skywalkerInclude @luke-skywalker in your post and this person will
be notified via email.This sounds pretty cool.
Since you mention that both the parts and the measuring are leading edge, is it possible to effectively split this into a 2-part study, meaning you could potentially use a previous generation of part that might be more stable or at least better known to pin down the measurement variation? From there, part 2 would be to use the now mor efamiliar measuring tool on the variable parts. At least that way you would have a means to check stability within the measuring. Seems this needs to be addressed before plunging into crossed/nested designs, etc.0February 17, 2009 at 10:46 pm #181357This guy’s problem is easy to fix – don’t make it hard.
0February 17, 2009 at 11:14 pm #181358It’s true, I don’t know how much variation is coming from the parts. I also don’t know how much is from the measurement system. That is the essence of the problem.
For sake of discussion, assume that both exhibit variation. I’m asking if there is a know systematic method to sort this out. Some others have suggested a bootstrap approach, but I don’t understand how that would apply. Perhaps some one of you have used it for this problem before.
If there is no know approach to this we’ll have to look at sources of variation in the parts and measurement one by one and eventually work it out. I was hoping there might be a statiscal approach to help sort it out.
I didn’t mean to use leading edge as an excuse, it’s just the world we live in. We often need to develop the product and measurment systems together.0February 17, 2009 at 11:16 pm #181359Stan,
Yeah, it is pretty cool. Thanks for giving it some thought. We have used a similar approach in the past to work through this, perhaps it’s the only way.0February 17, 2009 at 11:18 pm #181360Sorry, that last post was really meant for Luke, thanks again.
0February 17, 2009 at 11:36 pm #181361
luke skywalkerParticipant@luke-skywalkerInclude @luke-skywalker in your post and this person will
be notified via email.I’m sure there is an easier way to do it and you have stated such. It’s the warm sene of compassion for newbies that really chokes me up. Must be great for drumming up new business.
0February 17, 2009 at 11:56 pm #181362I told you how to deal with it – think about it.
0February 18, 2009 at 12:03 am #181363I don’t come on here to drum up business. That violates the forum’s rules (duh).
Do you prefer to accept the same old tired excuses or those that give mediocre advice?0February 18, 2009 at 12:49 am #181364That’s not true Stan – those are your rules, which you fervently apply to everybody except your buddies.
The Forum rules say don’t “promote” a product or service. They are fine with responses that are applicable to a poster’s question and may lead to the parties doing business together; ie, Adam Bowden, Mike Carnell, Eric Maas & others posting their company’s name, business email addresses and phone numbers. Forum has no problem with that…as evidenced by them not omitting them.
Let the Forum moderator do her job…and you do yours… of just criticising everybody for their stupidity.0February 18, 2009 at 12:51 am #181365Les honey,
Go do something worthwhile.
0February 18, 2009 at 1:00 am #181366BTW I gave the guy correct advice and the only thing I said to Mr. Star Wars is don’t complicate an easty problem.
0February 19, 2009 at 9:32 am #181431CI Guy,
you have a mix of 2 variation sources (parts that change value+ measurement variation).Like mentioned before this can not be seperated in 1 study.
Also options were mentioned:take 1 part; measure several times (repeat and/or reproduce) and look at average value found. Declare this the true value of the product. Do this for 10 parts. Now you can use these true values to perform MSA.
replace part-with-varying-value by part-with-stable-value (PWSV) just like when destructive testing. PWSV needs to be measured in ‘exactly’ the same as the original part and needs to cover the same area of values.
But: what is really your question?From your first post it looks like “is my gage r&R ok?” (reference: [quantify their measurement system variation]) Then you don’t need to know how the variation is split up as long as the result of the gage r&R is low enough.
If you perform a gage r&R study and ignore the part-varying this will be calculated by the software as extra repeatability (if the operator has no influence in how the part changes its value) because it assumes that the parts have constant value. The repeatability result will be higher than the repeatability in reality is (S-sq calculated repeatability = S-sq ‘real’ repeatability + S-sq part varying). But if the calculated value is low enough than the ‘real’ value is certainly low enough.
Hope this helps.0February 19, 2009 at 11:25 am #181433Remi,With all due respect, your method buys him nothing. Declaring the
real value by an average does not make it the real value when you
just go and do single readings in an R&R. The original variation is
still there and you still are not sure where it is from.This is a problem that is dealt with daily in measuring electronics –
neither the measurement nor the measured device is “leading
edge”. Go use an oscilloscope to measure and vary the time period.
You will see that you go from something that is nothing but
variation with a short time period to something that is a rock solid
signal with a long time period. All that is going on there is
averaging. This guy hasn’t got a clue where his variation is coming from. It is
not a problem of running a measurement study, it is a problem of
how he will measure. The averaging of multiple readings will allow
him to reduce the overall variation so that he can distinguish
differences between parts. It is the answer to the measurement
problem in the short term.If he wants to validate the claim that the parts are varying, he will
need a better measurement device. The problem is more likely
variation across the parts which can be validated by presenting the
part to the measurement device exactly the same way repeatedly
and assuring the test is run the same way repeatedly.0February 19, 2009 at 11:33 am #181434CI Guy,
I researched a little on PMD and I think I have a grasp on the measurement technique. Can you see if my analogy makes sense?
First, is it true that PMD is an indicator of how many impurities there are in an object? Here is my analogy for your measurement challenge. If I am way off-base, just advise me to not give up my daytime job!
I have 10 parts that are simply enclosed chutes that are 5 feet long by 1 foot wide and are fully enclosed. Their meaing in life is to deliver pingpong balls down a 45 degree slope. Laws of physics say that the balls should arrive at X seconds after departure. It is critical that the chutes deliver the balls in X +/- 3 seconds. The problem is that the chutes have random obstacles in them, and the arrival time of the ping pong ball can be changed. You also have this measurement gage called a stopwatch which is a new invention and you are not sure if gives reliable readings. You see all sorts of variation and you are not sure if the times vary because of the obtacles in the chutes or if this new thing called a stopwatch is reliable. (boy am I stretching it!) You have no other way of understanding the impurity level of the chutes other than with this technique.
Measurement gage is stopwatch (one ball is used throughout the study)
Parts are chutes with unknown levels of impurites
Does this make any sense or should I brew another pot of coffee?
HACL0February 19, 2009 at 11:46 am #181435Hacl,If the coffee you have does this for you, I’d like some of what you are
having.0February 19, 2009 at 3:15 pm #181442Hai Stan,
I agree with you that my ‘solution’ does not address the issue of ‘seperating the product-changing from the measurement variation’.
But I didn’t (at first) conclude from his post that this was what he wanted. If he only needs to ‘proof’ that he has a good MSA than maybe my answers have helped him enough.
Now I have read the whole string of posts (I skipped most of them the first time) and then I have to agree with you.
Remi0February 19, 2009 at 4:06 pm #181448
MrMHeadParticipant@MrMHeadInclude @MrMHead in your post and this person will
be notified via email.HACL, It sounds like you are putting together a classroom exercise!
So to Stan’s reference – for any one of the ten chutes, to measure repeatability, the one operator must be sure to place the ball in exactly the same spot across the 1-foot wide chute each time a measurement is made. And to evaluate reproduceability, that same spot must be used from operator to operator as they measure the chute-time. SOPs on HOW to measure.
Going back to the original question – if the measured value of an individual part changes from measurement to measurement, is the actual property of the part known to be changing with time? Is it unstable? (measuring a block of ice on a 90dF day, 15min apart) Or is it just that you are placing the balls at different points on the chute – so to speak?0February 19, 2009 at 4:11 pm #181449Greetings,
Out of curiousity, what industry do you serve? There are very specific ways to set up measurement system analysis. One item being key is your measurement plan and equipment. Are you measuring the part correctly? and on what type of equipment? What is the part tolerance should drive the equipment you use. Tighter tolerance calls for higher resuloution equipment. Smart scope, Nikon, CT Scan, ect. Once you have a demonstrated method for measurement – train the people who are taking the measurement for your GR&R. Regardless of part variation if the GR&R is unacceptable, use a different piece of equipment with higher resolution to measure with.
Once the above issue is resolved, let the data drive your decisions. All will be evident. By eliminating measurement method and operator error the only thing left is part to part variation. Then your arrows point to manufacturing capablity.0February 19, 2009 at 4:21 pm #181450What is the difference between Gage R&R and MSA? Does it assume annual calibrations?
0February 19, 2009 at 4:35 pm #181454I can drop some in your boat on the way to my Key West fishing trip in May! (Mike C told me you have a nice rig down there)
0February 19, 2009 at 4:46 pm #181456Hai Petros,
depends on the person you talk to.‘lazy’ person: they are the same
otherwise: Gage r&R is part of MSA: the study on repeatability and Reproducibility. Before that you should have checked: Validity; Resolution; Bias (also Linearityand Stability).
Remi0February 19, 2009 at 8:37 pm #181466Thanks for those of you who are offering some help. I admit that I may not have expressed the issue clearly.
The issue is that the measured value on any one part does vary with time i.e. the part is “noisy.” The measurement system is also being developed to measure the desired parameter and also represents an unkown source of variation.
The problem is how to sort out the measurement system repeatability from the part variation. At the end of the day, we need to understand variablility coming from both part and measurement, but it helps if we can separte the two early so we know which to focus.
I was hoping that someone had some similar experience and could recommmend a method to help separate them, but it may be that the iterative approach is the only answer (as Luke had suggested earlier).
0February 19, 2009 at 8:50 pm #181469Wrong.
I, amoung others on here, have been through this dozens of times.
I told you what the solution looks like. Think about it.0February 19, 2009 at 8:55 pm #181470Stan,
With all due respect, I have searched your responses for advice and found none except for “think about it” and “it’s easy.”0February 19, 2009 at 9:01 pm #181471
MrMHeadParticipant@MrMHeadInclude @MrMHead in your post and this person will
be notified via email.I had a hard time finding it too through all the banter (though not as bad as some threads):
https://www.isixsigma.com/forum/showmessage.asp?messageID=153437
Can you disclose to us what this “part” is? It’s rather intriguing.
An icicle? A black hole? Jar of wind?
Is the change over time linear, logrithmic, random?
I know – you fall into a catch 22 – how can you analyze the change if you can’t depend on your measurement to begin with.0February 19, 2009 at 9:10 pm #181472The example I gave earlier was Polarization Mode Dispersion. The parts are optical devices like switches and multiplexers.
We see this often however as we are developing new components and systems and the associated measurement systems.
It is a chicken and egg kind of thing. We ususally create theories about sources of variation, create new parts and/or measurement systems and, as eventually reduce variation to an acceptable level.
If it is possible to sort out the two early, then it allows us to focus in the right place. Often we look at parts and measuremetn systems as levels of categorical factors in an experiment and sort it that way.
0February 19, 2009 at 9:50 pm #181478CI Guy,
It is either in the way you are presenting the test item to the test and you need to be able to do it consistently or you need to take multiple measures and use the average.
“It’s easy” and you will not understand until you “think about it” instead of engaging in all these conversations about how hard it is.
If you don’t believe me, ask Mike Carnell.
If you want help from me, write [email protected].
If you keep on wanting to make this hard, I’ll keep telling you “it’s easy” because it is. I can solve this problem in 2 hours or less. You’ve wasted more time on here than that telling everyone how you are different and it’s hard for me – has anyone wever seen this?0February 19, 2009 at 10:16 pm #181481
Mike CarnellParticipant@Mike-CarnellInclude @Mike-Carnell in your post and this person will
be notified via email.CI Guy,
I stayed out of this String because Stan gave you the answer early on and it was clear the advice he gave.
We were plating chrome, nickle and gold on a glass substrate and it was measured in angstroms. Everyone claimed it was an impossible measurement because the measurement never repeated. Once the part was fixtured so that the measurement system saw the same place every time it became repeatable. We thought we were leading edge in those days as well.
Instead of rationalizing why it won’t work why don’t you try it and see. It is like the story about a group of people sitting around looking at an ox and pontificating about how many teeth it had. Then one of them went and looked and counted them.
Just my opinion.0February 19, 2009 at 10:36 pm #181482No Thanks, Stan. I won’t waste any more of your time.
0February 19, 2009 at 10:48 pm #181483What equipment did you use to measure in Angstroms?
0February 19, 2009 at 10:53 pm #181484
Mike CarnellParticipant@Mike-CarnellInclude @Mike-Carnell in your post and this person will
be notified via email.BJ,
I have been thinking about this for a while and I don’t even remember the thickness on any of the metals except the gold (which was the one we got beat up for if we went through gold targets to fast).
No idea what measurement device we used. I have a connection to the guy that ran the lab for us on Linkedin. I can check with him if you really want to know.
Regards0February 19, 2009 at 11:10 pm #181486The “Just my opinion” is muda. Whatever anybody writes is just their opinion – applies to all, unsaid.
0February 19, 2009 at 11:17 pm #181487
Mike CarnellParticipant@Mike-CarnellInclude @Mike-Carnell in your post and this person will
be notified via email.?,
And that would be just your opinion. What is your point?
It has certainly made a difference in the impact of your post by using the term muda instead of waste. I am always impressed when someone speaks to me in a language I don’t speak.0February 20, 2009 at 1:35 am #181488Doesn’t apply to me. I’ll going to start writing “that’s just my
experience” because that would be correct.You must be Les – no input, just critique.0February 20, 2009 at 1:40 am #181489Mike,Thanks for jumping in.Sorry for subjecting you to the dufus ?.I think CI Guy is invested in the fact he is different and this is an
incredibly hard problem. To bad, can’t learn when you are not
listening.0February 20, 2009 at 1:47 am #181490CI Guy,You only waste my time when you ask a question and then don’t
listen.Oh yeah, you’ve been wasting my time,Stop it.You want to learn how to address this problem? I’ll turn you on to a
PhD in Applied Physics if you don’t like Mike or my input. He is a
test professional and he’ll tell you the answer and tell you he
learned it from me 10 years into his career.Listen. Think, The problem is trivial.0February 20, 2009 at 9:53 am #181496I know – I just thought you wouldn’t know.
0February 20, 2009 at 11:02 am #181498CI guy,
Look at my very first post and see if I am making an accurate analogy to your measurement problem. Stan thinks I am drinking some kind of “special” coffee, but I checked and it’s plain-ole maxwell house! :-)
0February 20, 2009 at 12:17 pm #181500I thought your analogy was special and especially well thought out for
the hour of the morning. I need some of whatever allowed you to do
that. If therapy is the answer please don’t point it out in public.0February 20, 2009 at 12:21 pm #181501
SeverinoParticipant@Jsev607Include @Jsev607 in your post and this person will
be notified via email.I can’t tell if Stan is being sarcastic, but I thought your analogy was excellent and would love to see you carry it out to its logical conclusion irrespective of the OPs issue. It’s the sort of response that people tend to keep bookmarked for when we get this same question 10 days from now.
0February 20, 2009 at 12:21 pm #181503I was there too and I don’t remember either. Too many years and too many other companies and people that were
different with “leading edge” unsolvable problems.None of them were right by the way.0February 20, 2009 at 12:25 pm #181504I am not being sarcastic (I know it’s hard to tell sometimes).I always respect Hacl’s inputs and would like him to carry it through
assuming the student is ready to learn. Of course, someone who
labels themselves CI Guy probably thinks they are the teacher, not the
student.0February 20, 2009 at 12:42 pm #181505
Mike CarnellParticipant@Mike-CarnellInclude @Mike-Carnell in your post and this person will
be notified via email.Bj,We are all very proud of you. Thank you so much for your special contribution. The next time you have another self esteem issue please be sure to stop back by with another rehtorical question.
.0February 20, 2009 at 1:09 pm #181506You guys sure take offense easily!
0February 20, 2009 at 1:10 pm #181507I am not offended, just amused.
0February 20, 2009 at 2:33 pm #181511
Mike CarnellParticipant@Mike-CarnellInclude @Mike-Carnell in your post and this person will
be notified via email.Stan,
No worries. Dr. Deming documented the “we’re different” as an obstacle to improvement 40-50 years ago and it is alive and well today.
Regards0February 20, 2009 at 2:41 pm #181513
Mike CarnellParticipant@Mike-CarnellInclude @Mike-Carnell in your post and this person will
be notified via email.BJ,
I am not sure how you determined anyone was offended. Like Stan I am not offended just have no idea what point you thought you were making that would help the original poster understand that he had a possible solution and wasn’t willing to try it. If you want us to be impressed that you know the name of the measuring device – I don’t understand that thought process either.
So what is your point?
0February 20, 2009 at 3:28 pm #181517hacl,
Yes, I did read it and thanks for your thoughtfullness and genuine interest.
The analogy is good but perhaps more complex than my actual issue. I simply have sources of variation in both the part and the measurement system because both are in development concurrently. During the measurement the combination may be fairly stable. However when the measurement is repeated, either the part, the measurement system or both may vary.
We sort this out now using an iterative approach where the part configuration and/or the measurement configuration is changed and treat the new configurations as levels of categorical factors in a designed experiment. It works, but I thought someone on the forum may have another approach.
As a new user of the forum, I’m learning whose posts to skip and whose to listen to.
Thanks again for your genuine response.0February 20, 2009 at 4:21 pm #181518
TaylorParticipant@Chad-VaderInclude @Chad-Vader in your post and this person will
be notified via email.Stan I think the problem is your original answer was too simple. I wonder what the GR&R results are.
0February 20, 2009 at 4:38 pm #181519Chad,
GR&R assumes that any single part is repeatable and that the observed variation is due to the measurement system. The issue I’m looking at involves parts that also vary from measurement to measurement and sorting out that from variation due to the measurement system. It’s not impossible, we do it, but I’m always interested in a better way. If you can share any similar experience, I’d appreciate it.0February 20, 2009 at 5:03 pm #181520CI, let it go. As you can see through this 50 or whatever response chain you will not get answers here. You will get only “I’m so much better than you” comments that somehow make this little tribe feel better about themselves. They have their little pond with the big fish and the little fish who brown-nose them and it goes on and on. Trouble is the water in this pond is evaporating so they’re fighting for some form of “I’m still important”. Kind of a therapy group…”Hi my name is Stan (although not really) and I’m a has been who tries to act as if I still matter.”
0February 20, 2009 at 5:29 pm #181521
TaylorParticipant@Chad-VaderInclude @Chad-Vader in your post and this person will
be notified via email.CI Guy
Despite what Les (AKA Steve B, etc etc) says I will give my opinion and some advice that probably has already been stated here. First I want to ask this question. If you have Variability in the measurement system how do you know you have variability in the part. Given that setting up an MSA should require that each part be measured in the exact same location and same manner. Not knowing what you are measuring exactly it is very difficult for me to give you much more advice than that. Any measurement of a part not only measures the true part value, but also measures any variability that may exist because of the poor repeatability of the gauge and/or the poor reproducibility of the operators and their Methods of measuring.
Obviously you want to ascertain the true part value free of any other source of variability which goes back to how do you know the part has variation?
The only time I have ever had this issue is measuring plastic parts in an uncontrolled environment. So to compensate, the procedure for measurement was updated to include, Controlled environment Temp and humidity and without human interference (Fixture).0February 20, 2009 at 5:31 pm #181522I agree Les, my supplier assessment already told me what I need to know. It just confirms what someone told me about Florida.
0February 20, 2009 at 5:52 pm #181524we use step height profilometry with P-16 profilometer, depending upon the resolution needed. 3000 – 6000A’sLook at Zygo or similar.
0February 20, 2009 at 6:34 pm #181526This may be a bit too obvious and too simplistic an answer and if so, I apologize.
If you are testing new parts with a new measurement device, is it possible to test the device in a fixed, controlled environment with non-varying “dummy” parts first? Use a “proxy” for the real part that you want to measure but one that does not vary from observation to observation. Do a full gage R&R study in that environment and determine how reliable your measurement device and measurement procedure is. Once you are satisfied, then turn to your real parts. You should then be able to accuratley subtract the measurement system variation from the part variation.
Sorry if that is too simplistic and maybe there isn’t a suitable non-varying proxy that you could use.
Just my thoughts on the topic.
0February 20, 2009 at 6:51 pm #181528Two things Les -1) This guys question has been answered.2) Do you actually have a contribution or are you just here to critique?You seem to be the one with the problem.
0February 21, 2009 at 12:11 am #181542
SeverinoParticipant@Jsev607Include @Jsev607 in your post and this person will
be notified via email.Assuming you are not willing to take Stan’s advise which is sound, another poster has already suggested an alternative approach. You can utilize a “nested” approach. To read up on this, visit http://www.keithbower.com . He gives you advise on how to set it up and how to identify if the assumption of homgeniety (sp?) is violated.
Having said that, it is a more complicated approach and the simple solutions Stan has suggested will be more effective.0February 21, 2009 at 7:57 am #181544
Raja SekarParticipant@Raja-SekarInclude @Raja-Sekar in your post and this person will
be notified via email.Hi CI Guy
I had an exactly same problem when R&R study was conducted on my Dynamic Damping tester that measures the damping force values of a hydraulic shock absorber. The shock absorber, due to its inherent characteristic arising from the damping factor, kinematic friction etc, displays significantly a different damping value each time it is measured in consecutive cycles, though the readings fall within acceptable limits. This study yielded an % R&R of more than 56%. Hence my customer refused to accept the results from this Dynamic Damping Tester which was quite new, boasting of calibration standards to world class.
Well, with great difficulty I could locate a method that is explained in the file http://www.aiag.org/StaticContent/files/wiv.pdf. This method recognizes the ‘within-part-variation’ by measuring the range and not discrete values of the characteristic of the sample. I repeated the test as advised by this method and with the measurements I obtained now, the % R&R has drastically fallen to less than 10%!
Do confirm whether this method solves your problem.
0February 21, 2009 at 12:34 pm #181546Raja,
Good reference article, but I don’t think this issue is “within-piece” variation. I’d be surprised if CI guy could sub-divide the unit under test and take this approach…but only he can answer that.
CI Guy,
I had a similar issue with trying to characterize a torque analyzer. The “parts” in the study were torque wrenches. We had a hard time discerning whether the wrench was delivering a consistent amount of torque or whether the operator’s technique varied, or whether the gage varied. We agreed on a technique of 3 repeat measures by the operator, and used the average (just as Stan has suggested here). This is how we monitor the wrenches in production. (Qualify the tool with average of 3 readings…this is how you must use it!)
Keep in mind that averaging can be a problem if your data is non-random. I have seen this with SEM equipment for measuring critical dimensions on wafers. The data is highly auto-correlated due to the build up of surface charge from measurement to measurement. Before using this approach..make sure the measurements are not autocorrelated. (We could explain this observed variation, but I am still not sure how your part varies. I also know that if I run a GRR on my bathroom scale, my beer drinking will impact the weight measurements. I also step on the scale without any help, so I am the operator and the part! There’s that weird coffee again.)
If I were you, I would run a quick multi-vari study.
Days: 1 through 5
Operator (within-day): A, B, C
Part (Within operator, Day) 1,2,3,4,5
Repeat (1,2,3,4,5)
The error term in your nested ANOVA will represent the gage error and your suspected “noisy” part variation. I am not a salesman, but for this analysis I would use JMP. You will see if your data is autocorrelated, you can plot the data on a control chart and assess the stability of the measurement system, etc. Why is everyone so biased towards R&R? (Get it…that was an MSA joke!)
MSA = Linearity, Stability, Bias, Repeatability, Reproducibility0February 21, 2009 at 3:11 pm #181547Thanks to those who posted some genuine responses over the past few days. A lot of good food for thought for addressing specific part variation issues when performing an MSA.
0February 22, 2009 at 3:42 pm #181567CI Guy,Here’s hoping you learn who actually gives good advice some day.Come back and tell us what you learn when you are done.I could tell you about your parts and measurement in 2 hours or less.
Anyone who has taken appropriate training on MSA knows how to
deal with this.0 -
AuthorPosts
The forum ‘General’ is closed to new topics and replies.