Gage R&R with 3 people 10 parts 12 positions on each part

bobdoering

Stop X-bar/R Madness!!
Trusted Information Resource
#11
Re: 3 people 10 parts 12 positions on each part

Miner is correct. if you don't have each operator repeat each measurement (randomly without knowing what value they got the first time they measured that part and location) we cannot determine measurement error.
That can be an issue, especially with smaller number of samples. Usually people don't have to memorize data points, because they are presented with a form and write in the data themselves - so they can see the other data. If someone else is writing down the data, it might be very hard to remember 12 points. But, since they are measuring 12 independent points on 10 independent parts, they are really doing 120 independent data points. It would have been better to pick fewer parts and do the 12 points (if the geometry is so compellingly different - and it may be if it is an awkward shape) and repeat the measurement on those parts. Blending in the gage variation with the part to part variation really is over-complicating a simple process. I don't see it as a "shortcut" of any kind, myself.

Bottom line - an ndc of 1 (or 1.3 in miner's data) shows no matter how fine of a comb you use, this gaging isn't working.
 
Elsmar Forum Sponsor
B

biker6977

#12
Thank you for the help. You are correct, I do need to have each operator give me 2 more sets of measurements. Unfortunately the customer is requiring the 10 pieces so there's no getting out of that.
 

bobdoering

Stop X-bar/R Madness!!
Trusted Information Resource
#13
Thank you for the help. You are correct, I do need to have each operator give me 2 more sets of measurements. Unfortunately the customer is requiring the 10 pieces so there's no getting out of that.
OK - we will give them the 10 pieces. Did they require 12 positions?

Fact is, the measurement system is no better than its performance on the most difficult dimension it is being used for. So, doing 12 dimensions may be overkill. But, if curiosity is killing you or your customer, can you use a sample of 3 positions - the most difficult to measure, the easiest to measure and something in-between?

Quite frankly, to keep the focus sharp on the question - which is whether the gage is "good enough" for the measurement required, I would do 10 parts, 1 position (the most awkward), 3 operators, 3 trials. If more positions were to be used, I would analyze them separately (e.g. separate GR&R spreadsheets), and report the "worst" result. Physically separating the variation is a little more effective than statistically attempting to separate them - and easier to understand for most people.
 
B

biker6977

#14
They do require the 12 positions.
I may have a good argument that what they are actually requesting - to me- is a capability study combined with gage R&R.
I'm going to break down my data taking each individual point, using as a separate piece and getting the R&R that way. Then take the collective data and doing a cap study.
What do you think?
 

bobdoering

Stop X-bar/R Madness!!
Trusted Information Resource
#15
They do require the 12 positions.
I may have a good argument that what they are actually requesting - to me- is a capability study combined with gage R&R.
I'm going to break down my data taking each individual point, using as a separate piece and getting the R&R that way. Then take the collective data and doing a cap study.
What do you think?
I am tending to agree with you. I can see 1) a gage r&r on the most difficult dimension, (3 operators, 3 trials, 10 parts, 1 position) then 2) capability on each of the positions. That study should not require 3 operators or repetitions - in fact, that would just introduce more error into the capability evaluation, when what you are trying to zero in on there is the actual process variation.

Really, the idea of combining a capability study and a gage R&R is not a good idea. I am not sure what the customer's vision is, but the net result sounds even less useful than a Cpk calculation!
 

Bev D

Heretical Statistician
Staff member
Super Moderator
#16
Re: 3 people 10 parts 12 positions on each part

That can be an issue, especially with smaller number of samples. Usually people don't have to memorize data points, because they are presented with a form and write in the data themselves - so they can see the other data. If someone else is writing down the data, it might be very hard to remember 12 points. But, since they are measuring 12 independent points on 10 independent parts, they are really doing 120 independent data points. It would have been better to pick fewer parts and do the 12 points (if the geometry is so compellingly different - and it may be if it is an awkward shape) and repeat the measurement on those parts. Blending in the gage variation with the part to part variation really is over-complicating a simple process. I don't see it as a "shortcut" of any kind, myself.

Bottom line - an ndc of 1 (or 1.3 in miner's data) shows no matter how fine of a comb you use, this gaging isn't working.
two responses:
first I was responding in the general sense. The OP didn't perform the study correctly which in some specific cases may not matter but in general it does. and the OP does desrve to have feedback on how MSA's should be performed and not jsut feedback on his specific case. It is teh fundamental general knowledge that enables us all to learn and not jsut remember how to do things by rote...

at this time I can't agree with you that the gage is inadequate. (I do agree that using all 12 locations in the R&R study just messes up the study from a logistics standpoint and doesn't add value to understandign the measurement system...) I have attached a slide that shows the Youden plot of Rose vs Cindy and Rose vs Claude. The red dashed box is the specification range...the plots clearly show - in a very concise manner - that CINDY measures considerably lower than Rose and that Claude is slightly higher than Rose. (and by extension Cindy is much than Claude). looking at the scatter (in the direction perpindicular to the 45 degree perfection line, not the vertical Y axis scatter) the scatter for the Cindy:Rose plot is very large in comparison to the Claude:Rose plot. This is a strong indication that not only is Cindy measuring lower than the other two, but her repeatability is also worse than the other two.


Additionally if we look at the Claude:Rose plot we see relatively little scatter -other than the clear bias between the two - This scatter is fairly small in comparison to the specification box. I also note that the study variation does not span the entire specification range. (Are the parts representative of current process range?)

I believe that this gage may very well be perfectly acceptable for both SPC and acceptance sampling if the bias is fixed and if the OP will determine repeatability and then correct any issues - most likely the majority is due to Cindy's 'technique'.
 

Attachments

D

Dave Dunn

#17
Is the dimension and measurement system the same for all 12 locations? If so, there should be no need to do a separate GR&R for each or combine data from all the locations. Pick one of the locations and do a standard GR&R study (10x3x3 or how ever many you need.) The GR&R represents the measurement system for that feature - it does not need to be tied to a speficic location of that feature if all of the locations are supposed to be identical.
 

bobdoering

Stop X-bar/R Madness!!
Trusted Information Resource
#18
The GR&R represents the measurement system for that feature - it does not need to be tied to a specific location of that feature if all of the locations are supposed to be identical.
On the other hand if there is any impact of the location on the measurement - e.g. a hand held measurement with a cantilevered load that varies because the part is large or awkward, etc. - it is reasonable to do more than location. We can't tell for sure, and can't assume the location is not a factor - but the OP should be able to tell. Remember GR&R is the measurement system - part, product, operator and environment - not just gage and "dimension". That "identical" statement can be dangerous.
 
Thread starter Similar threads Forum Replies Date
S Gage R&R on Potentially Changing Parts - Guidance Needed Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 4
D 5 vs. 10 Parts for Gage R&R Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 2
J Minimum number of parts to do an attribute gage R&R Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 8
A Minimum Number of Parts for Attribute (Go / NoGo) Data Gage R&R Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 4
L Correct Sample Size for Attribute Gage R&R (Good / Bad parts) Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 12
H Gage R&R Data Collection Form w/ Appraisers Names, Number of Parts, Number of Trials Document Control Systems, Procedures, Forms and Templates 2
Z How many parts to measure in a Gage R&R study Quality Tools, Improvement and Analysis 5
H Gage R&R - No Repeats - Parts measured by my company and an outside supplier Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 3
M Gage R&R for Big Parts - Approving a Variable Gage using only 1 Part Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 7
C Interpreting Gage R&R Results - 3 operators, 3 iterations and 10 parts Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 6
N Correlation of Gage R&R Value with the Measured Value of Parts Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 6
K Alternatives to GR&R (Gage R&R) - Only 4 sample parts and one operator Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 22
C Gage R&R Study - Better to use parts or gage blocks? Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 6
G Gage R&R Procedures: Selecting parts (sample) to measure Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 2
I Measurement Systems Analysis (Gage R&R) - # of Parts Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 5
Z How to handle MSA's (Gage R&R) for different parts? Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 4
R Destructive Attribute Gage Studies - inserted/pressed in parts Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 6
M Gage R&R form for 2 operators 10 parts and 3 trials needed Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 1
K Difference a gage can detect - Similar Parts Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 16
G Gage R&R: Selecting Number of Trials and Appraisers and Parts Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 11
L Creation of Sample Parts to perform Gage R&R - Go/NoGo to Check Threading Operation Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 10
J What kappa value to use for Gage R+R (Gage R&R) study with > 10 parts? Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 1
S Calibration required? We buy part of our machined parts - Supplier gage calibration? General Measurement Device and Calibration Topics 6
A GR&R - Gage R&R for 1 test Stand, 10 locations, 10 parts Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 1
Q Gage R&R lite? This form only uses two operators measuring five parts one time Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 10
T Parts used for Gage R&R's Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 5
Z Gage R&R for sorting gage - Leaktester to inspect for leakrates on parts Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 9
B Stability study- Plastic injection molded parts with fixture gage & digital indicator Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 2
D Gage R&R Study - Marking Parts, Number of Parts and Number of Operators Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 7
T Plug Gage Calibration Calibration and Metrology Software and Hardware 1
L Gage R&R TMV Acceptance Criteria Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 4
S MSA for attribute relation gage Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 2
E Zero part to part variation - Gage R&R project Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 15
M Gage R&R and right way to measure Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 16
L Gage RandR on automated equipment. IATF 16949 - Automotive Quality Systems Standard 7
B Gage calibration frequency, ISO and IATF - What are the requirements Calibration Frequency (Interval) 3
D Difference between Test Method Validation and Gage R&R Qualification and Validation (including 21 CFR Part 11) 18
R Determining Uncertainty from Gage R&R Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 1
C Correct Calibration Method for Dial Depth Gage General Measurement Device and Calibration Topics 6
C Gage Block Wringing General Measurement Device and Calibration Topics 3
B Gage R&R with NDC=1 Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 19
S Type 1 Gage R&R or something else? Reliability Analysis - Predictions, Testing and Standards 6
G Should I perform Gage R&R only at the beginning of a new project? Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 6
V Thread Plug Gage Pitch GO Diameter out of spec AQL - Acceptable Quality Level 8
G Gage R&R - Where am I going wrong? Part of a FAIR submission (Aerospace) Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 2
R Gage R&R Excel templates Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 3
K Gage R&R with more than 3 appraisers Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 2
Anerol C Gage R&R Template AIAG 4th Edition IATF 16949 - Automotive Quality Systems Standard 3
T Attributes SPC study - Attributive control (Go gage) Statistical Analysis Tools, Techniques and SPC 5
S Capability or Gage R&R Study for Leak Tester? Reliability Analysis - Predictions, Testing and Standards 15

Similar threads

Top Bottom