SBS - The best value in QMS software

Analyzing Attribute Data - Mechanical Pull Testing of Joint

C

Conquer

#1
Fellow Elsmar members, I need some input.

At my company we were trying to validate a process for joining two plastics together. In the process, we will using mechanical pull testing of the joint to ensure it meets the 20 N minimum.

After the validation was completed, I reviewed the data and presented by the team and determined that the data was not normally distributed. The root cause of this was that the test method didn't always result in a failure of the joint, but rather a failure of the joint used to prepare the sample for testing.

So, now I am left with a bunch of data that I can only treat as attribute data and am trying to determine at what confidence I know that my pull strength will meet the 20N minimum. What statistical tools for attribute data can I use to provide me with confidence that I will meet the 20 N minimum.

Any help you could provide would be greatly appreciated.
 
Elsmar Forum Sponsor

Bev D

Heretical Statistician
Staff member
Super Moderator
#2
If you post your data we can provide better help. you do not necessarrily have to treat your data as categorical.
 

Statistical Steven

Statistician
Staff member
Super Moderator
#3
Fellow Elsmar members, I need some input.

At my company we were trying to validate a process for joining two plastics together. In the process, we will using mechanical pull testing of the joint to ensure it meets the 20 N minimum.

After the validation was completed, I reviewed the data and presented by the team and determined that the data was not normally distributed. The root cause of this was that the test method didn't always result in a failure of the joint, but rather a failure of the joint used to prepare the sample for testing.

So, now I am left with a bunch of data that I can only treat as attribute data and am trying to determine at what confidence I know that my pull strength will meet the 20N minimum. What statistical tools for attribute data can I use to provide me with confidence that I will meet the 20 N minimum.

Any help you could provide would be greatly appreciated.
You can use the binomial confidence interval to determine the limit on the percent outside the 20N limit.
 

bobdoering

Stop X-bar/R Madness!!
Trusted Information Resource
#4
At my company we were trying to validate a process for joining two plastics together. In the process, we will using mechanical pull testing of the joint to ensure it meets the 20 N minimum.

After the validation was completed, I reviewed the data and presented by the team and determined that the data was not normally distributed. The root cause of this was that the test method didn't always result in a failure of the joint, but rather a failure of the joint used to prepare the sample for testing.

So, now I am left with a bunch of data that I can only treat as attribute data and am trying to determine at what confidence I know that my pull strength will meet the 20N minimum. What statistical tools for attribute data can I use to provide me with confidence that I will meet the 20 N minimum.
I have this very same issue with weld pull tests, and it does render the data questionable. Typically, the idea is to understand the strength of the weld, not the material - so when the material breaks first the weld is good, but the data does not represent the weld strength. It must by its nature under-represent the weld strength. One would want to throw out that data point because the break did not represent the weld, but you do not know the actual weld strength. That is important, because you may be throwing out high data that would have beneficially affected your capability.

If the question is will the joint system meet 20 N, (so breakage at any point), then you can develop your statistics from the data you have using non-normal distribution statistical analysis for the appropriate distribution model.

The bottom line is you surely can not tell the capability of the joint strength itself accurately with this kind of data - although people will attempt to in order to appease myopic customers.

Ultimate Tensile Strength is usually the worst for repeatability. Often people will use yield to get a more consistent data point for tensile data, but that may still be confounded with the base material yield force in your case distorting the conclusion. I would not likely help your case.

I agree with Bev D - it would be nice to see the data. Also, do you ever get the tensile curves? They would also be nice to see.
 
C

Conquer

#5
Thank you Bev, Steven and Bob for your reply. I have attached my data to this post to provide some insight.

How the data was run was in 3 seperte lots at nominal processing conditions. As you can see from the histograms for the lots, the data is skewed because some break at the actual material joint while others break at the joint created to be able to conduct the test

In reply to Steven, I checked into the binomial confidence interval and all looks good accept that I have a p value of 1. In fact, I will always have a p-value of 1 because if anything fails my product fails.

Also, in the last tab on the sheet I have tried to use an equation for calcuating the sample size needed based on a zero-acceptance sampling plan. I used the equation to work backwards and determine based on a total sample size of 90 peices and a confidence interval how many pieces I could expect to be non-conforming. Not sure if any of you have a comment on this concept.
 

Attachments

Statistical Steven

Statistician
Staff member
Super Moderator
#6
Also, in the last tab on the sheet I have tried to use an equation for calcuating the sample size needed based on a zero-acceptance sampling plan. I used the equation to work backwards and determine based on a total sample size of 90 peices and a confidence interval how many pieces I could expect to be non-conforming. Not sure if any of you have a comment on this concept.
Here is the analysis of your data using the upper confidence interval on the binomial. It uses the SAME approach as your last sheet (though instead of solving for n, I solve for p in the binomial for a given sample size.

N Confidence Reliability PPM Upper Limit
150 90% 98% 19835 2.0%
95% 98% 24319 2.4%
99% 96% 35223 3.5%

30 90% 91% 94803 9.5%
95% 89% 114726 11.5%
99% 84% 160327 16.0%
 

bobdoering

Stop X-bar/R Madness!!
Trusted Information Resource
#7
As a quick test I put all of the data together into Distribution Analyzer and attached the results. Remember, this data does NOT represent the joint strength, just the joint system strength (including failures other than the joint itself)
 

Attachments

Jim Wynne

Staff member
Admin
#8
I have this very same issue with weld pull tests, and it does render the data questionable. Typically, the idea is to understand the strength of the weld, not the material - so when the material breaks first the weld is good, but the data does not represent the weld strength. It must by its nature under-represent the weld strength. One would want to throw out that data point because the break did not represent the weld, but you do not know the actual weld strength. That is important, because you may be throwing out high data that would have beneficially affected your capability.

If the question is will the joint system meet 20 N, (so breakage at any point), then you can develop your statistics from the data you have using non-normal distribution statistical analysis for the appropriate distribution model.
This is a good reason that cohesion failure (the material coming apart before the weld does) should be accounted for. In many instances of pull testing it's expected that the adhesive bond will be stronger than the cohesive properties of the materials joined material(s). If a bond is expected to withstand a pull force of x units, and there's cohesive failure before that limit is reached, the bond is considered adequate. This results in attributes data, which should be considered an acceptable way of validating the process.
 
A

adamsjm

#9
After the validation was completed, I reviewed the data and presented by the team and determined that the data was not normally distributed. The root cause of this was that the test method didn't always result in a failure of the joint, but rather a failure of the joint used to prepare the sample for testing.
A normal distribution is dealing with average of averages in the data. Testing to failure is dealing with the minimum of minimums. The data related to joint failure is most likely a weibull distribution. Ditto for the sample test joint. The two distributions are probably close to each other or are crossing at a failure load level. If so, you will need to strengthen the sample preparation joint as not to waste the test effort.
 

bobdoering

Stop X-bar/R Madness!!
Trusted Information Resource
#10
This is a good reason that cohesion failure (the material coming apart before the weld does) should be accounted for. In many instances of pull testing it's expected that the adhesive bond will be stronger than the cohesive properties of the materials joined material(s). If a bond is expected to withstand a pull force of x units, and there's cohesive failure before that limit is reached, the bond is considered adequate. This results in attributes data, which should be considered an acceptable way of validating the process.
Yes, it is considered adequate, but will not participate in statistically determining the prediction of the actual weld data, because the weld strength itself is unknown, yet stronger - so the reported data understates the weld strength. That, in turn, dilutes the prediction of the performance weld strength over time based on the data.

If "passing" is all that counts, the attribute data is adequate (just not very descriptive or as effective in prediction.) For some, it may be "good enough" - not sure in this case, so we looked a little deeper.
 
Thread starter Similar threads Forum Replies Date
qualprod Complying with ISO 9001:2015 - 9.1.1 b - Monitoring, measuring, analyzing and evaluation ISO 9000, ISO 9001, and ISO 9004 Quality Management Systems Standards 2
Q Analyzing Process Bottlenecks Tools ISO 9000, ISO 9001, and ISO 9004 Quality Management Systems Standards 16
S ANOVA/Regression - Analyzing a Dataset which contains over 4500 Points Using Minitab Software 3
T Analyzing internal data for corrective action Internal Auditing 4
G Characterization Studies: Analyzing Data to Establish Conclusions Statistical Analysis Tools, Techniques and SPC 1
W Best quadratic subset for analyzing a Response Surface Design with Minitab 15 Using Minitab Software 6
C Analyzing 3 Factors 3 Levels using Minitab Using Minitab Software 9
P Help Setting Up and Analyzing 3 Factor 2 Level Full Factorial Design for DOE Using Minitab Software 3
N Different Distribution Parameters when analyzing the same data in different ways Using Minitab Software 8
M Type 1 Gage R&R - Analyzing Run Chart and I-mR Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 12
M I came across this site with several analyzing tools (Excel) Statistical Analysis Tools, Techniques and SPC 4
R Analyzing Customer Satisfaction Indexes Quality Manager and Management Related Issues 1
S Chi-Square Conundrum - Analyzing tree death across 3 areas Inspection, Prints (Drawings), Testing, Sampling and Related Topics 13
C Analyzing Full Factorial Design in Minitab Using Minitab Software 5
M Transforming your Data - Analyzing a DOE Six Sigma 5
M FMEA Interface Matrix - Analyzing risks of electronic health records system FMEA and Control Plans 4
A Analyzing Corrective/Preventive Actions and How to Track Due Dates Preventive Action and Continuous Improvement 16
N ANOVA Help Analyzing Extrusion Data Statistical Analysis Tools, Techniques and SPC 7
D Analyzing fishbone diagram Quality Tools, Improvement and Analysis 4
A Net Promoter Score (NPS) for Analyzing the Client Satisfaction Misc. Quality Assurance and Business Systems Related Topics 3
K Process monitoring, measuring and analyzing, does this means all company processes? ISO 9000, ISO 9001, and ISO 9004 Quality Management Systems Standards 3
MarilynJ6354 Satmetrix Net Promoter - Has anyone used this for analyzing customer survey data? Service Industry Specific Topics 4
C Analyzing Data with a Non-Normal distribution Statistical Analysis Tools, Techniques and SPC 41
D Tools for analyzing 3 factors at the same time Quality Tools, Improvement and Analysis 12
I Overwhelmed with attribute MSA requirement for visual inspection IATF 16949 - Automotive Quality Systems Standard 6
H Need MSA 4th ed. compliant attribute MSA template General Measurement Device and Calibration Topics 4
A Attribute Analysis for colour matching scale Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 5
K Transform variable data into attribute data Reliability Analysis - Predictions, Testing and Standards 24
K IATF & Attribute Study requirements IATF 16949 - Automotive Quality Systems Standard 9
T Correct MSA study for an automated camera system which makes attribute inspection Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 1
O Examples of Critical process parameter (CPP) and Critical quality attribute (CQA) Manufacturing and Related Processes 2
C Applying Weibayes to Attribute sampling Reliability Analysis - Predictions, Testing and Standards 0
M Template for Attribute Gage R & R wanted Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 3
B Easy Software Needed for Recording Mainly Attribute Data Quality Assurance and Compliance Software Tools and Solutions 2
A Does an attribute study (Go/NoGo pin gage) need two studies (1 for each pin) Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 1
B Attribute Gage R&R study according to "Charbonneau" Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 2
R Can a Attribute Study be considered a Visual Inspection? Reliability Analysis - Predictions, Testing and Standards 6
J MSA on Part Specific Attribute Fixtures Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 2
B IATF 16949 Cl. 8.6.6 - Acceptance Criteria - Zero Defects Attribute Data Sampling IATF 16949 - Automotive Quality Systems Standard 2
L Gage Blocks: Attribute or Variable Gage? General Measurement Device and Calibration Topics 3
T Attribute vs Variable Inspection Data ISO 13485 Requirement ISO 9000, ISO 9001, and ISO 9004 Quality Management Systems Standards 2
D Calibration of a Width Gage Slot with an Attribute Gage - Maximum Width Condition General Measurement Device and Calibration Topics 16
R Visual Attribute Inspector Capability and KAPPA Inspection, Prints (Drawings), Testing, Sampling and Related Topics 3
D attribute gage RR in a unique way Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 4
M Proper Gauging - GD&T - Attribute gage to check true positioning on the shop floor Inspection, Prints (Drawings), Testing, Sampling and Related Topics 6
P RQL/AQL from Attribute Data Six Sigma 1
M Population failure rate based on attribute data Statistical Analysis Tools, Techniques and SPC 4
V Minitab - Attribute Gage Study Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 2
S Attribute G&R for all Visual Controls in Control Plan Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 1
J Attribute Test Method Validation 21 CFR Part 820 - US FDA Quality System Regulations (QSR) 1

Similar threads

Top Bottom