Which Sampling Plan(s) Should I Use?

Sherleen

Registered
Need help.
How to do the right sampling plan for the purchased material on inspection?

Example 1:
The purchased material is nose clip, the purchased order will describe the thickness and the size of the nose clip.
What standard should we use? ANSI Z1.4 or Z1.9?

Example 2:
The purchased material is melt-blown, the purchased order will describe the weight, width, filtering efficiency, breathing resistance of the fabric.
What standard should we use? ANSI Z1.4 or Z1.9?

Thank you.
 

chris1price

Trusted Information Resource
Which standard to use depends on how you intend to perform the sampling. To quote from ASQ:

ANSI/ASQ Z1.4-2003 (R2018): Sampling Procedures and Tables for Inspection by Attributes is an acceptance sampling system to be used with switching rules on a continuing stream of lots for Acceptance Quality Limit (AQL) specified. It provides tightened, normal, and reduced plans to be applied for attributes inspection for percent nonconforming or nonconformities per 100 units.

ANSI/ASQ Z1.9-2003 (R2018): Sampling Procedures and Tables for Inspection by Variables for Percent Nonconforming is an acceptance sampling system to be used on a continuing stream of lots for Acceptance Quality Limit (AQL) specified. It provides tightened, normal, and reduced plans to be used on measurements which are normally distributed. Variation may be measured by sample standard deviation, sample range, or known standard deviation. It is applicable only when the normality of the measurements is assured
 

William55401

Quite Involved in Discussions
Welcome to the Cove!

When done very well, your incoming sampling levels need to be connected to your finished device risk management process. Your purchased item (raw material, components or devices) specifications need to identify critical characteristics (safety, performance, process) that would trigger incoming (in harmony with supplier performed) assurance activities. Mature orgs have levels of importance (connected back to Product Risk) of these features that map to specific incoming sampling plans. The actual sampling plan could be pulled from one of those listed above or simply confidence / reliability based.

One more. In the absence of having features identified on the Design Outputs, many orgs create a Critical Feature Identification process to review the specifications and identify the features as an input to incoming inspection plan creation.

HTH. Have fun. Enjoy the ride.
 

Sherleen

Registered
Thank you for the explanations.
I decide to use the Inspections by Attributes.

On the single sampling plan for normal inspection (ANSI/ASQ Standard Z1.4-2003(R2018)) table, is there any standard to decide the general inspection levels or special inspection levels?

Thank you :)
 

Mike S.

Happy to be Alive
Trusted Information Resource
In my old copy of Z1.4-1993, section 9.2 Inspection Level addresses your question.

You might also consider a C=0 alternative sampling standard, Zero Acceptance Number Sampling Plans, Fifth Edition, by N.L. Squeglia, ASQ Quality Press.
 

Sam Lazzara

Trusted Information Resource
I have found that few practitioners understand or use the reduced/normal/tightened switching rules in Z1.4 (analogous to switching rules in ISO 2859-1). And in some cases, they do not seem to understand what it means when you hit a downward arrow in the tables. Unbelievable, right?

So this is why I recommend the C=0 Plan mentioned above. One table, no switching, no arrows.
 

Sam Lazzara

Trusted Information Resource
Regarding the ASQ C=0 Plan, confusion was caused a few years ago when ASQ published a "corrected" version of the 5th edition, rather than calling it the 6th edition. I have provided some information below.

ASQ C=0 5th Edition “corrected”
The first printings of the 5th Edition had a single Table 1. This Table 1 differed slightly from Table 1 in the 4th Edition.
Starting with the third printing of the 5th Edition, the author identified some issues (described in corrected 5th Edition on page xii) and with that version Table 1a and Table 1b appeared.
Table 1b in the later printing is the same as Table 1 in the first printings.
Table 1a is the same as Table 1 in the 4th Edition, and it requires less stringent sampling than Table 1b.
So you will need to decide whether to use Table 1a or 1b. That is a lot easier than implementing the switching rules in Z1.4.

Not sure if any other "corrections" have been made to the 5th edition, but here is a link to what ASQ offers at this time:
Zero Acceptance Number Sampling Plans, Fifth Edition (e-book) | ASQ
 

Sam Lazzara

Trusted Information Resource
As a follow on to the information I provided regarding the ASQ C=0 Plan, that attached posting from LinkedIn may shed some more light.
Difficult to read but hopefully you can make it out.
ASQ C0 Plan Anomaly.png
 

lizVR

Starting to get Involved
Welcome to the Cove!

When done very well, your incoming sampling levels need to be connected to your finished device risk management process. Your purchased item (raw material, components or devices) specifications need to identify critical characteristics (safety, performance, process) that would trigger incoming (in harmony with supplier performed) assurance activities. Mature orgs have levels of importance (connected back to Product Risk) of these features that map to specific incoming sampling plans. The actual sampling plan could be pulled from one of those listed above or simply confidence / reliability based.

One more. In the absence of having features identified on the Design Outputs, many orgs create a Critical Feature Identification process to review the specifications and identify the features as an input to incoming inspection plan creation.

HTH. Have fun. Enjoy the ride.

I am wondering and hoping that some folks might share a procedure or outline some ideas of how to best implement a a Critical Feature Identification process. I am currently working on this such thing as a Corrective Action and am struggling to get off the ground with how to implement it effectively.
 

lizVR

Starting to get Involved
I am wondering and hoping that some folks might share a procedure or outline some ideas of how to best implement a a Critical Feature Identification process. I am currently working on this such thing as a Corrective Action and am struggling to get off the ground with how to implement it effectively.

Hoping to get some guidance on this, so I'm bumping my inquiry. Still in process on implementing this in our system. The issue is that early design efforts did not identify critical characteristics or the associated risks consistently or clearly, so I am essentially reverse engineering our device to determine risk for each feature and why some features need to be inspected or inspected more. The big issue is putting a system in place for appropriate review and requirements and maintenance of sampling and inspection procedures for appropriateness. We also want to incorporate supplier performance monitoring to ensure that quality issues may impart additional scrutiny on a given feature, if necessary.
 
Top Bottom