Dan points out some of the statistical tools used for process validation. However, he has omitted the first step, which is to use tools such as Taguchi or Pladkett-Burman arrays to identify those inputs to the process that have significant effects on the output. Once you have identified those, you can use the two-level (0r even three-level) fractional factorial designs to establish the control lints for the process. You could further refine the process using EVOP or Response Surface Designs to determine the "sweet spot" in the process that produces the best results. Toyota used similar tools in 1982 to refine the cigarette lighter production process to a Cpk of 8.0, and amazing level to eliminate problems with processes including the use of the "red light" stopping of the process to fix problems. They could continue production while troubleshooting the process because output was so good.
Another tool that is used with Process Validation is Hazard Analysis and Critical Control Points (HACCP) to provide connection to operating the process after validation.
I recommend the use of the NIST Statistical Handbook covering industrial statistics referred to in one of my other posts on this topic.
NIST Statistical Handbook . It has a number of discussions useful for process validation.
------------------------------
Edwin Bills MEd, CQA, RAC, BSc, CQE, ASQ
Principal Consultant
Overland Park KS
United States
elb@edwinbillsconsultant.com------------------------------
Original Message:
Sent: 18-Feb-2019 13:22
From: Tim White
Subject: Manufacturing Process Validation
Hi Dan,
"...two cases where this is a problem - verification step uses a sampling plan."
A statistically-based sampling plan is not considered verification by the FDA? I only see "output cannot be/is not verified...", or similar in the standards and guidance. The ISO 13485 guidance itself lists "sampling plans" as an example method to validate a process. I would consider a sampling plan verification, but I have no experience with the FDA on this.
------------------------------
Tim White
Leadership, QA
Lewis Center OH
Original Message:
Sent: 16-Feb-2019 07:43
From: Dan O'Leary
Subject: Manufacturing Process Validation
In device manufacturing the basic requirement is that your production processes produce only conforming material. If the process were to produce a non-conforming product, the subsequent verification step would detect it and send it to the non-conforming product control process.
However, there are (at least) two cases where this is a problem – the verification step is destructive or the verification step uses a sampling plan.
In those cases, you need a different method, process validation. In this method you understand the process input that affect the process output you need to control. Then, set limits on each process input and monitor them during the production. If the process inputs stay inside the limits, the process output will be only conforming product.
Setting up the initial process validation requires statistical analysis, typically design of experiments methodology. I'm partial to two-level fractional factorial designs. Because there are many input parameters, the input is multi-dimensional. The fractional factorial results identify the worst case corners of the hypercube. After determining them, typically conduct three runs as confirmation. Usually, the worst case conditions are when all the parameters are set high together and when all the parameters are set low together. The third run is the nominal point. The question is the number of replicates in each run. You need to be careful here, because many people use some attribute formula when the parameter is a variable. As a result, you don't get good Cpk information and you run too many items.
In the end you want a production process with a Cpk of 1.33 or better. This provides the high degree of assurance from 820.75(a).
------------------------------
Dan O'Leary
Swanzey NH
United States
Original Message:
Sent: 15-Feb-2019 08:58
From: Anonymous Member
Subject: Manufacturing Process Validation
This message was posted by a user wishing to remain anonymous
Hi everyone,
I have a few questions regarding manufacturing validation. I am still a bit fuzzy on process validation. I need some help understanding what needs to be validated. In my last workplace, the head of regulatory and quality required validation on the whole manufacturing operation. It was repeating the manufacturing operation 5 times for 5 units we decided to validate. Does this mean none of the steps can be verified so there had to be validation, therefore repeat every step in the DMR 5 times? If anyone has suggestions to offer, I would appreciate it. Is there a template on a process validation plan and any readings I can look up? Thanks. I read the FDA guidance but I am looking for some practical guidance.
Thanks again.