Aerospace standard AS9138—“Quality management systems statistical product acceptance requirements” was issued this year (2018), a few years after its accompanying guidance materials in section 3.7 of the International Aerospace Quality Group’s (IAQG) Supply Chain Management Handbook. The new aerospace standard supersedes the aerospace recommended practice of ARP9013 and, related to MIL-STD-105 (ANSI/ASQ Z1.4), claims to shift focus from the producer’s risk to the consumer’s risk with sampling plans having an acceptance number of zero (c=0).

Somewhere along this evolutionary path, the sampling procedures of MIL-STD-105 have fallen out of favor, even though the consumer risks of MIL-STD-105 at their designed lot tolerance percent defective (LTPD) point are superior to most plans found within AS9138.

In this all-manufacturing episode, we look at the STEM pipeline into manufacturing, supplier development, how to make sense of manufacturing data and, no, manufacturing is not dead.

“Strengthening the STEM Workforce Pipeline Through Outreach”

NIST does more than just research and come up with really cool technology. It also has STEM outreach programs designed to help young people and minorities get excited by all this coolness.

“Making Sense of Manufacturing Data”

Are you collecting enough data? Are you collecting too much data? Do you know the difference between data and information? Doug Fair of InfinityQS does. He told us.

Parts One and Two of this series illustrated four problems with using a model-building approach when data snooping. This column will present an alternative approach for data snooping that is of proven utility. This approach is completely empirical and works with all types of data.

The model-building approach

When carrying out an experimental study we want to know how a set of input variables affect some response variable. In this scenario it makes sense to express the relationships with some appropriate model (such as a regression equation). The experimental runs will focus our attention on these specific input and response variables, and the model will answer our questions about the relationships.

During the early 1990s, I was president of the Twin Cities Deming Forum. I had a wonderful board whose members were full of great ideas. One member, Doug Augustine, was a 71-year-old retired Lutheran minister and our respected, self-appointed provocateur. He never missed an opportunity to appropriately pull us right back to reality with his bluntly truthful observations and guaranteed follow through on every commitment he made.

After W. Edwards Deming’s death in 1993, we tried to keep the forum alive, but monthly meeting attendance started to drop off significantly. We were offering innovative meetings to grow in practice of Deming’s philosophy, but our members wanted static rehashing and worship of “the gospel according to Dr. Deming.”

The last straw was a meeting where a self-appointed Deming expert/consultant went too far: He lobbed one too many of his predictable, pedantic “gotcha! grenades” at the speaker for alleged deviations from “the gospel.” His persistence blindsided and visibly upset our wonderful guest speaker. I was furious and publicly told him to stop. It did not go over well—except with my board.

In the foreword of Mark Graban’s book, Measures of Success: React Less, Lead Better, Improve More (Constancy Inc., 2018), renowned statistician, Donald J. Wheeler, writes about Graban: “He has created a guide for using and understanding the data that surround us every day.

“These numbers are constantly changing,” explains Wheeler. “Some of the changes in the data will represent real changes in the underlying system or process that generated the data. Other changes will simply represent the routine variation in the underlying system when nothing has changed.”

The problem is in deciding whether data changes are “noise” or signals of real changes in the system.

“Mark presents the antidote to this disease of interpreting noise as signals,” adds Wheeler. “And that is why everyone who is exposed to business data of any type needs to read this book.”

Quality and manufacturing practitioners are most familiar with the effect of variation on product quality, and this is still the focus of the quality management and Six Sigma bodies of knowledge. Other forms of variation are, however, equally important—in terms of their ability to cause what Prussian general Carl von Clausewitz called friction, a form of muda, or waste—in production control and also many service-related activities. This article shows how variation affects the latter as well as the former applications.

W. Edwards Deming’s Red Bead experiment was an innovative, hands-on exercise that demonstrated conclusively the drawbacks of blaming or rewarding workers for unfavorable and favorable variation, respectively, in a manufacturing process. The exercise consisted of using a sampling paddle to withdraw a certain number of beads from a container. White beads represented good parts, and red beads nonconforming parts. Results for five workers might, for example, be as follows for 200 parts, of which 3 percent are nonconforming. (You can simulate this yourself with Excel by means of the Data Analysis menu and Random Number Generation. Use a binomial distribution with 200 as the number of trials, and nonconforming fraction p = 0.03.)

A few months back, I was reading a really good article from The Wall Street Journal, titled “Stop Using Excel, Finance Chiefs Tell Staffs.” Even though it was geared toward accounting and corporate operations, the message of the article struck home: Excel shouldn’t be used as an enterprisewide financial platform. That’s as true for the manufacturing quality world as it is for finance.

One quote from the article stuck with me. An executive working on cutting Excel out of the process at his firm stated “I don’t want financial planning people spending their time importing and exporting and manipulating data, I want them to focus on what is the data telling us.” And I thought, “That’s what manufacturing organizations need to start thinking.” Manufacturers need to stop juggling spreadsheets and paper and start focusing on the information that can be found in the data they collect.