About Michel Baudin

Consultant, trainer, author on Lean Manufacturing

Posts by Michel Baudin:

null

Dec 1 2022

About Digital Twins

Some hosts showed digital twins during the Van of Nerds tour de France last September, but none mentioned the cyber-physical systems touted as a key component in Industry 4.0. Furthermore, we also found that the meaning of digital twin had drifted away from detailed simulations of physics and chemistry as part of a cyber-physical system for process control.

Instead, a digital twin is now an animation of part movements and machine status in a line for production control. This has effectively disabled discussions of digital twins in the context of cyber-physical systems, which matters in stabilizing and establishing capability for high-technology processes like additive manufacturing.

Continue reading…

By • Van of Nerds • 3 • Tags: , , , ,

ProcessProduct.png

Nov 22 2022

Processes and Products | Cécile Roche

This is the perspective of Cécile Roche about what we saw in the Van-of-Nerds tour in September, 2022:

The risk when we talk about digital, even more than when we talk about Lean, is to worry about processes before worrying about products. We must never forget that a process is never an end in itself. It is at the service of creating value for customers — in other words, products — and at the service of improving people’s working conditions — making the work easier and improving its quality. Lean practices are not implemented to produce faster. They are implemented to reveal problems as soon as possible, in order to take care of the customers by taking care of the products, and for that, make people grow in autonomy by developing their capacity for problem solving and then increase productivity through quality.

Continue reading…

By • Van of Nerds • 3 • Tags: , , ,

null

Nov 12 2022

Automation and People

This is the first in a series of posts about learnings from the Van of Nerds tour of 11 manufacturing sites in Northern France completed on September 9. First, I describe who we are, why and how we went on this tour. Then, to make this post more than just an introduction, I appended a summary of our observations on automation and people. There is more to come.

Continue reading…

By • Van of Nerds • 6 • Tags: , , , , , , , ,

DinosaurPresentingHistogram.png

Nov 7 2022

Analyzing Variation with Histograms, KDE, and the Bootstrap

Assume you have a dataset that is a clean sample of a measured variable. It could be a critical dimension of a product, delivery lead times from a supplier, or environmental characteristics like temperature and humidity. How do you make it talk about the variable’s distribution? This post explores this challenge in the simple case of 1-dimensional data. I have used methods from histograms to KDE and the Bootstrap, varying in vintage from the 1890s to the 1980s:

Timeline of tools used in this post

Other methods were surely invented for the same purpose between 1895 and 1960 or since 1979, that I don’t know about or haven’t used. Readers are welcome to point them out.

The ones discussed here are not black boxes, automatically producing answers from a stream of data. All require a human to tune the settings of the tools. And this human needs to know the back story of the data.

Continue reading…

By • Data science • 2 • Tags: , , ,

Jakob-Bernoulli-stamp-Swiss-formula-graph-law-1713

Oct 12 2022

Musings on Large Numbers

Anyone who has taken an introductory course in probability, or even SPC, has heard of the law of large numbers. It’s a powerful result from probability theory, and, perhaps, the most widely used. Wikipedia starts the article on this topic with a statement that is free of any caveat or restrictions:

In probability theory, the law of large numbers is a theorem that describes the result of performing the same experiment a large number of times. According to the law, the average of the results obtained from a large number of trials should be close to the expected value and tends to become closer to the expected value as more trials are performed.

This is how the literature describes it and most professionals understand it. Buried in the fine print within the Wikipedia article, however, you find conditions for this law to apply. First, we discuss the differences between sample averages and expected values, both of which we often call “mean.” Then we consider applications of the law of large numbers in cases ranging from SPC to statistical physics. Finally, we zoom in on a simple case, the Cauchy distribution. It easily emerges from experimental data, and the Law of Large Numbers does not apply to it.

Continue reading…

By • Laws of nature • 1

Screen Shot 2022-10-04 at 4.55.56 PM

Oct 4 2022

Strange Statements About Probability Models | Don Wheeler | Quality Digest

In his latest column in Quality Digest, Don Wheeler wrote the following blanket statements, free of any caveat:

  1. “Probability models are built on the assumption that the data can be thought of as observations from a set of random variables that are independent and identically distributed.”
  2. “In the end, which probability model you may fit to your data hardly matters. It is an exercise that serves no practical purpose.”

Source: Wheeler, D. (2022) Converting Capabilities, What difference does the probability model make? Quality Digest

Michel Baudin‘s comments:

Not all models assume i.i.d. variables

Wheeler’s first statement might have applied 100 years ago. Today, however, there are many models in probability that are not based on the assumption that data are “observations from a set of random variables that are independent and identically distributed”:

  • ARIMA models for time series are used, for example in forecasting beer sales.
  • Epidemiologists use models that assume existing infections cause new ones. Therefore counts for successive periods are not independent.
  • The spatial data analysis tools used in mining and oil exploration assume that an observation at any point informs you about its neighborhood. The analysts don’t assume that observations at different points are independent.
  • The probability models used to locate a wreck on the ocean floor, find a needle in a haystack, and other similar search problems have nothing to do with series of independent and identically distributed observations.

Probability Models Are Useful

In his second statement, Wheeler seems determined to deter engineers and managers from studying probability. If a prominent statistician tells them it serves no useful purpose, why bother? It is particularly odd when you consider that Wheeler’s beloved XmR/Process Behavior charts use control limits based on the model of observations as the sum of a constant and a Gaussian white noise.

Probability models have many useful purposes.  They can keep from pursuing special causes for mere fluctuations and help you find root causes of actual problems. They also help you plan your supply chain and dimension your production lines.

Histograms are Old-Hat; Use KDE Instead

As Wheeler also says, “Many people have been taught that the first step in the statistical inquisition of their data is to fit some probability model to the histogram.” It’s time to learn something new, that takes advantage of IT developments since Karl Pearson invented the histogram in 1891.

Fitting models to a sample of 250 points based on a histogram is old-hat. A small dataset today is more 30,000 points, and you visualize its distribution with kernel density estimation(KDE), not histograms.

#donwheeler, #probability, #quality

By • Press clippings • 8 • Tags: , ,

«< 4 5 6 7 8 >»