kordas

The fence panel manufacturer had a problem with excessively high variation in enamel coating thickness. The five-year anti-corrosion warranty offered to customers requires ensuring a minimum coating thickness of 80 microns, confirmed by salt spray chamber tests. High variation in thickness within the manufactured panels results in significantly higher consumption of enamel powder than assumed […]

What’s worse than a bar chart? A 3D bar chart Every chart has only one purpose: to show the truth contained in the data—and to do it as quickly as possible. And that’s precisely where the classic chart struggles. A bar chart looks innocent: it shows a single number as the height of the bar. […]

You can find the first parts of the article here: PART 1 PART 2 PART 3 PART 4 PART 5 It’s time for the final conclusions, i.e. the DoE analysis We’ll begin with the Y3: scale analysis, which is a visual assessment of the yolk set level on a scale of 1 to 16. The […]

You can find the first parts of the article here: PART 1 PART 2 PART 3 PART 4 How to analyze an experiment? Let’s start practically! 1. Did we create variation? We now face a practical analysis, i.e., a diagnostic to determine whether everything went “OK” during the DoE. The fundamental question we should ask […]

You can find the first parts of the article here: PART 1 PART 2 PART 3 Creating a Prediction Table – Summary of the Planning Stage To summarize the planning phase, it is useful to create a Prediction Table that documents our knowledge prior to the DoE. This is a good way to begin a […]

You can find the first parts of the article here: PART 1 PART 2 What makes the conclusions from DOE work in practice? Once we have the experimental matrix, our recipe for conducting a DOE, we need to consider how to approach its implementation. There will always be factors that we won’t manipulate during the […]