Skip to content
woodfrog
← Deep dives
What drives what, and by how muchManufacturing and pharmaUse case, not a client result

Why does yield vary between shifts, lines and batches?

Find which process settings, materials and handovers explain the variation, and what to change first.

The decision it informs

Which process parameters to tighten, and which line or shift practice to copy.

Why a dashboard cannot answer it

A dashboard shows that line 3 is worse than line 1. It cannot say whether the cause is the material, the settings, the operator handover or the machine, because those move together.

What we ask in the first week

The questions behind the question.

  • What counts as a good unit, and who decides?
  • Which settings can the operator change, and how often do they?
  • Which differences between shifts are known, and which are suspected?
  • What would it be worth to close half the gap?
Data we would look at
Batch and run recordsProcess parameters from PLCsRaw material lots and supplier dataShift rosters and handover notesQuality results and rework
How we would analyse it

Methods, chosen for this question.

Variance decompositionHow much of the spread comes from line, shift, material and settings.
Statistical process controlWhich variation is normal and which is a signal worth chasing.
Gemba walks and interviewsWhat the operators know that no sensor records, tested against the data.
  1. 01Scope
  2. 02Immerse
  3. 03Analyse
  4. 04Test the evidence
  5. 05Read out and hand over
What you would get

Findings you can act on.

Where the variation livesThe share of the spread explained by each source, so effort goes where it pays.
A parameter windowThe range of each key setting that goes with good yield, with evidence.
A practice comparisonHow the best shift runs a changeover, written down so it can be copied.
How a driver ranking readsSchematic, no values
Each bar is the size of a factor's effect and the marker is the range around it. In a real deep dive both come from your data.
Scenarios you could then run

Ask what-if, on your own numbers.

  • What if the key setting is held inside its window?
  • What if every shift followed the best changeover routine?
  • What if the weakest material lot is excluded?
Try a what-if playground →
More investigations

Is this your question?

Tell us the decision you are trying to make. We will say whether a deep dive is the right way to answer it, and what it would take.

Build your own brief