Billet heating is a schedule problem wearing an energy problem’s clothes. A billet at temperature with no press to go to keeps drawing power and keeps oxidising, and the metal that leaves as scale never books as a loss. The heat is logged; the wait that inflated it is not.
Your ERP logs the billets heated and the energy booked.
It won’t tell you the line stalled and the billets soaked long, burning surface into scale before they ever reached the die.
Why the gap existsWhere the losses hide
None of these stop the furnace. They show up as a little more scale, a little more draw, a billet reheated — and they average away by month-end.
A billet held past its soak keeps oxidising. The surface leaves as scale under the hammer, the piece comes up light, and the yield loss is charged to the melt, not to the wait that caused it.
Door and skid condition, loading practice and recuperator state all move the energy a tonne of billets takes. The count stays flat while the kilowatt-hours behind it climb.
A billet forged cold laps and cracks; one forged too hot grows and decarburises. Both trace to a temperature that drifted, and the drift is only visible if the furnace’s own readings were kept.
The join
Same run, same clock, same asset — three streams that only mean something together.
Billets charged, grade, energy booked to the furnace, and the forgings that came out.
Zone temperatures across the furnace sampled through the shift, the operator’s stall and reheat reasons tagged when they happen, and energy tied to the furnace.
Energy per tonne per heat, with the soak or stall that explains an outlier already attached — instead of a monthly average that hides both.
What Munshi surfaces
Teal is normal, maroon is flagged. Illustrative data.
Two heats sit well above the run. Both carry a delay reason logged at the furnace.
Tagged by the operator as it happened, so the soak lands against the cause, not the furnace.
When an outcome moves and a signal moves with it, Munshi shows both and says they moved together. It does not tell you one caused the other. The operator confirms the cause, and the confirmed cause is written back to that asset’s register — so the pattern is already named the next time it appears.
Related stages
Die wear you meet again at inspection, and downtime nobody booked.
Get started
See this on your own line.
Bring a month you already understand. The useful test is whether Munshi finds what you already know — and then what you didn’t.