CAM-363
The basket has been loaded from four different bays
Eleven in the morning, scrap yard. The bays are separated by grade: rusty sections and tubes, coils of wire, bright light scrap and baled cans. In the middle, the charging basket holds material from four bays at once: rusty beams, tubes, galvanised offcuts and pale sections. The loader is bringing another mixed bucket. Two operators watch from the ground. IRIS recognises what the material looks like and which bay it came out of; what is actually inside the metal comes from the heat analysis.
Turn on IRIS Vision
AI-generated image
What IRIS understands
What it recognises in this scene
- basket loaded from several bays
- bay of rusty sections and tubes
- bay of wire coils
- bay of baled cans
- loader bucket with a mixed load
- green skip of cans
What this camera measures
An alert says something is happening. The reading says how much.
- 4Grade bays in the yard
- 6Buckets tipped into the basket
- 4 minTime loading the basket
- 3People in the yard
- 11:05Time of the alert
The figures on this screen are an example from the illustration, not any client's measurement.
The rule
You decide once. IRIS applies it always.
If
material goes into the basket from bays that are not in the recipe for that heat
Then
- alert the yard supervisor and the charging pulpit with the camera and the time
- save a picture of the basket and of which bay each bucket came from
- leave the record ready to be compared with the heat analysis
The instruction that set it up«Tell me if material from a bay that does not belong in this recipe goes into the basket, and tell me which bay it came from.»
What changes
What changes for whoever answers for the plant
A badly composed basket does not show up until the heat comes out off specification, and by then there is a whole heat to downgrade or melt again. The camera looks at the step before: what the material going into the basket looks like, and which bay each bucket came from. That does not replace the laboratory, but it brings the doubt forward by hours and leaves a picture of every load. With that, the yard supervisor can hold the basket before it goes up to the furnace.
What people usually ask
Does IRIS know what the scrap is made of?
No. IRIS tells material apart by how it looks — shape, colour, shine, rust — and by which bay of the yard the bucket came from. That is enough to see that a load does not match the intended recipe and to raise the alert before the basket goes up to the furnace. The real composition of the steel comes from the laboratory heat analysis, and this camera does not replace it: it arrives earlier and prepares the ground for it.
What if two scrap grades look very much alike?
Then the bay of origin decides. When two materials look alike on screen, what separates them is where they were picked up: IRIS follows the bucket from the bay to the basket and logs it. If there is still doubt, the alert says so, and a person settles it. The camera does not guess: it shows what it saw and the picture it says it with.
Is it any use at night or with the yard wet?
Yes for the bay of origin, which is geometry and does not depend on the light. For the look of the material, rain and darkness make it harder, and that should be said: with the yard wet the shine changes and some grades get easier to confuse. That is why the rule leans on both things at once, appearance and origin, and not on colour alone.
Other cameras
- CAM-360 · The slab has stopped on the mill, with the beacons on red
- CAM-361 · The ladle stream has missed and molten metal is running across the floor
- CAM-362 · Snow and closed drums in the basket, still hanging over the furnace
- CAM-364 · Somebody is walking the aisle while the full ladle is moving
- CAM-365 · A coil is passing right over a worker
- CAM-366 · Two coils out of the rack, and the chocks lying on the floor
Demo · IRIS at work
Everything comes in. Only what matters gets through.
This sums up what IRIS does with one alert, from the moment it appears until it is closed. The real screen holds far more; this is the main thread.
- Checks the whole system
- Flags what is failing
- Puts it on one screen
Next step
Who watches an entire motorway?
10 cases: 8 raise an alert when something happens and 2 only measure. You see each image as it is, and then with what IRIS understands on top.
Who watches a whole station at rush hour?
17 cases: 11 raise an alert when something happens and 6 only measure. You see each image as it is, and then with what IRIS understands on top.
And the best part
What happens outside the framedoes not exist for IRIS. No camera sees the whole world.
So the first thing we do is check what each camera covers and write it down: from here you can understand this, and not that. A dull hour that saves a lot of misunderstandings.
Tell us your problem and we will say whether IRIS understands it, or not yet.
We reply the same working day.