Skip to content
IRIS NEURALContact

IndustryProduction efficiency

CAM-284

A green-lidded drum where it doesn’t belong

Mid-morning in the dispensing room. There are squares marked in blue on the floor: in one of them wait the gray-lidded drums and the excipient bags for the order in progress. On the right, inside a red outline, sits a drum with a green lid that doesn’t belong to that set and is outside the blue square. On the front table, trays of stoppers, vials and syringes. IRIS sees a different container in a place where it shouldn’t be.

Mid-morning in the dispensing room. There are squares marked in blue on the floor: in one of them wait the gray-lidded drums and the excipient bags for the order in progress. On the right, inside a red outline, sits a drum with a green lid that doesn’t belong to that set and is outside the blue square. On the front table, trays of stoppers, vials and syringes. IRIS sees a different container in a place where it shouldn’t be.
CAM-284IRIS VisionLive

Turn on IRIS Vision

AI-generated image

CAM-284 · DISPENSING ROOM · CONTAINER OUT OF ZONE

What IRIS understands

What it recognizes in this scene

  • green-lidded drum outside the zone
  • drums and bags for the order in progress
  • scale and bottle at the weighing point
  • trays of stoppers, vials and syringes
  • operator checking the order on the tablet

What this camera measures

An alert says something’s happening. The reading says how much.

  • 7Containers counted in the area
  • 1Containers outside their square
  • 6 minTime it has been out of zone
  • 3Component trays on the table
  • 11:38Time 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

a container different from the ones in the order appears inside the dispensing area

Then

  1. alert the dispensing supervisor with the camera, the time and the picture of the container
  2. save the video of when the container came into the room
  3. count the containers in the area and the ones outside their square
The instruction that set it up«Tell me if a container turns up in the dispensing area that is not one of those prepared for this order, or if any of them ends up outside its square.»

What changes

What changes for whoever answers for the plant

A component error is almost never spotted in the room: it shows up later, in the reactor, in the analysis or in the whole batch. With the camera, the dispensing supervisor gets the alert while the drum is still on the floor, with the picture, the square it’s standing in and the video of when it came into the room. A container that only moves when somebody moves it stops being a mystery for later.

What people usually ask

Does IRIS know what’s inside the drum?

No. A camera sees the container, not the contents: the color of the lid, the shape of the drum and the floor square it stands in. That’s already enough to spot that this drum isn’t from the set this order expects and that it’s outside its zone. If the label is printed and in focus, it is read and compared with the order. What’s inside is confirmed by the laboratory.

Can it mix up two similar containers?

Yes, it can, and that’s why the alert arrives with the picture and not with a verdict. IRIS shows the container, the square and the time, and a person decides. When two formats look almost identical, the plant adds a visible difference — lid color, label or position — and the rule leans on that. The rules are written by the plant, not by the camera.

Does it work for any component?

Yes, as long as it is visible from the camera and tells itself apart from the rest: a drum, a sack, a vial, a stopper or a syringe. A powdered excipient inside a closed bag is told apart by its packaging and its label, not by its contents. If two materials only differ on the inside, the camera isn’t the tool: the analysis is.

A different case every time

Everything comes in. Only what matters gets through.

This sums up what IRIS does with one alert, from the moment it appears until it’s closed. The real screen holds far more; this is the main thread.

  1. Four cameras at once
  2. Each understands its own view
  3. The numbers climb by themselves
IRIS NEURAL
30ES
IRISDirectoGrabacionesGISIncidencias3996SituaciónCasosLPRAutomatizacionesIRIS DATA
Ask a question or make a request…Send
IRIS · Infinity Neural

And the best part

By the eighth hour of a shiftnobody watches the way they did in the first. That isn’t a flaw.

It’s being human. A camera has no eighth hour: at four in the morning it understands what it understood at noon, and it speaks up just the same.

Tell us your problem and we’ll say whether IRIS understands it, or not yet.

A person answers, the same working day.