A scratch label that follows the lamp

CeciliaBailey · 29 Jan 2025, 20:43 UTC

Closed
CE
CeciliaBailey
Our planned UR5e camera station has a suspect reference set. One stainless plate acquires a 'scratch' when tilted. It disappears again when returned. No agreed physical inspection result. What are we training against?

15 replies

FE
FelixAli0197
Replying to CeciliaBailey

We nearly bought an inspection setup on pictures like that. Get someone who owns acceptance to examine the actual plate. You can't decide what the camera should reject while everyone disagrees about whether the reference part is defective.

15 points
CE
CeciliaBailey
Replying to FelixAli0197

Quality called it doubtful under their bench light. The image folder nevertheless labels it rejected.

1 points
FE
FelixAli0197
Replying to CeciliaBailey

Then pull it out of the definite rejects. Doubtful is a perfectly useful category while you sort this. Turning uncertainty into a confident filename won't help the lighting work.

12 points
JA
JamieBrown0904
Replying to CeciliaBailey

Could you photograph the same marked area across a few small presentation changes on the bench? With the physical part kept available. I mean mark its location in your records, not put a pen mark across the surface you're inspecting.

5 points
FE
FelixAli0197
Replying to JamieBrown0904

Include an agreed good plate and an agreed defective one in that comparison. Otherwise you'll learn how your uncertain plate photographs and still have no acceptance reference.

6 points
LO
LouisBell0659
Replying to FelixAli0197

Who will keep those physical references available after commissioning, when somebody replaces a light or bracket?

17 points
FE
FelixAli0197
Replying to LouisBell0659

Quality ought to be involved, but don't assume they have storage sorted. We lost our reference samples in an enthusiastic bench tidy. Photos survived. The useful bits didn't.

13 points
CE
CeciliaBailey
Replying to JamieBrown0904

Bench comparison done. The bright band crosses different surface features as presentation changes. Labels now marked uncertain.

7 points
JA
JamieCarter0991
Replying to CeciliaBailey

That supports reflection. It does not establish that the plate has no defect.

9 points
CE
CeciliaBailey
Replying to JamieCarter0991

Correct. I meant the image labels are uncertain, not that the plate passed.

14 points
JA
JamieCarter0991
Replying to CeciliaBailey

Fair enough. That distinction tends to disappear when somebody copies the summary.

22 points
FE
FelixAli0197
Replying to FelixAli0197

Have you got the two agreed reference plates yet? I'd rather see those results before anyone starts selling a threshold as the answer.

15 points
LO
LouisBell0659
Replying to LouisBell0659

And did anyone take ownership of storing them?

19 points
CE
CeciliaBailey
Replying to FelixAli0197

Quality supplied two accepted and two rejected references, with reasons. They own storage. Imaging comparison remains underway.

12 points
JA
JamieBrown0904
Replying to CeciliaBailey

That gives you a much better starting set. Include the uncertain plate as a separate investigation example so it doesn't quietly get promoted back into the reject folder next time someone combines folders.

15 points

Discussion closed

This discussion is closed to new replies after six months without activity. Last activity: .