# Defect inspection · Use cases · Dscvry

> Apply Dscvry to defect inspection: photograph every part at line speed, flag cracks, burrs and missing features, and link defects back to the process that...

Source: https://dscvryai.com/use-cases/defect-inspection/

# Is this part defective?

Catch the defect before it ships. Every part. Every surface. Every shift.

See it worked through ·

1. [Home](https://dscvryai.com/)
2. [Use cases](https://dscvryai.com/#use-cases)
3. Defect inspection

## Inspectors see a sample. Customers see the rest.

Manual inspection checks a fraction of what the line makes, and attention fades over a shift. The defects that get through are found by the customer.

### Sampled, not inspected.

Only a share of parts are checked, so most defects are never looked for.

### Tired eyes.

Hairline cracks and faint marks are easy to miss in the eighth hour.

### No link to the cause.

A rejected part is scrapped. Why it went wrong is rarely traced back to the process.

## What the AI reads.

Every part on the line, photographed and checked against what good looks like, with the process data from the moment it was made.

### In

- Line cameras
- Golden samples
- Defect library
- Process data
- Specifications
- Rework records

### At work

1. [Sense](https://dscvryai.com/technology/sense/) Photographs every part at line speed.
2. [Understand](https://dscvryai.com/technology/understand/) Finds and measures cracks, marks, burrs and missing features.
3. [Check](https://dscvryai.com/technology/check/) Tests each finding against your acceptance limits.
4. [Anticipate](https://dscvryai.com/technology/anticipate/) Links rising defect rates to drift in the process that made them.
5. [Operate](https://dscvryai.com/technology/operate/) Rejects the part at the gate and alerts the line lead.

### Out

One inspection log. Every reject keeps its image.

## Every part seen. Every reject explained.

Quality engineers see each finding, the image behind it and the process conditions when the part was made.

Inspection log · Why it's rejected · Shift report ·

Inspection · Line 3 · housings · shift B Illustrative

**1,176** passed · **5** for review · **1** rejected

| Part | Finding | Status | Measure | Time |
|---|---|---|---|---|
| Flagged this shift | | | | |
| 1191 | Hairline crack, mounting boss | Defect | 2.4 mm long; any crack is rejected | 10:41:18 |
| 1187 | Burr on edge B | Check | 0.3 mm; limit 0.2 mm | 10:41:12 |
| 1143 | Crack-like mark, zone A | Check | Below the review threshold | 10:38:40 |
| 1102 | Crack-like mark, zone A | Check | Below the review threshold | 10:35:02 |
| 1077 | Surface mark | Check | At the cosmetic limit | 10:32:47 |
| 1040 | Missing chamfer | Check | Chamfer 0.1 mm; drawing 0.5 mm | 10:29:10 |
| Latest passes | | | | |
| 1192 | No findings | Pass | All features present | 10:41:19 |
| 1190 | No findings | Pass | All features present | 10:41:16 |
| 1189 | No findings | Pass | All features present | 10:41:15 |

Illustrative example. Line, parts, measurements and times are fictional.

## Built for the line.

Inspection has to keep up with production, and run where the line runs.

### Keeps line speed.

Runs on hardware beside the line, so inspection never slows production.

Deployment options
https://dscvryai.com/#deployment

### Tuned to your parts.

Adapted to your golden samples and defect library only with your explicit permission.

Image understanding
https://dscvryai.com/technology/sense/images/

### Links finding to cause.

Every reject is tied to the process data from the moment it was made.

How Anticipate works
https://dscvryai.com/technology/anticipate/

## Same records. Other problems.

The same line data answers other questions too.

Is the supplier’s evidence complete?

### Supplier quality

Find missing or inconsistent evidence.

See how →
https://dscvryai.com/use-cases/supplier-quality/

What fails next?

### Equipment failure

Spot the patterns and warn what may fail next.

See how →
https://dscvryai.com/use-cases/equipment-failure/

What actually happened with this complaint?

### Customer complaints

Reconstruct what happened, and how it was handled.

See how →
https://dscvryai.com/use-cases/customer-complaints/

What’s blocking the restart?

### Plant restart

Decide what’s ready and what’s blocking restart.

See how →
https://dscvryai.com/use-cases/plant-restart/

Manufacturing solution
https://dscvryai.com/solutions/manufacturing/

More in Quality & safety
https://dscvryai.com/#use-cases

Every use case
https://dscvryai.com/use-cases/

## Bring us a box of rejects.

Send images of good and bad parts. We’ll show you what the AI finds, and what it misses.

[Talk to us →](https://dscvryai.com/contact/?topic=Defect%20inspection%20inquiry)

**London**Discovery AI Limited · United Kingdom

**Hyderabad**ReDscvry Technology Private Limited · India

**Chennai**ReDscvry Technology Private Limited · India