The problem
Defects are found after production, wasting material.
What to build
Model the link between process settings and defects and recommend adjustments in real time.
Success looks like
Defects predicted ahead of inspection on a public process dataset with explanations of the main drivers.
Suggested technologies
- Tabular ML
- Feature importance
- Process control
- Streaming
- Explainability
An original, independent statement. It is not an official Smart India Hackathon problem statement, and Arventiq Labs is not affiliated with or endorsed by that programme. The scenario is illustrative and does not describe any specific organisation. Free to use with credit.