Semiconductor yield prediction from sensors
Inspired by publicly reported work at Intel
Predict which wafers will fail from hundreds of process sensor readings, and find the sensors that matter.
The brief
Intel has written about using AI to analyse manufacturing yield, so engineers find what causes failures faster. Using public data from a semiconductor process, predict pass or fail from hundreds of sensor readings, cut the sensors down to the ones that matter, and report them to a process engineer. Good looks like: careful handling of missing values and imbalance, balanced metrics, a short list of key sensors, and an engineer-facing summary.
Read the case first
What Intel has said in public about this kind of work, on its own pages:
- Transforming Manufacturing Yield Analysis with AI (Intel IT) ↗
- Faster, More Accurate Defect Classification Using Machine Vision (Intel IT) ↗
Make it your own
Apply it to a process you can name: PCB assembly, solar cell manufacturing or an electronics lab's soldering. Write which sensors that process has and which failures matter most.
AITeky has no link with Intel, which has not reviewed or endorsed this brief. The brief only draws on what the company has published, uses open data rather than its data, and is a learning exercise: don't present your project as Intel's work or system.
What you will build
- Explore missing values and constant sensors
- Select features and reduce dimensions
- Train models with imbalance handling
- Evaluate with balanced accuracy and recall on failures
- Report the key sensors to a process engineer
Free, open data to build it with
Sign up free to get the data and links
It takes a minute with your email. AiTeky Pass (₹999/month or ₹9,999/year) is free for your first 30 days.