Semiconductor Process Integration Toolkit is a Python-based portfolio project that demonstrates the core skills required for semiconductor process integration engineering. Using simulated etch process data, it applies Statistical Process Control (SPC), Fault Detection & Classification (FDC), root cause analysis, and process capability (CpK) calculations — all of which are directly transferable to high-volume manufacturing environments at semiconductor fabs.
- SPC Control Charts: Real-time process monitoring with 3σ upper/lower control limits
- FDC Anomaly Detection: Isolation Forest algorithm to flag process excursions (parallel to fab fault detection)
- Root Cause Analysis: Correlation matrix identifying relationships between etch rate and process parameters (temperature, pressure)
- Process Capability (CpK): Quantifies process performance against specification limits
- Quality Event Form (QEF) Simulation: CAPA-style summary with root cause hypothesis and disposition recommendations
- Google Colab Ready: Run instantly in your browser without installation
Click the badge below to open the notebook directly in Google Colab:
Feel free to fork this project and adapt it for your own use case. Pull requests are welcome!
This project is open source and available under the MIT License.
- Built with Python in Google Colab and DeepSeek
- Visualization powered by Matplotlib and Seaborn
- Machine learning anomaly detection via Scikit-learn Isolation Forest
- Inspired by semiconductor process control methodologies used at semiconductor fabs.
📧 Contact email: liz21atang@gmail.com
Elizabeth (Epse Kombe) Atang:
