--- title: Intelligent Predictive Maintenance System emoji: 🏭 colorFrom: blue colorTo: indigo sdk: gradio sdk_version: 5.38.2 python_version: "3.11" app_file: app.py pinned: false license: mit --- # Engineering AI in Action This Hugging Face Space combines: - IoT sensor-based machine-failure prediction - Random Forest classification - Local reasoning using `HuggingFaceTB/SmolLM2-1.7B-Instruct` - AI-generated engineering assessment - Automated maintenance work-order generation - Human-in-the-loop approval ## Required files - `app.py` - `requirements.txt` - `README.md` - `ai4i2020.csv` ## Hardware note The 1.7B parameter language model may be slow on the free CPU Space and can require significant memory. A GPU Space will provide a much better live demonstration experience. ## Educational disclaimer This prototype is for teaching and demonstration only. It must not be used to make real industrial maintenance, repair, shutdown, or safety decisions without validation by a qualified engineer.