Operation AIRFlag: ESP32-Based Risk Monitoring with Local LLM-Assisted Diagnostics
Year: 2026
Type: preprint
Abstract: Operation AIRFlag is an educational monitoring prototype that combines an ESP32-based sensor node, a Python telemetry gateway, deterministic risk scoring, a Streamlit dashboard, and optional locally hosted large language model (LLM)-assisted diagnostics. The system uses DHT11, BMP280, MPU6050, and infrared obstacle sensors. The ESP32 transmits telemetry through USB serial, while the Python backend validates incoming data, calculates risk scores, records events in SQLite, and presents monitoring information through a dashboard. The primary telemetry session contains 450 records collected over 898.063 seconds (14.97 minutes). All records passed the configured validity checks. The session recorded 439 LOW, two GUARDED, and nine HIGH risk-state records. A separate benchmark evaluated three locally hosted language models across 162 synthetic test executions. The results demonstrate successful model execution, JSON formatting, and configured software validation checks. This work presents a laboratory proof-of-concept for embedded monitoring and LLM-assisted diagnostics. It does not establish aviation-grade hazard detection, sensor calibration accuracy, or certification for aircraft use.
Language: English
Topic: Arduino and IoT Applications
Subfield: Electrical and Electronic Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7225792814
Cites:
Cited by:
Related to: