Smart Air Quality Monitoring for Automotive Workshop Environments
Kauan Divino Pouso Mariano, Fabrycio Leite Nakano Almada, Maykon Adriell Dutra
TL;DR
The paper tackles the challenge of protecting worker health and ensuring regulatory compliance in automotive workshops by presenting an IoT/AI-based air quality monitoring system. It combines a hardware suite (DHT-11 for temperature/humidity, MQ-135 for toxic gases) with ESP8266 for Wi‑Fi connectivity, transmitting data via MQTT to the ThingSpeak cloud, and analyzes the data using ML models (LR, DT, SVM) to derive a Gaussian-based healthiness index $S \in [0,100]$ centered at $T=21^ extdegree C$ and $RH=40\%$. Real-time visualization, alerting, and historical reporting demonstrate robust data collection, pollutant spike detection, and actionable decision support for workshop managers. The approach yields a practical, replicable framework for industrial environmental monitoring that can enhance occupational safety and regulatory compliance, with potential extensions to additional sensors and more advanced AI methods for improved prediction and resilience in connectivity.
Abstract
Air quality monitoring in automotive workshops is crucial for occupational health and regulatory compliance. This study presents the development of an environmental monitoring system based on Internet of Things (IoT) and Artificial Intelligence (AI) technologies. DHT-11 and MQ-135 sensors were employed to measure temperature, humidity, and toxic gas concentrations, with real-time data transmission to the ThingSpeak platform via the MQTT protocol. Machine learning algorithms, including Linear Regression, Decision Trees, and SVM, were applied to analyze the data and compute an air salubrity index based on Gaussian functions. The system proved effective in detecting pollutant peaks and issuing automatic alerts, significantly improving worker health and safety. Workshops that implemented the system reported greater regulatory compliance and reduced occupational risks. The study concludes that the combination of IoT and AI provides an efficient and replicable solution for environmental monitoring in industrial settings.