DRW-TF-Based Multisensor Anomaly Detection for Industrial Air-Conditioning Systems
Year: 2026
Type: article
Abstract: Maintaining suitable storage conditions in aircraft spare-parts hangars requires continuous monitoring of air-conditioning equipment. Since temperature and humidity alone may not reveal equipment problems, this work develops an Arduino UNO-based multisensor system using DHT11, MQ135, current, and vibration sensors. The controller compares readings with predefined limits and provides local and remote alerts through a buzzer and GSM module. Hardware testing is performed using two 100 W bulbs to examine abnormal electrical loading. Additionally, the DRW-TF machine learning model analyzes combined sensor data and classifies equipment conditions into four categories: Normal, Warning, Anomaly, and Critical. The model is trained offline and stored for real-time prediction without repeated training. Experimental evaluation using 100 test samples achieves 93% classification accuracy, demonstrating the potential of combining threshold-based monitoring with machine learning for industrial air-conditioning condition assessment.
Institution: Dravidian University
Language: English
Subfield: Control and Systems Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7235846623
