DRW-TF-Based Multisensor Anomaly Detection for Industrial Air-Conditioning Systems
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.
Authors
- T. Sivakumar
- Andalam Praveen Kumar
- P. Ajay Kumar Reddy
Institutions
- Dravidian University (IN)
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2026-11-18
- DOI
- https://doi.org/10.5281/zenodo.24347265
- Primary Topic
- Fault Detection and Control Systems
- Type
- article
- Field-Weighted Citation Impact
- 0.00