Predictive Monitoring and Anomaly Detection in Industrial Systems

Archana Burujwale, Anuj Tadkase, Tejas Hirve, Yash Kolekar, Sumedh Bambal

2025

Abstract

In today’s industrial activities, the detection of anomalies in real-time is important for safety and efficiency primarily in the oil and gas sector. This paper introduces a strange finding detection system which processes time-series data from different pumps, ball-bearings and chemical sensors like CH4 , CO2 , O2 , temperature, humidity and pressure. The system employs various machine learning models such as Isolation Forest, Local Outlier Factor, Robust Covariance and a One- Class SVM. The individual models detect anomalous sensor behavior, and the ensemble model combines their predictions through majority voting. The solution suggested will resolve data quality issues, provide businesses with actionable insights for better decision- making, lowered operational costs and better safety by addressing critical anomalies on time.

Paper Citation

in Harvard Style

Burujwale A., Tadkase A., Hirve T., Kolekar Y. and Bambal S. (2025). Predictive Monitoring and Anomaly Detection in Industrial Systems. In Proceedings of the 3rd International Conference on Futuristic Technology - Volume 1: INCOFT; ISBN 978-989-758-763-4, SciTePress, pages 683-691. DOI: 10.5220/0013583700004664

in Bibtex Style

@conference{incoft25,
author={Archana Burujwale and Anuj Tadkase and Tejas Hirve and Yash Kolekar and Sumedh Bambal},
title={Predictive Monitoring and Anomaly Detection in Industrial Systems},
booktitle={Proceedings of the 3rd International Conference on Futuristic Technology - Volume 1: INCOFT},
year={2025},
pages={683-691},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013583700004664},
isbn={978-989-758-763-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 3rd International Conference on Futuristic Technology - Volume 1: INCOFT
TI - Predictive Monitoring and Anomaly Detection in Industrial Systems
SN - 978-989-758-763-4
AU - Burujwale A.
AU - Tadkase A.
AU - Hirve T.
AU - Kolekar Y.
AU - Bambal S.
PY - 2025
SP - 683
EP - 691
DO - 10.5220/0013583700004664
PB - SciTePress