Time series Forecasting to detect anomalous behaviours in Multiphase Flow Meters

TL;DR

This paper presents a machine learning-based anomaly detection system for Multiphase Flow Meters that uses time series forecasting to identify sensor anomalies through historical data analysis.

Contribution

It introduces a novel AD system leveraging time series forecasting specifically tailored for MPFM sensor self-diagnosis.

Findings

Effective detection of sensor anomalies demonstrated

Model accurately predicts sensor behavior

Improves reliability of Multiphase Flow Meters

Abstract

An Anomaly Detection (AD) System for Self-diagnosis has been developed for Multiphase Flow Meter (MPFM). The system relies on machine learning algorithms for time series forecasting, historical data have been used to train a model and to predict the behavior of a sensor and, thus, to detect anomalies.