Hybrid Autoencoder-Isolation Forest approach for time series anomaly detection in C70XP cyclotron operation data at ARRONAX

TL;DR

This paper introduces a hybrid Autoencoder-Isolation Forest method for early detection of subtle anomalies in time series data from a cyclotron, improving operational reliability in medical isotope production.

Contribution

It presents a novel combination of Autoencoder and Isolation Forest to enhance detection of subtle anomalies in time series data, addressing limitations of traditional methods.

Findings

Improved anomaly detection accuracy on cyclotron sensor data

Effective identification of subtle anomalies near normal data mean

Validated approach shows clear performance enhancement

Abstract

The Interest Public Group ARRONAX's C70XP cyclotron, used for radioisotope production for medical and research applications, relies on complex and costly systems that are prone to failures, leading to operational disruptions. In this context, this study aims to develop a machine learning-based method for early anomaly detection, from sensor measurements over a temporal window, to enhance system performance. One of the most widely recognized methods for anomaly detection is Isolation Forest (IF), known for its effectiveness and scalability. However, its reliance on axis-parallel splits limits its ability to detect subtle anomalies, especially those occurring near the mean of normal data. This study proposes a hybrid approach that combines a fully connected Autoencoder (AE) with IF to enhance the detection of subtle anomalies. In particular, the Mean Cubic Error (MCE) of the sensor data reconstructed by the AE is used as input to the IF model. Validated on proton beam intensity time series data, the proposed method demonstrates a clear improvement in detection performance, as confirmed by the experimental results.