Scalable changepoint and anomaly detection in cross-correlated data with an application to condition monitoring

TL;DR

This paper introduces a scalable, efficient method for detecting anomalies and changepoints in cross-correlated multivariate time series, with a focus on condition monitoring in subsea engineering, outperforming existing methods in accuracy and computational efficiency.

Contribution

The paper presents a novel scalable approach with a new dynamic programming algorithm for anomaly detection in correlated multivariate time series, applicable to real-world condition monitoring.

Findings

Method performs well in simulation studies

Outperforms competing methods in detection accuracy

Successfully detects faulty periods in real application

Abstract

Motivated by a condition monitoring application arising from subsea engineering we derive a novel, scalable approach to detecting anomalous mean structure in a subset of correlated multivariate time series. Given the need to analyse such series efficiently we explore a computationally efficient approximation of the maximum likelihood solution to the resulting modelling framework, and develop a new dynamic programming algorithm for solving the resulting Binary Quadratic Programme when the precision matrix of the time series at any given time-point is banded. Through a comprehensive simulation study, we show that the resulting methods perform favourably compared to competing methods both in the anomaly and change detection settings, even when the sparsity structure of the precision matrix estimate is misspecified. We also demonstrate its ability to correctly detect faulty time-periods of a pump within the motivating application.