Multivariate Industrial Time Series with Cyber-Attack Simulation: Fault Detection Using an LSTM-based Predictive Data Model

TL;DR

This paper presents an LSTM-based predictive model for fault detection in multivariate industrial time series, validated with a simulated gasoil plant model and fault injection, achieving high precision and recall.

Contribution

It introduces a novel fault detection approach using LSTM neural networks combined with a simulated fault injection framework for industrial data.

Findings

LSTM model effectively detects faults with high accuracy.

Fault detection performance depends on the chosen threshold.

Filtering mechanisms improve fault relevance to operators.

Abstract

We adopted an approach based on an LSTM neural network to monitor and detect faults in industrial multivariate time series data. To validate the approach we created a Modelica model of part of a real gasoil plant. By introducing hacks into the logic of the Modelica model, we were able to generate both the roots and causes of fault behavior in the plant. Having a self-consistent data set with labeled faults, we used an LSTM architecture with a forecasting error threshold to obtain precision and recall quality metrics. The dependency of the quality metric on the threshold level is considered. An appropriate mechanism such as "one handle" was introduced for filtering faults that are outside of the plant operator field of interest.