Concept Drift Detection with Variable Interaction Networks

TL;DR

This paper introduces a sliding window algorithm to detect changes in variable interactions within production plants, aiding early fault detection for predictive maintenance using machine learning models.

Contribution

It presents a novel variable interaction change detection algorithm based on sliding windows, tailored for monitoring complex production systems.

Findings

Effective detection of interaction changes in synthetic systems

Ability to identify early signs of system drift

Demonstrated potential for predictive maintenance applications

Abstract

The current development of today's production industry towards seamless sensor-based monitoring is paving the way for concepts such as Predictive Maintenance. By this means, the condition of plants and products in future production lines will be continuously analyzed with the objective to predict any kind of breakdown and trigger preventing actions proactively. Such ambitious predictions are commonly performed with support of machine learning algorithms. In this work, we utilize these algorithms to model complex systems, such as production plants, by focusing on their variable interactions. The core of this contribution is a sliding window based algorithm, designed to detect changes of the identified interactions, which might indicate beginning malfunctions in the context of a monitored production plant. Besides a detailed description of the algorithm, we present results from experiments with a synthetic dynamical system, simulating stable and drifting system behavior.