Explainable Anomaly Detection for Industrial IoT Data Streams

TL;DR

This paper introduces a real-time, interactive anomaly detection framework for industrial IoT data streams that combines unsupervised methods with human-in-the-loop learning to improve maintenance decision-making.

Contribution

It presents a novel collaborative DSM approach integrating unsupervised anomaly detection with interpretability tools and human feedback for industrial IoT data streams.

Findings

Effective real-time fault detection demonstrated on a Jacquard loom

Enhanced interpretability through incremental Partial Dependence Plots

Framework supports dynamic feature relevance reassessment

Abstract

Industrial maintenance is being transformed by the Internet of Things and edge computing, generating continuous data streams that demand real-time, adaptive decision-making under limited computational resources. While data stream mining (DSM) addresses this challenge, most methods assume fully supervised settings, yet in practice, ground-truth labels are often delayed or unavailable. This paper presents a collaborative DSM framework that integrates unsupervised anomaly detection with interactive, human-in-the-loop learning to support maintenance decisions. We employ an online Isolation Forest and enhance interpretability using incremental Partial Dependence Plots and a feature importance score, derived from deviations of Individual Conditional Expectation curves from a fading average, enabling users to dynamically reassess feature relevance and adjust anomaly thresholds. We describe the real-time implementation and provide initial results for fault detection in a Jacquard loom unit. Ongoing work targets continuous monitoring to predict and explain imminent bearing failures.