EdgeFD: An Edge-Friendly Drift-Aware Fault Diagnosis System for Industrial IoT

TL;DR

This paper introduces DAWC, a novel method for industrial fault diagnosis that effectively manages data drift on resource-limited edge devices, reducing the need for frequent model fine-tuning and enhancing generalization.

Contribution

The paper proposes DAWC, a drift-aware continual learning approach optimized for edge deployment, addressing data drift without extensive fine-tuning in industrial IoT fault diagnosis.

Findings

DAWC outperforms existing methods in fault diagnosis accuracy.

It reduces computational costs by minimizing fine-tuning.

The system effectively detects and adapts to data drift in real-time.

Abstract

Recent transfer learning (TL) approaches in industrial intelligent fault diagnosis (FD) mostly follow the "pre-train and fine-tuning" paradigm to address data drift, which emerges from variable working conditions. However, we find that this approach is prone to the phenomenon known as catastrophic forgetting. Furthermore, performing frequent models fine-tuning on the resource-constrained edge nodes can be computationally expensive and unnecessary, given the excellent transferability demonstrated by existing models. In this work, we propose the Drift-Aware Weight Consolidation (DAWC), a method optimized for edge deployments, mitigating the challenges posed by frequent data drift in the industrial Internet of Things (IIoT). DAWC efficiently manages multiple data drift scenarios, minimizing the need for constant model fine-tuning on edge devices, thereby conserving computational resources. By detecting drift using classifier confidence and estimating parameter importance with the Fisher Information Matrix, a tool that measures parameter sensitivity in probabilistic models, we introduce a drift detection module and a continual learning module to gradually equip the FD model with powerful generalization capabilities. Experimental results demonstrate that our proposed DAWC achieves superior performance compared to existing techniques while also ensuring compatibility with edge computing constraints. Additionally, we have developed a comprehensive diagnosis and visualization platform.