Cross-talk based multi-task learning for fault classification of machine system influenced by multiple variables

TL;DR

This paper introduces a cross-talk based multi-task learning framework that effectively classifies machine faults while accounting for variables influencing signals, outperforming traditional methods on drone and motor fault datasets.

Contribution

It proposes a novel cross-talk multi-task learning architecture that controls information exchange between tasks, improving fault classification accuracy in variable-influenced signals.

Findings

Outperforms single-task and shared trunk multi-task models.

Effective on drone fault and motor fault datasets.

Handles multiple influencing variables simultaneously.

Abstract

Machine systems inherently generate signals in which fault conditions and various variables influence signals measured from machine system. Although many existing fault classification studies rely solely on direct fault labels, the aforementioned signals naturally embed additional information shaped by other variables. Herein, we leverage this through a multi-task learning (MTL) framework that jointly learns fault conditions and other variables influencing measured signals. Among MTL architectures, cross-talk structures have distinct advantages because they allow for controlled information exchange between tasks through the cross-talk layer while preventing negative transfer, in contrast to shared trunk architectures that often mix incompatible features. We build on our previously introduced residual neural dimension reductor model, and extend its application to two benchmarks where system influenced by multiple variables. The first benchmark is a drone fault dataset, in which machine type and maneuvering direction significantly alter the frequency components of measured signals even under the same drone status. The second benchmark dataset is motor compound fault dataset. In this system, severity of each fault component, inner race fault, outer race fault, misalignment, and unbalance influences measured signal. Across both benchmarks, our residual neural dimension reductor, consistently outperformed single-task models, multi-class models that merge all label combinations, and shared trunk multi-task models.