Cross-talk based multi-task learning for fault classification of physically coupled machine system

2026-02-05

AI Summary

This work addresses the challenge of diagnosing faults in physically coupled mechanical systems, where fault signals are intricately entangled with multiple physical variables, rendering conventional classification methods—relying solely on fault labels—ineffective at leveraging such coupling information. To overcome this limitation, the authors propose a multi-task learning framework built upon a cross-talk architecture that jointly models fault categories and associated physical variables. This design facilitates beneficial information sharing across tasks while preserving task-specific features, thereby mitigating negative transfer. Integrated with a residual neural dimensionality reduction module, the framework accommodates both single- and multi-channel inputs, making it suitable for complex fault scenarios such as those involving drones and motors. Experimental results on two benchmark datasets demonstrate consistent and significant performance gains over single-task, label-merged, and shared-backbone multi-task baselines, confirming the method’s effectiveness and robustness.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Machine systems inherently generate signals in which fault conditions and various physical variables are physically coupled. Although many existing fault classification studies rely solely on direct fault labels, the aforementioned signals naturally embed additional information shaped by other physically coupled information. Herein, we leverage this coupling through a multi-task learning (MTL) framework that jointly learns fault conditions and the related physical variables. Among MTL architectures, crosstalk 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 physical coupling is prominent. 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 nominal condition. By learning fault classification together with these physical attributes, the cross-talk architecture can better classify faults. The second benchmark dataset is the motor compound fault dataset. In this system, each fault component, inner race fault, outer race fault, misalignment, and unbalance is coupled to the other. For motor compound fault, we also test classification performance when we use single-channel data or multi-channel data as input to the classifier. 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.

Problem

• fault classification
• physically coupled systems
• multi-task learning
• cross-talk
• machine fault diagnosis

Innovation

• cross-talk multi-task learning
• physical coupling
• fault classification
• residual neural dimension reductor
• negative transfer prevention