Multi-output Classification Framework and Frequency Layer Normalization for Compound Fault Diagnosis in Motor

2025-04-15

AI Summary

This work addresses the cross-domain fault diagnosis challenge for rotating machinery—particularly electric motors—under concurrent partial-label target domains and compound faults. We propose an interpretable multi-output classification framework that decouples compound faults into independent severity estimates for each constituent fault type. Methodologically, we introduce Frequency-layer Normalization (FLN), a novel normalization technique preserving dynamics-relevant, stable spectral structures; further, we jointly employ multi-kernel Maximum Mean Discrepancy (MK-MMD) and entropy minimization to achieve robust domain adaptation. Experiments on six partial-label domain adaptation tasks demonstrate that our approach significantly outperforms baselines in macro-F1 score, improves single-fault identification accuracy, and exhibits superior generalizability of FLN over conventional normalization strategies such as Batch Normalization (BN) and Layer Normalization (LN).

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Natural Language Processing: Safety and Robustness
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

Abstract

This work introduces a multi-output classification (MOC) framework designed for domain adaptation in fault diagnosis, particularly under partially labeled (PL) target domain scenarios and compound fault conditions in rotating machinery. Unlike traditional multi-class classification (MCC) methods that treat each fault combination as a distinct class, the proposed approach independently estimates the severity of each fault type, improving both interpretability and diagnostic accuracy. The model incorporates multi-kernel maximum mean discrepancy (MK-MMD) and entropy minimization (EM) losses to facilitate feature transfer from the source to the target domain. In addition, frequency layer normalization (FLN) is applied to preserve structural properties in the frequency domain, which are strongly influenced by system dynamics and are often stationary with respect to changes in rpm. Evaluations across six domain adaptation cases with PL data demonstrate that MOC outperforms baseline models in macro F1 score. Moreover, MOC consistently achieves better classification performance for individual fault types, and FLN shows superior adaptability compared to other normalization techniques.

Problem

• Develops MOC framework for compound fault diagnosis in motors
• Addresses partially labeled target domain scenarios effectively
• Improves interpretability and accuracy in fault severity estimation

Innovation

• Multi-output classification for independent fault severity estimation
• MK-MMD and EM losses for effective feature transfer
• Frequency layer normalization preserves frequency domain properties