Hypergraph Contrastive Sensor Fusion for Multimodal Fault Diagnosis in Induction Motors

2025-10-17

AI Summary

To address challenges in induction motor multi-fault (bearing/stator/rotor) diagnosis—including difficulty in multimodal signal modeling, poor noise robustness, and weak cross-domain generalization—this paper proposes the Multimodal Hypergraph Contrastive Attention Network (MHCA-Net). MHCA-Net is the first to embed contrastive learning into hypergraph topology, enabling unified modeling of intra- and inter-modal high-order dependencies while overcoming limitations of Euclidean-space representations. By integrating hypergraph neural networks, attention mechanisms, and multimodal feature alignment, it achieves end-to-end non-Euclidean signal correlation modeling and robust feature enhancement. Evaluated on three real-world benchmark datasets, MHCA-Net achieves 99.82% classification accuracy, significantly outperforming state-of-the-art methods. Ablation studies confirm the effectiveness of each component, demonstrating strong cross-domain generalization and noise resilience—making it suitable for industrial deployment.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Reliable induction motor (IM) fault diagnosis is vital for industrial safety and operational continuity, mitigating costly unplanned downtime. Conventional approaches often struggle to capture complex multimodal signal relationships, are constrained to unimodal data or single fault types, and exhibit performance degradation under noisy or cross-domain conditions. This paper proposes the Multimodal Hypergraph Contrastive Attention Network (MM-HCAN), a unified framework for robust fault diagnosis. To the best of our knowledge, MM-HCAN is the first to integrate contrastive learning within a hypergraph topology specifically designed for multimodal sensor fusion, enabling the joint modelling of intra- and inter-modal dependencies and enhancing generalisation beyond Euclidean embedding spaces. The model facilitates simultaneous diagnosis of bearing, stator, and rotor faults, addressing the engineering need for consolidated di- agnostic capabilities. Evaluated on three real-world benchmarks, MM-HCAN achieves up to 99.82% accuracy with strong cross-domain generalisation and resilience to noise, demonstrating its suitability for real-world deployment. An ablation study validates the contribution of each component. MM-HCAN provides a scalable and robust solution for comprehensive multi-fault diagnosis, supporting predictive maintenance and extended asset longevity in industrial environments.

Problem

• Capturing complex multimodal signal relationships in fault diagnosis
• Diagnosing multiple fault types simultaneously in induction motors
• Enhancing robustness under noisy or cross-domain operating conditions

Innovation

• Hypergraph contrastive learning for multimodal sensor fusion
• Joint modeling of intra- and inter-modal dependencies
• Simultaneous diagnosis of multiple motor fault types