AeroGPT: Leveraging Large-Scale Audio Model for Aero-Engine Bearing Fault Diagnosis

2025-06-19

AI Summary

To address the lack of interpretability and reliance on post-hoc processing in deep learning–based fault diagnosis of aero-engine bearings—and the underutilization of cross-modal large models—this paper pioneers the adaptation of general-purpose audio foundation models (e.g., AudioMAE and Whisper variants) to vibration signal analysis. We propose a Vibration Signal Alignment (VSA) mechanism to enable audio–vibration cross-modal knowledge transfer, design a generative fault classification (GFC) head for end-to-end, interpretable fault label generation without thresholding or post-processing, and integrate time-frequency alignment, prompt-based fine-tuning, and multi-scale feature fusion. Evaluated on the DIRG and HIT datasets, our method achieves 98.94% and 100% classification accuracy, respectively—significantly outperforming CNN, LSTM, and Transformer baselines. Interpretability and industrial applicability are further validated through visualization and case studies.

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: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Aerospace engines, as critical components in aviation and aerospace industries, require continuous and accurate fault diagnosis to ensure operational safety and prevent catastrophic failures. While deep learning techniques have been extensively studied in this context, they output logits or confidence scores, necessitating post-processing to derive actionable insights. Furthermore, the potential of large-scale audio models in this domain remains largely untapped. To address these limitations, this paper proposes AeroGPT, a novel framework that transfers knowledge from general audio domain to aero-engine bearing fault diagnosis. AeroGPT is a framework based on large-scale audio model that incorporates Vibration Signal Alignment (VSA) to adapt general audio knowledge to domain-specific vibration patterns, and combines Generative Fault Classification (GFC) to directly output interpretable fault labels. This approach eliminates the need for post-processing of fault labels, supports interactive, interpretable, and actionable fault diagnosis, thereby greatly enhancing industrial applicability. Through comprehensive experimental validation on two aero-engine bearing datasets, AeroGPT achieved exceptional performance with 98.94% accuracy on the DIRG dataset and perfect 100% classification on the HIT bearing dataset, surpassing traditional deep learning approaches. Additional Qualitative analysis validates the effectiveness of our approach and highlights the potential of large-scale models to revolutionize fault diagnosis.

Problem

• Enhancing aero-engine bearing fault diagnosis accuracy
• Eliminating post-processing for interpretable fault labels
• Leveraging large-scale audio models for vibration analysis

Innovation

• Transfers general audio knowledge to vibration patterns
• Uses Vibration Signal Alignment for domain adaptation
• Generative Fault Classification outputs interpretable labels directly