RmGPT: Rotating Machinery Generative Pretrained Model

2024-09-26

arXiv.org

AI Summary

Rotating machinery fault diagnosis and remaining useful life (RUL) prediction suffer from poor cross-operating-condition generalization, model task specificity, and limited adaptability to scarce labeled data. To address these challenges, this paper introduces the first generative pre-trained foundation model tailored for rotating machinery. We propose a novel signal tokenization framework that jointly encodes raw time-series signals, time-frequency features, fault categories, and task-specific prompts as unified tokens. The model is pre-trained via a self-supervised next-signal-token prediction objective, enabling prompt-based fine-tuning and few-shot transfer. Evaluated on 16 fault types, the model achieves 92% accuracy in single-shot diagnosis and near-perfect overall diagnostic accuracy. RUL prediction error significantly outperforms state-of-the-art methods. Moreover, it demonstrates exceptional robustness and generalization across multi-source heterogeneous datasets and varying operating conditions.

Technology Category

• Machine Learning: Other Foundations of Machine Learning
• Natural Language Processing: Generation
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

In industry, the reliability of rotating machinery is critical for production efficiency and safety. Current methods of Prognostics and Health Management (PHM) often rely on task-specific models, which face significant challenges in handling diverse datasets with varying signal characteristics, fault modes and operating conditions. Inspired by advancements in generative pretrained models, we propose RmGPT, a unified model for diagnosis and prognosis tasks. RmGPT introduces a novel token-based framework, incorporating Signal Tokens, Prompt Tokens, Time-Frequency Task Tokens and Fault Tokens to handle heterogeneous data within a unified model architecture. We leverage self-supervised learning for robust feature extraction and introduce a next signal token prediction pretraining strategy, alongside efficient prompt learning for task-specific adaptation. Extensive experiments demonstrate that RmGPT significantly outperforms state-of-the-art algorithms, achieving near-perfect accuracy in diagnosis tasks and exceptionally low errors in prognosis tasks. Notably, RmGPT excels in few-shot learning scenarios, achieving 92% accuracy in 16-class one-shot experiments, highlighting its adaptability and robustness. This work establishes RmGPT as a powerful PHM foundation model for rotating machinery, advancing the scalability and generalizability of PHM solutions.

Problem

• Handling diverse datasets with varying signal characteristics and fault modes
• Unified model for diagnosis and prognosis tasks in rotating machinery
• Improving accuracy and adaptability in few-shot learning scenarios

Innovation

• Generative token-based framework for unified tasks
• Self-supervised learning for robust feature extraction
• Next signal token prediction pretraining strategy