Open Access

ARTICLE

A Causal-Transformer Based Meta-Learning Method for Few-Shot Fault Diagnosis in CNC Machine Tool Bearings

Youlong Lyu^1,2,*, Ying Chu³, Qingpeng Qiu³, Jie Zhang^1,2, Jutao Guo⁴

1 Institute of Artificial Intelligence, Donghua University, Shanghai, 201620, China
2 Shanghai Engineering Research Center of Industrial Big Data and Intelligent System, Shanghai, 201620, China
3 College of Information Science and Technology, Donghua University, Shanghai, 201620, China
4 Shanghai Spaceflight Precision Machinery Institute, No. 388 Chuanda Road, Minhang District, Shanghai, 201109, China

* Corresponding Author: Youlong Lyu. Email:

(This article belongs to the Special Issue: Advancements in Machine Fault Diagnosis and Prognosis: Data-Driven Approaches and Autonomous Systems)

Computers, Materials & Continua 2025, 85(2), 3393-3418. https://doi.org/10.32604/cmc.2025.068157

Received 22 May 2025; Accepted 09 July 2025; Issue published 23 September 2025

Abstract

In intelligent manufacturing processes such as aerospace production, computer numerical control (CNC) machine tools require real-time optimization of process parameters to meet precision machining demands. These dynamic operating conditions increase the risk of fatigue damage in CNC machine tool bearings, highlighting the urgent demand for rapid and accurate fault diagnosis methods that can maintain production efficiency and extend equipment uptime. However, varying conditions induce feature distribution shifts, and scarce fault samples limit model generalization. Therefore, this paper proposes a causal-Transformer-based meta-learning (CTML) method for bearing fault diagnosis in CNC machine tools, comprising three core modules: (1) the original bearing signal is transformed into a multi-scale time-frequency feature space using continuous wavelet transform; (2) a causal-Transformer architecture is designed to achieve feature extraction and fault classification based on the physical causal law of fault propagation; (3) the above mechanisms are integrated into a model-agnostic meta-learning (MAML) framework to achieve rapid cross-condition adaptation through an adaptive gradient pruning strategy. Experimental results using the multiple bearing dataset show that under few-shot cross-condition scenarios (3-way 1-shot and 3-way 5-shot), the proposed CTML outperforms benchmark models (e.g., Transformer, domain adversarial neural networks (DANN), and MAML) in terms of classification accuracy and sensitivity to operating conditions, while maintaining a moderate level of model complexity.

---

Keywords

---