Skip to content

Multi-scale physics-informed reinforcement learning method for bearing fault diagnosis under data scarcity

Sep 2026 · Structural Health Monitoring · 0 citations · 25 references
Machine Fault Diagnosis Techniques

TL;DR

A novel multi-scale physics-informed neural network with enhanced reinforcement learning (MPINN-ERL) for bearing fault diagnosis under data scarcity and achieves competitive diagnostic accuracy.

Abstract

Identifying mechanical faults is crucial for maintaining stability in industrial systems. However, the lack of labeled fault data significantly undermines the accuracy and generalization of diagnostic methods in practical applications. To address this issue, this paper presents a novel multi-scale physics-informed neural network with enhanced reinforcement learning (MPINN-ERL) for bearing fault diagnosis under data scarcity. First, a multi-scale convolutional bi-directional gated recurrent unit with physics-inspired residual regularization module is developed to effectively integrate physics-inspired dynamic residual regularization into the system, thereby improving the stability of diagnostic performance. Furthermore, a conditional channel-spatial Wasserstein generative adversarial network is designed to generate augmented fault samples for alleviating the limited-sample problem. Finally, a novel loss function and an ERL algorithm are introduced to dynamically adjust the weight of physics-inspired dynamic residual regularization, thereby improving the model’s diagnostic stability when labeled data are scarce. Experimental results on the evaluated bearing fault datasets show that the proposed method achieves competitive diagnostic accuracy. Compared with several representative state-of-the-art deep learning methods, MPINN-ERL also exhibits relatively stable diagnostic performance.

Read PDF

Similar papers

Sep 2026

Physics-data coupled transfer learning for rolling bearing fault diagnosis under variable conditions

A novel cross-domain diagnosis method that deeply integrates dynamic mechanism modeling with conditional generative adversarial networks and synergizes physical interpretability with data adaptability is proposed, offering a robust solution for scenarios with limited samples and significant domain shifts.

Jian-Liang Sun, Zhi-Cong Han, Chao Ma et al. · 0 citations
Open access Sep 2026

Physics-Guided Multi-Source Representation Learning for Aero-Engine Bearing Fault Diagnosis under Data Scarcity

This paper proposes the physics-informed dual-stream contrastive diagnostic network (PIDC-Net), a unified framework resolving both difficulties through three integrated mechanisms. The fault-physics encoding stream (FPES) constructs multi-scale depth-wise separable convolutional encoders whose receptive field width...

Xiang-Di Meng, Jiang Ju, Xin Wang · 0 citations
Open access Aug 2026

GSR-enhanced sparse feature learning for bearing fault diagnosis under data scarcity

A GSR-enhanced robust sparse feature learning framework that derives stability control conditions for the GSR system, integrates a lightweight dual-branch architecture to fuse global convolutional features and local sparse spectral peak features, and constructs a Wasserstein-regularized dual-loss function to optimize t...

Xue Wen, Xue-Rui Zhang, Li-Feng Lin et al. · 0 citations
Open access Aug 2026

Bearing fault diagnosis based on a spectral-guided adaptive multi-scale convolutional network

The results show that SAMACNN outperforms both classical and advanced methods on the two datasets, demonstrating strong robustness and generalization capability in complex variable-condition measurement environments.

DaXin Li, Hong Wang, Hai Xue et al. · 0 citations
Open access Sep 2026

An Intelligent Bearing Fault Diagnosis Model with Physics-Information Fusion: Design and Interpretability Mechanism Research

A convolutional neural network model incorporating spectral physical constraints is proposed that enhances the spectral interpretability of the model’s decisions, achieving a transition from a “black box” to a “white box” and effectively improving the reliability of deep diagnostic models.

Zhen-Yang Yu, F. Shao, Qian Xu et al. · 0 citations
Conference Aug 2026

Application of Feature Fusion-Driven Physics-Informed Neural Network in Remaining Useful Life Prediction

Addressing the issues of traditional data-driven methods lacking interpretability and physics-informed neural network (PINN) being susceptible to noise due to statistical feature inputs, this paper proposes a feature fusion-based physics-informed neural network method for predicting the remaining useful life (RUL) of b...

Chao-Ge Wang, Xiang-Yin Meng, Zi-Yi Jia · 0 citations

Related blog posts

MIT News · Artificial Intelligence Nov 17, 2026

Learning the language of machine learning

By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.