Meta-Learning and Knowledge Discovery based Physics-Informed Neural Network for Remaining Useful Life Prediction

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Yu, Liu, Shujie, Lv, Shuai, Liu, Gengshuo
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917990147031040
author Wang, Yu
Liu, Shujie
Lv, Shuai
Liu, Gengshuo
author_facet Wang, Yu
Liu, Shujie
Lv, Shuai
Liu, Gengshuo
contents Predicting the remaining useful life (RUL) of rotating machinery is critical for industrial safety and maintenance, but existing methods struggle with scarce target-domain data and unclear degradation dynamics. We propose a Meta-Learning and Knowledge Discovery-based Physics-Informed Neural Network (MKDPINN) to address these challenges. The method first maps noisy sensor data to a low-dimensional hidden state space via a Hidden State Mapper (HSM). A Physics-Guided Regulator (PGR) then learns unknown nonlinear PDEs governing degradation evolution, embedding these physical constraints into the PINN framework. This integrates data-driven and physics-based approaches. The framework uses meta-learning, optimizing across source-domain meta-tasks to enable few-shot adaptation to new target tasks. Experiments on industrial data and the C-MAPSS benchmark show MKDPINN outperforms baselines in generalization and accuracy, proving its effectiveness for RUL prediction under data scarcity
format Preprint
id arxiv_https___arxiv_org_abs_2504_13797
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Meta-Learning and Knowledge Discovery based Physics-Informed Neural Network for Remaining Useful Life Prediction
Wang, Yu
Liu, Shujie
Lv, Shuai
Liu, Gengshuo
Machine Learning
Artificial Intelligence
Predicting the remaining useful life (RUL) of rotating machinery is critical for industrial safety and maintenance, but existing methods struggle with scarce target-domain data and unclear degradation dynamics. We propose a Meta-Learning and Knowledge Discovery-based Physics-Informed Neural Network (MKDPINN) to address these challenges. The method first maps noisy sensor data to a low-dimensional hidden state space via a Hidden State Mapper (HSM). A Physics-Guided Regulator (PGR) then learns unknown nonlinear PDEs governing degradation evolution, embedding these physical constraints into the PINN framework. This integrates data-driven and physics-based approaches. The framework uses meta-learning, optimizing across source-domain meta-tasks to enable few-shot adaptation to new target tasks. Experiments on industrial data and the C-MAPSS benchmark show MKDPINN outperforms baselines in generalization and accuracy, proving its effectiveness for RUL prediction under data scarcity
title Meta-Learning and Knowledge Discovery based Physics-Informed Neural Network for Remaining Useful Life Prediction
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2504.13797