Toward accurate RUL and SOH estimation using reinforced graph-based PINNs enhanced with dynamic weights

TL;DR

This paper introduces RGPD, a novel physics-informed neural network framework that combines graph-based learning, attention mechanisms, and reinforcement learning to improve RUL and SOH estimation accuracy in industrial systems.

Contribution

It presents a new integrated approach that dynamically weights physics constraints and captures spatio-temporal dependencies for more accurate prognostics.

Findings

Outperforms state-of-the-art models in RUL and SOH estimation.

Demonstrates robustness across diverse industrial datasets.

Reduces manual tuning through reinforcement learning-based dynamic weighting.

Abstract

Accurate estimation of Remaining Useful Life (RUL) and State of Health (SOH) is essential for Prognostics and Health Management (PHM) across a wide range of industrial applications. We propose a novel framework -- Reinforced Graph-Based Physics-Informed Neural Networks Enhanced with Dynamic Weights (RGPD) -- that combines physics-based supervision with advanced spatio-temporal learning. Graph Convolutional Recurrent Networks (GCRNs) embed graph-convolutional filters within recurrent units to capture how node representations evolve over time. Graph Attention Convolution (GATConv) leverages a self-attention mechanism to compute learnable, edge-wise attention coefficients, dynamically weighting neighbor contributions for adaptive spatial aggregation. A Soft Actor-Critic (SAC) module is positioned between the Temporal Attention Unit (TAU) and GCRN to further improve the spatio-temporal learning. This module improves attention and prediction accuracy by dynamically scaling hidden representations to minimize noise and highlight informative features. To identify the most relevant physical constraints in each area, Q-learning agents dynamically assign weights to physics-informed loss terms, improving generalization across real-time industrial systems and reducing the need for manual tuning. In both RUL and SOH estimation tasks, the proposed method consistently outperforms state-of-the-art models, demonstrating strong robustness and predictive accuracy across varied degradation patterns across three diverse industrial benchmark datasets.