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

2025-07-13

AI Summary

To address insufficient prediction accuracy for Remaining Useful Life (RUL) and State of Health (SOH) in industrial systems, this paper proposes a dynamic weighted Graph Neural Network (GNN) framework integrating physics-informed constraints with spatiotemporal feature learning. Methodologically, it introduces a Q-learning-driven dynamic weighting mechanism to adaptively balance physics-based loss terms and incorporates a Soft Actor-Critic (SAC) reinforcement learning module to optimize spatiotemporal attention representations—enabling automatic focus on multi-region physical constraints and end-to-end training. The architecture unifies graph convolutional recurrent networks, graph attention convolutions, temporal attention units, and Physics-Informed Neural Networks (PINNs). Evaluated on three representative industrial benchmark datasets, the model achieves statistically significant improvements in both RUL and SOH prediction accuracy over state-of-the-art methods, while demonstrating enhanced robustness and cross-scenario generalization capability.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• Accurate RUL and SOH estimation for industrial PHM applications
• Combining physics-based supervision with spatio-temporal learning
• Dynamic weighting of physics-informed loss terms for generalization

Innovation

• Reinforced Graph-Based Physics-Informed Neural Networks
• Graph Attention Convolution for adaptive spatial aggregation
• Soft Actor-Critic module enhances spatio-temporal learning