# Explainable Dynamic Graph Learning and Multi-Scale Feature Fusion for Hydraulic System Health Monitoring

## TL;DR

This paper introduces a new neural network for monitoring hydraulic system health by learning dynamic sensor relationships and multi-scale features, achieving high diagnostic accuracy.

## Contribution

The novel Dynamic Multi-Scale Graph Neural Network (DMS-GNN) combines adaptive graph learning with multi-scale feature extraction for hydraulic fault diagnosis.

## Key findings

- DMS-GNN achieved 98.47% diagnostic accuracy on an electro-hydraulic test bench.
- The model outperformed existing methods like GraphSAGE, Static GCN, and GAT.
- Dynamic graph learning and multi-scale feature fusion improved robustness in sensor fusion.

## Abstract

Hydraulic systems are pivotal components in safety-critical aerospace and industrial applications, making reliable health monitoring essential. However, traditional data-driven diagnosis methods typically rely on static graph structures that fail to capture evolving sensor correlations during different fault modes. Furthermore, existing grid-based models often struggle to extract multi-resolution features and maintain performance under data-limited conditions. To address these challenges, this paper proposes a novel Dynamic Multi-Scale Graph Neural Network (DMS-GNN) for hydraulic system fault diagnosis. The framework integrates a hierarchical multi-scale feature extraction module to capture diverse fault signatures across different frequency bands. Crucially, a self-attention-based dynamic graph learner is introduced to adaptively infer latent sensor topologies end-to-end, eliminating the reliance on predefined physical connections. Experimental validation on a dedicated electro-hydraulic test bench demonstrates that the proposed DMS-GNN achieves a superior diagnostic accuracy of 98.47%, outperforming state-of-the-art baselines such as GraphSAGE, Static GCN, and GAT. The result confirms the efficacy of combining multi-scale temporal learning with dynamic spatial reasoning for robust multi-sensor fusion diagnosis.