Graph Neural Networks With Trainable Adjacency Matrices for Fault Diagnosis on Multivariate Sensor Data
Open Access
- 15 October 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 152860-152872
Abstract
Timely detection and accurate diagnosis of faults in technological processes can significantly reduce production costs in manufacturing. Modern industrial equipment, equipped with numerous sensors, generates vast amounts of data, providing opportunities for advanced fault detection and diagnosis. While convolutional and recurrent neural networks have achieved state-of-the-art performance, they often overlook the correlations and hidden relationships among sensor signals. To address this, we propose a graph neural network (GNN) architecture that constructs graphs of sensor relationships from data. We evaluated five methods for training different types of adjacency matrices allowing to set certain restrictions on the structure of the graph. The resulting graph structures were analyzed and potential for their use in transfer learning was evaluated. Additionally, we developed an architecture that uses multiple adjacency matrices, which reduces the number of trainable parameters while maintaining high prediction quality. Our models demonstrated state-of-the-art performance on the Tennessee Eastman Process dataset, showcasing their potential for fault diagnosis on multivariate sensor data.Keywords
Funding Information
- Analytical Center for the Government of the Russian Federation (70-2021-00142)
This publication has 61 references indexed in Scilit:
- Electric Vehicle Battery State of Charge Prediction Based on Graph Convolutional NetworkInternational Journal of Automotive Technology, 2023
- Community Detection Based on the Nodes Role in a Network: The Telegram Platform Case2021
- A process fault diagnosis method using multi‐time scale dynamic feature extraction based on convolutional neural networkThe Canadian Journal of Chemical Engineering, 2020
- Link Prediction Regression for Weighted Co-authorship NetworksLecture Notes in Computer Science, 2019
- Co-authorship Network Embedding and Recommending Collaborators via Network Embedding2018
- Modelling of Technical Systems2013
- Canonical Variate Analysis2000
- Partial Least Squares2000
- Principal Component Analysis2000
- Knowledge-Based Fault Diagnosis of Technological Systems1995