Small-Sample Thermal Fault Diagnosis Using Knowledge Graph and Generative Adversarial Networks

Abstract excerpt

The scarcity of fault samples significantly impedes the generalization of data-driven diagnosis models for local thermal imbalances in integrated energy systems. To overcome this limitation, this paper proposes a novel knowledge graph-guided conditional generative adversarial network (KG-GAN) framework. The approach begins by constructing a dynamically updatable fault knowledge graph for district heating systems,...

Topics

Open a Topic to create a Post that cites this publication.

• Deep Learning
• Phenotype
• Reproducibility of Results
• Research Design

Identifiers and source

Literature Corpus work

d473612f-8289-5e67-93f4-bf43bc416d5b

DOI

10.20944/preprints202511.1670.v1