Generative Design of a Gas Turbine Combustor Using Invertible Neural Networks

2026-04-27

AI Summary

This work addresses the challenge of achieving low-NOx premixed combustion of 100% hydrogen in high-efficiency gas turbines across a range of 4–600 MW units, which requires extensive combustor redesign to mitigate flashback and ensure stability—tasks traditionally hindered by prohibitively high iterative costs. For the first time, invertible neural networks (INNs) are introduced into generative combustor design for gas turbines. Trained on parametric geometry models and CFD simulation data, the INN framework enables inverse inference to directly map target performance specifications to feasible geometric configurations. The approach facilitates cross-platform knowledge transfer and efficiently generates multiple designs meeting stringent performance criteria, substantially shortening development cycles. This study demonstrates the feasibility and transformative potential of AI-driven generative design in complex energy systems.

Technology Category

• Natural Language Processing: Generation
• Search and Optimization: Learning to Search
• Machine Learning: Deep Neural Architectures and Foundation Models

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

The need to burn 100% H2 in high efficient gas turbines featuring low NOx combustion in premix mode require the complete redesign of the combustion system to ensure stable operation without any flashback. Since all engine frames featuring a power range from 4 MW up to 600 MW are affected, a huge design effort is expected. To reduce this effort, especially to transfer knowledge between the different engine classes, generative design methods using latest AI technology will provide promising potential. In this work, this challenge is approached utilizing the current advances in generative artificial intelligence. We train an Invertible Neural Network (INN) on an expandable database of geometrically parameterized combustor designs with simulated performance labels. Utilizing the INN in its inverse direction, multiple design proposals are generated which fulfill specified performance labels.

Problem

• hydrogen combustion
• gas turbine combustor
• low NOx
• flashback prevention
• generative design

Innovation

• Invertible Neural Networks
• Generative Design
• Hydrogen Combustion
• Gas Turbine Combustor
• Low NOx