Early detection of combustion oscillations using machine learning
JAXA Supercomputer System Annual Report February 2025-January 2026
Report Number: R25EDA201C17
Subject Category: Aeronautical Technology
- Responsible Representative: Atsushi Kanda, Aviation Technology Directorate, Aviation Enviromental Sustanability Innovation Hub
- Contact Information: Seiji Yoshida, Aviation Technology Directorate, Aviation Environmental Sustainability Innovation Hub(yoshida.seiji@jaxa.jp)
- Members: YOSHIDA Seiji
Abstract
Lean‑premixed jet‑engine combustors are susceptible to combustion instability. Because the occurrence of combustion instability can damage the combustor and other engine components, the development of technologies to suppress its onset is essential. This study aims to develop a machine‑learning‑based technique that enables early detection of combustion instability and adjustment of engine operating conditions before pressure oscillations grow, thereby avoiding its occurrence.
Reference URL
N/A
Reasons and benefits of using JAXA Supercomputer System
Building machine‑learning models requires optimizing a large number of parameters and therefore necessitates large‑scale computational resources. Moreover, because GPUs can substantially accelerate these optimization calculations, we will employ JSS3 (TOKI-GP).
Achievements of the Year
We conducted a trial migrating the optimization of machine-learning model parameters—previously performed on a desktop PC—to TOKI-GP. The results confirmed that high-speed computation is achievable even for large-scale machine-learning models.
Publications
N/A
Usage of JSS
Computational Information
- Process Parallelization Methods: N/A
- Thread Parallelization Methods: Automatic Parallelization
- Number of Processes: 1
- Elapsed Time per Case: 20 Minute(s)
JSS3 Resources Used
Fraction of Usage in Total Resources*1(%): 0.00
Details
Please refer to System Configuration of JSS3 for the system configuration and major specifications of JSS3.
| System Name | CPU Resources Used(Core x Hours) | Fraction of Usage*2(%) |
|---|---|---|
| TOKI-SORA | 0.00 | 0.00 |
| TOKI-ST | 0.00 | 0.00 |
| TOKI-GP | 246.95 | 0.00 |
| TOKI-XM | 0.00 | 0.00 |
| TOKI-LM | 0.00 | 0.00 |
| TOKI-TST | 0.00 | 0.00 |
| TOKI-TGP | 0.00 | 0.00 |
| TOKI-TLM | 0.00 | 0.00 |
| File System Name | Storage Assigned(GiB) | Fraction of Usage*2(%) |
|---|---|---|
| /home | 0.00 | 0.00 |
| /data and /data2 | 0.00 | 0.00 |
| /ssd | 0.00 | 0.00 |
| Archiver Name | Storage Used(TiB) | Fraction of Usage*2(%) |
|---|---|---|
| J-SPACE | 0.00 | 0.00 |
*1: Fraction of Usage in Total Resources: Weighted average of three resource types (Computing, File System, and Archiver).
*2: Fraction of Usage：Percentage of usage relative to each resource used in one year.
ISV Software Licenses Used
| ISV Software Licenses Used(Hours) | Fraction of Usage*2(%) | |
|---|---|---|
| ISV Software Licenses(Total) | 0.00 | 0.00 |
*2: Fraction of Usage：Percentage of usage relative to each resource used in one year.
JAXA Supercomputer System Annual Report February 2025-January 2026