Evaluation of Pad-Clearance at Lift-off based on Image Recognition Technology
JAXA Supercomputer System Annual Report February 2022-January 2023
Report Number: R22EEK20201
Subject Category: Space Technology
- Responsible Representative: Space Transportation Technology Derectorate, Kagoshima Space Center, Range Technology Development Unit, Yoshinori Sunasaka
- Contact Information: Space Transportation Technology Derectorate, Kagoshima Space Center, Range Technology Development Unit, Yukari Sakano(sakano.yukari@jaxa.jp)
- Members: Yukari Sakano
Abstract
It is important to acquire a behavior of a rocket after lift-off. This is because, this behavior is relevant to a clearance between the rocket and ground equipment, acoustic environment and acquisitions of positioning satellites. However, since avionics used in flight, for example pisitioning satellite tracking devices or on bord acceleration sensor, is indirect evaluation and include errors in measurement, their accuracies can be further improved. If the new system for measuring a rocket’s position, velocity and attitude independently and accurately is developed, direct evaluation is realized, and it can contribute to the operation or designing of these avionics. Therefore, as the first step of this development, we aimed to measure the pad clearance, which is the distance between a rocket and a launcher, by analyzing image data taken from near the launch pad.
Reference URL
N/A
Reasons and benefits of using JAXA Supercomputer System
In order to calculate the pad clearance, calculations with two steps are required: 1) Detection of a rocket from image, 2) Acquisition of the three-dimensional position of the rocket. The deep learning model is applied to the former calculation and JAXA Supercomputer System is applied to the training of the model. As a result, large scale calculation of image processing can be conducted rapidly, and the whole processes of the measurement can work efficiently.
Achievements of the Year
By inputting image data, which is taken from near the launch pad, into the image recognition model trained by JAXA Supercomputer System, we successfully detect the serial three-dimensional positions of a rocket as shown in Fig,1. Moreover, by integrating two positional data at different position at the same time, we also success to measure height (for verification of this method, Fig.2) and pad clearance (the aim of this project, Fig. 3) quantitively and got reasonable values. On the other hand, we also recognized some problems, for example detection accuracy in very high or very low positions, vibration of cameras and lack of data, throughout this project, and we are going to improve this method based on these points in future.
Publications
N/A
Usage of JSS
Computational Information
- Process Parallelization Methods: N/A
- Thread Parallelization Methods: N/A
- Number of Processes: 1
- Elapsed Time per Case: 2 Hour(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 | 285.67 | 0.00 |
TOKI-GP | 8.52 | 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 | 2.50 | 0.00 |
/data and /data2 | 1625.00 | 0.01 |
/ssd | 25.00 | 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 2022-January 2023