PDF
Full
Outline
In flow experiments, it is often necessary to measure the flow time history at several locations. However, the number of sensors in the experiment is limited by sensor size and their interference with flow. By optimizing sensor placement, the testing efficiency and accuracy can be improved with more significant time-varying features being captured. Using a time history deep learning method, the study carries out the dimensionality reduction and clustering on the flows of the time-varying features, obtaining distribution of measurement points distributions with similar features. This provides a basis for optimal sensor placement. As an example, the low Reynolds number flow around a square and a circular cylinder was studied respectively. Firstly, dimensionality reduction and feature reconstruction was performed on the flow's time-varying big data. Next, clustering analysis was applied to the low-dimensional latent code, followed by feature judgment across different flow regions, yielding the optimal sensor arrangement for the physical quantities to be measured. The results show that the method in this paper obtains a more refined layout of sensors compared with traditional empirical approaches, providing a useful reference for flow experiments.
PDF
112
47
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |
关闭全屏
No. 86 Xueyuan South Road, Haidian District, Beijing
010-62199257
qkjq@cast.org.cn
Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House
