Artificial-Intelligence-Controlled Flow Separation from a Longitudinal Slender Axisymmetric Body

Y. K. Song; Y. Y. Lin; D. W. Fan; Y. Zhou

doi:10.1007/978-981-97-6211-8_8

Artificial-Intelligence-Controlled Flow Separation from a Longitudinal Slender Axisymmetric Body

Y. K. Song
, Y. Y. Lin
, D. W. Fan
, Y. Zhou^*

^*Corresponding author for this work

Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The flow separation from a longitudinal slender axisymmetric body is experimentally investigated. The experimental model is a DARPA SUBOFF model with a semi-sphere after-body which is associated with flow separation. The control system employs six tangentially blowing microjets as actuators and a loadcell as the sensor to monitoring the drag force. In conventional open-loop control, the DR is found to be proportional to the total momentum coefficient C_μ of the control jets. At C_μ,ol = 3.23 × 10^–2, flow separation is completely suppressed with a pressure recovery of 71.2%, resulting in a considerable DR of 18.23%. However, the control-consumed energy exceeds the energy saved from drag reduction. To improve the control performance, an artificial intelligence (AI) control system is deployed and an unsupervised learning is conducted under an ant colony algorithm with a cost function J = C_D. The AI control achieves a DR of 19.8% at C_μ,opt = 0.79 × 10^–2 associated with a lower pressure recovery of 94.5%. The power saved from drag reduction is estimated to be 4.9 times of the control input power. The physical mechanism behind the finding is discussed.

Original language	English
Title of host publication	Fluid-Structure-Sound Interactions and Control - Proceedings of the 6th Symposium on Fluid-Structure-Sound Interactions and Control FSSIC 2023
Editors	Daegyoum Kim, Kyung Chun Kim, Yu Zhou, Lixi Huang
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	59-64
Number of pages	6
ISBN (Print)	9789819762101
DOIs	https://doi.org/10.1007/978-981-97-6211-8_8
State	Published - 2024
Externally published	Yes
Event	6th Symposium on Fluid-Structure-Sound Interactions and Control, FSSIC 2023 - Busan, Korea, Republic of Duration: 26 Aug 2023 → 30 Aug 2023

Publication series

Name	Lecture Notes in Mechanical Engineering
ISSN (Print)	2195-4356
ISSN (Electronic)	2195-4364

Conference

Conference	6th Symposium on Fluid-Structure-Sound Interactions and Control, FSSIC 2023
Country/Territory	Korea, Republic of
City	Busan
Period	26/08/23 → 30/08/23

Keywords

Axisymmetric body
Drag reduction
Flow separation control

Access to Document

10.1007/978-981-97-6211-8_8

Cite this

Song, Y. K., Lin, Y. Y., Fan, D. W., & Zhou, Y. (2024). Artificial-Intelligence-Controlled Flow Separation from a Longitudinal Slender Axisymmetric Body. In D. Kim, K. C. Kim, Y. Zhou, & L. Huang (Eds.), Fluid-Structure-Sound Interactions and Control - Proceedings of the 6th Symposium on Fluid-Structure-Sound Interactions and Control FSSIC 2023 (pp. 59-64). (Lecture Notes in Mechanical Engineering). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-97-6211-8_8

Song, Y. K. ; Lin, Y. Y. ; Fan, D. W. et al. / Artificial-Intelligence-Controlled Flow Separation from a Longitudinal Slender Axisymmetric Body. Fluid-Structure-Sound Interactions and Control - Proceedings of the 6th Symposium on Fluid-Structure-Sound Interactions and Control FSSIC 2023. editor / Daegyoum Kim ; Kyung Chun Kim ; Yu Zhou ; Lixi Huang. Springer Science and Business Media Deutschland GmbH, 2024. pp. 59-64 (Lecture Notes in Mechanical Engineering).

@inproceedings{cf95083215d0425e853ac9b240ac260d,

title = "Artificial-Intelligence-Controlled Flow Separation from a Longitudinal Slender Axisymmetric Body",

abstract = "The flow separation from a longitudinal slender axisymmetric body is experimentally investigated. The experimental model is a DARPA SUBOFF model with a semi-sphere after-body which is associated with flow separation. The control system employs six tangentially blowing microjets as actuators and a loadcell as the sensor to monitoring the drag force. In conventional open-loop control, the DR is found to be proportional to the total momentum coefficient Cμ of the control jets. At Cμ,ol = 3.23 × 10–2, flow separation is completely suppressed with a pressure recovery of 71.2\%, resulting in a considerable DR of 18.23\%. However, the control-consumed energy exceeds the energy saved from drag reduction. To improve the control performance, an artificial intelligence (AI) control system is deployed and an unsupervised learning is conducted under an ant colony algorithm with a cost function J = CD. The AI control achieves a DR of 19.8\% at Cμ,opt = 0.79 × 10–2 associated with a lower pressure recovery of 94.5\%. The power saved from drag reduction is estimated to be 4.9 times of the control input power. The physical mechanism behind the finding is discussed.",

keywords = "Axisymmetric body, Drag reduction, Flow separation control",

author = "Song, \{Y. K.\} and Lin, \{Y. Y.\} and Fan, \{D. W.\} and Y. Zhou",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.; 6th Symposium on Fluid-Structure-Sound Interactions and Control, FSSIC 2023 ; Conference date: 26-08-2023 Through 30-08-2023",

year = "2024",

doi = "10.1007/978-981-97-6211-8\_8",

language = "英语",

isbn = "9789819762101",

series = "Lecture Notes in Mechanical Engineering",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "59--64",

editor = "Daegyoum Kim and Kim, \{Kyung Chun\} and Yu Zhou and Lixi Huang",

booktitle = "Fluid-Structure-Sound Interactions and Control - Proceedings of the 6th Symposium on Fluid-Structure-Sound Interactions and Control FSSIC 2023",

address = "德国",

}

Song, YK, Lin, YY, Fan, DW & Zhou, Y 2024, Artificial-Intelligence-Controlled Flow Separation from a Longitudinal Slender Axisymmetric Body. in D Kim, KC Kim, Y Zhou & L Huang (eds), Fluid-Structure-Sound Interactions and Control - Proceedings of the 6th Symposium on Fluid-Structure-Sound Interactions and Control FSSIC 2023. Lecture Notes in Mechanical Engineering, Springer Science and Business Media Deutschland GmbH, pp. 59-64, 6th Symposium on Fluid-Structure-Sound Interactions and Control, FSSIC 2023, Busan, Korea, Republic of, 26/08/23. https://doi.org/10.1007/978-981-97-6211-8_8

Artificial-Intelligence-Controlled Flow Separation from a Longitudinal Slender Axisymmetric Body. / Song, Y. K.; Lin, Y. Y.; Fan, D. W. et al.
Fluid-Structure-Sound Interactions and Control - Proceedings of the 6th Symposium on Fluid-Structure-Sound Interactions and Control FSSIC 2023. ed. / Daegyoum Kim; Kyung Chun Kim; Yu Zhou; Lixi Huang. Springer Science and Business Media Deutschland GmbH, 2024. p. 59-64 (Lecture Notes in Mechanical Engineering).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Artificial-Intelligence-Controlled Flow Separation from a Longitudinal Slender Axisymmetric Body

AU - Song, Y. K.

AU - Lin, Y. Y.

AU - Fan, D. W.

AU - Zhou, Y.

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

PY - 2024

Y1 - 2024

N2 - The flow separation from a longitudinal slender axisymmetric body is experimentally investigated. The experimental model is a DARPA SUBOFF model with a semi-sphere after-body which is associated with flow separation. The control system employs six tangentially blowing microjets as actuators and a loadcell as the sensor to monitoring the drag force. In conventional open-loop control, the DR is found to be proportional to the total momentum coefficient Cμ of the control jets. At Cμ,ol = 3.23 × 10–2, flow separation is completely suppressed with a pressure recovery of 71.2%, resulting in a considerable DR of 18.23%. However, the control-consumed energy exceeds the energy saved from drag reduction. To improve the control performance, an artificial intelligence (AI) control system is deployed and an unsupervised learning is conducted under an ant colony algorithm with a cost function J = CD. The AI control achieves a DR of 19.8% at Cμ,opt = 0.79 × 10–2 associated with a lower pressure recovery of 94.5%. The power saved from drag reduction is estimated to be 4.9 times of the control input power. The physical mechanism behind the finding is discussed.

AB - The flow separation from a longitudinal slender axisymmetric body is experimentally investigated. The experimental model is a DARPA SUBOFF model with a semi-sphere after-body which is associated with flow separation. The control system employs six tangentially blowing microjets as actuators and a loadcell as the sensor to monitoring the drag force. In conventional open-loop control, the DR is found to be proportional to the total momentum coefficient Cμ of the control jets. At Cμ,ol = 3.23 × 10–2, flow separation is completely suppressed with a pressure recovery of 71.2%, resulting in a considerable DR of 18.23%. However, the control-consumed energy exceeds the energy saved from drag reduction. To improve the control performance, an artificial intelligence (AI) control system is deployed and an unsupervised learning is conducted under an ant colony algorithm with a cost function J = CD. The AI control achieves a DR of 19.8% at Cμ,opt = 0.79 × 10–2 associated with a lower pressure recovery of 94.5%. The power saved from drag reduction is estimated to be 4.9 times of the control input power. The physical mechanism behind the finding is discussed.

KW - Axisymmetric body

KW - Drag reduction

KW - Flow separation control

UR - https://www.scopus.com/pages/publications/85205087476

U2 - 10.1007/978-981-97-6211-8_8

DO - 10.1007/978-981-97-6211-8_8

M3 - 会议稿件

AN - SCOPUS:85205087476

SN - 9789819762101

T3 - Lecture Notes in Mechanical Engineering

SP - 59

EP - 64

BT - Fluid-Structure-Sound Interactions and Control - Proceedings of the 6th Symposium on Fluid-Structure-Sound Interactions and Control FSSIC 2023

A2 - Kim, Daegyoum

A2 - Kim, Kyung Chun

A2 - Zhou, Yu

A2 - Huang, Lixi

PB - Springer Science and Business Media Deutschland GmbH

T2 - 6th Symposium on Fluid-Structure-Sound Interactions and Control, FSSIC 2023

Y2 - 26 August 2023 through 30 August 2023

ER -

Song YK, Lin YY, Fan DW, Zhou Y. Artificial-Intelligence-Controlled Flow Separation from a Longitudinal Slender Axisymmetric Body. In Kim D, Kim KC, Zhou Y, Huang L, editors, Fluid-Structure-Sound Interactions and Control - Proceedings of the 6th Symposium on Fluid-Structure-Sound Interactions and Control FSSIC 2023. Springer Science and Business Media Deutschland GmbH. 2024. p. 59-64. (Lecture Notes in Mechanical Engineering). doi: 10.1007/978-981-97-6211-8_8

Artificial-Intelligence-Controlled Flow Separation from a Longitudinal Slender Axisymmetric Body

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this