Damage assessment algorithm based on deep learning and fuzzy analytic hierarchy process

被引：0

作者：

Kong, Xiangxi ^{[1
]}

Qin, Wenyuan ^{[1
]}

Su, Piaoyi ^{[2
]}

Hua, Yongzhao ^{[1
]}

Dong, Xiwang ^{[3
]}

Wang, Li ^{[3
]}

Su, Ying ^{[3
]}

Lyu, Kun ^{[3
]}

机构：

[1] Institute of Artificial Intelligence, Beihang University, Beijing

[2] School of Aeronautic Science and Engineering, Beihang University, Beijing

[3] Wuhan Guide Infrared Co. ，Ltd., Wuhan

来源：

Hangkong Xuebao/Acta Aeronautica et Astronautica Sinica | 2024年 / 45卷 / 19期

关键词：

attention mechanism; damage assessment; damage classification; deep learning; fuzzy analytic hierarchy process;

D O I：

10.7527/S1000-6893.2023.29503

中图分类号：

学科分类号：

摘要：

To address the detection and assessment of military target damage，this paper proposes a two-stage dam⁃ age assessment method based on deep learning and fuzzy analytic hierarchy process. Firstly，in the Yolov5-based dual-stage target detection subsystem with coordinate attention mechanism，a key region extraction mechanism is em⁃ ployed to extract damage components，and a damage component classifier based on the combination of intersection over union，Hungarian linear matching，and decision tree is used for classification and quantification of damage sever⁃ ity. Then，in the damage assessment subsystem based on the triangular fuzzy analytic hierarchy process，multiple damage assessment weight systems and damage tree criteria are designed to comprehensively consider the damage features and categories extracted from the previous stage，achieving online real-time damage assessment for targets. Experimental results show that on various simulated datasets with multiple interference factors，the Yolov5-based dual-stage target detection subsystem with the attention mechanism achieves an average improvement in detection accu⁃ racy of over 3. 6% when compared to classical target fine-grained recognition algorithms. It demonstrates better perfor⁃ mance in target key region extraction，and damage classification and assessment，providing strong support and refer⁃ ence for target damage assessment and military operation decision making. © 2024 Chinese Society of Astronautics. All rights reserved.

引用

共 25 条

[1]

ZHU X J, ZHAO C J，, LIANG Z，, Et al., Thoughts on technology development of OODA empowered with AI ［J］, Acta Aeronautica et Astronautica Sinica, 42, 4, (2021)

[2]

SUN Z X, YANG S Q, Et al., A survey of air combat artificial intelligence［J］, Acta Aeronautica et Astronautica Sinica, 42, 8, (2021)

[3]

PEI Y, SONG B F, SHI S., Analysis method of aircraft combat survivability：Progress and challenge［J］, Acta Aeronautica et Astronautica Sinica, 37, 1, pp. 216-234, (2016)

[4]

GOU T., Research on key technologies of damage assess⁃ ment system based on image analysis［D］, pp. 1-4, (2019)

[5]

HUANG Y, SHAO C S，, WU B，, Et al., State-of-the-art review on Bayesian inference in structural system identifi⁃ cation and damage assessment［J］, Advances in Struc⁃ tural Engineering, 22, 6, pp. 1329-1351, (2019)

[6]

LIU Y, Et al., Damage assessment of phased array antenna based on analytic hierarchy pro⁃ cess and fuzzy comprehensive assessment［J］, Transac⁃ tions of Beijing Institute of Technology, 36, 10, pp. 996-1000, (2016)

[7]

ZHOU Y, LI W M., Evaluation of operational ef⁃ fectiveness for anti-aircraft Gun-missile system based on BP neural networks［J］, Systems Engineering and Elec⁃ tronics, 27, 1, pp. 84-86, (2005)

[8]

QU W J, ZHANG B L，, Et al., Battle damage as⁃ sessment method based on BN-cloud model ［J］, Acta Ar⁃ mamentarii, 37, 11, pp. 2075-2084, (2016)

[9]

CHEN Q, ZHU M B, LIU X D., Summarized of battle damage assessment based on image［J］, Ship Electronic Engineering, 33, 4, pp. 10-12, (2013)

[10]

WEI X, LI X T., Comprehensive damage effectiveness evaluation method based on fuzzy reasoning［J］, Intelli⁃ gent Computer and Applications, 12, 7, pp. 146-150, (2022)

← 1 2 3 →