Integrating FSA and CNN: An architecture for weapon combat effectiveness evaluation in real meteorological environments

Yi Sun

doi:10.1016/j.aei.2026.104663

Integrating FSA and CNN: An architecture for weapon combat effectiveness evaluation in real meteorological environments

2026-05-05

0

PRE

AI

Y

Yi Sun

S

Shichao Li *

H

Hongliang Song

H

Hongli Gao

J

Jie Li

S

Shuang Yin

W

Wuyu Li

DOI：10.1016/j.aei.2026.104663

Original

Original request for help

Save

Abstract

En 中文

The importance of meteorological environment in various fields, such as modern military operations, aerospace and supply chain cannot be underestimated. Wind speed, sandstorm, visibility, thunderstorm and precipitation and other meteorological factors have a significant impact on the effectiveness of each field. However, existing research often focuses on isolated problems, such as feature extraction or performance evaluation under specific meteorological conditions, lacking a comprehensive architecture that integrates these aspects. This fragmented approach can lead to inconsistencies and biases in the evaluation results, thereby affecting the accuracy and timeliness of decision-making. To address this gap, a new supervised regression evaluation architecture based on fish swarm algorithm and convolutional neural network (FSA-CNN) is proposed, which integrates feature extraction and performance evaluation into a unified framework, thus ensuring the coherent flow of data. FSA-CNN uses the dynamic search strategy of FSA to find the global optimal solution, and uses CNN to automatically extract complex features from the original data. The validity of FSA-CNN is verified through the evaluation of weapon combat effectiveness (WCE) under real meteorological conditions. The experimental results indicate that the FSA-CNN attained a mean squared error of 0.0009 and an R-squared of 0.9947, underscoring its superior predictive accuracy and robustness. FSA-CNN provides accurate WCE prediction and evaluation in real meteorological environments. In addition, by accurately quantifying the impact of meteorological factors on WCE, military strategists can make wiser decisions, thus improving operational efficiency and tactical success rate.

Keywords:

FSA-CNN

weapon combat effectiveness

meteorological environment

feature extraction

supervised regression

Integrating FSA and CNN: An architecture for weapon combat effectiveness evaluation in real meteorological environments

Abstract

Journal

Organization

Cited Papers

Citing Papers