TY  - JOUR
T1  - Deep Model-Based Optimization of Jamming Effectiveness under Aircraft AESA Radar Operational Environments
AU  - Cho, Hanseul 
AU  - Shin, Baekrok 
AU  - Moon, Chaewon 
AU  - Hong, Sang-Geun 
AU  - Byoun, U-Ju 
AU  - Sung, Jin-Yong 
AU  - Yun, Chulhee 
JO  - The Journal of Korean Institute of Communications and Information Sciences
PY  - 2025
DA  - 2025/1/1
DO  - 10.7840/kics.2025.50.11.1647
KW  - AESA Radar
KW  - Jamming Effectiveness
KW  - Modeling and Simulation
KW  - Model-Based Optimization
KW  - 
KW  - Neural Network
AB  - We propose a deep learning algorithm to find effective jamming parameters in the aircraft AESA radar operational environment, based on a model-based optimization technique called RoMA. To represent a series of measurements obtained under the operational environment as a single number, we design jamming effectiveness by combining ranging failure rate and average range error. Next, we collect a jamming effectiveness dataset for various radar/jammer parameter combinations by repeatedly running the simulation. Our algorithm consists of two stages: the first is to pre-train a neural network that robustly approximates the function from radar/jammer parameters to jamming effectiveness; the second is to estimate the optimal jamming parameters by exploiting our model. As a result, the proposed method improved jamming effectiveness by an average of 41.2% and up to 80.3% compared to random search, and consistently outperformed other baseline models.