基于改進鯨魚算法和BiGRU的彈道目標HRRP識別方法

打開文本圖片集

中圖分類號：TP183 文獻標志碼：A DOI：10.12305/j.issn.1001-506X.2025.06.11

Abstract：To address the problem time sequence feature extraction recognition high resolution range image（HRRP）for ballstic mid-course targets，a ballistic target recognition method based on optimized bidirectional gate recurrent unit （BiGRU）is proposed.Firstly，the HRRP data is processed asa bidirectional sequence，a BiGRU network is established to extract the temporal features both directions HRRP. Secondly，the double weight strategy whale optimization algorithm （DWSWOA）.Double weight factors enable higher whale optimization algorithm（WOA）converage velocity lower probability faling into local optimal solution， are used to optimize the parameters BiGRU.The experimental results target HRRP recognition based on optimized BiGRU model show that the proposed method exhibits higher accuracy in target recognition，robustness reliability on noisy data sets than the other four algorithms.

Keywords：target recognition；high resolution range prile（HRRP）；whale optimization algorithm （WOA）；bidirectional gate recurrent unit（BiGRU）；confidence

0 引言

彈道導彈具有射程遠、速度快、難以攔截的特點，中段的飛行時間最長，且彈道相對固定，因此如何從中段目標群準確識別出真彈頭一直是各國研究的熱點問題[1-2]。（剩余15324字）