Modern Defense Technology ›› 2026, Vol. 54 ›› Issue (2): 137-146.DOI: 10.3969/j.issn.1009-086x.2026.02.013

• PAPERS • Previous Articles    

Bayesian Regularization Design Method for Test Samples of Multi-sensitive Factor Anti-suppression Interference

Lin GENG1, Jinxi HAN1, Jianguang JIA1, Yihui LIN2, Zhiwen XU2, Rui ZHAO1   

  1. 1.PLA 32801 Troops
    2.Xidian University,Xi′an 710071,China
  • Received:2025-09-11 Revised:2026-03-01 Online:2026-04-28 Published:2026-04-30

多因素抗压制干扰贝叶斯正则化试验样本设计

耿琳1, 韩进喜1, 贾建光1, 林熠晖2, 许智文2, 赵蕊1   

  1. 1.中国人民解放军32801部队
    2.西安电子科技大学,陕西 西安 710071
  • 作者简介:耿琳(1971-),男,河北涿州人。副研究员,硕士,研究方向为装备试验鉴定规划设计。

Abstract:

To improve the anti-interference test capability of missiles in complex electromagnetic environments, this paper proposed a Bayesian regularization design method for test samples of multi-sensitive factor anti-suppression interference. First, this method analyzed the typical multi-sensitive factors affecting the anti-suppression interference capability of the seeker and then designed a Bayesian regularization network to solve the test sample design problem of missile anti-interference. The constructed Bayesian regularization network for multi-sensitive factor anti-suppression interference tests could establish a nonlinear mapping relationship between different multi-sensitive anti-interference influencing factors and anti-interference capability, greatly reducing the sample size of traditional all-factor traversal tests. Then, the hyperparameter solving method for the constructed network was studied, thereby realizing the Bayesian regularization design method for test samples. Finally, simulation experiments on typical anti-suppression interference were conducted to verify the performance of the proposed test sample design method. The results indicate that the Bayesian regularization test sample design for multi-sensitive factor anti-suppression interference effectively shortens the time cycle, saves test resources, and provides theoretical support for the anti-interference test evaluation of precision-guided missiles.

Key words: multi-sensitive factor, Bayesian regularization, sample design, precision-guided missile, suppression jamming

摘要:

为了提高导弹在复杂电磁环境中抗干扰试验能力,提出了多敏感因素抗压制干扰试验贝叶斯正则化样本设计方法。该方法分析了影响导引头抗压制干扰能力的典型多敏感因素,进而设计了贝叶斯正则化网络以解决导弹抗干扰试验样本设计问题。所构建多敏感因素抗压制干扰试验贝叶斯正则化网络能够建立不同多敏感抗干扰影响因素与抗干扰能力之间的非线性映射关系,大大降低传统全要素遍历试验样本数量。研究了所构建网络的超参数求解方法,从而实现了贝叶斯正则化试验样本设计方法。最后,抗典型压制干扰的仿真实验对所提试验样本设计方法性能进行验证,结果表明多敏感因素抗压制干扰贝叶斯正则化试验样本设计有效缩短时间周期,节省试验资源,为精确制导导弹抗干扰试验鉴定提供理论支撑。

关键词: 多敏感因素, 贝叶斯正则化, 样本设计, 精确制导导弹, 压制干扰

CLC Number: