The development of wireless communication has led to the wide application of passive localization. Although passive localization has strong antijamming and concealment, its accuracy will be reduced due to false location. In order to solve the above problem, particle swarm optimization–back‐propagation (PSO‐BP) algorithm was used to improve the accuracy of passive location model in this study, and it was compared with the traditional BP algorithm and extreme learning machine (ELM) algorithm by simulation. The results showed that the coordinate error calculated by the PSO‐BP neural network was smaller than that of the BP neural network and ELM algorithms, and the error fluctuation was smaller; with the increase of the number of multitarget localization, the average error and positioning time of the BP algorithm gradually increased, while the average positioning error and positioning time of the PSO‐BP algorithm basically remained stable, smaller than the BP algorithm. © 2020 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

中文翻译：

---

远程多目标定位信息的被动定位算法

无线通信的发展已导致无源定位的广泛应用。尽管被动定位具有很强的抗干扰和隐蔽性，但由于错误的定位，其准确性会降低。为了解决上述问题，本文采用粒子群优化-反向传播（PSO-BP）算法提高了被动定位模型的精度，并与传统的BP算法和极限学习机（ELM）进行了比较。 ）算法进行仿真。结果表明，PSO-BP神经网络计算的坐标误差小于BP神经网络和ELM算法的坐标误差，误差波动较小。随着多目标定位数量的增加，BP算法的平均误差和定位时间逐渐增加，而PSO-BP算法的平均定位误差和定位时间基本保持稳定，小于BP算法。©2020日本电气工程师学会。由Wiley Periodicals LLC发布。