学术
摘 要:
针对威胁度估计问题和装甲车辆在战场上的实际情况，运用神经网络和遗传算法理论探索反装甲目标威胁度评估问题。基于BP神经网络模型的算法，利用神经网络良好的自适应能力和遗传算法强大的全局搜索能力，通过样本数据训练，提高了威胁度估计的准确性和适应性。经过验证该算法能够有效反应出反各种反装甲目标的威胁度，其稳定性、精确性也比较高。[著者文摘]
文章出处:
《指挥控制与仿真》-2008年1期 -60-62页
栏目信息:
文献标识码:
A
文章编号:
1673-3819（2008）01-0060-03
相关文章:
Study on Threat Evaluation of Anti-Armor Target Based on Neural Network and Genetic Algorithm Theory
ZHANG Wen-hua, NING Shu-liang, MA Yong （Bengbu Tank Academy, Bengbu 233013, China）
Abstract:
Aim at the estimate problem of minacity degree and armored vehicle exert in the actual conditions on the battlefield, make use of neural network and genetic algorithm theory to investigate anti-armor target minacity degree assessment problem. The algorithm of in consequence of BP neural network model, make use of the fair self-adapting capacity of the neural network and the strong global search capacity of the genetic algorithm. By sample data training, raise minacity degree estimate of accuracy and applicability. The algorithm can effectively respond various anti- minacity degree of anti-armor target through authentication, and it＇s steadiness and precision are also higher.[著者文摘]
Key words:
threaten estimate; neural network; genetic algorithm; anti-armor target
更多>>免费文章
cqvip.com