摘要
雷达电源系统的运行状态直接影响整个雷达设备的安全性与性能指标的实现,如何实现雷达电源的健康状态评估是亟待解决的问题。首先采用雷达电源正常状态下的健康特征数据训练自组织神经网络;然后计算监测数据与训练后的自组织神经网络中权重向量的距离,将距离值归一化表示为健康度;最后利用试验数据计算健康度,并实现健康分级。结果表明:该模型计算的健康度随电源老化时间变化整体呈现下降的特点,该模型可以实现雷达电源健康状态评估。
The operation status of radar power supply system directly affects the safety and performance of the whole radar equipment.How to realize the health status assessment of radar power supply is a problem to be solved.Firstly,the health feature data of radar power supply under normal state is used to train the self-organizing neural network.Then the distance between the monitoring data and the weight vector of the trained self-organizing neural network is calculated,and the distance value is normalized and expressed as the health degree.Finally,the health degree is calculated by using the test data,and the health classification is realized.The results show that the health degree calculated by the proposed model decreases with the aging time of power supply,and the model can realize the evaluation of the health status of radar power supply.
作者
洪晟
罗无为
周闯
李庆岚
叶景文
HONG Sheng;LUO Wuwei;ZHOU Chuang;LI Qinglan;YE Jingwen(School of Cyber Science and Technology,Beihang University,Beijing 100191,China;School of Reliability and System Engineering,Beihang University,Beijing 100091,China;Information Processing Department,Nanjing Institute of electronic technology,Nanjing 210039,China;School of Mechanical Engineering,Beihang University,Beijing 100091,China)
出处
《航空工程进展》
CSCD
2020年第4期585-590,共6页
Advances in Aeronautical Science and Engineering
基金
国家自然科学基金(61773001)
国家重点研发计划课题(2019YFB1706001)
工业互联网创新发展工程(TC190H46B)
国防基础科研计划(JCKY2017210Bxxx)。
关键词
雷达电源
安全性
神经网络
加速退化试验
健康状态评估
radar power supply
safety
neural network
accelerated degradation test
health state evaluation
