BP神经网络在雷达故障诊断中的应用研究

Application Research of BP Neural Network in Fault Diagnosis of Radar

对雷达混合电路故障诊断问题进行了研究,针对传统雷达故障诊断中的“自适应差”,“过分依赖故障数学模型”的缺陷,采用了一种故障诊断表示模型,提出将专家系统与神经网络相结合的诊断方法,避免了在实际中雷达电路难以建立精确的数学模型的问题。利用人工神经网络理论为其建立了BP神经故障诊断网络,增加了雷达电路故障诊断系统的“自适应性”,进而给出了网络训练算法和诊断步骤,最后给出了在某型雷达设备上仿真调试诊断的实例。

Aimed at ＂self adaptation limitation＂ and ＂dependency of fault math model＂ of traditional fault diagnosis of radar, a method baaed on integration of expert system and neural network is proposed. A BP neural network is founded, which bases on theory of ANN, the training algorithm and fault diagnosis steps are described. An imitated diagnosis examples in some part of a radar system is also given.