一种基于动态更新神经网络的无监督雷达退化故障预测方法

为了克服传统雷达故障检测方法对专家经验依赖性强、耗费大量人力物力、容易造成过度检修、无法对退化故障进行提前告警等缺点，提出了一种基于动态更新神经网络的无监督雷达退化故障预测方法。首先通过微波测量设备采集峰值功率和工作频率历史数据，其次利用动态更新神经网络对历史数据进行动态更新并预测后续数据，最后采用孤立森林方法对预测数据进行无监督故障检测，以此实现雷达退化故障预测并提前告警。结果表明，本文提出的方法可至少提前10个时间步(100 min)预测退化故障并实时告警，能够在小样本、无故障样本、无特征提取、无人工阈值的情况下实现雷达退化故障预测。

An unsupervised radar degradation fault prediction method based on dynamic updated-neural network

In order to overcome the shortcomings of the traditional radar fault detection method, which is highly dependents on expert experience, consumes a lot of manpower and material resources, causes over-repair, cannot give advance warnings for degradation faults, and so on. An unsupervised radar degradation fault prediction method based on dynamic updated-neural network is proposed. Firstly, the historical data of peak power and operating frequency are collected by microwave measurement equipment. Secondly, the dynamic updated-neural network is used to dynamically update the historical data and predict the subsequent data. Finally, the isolated forest method is adopted for unsupervised fault detection on the predicted data. In this way, radar degradation fault prediction and early warning can be realized. The results show that the method proposed in this paper can predict degradation faults at least 10-time steps (100 minutes) in advance and give the real-time alarms. It also can realize radar degradation fault prediction when there are small samples, no fault samples, no feature extractions and no artificial thresholds.