无人机故障元数据属性分类与识别技术

Classification and Recognition Technology of UAV Fault Metadata Attributes

传统方法在对无人机故障进行识别时,未对无人机故障进行有效分类,使得无人机故障识别结果差,应用性不高。为此,本文引入诊断分类树状模型对无人机故障元数据进行分类,解决传统方法中存在的问题。分析无人机故障元数据特点,在此基础上完成诊断层分类,获得对象层、故障层、征兆层、测试层、现象层及原因层6种不同的元数据属性类型;建立诊断分类树状模型对上述的元数据属性类型分类,获得统一格式为CML类型数据;依据雷达天线信息采集相关无人机故障元数据,根据左右识别及判断脉冲点方法完成元数据属性瞬时识别过程;获取最终的数据单元,实现无人机故障元数据属性的精确识别。实验结果表明,研究的技术能够精准地识别到故障元数据属性,并对其分类,分类处理所需时间短,该技术具有很高的发展空间,对于保障无人机安全运行有重要意义。

In the traditional method,when the Unmanned Aerial Vehicle(UAV)fault is identified,the UAV fault is not effectively classified,so that the UAV fault recognition result is poor and the applicability is not high.To this end,this paper introduces a diagnostic classification tree model to classify the UAV metadata failures and solve the problems in the traditional methods.Analyze the characteristics of the UAV fault metadata,and complete the classification of the diagnostic layer on the basis of this,and obtain six different metadata attribute types:the target layer,the fault layer,the symptom layer,the test layer,the phenomenon layer and the cause layer.Establish a diagnostic classification tree model to classify the above metadata attribute types,and obtain a unified format as CML type data.According to the radar antenna information,the relevant UAV fault metadata is collected,and the metadata attribute instantaneous identification process is completed according to the left and right recognition and judgment pulse point method;the final data unit is obtained to realize the accurate identification of the UAV fault metadata attribute.The experimental results show that the research technology can accurately identify and classify fault metadata attributes,and the time required for classification processing is short.This technology has a high development space and is of great significance for ensuring the safe operation of drones.