基于MDARM和VxWorks的小型无人机执行器故障检测方法

由于目前在小型无人机执行器故障诊断中存在着智能化程度较低,容易受到人为因素干扰,从而出现故障漏检等问题,难以满足小型无人机对飞行安全的要求。为此,本文提出一种基于多维数据关联规则挖掘(Multidimensional Data Association Rules Mining: MDARM)和VxWorks操作系统的小型无人机执行器故障诊断方法,通过建立执行器内部传感器测量的温度、压力、流速、力矩等相关变量的历史数据库,并对这些数据进行预处理,以避免带来噪声污染,并利用可测量参数与不可测量参数之间的关联性,建立故障诊断知识库,避免了诊断过程中的人为因素干扰,实现小型无人机执行器故障的精准测量。实验结果证明,这种方法能够有效地提高故障准确率64.7%,对小型无人机执行器的智能诊提供有效指导,应用前景广阔。

Based on MDARM and VxWorks small unmanned aircraft actuator fault detection method

Due to currently exist in the small unmanned aircraft actuator fault diagnosis intelligent degree is low, vulnerable to human factors interference, so malfunction undetection problem such as, difficult to meet the requirements of small unmanned aircraft to flight safety. To this end, this paper puts forward a kind of based on Multidimensional Association rule Data Mining (Multidimensional Data Association Rules Mining, : MDARM) and VxWorks operating system of small unmanned aircraft actuator fault diagnosis methods, through the establishment of internal sensor actuator, such as temperature, pressure, flow velocity, torque of historical database of relevant variables, and the Data preprocessing, in order to avoid noise pollution, and use the measurable parameters and cannot be measured, the connection between the based fault diagnosis knowledge base, to avoid interference with human factors in the process of diagnosis, precision measurement of small unmanned aircraft actuator fault. Experimental results show that this method can effectively improve the fault accuracy 64.7%, intelligent diagnosis for small unmanned aerial vehicle (uav) actuators provide effective guidance and application prospect.