基于支持向量回归机的航空飞机零部件异常检测研究

Research on Abnormal Detection of Aircraft Components Based on Support Vector Regression Machine

为优化航空飞机零部件异常检测效果,准确地检测识别出航空飞机零部件的异常状态,利用支持向量回归机,开展了零部件异常检测研究。首先,实时采集飞机零部件的相关数据,提取零部件特征;其次,基于支持向量回归机,构建检测模型,判断数据点是否为异常值;在此基础上,利用劣化度,对飞机零部件的异常情况作出检测,识别零部件的健康状态。实验结果表明,提出方法应用后,零部件异常检测结果与实际情况更加接近,能够更准确地检测识别出航空飞机零部件的异常状态。

In order to optimize the anomaly detection effect of aviation aircraft components and accurately detect and identify the abnormal status of aviation aircraft components,support vector regression machine was used to carry out research on component anomaly detection.Firstly,real-time collection of relevant data on aircraft components and extraction of component features;Secondly,based on support vector regression,a detection model is constructed to determine whether the data points are outliers;On this basis,using degradation degree,abnormal situations of aircraft components are detected to identify their health status.The experimental results show that after the proposed method is applied,the abnormal detection results of components are closer to the actual situation,and can more accurately detect and identify the abnormal status of aviation aircraft components.