振动加速度检测中传感器连接状态的自动识别

摘要

在振动加速度检测中,如果系统不能对传感器连接状态加以自动区分,将正常连接状态下的数据和异常连接状态下的数据全部存入数据库,则必然会给数据库增加不必要的负担,造成数据污染；另外,为了传感器检修的便利,也有必要自动识别传感器的连接状态.对振动加速度检测中传感器四种连接状态的自动识别方法进行了研究:定义了表征不同传感器连接状态的加速度信号数字特征,结合基于LDA的特征降维和最近邻分类器采实现自动识别.实验显示,提出的振动加速度传感器四种连接状态的自动识别方法是有效的.%In order to make it more convenient to maintain sensors, it is needed to identify the sensor linking states automatically. The automatic identification for the four linking states of sensors in vibration acceleration detection is discussed in this paper. In the proposed method, the digital characteristics of aceleration signal are defined, which can characterize the different sensor linking states. The automatic identification of the sensor linking states is realized by means of the LDA-based dimension reduction of the characteristic vectors and the nearest-neighbor classifier. The experiment indicates that the proposed method can identify the sensor linking states automatically.