基于D-S理论的震动信号目标识别研究

为了解决干扰情况下地震动信号发射源的定性问题,提出了在决策层上的多传感器数据融合的识别方法。利用定位传感器组中各个传感器得到的数据,同时考虑在同一个定位组中各个传感器所得数据的置信度不同,来对地震动信号发射源性质进行识别。实验结果证明了基于D-S证据理论的目标识别数据融合后,地震动信号发射源特性识别的可靠性明显大于单个传感器的识别效果,这也表明了多传感器融合识别的可能性和有效性。

Research in Seismic Target Recognition Based on D-S Evidence Theory

In order to resolve the problem, the method of multi-sensor data fusion on decision level is submitted. Using the data from each sensor in a location set and considering the confidence value for each sensor, ME source characteristics can be acquired. Experimental results show that data fusion result of the target recognition based on D-S evidence Theory is better than that of single sensor and illustrates effectiveness of multi-sensor data fusion method.