基于接近度的多传感器数据融合方法研究

Study on Multi-sensor Data Fusion Based on Approach Degree

针对多个传感器对某一特性指标多次测量的数据融合问题,提出了一种基于接近度的多传感器数据融合新方法。该方法将各传感器的测得数据视为一个模糊集合,利用模糊集合的最大、最小接近度对不同传感器测得数据间的接近程度进行量化处理,并通过接近度矩阵度量各传感器测得数据的综合接近程度,以合理地分配测得数据在融合过程中所占权重,得到数据融合估计的最终表达式,从而实现了多传感器数据的融合。实例分析表明应用所提出方法可达到比传统方法更高的融合精度,方差估计进一步验证了该方法的有效性。

Aiming at data fusion of multi-sensors experiment at many times on some characteristic index, a novel fusion method is proposed based on the approach degree. The method views the measured data of every sensor as a fuzzy set. Using the maximum and minimum approach degree of this fuzzy set, the approach degree of the measured data from various sensors is processed quantitatively. The synthesis approach degreeof data from various sensors is measured by an approach degree matrix to assigned the weights of data measured in the fusion process reasonably,so that the final expression of the data fusion and estimation is obtained, thus the data fusion of multi-sensor is realized. Test results demonstrate that this method can bring higher fusion precision than the traditional methods,and the variance estimation has further confirmed the validity of this method.