基于改进自适应加权的多传感器融合监测

Multi-sensor fusion monitoring based on improved adaptive weighted fusion algorithm

摘要:

针对加注系统多传感器测量数据融合,为满足融合的可靠性与准确性需求,提出了一种改进的自适应加权融合算法。加权融合算法的关键是如何准确判定测量数据权重值,在总结分析当前权重值判定方法优缺点的基础上,将证据理论中的修正证据距离引入测量数据间距离计算,生成融合权重值,完成传感器数据融合。通过一般算例与加注系统典型算例,对所提融合算法进行验证,结果表明算法融合效果较好、鲁棒性强,具有一定的理论意义和较好的工程实用价值。

关键词:数据融合; 自适应加权; 修正证据距离; 加注系统;健康监测

Abstract:

Aiming at the research of multi-sensor fusion of filling system, in order to meet the accuracy and reliability requirements of the fusion, an improved adaptive weighted fusion algorithm is presented. The key point of weighted fusion is the accurate calculation of fusion weights. The research on fusion weights calculation is summarized and analyzed, a modified evidence distance from D-S evidence theory is used to calculate the distance of test data, and fusion weights can be obtained. General example and typical example of filling system is used to test the proposed fusion algorithm. The example show that the proposed fusion algorithm takes on strong robustness and good fusion result, and it has theoretical and practical significance.

Key words:data fusion; adaptive weighted fusion; modified evidence distance; filling system; health monitoring