一种高冲突修正的区间证据水质数据融合研究

Research on Interval Evidence Water Quality Data Fusion with High Conflict Correction

针对水质评价不完善的问题,提出了一种基于区间证据理论的高冲突水质多参数数据融合方法。采用D-S证据理论结合区间数的做法,通过高冲突修正原始数据后达到能够直接分类的结果。提供了一种基于区间相似度的基本概率分配生成方法,并采用系数α调节,在修改冲突数据的同时保留最多的原始数据。运算后得到水质分类Ⅰ~Ⅴ依次为0.3516、0.5224、0.0913、0.0247、0.0099,不确定度概率为0,信度最大值即当前的水质分类。通过融合后的信度,能清晰地了解每个等级的支持度的概率,迅速判断水质当前所处等级,为水质分类提供了新思路。

Aiming at the problem of imperfect water quality evaluation,a high-conflict multi-parameter data fusion method based on interval evidence theory is proposed.D-S evidence theory combined with interval number is adopted to correct the original data through high conflict,and the result of direct classification is achieved.This experiment provides a BPA generation method based on interval similarity,adjusted by the coefficientα,the original data is retained while modifying the data conflictdata.After the calculation,the water quality classificationsⅠtoⅤare 0.3516、0.5224、0.0913、0.0247、0.0099 in order,the probability of uncertainty is 0,and the most reliable value is the current water quality classification.The fused reliability can clearly understand the probability of each level of support,and can quickly determine the current level of water quality.This method provides a new idea for water quality classification.