摘要
针对多传感器水质监测数据融合中测量数据存在误差的现象,论文提出一种基于DS证据融合理论的多源监测数据融合算法.该算法将影响水质的氨氮含量(NH3-N)、溶解氧(DO)、pH值、电导率(CD)等多环境因子变量作为证据,并赋予可靠性折扣,计算出水质等级的质量函数,然后通过DS方法将其与其他证据结合起来,最后使用融合质量函数值的决策规则确定水质类别.实验证明这种方法适用于具有多源监测数据的水质类别预测,可以从不确定性传感器数据中评估水质,并提高评估性能.
In response to the uncertainty associated with sensor data in the fusion of multi-source data for water quality assessment monitoring,a fusion algorithm based on the DS evidence theory has been proposed.This algorithm takes various environmental factors such as ammonia nitrogen content(NH3-N),dissolved oxygen(DO),pH value,and conductivity(CD)that impact water quality as evidence,assigns them reliability discounts,computes a quality function for water quality levels,combines them with other evidence using the DS method,and then employs decision rules based on the fused quality function values to determine water quality categories.Experimental results have demonstrated that the proposed approach is suitable for predicting water quality categories with multi-source monitoring data,enabling the assessment of water quality from uncertain sensor data and improving assessment performance.
作者
左现刚
张志霞
王梦
刘艳昌
韩旭
丁佰成
ZUO Xiangang;ZHANG Zhixia;WANG Meng;LIU Yanchang;HAN Xu;DING Baicheng(School of Information Engineering,Henan Institute of Science and Technology,Xinxiang 453003,China;Higher Vocational and Technology College,Henan Institute of Science and Technology,Xinxiang 453003,China)
出处
《河南科技学院学报（自然科学版）》
2024年第2期56-64,共9页
Journal of Henan Institute of Science and Technology(Natural Science Edition)
基金
河南省科技厅科技攻关(232102210106)
河南科技学院大学生创新训练项目(2023CX106)。
关键词
证据理论
传感器
数据融合
水质
evidence theory
sensors
data fusion
water quality
