CAJ | 학술논문

针对黄河含沙量监测易受环境因素影响的特点,研究了基于云计算的分布式灰色数据融合技术,建立了黄河含沙量在线监测云平台。平台依靠分散在黄河流域的水温、测点深度等传感器建立分布式数据采集子云,然后用主成分分析法分析出含沙量监测的主成分因素,最后基于灰色GM(1,N)模型进行含沙量数据融合处理。为了比较灰色GM(1, N)模型含沙量监测的融合效果,在相同环境下进行了一元线性拟合、多元线性拟合的对比处理。结果表明,基于灰色GM(1,N)模型数据融合的精度最高,稳定性最强,能够拟合出较为准确的结果。
침대황하함사량감측역수배경인소영향적특점,연구료기우운계산적분포식회색수거융합기술,건립료황하함사량재선감측운평태。평태의고분산재황하류역적수온、측점심도등전감기건립분포식수거채집자운,연후용주성분분석법분석출함사량감측적주성분인소,최후기우회색GM(1,N)모형진행함사량수거융합처리。위료비교회색GM(1, N)모형함사량감측적융합효과,재상동배경하진행료일원선성의합、다원선성의합적대비처리。결과표명,기우회색GM(1,N)모형수거융합적정도최고,은정성최강,능구의합출교위준학적결과。
For monitoring the Yellow River sediment characteristics susceptible to environmental factors, it studied the distributed grey data fusion technology based on cloud computing and established the Yellow River sediment online testing cloud platform. Firstly, the platform would be distributed in the Yellow River basin water temperature, depth sensor measuring point to establish a distributed data acquisition sub-cloud and then analyzed the principal component factor of the sediment testing by using principal component analysis, and finally carried sediment data fusion based on gray GM (1, N) model. In order to compare the gray GM (1, N) fusion effect sediment detection methods, in the same environment also carried out a linear fit and multivariate linear fitting process. The results show that the highest accuracy and the strongest stability based on gray GM (1, N) model data fusion can fit more accurate results.