摘要
地下水监测主要通过自动化监测设备对地下水位进行监测,从而获得随时间变化的水位曲线.目前的自动化监测设备采集的水位数据中存在很多异常值,会影响正常的决策判断.针对此问题,提出将自学习算法融入到奇异值剔除—拉依达准则中,用于异常值的检测,将其应用于地下水位数据的平滑处理中,通过对内蒙古某地采集的水位数据进行平滑处理验证,表明本文方法能够有效剔除水位数据中的异常值,而且不会影响曲线的整体趋势走向,效果良好.
Groundwater monitoring monitors groundwater levels primarily through automated monitoring equipment to obtain time-varying water level curves. There are many abnormal values in the water level data collected by the current automatic monitoring equipment, which affects the normal decision-making. Aiming at this problem, it is proposed to integrate the self-learning algorithm into the singular value culling criterion—Layida criterion for the detection of outliers, and apply it to the smoothing of groundwater level data through the water level data collected in a certain area of Inner Mongolia. The smoothing process verification shows that the method can effectively eliminate the outliers in the water level data, and does not affect the overall trend of the curve, and the effect is good.
作者
李丽敏
温宗周
王真
董勋凯
LI Limin;WEN Zongzhou;WANG Zhen;DONG Xunkai(School of Electronics and Information,Xi′an Polytechnic University,Xi′an 710048,China)
出处
《西安工程大学学报》
CAS
2018年第5期604-608,共5页
Journal of Xi’an Polytechnic University
基金
陕西省教育厅科学研究项目(17JK0346)
西安工程大学博士科研启动基金(BS1506)
关键词
地下水位监测
自学习
改进Pauta准则
平滑处理
groundwater lever monitoring
self-learning
improved Pauta criterion
smooth processing
