基于动态融合LOF的城市污水处理过程数据清洗方法
作者:
作者单位:

北京工业大学

作者简介:

通讯作者:

中图分类号:

TP181

基金项目:

国家自然科学基金项目(面上项目,重点项目,重大项目),国家重点基础研究发展计划(973计划)国家自然科学基金创新群体项目,北京高校卓越青年科学家项目


Data-cleaning method based on dynamic fusion LOF for municipal wastewater treatment process
Author:
Affiliation:

Beijing University of Technology

Fund Project:

The National Natural Science Foundation of China (General Program, Key Program, Major Research Plan) ,The National Basic Research Program of China (973 Program)

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    围绕城市污水处理过程数据存在连续噪声和缺失的问题,文中提出一种基于动态融合局部异常因子(Dynamic fusion local outlier factor, DFLOF)的污水处理过程数据清洗方法。首先,设计了一种基于滑动窗口的数据动态分段方法,通过计算每个子段数据的均值、最大值和峰值区间信息,获得数据异常属性值。其次,建立了一种基于DFLOF的数据可信度评价模型,利用基于动态融合局部异常因子算法评估数据的可信度,保证异常数据检测和剔除的准确率。最后,提出了一种基于径向基函数(Radial basis function, RBF)神经网络的数据补偿方法对缺失数据进行补偿,实现污水处理过程数据的清洗。将该数据清洗方法应用于实际污水处理过程中,实验结果表明:基于动态融合局部异常因子的数据清洗方法能够实现污水处理过程中异常数据的清洗,提高了数据质量。

    Abstract:

    In order to reduce the impact of continuous data noise and loss, a dynamic fusion local outlier factor (DFLOF) method was proposed for data-cleaning of the municipal wastewater treatment process (WWTP). First, a data dynamic segmentation method based on sliding window was designed to obtain the abnormal attribute of each segment, including mean value, maximum value and peak interval. Second, a data reliability evaluation model based on DFLOF was established to evaluate each data segment by using the dynamic fusion local outlier factor algorithm, which improved the accuracy of abnormal data detection and elimination. Finally, a data compensation method based on radial basis function neural network was proposed to compensate the missing data and further realize the data-cleaning of WWTP. This proposed cleaning method was applied to a real WWTP, the experimental results show that the data-cleaning method based on the dynamic fusion local outlier factor is able to clear abnormal data and improve the data quality.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2020-11-06
  • 最后修改日期:2021-02-01
  • 录用日期:2021-02-10
  • 在线发布日期: 2021-03-03
  • 出版日期: