文章摘要
随钻监测数据预处理方法研究
Research on Preprocessing Methods for Monitoring Drilling Data
投稿时间:2023-12-30  修订日期:2024-05-31
DOI:
中文关键词: 随钻钻进(探)  数据预处理  机器学习  缺失插补  滤波降噪
英文关键词: digital drilling, data preprocessing, machine learning, missing data interpolation, noise reduction
基金项目:国家电网公司总部科技项目(5200-202322135A-1-1-ZN);国家自然科学基金项目(52079150)
作者单位邮编
肖浩汉 中国水利水电科学研究院流域水循环模拟与调控国家重点实验室 100048
曹瑞琅* 中国水利水电科学研究院流域水循环模拟与调控国家重点实验室 100048
王玉杰 中国水利水电科学研究院流域水循环模拟与调控国家重点实验室 
赵宇飞 中国水利水电科学研究院流域水循环模拟与调控国家重点实验室 
孙彦鹏 中国水利水电科学研究院流域水循环模拟与调控国家重点实验室 
摘要点击次数: 93
全文下载次数: 0
中文摘要:
      为攻克多维异构随钻监测数据处理难题,本研究分析多钻孔钻进数据特征,采用统计分析和机器学习方法,提出了一种数据预处理方法。该方法首先对原始钻进数据特征进行分析,确定了稳定钻进阶段数据提取判断标准,提出识别异常钻进数据的准则,并评估了多种方法在钻进数据缺失修补和滤波降噪方面的适用性。最后,开发了轻量化钻进数据自动预处理软件,并在工程案例中验证了其快速完成数据提取、分类、修补和降噪的能力,为工程实践提供了可靠的理论依据和数据支持。
英文摘要:
      To address challenges associated with processing multi-dimensional heterogeneous monitoring drilling data, this study conducts an analysis of the characteristics of multi-borehole drilling data and introduces a data preprocessing method leveraging statistical analysis and machine learning techniques. This methodology begins with an examination of the original drilling data's features, establishes criteria for extracting stable drilling stage data, defines parameters for identifying abnormal drilling data, and assesses the effectiveness of various methods for repairing missing drilling data and reducing noise. Subsequently, a lightweight automatic preprocessing software for drilling data is developed, and its efficacy in swiftly completing tasks such as data extraction, classification, repair, and noise reduction is validated through engineering case studies. This endeavor furnishes a dependable theoretical framework and empirical data support for practical applications in engineering.
  查看/发表评论  下载PDF阅读器
关闭