Fuzzy clustering and classification for automated leak detection systems
Fuzzy clustering and classification for automated leak detection systems
复制标题
自动泄漏检测系统的模糊聚类和分类
DOI：
--
复制
发表时间：
2002
期刊：
影响因子：
--
通讯作者：
O. Wolkenhauer
中科院分区：
文献类型：
--
作者：
Nathalie Taillefond;O. Wolkenhauer
摘要本文提出了一种混合使用聚类和分类工具进行故障检测的管道完整性监测系统的方法。该方法用于更容易地分类故障或变化的背景下，在线泄漏检测与初始离线训练。该方法适用于一个小规模的管道监测的情况下，便携性，鲁棒性和可靠性是最重要的标准之一。结果是令人鼓舞的，因为获得了相对低水平的假警报和增加的故障检测。
Abstract A methodology for pipeline integrity monitoring systems using a mixture of clustering and classification tools for fault detection is presented here. The approach is used to classify more readily faults or changes in the context of on-line leak detection with initially off-line training. The methodology is applied to a small-scale pipeline monitoring case where portability, robustness and reliability are amongst the most important criteria. The results are encouraging as relatively low levels of false alarms and increased fault detection are obtained.