高铁大风预警模式挖掘

高铁大风预警的传统方法基于风速预测,当瞬时值高于限速阈值时触发报警,存在大量的误报警,不必要的限速控制影响了高铁行车效率。创新地提出了基于序列模式的预警方法,旨在挖掘报警事件前序数据中的频繁模式,找出报警事件的变化规律,通过滤除与非预警序列共有的频繁模式,得到预警序列独有的序列特征,构建了预警模式库。经兰新高铁沿线的监测数据验证,该方法在提高预测准确率的基础上降低了漏报率,同时有效地减少了模式匹配所需的时间,为提前预警预留充分的时间窗口,更加符合实际应用的需求。

Pattern mining of gale warning for high-speed railway

The traditional method of alarming high-speed rail traffic in gale is based on instantaneous threshold. Although it covers all alarm events, there are a lot of unnecessary alarms, which affect the efficiency of high-speed rail traffic. This paper innovatively proposes an early warning method based on sequence pattern. It aims at mining frequent patterns in the pre-order data and finding out the changing rules of alarm events. By filtering out the public frequent patterns of non-early warning sequences, it obtains the unique sequence characteristics of early warning sequences, and constructs a database of early warning patterns. Through the verification of monitoring data along Lanzhou-Wulumuqi High-speed Railway, the method does improve the accuracy of prediction, and reduce the rate of missing reports concurrently. It reduces the time required for pattern matching effectively, and reserves sufficient time windows for early warning, which accord more with the practical application requirements.