基于排列熵的泵站压力管道运行状态监测

为实现泵站管道工作状态的在线监测,保障其安全稳定运行,提出一种基于排列熵算法(permutation entropy,简称PE)的泵站压力管道监测方法。该方法充分发挥排列熵算法计算简单和敏感度高等优点,适宜于处理非线性、非平稳信号,通过在关键部位设置传感器获取泵站管道的振动信号,利用信号子序列熵值的变化判断泵站管道振动状况。将该方法应用于景电工程二期七泵站管道的运行监测,通过设置不同的运行工况进行实例验证。结果表明,在开关机组瞬间,振动信号子序列熵值的最大幅差达到0.37,机组稳定运行期间子序列熵值的最大幅差仅为0.07,根据其熵值的变化可快速方便地识别出泵站管道的运行状态,具有较高的精度与可靠度。该方法为泵站管道运行状况的在线监测提供了新思路,为结构下一步安全诊断工作提供基础,具有较好的工程实用性和推广价值。

Monitoring Operating Condition of Pipeline of Pumping Stations Based on Permutation Entropy

In order to realize the online monitoring of the working conditions of pipeline of pumping stations, and to ensure the operation of the pumping station safely and stably, a monitoring method based on permutation entropy algorithm for pressure pipeline of pumping station is proposed. This method can give full play to the advantage of permutation entropy algorithm including the simple calculation and the high sensitivity, which can reflect the small changes of the non-linear and non-stationary signal. It can obtain the vibration signal of the pipeline in the pumping station by arranging the sensors in the key parts, which determines the vibration state of the pumping station pipeline by the change of the subsequences entropy in vibration signal. The method of this paper is applied to monitor the operation of the seven pump station pipelines of Jingtai Project Phase II. By setting different operating conditions for instance verification, the results show that in the moment of switching unit the maximum amplitude error of vibration signal subsequence entropy reaches 0.37, and when the unit operate stably, it is only 0.07, this method has high accuracy and reliability in identifying the changes in operating state of the pump pipeline quickly and easily by the change of the entropy. A new idea for the online monitoring of the operating conditions of the pumping station pipeline and a basis for the structural safety diagnosis in the next step are provided by this method, which has good engineering practicability and popularization value.