Volume 38, Number 6, December 2020
|1308 - 1315
|02 February 2021
Study on Early Warning Method of Cylinder Block's Off-Center Position and Swing Failure for 50 MW Steam Turbine
School of Electrical Engineering and Automation, Harbin Institute of Technology, Harbin 150001, China
2 School of Mechanical Engineering and Automation, Harbin Institute of Technology(Shenzhen), Shenzhen 518055, China
3 Zhejiang Zheneng Shaoxing Binhai Thermal Power Co., Ltd, Shaoxing 312073, China
Due to the special structure of the cylinder block, there is an off-center position and swing fault in the process of start-up and operation of the 50 MW extraction unit. Moreover, the lack of effective monitoring and early warning means seriously affects the safety of the unit operation. Therefore, it is very important to forewarn the fault of cylinder off-center position and swing. First of all, through the design of cylinder block offset amplifying mechanism for fault monitoring, the data of eccentric swing required for establishing mathematical model is obtained. Then, neural network is selected for data-driven modeling, two time series prediction models are obtained, and the influence of input and output parameters on the prediction accuracy is studied. Finally, by selecting reasonable early warning value and decision rules, an effective early warning of off-center position and swing fault is realized, and a monitoring device for real-time monitoring and fault early warning is developed. The actual application effect shows that this early warning method has important engineering value to avoid equipment damage caused by the swing fault for 50 MW unit.
50 MW背压机组汽轮机由于缸体结构特殊性，在启动及运行过程中存在偏心摆动故障风险，并且缺乏有效的监测预警手段，严重影响了机组运行的安全性。因此，缸体偏心摆动故障的提前预警非常重要。通过设计缸体偏移放大机构进行故障的监测，获取建立数理模型所需的偏心摆动数据。选择神经网络进行数据驱动建模，得到了2个时序预测模型，并研究了输入输出参数对预测精度的影响。通过选取合理的预警值及判定规则，实现了对偏心摆动故障的有效预警，开发了实时监测及故障预警装置。所提方法对避免50 MW机组偏心摆动故障带来的设备损坏具有重要的工程价值。
Key words: 50 MW back pressure unit / cylinder eccentric swing / fault early warning / vibration / monitoring device / neural network / data-driven model
关键字 : 50 MW背压机组 / 汽缸偏心摆动 / 故障预警 / 振动 / 监测装置 / 神经网络 / 数据驱动模型
© 2020 Journal of Northwestern Polytechnical University. All rights reserved.
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.