Study on Early Warning Method of Cylinder Block's Off-Center Position and Swing Failure for 50 MW Steam Turbine
| Autor: | Shi Jiakui, Ju Guoteng, Li Fengjun, Jie Wan, Kun Yao, Junfeng Fu |
|---|---|
| Jazyk: | čínština |
| Rok vydání: | 2020 |
| Předmět: |
data-driven model
Offset (computer science) Warning system Computer science cylinder eccentric swing neural network General Engineering Process (computing) TL1-4050 Swing fault early warning Fault (power engineering) Unit operation Automotive engineering Steam turbine monitoring device 50 mw back pressure unit Cylinder block vibration Motor vehicles. Aeronautics. Astronautics |
| Zdroj: | Xibei Gongye Daxue Xuebao, Vol 38, Iss 6, Pp 1308-1315 (2020) |
| ISSN: | 2609-7125 1000-2758 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|