Steam turbine rotor fault diagnosis method based on LSTM

• Main Authors: ZHANG DI, LIU TIANYUAN, XIE YONGHUI, WANG CHONGYU
• Format: Patent
• Language: Chinese; English
• Published: 02.04.2019
• Subjects: BLASTING; CALCULATING; COMPUTING; COUNTING; ENGINE PLANTS IN GENERAL; HANDLING RECORD CARRIERS; HEATING; LIGHTING; MACHINES OR ENGINES IN GENERAL; MECHANICAL ENGINEERING; NON-POSITIVE DISPLACEMENT MACHINES OR ENGINES, e.g. STEAMTURBINES; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS; STEAM ENGINES; WEAPONS

The invention discloses a steam turbine rotor fault diagnosis method based on LSTM, and belongs to the technical field of mechanical fault diagnosis. Firstly, multi-point acquisition sensors are deployed and controlled, and vibration signals of various typical turbine rotor faults are collected as a training set and a verification set. Secondly, the steam turbine rotor vibration signals are extracted from a power plant DCS system to serve as a testing set. Thirdly, the training set, the testing set and the verification set realize fusion of multi-point signal data and data enhancement throughsignal division, stacking and other operations. Fourthly, a neural network based on the LSTM is constructed, the training set and the verification set are used for completing training of the network,and finally, maintenance of a diagnostic model is achieved in cooperation with an actual diagnostic task, and finally the steam turbine rotor fault diagnosis is realized on the testing set. 本发明公开了种基于LSTM的汽轮机转子故障诊断方法，属于机械故障诊断技术