Turbine rotor transient stress detection method

Abstract

The invention discloses a steam turbine rotor transient stress detection method, and relates to the field of steam turbines. The method comprises the steps of obtaining characteristic parameters influencing turbine rotor transient stress in a turbine set; Establishing a transient stress prediction model; the transient stress prediction model is trained according to the characteristic parameters, the transient stress prediction model comprises a two-layer structure, the first layer structure is composed of n different machine learning models, the outputs of the n machine learning models in thefirst layer structure are connected with the input of the machine learning model in the second layer structure, and n is larger than or equal to 2; And detecting the transient stress of the steam turbine rotor according to the trained transient stress prediction model. According to the detection method provided by the invention, the prediction capability of the transient stress prediction model oncomplex conditions is improved, information between data is fully learned, the precision of rotor transient stress prediction under the multi-parameter complex conditions is improved, and complex modeling is not needed.

Description

technical field [0001] The invention relates to the field of steam turbines, in particular to a detection method for the transient stress of a steam turbine rotor. Background technique [0002] In a steam turbine unit, the working condition of the rotor is of great significance to the operation safety and life management of the steam turbine unit. During the start-up and shutdown of the steam turbine unit, the main shaft, blades and impellers of the steam turbine unit will generate huge transient stress due to high-speed rotation, strong torque and high-temperature steam, threatening the normal operation of the rotor. Therefore, the analysis and prediction of the transient stress of the rotor becomes the key to the life management of the steam turbine unit. However, the harsh working environment of the rotor makes it difficult to directly measure the transient stress. [0003] At present, in the study of steam turbine rotor life, usually, the prediction of the transient st...

AI Technical Summary

Problems solved by technology

However, the prediction effect of complex situations where multiple parameters of large steam turbines interact is not good, the modeling process is cumbersome and time-consuming, and the accuracy of the results obtained is low, and the calculation efficiency is not high

Images