Steam turbine vibration monitoring method and device

Abstract

The invention provides a steam turbine vibration monitoring method and device, and the method comprises the steps: obtaining historical vibration target parameters and historical operation state characteristic parameters under different working conditions, and dividing the parameters into a training sample set and a test sample set; training a pre-established initial random forest model by using the training sample set to obtain a trained random forest model, and performing parameter optimization on the trained random forest model by using the test sample set to obtain a vibration prediction model; inputting the obtained real-time operation state characteristic parameters into a vibration prediction model for processing to obtain a steam turbine vibration prediction result; and comparing the steam turbine vibration prediction result with the obtained real-time vibration target parameters to obtain a steam turbine vibration monitoring result. According to the method, the vibration prediction models under different working conditions are established, and the real-time operation parameters under different working conditions are combined, so that the long-term, accurate and efficient monitoring of the vibration of the steam turbine is realized.

Description

technical field [0001] The invention relates to the technical field of steam turbines, in particular to a method and device for monitoring vibration of steam turbines. Background technique [0002] As an important medium for energy conversion, steam turbines are widely used in various engineering practices. In large thermal power plants, steam turbines convert the internal energy of steam into electrical energy, and their normal operation is directly related to the safety and stability of the power grid; for common thermal power plants in the north, they not only output electrical energy, but also provide winter heating for surrounding towns. Therefore, the safe operation of steam turbines under heating conditions has important practical significance in the protection of people's livelihood. [0003] Turbine operation monitoring is becoming more and more complete, and the steam turbine monitoring system can monitor and record mechanical parameters such as turbine speed, vib...

AI Technical Summary

Problems solved by technology

At present, there is a problem of inaccurate monitoring in the domestic research on the vibration prediction of the main engine

Images