Steam turbine host fault diagnosis method based on feature selection of stationary and non-stationary vibration signals

Abstract

The invention discloses a steam turbine host fault diagnosis method based on feature selection of stationary and non-stationary vibration signals. For a steam turbine in a thermal power steam turbineunit, the method combines use of ensemble empirical mode decomposition (EEMD) and a recursive feature elimination method to decompose and extract key features of the stationary and non-stationary signals in detail, and uses the same for fault diagnosis of steam turbine vibration signals. According to the method, the characteristics of non-stationarity, massive noise inclusion and the like of the steam turbine vibration signals are fully considered, potential information contained in fault data is fully exploited, features are respectively extracted for the stationary and non-stationary data, and the problem that non-stationary data features are liable to be masked is overcome. At the same time, the key features are extracted, dimension quantity of feature vectors is decreased, redundancy of data is reduced, accuracy of fault diagnosis of the steam turbine vibration signals is improved, accurate repair of an on-site engineer on a fault is facilitated, thus safe and reliable running of generator steam turbine equipment is guaranteed, and production benefits are improved.

Description

technical field [0001] The invention belongs to the technical field of fault diagnosis of vibration signals, in particular to a fault diagnosis method based on feature selection of stable and non-stationary vibration signals for a steam turbine main engine of a thermal power generating set. Background technique [0002] With the progress of society and the development of science and technology, people's demand for electricity is also increasing. Among them, coal-fired power generation is one of the main power generation methods in my country. In recent years, with the adjustment of the structure of the power generation industry, large-scale units with large capacity, high parameters, and low energy consumption have gradually replaced small units with high energy consumption, and the industrial process has become more and more complicated. As the main equipment for coal-fired power generation, the safe operation of the main engine of the steam turbine affects the operation s...

AI Technical Summary

Problems solved by technology

Have not yet seen the research reports relevant to the present invention

Images