Wind turbine generator gearbox bearing temperature state monitoring method based on self-organizing kernel regression model

Abstract

The invention discloses a wind turbine generator gearbox bearing temperature state monitoring method based on a self-organizing kernel regression model. A self-organizing kernel regression modeling method and a sequential probability ratio residual error analysis method are introduced into wind turbine generator state monitoring. A partial least squares method is adopted to select variables, a self-organizing kernel regression method is adopted to establish a relation model between the bearing temperature of the gearbox and influence variables of the bearing temperature, and the model is usedfor predicting the bearing temperature of the gearbox in the monitoring stage. In order to reduce the false alarm rate and the missing alarm rate of gearbox bearing temperature early warning, a sequential probability ratio method is adopted to analyze a residual error between a gearbox bearing temperature prediction value calculated by the model and an actual value, and when the sequential probability ratio is larger than a set threshold value, a gearbox bearing temperature abnormity alarm is given out. The method is used for analyzing the temperature data of the gearbox bearing, the purposesof temperature monitoring and fault early warning of the gearbox bearing of the wind turbine generator are accurately achieved, and the practicability and universality of the method are verified.

Description

technical field [0001] The invention belongs to the field of monitoring the state of a gearbox of a wind turbine, and in particular relates to a method for monitoring the temperature state of a bearing of a gearbox of a wind turbine based on a self-organizing kernel regression model. Background technique [0002] In recent years, the air environment in some areas of my country has been deteriorating, and severe smog has occurred frequently. The traditional energy structure dominated by fossil fuels such as coal and oil needs to be adjusted urgently. The scientific and efficient development of renewable energy is imminent. As an important part of renewable energy, wind power is developing rapidly in my country, and its cumulative installed capacity and new installed capacity both rank first in the world. [0003] The operating conditions of wind turbines are harsh, such as large changes in external temperature difference and random changes in wind speed. These uncertain exte...

AI Technical Summary

Problems solved by technology

The current vibration analysis technology is aimed at the time-varying and complex working conditions of variable speed and variable load of gearbox bearings. The accuracy of fault diagnosis is low, and the rate of false alarms and missing alarms is high.

The gearbox oil analysis technology diagnoses the state of the gearbox bearings by collecting gearbox oil samples during the shutdown of the wind turbine, and analyzing the water content in the lubricating oil, the number and diameter of metal particles in the laboratory, but the oil analysis It can only be diagnosed offline, and cannot realize online real-time monitoring and diagnosis of gearbox bearings

There is also a multi-layer forward neural network to model and monitor the bearing temperature of the wind turbine gearbox. However, due to the complex structure of the forward neural network, many model parameters, and long training time, it is difficult to detect abnormal changes in the gearbox bearing temperature. timely and accurate warning

Images