Wind turbine generator bearing early warning method based on feature fusion

Abstract

The invention discloses a wind turbine generator bearing early warning method based on feature fusion. The method comprises the following steps: preprocessing CMS data; obtaining a time domain characteristic index; obtaining trend characteristic indexes; obtaining a frequency domain characteristic index; obtaining envelope characteristic indexes; carrying out feature fusion; training an extreme gradient lifting model; training a function set in the classification model, and constructing a learning objective function of XGBoost; and calculating the learning objective function of the XGBoost. According to the technical scheme, the vibration data of the CMS state monitoring system is utilized, the generator bearing fault mechanism is analyzed from the time domain feature, the trend feature, the frequency domain feature and the envelope feature, the four features are fused, the feature vector representing the running state of the generator is effectively extracted, the method greatly improves the recognition sensitivity of the algorithm for the generator set bearing fault, achieves the fault early warning through employing a limit gradient lifting method, and is higher in accuracy.

Description

technical field [0001] The invention relates to the technical field of wind power generation, in particular to a feature fusion-based early warning method for generator bearings of wind turbines. Background technique [0002] According to data, in recent years, wind energy has become more and more prominent in my country's energy structure because of its clean and renewable characteristics. With the increase in the number of grid-connected units, a large number of units that have been in operation for 2-5 years have a greatly increased probability of failure due to the loss of continuous operation. The operating environment of generator bearings is complex and the working conditions are changeable, and they are prone to damage, looseness, etc. Faults, high maintenance costs and long downtime, resulting in huge economic losses, are a major problem in the operation and maintenance of wind turbines. Therefore, monitoring and early warning of generator operating status is the k...

AI Technical Summary

Problems solved by technology

[0007]The present invention mainly solves the technical problems of the original technical solution, such as single fault identification method, weak generalization ability, and inaccurate fault judgment, and provides a feature fusion-based The wind turbine generator bearing early warning method uses the vibration data of the CMS condition monitoring system to analyze the failure mechanism of the generator bearing from the time domain characteristics, trend characteristics, frequency domain characteristics and envelope characteristics, and integrates the four characteristics to effectively extract The eigenvector representing the operating state of the generator is obtained, which greatly improves the sensitivity of the algorithm to identify the generator bearing fault of the unit. The limit gradient lifting method is used to realize the fault early warning, which has a higher accuracy rate.

Images