A Fault Prediction Method for Wind Power Converter

Abstract

The invention discloses a fault prediction method for a wind power converter, which comprises the following steps: dividing all wind power generators in a wind farm into several wind power generator subclusters. For each wind turbine sub-cluster, the historical monitoring signal of the wind power converter sub-cluster is used as the original feature library, and the main feature matrix of the wind power converter sub-cluster at each sampling time is extracted from the original feature library through the sparse self-encoding algorithm , based on the fast clustering algorithm to search for the wind power converter of the cluster center at each sampling moment, calculate the cumulative eccentricity distance matrix of the wind power converter sub-cluster, normalize the cumulative eccentricity distance matrix and set the early warning threshold, comprehensive The fault prediction results of wind power converters in all wind turbine sub-clusters can be used to obtain the fault prediction results of wind power converters in wind farms. The invention realizes the prediction of the fault of the wind power converter, is beneficial to the maintenance personnel to establish a reasonable and effective maintenance plan, and ensures the safe and stable operation of the power grid.

Description

technical field [0001] The invention relates to a fault prediction method for a wind power converter, belonging to the technical field of power grids. Background technique [0002] A wind turbine is a kind of electrical equipment that converts wind energy into mechanical energy, and drives the rotor of the generator to rotate through the mechanical energy, thereby outputting alternating current. The wind power converter is a key component of the wind turbine, and its health status directly affects the safety of the wind turbine operation, and then affects the stable operation of the entire wind farm. Since wind turbines are often located in remote areas with abundant wind resources, and the capacity of wind power generation systems continues to increase, the power grid also puts forward higher requirements for the health status assessment technology of wind power converters. Therefore, real-time monitoring of the operating status of wind turbines and timely and accurate pre...

AI Technical Summary

Problems solved by technology

[0003] At present, the maintenance of wind power converters usually adopts after-the-fact maintenance, and it is difficult for maintenance personnel to grasp the health status of wind power converters in real time

Fault prediction technology can help maintenance personnel to predict possible faults of wind power converters in advance. However, most of the existing fault prediction methods rely on the operation data of the entire life cycle of the equipment, and the established fault prediction model is only applicable to a single device. The portability of the model is poor, and there is still a lack of an effective and generalizable fault prediction method for wind power converters

Images