Wind power plant fault wind speed sensor wind speed prediction method and device and storage medium

Abstract

The invention relates to a wind power plant fault wind speed sensor wind speed prediction method and device and a storage medium, and the method comprises the steps: carrying out the community division of wind power plant units according to the wind speed spatial correlation, and dividing a plurality of units with higher wind speed spatial correlation into one community; positioning a community where a fault wind speed sensor is located; and according to the actually-measured wind speed data of the wind speed sensors, screening the associated unit with the optimal wind speed correlation with the fault wind speed sensor in a community in a rolling mode, inputting the actually-measured wind speed sequence of the associated unit into a pre-trained wind speed prediction model, and enabling the wind speed prediction model to output the predicted wind speed sequence of the fault wind speed sensor. Compared with the prior art, the invention has the advantages of high prediction speed, high accuracy and the like.

Description

technical field [0001] The invention relates to the technical field of wind power generation, in particular to a wind speed prediction method, device and storage medium of a wind farm fault wind speed sensor. Background technique [0002] As an important parameter of wind turbine operation control, wind speed directly affects the operation mode of wind turbine. The functions of wind turbine control system that need to input wind speed and wind direction parameters mainly include: (1) The unit automatically starts and stops according to the input wind speed signal value, connects to the grid or Off-grid operation; (2) When the wind speed changes, the unit can automatically perform speed conversion and power control; (3) When the wind direction changes, the unit can perform yaw operation to complete automatic wind control. The wind speed and direction parameters of wind turbines are mainly measured by sensors exposed on the outside of the fuselage. The health of the sensors ha...

AI Technical Summary

Problems solved by technology

[0003] (1) Destructive failure: the sensor stops running or the system has no wind speed signal input, and the wind speed data is missing or missing, for example: the power supply line of the wind speed sensor is damaged, causing the power supply voltage of the wind speed sensor to be unstable, and the wind speed data is missing;

[0004] (2) Non-destructive failure: the sensor malfunctions, and the measurement data deviates from the normal value. For example, due to factors such as thunderstorms and bird impacts, the wind cup or rotating shaft of the wind speed sensor is deformed, causing the sensor to rotate stuck and inflexible, etc. Problems, long-term inaccurate measurement data;

For example: storms, rainstorms, hail and other weather will affect the performance of the lubricating oil of the rolling bearing, and gradually decay with the accumulation of time. Data is progressively inaccurate

[0006] In actual engineering applications, there is a sensor fault diagnosis module in the wind turbine SCADA system. The basic logic of the diagnosis is to set the upper and lower thresholds of wind speed. When the measured value of the sensor exceeds the threshold range, the system alarms, the sensor fails, and the unit is in the operating state of no input wind speed signal. , prone to operational accidents

Images