US 12,669,111 B2Granted

Method and device for fault early warning of a yaw system of a wind turbine generator set

OwnerXueliang Wang, Lianbo Liu +5inventors

InventorsXueliang Wang, Lianbo Liu, Dengke Ma, Xingzhong Liu, Bosong Ding, Xiaokang Chu, Qingyong Wu

Life of this patent

Estimating the term…

Loading patent…

Abstract

The invention provides a method and a device for fault diagnosis of a yaw system in a wind turbine, and relates to the technical field of wind turbines. The method comprises the following steps: acquiring monitoring data collected in a yaw system, inputting the monitoring data into a yaw fault diagnosis model, and outputting a fault diagnosis result, wherein the fault diagnosis model is obtained by training known fault diagnosis results and corresponding monitoring data, and the fault diagnosis result comprises at least one of the following: the position of a yaw sensor is shifted, the yaw sensor is damaged, the yaw contactor is stuck, the hardware of a yaw motor/reducer is damaged, and the yaw motor is braked, In the working process, the monitoring data collected by the yaw system can be input into the yaw fault diagnosis model in real time, and the yaw fault diagnosis model can be used to determine whether the yaw system has a fault and the specific fault diagnosis results when the fault occurs. In this way, the operation and maintenance personnel can be prevented from going to the aircraft seat for inspection, and the fault diagnosis efficiency of the yaw system can be improved.

Claims8

Dependent claims

A method for fault early warning of a yaw system of a wind turbine generator set, comprising:

monitoring real-time data of the yaw system of the wind turbine generator set, wherein the real-time data includes an effective output power and an incoming wind speed, and the incoming wind speed includes an average incoming wind speed at the effective output power and an average incoming wind speed at a rated power;
inputting the effective output power, the average incoming wind speed at the effective output power, and the average incoming wind speed at the rated power into a pre-constructed fault identification model, which outputs a fault identification result;
and
performing the fault early warning based on the fault identification result, including:
if the fault identification result indicates a fault, then performing a first classification on the fault identification result to determine a first fault type, wherein the first fault type comprises an actuator fault and a wind vane fault of the yaw system;
and performing the fault early warning based on the actuator fault and the wind vane fault, respectively;
wherein said performing a first classification on the fault identification result to determine a first fault type includes:
acquiring first wind direction data of a wind vane of the yaw system of the wind turbine generator set in a first time period, and constructing a first wind direction sequence;
acquiring second wind direction data of a wind direction of a wind farm in the first time period, and constructing a second wind direction sequence;
determining a similarity value between the first wind direction sequence and the second wind direction sequence;
if the similarity value is greater than or equal to a similarity threshold, then determining that the first fault type is the actuator fault of the yaw system;
and if the similarity value is less than the similarity threshold, then determining that the first fault type is the wind vane fault;
and
wherein the fault identification model is the following formula:
V
=
1
-
P
/
V
_
3
P
0
/
V
0
_
3
;
in the formula, V represents the fault identification result, with a value range of (0, 1);
P represents the effective output power;
P0 is the rated power of the wind turbine generator set;
V represents the average incoming wind speed at the effective output power;
and V0 represents the average incoming wind speed at the rated power.

33 more elements

A device for fault early warning of a yaw system of a wind turbine generator set, comprising:

a detection module configured to monitor real-time data of the yaw system of the wind turbine generator set, wherein the real-time data includes an effective output power and an incoming wind speed, and the incoming wind speed includes an average incoming wind speed at the effective output power and an average incoming wind speed at a rated power;
an identification module configured to input the effective output power, the average incoming wind speed at the effective output power, and the average incoming wind speed at the rated power into a pre-constructed fault identification model, and output a fault identification result;
and
an early warning module configured to perform the fault early warning based on the fault identification result, including:
if the fault identification result indicates a fault, then performing a first classification on the fault identification result to determine a first fault type, wherein the first fault type comprises an actuator fault and a wind vane fault of the yaw system;
and performing the fault early warning based on the actuator fault and the wind vane fault, respectively;
wherein said performing a first classification on the fault identification result to determine a first fault type includes:
acquiring first wind direction data of a wind vane of the yaw system of the wind turbine generator set in a first time period, and constructing a first wind direction sequence;
acquiring second wind direction data of a wind direction of a wind farm in the first time period, and constructing a second wind direction sequence;
determining a similarity value between the first wind direction sequence and the second wind direction sequence;
if the similarity value is greater than or equal to a similarity threshold, then determining that the first fault type is the actuator fault of the yaw system;
and if the similarity value is less than the similarity threshold, then determining that the first fault type is the wind vane fault;
and
wherein the fault identification model is the following formula:
V
=
1
-
P
/
V
_
3
P
0
/
V
0
_
3
;
in the formula, V represents the fault identification result, with a value range of (0, 1);
P represents the effective output power;
P0 is the rated power of the wind turbine generator set;
V represents the average incoming wind speed at the effective output power;
and V0 represents the average incoming wind speed at the rated power.

33 more elements

Dependencies are inferred from the claim text.

Facts

Application: 19/356,117Filed 11 Oct 2025
Priority: CN 202411416502.211 Oct 2024
Published: US 2026/0036114 A15 Feb 2026
Granted: 30 Jun 2026
Term ends: Not estimatedThe source records don’t support an estimate.

Classification7 codes

F03D 17/014
For detecting abnormalities or damage: indicative of a fault or failure
F03D 17/0065
Using computation methods, e.g. neural networks: for diagnostics
F03D 17/029
Characterised by the component being monitored or tested: blade pitch or yaw drive systems, e.g. pitch or yaw angle
F05B 2260/80
Function: diagnostics