A wind turbine pitch motor abnormality warning method and system

Abstract

The present invention provides a wind turbine pitch motor abnormality warning method and system, comprising the following steps: Step 1, obtaining historical data and real-time operating data of the wind turbine to be tested; Step 2, preprocessing the obtained historical data and real-time operating data respectively to obtain two data sets; Step 3, dividing the two obtained data sets according to wind speed, pitch angle and pitch speed respectively to obtain multiple pitch speed intervals corresponding to the two data sets; Step 4, obtaining the pitch motor current threshold corresponding to each pitch speed interval; Step 5, calculating the pitch current mean of each pitch speed interval corresponding to the real-time operating data; Step 6, comparing the obtained pitch current mean with the pitch motor current threshold of the corresponding interval, and judging whether the pitch motor of the wind turbine to be tested is abnormal based on the comparison result; the present invention can detect pitch motor abnormalities earlier, reduce the influence of the pitch motor operating environment, and more accurately reflect whether the pitch motor itself is operating abnormally.

Description

Technical Field

[0001] The present invention belongs to the technical field of current early warning for variable pitch motors of wind turbines, and in particular relates to an abnormality early warning method and system for variable pitch motors of wind turbines. Background Art

[0002] The variable pitch system is an important component of the variable speed constant frequency wind turbine. Its function is to adjust the blade angle in real time according to the changes in wind speed near the rated wind speed, control the absorbed mechanical energy, and reduce the impact of wind on the wind turbine while ensuring maximum energy. In the event of a fault, shutdown or extreme weather, the variable pitch system will adjust the blades to the feathered position to achieve aerodynamic braking and safely shut down the wind turbine. The variable pitch motor is the core component that drives the blade movement, so the variable pitch motor must have high reliability and safety.

[0003] At present, the industry uses pitch motor temperature as the main research object for abnormal prediction and diagnosis of pitch motors. In addition to the heat generated by the pitch motor itself, the heat generated by other electrical components of the hub, the heat dissipation performance of the hub, and temperature sensor abnormalities may all affect the pitch motor temperature. In addition, temperature data has a certain inertia and cannot reflect pitch motor abnormalities in a timely manner. Therefore, using pitch motor temperature to analyze pitch motor abnormalities will result in false alarms and a certain lag. Summary of the Invention

[0004] The purpose of the present invention is to provide a wind turbine pitch motor abnormality warning method and system, which takes the pitch motor current as the research object, directly reflects the operating status of the pitch motor, and can quickly determine whether the pitch motor is abnormal, thereby solving the defects of false alarms and hysteresis in the existing pitch motor abnormality diagnosis method.

[0005] In order to achieve the above object, the technical solution adopted in the present invention is:

[0006] The present invention provides a wind turbine generator set pitch motor abnormality early warning method, comprising the following steps:

[0007] Step 1: Acquire historical data of the wind turbine to be tested, wherein the historical data includes turbine status, wind speed, pitch angle, pitch speed, and pitch motor current;

[0008] Step 2: preprocess the historical data to obtain a data set;

[0009] Step 3: Divide the obtained data set by wind speed, pitch angle, and pitch speed to obtain multiple pitch speed intervals;

[0010] Step 4: Obtain the pitch motor current threshold corresponding to each pitch speed interval;

[0011] Step 5: Acquire real-time operating data of the wind turbine to be tested, and process the obtained real-time operating data according to steps 2 and 3 to obtain multiple pitch speed intervals corresponding to the real-time operating data;

[0012] Step 6: Calculate the mean value of the pitch current in each pitch speed interval corresponding to the real-time operation data;

[0013] Step 7: Compare the obtained pitch current mean value with the pitch motor current threshold value of the corresponding interval in step 4, and determine whether the pitch motor of the wind turbine to be tested is abnormal based on the comparison result.

[0014] A preferred embodiment is that in step 2, the historical data obtained is preprocessed to obtain a data set, and the specific method is:

[0015] From the historical data obtained, the wind speed, pitch angle, pitch speed, and pitch motor current at the same moment when the unit is in normal power generation state, the wind speed is greater than the cut-in wind speed and less than the cut-out wind speed, and the pitch angle is greater than 0° and less than 60° are selected to form a data set.

[0016] A preferred embodiment is that in step 3, the obtained data set is divided according to wind speed, pitch angle and pitch speed to obtain multiple pitch speed intervals. The specific method is:

[0017] S301, dividing the obtained data set by wind speed with a set step distance to obtain multiple wind speed intervals,

[0018] S302, dividing each wind speed interval by a set step size according to the pitch angle to obtain a plurality of pitch angle intervals;

[0019] S303 , dividing each pitch angle interval by a set step size according to the pitch speed to obtain a plurality of pitch speed intervals.

[0020] A preferred embodiment is that in step 4, the pitch motor current threshold corresponding to each pitch speed interval is obtained, and the specific method is:

[0021] Calculate the current mean and variance of the pitch motor corresponding to each pitch speed interval;

[0022] The pitch motor current threshold is calculated based on the obtained mean and variance.

[0023] A preferred embodiment is that in step 7, the obtained pitch current mean value is compared with the pitch motor current threshold value of the corresponding interval in step 4, and whether the pitch motor of the wind turbine to be tested is abnormal is determined based on the comparison result. The specific method is:

[0024] If the obtained pitch current mean value is greater than the pitch motor current threshold value of the corresponding interval in step 4, the pitch speed interval corresponding to the pitch current mean value is an abnormal interval;

[0025] The number of abnormal intervals is counted, wherein, if the proportion of the abnormal intervals is greater than a set threshold, the pitch motor of the wind turbine to be tested is abnormal.

[0026] This preferred embodiment provides a wind turbine pitch motor abnormality warning system, comprising:

[0027] A data acquisition unit is used to acquire historical data and real-time operating data of the wind turbine to be tested, wherein the data includes turbine status, wind speed, pitch angle, pitch speed and pitch motor current;

[0028] A data processing unit is used to pre-process the obtained historical data and real-time operation data to obtain different data sets;

[0029] A data partitioning unit is used to partition the two obtained data sets according to wind speed, pitch angle and pitch speed, respectively, to obtain a plurality of pitch speed intervals corresponding to the two data sets;

[0030] A threshold calculation unit is used to obtain a pitch motor current threshold corresponding to each pitch speed interval corresponding to historical data;

[0031] A mean value calculation unit is used to calculate the mean value of the pitch current in each pitch speed interval corresponding to the real-time operation data;

[0032] The abnormality judgment unit is used to compare the obtained pitch current mean with the pitch motor current threshold of the corresponding interval, and judge whether the pitch motor of the wind turbine to be tested is abnormal based on the comparison result.

[0033] A preferred embodiment is that the data partitioning unit includes:

[0034] The wind speed division module is used to divide the obtained data set into multiple wind speed intervals according to the wind speed with a set step size.

[0035] A pitch angle division unit is used to divide each wind speed interval into a set step according to the pitch angle to obtain multiple pitch angle intervals;

[0036] The pitch speed division unit is used to divide each pitch angle interval into a set step according to the pitch speed to obtain multiple pitch speed intervals.

[0037] Compared with the prior art, the present invention has the following beneficial effects:

[0038] The present invention provides a wind turbine pitch motor abnormality warning method, which obtains the unit's SCADA historical data, divides the three-dimensional bin interval into three-dimensional bin intervals according to wind speed, pitch angle, and pitch speed, eliminates abnormal data in the pitch motor current data of each interval, and establishes a normal operating range interval, then obtains the unit's recent test data, and classifies the data using the same bin division method as the historical data, then compares the pitch motor current in each interval with the normal operating range established by the historical data, and marks whether the pitch motor current in the interval is abnormal, and finally compares the statistical abnormal interval ratio with a given threshold value, and gives a prediction result; the present invention can detect pitch motor abnormalities earlier, reduce the impact of the pitch motor operating environment, and more accurately reflect whether the pitch motor itself is operating abnormally. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is a flow chart of the early warning method of the present invention. DETAILED DESCRIPTION

[0040] The present invention will be further described below with reference to the accompanying drawings.

[0041] like Figure 1 As shown, the present invention provides a wind turbine pitch motor abnormality warning method, comprising the following steps:

[0042] Step 1: Obtain historical data of the wind turbine to be tested from the SCADA system, wherein the historical data includes turbine status, wind speed, pitch angle, pitch speed, and pitch motor current.

[0043] Step 2: The wind speed, pitch angle, pitch speed, and pitch motor current at the same time when the unit is in normal power generation state, the wind speed is greater than the cut-in wind speed and less than the cut-out wind speed, and the pitch angle is greater than 0° and less than 60° are combined into data set D1.

[0044] Step 3: Divide the data set D1 into intervals according to wind speed with a step distance of 1 m to obtain multiple wind speed intervals.

[0045] Step 4: For each wind speed interval, divide the interval into 1° steps according to the pitch angle to obtain multiple pitch angle intervals.

[0046] Step 5: Divide each pitch angle interval into intervals according to the pitch speed in steps of 0.1° / s to obtain multiple pitch speed intervals, and record the pitch motor current value corresponding to each pitch speed interval.

[0047] Step 6: Use the quartile method to eliminate outliers for the pitch motor current in each pitch speed interval, calculate the mean Mpi and variance Epi of the pitch motor current corresponding to each pitch speed interval, and calculate the pitch motor current threshold Thi=Mpi+3Epi.

[0048] Step 7: Obtain the real-time operating data of the wind turbine to be tested from the SCADA system, including turbine status, wind speed, pitch angle, pitch speed, and pitch motor current.

[0049] Step 8: The wind speed, pitch angle, pitch speed, and pitch motor current at the same moment when the unit is in normal power generation state, the wind speed is greater than the cut-in wind speed and less than the cut-out wind speed, and the pitch angle is greater than 0° and less than 60° are combined into data set d1.

[0050] Step 9: Divide the data set d1 into intervals according to steps 3 to 5 to obtain multiple pitch speed intervals corresponding to the real-time operation data.

[0051] Step 10. For each pitch speed interval obtained in step 9, if the data amount meets the requirements, the pitch current mean mpi is calculated. If the pitch motor current mean is greater than the pitch motor current threshold Thi of the corresponding interval in step 6, the interval is marked as an interval with abnormal pitch motor current. If the data amount does not meet the requirements, the data samples of this pitch speed interval are too few and too random, so the data of this interval is discarded and not analyzed.

[0052] Step 11: Count the number of intervals where the pitch motor current is abnormal. If the ratio of the number of abnormal intervals is greater than a set threshold, it is considered that the pitch motor of the wind turbine to be tested is abnormal, and an early warning is triggered.

[0053] The current of the wind turbine pitch motor is mainly determined by the load applied to the blades, and the determining factors of the load applied to the blades are wind speed, blade angle and pitch speed.

[0054] The data set is divided according to wind speed, pitch angle and pitch speed in turn. In fact, the pitch current data is mapped in the four-dimensional grid model, that is, the boundary conditions for modeling similar working conditions are established; the pitch current data in each grid in the four-dimensional grid model represents the sample pitch current set of the pitch system in a certain wind speed range, pitch angle range and pitch speed range. In each set, the pitch current should obey the normal distribution, and the numerical range of each set is determined by the 99% probability distribution boundary, and the current threshold range is calculated.

[0055] Based on the principle of similarity modeling, pitch systems should produce similar operating results under similar operating conditions. Therefore, within small wind speed ranges, blade angle ranges, and pitch speed ranges, the pitch motor current should be highly similar. Based on the wind speed, blade angle, and pitch speed data from the pitch system's operating data, the pitch motor current can be categorized into specific grids. The pitch motor current in each grid should be within the current threshold calculated by the model, allowing for rapid identification of any pitch motor anomalies.

[0056] This preferred embodiment provides a wind turbine pitch motor abnormality warning system, comprising:

[0057] A data acquisition unit is used to acquire historical data and real-time operating data of the wind turbine to be tested, wherein the data includes turbine status, wind speed, pitch angle, pitch speed and pitch motor current;

[0058] A data processing unit is used to pre-process the obtained historical data and real-time operation data to obtain different data sets;

[0059] A data partitioning unit is used to partition the two obtained data sets according to wind speed, pitch angle and pitch speed, respectively, to obtain a plurality of pitch speed intervals corresponding to the two data sets;

[0060] A threshold calculation unit is used to obtain a pitch motor current threshold corresponding to each pitch speed interval corresponding to historical data;

[0061] A mean value calculation unit is used to calculate the mean value of the pitch current in each pitch speed interval corresponding to the real-time operation data;

[0062] The abnormality judgment unit is used to compare the obtained pitch current mean with the pitch motor current threshold of the corresponding interval, and judge whether the pitch motor of the wind turbine to be tested is abnormal based on the comparison result.

[0063] The data partitioning unit includes:

[0064] The wind speed division module is used to divide the obtained data set into multiple wind speed intervals according to the wind speed with a set step size.

[0065] A pitch angle division unit is used to divide each wind speed interval into a set step according to the pitch angle to obtain multiple pitch angle intervals;

[0066] The pitch speed division unit is used to divide each pitch angle interval into a set step according to the pitch speed to obtain multiple pitch speed intervals.

Claims

1. A wind turbine pitch motor abnormality warning method, characterized in that: The following steps are involved: Step 1: Acquire historical data of the wind turbine to be tested, wherein the historical data includes turbine status, wind speed, pitch angle, pitch speed, and pitch motor current; Step 2: preprocess the historical data to obtain a data set; Step 3: Divide the obtained data set by wind speed, pitch angle, and pitch speed to obtain multiple pitch speed intervals; Step 4: Obtain the pitch motor current threshold corresponding to each pitch speed interval; Step 5: Acquire real-time operating data of the wind turbine to be tested, and process the obtained real-time operating data according to steps 2 and 3 to obtain multiple pitch speed intervals corresponding to the real-time operating data; Step 6: Calculate the mean value of the pitch current in each pitch speed interval corresponding to the real-time operation data; Step 7: Compare the obtained pitch current mean value with the pitch motor current threshold value of the corresponding interval in step 4, and determine whether the pitch motor of the wind turbine to be tested is abnormal based on the comparison result.

2. The wind turbine pitch motor abnormality warning method according to claim 1, characterized in that: In step 2, the historical data is preprocessed to obtain a data set. The specific method is: From the historical data obtained, the wind speed, pitch angle, pitch speed, and pitch motor current at the same moment when the unit is in normal power generation state, the wind speed is greater than the cut-in wind speed and less than the cut-out wind speed, and the pitch angle is greater than 0° and less than 60° are selected to form a data set.

3. The wind turbine generator set pitch motor abnormality early warning method according to claim 1, characterized in that: In step 3, the obtained data set is divided according to wind speed, pitch angle and pitch speed to obtain multiple pitch speed intervals. The specific method is: S301, dividing the obtained data set by wind speed with a set step distance to obtain multiple wind speed intervals, S302, dividing each wind speed interval by a set step size according to the pitch angle to obtain a plurality of pitch angle intervals; S303 , dividing each pitch angle interval by a set step size according to the pitch speed to obtain a plurality of pitch speed intervals.

4. The wind turbine generator set pitch motor abnormality early warning method according to claim 1, characterized in that: In step 4, the pitch motor current threshold corresponding to each pitch speed interval is obtained. The specific method is: Calculate the current mean and variance of the pitch motor corresponding to each pitch speed interval; The pitch motor current threshold is calculated based on the obtained mean and variance.

5. The wind turbine pitch motor abnormality warning method according to claim 1, characterized in that: In step 7, the obtained pitch current mean value is compared with the pitch motor current threshold value of the corresponding interval in step 4, and whether the pitch motor of the wind turbine to be tested is abnormal is determined based on the comparison result. The specific method is: If the obtained pitch current mean value is greater than the pitch motor current threshold value of the corresponding interval in step 4, the pitch speed interval corresponding to the pitch current mean value is an abnormal interval; The number of abnormal intervals is counted, wherein, if the proportion of the number of abnormal intervals is greater than a set threshold, the pitch motor of the wind turbine to be tested is abnormal.

6. A wind turbine pitch motor abnormality warning system, characterized in that: include: A data acquisition unit is used to acquire historical data and real-time operating data of the wind turbine to be tested, wherein the data includes turbine status, wind speed, pitch angle, pitch speed and pitch motor current; A data processing unit is used to pre-process the obtained historical data and real-time operation data to obtain different data sets; A data partitioning unit is used to partition the two obtained data sets according to wind speed, pitch angle and pitch speed, respectively, to obtain a plurality of pitch speed intervals corresponding to the two data sets; A threshold calculation unit is used to obtain a pitch motor current threshold corresponding to each pitch speed interval corresponding to historical data; A mean value calculation unit is used to calculate the mean value of the pitch current in each pitch speed interval corresponding to the real-time operation data; The abnormality judgment unit is used to compare the obtained pitch current mean with the pitch motor current threshold of the corresponding interval, and judge whether the pitch motor of the wind turbine to be tested is abnormal based on the comparison result.

7. The wind turbine pitch motor abnormality warning system according to claim 6, characterized in that: The data partitioning unit includes: The wind speed division module is used to divide the obtained data set into multiple wind speed intervals according to the wind speed with a set step size. A pitch angle division unit is used to divide each wind speed interval into a set step according to the pitch angle to obtain multiple pitch angle intervals; The pitch speed division unit is used to divide each pitch angle interval into a set step according to the pitch speed to obtain multiple pitch speed intervals.

Images