CN114962173A - Method and device for detecting yawing abnormity of wind driven generator and electronic equipment - Google Patents

Abstract

The application provides a method and a device for detecting yaw abnormity of a wind driven generator and electronic equipment. The method for detecting the yaw abnormality of the wind driven generator comprises the following steps: acquiring wind direction data, yaw frequency data and engine room position data of the wind driven generator; determining the wind deflection angle of the wind driven generator according to the cabin position data and the wind direction data; and determining whether the wind driven generator has abnormal yaw according to the wind deflection angle and the yaw frequency data. Therefore, the accuracy of detecting the yaw abnormity of the wind driven generator can be improved.

Description

Wind turbine yaw abnormality detection method, device and electronic device

technical field

The present invention relates to the technical field of abnormality detection of wind turbines, in particular to a method, device and electronic equipment for detecting abnormality of yaw of wind turbines.

Background technique

With the development of wind power generation technology, wind turbines, like hydraulic machinery, act as a power source to replace human and animal power, and play an important role in the development of productivity. Wind turbines convert wind energy into mechanical energy. The wind turbine includes a yaw system. The function of the yaw system is to align the wind direction quickly and smoothly when the direction of the wind speed vector changes, so that the wind rotor can obtain the maximum wind energy.

In actual operation, the yaw system will be abnormal, which will affect the power generation stability of the wind turbine, and will also cause serious hardware failures and even safety accidents. Therefore, the related technology will perform statistical analysis on the yaw times of the wind turbine and wind turbine in advance, and identify the wind turbine with frequent yaw.

However, due to the complex operation system of wind turbines, it is difficult to reflect the yaw situation of wind turbines by only using the number of yaw of wind turbines as the yaw data of wind turbines, resulting in low accuracy of yaw detection and early warning of wind turbines.

SUMMARY OF THE INVENTION

The present application provides a method, device, and electronic device for abnormal yaw detection of a wind turbine. The method has high accuracy in yaw detection of a wind turbine.

The present application provides a wind turbine yaw abnormality detection method, comprising:

Obtain wind direction data, yaw times data and cabin position data of the wind turbine;

According to the nacelle position data and the wind direction data, determine the windward deflection angle of the wind turbine;

It is determined whether the wind turbine has an abnormal yaw according to the yaw angle to the wind and the data of the number of yaw times.

Further, determining whether the wind turbine has an abnormal yaw according to the yaw angle against the wind and the yaw times data includes:

determining the mean value of the deflection angle to the wind at a plurality of times within a predetermined time period of the wind turbine;

determining an angle threshold according to the mean value of the deflection angles to the wind of the plurality of wind turbines;

determining the yaw number data of the wind turbine within the predetermined time period;

determining the yaw times threshold according to the yaw times data of a plurality of the wind turbines;

When there is at least one of the mean value of the yaw angle to the wind of the wind turbine exceeds the angle threshold, and the yaw number data of the wind turbine exceeds the yaw number threshold, it is determined that the wind turbine The generator yaw is abnormal.

Further, determining the yaw times threshold according to the yaw times data of a plurality of the wind turbines includes:

determining an average value of the yaw number data for a plurality of the wind turbines;

determining a standard deviation of the yaw number data for a plurality of the wind turbines;

The yaw number threshold is determined according to the average value of the yaw number data and the standard deviation of the yaw number data.

Further, determining the angle threshold according to the mean value of the wind deflection angles of the plurality of wind turbines includes:

determining an average value of the average values of the deflection angles to the wind for a plurality of the wind turbines;

determining the standard deviation of the mean value of the deflection angles to the wind for a plurality of the wind turbines;

The angle threshold is determined according to the mean value of the mean values of the opposite wind deflection angles and the standard deviation of the mean values of the opposite wind deflection angles.

Further, the predetermined period of time includes multiple sub-periods, and the multiple sub-periods have the same time length;

The determining whether the wind turbine yaw is abnormal according to the yaw angle to the wind and the yaw times data includes:

According to the data of the yaw angle against the wind and the number of yaw times in the sub-time period, determine whether the plurality of wind turbines in the sub-time period have abnormal yaw;

After determining whether the wind turbine has an abnormal yaw according to the yaw angle to the wind and the yaw times data, the method further includes:

Mark the wind turbines with abnormal yaw in the sub-time period as abnormal yaw wind turbines;

Count the times of marking of the same abnormal yaw fan in the predetermined time period;

According to the marking times and the number of segments of the multiple sub-time segments, the failure level of the same yaw abnormal fan is determined.

Further, determining the failure level of the same abnormal yaw fan according to the number of marks and the number of segments of the plurality of sub-times includes:

Determining the abnormal yaw fan whose number of times of marking is greater than half of the number of segments of the plurality of sub-periods as a high-risk abnormal yaw fan;

Determining the abnormal yaw wind turbine with the number of marking times equal to half of the number of segments in the sub-time segment as a medium-risk abnormal yaw wind turbine;

The abnormal yaw wind turbines whose marking times are greater than zero and less than half of the number of segments of the sub-period are determined as low-risk abnormal yaw wind turbines.

Further, the method includes:

acquiring working condition data of multiple wind turbines in the wind farm, where the working condition data includes the wind direction data and wind speed data;

According to the wind direction data and the wind speed data, classifying a plurality of wind turbines in the wind farm to obtain a plurality of wind turbine clusters;

The determining, according to the nacelle position data and the wind direction data, the deflection angle to the wind of the wind turbine includes:

According to the nacelle position data and the wind direction data of the plurality of wind turbines in the wind turbine cluster, determining the deflection angle to the wind of the plurality of wind turbines in the wind turbine cluster;

The determining whether the wind turbine yaw is abnormal according to the yaw angle to the wind and the yaw times data includes:

Whether the wind turbines in the wind turbine cluster are abnormally yawed is determined according to the data of the yaw angle and the yaw times of the plurality of wind turbines in the wind turbine cluster.

Further, according to the wind direction data and the wind speed data, the multiple wind turbines in the wind farm are classified to obtain multiple fan clusters, including:

determining the degree of correlation of the working condition data of every two wind turbines among the multiple wind turbines in the wind farm;

Every two wind turbines whose correlation is greater than the correlation threshold are determined to belong to the same wind turbine cluster.

Further, the determining the correlation degree of the working condition data of every two wind turbines among the multiple wind turbines in the wind farm includes:

determining the correlation degree of the wind speed data and the correlation degree of the wind direction data;

The mean value of the correlation degree of the wind speed data and the correlation degree of the wind direction data is determined as the correlation degree of the working condition data.

Further, after the determination of the correlation of the working condition data of every two wind turbines among the multiple wind turbines in the wind farm, the method further includes:

A wind turbine whose correlation degree with other wind turbines in the wind farm except the wind turbine cluster is not greater than the correlation degree threshold is determined as a wind turbine with abnormal working conditions.

The present application provides a wind turbine yaw abnormality detection and early warning device, comprising:

The acquisition module is used to acquire the wind direction data, yaw times data and cabin position data of the wind turbine;

a first processing module, configured to determine the windward deflection angle of the wind turbine according to the nacelle position data and the wind direction data;

The second processing module is configured to determine whether the wind turbine has an abnormal yaw according to the yaw angle to the wind and the data of the yaw times.

The present application provides an electronic device, including a processor and a memory;

memory for storing computer programs;

The processor is configured to implement the method described in any one of the above when executing the program stored in the memory.

The present application provides a computer-readable storage medium on which a program is stored, and when the program is executed by a processor, implements any of the methods described above.

In some embodiments, a method for detecting abnormal yaw of a wind turbine according to the present application determines whether the yaw of the wind turbine is abnormal through the yaw number data and the yaw angle to the wind that can reflect the yaw situation of the wind turbine. Compared with only considering the number of yaw of the wind turbine in the related art, the present application considers more factors related to the yaw of the wind turbine, which can improve the accuracy of abnormal detection of the yaw of the wind turbine.

Description of drawings

1 shows a schematic flowchart of a method for detecting abnormal yaw of a wind turbine according to an embodiment of the present application;

FIG. 2 is a schematic flowchart of step 130 in the wind turbine yaw abnormality detection method shown in FIG. 1;

FIG. 3 is a detailed schematic flow chart of the method for detecting yaw abnormality of the wind turbine shown in FIG. 1;

Fig. 4 is a schematic flow chart when there are multiple wind turbines in the wind turbine yaw abnormality detection method shown in Fig. 1;

Fig. 5 shows the correlation degree heat map between multiple wind turbines in the wind turbine yaw abnormality detection method shown in Fig. 1;

6 is a schematic flowchart of an application example of the method for detecting yaw abnormality of a wind turbine according to an embodiment of the present application;

7 is a schematic diagram of a module of a wind turbine yaw abnormality detection device provided in an embodiment of the present application;

FIG. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed ways

Exemplary embodiments will be described in detail herein, examples of which are illustrated in the accompanying drawings. Where the following description refers to the drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with one or more embodiments of this specification. Rather, they are merely examples of apparatus and methods consistent with some aspects of one or more embodiments of this specification, as recited in the appended claims.

It should be noted that: in other embodiments, the steps of the corresponding methods are not necessarily performed in the order shown and described in this specification. In some other embodiments, the method may include more or fewer steps than described in this specification. In addition, a single step described in this specification may be decomposed into multiple steps for description in other embodiments; and multiple steps described in this specification may also be combined into a single step in other embodiments. describe.

In order to solve this technical problem, an embodiment of the present application provides a method for detecting abnormal yaw of a wind turbine, which determines whether the wind turbine has abnormal yaw through the yaw number data and the yaw angle to the wind that can reflect the yaw situation of the wind turbine. , compared with only considering the number of yaw of the wind turbine in the related art, the present application considers more factors related to the yaw of the wind turbine, which can improve the accuracy of abnormal detection of the yaw of the wind turbine.

FIG. 1 is a schematic flowchart of a method for detecting abnormal yaw of a wind turbine according to an embodiment of the present application. The method may include the following steps 110 to 130:

Step 110: Obtain wind direction data, yaw times data and cabin position data of the wind turbine.

The nacelle position data, wind direction data and yaw times data can reflect the yaw of the wind turbine.

Wherein, the wind generator may be a single wind generator. In this way, it is possible to detect whether the yaw of a single wind turbine is abnormal. The wind turbine may also be a plurality of wind turbines in a wind farm. In this way, it is possible to detect whether the yaw of multiple wind turbines is abnormal. See below for details.

Step 120: Determine the deflection angle to the wind of the wind turbine according to the nacelle position data and the wind direction data.

The nacelle position data may include angle data of the nacelle. The deflection angle to the wind is the angle of the nacelle relative to the wind direction, that is, the angle between the nacelle and the wind direction. The angle of the nacelle at the initial position is 0 degrees, which is the reference position. After the cabin yaws, it deviates from this initial position, and the cabin position data is the angle data of the current position of the cabin relative to the initial position, which is the yaw angle.

Step 130: Determine whether the yaw of the wind turbine is abnormal according to the data of the yaw angle to the wind and the number of yaw times.

In the embodiment of the present application, both the yaw number data and the yaw angle to the wind of the wind turbine can reflect whether the wind turbine has an abnormal yaw. Considering more factors related to the yaw of the wind turbine, the accuracy of the abnormal detection of the yaw of the wind turbine can be improved. Moreover, the method for detecting and early warning of frequent yaw times of wind turbines in the related art is to realize the detection and early warning of frequent yaw times of wind turbines by calculating the frequent yaw probability of wind turbines, and the frequent yaw probability reflects wind power generation. Compared with the probability of frequent yaw, the yaw frequency data of the wind turbine and the yaw angle to the wind are more conducive to reflect whether the actual wind turbine has an abnormal yaw, and improve the yaw deviation of the wind turbine. accuracy of anomaly detection.

FIG. 2 is a schematic flowchart of step 130 in the wind turbine yaw abnormality detection method shown in FIG. 1 . As shown in FIG. 2 , in some embodiments of step 130 , step 130 further includes steps 131 to 135 .

Step 131: Determine the mean value of the deflection angle to the wind at multiple times within a predetermined time period of the wind turbine. The preset time period may be a time period set by user requirements. The time may also be a time set by the user as required. The preset time period is, for example, 1 day or more, or even longer. The time, such as 1 hour or more, or even longer, is not limited here. Exemplarily, the preset time period may be 24 hours, and the moment may be 1 hour.

The preset time period may include an entire period of time. In this way, the user can determine whether the yaw of the wind turbine is abnormal in a whole period of time. The preset time period may include multiple sub-time periods. In this way, the user can determine whether the wind turbine has an abnormal yaw in multiple sub-times. By calculating the yaw abnormality multiple times, the abnormal yaw fan can be more accurately determined, and the data volume of each sub-time period can be calculated multiple times. Smaller, so that the rate of each calculation is faster. See below for details.

Step 132: Determine an angle threshold according to the mean value of the yaw angles of the plurality of wind turbines, and the angle threshold is used to determine whether the wind turbine has an abnormal yaw.

为对风偏向角的平均值μ₁及2倍的标准差σ₁之和，即

角度下限阈值

为对风偏向角的平均值μ₁及2倍的标准差σ₁之差，比如

如此角度阈值不是固定的阈值，会随着对风偏向角的均值的平均值及对风偏向角的均值的标准差变化，提高角度阈值确定的准确性。The above-mentioned step 132 may be implemented through various embodiments. In some embodiments, the above-mentioned step 132 further includes the first step to the third step. The first step, in some embodiments, is to determine the average value of the mean values of the deflection angles to the wind of the plurality of wind turbines. The mean value can reflect the change trend of the overall data, and individual abnormal data will not affect the change trend of the overall data. Therefore, the subsequent use of the mean value is more conducive to determining a reasonable threshold. The average value of the wind deflection angle can reflect the changing trend of the wind deflection angle. In the second step, the standard deviation of the mean value of the wind deflection angles of the plurality of wind turbines is determined. The standard deviation can reflect the fluctuation of the wind deflection angle, that is, the standard deviation reflects the variation range of the data. The smaller the mean value of the wind deflection angle and the smaller the standard deviation of the wind deflection angle, the more stable the wind deflection angle, and the more stable the wind turbine is. In the third step, the angle threshold is determined according to the average value of the mean value of the wind deflection angle and the standard deviation of the mean value of the wind deflection angle. The angle threshold includes the upper and lower angle thresholds, and the upper and lower angle thresholds.

is the sum of the mean value μ ₁ and 2 times the standard deviation σ ₁ of the wind deflection angle, namely

Angle lower limit threshold

is the difference between the mean value of the wind deflection angle μ ₁ and 2 times the standard deviation σ ₁ , such as

In this way, the angle threshold is not a fixed threshold, and will change with the average value of the mean value of the wind deflection angle and the standard deviation of the mean value of the wind deflection angle, so as to improve the accuracy of determining the angle threshold value.

The steps in other embodiments of the above-mentioned step 132 are similar to the steps in the above-mentioned embodiments of the above-mentioned step 132, and the difference lies in the second step in this other embodiment, which can determine the deviation of the wind deflection angle of the plurality of wind turbines. Variance of the mean, and then square the variance to get the standard deviation. The details are not repeated here.

Step 133 , determining the yaw times data of the wind turbine within a predetermined time period.

Step 134: Determine the yaw times threshold according to the yaw times data of the multiple wind turbines.

及偏航次数下限阈值

偏航次数上限阈值

为偏航次数数据的平均值μ₂及2倍的标准差σ₂之和，即

偏航次数下限阈值

为偏航次数数据的平均值μ₂及2倍的标准差σ₂之差，比如

如此使用偏航次数数据的平均值和偏航次数数据的标准差，更好地反映偏航次数数据相较于平均值的波动情况，从而确定出更为合理的偏航次数阈值。The above-mentioned step 134 may be implemented by various embodiments. In some embodiments, the above-mentioned step 134 further includes the first to third steps. The first step is to determine the average value of the yaw times data of multiple wind turbines. The average value of the yaw times data can reflect the changing trend of the yaw times data. The second step is to determine the standard deviation of the yaw times data of multiple wind turbines. The standard deviation can reflect the fluctuation of the yaw times data. The smaller the average value of the yaw times data and the smaller the standard deviation of the yaw times data, the more stable the yaw times data. In the third step, the threshold of the yaw times is determined according to the average value of the yaw times data and the standard deviation of the yaw times data. The yaw times threshold includes the upper threshold of yaw times

and the lower limit threshold of yaw times

The upper threshold of the number of yaw

is the sum of the average μ ₂ of the yaw times data and the standard deviation σ ₂ of 2 times, namely

Yaw times lower limit threshold

is the difference between the average μ ₂ of the yaw times data and the standard deviation σ ₂ times 2 times, such as

In this way, the average value of the yaw times data and the standard deviation of the yaw times data are used to better reflect the fluctuation of the yaw times data compared with the average value, so as to determine a more reasonable threshold for the yaw times.

The steps in some other embodiments of the above-mentioned step 134 are similar to the steps in the above-mentioned embodiments of the above-mentioned step 134, the difference is that the second step in this another embodiment can determine the yaw times data of multiple wind turbines The variance of , and then square root the variance to get the standard deviation. The details are not repeated here.

Step 135, when there is at least one of the mean value of the wind turbine yaw angle to the wind exceeds the angle threshold and the yaw number data of the wind turbine exceeds the yaw number threshold, it is determined that the wind turbine yaw is abnormal. In this way, the angle threshold and the yaw number threshold are determined respectively, which are not fixed thresholds. The angle threshold and the yaw number threshold are respectively a threshold value that changes with the wind direction angle and the yaw number data. , in line with the operating conditions of wind turbines, and improve the accuracy of yaw anomaly detection.

FIG. 3 is a schematic diagram showing a detailed flow of the method for detecting yaw abnormality of the wind turbine shown in FIG. 1 . As shown in FIG. 3 , the wind turbine yaw abnormality detection method may include steps 210 to 260 .

Step 210: Acquire wind direction data, yaw times data and nacelle position data of multiple wind turbines in a predetermined time period, where the predetermined time period includes multiple sub-times, and the sub-times have the same time length. For example, the preset time period may be 24 hours, the sub-time period may be 6 hours, the number of sub-time periods may be 4, and the number of cycles of executing steps 220 to 260 is 4 times in total. The fan is marked up to 4 times, so the amount of data processed each time is small, and the amount of data marked in total is also small, which improves the processing efficiency.

Step 220: Determine, according to the nacelle position data and the wind direction data, the deflection angles to the wind of the plurality of wind turbines in the sub-time period.

Step 230: Determine whether the yaw of the multiple wind turbines in the sub-period is abnormal according to the data of the yaw angle against the wind and the number of yaw times in the sub-period.

In this step 230, after it is determined whether the yaw abnormality of the multiple wind turbines in the sub-period is abnormal, if the wind turbines are not yaw abnormally, these wind turbines with normal yaw can record the number of their wind turbines, or they can not Record the numbers of these wind turbines with normal yaw. When the yaw of the wind turbine is abnormal, the subsequent steps 240 to 260 are executed to facilitate the subsequent early warning to the user for preventive protection.

Step 240 , marking the wind turbines with abnormal yaw in the sub-time period as wind turbines with abnormal yaw.

In step 240, counting the times of marking of the same abnormal yaw fan within a predetermined time period is to mark the same abnormal yaw fan according to the unique identifier of the abnormal yaw fan. The unique identifier may be the number of the abnormal yaw fan. In this way, the same yaw abnormal fan can be accurately marked to avoid omission or error.

Step 250 , count the times of marking of the same abnormal yaw fan in a predetermined time period.

Step 260: Determine the failure level of the same fan with abnormal yaw according to the number of times of marking and the number of sub-periods. After this step 260, the method further includes performing abnormal yaw warning for the fault level. This is convenient for reminding users and timely protection.

The above-mentioned step 260 may be implemented through various embodiments. In some embodiments, the above-mentioned step 260 includes determining the abnormal yaw wind turbines whose marking times are greater than half of the number of segments of the plurality of sub-periods as high-risk abnormal yaw wind turbines. The abnormal yaw wind turbine whose number of marking times is equal to half of the number of segments in the sub time period is determined as the medium-risk abnormal yaw wind turbine. The abnormal yaw wind turbines whose marking times are greater than zero and less than half of the number of sub-periods are determined as low-risk abnormal yaw wind turbines. In this way, by marking the abnormal yaw fan, it is more conducive to reflect the abnormal degree of the abnormal yaw fan, and at the same time, the error caused by a single statistical data can be reduced, and the accuracy of determining different fault levels of the abnormal yaw fan can be improved. In other embodiments, the above-mentioned step 260 includes determining the occurrence probability of abnormality of the same yaw abnormal wind turbine by taking the ratio of the number of marking times to the number of segments of the multiple sub-time segments. An abnormal yaw fan with an abnormal probability greater than 1/2 is determined as a high-risk yaw abnormal fan. The abnormal yaw fan with an abnormal probability equal to 1/2 is determined as a medium-risk yaw abnormal fan. The abnormal yaw fan with an abnormal probability of less than 1/2 is determined as a low-risk abnormal yaw fan. Exemplarily, if the number of sub-time periods is 20, and the number of times of marking is 12, the abnormal probability of occurrence of the same yaw abnormal wind turbine is equal to 1/2, and the yaw abnormal wind turbine is a medium-risk yaw abnormal wind turbine.

In this embodiment, when a number of abnormal yaw fans are counted in multiple sub-periods in the same predetermined time period, it is found that one or some abnormal yaw fans are continuously appearing, indicating that the abnormal yaw fan has abnormal yaw. The degree is more serious, and the deviation caused by the single statistical data is avoided, so that the detection of the abnormal yaw fan is more accurate.

In the related art method for frequent detection and early warning of wind turbine yaw times, the object of analysis is the wind turbine in the wind farm. However, the environmental conditions of wind turbines are different, and the working condition data are quite different, such as wind turbines at the top of the mountain and wind turbines at the foot of the mountain. Therefore, the yaw frequency of the wind turbines of multiple wind turbines in the wind farm is detected at the same time, resulting in a low accuracy of the yaw detection and early warning of the wind turbines.

FIG. 4 is a schematic flowchart when there are multiple wind turbines in the wind turbine yaw abnormality detection method shown in FIG. 1 . When the wind turbine is a plurality of wind turbines in the wind farm, the method for detecting abnormal yaw of the wind turbine includes steps 310 to 360, which are described in detail as follows:

1 and 4, in step 310, the working condition data of multiple wind turbines in the wind farm are acquired, and the working condition data includes wind direction data and wind speed data.

The working condition data is used to reflect the working condition of the environment where the wind turbine is located. The environment where the wind turbine is located is, for example, the top of the mountain or the foot of the mountain, and the working conditions of the corresponding wind turbine are quite different. Exemplarily, the working condition data includes the working condition data of the wind turbine at the top of the mountain and the working condition data of the wind turbine at the foot of the mountain. Subsequently, according to the different working condition data, multiple fan clusters are classified to make it easier to distinguish different working conditions. In this way, it is more accurate to further determine whether the yaw of the wind turbine is abnormal.

Step 320, according to the wind direction data and the wind speed data, classify the multiple wind turbines in the wind farm to obtain multiple fan clusters. Distinguishing the wind turbines with different working condition data in this way can improve the accuracy of abnormal working conditions of the wind turbine.

The above-described step 320 may adopt various embodiments. In some embodiments, the above step 320 may include using a correlation algorithm to classify multiple wind turbines in the wind farm according to the wind direction data and the wind speed data to obtain multiple wind turbine clusters. In this way, the wind turbines with similar working conditions can be determined through the correlation algorithm, which is more beneficial to determine the wind turbines with abnormal working conditions.

Further, the above-mentioned step 320 further includes the first step of determining the correlation degree of the working condition data of every two wind turbines among the multiple wind turbines in the wind farm. In the second step, the two wind turbines whose correlation is greater than the correlation threshold are determined as belonging to the same wind turbine cluster. By using the correlation in this way, one-dimensional linear data is processed, the amount of processed data is small, and the processing efficiency is improved. The correlation threshold may be determined according to user requirements. The larger the correlation threshold, the closer the working condition data of each two wind turbines, the stronger the correlation, and the more accurate the subsequent analysis. The smaller the correlation threshold is. The correlation threshold may be greater than 0.6 and less than 0.9. Exemplarily, the correlation threshold is 0.7. In this way, two wind turbines with a correlation greater than 0.7 can be divided into the same wind turbine cluster.

After the above-mentioned first step, in some embodiments, the method may include a third step, classifying the wind turbines whose correlations with other wind turbines in the wind farm except for the wind turbine cluster are not greater than the correlation threshold , it is determined that it is a fan with abnormal working conditions. In this way, the maintenance of wind turbines in the entire wind farm is considered, and the abnormal conditions of wind turbines in the wind farm are comprehensively analyzed, which improves the maintenance efficiency of wind turbines in the wind farm and facilitates direct monitoring of wind turbines with abnormal working conditions in the later stage. After the step of determining the fan with abnormal working condition, the method further includes marking the fan with abnormal working condition. Later, the fan with abnormal working condition can be marked to facilitate finding the fan with abnormal working condition. For the above-mentioned fan with abnormal working conditions, the method may further include performing an abnormal working condition warning for the fan with abnormal working conditions. In this way, it is convenient to remind the user to protect the fan in abnormal working condition in time. After the above-mentioned first step, in some other embodiments, the method further includes setting the wind turbines whose correlations with other wind turbines in the wind farm except for the wind turbine cluster are not greater than the correlation threshold, can be obtained from the wind turbines. The wind turbines of the wind farm are removed, reducing the data for subsequent processing.

Wherein, the above-mentioned first step further includes the first step of determining the correlation degree of wind speed data and the correlation degree of wind direction data. Step 2: Determine the mean value of the correlation between the wind speed data and the wind direction data as the correlation of the working condition data.

Among them, the following Pearson correlation coefficient calculation formula is used to determine the correlation of wind speed data and the correlation of wind direction data:

表示预定时间段内数据样本X平均值，

表示预定时间段内数据样本Y的样本平均值，i的取值范围为(1，n)，n表示风机数量，∑表示求和。In the formula, ρ _{X and Y} represent the correlation coefficient between the two units, cov represents the covariance, and X and Y represent the data sets of the two wind turbines in a predetermined period of time respectively (here refers to the two wind speed data and wind direction data). data), μ _X and μ _Y respectively represent the mean value of the data of the two wind turbines in a predetermined time period, E represents the expectation, σ _X and σ _Y represent the standard deviation of the data in the predetermined time period of the two wind turbines, X _i and Y _i respectively represent the i-th data related to the data of the two wind turbines,

represents the average value of data sample X within a predetermined time period,

Represents the sample average value of the data sample Y in the predetermined time period, the value range of i is (1, n), n represents the number of fans, and Σ represents the summation.

The following mean value calculation formula is used to determine the mean value of the correlation degree of the wind speed data and the wind direction data as the correlation degree of the working condition data:

表示风力发电机工况数据的相关度，此工况数据的相关度为风速数据的相关度和风向数据的相关度的均值，

分别代表风力发电机风速数据的相关度和风向数据的相关度，由前面介绍的皮尔逊相关系数计算公式得出。In the formula,

Represents the correlation degree of wind turbine operating condition data, the correlation degree of this operating condition data is the mean value of the correlation degree of wind speed data and the correlation degree of wind direction data,

respectively represent the correlation degree of wind speed data of wind turbine and the correlation degree of wind direction data, which are obtained by the calculation formula of Pearson correlation coefficient introduced above.

In the embodiment of the above step 320, the average value of the correlation degree of the wind speed data and the wind direction data is used as the correlation degree of the working condition data, and the correlation degree of the working condition data can be effectively used to reflect the multiple wind turbines. It can improve the accuracy of determining the working conditions of multiple wind turbines.

In other embodiments of the above step 320, the above step 320 may include using a clustering algorithm to classify multiple wind turbines in the wind farm according to the wind direction data and the wind speed data to obtain multiple wind turbine clusters. In this way, fans with similar working conditions can be determined through the clustering algorithm, and it is easier to determine the wind turbines with yaw working conditions, and then it is easier to determine the wind turbines with abnormal yaw. The clustering algorithm may include a k-meas algorithm. No detailed examples are given here.

Step 330: Acquire wind direction data, yaw times data and nacelle position data of the wind turbines in the multiple wind turbine clusters.

This step 330 may include acquiring the wind direction data, yaw times data and nacelle position data of the wind turbines of a single cluster from multiple wind turbine clusters each time, and performing subsequent processing until the wind direction data of all clusters, Yaw times data and cabin position data, and the number of acquisitions is the same as the number of wind turbine clusters, so the amount of data processed each time is small.

Step 330 in FIG. 4 is similar to step 110 in FIG. 1 . Compared with step 110 in FIG. 1 , in step 330 in FIG. 4 , the acquired objects are wind turbines in a plurality of wind turbine clusters. In this way, it can be determined whether the yaw of multiple wind turbines is abnormal.

Step 340 , according to the nacelle position data and wind direction data of the plurality of wind turbines in the wind turbine cluster, determine the deflection angles to the wind of the plurality of wind turbines in the wind turbine cluster.

Step 350: Determine whether the wind turbine has an abnormal yaw according to the data of the yaw angle to the wind and the number of yaw times.

Step 360: Determine whether the wind turbines in the wind turbine cluster have abnormal yaw according to the data of the yaw angle and the yaw times of the multiple wind turbines in the wind turbine cluster. In this way, on the basis of distinguishing wind turbines, it is possible to determine whether the wind turbines in each wind turbine cluster have abnormal yaw, which can improve the accuracy of yaw abnormality detection, and execute the entire process according to each wind turbine cluster. Less, the processing efficiency is higher.

FIG. 5 is a heat map of correlation degrees among multiple wind turbines in the method for detecting abnormal yaw of wind turbines shown in FIG. 1 . FIG. 6 is a schematic flowchart of an application example of the method for detecting yaw abnormality of a wind turbine according to an embodiment of the present application. In FIG. 5 , the degree of correlation is represented by the degree of grayscale, and the higher the degree of correlation, the deeper the grayscale.

Taking 124 wind turbines in a 4MW offshore wind farm as an example, the embodiments of the present application will be described in detail.

Step 410, extracting wind direction data, yaw times data and wind speed data of the 124 wind turbines in the wind farm within a preset time period. The preset time period includes a six-hour sub-period of 2019-03-03 00:00:00-2019-03-03 06:00:00.

Step 420: Determine the mean value of the correlation between the wind speed data and the wind direction data of each two wind turbines in the multiple wind turbines in the sub-time period as the correlation between the two wind turbines, and as the correlation of the working condition data. The correlation degree is formed to form a correlation degree coefficient matrix, and according to the correlation degree coefficient matrix, the correlation heat map between the multiple wind turbines in FIG. 5 is given.

Step 430: According to the correlation degree of the working condition data of every two wind turbines among the multiple wind turbines in the wind farm, determine the two wind turbines whose correlation degree is greater than 0.7 as belonging to the same wind turbine cluster, and will not form a wind turbine. A cluster of wind turbines is determined to be a wind turbine with abnormal working conditions. Table 1 shows the wind turbine clusters of 124 wind turbines and the wind turbines that do not form clusters. Exemplarily, taking the wind turbine 1 in the first column in FIG. 5 as the criterion, determine the wind turbines whose correlation degree with the wind turbine 1 in the first column is greater than 0.7 in the 10 rows of wind turbines in the first column For example, wind turbine 1, wind turbine 2, wind turbine 3, wind turbine 4, wind turbine 5, wind turbine 33, wind turbine 34, wind turbine 35, and wind turbine 36 are determined to be the same Fan cluster. For example, this fan cluster is called fan cluster 1 . The correlations for all rows and columns in wind turbine cluster 1 can then be deleted from FIG. 5 . After that, continue to take the wind turbines 6 in the first column as the criterion, and determine the wind turbines whose correlation degree with the wind turbines 6 in the first column is greater than 0.7 among the 10 rows of wind turbines in the first column. For details, please refer to the wind turbine cluster 2, and so on. According to the correlation of the 124 wind turbines, the obtained wind turbine cluster and the wind turbines that do not form a cluster. The amount of data processed in this way is decreasing, which can improve processing efficiency.

Table 1 Wind turbine clusters and wind turbines without clusters

Step 440, according to the plurality of wind turbine clusters, respectively determine the number of fan yaw times of each wind turbine in the multiple wind turbines in each wind turbine cluster within 6 hours and the yaw angle to the wind for each hour within 6 hours. . Among them, the number of yaw times of the fan within 6 hours includes recording the number of yaw times of the fan per hour, and at this time, the number of yaw times of the fan here is the cumulative sum of the number of yaw times of the fan for 6 hours. Fan yaw times include the fan yaw times within 6 hours and the fan yaw times is the data recorded once every 6 hours. At this time, the fan yaw times here is the fan yaw times in 6 hours.

Step 450: Determine the angle threshold according to the average value of the deflection angles of the multiple wind turbines against the wind. For example, the wind turbine cluster 1 includes 9 wind turbines as an example for description. First, the mean values of the deflection angles to the wind of the 9 wind turbines are averaged to obtain the mean value μ ₁ of the mean values of the deflection angles to the wind. Thirdly, the standard deviation of the mean values of the wind deflection angles of the 9 wind turbines is calculated to obtain the standard deviation σ ₁ of the mean values of the wind deflection angles. Then, according to the mean value μ ₁ and the standard deviation σ ₁ , the angle threshold is obtained.

Step 460: Determine the yaw times threshold according to the yaw times data of a plurality of the wind turbines. For example, the wind turbine cluster 1 includes 9 wind turbines as an example for description. First, the yaw frequency data of the nine wind turbines are averaged to obtain the average value μ ₂ of the yaw frequency data. Thirdly, the standard deviation of the yaw times data of the nine wind turbines is calculated to obtain the standard deviation σ ₂ of the yaw times data. Then, according to the mean value μ ₂ and the standard deviation σ ₂ , the angle threshold is obtained.

In step 470, the wind turbines whose mean value of the wind deflection angle exceeds the angular threshold and/or whose yaw number data exceeds the yaw number threshold are determined as abnormal yaw wind turbines. In Table 2 below, the underlined and bolded part is used to identify the abnormal yaw fan and its data. For example, the abnormal yaw fan 5 in the fan cluster 1 and the abnormal yaw fan 23 in the fan cluster 6 . The abnormal yaw fan 64 in the fan cluster 3 , the abnormal yaw fan 66 , and the abnormal yaw fan 92 in the fan cluster 4 .

Table 2 Fans with abnormal yaw in the fan cluster

Step 480 , marking the wind turbines with abnormal yaw in the sub-time period as abnormal yaw wind turbines, and marking the wind turbines with abnormal working conditions.

Step 490, the preset time period further includes a six-hour sub-time period of 2019-03-03 06:00:00-2019-03-03 12:00:00, 2019-03-03 12:00:00- A six-hour subperiod of 2019-03-03 18:00:00 and a six-hour subperiod of 2019-03-03 18:00:00-2019-03-03 00:00:00. According to the sub time period of the preset time period, return to and continue to execute steps 420 to 480, repeat steps 420 to 480 according to the above three sub time periods, until the sub time period is used up, and continue to execute step 510.

Step 510: Count the times of marking of the same wind turbine with abnormal yaw within the predetermined time period.

Step 520: Determine the failure level of the same fan with abnormal yaw according to the number of times of marking and the number of sub-periods. If the abnormal yaw fan is marked more than or equal to 3 times, the abnormal yaw fan is determined as a high-risk abnormal yaw fan; if the number of times the abnormal yaw fan is marked is equal to 2, the abnormal yaw fan is determined as a medium risk yaw fan Abnormal fan; if the number of times the abnormal yaw fan is marked is equal to 1, the abnormal yaw fan is determined as a low-risk abnormal yaw fan. Table 3 shows the failure levels of the high-risk abnormal yaw fan, the medium-risk abnormal yaw fan, and the low-risk abnormal yaw fan.

Table 3 Fault levels and numbers of abnormal yaw fans

FIG. 7 is a schematic block diagram of the device for detecting abnormal yaw of a wind turbine according to an embodiment of the present application.

As shown in Figure 7, the wind turbine yaw abnormality detection and early warning device includes:

The obtaining module 21 is used for obtaining wind direction data, yaw times data and cabin position data of the wind turbine.

The first processing module 22 is configured to determine the deflection angle to the wind of the wind turbine according to the nacelle position data and the wind direction data.

The second processing module 23 is configured to determine whether the yaw of the wind turbine is abnormal according to the data of the yaw angle to the wind and the number of yaw times.

For details of the implementation process of the functions and functions of each unit in the above device, please refer to the implementation process of the corresponding steps in the above method, which will not be repeated here.

FIG. 8 is a schematic structural diagram of an electronic device 30 according to an embodiment of the present application. The electronic device 30 may include a processor 31 , a memory 33 storing machine-executable instructions, and a communication interface 32 . The processor 31 and the memory 33 may communicate via a system bus 34 . Also, by reading and executing machine-executable instructions in the memory 33 corresponding to the data pull or data return logic, the processor 31 can execute the methods described above.

Memory 33 referred to herein may be any electronic, magnetic, optical, or other physical storage device that may contain or store information, such as executable instructions, data, and the like. For example, the machine-readable storage medium may be: RAM (Radom Access Memory, random access memory), volatile memory, non-volatile memory, flash memory, storage drive (such as hard disk drive), solid state drive, any type of storage disk ( such as optical discs, DVDs, etc.), or similar storage media, or a combination thereof.

In some embodiments, a machine-readable storage medium is also provided, such as the memory 33 in FIG. 8 , where machine-executable instructions are stored in the machine-readable storage medium, and when the machine-executable instructions are executed by the processor Implement the method described above. For example, the machine-readable storage medium may be ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, and the like.

The embodiment of the present application further provides a computer program, which is stored in a machine-readable storage medium, such as the memory 33 in FIG. 8 , and when the processor executes the computer program, causes the processor 31 to execute the method described above.

The above descriptions are only preferred embodiments of this specification, and are not intended to limit this specification. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of this specification shall be included in this specification. within the scope of protection.

It should also be noted that the terms "comprising", "comprising" or any other variation thereof are intended to encompass a non-exclusive inclusion such that a process, method, article or device comprising a series of elements includes not only those elements, but also Other elements not expressly listed, or which are inherent to such a process, method, article of manufacture, or apparatus are also included. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in the process, method, article of manufacture, or device that includes the element.

Claims (13)

1. a wind turbine yaw abnormality detection method, is characterized in that, comprises: Obtain wind direction data, yaw times data and cabin position data of the wind turbine; According to the nacelle position data and the wind direction data, determine the windward deflection angle of the wind turbine; It is determined whether the wind turbine has an abnormal yaw according to the yaw angle to the wind and the data of the number of yaw times. 2 . The abnormal yaw detection method for a wind turbine according to claim 1 , wherein the method for determining whether the wind turbine has an abnormal yaw is determined according to the data of the yaw angle to the wind and the number of yaw times. 3 . include: determining the mean value of the deflection angle to the wind at a plurality of times within a predetermined time period of the wind turbine; determining an angle threshold according to the mean value of the deflection angles to the wind of the plurality of wind turbines; determining the yaw number data of the wind turbine within the predetermined time period; determining the yaw times threshold according to the yaw times data of a plurality of the wind turbines; When there is at least one of the mean value of the yaw angle to the wind of the wind turbine exceeds the angle threshold, and the yaw number data of the wind turbine exceeds the yaw number threshold, it is determined that the wind turbine The generator yaw is abnormal. 3 . The abnormal yaw detection method for a wind turbine according to claim 2 , wherein the determining a threshold for the number of yaw according to a plurality of data of the number of yaw of the wind turbine comprises: 3 . determining an average value of the yaw number data for a plurality of the wind turbines; determining a standard deviation of the yaw number data for a plurality of the wind turbines; The yaw number threshold is determined according to the average value of the yaw number data and the standard deviation of the yaw number data. 4 . The abnormal yaw detection method for wind turbines according to claim 3 , wherein the determining an angle threshold according to the average value of the deflection angles to the wind of a plurality of the wind turbines comprises: 4 . determining an average value of the average values of the deflection angles to the wind for a plurality of the wind turbines; determining the standard deviation of the mean value of the deflection angles to the wind for a plurality of the wind turbines; The angle threshold is determined according to the mean value of the mean values of the opposite wind deflection angles and the standard deviation of the mean values of the opposite wind deflection angles. 5 . The abnormal yaw detection method for a wind turbine according to claim 2 , wherein the predetermined time period comprises a plurality of sub-time periods, and the time lengths of the plurality of sub-time periods are the same; 5 . The determining whether the wind turbine yaw is abnormal according to the yaw angle to the wind and the yaw times data includes: According to the data of the yaw angle against the wind and the number of yaw times in the sub-time period, determine whether the plurality of wind turbines in the sub-time period have abnormal yaw; After determining whether the wind turbine has an abnormal yaw according to the yaw angle to the wind and the yaw times data, the method further includes: Mark the wind turbines with abnormal yaw in the sub-time period as abnormal yaw wind turbines; Count the times of marking of the same abnormal yaw fan in the predetermined time period; According to the marking times and the number of segments of the multiple sub-time segments, the failure level of the same yaw abnormal fan is determined. 6 . The abnormal yaw detection method for a wind turbine according to claim 5 , wherein determining the failure level of the same abnormal yaw wind turbine according to the number of marks and the number of segments of the plurality of sub-periods, comprising: 7 . : Determining the abnormal yaw fan whose number of times of marking is greater than half of the number of segments of the plurality of sub-periods as a high-risk abnormal yaw fan; Determining the abnormal yaw wind turbine with the number of marking times equal to half of the number of segments in the sub-time segment as a medium-risk abnormal yaw wind turbine; The abnormal yaw wind turbines whose marking times are greater than zero and less than half of the number of segments of the sub-period are determined as low-risk abnormal yaw wind turbines. 7. The abnormal yaw detection method for a wind turbine according to claim 1, wherein the method comprises: acquiring working condition data of multiple wind turbines in the wind farm, where the working condition data includes the wind direction data and wind speed data; According to the wind direction data and the wind speed data, classifying a plurality of wind turbines in the wind farm to obtain a plurality of wind turbine clusters; The determining, according to the nacelle position data and the wind direction data, the deflection angle to the wind of the wind turbine includes: According to the nacelle position data and the wind direction data of the plurality of wind turbines in the wind turbine cluster, determining the deflection angle to the wind of the plurality of wind turbines in the wind turbine cluster; The determining whether the wind turbine yaw is abnormal according to the yaw angle to the wind and the yaw times data includes: Whether the wind turbines in the wind turbine cluster are abnormally yawed is determined according to the data of the yaw angle and the yaw times of the plurality of wind turbines in the wind turbine cluster. 8 . The abnormal yaw detection method for wind turbines according to claim 7 , wherein, according to the wind direction data and the wind speed data, classifying a plurality of wind turbines in the wind farm to obtain the following: 8 . Multiple wind turbine clusters including: determining the degree of correlation of the working condition data of every two wind turbines among the multiple wind turbines in the wind farm; Every two wind turbines whose correlation is greater than the correlation threshold are determined to belong to the same wind turbine cluster. 9 . The abnormal yaw detection method for wind turbines according to claim 8 , wherein, by determining the correlation degree of the working condition data of every two wind turbines in the wind farm, include: determining the correlation degree of the wind speed data and the correlation degree of the wind direction data; The mean value of the correlation degree of the wind speed data and the correlation degree of the wind direction data is determined as the correlation degree of the working condition data. 10 . The abnormal yaw detection method for a wind turbine according to claim 8 , wherein, in said determining the correlation degree of the working condition data of every two wind turbines among the multiple wind turbines in the wind farm. 11 . Afterwards, the method further includes: A wind turbine whose correlation degree with other wind turbines in the wind farm except the wind turbine cluster is not greater than the correlation degree threshold is determined as a wind turbine with abnormal working conditions. 11. A wind turbine yaw abnormality detection and early warning device, characterized in that, comprising: The acquisition module is used to acquire the wind direction data, yaw times data and cabin position data of the wind turbine; a first processing module, configured to determine the windward deflection angle of the wind turbine according to the nacelle position data and the wind direction data; The second processing module is configured to determine whether the wind turbine has an abnormal yaw according to the yaw angle to the wind and the data of the yaw times. 12. An electronic device, comprising a processor and a memory; memory for storing computer programs; The processor is configured to implement the method described in any one of claims 1-10 when executing the program stored in the memory. 13. A computer-readable storage medium, characterized in that a program is stored thereon, and when the program is executed by a processor, the method according to any one of claims 1-10 is implemented.

Images