Variable pitch part anomaly detection method and system and readable medium

Abstract

The invention belongs to the technical field of new energy equipment anomaly analysis, and relates to a variable pitch component anomaly detection method and system and a readable medium, and the method comprises the following steps: calculating the actual pitch angle standard deviation of a blade, and recognizing whether the variable pitch angle is abnormal or not through the actual pitch angle standard deviation; if the variable pitch angle is not abnormal, the standard deviation of the collected data of all the measuring points is obtained, and whether measurement abnormity exists in all the components or not is judged one by one according to the standard deviation of the collected data; if the measurement abnormity does not exist in each part, calculating the slope of the standard deviation of the collected data, so as to judge whether the standard deviation of the collected data has a rising trend or not and judge whether a gradual deterioration risk exists or not; and if the deterioration risk does not exist, calculating a correlation matrix among the measuring points under various working conditions through the established working condition model, and judging whether the variable pitch component is abnormal under various working conditions according to the correlation matrix. According to the method, more complete and careful abnormal detection of the variable-pitch component can be realized.

Description

Technical Field

[0001] The invention relates to a method, a system and a readable medium for detecting abnormality of a variable pitch component, and belongs to the technical field of abnormality analysis of new energy equipment. Background Art

[0002] As the trend of wind turbines becoming larger and larger continues to increase, the importance of abnormal detection of wind turbine equipment is becoming increasingly important. Abnormal operation of wind turbine equipment will bring serious safety hazards to the unit.

[0003] The blade pitch system is an important component of a wind turbine. Abnormalities in the pitch system can cause serious operational risks to the unit and result in a large amount of power generation loss.

[0004] Existing abnormality detection of turbine pitch control systems mostly uses a single threshold method to detect temperature and other measurement points. However, turbine abnormality is often a gradual process, and temperature detection alone will cause lags and missed reports.

[0005] Patent CN117889050A proposes a data-driven wind turbine pitch system abnormality detection method and system, which realizes abnormality detection of the pitch system by constructing the pitch angle-wind speed function of the unit. This method can realize the early identification of abnormal pitch angle, but it cannot detect abnormalities of various components inside the pitch system. Summary of the invention

[0006] In view of the above problems, an object of the present invention is to provide a method, system and readable medium for detecting abnormalities of a pitch component, which can achieve more complete and detailed abnormality detection of the pitch component.

[0007] To achieve the above-mentioned purpose, the present invention proposes the following technical solutions: a method for detecting abnormalities of a variable pitch component, comprising the following steps: calculating the standard deviation of the actual pitch angle of the blade, and identifying whether the variable pitch angle is abnormal through the standard deviation of the actual pitch angle; if there is no abnormality in the variable pitch angle, calculating the standard deviation of the collected data of several blades for each measuring point, and judging whether there is a measurement abnormality for each component one by one according to the standard deviation of the collected data; if there is no measurement abnormal component, calculating the slope of the average value of the collected data, and judging whether there is an upward trend in the collected data according to the slope, so as to judge whether there is a risk of gradual degradation; if there is no risk of degradation, judging whether there is an abnormality at each measuring point of the variable pitch component under various working conditions through the measuring point-working condition model; if there is no abnormality, calculating the correlation matrix between the measuring points in the time window, and the PCA feature contribution curve, and judging whether there is an abnormality in the variable pitch component according to the changing trends of the correlation matrix and the PCA feature contribution curve.

[0008] Furthermore, the method of calculating the standard deviation of the actual pitch angle of the blades and identifying whether the pitch angle is abnormal through the standard deviation of the actual pitch angle is as follows: for the actual pitch angles of several blades at each timestamp, the standard deviation of the actual pitch angle is calculated; when the standard deviation of the actual pitch angle is greater than a first threshold, it is considered that there is an abnormality in the pitch component at this time; if there is no abnormality in the pitch component, and the standard deviation of the collected data of several blades at a certain measuring point of a certain pitch component is greater than a second threshold, it is considered that there is an abnormality in the measuring point.

[0009] Furthermore, the measuring points include: pitch rate, pitch motor temperature, pitch motor current, pitch motor voltage, pitch control cabinet temperature and pitch capacitor temperature.

[0010] Furthermore, based on the slope, a method for determining whether the collected data has an upward trend is as follows: if there is no abnormal measurement component, then the slope of the average values ​​of each temperature and voltage measurement point within the time window is calculated; if the slope of the average value of a certain temperature or voltage measurement point is greater than a third threshold, then it is considered that the measurement point is at risk of gradual deterioration.

[0011] Furthermore, the method for establishing the measuring point-operating condition model is as follows: a time window is selected, and the measuring point information at the current moment is used as the dependent variable y, and the operating condition information at the current moment and the measuring point information in the previous period of time are secondary processed, and various features generated after the secondary processing are used as independent variables x; based on the machine learning model, a model is built according to the dependent variable y and the independent variable x, and the predicted value y_pred is calculated based on the measuring point-operating condition model. When the residual between the actual value y_true and the predicted value y_pred is higher than the threshold, it is considered that there is an abnormality in the measuring point corresponding to the variable pitch component at this time.

[0012] Furthermore, the operating conditions include: wind speed, power, rotation speed, pitch angle, pitch rate, ambient temperature and hub temperature.

[0013] Furthermore, a method for judging whether there is an abnormality in a variable pitch component according to the changing trends of the correlation matrix and the PCA characteristic contribution curve is as follows: based on the correlation matrix of the data of each measuring point in each time window and the degree of change of the PCA characteristic contribution distribution over time, an abnormality detection is performed on the variable pitch mechanism.

[0014] Furthermore, statistical aggregation is performed based on the correlation matrix to obtain the correlation coefficient. If it is detected that the correlation coefficient in a certain period of time is suddenly higher or lower than that in other periods, it is considered that there is an abnormality in the variable pitch component during this period; or based on the temperature average value series within the preset time, PCA principal component analysis is performed, and the variance contribution rate of the first N principal components is calculated; if it is detected that the characteristic contribution rate of a principal component in a certain period of time is suddenly higher or lower than that in other periods, it is considered that there is an abnormality in the variable pitch component during this period.

[0015] The present invention also discloses a variable pitch component abnormality detection system, comprising: a variable pitch angle abnormality judgment module, used for calculating the standard deviation of the actual pitch angle of the blade, and identifying whether the variable pitch angle is abnormal through the standard deviation of the actual pitch angle; a component measurement abnormality judgment module, used for calculating the standard deviation of the collected data of several blades for each measuring point respectively if there is no abnormality in the variable pitch angle, and judging whether there is a measurement abnormality for each component one by one according to the standard deviation of the collected data; a degradation risk judgment module, used for calculating the slope of the average value of the collected data if there is no measurement abnormality component, and judging whether there is an upward trend in the collected data according to the slope, so as to judge whether there is a gradual degradation risk; an operating condition abnormality judgment module, used for judging whether there is an abnormality at each measuring point of the variable pitch component under various operating conditions through a measuring point-operating condition model if there is no degradation risk; if there is no abnormality, calculating the correlation matrix between the measuring points in the time window and the PCA feature contribution curve, and judging whether there is an abnormality in the variable pitch component according to the changing trends of the correlation matrix and the PCA feature contribution curve.

[0016] The present invention also discloses a computer-readable storage medium, on which a computer program is stored. The computer program is executed by a processor to implement any of the above-mentioned methods for detecting abnormalities in variable pitch components.

[0017] The technical solution of the present invention has at least the following technical effects or advantages: the detection method in the present invention has clear and controllable logic, and the detection results are dynamically sensitive, so it can capture abnormal information of the variable pitch system more quickly, and the detection results of each step are traceable, and more complete and detailed abnormal detection of the variable pitch components can be achieved, which provides an effective detection basis for the abnormal diagnosis of the variable pitch components and realizes root cause tracing. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 is a flow chart of a method for detecting abnormality of a pitch component in one embodiment of the present invention;

[0019] Figure 2 is a graph showing the change of the blade angle of three blades over time in one embodiment of the present invention, Figure 2 (a) is a graph showing the variation of the blade angle of the first blade over time; Figure 2 (b) is a graph showing the variation of the propeller blade angle of the second blade over time; Figure 2 (c) is a graph showing the variation of the propeller blade angle of the third blade over time;

[0020] Figure 3 is a schematic diagram of an embodiment of the present invention when the measured values ​​of the pitch angles of the three blades are consistent. Figure 3 (a) is a graph showing the variation of propeller blade angle over time; Figure 3 (b) is the graph showing the standard deviation of blade pitch angle changing with time;

[0021] Figure 4 is a schematic diagram of an embodiment of the present invention when the measured values ​​of the pitch angles of the three blades are inconsistent. Figure 4 (a) is a graph showing the variation of propeller blade angle over time; Figure 4 (b) is the graph showing the standard deviation of blade pitch angle changing with time;

[0022] Figure 5 is a schematic diagram of a case where the temperature measurement values ​​of a pitch motor of a blade pitch motor are inconsistent in one embodiment of the present invention, Figure 5 (a) is the temperature variation of the three blade pitch motors over time; Figure 5 (b) is the temperature variation of the three blade pitch motors over time;

[0023] Figure 6 is a graph showing the average temperature of a blade pitch motor changing over time in one embodiment of the present invention;

[0024] Figure 7 is a comparison diagram between the prediction of the measuring point-operating condition model and the actual situation in one embodiment of the present invention, Figure 7 (a) is a comparison chart between the predicted value of the measuring point-operating condition model and the actual measured value; Figure 7 (b) is a comparison chart of the residuals of the predicted values ​​of the measuring point-operating condition model and the actual values;

[0025] Figure 8 is a graph showing the change of correlation coefficient over time window in one embodiment of the present invention;

[0026] Fig. 9 It is a graph showing the variation of PCA feature contribution over time window in one embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention is described in detail through specific embodiments. However, it should be understood that the provision of specific embodiments is only for a better understanding of the present invention, and they should not be understood as limitations of the present invention. In the description of the present invention, it should be understood that the terms used are only for the purpose of description and cannot be understood as indicating or implying relative importance.

[0028] In order to solve the problems of alarm lag or even missed alarm caused by the process of failing to identify abnormalities of the variable pitch system in the prior art, the present invention proposes a method, system and readable medium for detecting abnormalities of variable pitch components, proposes and implements the calculation of the standard deviation and average value of the actual pitch angle of the blade, as well as the calculation of the standard deviation and average value of the blade's variable pitch motor temperature, variable pitch motor current, variable pitch motor voltage, variable pitch control cabinet temperature, variable pitch capacitor temperature and other measurement points, and constructs a series of analysis and judgment rules to detect abnormalities of variable pitch components; it provides an effective detection basis for abnormal diagnosis of variable pitch components and realizes root cause tracing. The scheme of the present invention is described in detail below through embodiments in conjunction with the accompanying drawings.

[0029] Embodiment 1

[0030] This embodiment discloses a method for detecting abnormality of a pitch component. Figure 1 As shown, the following steps are included:

[0031] S1 calculates the standard deviation of the actual pitch angle of the blade and identifies whether the pitch angle is abnormal through the standard deviation of the actual pitch angle.

[0032] For the actual pitch angles of several blades at each timestamp, the standard deviation of the actual pitch angles of the blades is calculated, and the method for identifying whether the pitch angle is abnormal through the standard deviation of the actual pitch angle is as follows: for the actual pitch angles of several blades at each timestamp, the standard deviation of the actual pitch angle is calculated; when the standard deviation of the actual pitch angle is greater than the first threshold, it is considered that there is an abnormality in the pitch component at this time. In this embodiment, since the number of blades is 3, the change of the blade angle of the 3 blades over time is shown in the figure Figure 2 As shown, the actual pitch angle standard deviation of the blades is calculated, and the average value of each blade is taken. In this embodiment, the first threshold is 1, but the user can adjust the threshold according to actual needs, such as Figure 3 , Figure 4 shown. Figure 3 It is a schematic diagram when the measured values ​​of the pitch angles of the three blades are consistent. Since the pitch angles of the three blades are the same, the blade angle variation curves over time and the blade pitch angle standard deviation variation curves over time coincide, so there is only one line in the figure. Figure 4 The figure is a schematic diagram of the three blades when the measured values ​​of the pitch angle are inconsistent. Therefore, the curve of the blade angle changing with time and the curve of the standard deviation of the blade pitch angle changing with time do not overlap. Figure 4 In (b), the standard deviation of the blade pitch angle exceeds the first threshold, which is the dotted line in the figure, indicating that there is an abnormality in the pitch angle.

[0033] S2 If there is no abnormality in the pitch angle, the standard deviation of the collected data of several blades is calculated for each measuring point, and whether there is any measurement abnormality is determined for each component one by one based on the standard deviation of the collected data.

[0034] If there is no abnormality in the pitch angle, the standard deviation of the data collected at each measuring point is obtained, and each component is judged one by one whether there is a measurement abnormality according to the standard deviation of the collected data. In this embodiment, the measuring points include: pitch rate, pitch motor temperature, pitch motor current, pitch motor voltage, pitch control cabinet temperature, pitch capacitor temperature, etc.

[0035] If there is no abnormality in the pitch component, and the standard deviation of the data collected from several blades at a certain measuring point of a certain pitch component is greater than the second threshold, then the measuring point is considered to have an abnormality. For example, in this embodiment, the standard deviation of the pitch motor temperature, pitch motor current, pitch motor voltage, pitch control cabinet temperature, pitch capacitor temperature and other measuring points of the three blades at each timestamp is calculated; when the standard deviation is greater than 5, it is considered that there is an abnormality in the corresponding measuring point of the pitch component at this time. At the same time, multiple components or measuring points may have abnormalities. In this embodiment, the second threshold is 5, but the user can adjust the threshold according to actual needs. Different measuring points can use different second thresholds, such as Figure 5 shown.

[0036] If there is no abnormal component in measurement, S3 calculates the slope of the average value of the collected data, and determines whether the collected data has an upward trend based on the slope to determine whether there is a risk of gradual deterioration.

[0037] According to the slope, the method for judging whether the collected data has an upward trend is as follows: if there is no abnormal measurement component in each component, then the slope of the average value of each temperature and voltage measurement point in the time window is calculated; if the slope of the average value of a certain temperature or voltage measurement point is greater than the third threshold, then it is considered that the measurement point has a risk of gradual degradation, such as Figure 6 shown.

[0038] If there is no degradation risk in S4, the measuring point-operating condition model is used to determine whether there are abnormalities at each measuring point of the variable pitch component under various operating conditions.

[0039] If there is no risk of gradual degradation of the measured value of the measuring point, a measuring point-operating condition model is established to determine the functional relationship between the operating condition and the measuring points of each pitch component, and to judge the reference level of each pitch component measuring point corresponding to different operating conditions, so as to judge whether there are abnormalities at each measuring point of the pitch component under various operating conditions;

[0040] The method for establishing the measuring point-operating condition model is as follows: a time window is selected, the measuring point information at the current moment is used as the dependent variable y, the operating condition information at the current moment and the measuring point information in the previous period of time are processed twice, and the various features generated after the secondary processing are used as the independent variable x; based on the machine learning model, a model is built according to the dependent variable y and the independent variable x, and the predicted value y_pred is calculated based on the measuring point-operating condition model. When the residual between the actual value y_true and the predicted value y_pred is higher than the threshold, it is considered that there is an abnormality in the corresponding measuring point of the variable pitch component at this time, such as Figure 7 As shown. For example, the average value of the variable pitch motor temperature is used as the dependent variable y, the blade pitch angle, and the slope of the dependent variable y in the past hour are used as the independent variable X, and the predicted value y_pred. When the residual between the actual value y_true and the predicted value y_pred is higher than the threshold, it is considered that the corresponding measuring point of the variable pitch component is abnormal at this time. At the same time, multiple components or measuring points may be abnormal. Machine learning models can include linear models, tree models, neural network models, etc.

[0041] The working conditions include: wind speed, power, rotation speed, pitch angle, pitch rate, ambient temperature, hub temperature, etc. For example, in this embodiment, the measurement point-working condition model can be a working condition-temperature model, and the functional relationship between the average temperature of each pitch component and the external working condition is determined according to the working condition-temperature model, so as to identify the problem of excessively high average temperature.

[0042] If there is no abnormality in S5, the correlation matrix between the measuring points in the time window and the PCA characteristic contribution curve are calculated, and according to the change trends of the correlation matrix and the PCA characteristic contribution curve, it is judged whether there is an abnormality in the variable pitch component.

[0043] Based on the sliding time window, the correlation matrix and the PCA feature contribution curve between each measuring point are detected to determine the abnormality. The method for judging whether there is an abnormality in the variable pitch component based on the change trend of the correlation matrix and the PCA feature contribution curve is as follows: principal component analysis is performed on the data of each measuring point in the time window, and according to the correlation matrix, the correlation matrix of the working condition detected in a certain period, the correlation matrix of the working condition detected in other periods, and the distribution of PCA feature contribution are detected to determine whether they are similar. If the difference is large, an early warning is issued.

[0044] When it is detected that the correlation coefficient in a certain period of time is suddenly higher or lower than that in other periods, it is considered that there is an abnormality in the pitch control component during this period, such as Figure 8 As shown; or based on the temperature average sequence within the preset time, PCA principal component analysis is performed, and the variance contribution rate of the first N principal components is calculated; when it is detected that the characteristic contribution rate of a principal component in a certain period of time is suddenly higher or lower than that of other periods, it is considered that the pitch control component during this period is abnormal, such as Fig. 9 shown.

[0045] Embodiment 2

[0046] Based on the same inventive concept, this embodiment discloses a pitch component abnormality detection system, including:

[0047] The pitch angle abnormality judgment module is used to calculate the standard deviation of the actual pitch angle of the blade and identify whether the pitch angle is abnormal through the standard deviation of the actual pitch angle;

[0048] The component measurement abnormality judgment module is used to calculate the standard deviation of the collected data of several blades for each measuring point when there is no abnormality in the pitch angle, and judge whether there is a measurement abnormality for each component one by one according to the standard deviation of the collected data;

[0049] A degradation risk judgment module is used to calculate the slope of the average value of the collected data if there is no abnormal measurement component, and judge whether the collected data has an upward trend according to the slope, so as to judge whether there is a gradual degradation risk;

[0050] The abnormal working condition judgment module is used to determine whether there are abnormalities at each measuring point of the variable pitch component under various working conditions if there is no degradation risk. The measuring point-working condition model is used to determine whether there are abnormalities at each measuring point of the variable pitch component under various working conditions. If there are no abnormalities, the correlation matrix between the measuring points in the time window and the PCA feature contribution curve are calculated, and the abnormality of the variable pitch component is determined based on the changing trends of the correlation matrix and the PCA feature contribution curve.

[0051] Embodiment 3

[0052] Based on the same inventive concept, this embodiment discloses a computer-readable storage medium, on which a computer program is stored. The computer program is executed by a processor to implement any of the above-mentioned pitch component abnormality detection methods.

[0053] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0054] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0055] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0056] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0057] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit them. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation of the present invention can still be modified or replaced by equivalents, and any modification or equivalent replacement that does not deviate from the spirit and scope of the present invention should be included in the protection scope of the claims of the present invention. The above content is only a specific implementation of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or replacements within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for detecting abnormality of a pitch component, characterized in that: The following steps are involved: Calculating the actual pitch angle standard deviation of the blades, and identifying whether the pitch angle is abnormal through the actual pitch angle standard deviation; If there is no abnormality in the pitch angle, the standard deviation of the data collected from several blades is calculated for each measuring point, and whether there is any measurement abnormality is determined for each component one by one based on the standard deviation of the collected data; If there is no abnormal component, the slope of the average value of the collected data is calculated, and according to the slope, whether the collected data has an upward trend is determined to determine whether there is a risk of gradual deterioration; If there is no risk of degradation, the measuring point-operating condition model is used to determine whether there are abnormalities at each measuring point of the pitch component under various operating conditions; If there is no abnormality, the correlation matrix between the measuring points in the time window and the PCA characteristic contribution curve are calculated, and whether the pitch control component has an abnormality is determined based on the change trends of the correlation matrix and the PCA characteristic contribution curve.

2. The method for detecting abnormality of a pitch component according to claim 1, characterized in that: The method for calculating the standard deviation of the actual pitch angle of the blade and identifying whether the pitch angle is abnormal through the standard deviation of the actual pitch angle is as follows: for the actual pitch angles of several blades at each timestamp, the standard deviation of the actual pitch angle is calculated; when the standard deviation of the actual pitch angle is greater than a first threshold, it is considered that there is an abnormality in the pitch component at this time; if there is no abnormality in the pitch component, and the standard deviation of the collected data of several blades at a certain measuring point of a certain pitch component is greater than a second threshold, it is considered that there is an abnormality in the measuring point.

3. The method for detecting abnormality of a pitch component according to claim 1, characterized in that: The measuring points include: pitch rate, pitch motor temperature, pitch motor current, pitch motor voltage, pitch control cabinet temperature and pitch capacitor temperature.

4. The method for detecting abnormality of a pitch component according to claim 1, characterized in that: According to the slope, a method for judging whether the collected data has an upward trend is as follows: if there is no abnormal measurement component, the slope of the average value of each temperature and voltage measurement point in the time window is calculated; if the slope of the average value of a certain temperature or voltage measurement point is greater than a third threshold, it is considered that the measurement point has a risk of gradual degradation.

5. The method for detecting abnormality of a pitch component according to claim 1, characterized in that: The method for establishing the measuring point-operating condition model is: Select a time window, take the current measurement point information as the dependent variable y, perform secondary processing on the current working condition information and the measurement point information of the previous period, and take the various features generated after secondary processing as the independent variable x; Based on the machine learning model, the model is built according to the dependent variable y and the independent variable x, and the predicted value y_pred is calculated based on the measuring point-operating condition model. When the residual between the actual value y_true and the predicted value y_pred is higher than the threshold, it is considered that there is an abnormality in the corresponding measuring point of the variable pitch component.

6. The method for detecting abnormality of a pitch component according to claim 5, characterized in that: The operating conditions include: wind speed, power, rotation speed, pitch angle, pitch rate, ambient temperature and hub temperature.

7. The method for detecting abnormality of a pitch component according to claim 1, characterized in that: The method for judging whether there is an abnormality in the variable pitch component according to the change trend of the correlation matrix and the PCA characteristic contribution curve is: based on the correlation matrix of each measuring point data in each time window and the degree of change of the PCA characteristic contribution distribution over time, the variable pitch mechanism is detected for abnormality.

8. The method for detecting abnormality of a pitch component according to claim 7, characterized in that: The correlation coefficient is obtained by statistical aggregation based on the correlation matrix. If it is detected that the correlation coefficient in a certain period of time is suddenly higher or lower than that in other periods, it is considered that there is an abnormality in the variable pitch component during this period; or based on the temperature average value sequence within the preset time, PCA principal component analysis is performed, and the variance contribution rate of the first N principal components is calculated; if it is detected that the characteristic contribution rate of a principal component in a certain period of time is suddenly higher or lower than that in other periods, it is considered that there is an abnormality in the variable pitch component during this period.

9. A pitch component abnormality detection system, characterized in that: include: A pitch angle abnormality judgment module is used to calculate the actual pitch angle standard deviation of the blade, and identify whether the pitch angle is abnormal through the actual pitch angle standard deviation; The component measurement abnormality judgment module is used to calculate the standard deviation of the collected data of several blades for each measuring point when there is no abnormality in the pitch angle, and judge whether there is a measurement abnormality for each component one by one according to the standard deviation of the collected data; A degradation risk judgment module, for calculating the slope of the average value of the collected data if there is no abnormal measurement component, and judging whether the collected data has an upward trend according to the slope, so as to judge whether there is a gradual degradation risk; The abnormal working condition judgment module is used to judge whether there are abnormalities at each measuring point of the pitch component under various working conditions through the measuring point-working condition model if there is no degradation risk; If there is no abnormality, the correlation matrix between the measuring points in the time window and the PCA characteristic contribution curve are calculated, and whether the pitch control component has an abnormality is determined based on the change trends of the correlation matrix and the PCA characteristic contribution curve.

10. A computer-readable storage medium, characterized in that: A computer program is stored on the computer-readable storage medium, and the computer program is executed by a processor to implement the method for detecting abnormality of a pitch component according to any one of claims 1 to 8.

Images