Shaft current early-warning method applied to wind turbine

Abstract

The present invention relates to the technical field of wind turbines, and in particular to a shaft current early-warning method applied to a wind turbine. The method comprises the steps of: in a wind turbine, arranging an acquisition module on a generator shaft to acquire operation data of the generator shaft, and preprocessing the operation data of the generator shaft; extracting multivariate features of the operation data of the generator shaft, the multivariate features including a mean value feature, a standard deviation feature, a kurtosis feature, and a skewness feature; and defining a shaft current early-warning degree model, on the basis of the multivariate features of the operation data of the generator shaft, solving the shaft current early-warning degree model to obtain an early-warning degree of a generator shaft current, and executing a graded alarm of the generator shaft current. By means of multivariate feature extraction and an early-warning degree model, the present invention achieves intelligent and accurate monitoring of a shaft current abnormality, facilitating predictive maintenance of a wind turbine, improving device reliability and prolonging the service life.

Description

A shaft current early warning method applied to a wind driven generator TECHNICAL FIELD

[0001] The present application relates to the technical field of wind driven generators, in particular to a shaft current early warning method applied to a wind driven generator. BACKGROUND

[0002] As an important part of renewable energy, the safe and stable operation of wind turbines is of great importance. The generator shaft is one of the core components of the wind turbine, and its operating state directly affects the performance and life of the entire system. Shaft current is a key parameter during the operation of the generator shaft, and abnormal shaft current may cause bearing damage, insulation failure and other serious faults. Therefore, real-time monitoring and early warning of shaft current abnormalities are of great significance for preventing faults, prolonging equipment life and ensuring the reliable operation of wind turbines. At present, the traditional shaft current monitoring method mainly relies on periodic manual inspection or simple threshold alarm. On the one hand, manual inspection is time-consuming and difficult to detect acute faults in time; on the other hand, single threshold alarm is easily disturbed by environmental noise, causing false alarms or missed alarms, and cannot fully reflect the dynamic characteristics of shaft current, making it difficult to perform early fault warning. Based on this, we designed a shaft current early warning method applied to a wind driven generator to solve the above problems. SUMMARY

[0003] The purpose of the present application is to provide a shaft current early warning method applied to a wind driven generator, which realizes intelligent and accurate monitoring of shaft current abnormalities through multi-feature extraction and early warning degree model. It can not only fully reflect the dynamic characteristics of shaft current, provide quantitative early warning indicators, realize graded alarm, greatly improve the accuracy and timeliness of fault warning, but also help to realize predictive maintenance of wind turbines, reduce maintenance cost, and improve equipment reliability and service life.

[0004] The embodiments of the present application are implemented by the following technical solutions:

[0005] A shaft current early warning method applied to a wind driven generator, the steps of the method comprising:

[0006] In the wind turbine, a collection module is arranged on the generator shaft to obtain the operating data of the generator shaft, and the operating data of the generator shaft is preprocessed;

[0007] Multi-features of the operating data of the generator shaft are extracted, including mean feature, standard deviation feature, kurtosis feature and skewness feature;

[0008] An early warning degree model of shaft current is defined, and the early warning degree model of shaft current is solved in combination with the multi-features of the operating data of the generator shaft to obtain the early warning degree of the shaft current of the generator, and graded alarm of the shaft current of the generator is performed.

[0009] Optionally, the collecting module arranged on the generator shaft is a plurality of current sensors, and the current sensors are arranged and installed at the slip rings close to the generator shaft end of the wind turbine generator set to obtain the current operation data at the generator shaft.

[0010] Optionally, the operation data of the generator shaft is preprocessed, specifically by data cleaning and data smoothing of the current operation data at the generator shaft, and the calculation formula of the data smoothing of the current operation data at the generator shaft is:

[0011] wherein, is the i-th smoothed data point, n is the moving window size, and x j is the current operation data at the generator shaft.

[0012] Optionally, the multi-element feature of the generator shaft operation data is extracted, and the mean feature of the generator shaft operation data is extracted, and the calculation formula is:

[0013] wherein, μ is the mean feature, N is the sampling point number of the current sensor, and I i is the sampling value of the i-th current sensor.

[0014] Optionally, the multi-element feature of the generator shaft operation data is extracted, and the standard deviation feature of the generator shaft operation data is extracted, and the calculation formula is:

[0015] wherein, σ is the standard deviation feature.

[0016] Optionally, the multi-element feature of the generator shaft operation data is extracted, and the kurtosis feature of the generator shaft operation data is extracted, and the calculation formula is:

[0017] wherein, K is the kurtosis feature.

[0018] Optionally, the multi-element feature of the generator shaft operation data is extracted, and the skewness feature of the generator shaft operation data is extracted, and the calculation formula is:

[0019] wherein, S is the skewness feature.

[0020] Optionally, the multi-element feature of the generator shaft operation data is combined to solve the shaft current early warning degree model, and the calculation formula is:

[0021] Wherein, the CWI is a warning degree of the generator shaft current, to evaluate the abnormality degree of the generator shaft current, i is a shaft current characteristic index, the value range is 1 to 4, corresponding to the multiple characteristics of the generator shaft operation data, F i is the value of the i-th shaft current characteristic at the current time point, F i,0 is the reference value of the i-th shaft current characteristic under the normal operation state.

[0022] Optionally, the threshold values of the warning degree of the generator shaft current are respectively: a first-grade warning degree threshold, a second-grade warning degree threshold and a third-grade warning degree threshold:

[0023] Wherein: Q is an abnormal alarm level of the shaft current, T L is the first-grade warning degree threshold, T M is the second-grade warning degree threshold, T H is the third-grade warning degree threshold.

[0024] If not, it is determined that the generator shaft current is in a normal state, and the monitoring is continued; if yes, it is judged whether the warning degree of the generator shaft current is greater than the second-grade warning degree threshold, if not, the periodic change of the generator shaft operation data is analyzed, and the generator maintenance plan is prepared; if yes, it is judged whether the warning degree of the generator shaft current is greater than the third-grade warning degree threshold, if not, the monitoring frequency of the generator shaft operation data is increased, and the generator is maintained at a set time; if yes, the wind turbine operation is stopped, and the fault reason of the generator is analyzed and processed.

[0025] The technical scheme of the embodiment of the present application has at least the following advantages and beneficial effects:

[0026] The embodiment of the present application realizes intelligent and accurate monitoring of the shaft current abnormality through the multiple characteristic extraction and the warning degree model, can not only comprehensively reflect the dynamic characteristics of the shaft current, provide quantitative warning indexes, realize graded alarm, greatly improve the accuracy and timeliness of fault warning, but also helps to realize predictive maintenance of the wind turbine, reduce maintenance cost, and improve equipment reliability and service life. BRIEF DESCRIPTION OF DRAWINGS

[0027] Fig. 1 is a flowchart of a shaft current warning method applied to a wind turbine according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. The components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations.

[0029] As shown in FIG. 1, the present application provides one of the embodiments: a shaft current early warning method applied to a wind turbine, the steps of the method comprising:

[0030] In the wind turbine, a collection module is arranged on the generator shaft to obtain the operation data of the generator shaft, and the operation data of the generator shaft is preprocessed;

[0031] The multivariate features of the operation data of the generator shaft are extracted, including mean feature, standard deviation feature, kurtosis feature and skewness feature;

[0032] A shaft current early warning degree model is defined, the shaft current early warning degree model is solved in combination with the multivariate features of the operation data of the generator shaft, the early warning degree of the generator shaft current is obtained, and the graded alarm of the generator shaft current is performed.

[0033] In the present embodiment, the collection module arranged on the generator shaft is specifically a plurality of current sensors, the current sensors are respectively arranged and installed at the slip rings close to the shaft end of the wind turbine to obtain the current operation data at the generator shaft.

[0034] In implementation, the present embodiment selects the position close to the shaft end of the slip ring for installation, the main purpose of which is that the installation at the slip ring can stably capture the current signal passing through the shaft, and is less affected by mechanical stress and vibration, and the current sensor selected in the present embodiment is mainly a Hall effect sensor.

[0035] Further, the preprocessing of the operation data of the generator shaft is specifically data cleaning and data smoothing of the current operation data at the generator shaft, wherein the data smoothing of the current operation data at the generator shaft is calculated by the following formula:

[0036] wherein, is the ith smoothed data point, n is the moving window size, x j is the current operation data at the generator shaft.

[0037] Specifically, data cleaning is used to remove noise data and outliers, such as current values obviously higher or lower than the normal working range, and data smoothing is used to smooth the data by moving average method to reduce the influence of short-term fluctuations.

[0038] In the embodiment, the multivariate features of the generator shaft operation data are extracted, wherein the mean feature of the generator shaft operation data is extracted, and a calculation formula of the mean feature is:

[0039] wherein μ is the mean feature, N is the number of sampling points of the current sensor, I i is the sampling value of the i-th current sensor.

[0040] The multivariate features of the generator shaft operation data are extracted, wherein the standard deviation feature of the generator shaft operation data is extracted, and a calculation formula of the standard deviation feature is:

[0041] wherein σ is the standard deviation feature.

[0042] The multivariate features of the generator shaft operation data are extracted, wherein the kurtosis feature of the generator shaft operation data is extracted, and a calculation formula of the kurtosis feature is:

[0043] wherein K is the kurtosis feature.

[0044] The multivariate features of the generator shaft operation data are extracted, wherein the skewness feature of the generator shaft operation data is extracted, and a calculation formula of the skewness feature is:

[0045] wherein S is the skewness feature.

[0046] In the specific application of the embodiment, the multivariate features of the generator shaft operation data are combined to solve the shaft current early warning degree model, and a calculation formula of the shaft current early warning degree model is:

[0047] wherein CWI is the early warning degree of the generator shaft current, to evaluate the abnormality degree of the generator shaft current, i is the shaft current feature index, and the value range is 1 to 4, corresponding to the multivariate features of the generator shaft operation data, F i is the value of the i-th shaft current feature at the current time point, and F i,0 is the reference value of the i-th shaft current feature in the normal operation state.

[0048] According to the above application process, the threshold values of the early warning degree of the generator shaft current are defined as follows in the embodiment: a first grade early warning degree threshold value, a second grade early warning degree threshold value, and a third grade early warning degree threshold value:

[0049] wherein Q is the shaft current abnormality alarm level, T L is the first grade early warning degree threshold value, T M is the second grade early warning degree threshold value, and T H is the third grade early warning degree threshold value.

[0050] If not, it is determined that the generator shaft current is in a normal state, and the monitoring is continued. If yes, it is determined whether the pre-warning degree of the generator shaft current is greater than a second level pre-warning threshold value. If not, the periodic change of the generator shaft operation data is analyzed, and a generator maintenance plan is prepared. If yes, it is determined whether the pre-warning degree of the generator shaft current is greater than a third level pre-warning threshold value. If not, the monitoring frequency of the generator shaft operation data is increased, and the generator is maintained at a set time. If yes, the wind turbine generator set is stopped, and the failure cause of the generator is analyzed and processed.

[0051] The above merely describes the preferred embodiments of the present application, but is not intended to limit the present application. The present application can be variously changed and modified by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for early warning of shaft current applied to wind turbine generators, characterized in that, The steps of the method comprise: In the wind turbine, a collecting module is arranged on the generator shaft to obtain operation data of the generator shaft, and the operation data of the generator shaft is preprocessed; Multivariate features of the operation data of the generator shaft are extracted, including mean value features, standard deviation features, kurtosis features and skewness features; An early warning degree model of the shaft current is defined, the early warning degree model of the shaft current is solved in combination with the multivariate features of the operation data of the generator shaft to obtain the early warning degree of the generator shaft current, and a graded alarm of the generator shaft current is performed.

2. The shaft current warning method for a wind power generator according to claim 1, characterized in that, The collecting module is arranged on the generator shaft, and the collecting module is specifically a plurality of current sensors, which are respectively arranged and installed at the slip rings close to the end of the generator shaft of the wind turbine to obtain the current operation data at the generator shaft.

3. The shaft current warning method for a wind power generator according to claim 2, characterized in that, The operation data of the generator shaft is preprocessed, specifically: the current operation data at the generator shaft is cleaned and smoothed, wherein the current operation data at the generator shaft is smoothed, and the calculation formula is: wherein, For the ith smoothed data point, n is the moving window size, x j is the current operating data for the generator shaft.

4. The shaft current warning method for a wind power generator according to claim 2, wherein The multivariate feature of the extracted generator shaft operation data, wherein the mean value feature of the extracted generator shaft operation data is calculated by the following formula: wherein μ is the mean feature, N is the number of sampling points of the current sensor, I i is the sampling value of the i-th current sensor.

5. The shaft current warning method for a wind power generator according to claim 4, characterized in that, The multivariate features of the extracted generator shaft operation data, wherein a standard deviation feature of the extracted generator shaft operation data is extracted, and a calculation formula of the standard deviation feature is: Wherein, σ is the standard deviation feature.

6. The shaft current warning method for a wind power generator according to claim 5, wherein The multivariate feature of the extracted generator shaft operation data, wherein the kurtosis feature of the extracted generator shaft operation data is calculated by the following formula: Wherein, K is the kurtosis feature.

7. A shaft current warning method for a wind power generator according to claim 6, characterized in that, The multivariate feature of the extracted generator shaft operation data, wherein the skewness feature of the extracted generator shaft operation data is calculated by the following formula: Wherein, S is the skewness feature.

8. The shaft current warning method for a wind power generator according to any one of claims 1 to 7, characterized in that, The multi-element characteristic of the combined generator shaft operation data is solved to obtain a shaft current early warning degree model, and the calculation formula is: Wherein, CWI is the early warning degree of the generator shaft current, to evaluate the abnormal degree of the generator shaft current, i is the shaft current characteristic index, the value range is 1 to 4, corresponding to the multivariate characteristics of the generator shaft operation data, F i is the value of the i th shaft current characteristic at the current time point, F i,0 is the reference value of the i th shaft current characteristic under the normal operation state.

9. A shaft current warning method for a wind power generator according to claim 8, characterized in that, The threshold values for defining the early warning degree of the generator shaft current are respectively: a first-grade early warning degree threshold value, a second-grade early warning degree threshold value, and a third-grade early warning degree threshold value: Wherein: Q is the shaft current abnormal alarm level, T L T is the first grade warning degree threshold M T is the second grade warning degree threshold H T is the third grade warning degree threshold It is judged whether the early warning degree of the generator shaft current is greater than a first grade early warning degree threshold, if not, it is determined that the generator shaft current is in a normal state, and the monitoring is continued; if yes, it is judged whether the early warning degree of the generator shaft current is greater than a second grade early warning degree threshold, if not, the periodic change of the operation data of the generator shaft is analyzed, and a generator maintenance plan is prepared; if yes, it is judged whether the early warning degree of the generator shaft current is greater than a third grade early warning degree threshold, if not, the monitoring frequency of the operation data of the generator shaft is increased, and the generator is maintained at a set time; if yes, the wind turbine is stopped, and the fault reason of the generator is analyzed and processed.

Images