Shaft current early warning method applied to wind driven generator

Abstract

The invention relates to the technical field of wind driven generators, in particular to a shaft current early warning method applied to a wind driven generator, and the method comprises the steps: arranging an acquisition module for a generator shaft in a wind turbine generator to obtain the operation data of the generator shaft, and carrying out the preprocessing of the operation data of the generator shaft; extracting multivariate features of the generator shaft operation data, wherein the multivariate features comprise a mean value feature, a standard deviation feature, a kurtosis feature and a skewness feature; and a shaft current early warning degree model is defined, the shaft current early warning degree model is solved by combining the multivariate features of the generator shaft operation data, the early warning degree of the generator shaft current is obtained, and graded alarm of the generator shaft current is executed. Through multivariate feature extraction and the early warning degree model, intelligent and accurate monitoring of the shaft current abnormity is realized, predictive maintenance of the wind turbine generator is realized, the reliability of equipment is improved, and the service life of the equipment is prolonged.

Description

Technical Field

[0001] 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. Background Art

[0002] As an important part of renewable energy, the safe and stable operation of wind turbines is of vital importance. The generator shaft is one of the core components of wind turbines, and its operating status directly affects the performance and life of the entire system. Shaft current is a key parameter in the operation of the generator shaft. Abnormal shaft current may cause serious faults such as bearing damage and insulation failure. Therefore, real-time monitoring and early warning of shaft current abnormalities are of great significance for preventing faults, extending equipment life, and ensuring the reliable operation of wind turbines. At present, traditional shaft current monitoring methods often rely on regular manual inspections or simple threshold alarms. On the one hand, the manual inspection cycle is long and it is difficult to detect acute faults in time; on the other hand, the single threshold alarm is easily interfered by environmental noise, resulting in false alarms or missed alarms, and it cannot fully reflect the dynamic characteristics of the shaft current, making it difficult to carry out early fault warnings. Based on this, in response to the above problems, we designed a shaft current early warning method for wind turbines. Summary of the invention

[0003] The purpose of the present invention is to provide a shaft current warning method applied to wind turbines, which realizes intelligent and precise monitoring of shaft current anomalies through multivariate feature extraction and warning degree model. It can not only comprehensively reflect the dynamic characteristics of shaft current, provide quantitative warning indicators, and realize graded alarm, greatly improving the accuracy and timeliness of fault warning, but also helps to realize predictive maintenance of wind turbines, reduce maintenance costs, and improve equipment reliability and service life.

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

[0005] A shaft current early warning method for a wind turbine generator, the method comprising the following steps:

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

[0007] Extract multivariate features of generator shaft operation data, including mean feature, standard deviation feature, kurtosis feature and skewness feature;

[0008] A shaft current warning degree model is defined, and the shaft current warning degree model is solved in combination with the multivariate characteristics of the generator shaft operation data to obtain the warning degree of the generator shaft current, and perform graded alarm of the generator shaft current.

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

[0010] Optionally, the preprocessing of the operating data of the generator shaft is specifically: data cleaning and data smoothing of the current operating data at the generator shaft, wherein the data smoothing of the current operating data at the generator shaft is calculated by the following formula:

[0011]

[0012] in, is the i-th smoothed data point, n is the moving window size, x j is the operating data of the current at the generator shaft.

[0013] Optionally, the multivariate features of the generator shaft operation data are extracted, wherein the mean feature of the generator shaft operation data is extracted, and the calculation formula is:

[0014]

[0015] Among them, μ is the mean characteristic, N is the number of sampling points of the current sensor, I i is the sampling value of the i-th current sensor.

[0016] Optionally, the multivariate features of the generator shaft operation data are extracted, wherein the standard deviation features of the generator shaft operation data are extracted, and the calculation formula is:

[0017]

[0018] Among them, σ is the standard deviation characteristic.

[0019] Optionally, the multivariate features of the generator shaft operation data are extracted, wherein the kurtosis feature of the generator shaft operation data is extracted, and the calculation formula is:

[0020]

[0021] Among them, K is the kurtosis characteristic.

[0022] Optionally, the multivariate features of the generator shaft operation data are extracted, wherein the skewness feature of the generator shaft operation data is extracted, and the calculation formula is:

[0023]

[0024] Among them, S is the skewness characteristic.

[0025] Optionally, the shaft current warning degree model is solved by combining the multivariate characteristics of the generator shaft operation data, and the calculation formula is:

[0026]

[0027] Among them, CWI is the warning degree of the generator shaft current, which is used to evaluate the abnormal degree of the generator shaft current. i is the shaft current feature index, which ranges from 1 to 4, corresponding to the multivariate characteristics of the generator shaft operation data. i is the value of the i-th axis current characteristic at the current time point, F i,0 is the reference value of the i-th axis current characteristic under normal operating conditions.

[0028] Optionally, the thresholds for the warning degree of the generator shaft current are defined as: a first-level warning degree threshold, a second-level warning degree threshold, and a third-level warning degree threshold:

[0029]

[0030] Where: Q is the shaft current abnormal alarm level, T L is the first level warning threshold, T M is the second level warning threshold, T H It is the third level warning threshold;

[0031] Determine whether the warning degree of the generator shaft current is greater than the first-level warning threshold. If not, determine that the generator shaft current is in normal state and continue monitoring; if so, determine whether the warning degree of the generator shaft current is greater than the second-level warning threshold. If not, analyze the periodic changes of the generator shaft operation data and prepare a generator maintenance plan; if so, determine whether the warning degree of the generator shaft current is greater than the third-level warning threshold. If not, increase the monitoring frequency of the generator shaft operation data and maintain the generator at the set time; if so, stop the operation of the wind turbine set, analyze and handle the cause of the generator failure.

[0032] The technical solution of the embodiment of the present invention has at least the following advantages and beneficial effects:

[0033] The embodiment of the present invention realizes intelligent and precise monitoring of shaft current anomalies through multivariate feature extraction and early warning model. It can not only comprehensively 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 costs, and improve equipment reliability and service life. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1A schematic flow chart of a shaft current early warning method applied to a wind turbine provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0036] like Figure 1 As shown, the present invention provides one embodiment: a shaft current early warning method applied to a wind turbine generator, the method comprising the steps of:

[0037] In the wind turbine, a collection module is arranged on the generator shaft to obtain the operating data of the generator shaft and pre-process the operating data of the generator shaft;

[0038] Extract multivariate features of generator shaft operation data, including mean feature, standard deviation feature, kurtosis feature and skewness feature;

[0039] A shaft current warning degree model is defined, and the shaft current warning degree model is solved in combination with the multivariate characteristics of the generator shaft operation data to obtain the warning degree of the generator shaft current, and perform graded alarm of the generator shaft current.

[0040] In this embodiment, the generator shaft is provided with a collection module, which is specifically a plurality of current sensors, and the current sensors are respectively installed at the slip rings of the wind turbine set close to the generator shaft end to obtain the current operation data at the generator shaft.

[0041] During implementation, this embodiment selects a position where the slip ring is installed close to the shaft end. The main purpose is that the installation at the slip ring can stably capture the current signal passing through the shaft, and is also less affected by mechanical stress and vibration. The current sensor selected in this embodiment is mainly a Hall effect sensor.

[0042] Furthermore, the preprocessing of the operating data of the generator shaft is specifically: data cleaning and data smoothing of the current operating data at the generator shaft, wherein the data smoothing of the current operating data at the generator shaft is calculated by the following formula:

[0043]

[0044] in, is the i-th smoothed data point, n is the moving window size, x jis the operating data of the current at the generator shaft.

[0045] Specifically, data cleaning is used to remove noisy data and outliers, such as current values ​​that are significantly higher or lower than the normal operating range, and data smoothing uses a moving average method to smooth the data to reduce the impact of short-term fluctuations.

[0046] In this 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 the calculation formula is:

[0047]

[0048] Among them, μ is the mean characteristic, N is the number of sampling points of the current sensor, I i is the sampling value of the i-th current sensor.

[0049] The multivariate features of the generator shaft operation data are extracted, wherein the standard deviation features of the generator shaft operation data are extracted, and the calculation formula is:

[0050]

[0051] Among them, σ is the standard deviation characteristic.

[0052] The multivariate features of the generator shaft operation data are extracted, wherein the kurtosis feature of the generator shaft operation data is extracted, and the calculation formula is:

[0053]

[0054] Among them, K is the kurtosis characteristic.

[0055] The multivariate features of the generator shaft operation data are extracted, wherein the skewness features of the generator shaft operation data are extracted, and the calculation formula is:

[0056]

[0057] Among them, S is the skewness characteristic.

[0058] In the specific application of this embodiment, the shaft current warning degree model is solved by combining the multivariate characteristics of the generator shaft operation data, and the calculation formula is:

[0059]

[0060] Among them, CWI is the warning degree of the generator shaft current, which is used to evaluate the abnormal degree of the generator shaft current. i is the shaft current feature index, which ranges from 1 to 4, corresponding to the multivariate characteristics of the generator shaft operation data. i is the value of the i-th axis current characteristic at the current time point, F i,0is the reference value of the i-th axis current characteristic under normal operating conditions.

[0061] According to the above application process, this embodiment defines the thresholds of the warning degree of the generator shaft current as follows: the first level warning degree threshold, the second level warning degree threshold and the third level warning degree threshold:

[0062]

[0063] Where: Q is the shaft current abnormal alarm level, T L is the first level warning threshold, T M is the second level warning threshold, T H It is the third level warning threshold;

[0064] Determine whether the warning degree of the generator shaft current is greater than the first-level warning threshold. If not, determine that the generator shaft current is in normal state and continue monitoring; if so, determine whether the warning degree of the generator shaft current is greater than the second-level warning threshold. If not, analyze the periodic changes of the generator shaft operation data and prepare a generator maintenance plan; if so, determine whether the warning degree of the generator shaft current is greater than the third-level warning threshold. If not, increase the monitoring frequency of the generator shaft operation data and maintain the generator at the set time; if so, stop the operation of the wind turbine set, analyze and handle the cause of the generator failure.

[0065] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A shaft current early warning method for a wind turbine, characterized in that: The steps of the method include: In the wind turbine, a collection module is arranged on the generator shaft to obtain the operating data of the generator shaft and pre-process the operating data of the generator shaft; Extract multivariate features of generator shaft operation data, including mean feature, standard deviation feature, kurtosis feature and skewness feature; A shaft current warning degree model is defined, and the shaft current warning degree model is solved in combination with the multivariate characteristics of the generator shaft operation data to obtain the warning degree of the generator shaft current, and perform graded alarm of the generator shaft current.

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

3. The shaft current early warning method for a wind turbine according to claim 2 is characterized in that: The preprocessing of the generator shaft operation data 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 as follows: in, is the i-th smoothed data point, n is the moving window size, x j is the operating data of the current at the generator shaft.

4. The shaft current early warning method for a wind turbine according to claim 2, characterized in that: The multivariate features of the generator shaft operation data are extracted, wherein the mean feature of the generator shaft operation data is extracted, and the calculation formula is: Among them, μ is the mean characteristic, 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 early warning method for a wind turbine according to claim 4, characterized in that: The multivariate features of the generator shaft operation data are extracted, wherein the standard deviation features of the generator shaft operation data are extracted, and the calculation formula is: Among them, σ is the standard deviation characteristic.

6. The shaft current early warning method for a wind turbine according to claim 5, characterized in that: The multivariate features of the generator shaft operation data are extracted, wherein the kurtosis feature of the generator shaft operation data is extracted, and the calculation formula is: Among them, K is the kurtosis characteristic.

7. The shaft current early warning method for a wind turbine generator according to claim 6, characterized in that: The multivariate features of the generator shaft operation data are extracted, wherein the skewness features of the generator shaft operation data are extracted, and the calculation formula is: Among them, S is the skewness characteristic.

8. The shaft current early warning method for a wind turbine generator according to any one of claims 1 to 7, characterized in that: The shaft current warning degree model is solved by combining the multivariate characteristics of the generator shaft operation data, and its calculation formula is: Among them, CWI is the warning degree of the generator shaft current, which is used to evaluate the abnormal degree of the generator shaft current. i is the shaft current feature index, which ranges from 1 to 4, corresponding to the multivariate characteristics of the generator shaft operation data. i is the value of the i-th axis current characteristic at the current time point, F i,0 is the reference value of the i-th axis current characteristic under normal operating conditions.

9. The shaft current early warning method for a wind turbine according to claim 8, characterized in that: The thresholds for the warning degree of the generator shaft current are defined as: the first level warning degree threshold, the second level warning degree threshold and the third level warning degree threshold: Where: Q is the shaft current abnormal alarm level, T L is the first level warning threshold, T M is the second level warning threshold, T H It is the third level warning threshold; Determine whether the warning degree of the generator shaft current is greater than the first-level warning threshold. If not, determine that the generator shaft current is in normal state and continue monitoring; if so, determine whether the warning degree of the generator shaft current is greater than the second-level warning threshold. If not, analyze the periodic changes of the generator shaft operation data and prepare a generator maintenance plan; if so, determine whether the warning degree of the generator shaft current is greater than the third-level warning threshold. If not, increase the monitoring frequency of the generator shaft operation data and maintain the generator at the set time; if so, stop the operation of the wind turbine set, analyze and handle the cause of the generator failure.

Images