Method and system of wind turbine condition monitoring

• US 8,538,729 B2
• Filed: 10/01/2009
• Issued: 09/17/2013
• Est. Priority Date: 10/01/2008
• Status: Expired due to Fees

• Current Assignee: Gram & Juhl A/S, Siemens Gamesa Renewable Energy A/S (Siemens AG)
• Original Assignee: Gram & Juhl A/S, Siemens AG
• Inventors: Gram-Hansen, Klaus, Juhl, Axel, Moeller, Troels Kildemoes
• Primary Examiner(s): Taningco, Alexander H
• Assistant Examiner(s): RIVERA VARGAS, MANUEL A
• Application Number:
  US12/571,773
• Publication Number:
  US 20100082295A1
• Time in Patent Office: 1,447 Days
• Field of Search: 702/182
• US Class Current: 702/182
• CPC Class Codes: F03D 17/00 Monitoring or testing of wind motors, e.g. diagnostics testing during commissioning of wind motors F03D13/30
• CPC Class Codes: G05B 23/0221 Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods
• CPC Class Codes: G05B 23/0264 Control of logging system, e.g. decision on which data to store; time-stamping measurements
• CPC Class Codes: Y02E 10/72 Wind turbines with rotation axis in wind direction

Abstract

The invention relates to a method of condition monitoring of a wind turbine. Measurement data and operating condition parameters are captured. A subset of the operating condition parameters is selected. A set of n characterizing moments is calculated based on the subset of operating condition parameters. A finite n-dimensional space each representing possible values for one of the characterising moments is provided. The n-dimensional space is sub-divided into a number of bins each representing a n-dimensional interval defined by n one-dimensional intervals. Each one- dimensional intervals represents an interval in one of the n dimensions. Each bin defines an acceptable range for the set of n characterizing moments. The set of the characterising moments is determined if it belongs to one of the bins. The set of the characterising moments and measurement data are accepted if the set of the characterising moments belongs to one of the bins.

Claims

1. A method for monitoring an operating condition of a wind turbine, comprising:

capturing measurement data and operating condition parameters by various sensors and recording in memory;

assigning the captured measurement data to a correct one of a plurality of bins by;

selecting a subset of the operating condition parameters by a processing unit;

calculating a set of n characterizing moments based on the selected subset of the operating condition parameters by the processing unit, wherein the n characterizing moments comprise a set of values that characterize operational states of the turbine;

defining a finite n-dimensional space, each of the n-dimensional space representing possible values for one of the n characterising moments by the processing unit;

sub-dividing the n-dimensional space into the plurality of bins by the processing unit, each of the bins representing a n-dimensional interval and defining an acceptable range for the set of the n characterizing moments that characterize operational states of the turbine;

defining the n-dimensional interval by n one-dimensional intervals by the processing unit, each of the n one-dimensional intervals representing an interval in one of the n-dimensional space;

determining if the set of the characterising moments falls within the acceptable range for one of the bins by the processing unit;

accepting the set of the characterising moments and the captured measurement data if the set of the characterising moments belongs to the one of the bins by the processing unit;

assigning the captured measurement data to the correct one of the bins based on the acceptable range determination to correlate the captured measurement data with the operational state of the turbine represented by that bin; and

determining if required input values are available for a selected evaluation method from the captured measurement data and evaluating the captured measurement data correlated with operational state of the turbine by bin according to the selected evaluation method.

2. The method as claimed in claim 1, wherein if the set of the characterizing moments does belong to the one of the bins, processed data of the captured measurement data and the set of the characterising moments are determined whether to be stored in a long-term storage.

3. The method as claimed in claim 2, wherein an alarm status is detected for checking whether the alarm status has changed with respect to the processed measurement data and characterising moments contained in the long-term storage and the processed measurement data and characterising moments are to be stored in the long-term storage if the alarm status has changed.

4. The method as claimed in claim 3, wherein a given time is determined for checking whether the given time has passed since a last storing of the processed measurement data and characterising moments in the long-term storage and the processed measurement data and characterising moments are to be stored in the long-term storage if the given time has passed.

5. The method as claimed in claim 4, wherein the given time is determined for checking whether the given time has passed since the last storing of processed measurement data in the long-term storage only when the alarm status has not changed.

6. The method as claimed in claim 1, wherein the captured measurement data and the operating condition parameters are evaluated based on evaluating a rule definition.

7. The method as claimed in claim 6, wherein the rule definition comprises a rule expression defining a type of an evaluation method, a time of evaluating the measurement data, a frequency of evaluating the measurement data, a type of data to be used for evaluating the measurement data, and an amount of data to be used for evaluating the measurement data.

8. The method as claimed in claim 1, wherein an index of the one of the bins is provided and an evaluation of the captured measurement data is tagged with the index of the one of the bins to which the set of the characterising moments belongs.

9. The method as claimed in claim 1, wherein if the set of the characterizing moments does not belong to the one of the bins, the set of the characterising moments is determined again.

10. The method as claimed in claim 1, wherein the captured measurement data and the operating condition parameters are continuously captured.

11. The method as claimed in claim 1, wherein the captured measurement data and the operating condition parameters comprise measurement data captured from a condition monitoring system, a vibration measurement value, a strain gauge measurement value, a wind speed measurement value, a rotor rotational speed value, a generated power value, a temperature measurement value, and a measurement value representative of an amount of metal particles detected in a lubricating oil of the wind turbine.

12. The method as claimed in claim 1, wherein the characterizing moments are calculated by calculating a root mean square or a mean value of the operating condition parameters.

13. The method as claimed in claim 1, wherein the measurement data is evaluated by processing the captured measurement data and comparing the processed captured measurement data with previously processed captured measurement data associated to the set of the characterising moments which belongs to the same bin.

14. The method as claimed in claim 1, wherein the captured measurement data is processed in real time for pulse-counting on oil-debris monitoring equipment, safety critical monitor of general vibration level, tower sway detection, and over speed detection.

15. The method as claimed in claim 1, wherein the captured measurement data is stored in a memory and is subsequently processed offline for autospectra, time series, and envelopes.

16. A wind turbine monitoring system for monitoring an operating condition of a wind turbine, comprising:

a memory that comprises captured measurement data and operating condition parameters and a plurality of bins; and

a processing unit that;

selects a subset of the operating condition parameters;

calculates a set of n characterizing moments based on the selected subset of the operating condition parameters, wherein the n characterizing moments comprise a set of values that characterize operational states of the turbine;

defines a finite n-dimensional space, each of the n-dimensional space representing a possible value for one of the n characterising moments;

sub-divides the n-dimensional space into the plurality of bins, each of the bins representing a n-dimensional interval and defining an acceptable range for the set of the n characterizing moments that characterize operational states of the turbine;

defines the n-dimensional interval by n one-dimensional intervals, each of the n one-dimensional intervals representing an interval in one of the n-dimensional space;

determines if the set of the characterising moments falls within the acceptable range for one of the bins;

accepts the set of the characterising moments and the captured measurement data if the set of the characterising moments belongs to the one of the bins;

assigns the captured measurement data to a correct one of the bins based on the acceptable range determination in order to correlate the captured measurement data with operational state of the turbine represented by that bin; and

determines if required input values are available for a selected evaluation method from the captured measurement data and evaluates the captured measurement data correlated with operational state of the turbine by bin according to the selected evaluation method.