Turbulence intensity correction

Abstract

A method is provided for providing a correction model for correcting turbulence intensity values, the method comprising the step of acquiring one or more input signals, the input signals comprising at least a LIDAR_TI value, at least an anemometer-based turbulence intensity value (ANEMO_TI value), the standard deviation of horizontal wind speed at one or more measurement heights, and one or more oceanographic measurements. The method further comprises the step of providing a correction model by training a supervised computer-implemented machine learning (ML) model using training variables to map a subset of input signals to corresponding ratio LIDAR_TI / ANEMO_TI values, the training variables comprising a subset of input signals and corresponding resulting ratio LIDAR_TI / ANEMO_TI values ​​for one or more measurement heights, the subset of input signals comprising at least a LIDAR_TI value at one or more measurement heights, the standard deviation of horizontal wind speed at one or more measurement heights measured by a floating LIDAR, and one or more oceanographic measurements. Furthermore, a method for correcting turbulence intensity (TI) values ​​is provided, which includes the steps of providing a set of environment variables to a correction model, obtaining the current ratio LIDAR_TI / ANEMO_TI, and providing a corrected LIDAR_TI value by calculating corrected LIDAR_TI value = current ratio ANEMO_TI / LIDAR_TI * turbulence intensity (TI) value.

Claims

1. A computer implementation method for providing a correction model for correcting turbulence intensity values ​​(TI values), wherein the method is: A step of acquiring one or more input signals, wherein the input signals are A LiDAR-based turbulence intensity value (LIDAR_TI value) based on wind speed measured by a floating LiDAR at one or more measurement heights, At one or more measurement heights, at least an anemometer-based turbulence intensity value (ANEMO_TI value) is determined based on the wind speed measured by at least one anemometer attached to the weather mast, The standard deviation of the horizontal wind speed at one or more measurement heights measured by the floating LIDAR, One or more oceanographic measurement values, wherein the oceanographic measurement values ​​include one or more of the following: wave measurement values, significant wave height, significant wave period, salinity measurement values, mean wave direction, and seawater temperature. Steps including at least, A step of providing a correction model by training a supervised computer-implemented machine learning (ML) model using training variables to map at least a subset of the input signals to corresponding ratio LIDAR_TI / ANEMO_TI values, wherein the training variables include the at least subset of the input signals and corresponding result ratio LIDAR_TI / ANEMO_TI values ​​for each of the one or more measurement heights, and the at least subset of the input signals includes at least LIDAR_TI values ​​at the one or more measurement heights, the standard deviation of horizontal wind speed at the one or more measurement heights measured by the floating LIDAR, and the one or more sea condition measurements. Computer implementation methods, including those mentioned above.

2. Acquiring one or more input signals The wind speed measured by the floating LIDAR is received from the floating LIDAR, The acquisition of at least the LIDAR_TI value based on the wind speed received from the floating LIDAR, Receiving the wind speed measured by at least one anemometer mounted on a weather mast at one or more measurement heights from at least one anemometer, To obtain the at least one ANEMO_TI value based on the wind speed received from the at least one anemometer. The computer implementation method according to claim 1, including the method described in claim 1.

3. Acquiring one or more input signals Receiving the wind speed measured by the floating LIDAR from the first database, Obtaining at least the LIDAR_TI value based on the wind speed received from the second database, Receiving the wind speed measured by at least one anemometer attached to the weather mast from a third database, Obtaining at least the ANEMO_TI value based on the wind speed received from the fourth database, Includes, The first, second, third, and fourth databases mentioned above are the same or different databases. The computer implementation method according to claim 1.

4. A computer implementation method according to any one of claims 1 to 3, wherein obtaining or acquiring the at least LIDAR_TI value based on the wind speed measured by the floating LIDAR is performed by calculating the ratio of the standard deviation of the wind speed measured by the floating LIDAR to the average value of the corresponding wind speed measured by the floating LIDAR over a certain period of time, and / or obtaining or acquiring the at least ANEMO_TI value based on the wind speed measured by the at least one anemometer is performed by calculating the ratio of the standard deviation of the wind speed measured by the at least one anemometer to the average value of the corresponding wind speed measured by the at least one anemometer over a certain period of time.

5. Selecting one or more of the acquired one or more input signals, and Calculating or acquiring one or more secondary signals from the one or more input signals acquired. A computer implementation method according to any one of claims 1 to 4, further comprising providing the subset of the input signals by one or both of the following:

6. The computer implementation method according to any one of claims 1 to 5, wherein the ML model is a gradient boosting ML model.

7. A computer implementation method for correcting turbulence intensity (TI) values, wherein the method is: To provide a set of environment variables for a correction model provided by the method of any one of claims 1 to 6, wherein the set of environment variables includes at least a LIDAR_TI value at one or more measurement heights, a standard deviation of the horizontal wind speed at one or more measurement heights measured by the floating LIDAR, and one or more ocean condition measurements. From the correction model, obtain the current ratio LIDAR_TI / ANEMO_TI for each of the one or more measurement heights, The corrected LIDAR_TI value for each of the one or more measurement heights is provided by calculating the product of the ratio and the turbulence intensity (TI) value for each of the one or more measurement heights such that the corrected LIDAR_TI value is equal to the current ratio ANEMO_TI / LIDAR_TI * turbulence intensity (TI) value obtained by multiplication. Computer implementation methods, including those mentioned above.

8. A computer program product that, when executed by a computer, includes instructions causing the computer to perform the steps of the method according to claims 1 to 6, and / or causing the computer to perform the steps of the method according to claim 7.

9. A system for providing a correction model for correcting turbulence intensity values ​​(TI values), wherein the system is: Processor and A non-temporary computer-readable medium that communicates with the processor and stores instruction codes, wherein the instruction codes, when executed by the processor, cause the processor to perform the steps of the method according to any one of claims 1 to 6. A system equipped with these features.

10. The system according to claim 9, wherein the non-temporary computer-readable medium stores the corrected model once the ML model has been trained in a supervised manner using training variables to map a subset of input signals to corresponding ratio LIDAR_TI / ANEMO_TI values, the training variables comprising a subset of input signals and corresponding ground truth ratio LIDAR_TI / ANEMO_TI values ​​for one or more measurement heights, the subset of input signals comprising at least the LIDAR_TI values ​​at one or more measurement heights, the standard deviation of horizontal wind speed at one or more measurement heights measured by the floating LIDAR, and one or more ocean condition measurements.

11. A system for providing the correction model according to claim 9 or 10, further comprising a LIDAR mounted on a floating platform.

12. A system for providing the correction model according to any one of claims 9 to 11, wherein the floating platform comprises a communication module configured to receive wind speed from a weather mast.

13. A system for correcting turbulence intensity (TI) values, wherein the system is Correction processor, A non-temporary computer-readable medium that communicates with the correction processor and stores instruction codes, wherein, when the instruction codes are executed by the processor, the non-temporary computer-readable medium causes the processor to perform the steps of the method according to claim 7. A system equipped with these features.

14. A system for correcting turbulence intensity (TI) values ​​according to claim 13, further comprising a LIDAR attached to a floating platform.

15. Correction models provided by the method described in any one of claims 1 to 6, and / or An instruction, when executed by a processor, causes the processor to perform the method described in any one of claims 1 to 7. A non-temporary, readable memory medium that stores data.

Images