Traitement en cours

Veuillez attendre...

Paramétrages

Paramétrages

Aller à Demande

1. WO2020165047 - PROCÉDÉ D'ANALYSE MISE EN ŒUVRE PAR ORDINATEUR D'UN PARC ÉOLIEN COMPRENANT UN CERTAIN NOMBRE D'ÉOLIENNES

Note: Texte fondé sur des processus automatiques de reconnaissance optique de caractères. Seule la version PDF a une valeur juridique

[ EN ]

Patent Claims

1. A method for computer-implemented analysis of a wind farm (1) comprising a number of wind turbines (2), wherein at each time point of one or more time points the following steps are performed :

i) applying an object detection algorithm (ODA) to a digi tal image (IM) showing the current state of the earth's ground in a surrounding area of the wind farm (1), re sulting in the extraction and localization of a number of detected objects (3) not belonging to the wind farm (1) within the image (IM), where each detected object (3) is of an object type (OT) out of a number of object types (OT) ;

ii) determining an information on whether there is a change with respect to the number of detected objects (3) in comparison to an earlier state of the earth's ground in the surrounding area of the wind farm (1), the change enabling an adaptation of the operation of the wind farm (1) in compliance with a predetermined curtailment (CU) limiting one or more effects resulting from the opera tion of the wind farm (1), and/or determining a number of operation constraints (OC) for the wind farm (1) based on the number of detected objects (3) such that the wind farm (1) generates maximum electric energy (AEP) within a predetermined time interval on condition that a predetermined curtailment (CU) limiting one or more effects resulting from the operation of the wind farm (1) is complied with.

2. The method according to claim 1, wherein the one or more effects limited by the predetermined curtailment refer to sound and/or shadow flickering and/or ice throw caused by the wind farm ( 1 ) .

3. The method according to claim 1 or 2, wherein the number of object types (OT) comprises:

one or more building types, preferably residential and non-residential buildings, and/or

one or more traffic route types, preferably one or more road types, and/or

one or more ground inclination types, and/or

one or more tree types.

4. The method according to one of the preceding claims, wherein one or more of the detected objects (3) are associat ed with one or more properties thereof which are extracted by the object detection algorithm (ODA) .

5. The method according to claim 4, wherein the one or more properties comprise the height of a detected object (3) .

6. The method according to one of the preceding claims, wherein steps i) and ii) are repeated in case that an updated digital image (IM) is available.

7. The method according to one of the preceding claims, wherein steps i) and ii) are repeated in case that the prede termined curtailment (CU) has changed.

8. The method according to one of the preceding claims, wherein the object detection algorithm (ODA) is based on a trained data driven model.

9. The method according to claim 8, wherein the data driven model is a neural network, preferably a Convolutional Neural Network .

10. The method according to one of the preceding claims, wherein the digital image (IM) is an image taken by a flying object over ground, particularly taken by a satellite or a plane or a drone.

11. The method according to one of the preceding claims, wherein the information on whether there is a change with re- spect to the number of detected objects (3) in comparison to an earlier state of the earth's ground in the surrounding ar ea of the wind farm (1) and/or the number of operation con straints (OC) for the wind farm (1) and/or the maximum elec tric energy production (AEP) are output via a user interface (UI) .

12. A system for computer-implemented analysis of a wind farm (1) comprising a number of wind turbines (2), where the sys tem comprises a processor (PR) configured to carry out a method, in which at each time point of one or more time points the following steps are performed:

i) applying an object detection algorithm (ODA) to a digi tal image (IM) showing the current state of the earth's ground in a surrounding area of the wind farm (1), re sulting in the extraction and localization of a number of detected objects (3) not belonging to the wind farm (1) within the image (IM), where each detected object (3) is of an object type (OT) out of a number of object types (OT) ;

ii) determining an information on whether there is a change with respect to the number of detected objects (3) in comparison to an earlier state of the earth's ground in the surrounding area of the wind farm (1), the change enabling an adaptation of the operation of the wind farm (1) in compliance with a predetermined curtailment (CU) limiting one or more effects resulting from the opera tion of the wind farm (1), and/or determining a number of operation constraints (OC) for the wind farm (1) based on the number of detected objects (3) such that the wind farm (1) generates annual energy production (AEP) within a predetermined time interval on condition that a predetermined curtailment (CU) limiting one or more effects resulting from the operation of the wind farm (1) is complied with.

13. The system according to claim 12, wherein the system is configured to perform a method according to one of claims 2 to 11.

14. A computer program product with program code, which is stored on a non-transitory machine-readable carrier, for car rying out a method according to one of claims 1 to 11 when the program code is executed on a computer.

15. A computer program with program code for carrying out a method according to one of claims 1 to 11 when the program code is executed on a computer.