Traitement en cours

Veuillez attendre...

PATENTSCOPE sera indisponible durant quelques heures pour des raisons de maintenance le mardi 26.10.2021 à 12:00 PM CEST
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 ]

Description

A method for computer-implemented analysis of a wind farm comprising a number of wind turbines

The invention refers to a method and a system for computer-implemented analysis of a wind farm comprising a number of wind turbines. Furthermore, the invention refers to a corre sponding computer program product and a corresponding comput er program.

During the planning phase of a wind farm, a surrounding area around the planned location of the wind farm is analyzed. In this analysis, all impacts of wind turbines on humans and particularly residents in the neighborhood of the farm are evaluated. As a result, operation constraints are determined in order to comply with a curtailment limiting the adverse effects resulting from the operation of the wind farm.

A curtailment may refer to a maximum sound pressure level, particularly during night, at residential buildings around the wind farm. To comply with this curtailment, the wind farm has to be operated with reduced power resulting in less speed of the rotor blades of wind turbines and thus in less sound. Another curtailment may refer to a limited operation time of the wind turbines in order to reduce the adverse effects of shadow flickering for residents in the neighborhood of a wind farm. To comply with this curtailment, fixed operation inter vals for the turbines are defined.

After having determined operation constraints in the planning phase, the wind farm launched after planning is usually oper ated based on the operation constraints for its complete life time even in case that sources of curtailment disappear in the meantime.

It is an object of the invention to provide a method for com puter-implemented analysis of a wind farm in order to auto matically determine an efficient operation of the farm.

This object is solved by the method according to claim 1. Preferred embodiments of the invention are defined in the de pendent claims.

The method of the invention provides a computer-implemented analysis of a wind farm comprising a number of wind turbines, i.e. at least one wind turbine. This wind farm has already been installed at a location on the earth's ground.

In method of the invention, the following steps i) and ii) are performed at each time point of one or more time points. In step i), an object detection algorithm is applied to a digital image showing the current state of the earth's ground in a surrounding area of the wind farm. This object detection algorithm results in the extraction and localization of a number of detected objects not belonging to the wind farm within the image, where each detected object is of an object type out of a number of object types. Relevant object types may be defined beforehand. As an object detection algorithm, any prior art algorithm for analyzing images may be used. In a particularly preferred embodiment, the object detection al gorithm is based on a trained data driven model where images comprising known objects of corresponding object types were used as training data so that objects of these object types can indeed be extracted. In a particular preferred embodi ment, the data driven model is a neural network. Preferably, a Convolutional Neural Network well known from the prior art is used. Convolutional Neural Networks are particularly suit able for processing image data.

In a first variant of step ii) of the method, an information is determined on whether there is a change with respect to the number of detected objects (i.e. whether objects have disappeared or occurred and whether properties of existing objects have changed) in comparison to an earlier state (i.e. a state at a time point before the current state) of the earth's ground in the surrounding area of the wind farm, the change enabling an adaptation of the operation of the wind farm in compliance with a predetermined curtailment limiting one or more (adverse) effects resulting from the operation of the wind farm. Hence, in this first variant, only an indica tion of a possible adaptation of the operation of the wind farm due to environmental changes is given. E.g., this infor mation may be used by the operator of the wind farm in order to obtain permission for an adapted operation of the wind farm from authorities. Preferably, the earlier state of the earth's ground is derived from a corresponding (earlier) im age by applying an object detection algorithm, as it is the case for the current state of the earth's ground. However, the earlier state of the earth's ground may also be based on another digital description not being based on an image.

In a second variant of step ii) which can be performed alone or in combination with the first variant, a number of opera tion constraints for the wind farm is (automatically) deter mined based on the number of detected objects such that the wind farm generates maximum electric energy within a prede termined time interval on condition that a predetermined cur tailment (corresponding to the above curtailment if the first and second variants are combined) limiting one or more (ad verse) effects resulting from the operation of the wind farm is complied with. A predetermined time interval may refer e.g. to one year so that the maximum electric energy refers to the maximum annual energy production of the wind farm. Methods for automatically determining operation constraints based on objects in the neighborhood of a wind farm are known for a skilled person and, thus, will not be described in de tail herein.

The invention is based on the finding that an automatic anal ysis of images of the earth' s ground around a wind farm ena bles to derive objects relevant for operation constraints based on a predetermined curtailment defined for the wind farm. Hence, it is possible to update operation constraints based on newly acquired images. As a consequence, the opera tion of a wind farm can be adapted to changing environmental conditions .

In a particularly preferred embodiment, the one or more ef fects limited by the predetermined curtailment refer to sound and/or shadow flickering and/or ice throw caused by the wind farm. The predetermined curtailment includes those effects by defining corresponding restrictions, e.g. by defining a maxi mum sound pressure level at residential buildings in the sur rounding area of the wind farm or by defining a maximum oper ation time of the wind turbines during day in order to limit sound propagation and/or shadow flickering or by defining a maximum rotation speed of the wind turbine rotors in order to avoid ice throw during winter.

In a particularly preferred embodiment, the above number of object types comprises the following types:

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 (e.g. walkway, cycling path, main road, second ary road, highway and the like), and/or

one or more ground inclination types, and/or

one or more tree types.

In a variant of the above embodiment, only the object types "building" and/or "traffic route" and/or "ground inclination" and/or "tree" may be defined.

In a particularly preferred embodiment, the one or more de tected objects are associated with one or more properties thereof which are extracted by the object detection algo rithm. This enables a very exact determination of operation constraints .

In another preferred embodiment, the one or more properties of the detected objects refer to the height of a detected ob ject which is particularly useful when considering sound and/or shadow flickering as the effects limited by the prede termined curtailment.

The above steps i) and ii) are preferably performed several times based on certain criteria. In a preferred embodiment, steps i) and ii) are repeated in case that an updated digital image is available, e.g. from a database storing those imag es. In another preferred embodiment, steps i) and ii) are re peated in case that the predetermined curtailment has

changed. This enables an adaptation of the operation of the wind farm to changed regulations of authorities.

The digital image processed by the method of invention is preferably taken by a flying object over ground, particularly by a satellite or a plane or a drone. Nevertheless, the image may also be taken by one or more cameras installed on ground at the location of the wind farm, e.g. at the position of the nacelle of one or more wind turbines.

In a particularly preferred embodiment, the information on whether there is a change with respect to the number of de tected objects in comparison to an earlier state of the earth's ground in the surrounding area of the wind farm and/or the number of operation constraints for the wind farm and/or the maximum electric energy as determined in step ii) are output via a user interface. This user interface may be accessible for staff of the operator of the wind farm. Hence, the operator has the option to change the operation of the wind farm or to negotiate with authorities in order to achieve an adapted operation resulting in higher energy out put .

Besides the above method, the invention refers to a system for computer-implemented analysis of a wind farm comprising a number of wind turbines, where the system comprises a proces- sor configured to carry out the method according to the in vention or according to one or more embodiments of the inven tion .

The invention also refers to a computer program product with program code, which is stored on a non-transitory machine-readable carrier, for carrying out the method according to the invention or according to one or more embodiments of the invention, when the program code is executed on a computer.

Furthermore, the invention refers to a computer program with program code for carrying out the method according to the in vention or according to one or more embodiments of the inven tion, when the program code is executed on a computer.

In the following, an embodiment of the invention will be de scribed in detail with respect to the accompanying drawings wherein :

Fig. 1 shows a flow chart illustrating the steps according to a method based on an embodiment of the inven tion; and

Fig. 2 shows a system for performing the method as shown in Fig . 1.

The method as described in the following refers to the analy sis of a wind farm where the operation of the wind farm is subjected to a curtailment limiting one or more adverse ef fects for humans resulting from the operation of the wind farm. In a preferred embodiment, the curtailment refers to restrictions given by an authority in order to limit sound and shadow flickering of the wind farm for residential build ings in the surrounding area of the wind farm. Sound and shadow flickering is caused by the rotation of the wind tur bine rotors of the wind farm.

The above curtailment can be defined in various ways. E.g., a curtailment with respect to sound can be such that a sound pressure level caused by the wind farm at the location of a residential building must not exceed a certain threshold. Furthermore, the sound curtailment may also be coupled to certain time periods, e.g. the above threshold may only be applicable for the operation of the wind farm during night or different thresholds for night and day may be defined.

Furthermore, a curtailment with respect to shadow flickering may be given by a maximum amount of operation hours of the wind farm in a given time interval, e.g. within one year. Further criteria may apply with respect to shadow flickering, e.g. the restriction of the operation hours may only be ap plicable during day time or in case that the sun is shining. The condition that the sun is shining can be determined based on corresponding sensors positioned at the location of the wind farm.

Another curtailment may refer to the operation of the wind farm during possible icing conditions, e.g. in order to limit ice throw caused by the rotation of the rotor blades of the wind turbines. In this case, a curtailment with respect to a maximum rotation speed of the rotor blades of the wind tur bines may be given during winter or during periods with low temperatures in case that humans are expected in the sur rounding area of the wind farm, e.g. in case that a street is located near the wind farm.

In the embodiment described herein, a wind farm already in operation is analyzed based on satellite images in order to get information about changes in the surrounding area of the wind farm. Those changes may allow an adaptation of the oper ation of the wind farm resulting in higher electric energy production whilst a given curtailment is still complied with.

The method according to Fig. 1 has access to digital satel lite images IM provided from the earth's ground in the sur- rounding area of the wind farm. An example of a satellite im age is shown schematically in Fig. 1. The digital image com prises the wind farm 1 in the form of several wind turbines 2 which are shown schematically as horizontal bars. Further more, the image includes an object 3 of a given object type OT . In the image shown in Fig. 1, this object type is a resi dential building, i.e. the object 3 is a building in which humans live. The object 3 is only shown schematically as a hatched square.

The satellite images IM are taken from a central database which may be a database publicly available. Furthermore, the method of the invention has access to a curtailment CU in the form of digital data given by an authority in order to limit adverse effects resulting from the operation of the wind farm, e.g. the above described effects concerning sound, shadow flickering and ice throw. This curtailment will be processed in step S2 of Fig. 1 which will be described fur ther below.

According to the method of Fig. 1, steps SI and S2 are per formed in case that an updated satellite image IM is availa ble in order to check whether the operation of the wind farm can be adapted. E.g., in case that objects in the surrounding area of the wind farm have changed or have disappeared, cer tain aspects of the curtailment may no longer be relevant al lowing a higher energy production of the wind farm. Particu larly, it may happen that the residential building 3 shown in the image IM disappears at a later time point so that a cur tailment with respect to sound and shadow flickering is no longer relevant resulting in the possibility to operate the wind farm with higher energy output.

In the method of Fig. 1, the image IM is subjected to a well-known object detecting algorithm EDA in step SI. This object detection algorithm extracts objects of certain object types from the image together with the locations of these objects within the image. In a preferred embodiment, object types in the form of buildings, traffic routes, ground inclinations and trees are extracted where the object types may be re fined. E.g., it can be extracted if a residential or non-residential building is located adjacent to the wind farm, which kind of traffic route (walkway, main road, secondary road, highway and the like) is located in the surrounding ar ea of the wind farm or which trees are growing in the neigh borhood of the wind farm. Moreover, in a particularly pre ferred embodiment, additional properties of the objects de tected in the image IM are derived, particularly the height of the objects. Based on the image IM, the object 3 having the object type "residential building" is detected in step SI .

In the embodiment described herein, a well-known algorithm based on a Convolutional Neural Network CNN is used for de tecting objects within the image. The Convolutional Neural Network is trained based on training images having known ob jects of known object types shown therein. As known from the prior art, a Convolutional Neural Network comprises convolu tional layers followed by pooling layers as well as fully connected layers in order to extract and classify the objects within an image.

After having performed step SI, the information about the de tected objects is used in order to determine one or more op eration constraints OC of the wind farm taking into account the above mentioned curtailment CU provided as digital data in step S2.

The operation constraints OC for the wind farm are defined such that the wind farm generates maximum electric energy within a predetermined time interval on condition that the curtailment CU is complied with. In the embodiment described herein, the maximum electric energy refers to the maximum an nual energy production AEP.

The result of the method of Fig. 1, namely the operation con straints OC and the maximum annual energy production AEP are provided via a user interface to the operator of the wind farm. It may happen that due to environmental changes detect ed in an updated satellite image, e.g. due to the demolition of residential buildings or changes of use (from residential to industrial), the original operation constraints OC result ing from the curtailment CU have been changed allowing a much higher annual energy production AEP. This information may be used by the operator in order to contact the corresponding authority having issued the curtailment CU in order to get a permission for an adapted operation resulting in a much high er annual energy production.

The derivation of operation constraints OC based on step S2 of Fig. 1 is well-known to a skilled person and, thus, will not be described in detail. Particularly, the location of residential buildings may be used in order to determine the sound pressure level occurring at the respective building due to the operation of the wind farm. To do so, a sound propaga tion model is provided from which sound pressure levels at different locations can be derived. Such a sound propagation model may also use additional information from detected ob jects, e.g. height information of buildings or of ground in clinations. Furthermore, information of trees may be used for determining operation constraints. E.g., it can be detected that a tree or a forest (several trees) is located between the wind farm and a residential building, thus resulting in less or no shadow flickering which leads to relaxed operation constraints .

Fig. 2 shows an embodiment of a system in order to perform the method as described with respect to Fig. 1. The system is implemented as a platform based on a central server SE com prising a processor PR which is used in order to perform the above described method steps SI and S2. To do so, the server SE has access to up-to-date satellite images IM as well as to the curtailment CU where the server preferably can process the data of a plurality of different wind farms. After having performed the method of Fig. 1, the corresponding operation constraints OC and the corresponding maximum annual energy production AEP is provided via user interface UI to an opera-tor of the respective wind farm. The operator can then try to get permission to a changed operation regime from an authori ty in case that the maximum annual energy production is pre dicted to increase due to changes in the surroundings of the wind farm which have been detected in an updated satellite image.

The invention as described in the foregoing has several ad vantages. Particularly, the conditions with respect to the operation of a wind farm can be checked regularly based on updated images of the wind farm. In one embodiment, those im ages are satellite images. Nevertheless, the images may also refer to images taken by other flying objects (plane or drone) or by a camera installed on ground at the location of the wind farm. As a result of the invention, a higher energy output of a wind farm may be achieved in case that objects relevant for a predetermined curtailment are no longer pre sent or have been changed. Furthermore, it is also possible to perform the method of the invention in case that a cur tailment given by an authority has been changed (particularly relaxed) in order to evaluate if the wind farm can be operat ed with higher energy output.