CN114254848A - Method and device for predicting installation period of wind generating set - Google Patents

Abstract

The present disclosure provides a method and equipment for predicting the installation construction period of a wind turbine. The installation duration prediction method includes: obtaining environmental data at the location of the wind turbine generator set within a preset time in the future and identification information of the next step to be performed, wherein the environmental data includes factors affecting the installation of the wind turbine generator set. The parameter value of the environmental parameter; the obtained environmental data and the identification information of the process are input into the trained installation duration prediction model, so as to obtain the identification information of at least one process that can be executed within the preset future duration predicted by the installation duration prediction model and its identification information. execution time period.

Description

Installation period forecasting method and equipment for wind turbines

technical field

The present disclosure generally relates to the technical field of wind power, and more particularly, to a method and equipment for predicting the installation period of a wind turbine.

Background technique

The offshore wind power technology has just started, the transportation and hoisting experience of offshore wind power projects is limited, the theoretical accumulation is shallow, and there is a lack of mature theoretical system and perfect system specifications. Offshore wind power is a typical industry with an industry followed by theory. Today, with the booming development of offshore wind power, it is an inevitable requirement for the leap-forward development of offshore wind power to summarize the theory in combination with practice, and to apply the theory to practice and to be tested by practice.

The hoisting of offshore wind turbines is one of the most important links in offshore wind power construction projects. At present, although the hoisting of offshore wind turbines has formed a standardized and standardized installation process and technological requirements, due to the fickle offshore environment, offshore installation faces uncertainty. much larger than land. It is difficult for hoisting technicians to scientifically evaluate the future hoisting construction period, which greatly affects the effective arrangement of the hoisting construction period of offshore wind turbines.

Therefore, how to accurately estimate the installation period of wind turbines to reduce the uncertainty of future installation period is particularly important.

SUMMARY OF THE INVENTION

Exemplary embodiments of the present disclosure provide a method and device for predicting the installation duration of a wind turbine, which can quickly and accurately predict the future installation duration of the wind turbine.

According to an exemplary embodiment of the present disclosure, a method for predicting the installation duration of a wind turbine is provided, the method for predicting the installation duration includes: acquiring environmental data at the location of the wind turbine within a preset time in the future and the next step The identification information of the process to be executed, wherein the environmental data includes parameter values of environmental parameters affecting the installation of the wind turbine; input the acquired environmental data and the identification information of the process into the trained installation duration prediction model to obtain the installation Identification information of at least one process that can be executed within a preset time period in the future predicted by the duration prediction model and its execution time period.

Optionally, the installation duration prediction method further includes: training the installation duration prediction model based on the environmental data and the duration arrangement data at the location points of the wind turbines in multiple historical periods, as well as the process execution conditions, wherein , the length of each historical period is the preset time length, wherein the construction period arrangement data of each historical period includes: the identification information of the process executed in the historical period and the execution time period thereof, wherein the process execution conditions include: Restrictions to which environmental data is required to be carried out for each procedure used to install wind turbines.

Optionally, the process execution conditions further include: the continuous duration and extent of acceptable environmental data exceeding the limit conditions during the execution of each process, and the number of time periods during which the acceptable environmental data exceeds the limit conditions.

Optionally, when any process includes multiple work steps, the restriction conditions that the environmental data is required to meet when the process is executed include: the restriction conditions that the environmental data is required to meet when each process step of the process is executed; The continuous duration and extent of the acceptable environmental data exceeding the limit conditions during the execution of the process, and the number of time periods during which the acceptable environmental data exceeds the limit conditions include: the acceptable environment during the execution of each step of the process The continuous duration and extent of data violations, and the number of time periods during which the acceptable environmental data exceeded the constraints.

Optionally, the installation duration prediction model is an adaptive neuro-fuzzy system ANFIS model, and the learning algorithm of the installation duration prediction model is a combination of a back-propagation algorithm and a least squares method.

Optionally, based on the environmental data and construction period arrangement data at the site points of the wind turbines in multiple historical periods, and the process execution conditions, the step of training the installation construction period prediction model includes: The environmental data at the site, the identification information of the process performed first in each historical period, and the process execution conditions are used as the input of the installation duration prediction model, and the identification information of the process executed in each historical period is used. and its execution time period is used as the output of the installation duration prediction model, and a learning algorithm combining the back-propagation algorithm and the least squares method is used to train to obtain the parameters of the installation duration prediction model.

According to another exemplary embodiment of the present disclosure, there is provided an installation duration prediction device for a wind turbine, the installation duration prediction device comprising: a data acquisition unit for acquiring the location of the wind turbine within a preset time period in the future The environmental data and the identification information of the process that needs to be executed in the next step, wherein, the environmental data includes the parameter value of the environmental parameters affecting the installation of the wind turbine; the prediction unit inputs the acquired environmental data and the identification information of the process into the training The installation duration prediction model is used to obtain identification information of at least one process that can be executed within a preset future duration predicted by the installation duration prediction model and its execution time period.

Optionally, the installation duration prediction device further includes: a training unit for training the installation duration prediction based on the environmental data and duration arrangement data at the location points of the wind turbines in multiple historical periods, as well as process execution conditions. model, wherein the length of each historical period is the preset duration, wherein the construction period arrangement data of each historical period includes: the identification information of the process executed in the historical period and the execution time period thereof, wherein the process The execution conditions include the constraints that environmental data is required to meet when each process for installing the wind turbine is executed.

Optionally, the process execution conditions further include: the continuous duration and extent of acceptable environmental data exceeding the limit conditions during the execution of each process, and the number of time periods during which the acceptable environmental data exceeds the limit conditions.

Optionally, when any process includes multiple work steps, the restriction conditions that the environmental data is required to meet when the process is executed include: the restriction conditions that the environmental data is required to meet when each process step of the process is executed; The continuous duration and extent of the acceptable environmental data exceeding the limit conditions during the execution of the process, and the number of time periods during which the acceptable environmental data exceeds the limit conditions include: the acceptable environment during the execution of each step of the process The continuous duration and extent of data violations, and the number of time periods during which the acceptable environmental data exceeded the constraints.

Optionally, the installation duration prediction model is an adaptive neuro-fuzzy system ANFIS model, and the learning algorithm of the installation duration prediction model is a combination of a back-propagation algorithm and a least squares method.

Optionally, the training unit uses the environmental data at the machine location in each historical period, the identification information of the process performed first in each historical period, and the process execution condition as the input of the installation duration prediction model, and The identification information of the process performed in each historical period and its execution time period are used as the output of the installation duration prediction model, and a learning algorithm combining a back-propagation algorithm and a least squares method is used to train to obtain the installation duration. Predict the parameters of the model.

According to another exemplary embodiment of the present disclosure, a computer-readable storage medium storing a computer program is provided, characterized in that, when the computer program is executed by a processor, the installation schedule of the wind turbine as described above is realized method of prediction.

According to another exemplary embodiment of the present disclosure, there is provided a computing device, the computing device comprising: a processor; a memory storing a computer program, when the computer program is executed by the processor, the wind power as described above is implemented Prediction method of generator set installation period.

According to the method and device for predicting the installation duration of the wind turbines according to the exemplary embodiments of the present disclosure, the future installation duration of the wind turbines can be quickly and accurately estimated to reduce the uncertainty of the future installation duration, thereby facilitating reasonable arrangements for future installations. An installation plan to ensure that the installation can be completed on schedule.

Additional aspects and/or advantages of the present disclosure will be set forth in part in the description that follows, and in part will be apparent from the description, or may be learned by practice of the present disclosure.

Description of drawings

The above and other objects and features of exemplary embodiments of the present disclosure will become more apparent from the following description taken in conjunction with the accompanying drawings that exemplarily illustrate the embodiments, wherein:

FIG. 1 shows a flowchart of a method for predicting the installation duration of a wind turbine according to an exemplary embodiment of the present disclosure;

FIG. 2 shows a structural block diagram of an installation schedule prediction device for a wind turbine according to an exemplary embodiment of the present disclosure.

Detailed ways

Reference will now be made in detail to the embodiments of the present disclosure, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to like parts throughout. The embodiments are described below in order to explain the present disclosure by referring to the figures.

FIG. 1 shows a flowchart of a method for predicting the installation schedule of a wind turbine according to an exemplary embodiment of the present disclosure.

Referring to FIG. 1 , in step S10 , the environmental data at the location of the wind power generating set within a preset time period in the future and the identification information of the process to be performed in the next step are acquired.

Here, the environmental data includes parameter values affecting environmental parameters of the wind turbine installation. For example, the environmental parameters affecting the installation of the wind turbine may include environmental parameters that cannot be installed normally when the parameter value exceeds a certain threshold for a long time.

As an example, environmental data may include: meteorological data. Accordingly, for example, the meteorological data may include parameter values for at least one of the following meteorological parameters: wind speed, wave height, rainfall, thunderstorms. It should be understood that the meteorological data may also include parameter values of other types of meteorological parameters, which are not limited in the present disclosure.

As an example, when the method for predicting the installation duration of a wind turbine according to an exemplary embodiment of the present disclosure is applied to predict the hoisting duration of an offshore wind turbine, the environmental data may include: meteorological data and hydrological data. For example, the hydrological data may include parameter values for at least one of the following hydrological parameters: swell, tide. It should be understood that the hydrological data may also include parameter values of other types of hydrological parameters, which are not limited in the present disclosure.

As an example, the stand point may be the latitude and longitude coordinates of the installation location of the wind turbine.

In step S20, the acquired environmental data and the identification information of the process are input into the trained installation duration prediction model to obtain the identification information and execution time of at least one process that can be executed in the future preset duration predicted by the installation duration prediction model part.

It should be understood that the method for predicting the installation duration of a wind turbine according to an exemplary embodiment of the present disclosure may be executed after one process is completed, so as to predict the next process ( That is, the next process that needs to be executed) starts to be able to execute at least one subsequent process and a time period (ie, execution time period) during which each process can be executed.

The method for predicting the installation duration of a wind turbine according to an exemplary embodiment of the present disclosure may further include: based on the environmental data and duration arrangement data (hereinafter, also referred to as historical installations) at the site points of the wind turbine in a plurality of historical periods data), and process execution conditions, to train the installation duration prediction model, wherein the length of each historical period is the preset duration.

Here, the construction period arrangement data of each historical period includes: identification information of the process executed in the historical period and its execution time period.

Here, the process execution conditions include constraints that environmental data is required to meet when each process for installing the wind turbine is executed. In addition, as an example, the process execution conditions may further include: the continuous duration and extent of acceptable environmental data exceeding the limit conditions during the execution of each process, and the number of time periods during which the acceptable environmental data exceeds the limit conditions. That is to say, the situation that each process can occasionally exceed its corresponding limit condition for a certain period of time and the number of times that this situation is allowed to occur is also given.

It should be understood that the execution conditions of different processes may be the same or different.

As an example, the process execution conditions may be obtained based on actual installation experience data in the field.

As an example, when any process includes multiple work steps, the constraints that the environmental data must meet when the process is executed may include: the constraints that the environmental data must meet when each process step of the process is executed; each process The continuous duration and extent of the acceptable environmental data exceeding the limit conditions during the execution of the process, and the number of time periods during which the acceptable environmental data exceeds the limit conditions may include: acceptable during the execution of each step of the process Continued duration and extent of environmental data violations, and the number of acceptable time periods in which environmental data exceeded constraints.

In fact, the trained installation duration prediction model has learned the execution sequence of all processes, the working hours of each process, and the process execution conditions based on historical installation data; in addition, if any process includes multiple steps, the trained installation duration Based on the historical installation data, the prediction model will also learn: the execution sequence of multiple work steps included in the process, the working hours of each work step, and the execution conditions of each work step; When the continuous execution is completed, the trained installation duration prediction model will also learn that the process must be executed continuously based on the historical installation data (for example, if a process includes multiple work steps, these multiple work steps must be executed continuously, It is not possible to execute the next step of the step after a period of time after the execution of a step), so that the obtained environmental data and the identification information of the process are input into the trained installation period prediction model, which can predict the next step in the next step. Within the preset time period of , the subsequent at least one process that can be executed from the process that needs to be executed next and the time period during which the at least one process can be executed.

Table 1 Hoisting data of offshore wind turbines

Table 1 shows the hoisting process of offshore wind turbines and the execution sequence of the process, the man-hours of each process, and the required environmental data (only wind speed and wave height are exemplified here) when each process is executed. Take the process of reverse transportation of the tower and installation of the tower at the top section as an example. This process includes two steps of “reverse transportation of the tower” and “installation of the tower at the top section”. The total working time of this process is 5.5 hours. The man-hours for the “reverse transport of the tower” is 1 hour, the working time of the step “tower installation at the top section” is 4.5 hours, and the wind speed is required to be less than 10 and the wave height is less than 1.25 when the step “tower reverse transport” is performed; The wind speed is required to be less than 10 and there is no requirement for wave height (that is, the "—" in Table 1 indicates no requirement), and the step "tower reverse transport" and the step "top tower installation" are required to be continuous. Execution, that is, to perform the completion step "Tower Reverse Transportation", the step "Top Section Tower Installation" needs to be performed immediately, that is, the first hour of the continuous 5.5 hours meets the execution conditions of the step "Tower Reverse Transportation", and the last 4.5 hours. Only when the execution conditions of the step "top tower installation" are met, the 5.5 hours can be used to perform the process of "tower reverse transportation and top tower installation".

In addition, the installation ship refers to the ship that performs the installation operation of the offshore wind turbine, and the transport ship refers to the ship that transports the components of the generator set from the wharf to the aircraft site.

It should be understood that the method for predicting the installation duration of a wind turbine according to the exemplary embodiment of the present disclosure can be applied to the prediction of the installation duration of the wind turbine under various installation modes, and it is only necessary to ensure that the installation duration prediction model is based on the corresponding installation mode. It can be obtained by training the historical installation data of wind turbines. As an example, the method for predicting the installation duration of a wind turbine according to an exemplary embodiment of the present disclosure can be used to predict the installation duration of an offshore wind turbine in a certain lifting mode. Accordingly, the installation duration prediction model is based on the installation duration in this lifting mode Training on historical installation data for hoisting offshore wind turbines. For example, the hoisting mode of the offshore wind turbine can be specifically classified into at least one of the following items: horizontal single-blade hoisting, obliquely inserted single-blade hoisting, split three-blade hoisting, and combined three-blade hoisting.

As an example, when training the installation duration prediction model, the environmental data at the aircraft site in each historical period, the identification information of the process performed first in each historical period, and the process execution conditions may be used as the installation duration The input of the prediction model is used as the output of the installation duration prediction model to train the installation duration prediction model by using the identification information of the process executed in each historical period and its execution time period as the output of the installation duration prediction model.

It should be understood that the environmental data and construction period arrangement data at the aircraft site in each historical period may be historical actual data or historical simulated data. For example, when historical simulation data is used, the historical simulation data can be corrected according to the actual field data.

As an example, the installation duration prediction model may be an adaptive neuro-fuzzy system ANFIS model, and the learning algorithm of the installation duration prediction model may be a combination of a back-propagation algorithm and a least squares method.

As an example, the installation duration prediction model may include the following five-layer structures: a fuzzy layer (the first layer), a product layer (the second layer), a normalization layer (the third layer), and a rule output layer (the fourth layer) ), and the output layer (the fifth layer).

Specifically, the fuzzy layer is used to calculate the membership degree of the fuzzy set according to the fuzzy membership function; the product layer is used to calculate the excitation intensity of each rule; the normalization layer is used to normalize the excitation intensity of each rule; The output layer is used to calculate the output of each rule according to the conclusion parameters; the output layer is used to calculate the total output.

As an example, the specific training process can be as follows: firstly, the acquired historical installation data is divided into a training data set and a test data set; the number, type, and initial value of the prerequisite parameters of the membership functions of each input variable in the first layer are determined. , and the initial values of the fourth-layer conclusion parameters; then, each parameter of the ANFIS model is trained based on the training data set and the test data set.

As an example, the nodes of the first and fourth layers are adaptive, and the nodes of the second and third layers are fixed.

As an example, the membership function of the ith node in the fuzzification layer can adopt a bell-shaped function, and its expression is as follows:

Among them, μ _i (x) represents the membership function of the ith node in the fuzzification layer; x represents the input of the ith node; {a _i , b _i , c _i } is the prerequisite parameter set of the membership function.

As an example, the fourth rule output layer can be used to calculate the contribution ratio O _4,i of the ith rule to the total output, which is expressed as follows:

表示第i条规则在第三层得到的归一化激励强度；x，y表示第i个节点的输入；{p_i，q_i，r_i}是所述第i个节点的结论参数。in,

represents the normalized excitation intensity obtained by the ith rule in the third layer; x, y represent the input of the _ith node; {pi, qi, ri _} are the conclusion parameters of the _ith node.

FIG. 2 shows a structural block diagram of an installation schedule prediction device for a wind turbine according to an exemplary embodiment of the present disclosure.

As shown in FIG. 2 , the installation schedule prediction apparatus for a wind turbine according to an exemplary embodiment of the present disclosure includes: a data acquisition unit 10 and a prediction unit 20 .

Specifically, the data acquisition unit 10 is configured to acquire environmental data at the location of the wind turbine within a preset time period in the future and identification information of the process to be performed in the next step, wherein the environmental data includes factors affecting the wind turbine. The parameter value of the installed environment parameter.

The prediction unit 20 is used to input the acquired environmental data and the identification information of the process into the trained installation duration prediction model, so as to obtain the identification information of at least one process that can be executed within the preset future duration predicted by the installation duration prediction model and its execution. period.

As an example, the installation schedule prediction apparatus for a wind turbine according to an exemplary embodiment of the present disclosure may further include: a training unit (not shown).

The training unit is used to train the installation duration prediction model based on the environmental data and construction period arrangement data at the site points of multiple historical periods of the wind turbine, and the process execution conditions, wherein the length of each historical period is The preset duration, wherein the construction period arrangement data of each historical period includes: identification information of the process executed in the historical period and the execution time period thereof, wherein the process execution condition includes each Constraints to which environmental data is required to be met when the process is executed.

As an example, the process execution conditions may further include: the continuous duration and extent of acceptable environmental data exceeding the limit conditions during the execution of each process, and the number of time periods during which the acceptable environmental data exceeds the limit conditions.

As an example, when any process includes multiple work steps, the constraints that the environmental data must meet when the process is executed may include: the constraints that the environmental data must meet when each process step of the process is executed; each process The continuous duration and extent of the acceptable environmental data exceeding the limit conditions during the execution of the process, and the number of time periods during which the acceptable environmental data exceeds the limit conditions may include: acceptable during the execution of each step of the process Continued duration and extent of environmental data violations, and the number of acceptable time periods in which environmental data exceeded constraints.

As an example, the installation duration prediction model may be an adaptive neuro-fuzzy system ANFIS model, and the learning algorithm of the installation duration prediction model may be a combination of a back-propagation algorithm and a least squares method.

As an example, the training unit may use the environmental data at the aircraft site in each historical period, the identification information of the process performed first in each historical period, and the process execution conditions as the input of the installation duration prediction model, and The identification information of the process performed in each historical period and its execution time period are used as the output of the installation duration prediction model, and a learning algorithm combining a back-propagation algorithm and a least squares method is used to train to obtain the installation duration. Predict the parameters of the model.

It should be understood that the specific processing performed by the installation schedule prediction device for the wind turbine according to the exemplary embodiment of the present disclosure has been described in detail with reference to FIG. 1 , and the relevant details will not be repeated here.

It should be understood that each unit in the installation schedule prediction apparatus for a wind turbine according to an exemplary embodiment of the present disclosure may be implemented as hardware components and/or software components. Those skilled in the art can implement each unit by using, for example, a Field Programmable Gate Array (FPGA) or an Application Specific Integrated Circuit (ASIC) according to the defined processing performed by each unit.

Exemplary embodiments of the present disclosure provide a computer-readable storage medium storing a computer program, which, when the computer program is executed by a processor, implements the method for predicting the installation schedule of a wind turbine according to the above-mentioned exemplary embodiments. The computer-readable storage medium is any data storage device that can store data read by a computer system. Examples of computer-readable storage media include read-only memory, random-access memory, optical disks, magnetic tapes, floppy disks, optical data storage devices, and carrier waves (such as data transmission over the Internet via wired or wireless transmission paths).

A computing device according to an exemplary embodiment of the present disclosure includes a processor (not shown) and a memory (not shown), wherein the memory stores a computer program that, when executed by the processor, realizes the above-mentioned The method for predicting the installation schedule of a wind turbine according to the exemplary embodiment.

While a few exemplary embodiments of the present disclosure have been shown and described, those skilled in the art will appreciate that these Examples are modified.

Claims (12)

1. The method for predicting the installation period of the wind generating set is characterized by comprising the following steps:

acquiring environmental data of a machine position of a wind generating set in a preset time length in the future and identification information of a next procedure to be executed, wherein the environmental data comprises parameter values of environmental parameters influencing the installation of the wind generating set;

and inputting the acquired environmental data and the identification information of the working procedures into the trained installation period prediction model to obtain the identification information and the execution time period of at least one working procedure which can be executed within the future preset time length predicted by the installation period prediction model.

2. The method for predicting the installation period according to claim 1, further comprising:

training the installation period prediction model based on environmental data and period arrangement data at machine sites of a plurality of historical periods of the wind generating set and process execution conditions, wherein the length of each historical period is the preset time length,

the construction period arrangement data of each historical period comprises: identification information of the processes performed within the history period and the execution time periods thereof,

the process execution conditions comprise limiting conditions which are required to be met by environmental data when each process for installing the wind generating set is executed.

3. The method for predicting the construction period of an installation according to claim 2, wherein the process execution conditions further include:

the continuous length and extent of exceeding of the limit condition by the acceptable environmental data during the execution of each process, and the number of time periods during which the acceptable environmental data exceeds the limit condition.

4. The method for predicting an installation period according to claim 3, wherein when any one process step includes a plurality of process steps,

the limiting conditions that the environmental data is required to meet when the process is executed comprise: each step of the process requires a limiting condition that the environmental data need to meet when being executed;

the continuous time length and the exceeding degree of the acceptable environmental data exceeding the limit condition in the execution process of each process and the number of the time period for which the acceptable environmental data exceeds the limit condition include: the continuous length and extent of the exceeding of the limit condition by the acceptable environmental data and the number of time periods during which the acceptable environmental data exceeds the limit condition during the execution of each step of the process.

5. The method of predicting construction period for installation according to claim 2, wherein the model for prediction of construction period for installation is an adaptive neural fuzzy system ANFIS model,

the learning algorithm of the installation period prediction model is an algorithm combining a back propagation algorithm and a least square method.

6. The installation period prediction method according to claim 5, wherein the step of training the installation period prediction model based on environmental data and period arrangement data at the machine site of a plurality of historical periods of the wind turbine generator system, and process execution conditions includes:

and training parameters of the installation period prediction model by using a learning algorithm combining a back propagation algorithm and a least square method, wherein the environment data at the machine position of each historical period, the identification information of the process executed firstly in each historical period and the process execution condition are used as the input of the installation period prediction model, the identification information of the process executed in each historical period and the execution time period thereof are used as the output of the installation period prediction model, and the parameters of the installation period prediction model are obtained.

7. An installation period prediction apparatus of a wind turbine generator system, characterized by comprising:

the data acquisition unit is used for acquiring environmental data of machine positions of the wind generating set in a preset time length in the future and identification information of a next procedure to be executed, wherein the environmental data comprise parameter values of environmental parameters influencing the installation of the wind generating set;

and the prediction unit is used for inputting the acquired environmental data and the identification information of the working procedures into the trained installation period prediction model so as to obtain the identification information of at least one working procedure which can be executed within the future preset time length predicted by the installation period prediction model and the execution time period of the working procedure.

8. The installation period prediction apparatus according to claim 7, characterized in that the installation period prediction apparatus further comprises:

a training unit for training the installation period prediction model based on environmental data and period arrangement data at a plurality of historical periods of the wind turbine generator system, and process execution conditions, wherein the length of each historical period is the preset time length,

the construction period arrangement data of each historical period comprises: identification information of the processes performed within the history period and the execution time periods thereof,

the process execution conditions comprise limiting conditions which are required to be met by environmental data when each process for installing the wind generating set is executed.

9. The installation period prediction apparatus according to claim 8, wherein the process execution condition further includes:

the continuous length and extent of exceeding of the limit condition by the acceptable environmental data during the execution of each process, and the number of time periods during which the acceptable environmental data exceeds the limit condition.

10. The installation period prediction apparatus according to claim 9, characterized in that the training unit trains parameters of the installation period prediction model using a learning algorithm combining a back propagation algorithm and a least square method, with environmental data at a machine site for each history period, identification information of a process executed first in each history period, and process execution conditions as inputs of the installation period prediction model, and identification information of a process executed in each history period and an execution time period thereof as outputs of the installation period prediction model.

11. A computer-readable storage medium storing a computer program, characterized in that the computer program, when executed by a processor, implements a method for predicting an installation period of a wind park according to any one of claims 1 to 6.

12. A computing device, the computing device comprising:

a processor;

a memory storing a computer program which, when executed by the processor, implements the method of predicting an installation period of a wind park according to any one of claims 1 to 6.

Images