Risk assessment method for wind turbine generator of offshore wind plant

Abstract

The invention discloses a risk assessment method for a wind turbine generator of an offshore wind plant, and is applied to the technical field of offshore wind power. The method includes: acquiring current sea area position information of an offshore wind plant according to a positioning system; acquiring offshore data of the current sea area of the offshore wind plant based on a satellite remote sensing technology; according to the offshore data, analyzing operation characteristics of the offshore wind power plant wind turbine generator in the current sea area to obtain offshore wind turbine generator operation data and fan vibration data of the current sea area; determining an anti-storm control strategy of the wind turbine generator of the offshore wind plant; analyzing the anti-storm control countermeasures and the storm parameters by using a deep learning model to obtain operation risk data of the wind turbine generator of the offshore wind plant; constructing a security risk assessment model; and performing security assessment on the operation risk data to obtain a security assessment level. The risk of the offshore wind power plant is accurately evaluated, the operation safety of the offshore wind power plant under the storm weather condition is reasonably evaluated, and safe operation monitoring of the offshore wind power plant is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of offshore wind power, and more particularly to a risk assessment method for wind turbines in an offshore wind farm. Background Art

[0002] Risk assessment refers to the work of quantitatively evaluating the impact and possibility of loss caused by a risk event on people's lives, lives, property, etc. before or after the risk event occurs. In other words, risk assessment is to quantitatively evaluate the possible degree of impact or loss caused by an event or thing.

[0003] Risk assessment is used to measure the possibility and magnitude of losses caused by or to a system. It is done by estimating the probability of factors that lead to dangerous events, thereby quantifying the health, safety, economic and other impacts of each dangerous event. Although risk assessment methods vary greatly for different engineering fields. In general, risk assessment methods can be divided into static assessment and dynamic assessment. However, no matter which assessment method is used, in engineering evaluation, domestic and foreign scholars have the same definition of risk, that is, risk has the duality of probability and consequence.

[0004] Offshore wind farms are built in coastal areas and face complex and harsh marine meteorological environments. Under extreme conditions, they also need to face the invasion of storms and severe weather. Therefore, in order to ensure the safe operation of offshore wind farms, it is necessary to conduct safety risk monitoring of offshore wind farms.

[0005] Therefore, it is an urgent problem for those skilled in the art to propose a risk assessment method for wind turbines in offshore wind farms to solve the difficulties existing in the prior art. Summary of the invention

[0006] In view of this, the present invention provides a risk assessment method for wind turbines in an offshore wind farm, which is used to solve the technical problems existing in the prior art.

[0007] In order to achieve the above object, the present invention provides the following technical solutions:

[0008] A risk assessment method for wind turbines in an offshore wind farm comprises the following steps:

[0009] Obtain the current sea area location information of the offshore wind farm based on the GPS positioning system;

[0010] According to the current sea area location information of the offshore wind farm, the offshore data of the current sea area of ​​the offshore wind farm is obtained based on satellite remote sensing technology;

[0011] According to the offshore data, the operating characteristics of the wind turbines in the offshore wind farm in the current sea area are analyzed to obtain the operating data and vibration data of the offshore wind turbines in the current sea area;

[0012] Determine the storm control countermeasures for offshore wind farm wind turbines based on the obtained offshore wind turbine operation data and wind turbine vibration data;

[0013] Using deep learning models, we analyze storm control strategies and storm parameters to obtain operational risk data for wind turbines in offshore wind farms in the current sea area.

[0014] Construct a security risk assessment model;

[0015] Conduct safety assessment on operational risk data based on the constructed safety risk assessment model and obtain the safety assessment level in real time.

[0016] In the above method, optionally, the marine data includes: meteorological data, wave data, current data, and marine environmental parameters.

[0017] The above method can optionally analyze the operating characteristics of wind turbines in the offshore wind farm in the current sea area based on offshore data. The specific contents are as follows:

[0018] Clean and fuse the marine data to obtain the cleaned and fused target data set;

[0019] Based on the preset clustering model, cluster analysis is performed on the target data set to obtain cluster analysis results;

[0020] According to the cluster analysis results, the operating characteristics of wind turbines in offshore wind farms in the current sea area are obtained.

[0021] The above method can be optionally performed by cleaning and fusion as follows: digitizing and standardizing the offshore data, and then performing dimensionality reduction.

[0022] The above method optionally uses a deep learning model to analyze the storm control countermeasures and storm parameters, and obtains the specific content of the operation risk data of the offshore wind farm wind turbine in the current sea area:

[0023] The anti-storm control strategy and storm parameters are input into the deep learning model, and the probability of wind turbines in offshore wind farms being detached under storm weather conditions is predicted according to time, thereby obtaining the operating risk data of wind turbines in offshore wind farms in the current sea area.

[0024] The above method is optional, and the specific content of building a security risk assessment model is as follows:

[0025] Training samples are selected from the operational risk data of wind turbines in offshore wind farms in the current sea area as input, and the safety risk level is used as output. The machine learning model is used for training, and a safety risk assessment model is constructed after training.

[0026] The above method optionally performs a safety assessment on the operation risk data according to the constructed safety risk assessment model, and obtains the specific content of the safety assessment level in real time as follows:

[0027] Obtain the expected threshold of the preset operation risk data, analyze and calculate the operation risk data through the safety risk assessment model, compare it with the preset expected threshold, and output the corresponding safety assessment level.

[0028] It can be seen from the above technical solutions that, compared with the prior art, the present invention discloses a risk assessment method for wind turbines in an offshore wind farm, which has the following beneficial effects:

[0029] 1) Based on offshore data, the operating characteristics of wind turbines in offshore wind farms in the current sea area can be analyzed to identify the key factors causing the operating risks of wind turbines in offshore wind farms;

[0030] 2) Determine the storm control countermeasures of the wind turbines in the offshore wind farm based on the obtained offshore wind turbine operation data and wind turbine vibration data, so as to consider the ability of the storm control countermeasures in the current area to cope with storm weather;

[0031] 3) Use deep learning models to comprehensively and accurately assess the risks of offshore wind farms, reasonably and effectively assess the operational safety of offshore wind power under storm weather conditions, and realize safe operation monitoring of offshore wind farms. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0033] Figure 1 A flow chart of a risk assessment method for wind turbines in an offshore wind farm provided by the present invention. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] See also Figure 1 As shown, the present invention discloses a risk assessment method for wind turbines in an offshore wind farm, comprising the following steps:

[0036] Obtain the current sea area location information of the offshore wind farm based on the GPS positioning system;

[0037] According to the current sea area location information of the offshore wind farm, the marine data of the current sea area of ​​the offshore wind farm is obtained based on satellite remote sensing technology;

[0038] According to the offshore data, the operating characteristics of the wind turbines in the offshore wind farm in the current sea area are analyzed to obtain the operating data and vibration data of the offshore wind turbines in the current sea area;

[0039] Determine the storm control countermeasures for offshore wind farm wind turbines based on the obtained offshore wind turbine operation data and wind turbine vibration data;

[0040] Using deep learning models, we analyze storm control strategies and storm parameters to obtain operational risk data for wind turbines in offshore wind farms in the current sea area.

[0041] Construct a security risk assessment model;

[0042] Conduct safety assessment on operational risk data based on the constructed safety risk assessment model and obtain the safety assessment level in real time.

[0043] Furthermore, the marine data includes: meteorological data, wave data, current data, and marine environmental parameters.

[0044] Specifically, meteorological data include wind speed, wind direction, rainfall, temperature, and humidity; wave data include wave height, wavelength, wave direction, wave period, and wave frequency data of wind waves, swell waves, and composite waves; and ocean current data include flow velocity and direction data of water level, astronomical tide level, wind current, tidal current, and composite flow.

[0045] Furthermore, based on offshore data, the operating characteristics of wind turbines in offshore wind farms in the current sea area are analyzed as follows:

[0046] Clean and fuse the marine data to obtain the cleaned and fused target data set;

[0047] Based on the preset clustering model, cluster analysis is performed on the target data set to obtain cluster analysis results;

[0048] According to the cluster analysis results, the operating characteristics of wind turbines in offshore wind farms in the current sea area are obtained.

[0049] Furthermore, the cleaning and fusion are as follows: the offshore data are digitized and standardized, and then the dimension reduction is performed.

[0050] Specifically, digitization: Since raw data often exists in various formats, for example, the data to be processed is numeric, but the raw data may be character or other, it needs to be standardized. To get the value of a string, you can sum the ANSI code value to get the value of the string. If the value is too large, you can take an appropriate prime number to modulo it, which is essentially mapping it to an interval to get the numeric data.

[0051] Standardization: Since the values ​​of the various dimensions of the original data often vary greatly, for example, the minimum value of one dimension is 0.01, while the minimum value of another dimension is 1000, then when calculating the correlation or variance index during data analysis, the latter may overshadow the effect of the former. Therefore, it is necessary to normalize the overall data, that is, map them all to a specified numerical range, so that it will not have a significant impact on subsequent data analysis. One approach that has been adopted is min-max standardization.

[0052] Dimensionality reduction: Since raw data often contains many dimensions, these dimensions are often not independent, that is, there may be correlations between some of the dimensions, so data correlation analysis can be used to reduce the data dimension. PCA (Principal Component Analysis) is a commonly used dimensionality reduction method that converts a set of variables that may be correlated into a set of linearly unrelated variables through orthogonal transformation. The converted set of variables is called principal components.

[0053] Furthermore, by using the deep learning model, we analyzed the storm control countermeasures and storm parameters, and obtained the specific contents of the operational risk data of wind turbines in offshore wind farms in the current sea area:

[0054] The anti-storm control strategy and storm parameters are input into the deep learning model, and the probability of wind turbines in offshore wind farms being detached under storm weather conditions is predicted according to time, thereby obtaining the operating risk data of wind turbines in offshore wind farms in the current sea area.

[0055] Specifically, storm parameters include storm intensity parameters, storm radius parameters, storm moving speed parameters and storm path parameters.

[0056] Specifically, the risk of offshore wind turbine shutdown refers to the wind farm being disconnected from the grid for some reason or the wind turbines in the wind farm suddenly stopping operation when in power generation mode. If the grid voltage is too high or too low, the frequency is too high or the harmonics are too large, all wind turbines in the wind farm will shut down.

[0057] Furthermore, the specific contents of building a security risk assessment model are as follows:

[0058] Training samples are selected from the operational risk data of wind turbines in offshore wind farms in the current sea area as input, and the safety risk level is used as output. The machine learning model is used for training, and a safety risk assessment model is constructed after training.

[0059] Furthermore, the operational risk data is subjected to safety assessment according to the constructed safety risk assessment model, and the specific contents of the safety assessment level obtained in real time are as follows:

[0060] Obtain the expected threshold of the preset operation risk data, analyze and calculate the operation risk data through the safety risk assessment model, compare it with the preset expected threshold, and output the corresponding safety assessment level.

[0061] Specifically, training samples are selected from the operating risk data of wind turbines in offshore wind farms in the current sea area as input, and the safety risk level is used as output. The machine learning model is used for training to establish a safety risk assessment model. The operating risk data is sent to the safety risk assessment model for analysis and calculation, and then compared with the expected threshold to obtain the safety assessment level of the offshore wind farm. The safety level includes four levels: safe, low risk, medium risk and high risk. The full score is 100. The higher the score, the more dangerous it is. 0-25 is safe, 26-50 is low risk, 50-75 is medium risk and 76-100 is high risk.

[0062] In short, offshore wind farms have greater risks when facing storms. Therefore, safety assessment of storm risks of offshore wind farms is the key to ensuring the safe operation of offshore wind power. Through the technical solution implemented by the present invention, the wind resistance of offshore wind power in storm environments can be further improved, reducing the impact of storm weather.

[0063] Specifically, the present invention also provides a terminal device, which includes a processor and a memory, the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in a computer storage medium. The processor may be a central processing unit, or other general-purpose processors, digital signal processors, application-specific integrated circuits, off-the-shelf programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, loading and executing one or more instructions to implement the above method flow.

[0064] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0065] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A risk assessment method for wind turbines in an offshore wind farm, characterized in that: The following steps are involved: Obtain the current sea area location information of the offshore wind farm based on the GPS positioning system; According to the current sea area location information of the offshore wind farm, the marine data of the current sea area of ​​the offshore wind farm is obtained based on satellite remote sensing technology; According to the offshore data, the operating characteristics of the wind turbines in the offshore wind farm in the current sea area are analyzed to obtain the operating data and vibration data of the offshore wind turbines in the current sea area; Determine the storm control countermeasures for offshore wind farm wind turbines based on the obtained offshore wind turbine operation data and wind turbine vibration data; Using deep learning models, we analyze storm control strategies and storm parameters to obtain operational risk data for wind turbines in offshore wind farms in the current sea area. Construct a security risk assessment model; Conduct safety assessment on operational risk data based on the constructed safety risk assessment model and obtain the safety assessment level in real time.

2. A risk assessment method for wind turbines in an offshore wind farm according to claim 1, characterized in that: Marine data include: meteorological data, wave data, current data, and marine environmental parameters.

3. A risk assessment method for wind turbines in an offshore wind farm according to claim 1, characterized in that: According to the offshore data, the specific contents of the analysis of the operating characteristics of wind turbines in offshore wind farms in the current sea area are as follows: Clean and fuse the marine data to obtain the cleaned and fused target data set; Based on the preset clustering model, cluster analysis is performed on the target data set to obtain cluster analysis results; According to the cluster analysis results, the operating characteristics of wind turbines in offshore wind farms in the current sea area are obtained.

4. A risk assessment method for wind turbines in an offshore wind farm according to claim 3, characterized in that: The specific steps of cleaning and fusion are: digitizing and standardizing the offshore data, and then performing dimensionality reduction.

5. The risk assessment method for wind turbines in an offshore wind farm according to claim 1, characterized in that: By using the deep learning model, we analyzed the storm control countermeasures and storm parameters, and obtained the specific contents of the operational risk data of wind turbines in offshore wind farms in the current sea area: The anti-storm control strategy and storm parameters are input into the deep learning model, and the probability of wind turbines in offshore wind farms being detached under storm weather conditions is predicted according to time, thereby obtaining the operating risk data of wind turbines in offshore wind farms in the current sea area.

6. A risk assessment method for wind turbines in an offshore wind farm according to claim 1, characterized in that: The specific contents of building a security risk assessment model are: Training samples are selected from the operational risk data of wind turbines in offshore wind farms in the current sea area as input, and the safety risk level is used as output. The machine learning model is used for training, and a safety risk assessment model is constructed after training.

7. A risk assessment method for wind turbines in an offshore wind farm according to claim 1, characterized in that: According to the constructed safety risk assessment model, the operation risk data is evaluated in safety, and the specific contents of the safety assessment level obtained in real time are as follows: Obtain the expected threshold of the preset operation risk data, analyze and calculate the operation risk data through the safety risk assessment model, compare it with the preset expected threshold, and output the corresponding safety assessment level.

Images