A yaw control method and system based on meteorological data

Abstract

The present invention discloses a yaw control method and system based on meteorological data, including: acquiring first environmental data around a first object; predicting first characteristic data in the first environmental data according to the first environmental data; generating a first control target according to the first characteristic data; and using the first control target to generate a control instruction to control the first object. By combining meteorological data prediction and the dynamic response characteristics of the wind turbine, accurate yaw control instructions can be generated in real time, significantly improving the wind turbine's ability to capture the dominant wind direction and improving power generation efficiency. At the same time, the optimized control strategy effectively reduces the mechanical load and energy consumption of the yaw system and extends the service life of the equipment. Under extreme weather conditions, the present invention has higher stability and safety, avoids equipment wear caused by overly fast or over-frequency adjustments, and further improves the reliability and economic benefits of the wind power generation system.

Description

Technical Field

[0001] The present invention relates to the technical field of yaw control, and in particular to a yaw control method and system based on meteorological data. Background Art

[0002] With the rapid development of wind power generation technology, the accuracy and efficiency of yaw control of wind turbines have become key factors in improving power generation efficiency and extending equipment life. The core of yaw control is to adjust the orientation of the wind turbine nacelle so that it is always aligned with the dominant wind direction to maximize wind energy capture. However, due to the dynamic changes in wind direction and wind speed and the response limitations of the wind turbine mechanical system, traditional yaw control methods often have problems such as response lag, energy waste and error accumulation. In addition, too fast yaw adjustments under extreme weather conditions may cause equipment wear or safety hazards. The existing technology mostly adopts a simple control strategy based on wind speed and wind direction data, which fails to fully utilize the predictive ability of meteorological data and the dynamic response characteristics of the wind turbine. The present invention proposes a yaw control method based on meteorological data, which generates accurate control instructions by predicting the wind direction change trend and combining the actual yaw angle and dynamic response capability of the wind turbine, thereby significantly improving the accuracy and stability of yaw control. Summary of the Invention

[0003] In view of the above-mentioned problems, the present invention is proposed.

[0004] To solve the above technical problems, the present invention provides the following technical solution: a yaw control method based on meteorological data, comprising:

[0005] Acquiring first environmental data around a first object;

[0006] predicting first feature data in the first environmental data based on the first environmental data;

[0007] generating a first control target according to the first characteristic data;

[0008] Using the first control target, a control instruction is generated to control the first object.

[0009] As a preferred solution of the meteorological data-based yaw control method of the present invention, the first environmental data includes parameters of the first characteristic data that can be affected by the environment surrounding the first object.

[0010] As a preferred solution of the meteorological data-based yaw control method of the present invention, the first characteristic data includes parameters that affect the optimal working state of the first object when it is working.

[0011] As a preferred solution of the meteorological data-based yaw control method described in the present invention, the first control target includes the state of the first object itself being able to reach an optimal working state under the action of the first characteristic data.

[0012] As a preferred solution of the meteorological data-based yaw control method described in the present invention, the control instruction includes taking the first control target as the control target and adjusting the state of the first object itself to achieve an optimal working state.

[0013] As a preferred embodiment of the meteorological data-based yaw control method of the present invention, the predicting of the first characteristic data in the first environmental data includes preprocessing the collected meteorological data; determining the current prevailing wind direction and wind speed change trend based on the preprocessed meteorological data, and predicting future wind direction changes;

[0014] In order to improve the smoothness and robustness of the dominant wind direction, a weighted window filter w(i) and a nonlinear normalization function are introduced to determine the dominant wind direction;

[0015]

[0016] Among them, w(i)=e -σ|i-n / 2| , the weight of the control center data is high, σ>0 is the smoothing parameter;

[0017] Based on the sliding window linear regression, the second-order derivative and exponential smoothing are combined to achieve multi-scale fitting of wind speed trend:

[0018]

[0019] Among them, δ>0 is the second-order adjustment coefficient, γ>0 is the exponential smoothing coefficient;

[0020] Combining the prevailing wind direction and wind speed trends, a time series fusion model is constructed to achieve future wind direction prediction:

[0021]

[0022] Among them, the integral term is used to correct the cumulative prediction deviation; θ d is the prevailing wind direction angle; θ i is the wind direction angle at the i-th moment; v i is the wind speed at the i-th moment; Θ d is the improved dominant wind direction, t i is the time of moment i; t is the current time, and are the mean of time and wind speed respectively, w(i) is the weight function, γ is the exponential smoothing coefficient, is the autoregressive coefficient, ψ j is the moving average coefficient, ∈(tj) is the noise term, To predict future wind direction;

[0023] Θ d ∈[0,2π): represents the current dominant wind direction angle;

[0024] Indicates the changing trend of wind speed. A positive value indicates an increase in wind speed, while a negative value indicates a decrease in wind speed. Used to represent the set of real numbers;

[0025] The predicted future wind direction angle, periodically defined to conform to the physical properties of wind direction.

[0026] As a preferred embodiment of the meteorological data-based yaw control method of the present invention, the control instruction includes generating a control instruction based on the target wind direction and in combination with the current actual yaw angle and dynamic response capability of the wind turbine generator set;

[0027] Target yaw angle θ t is the wind direction that the wind turbine needs to be aligned with, the actual yaw angle θ a is the direction of the current unit, and the error between the two is defined as:

[0028] e(t)=θ t -θ a

[0029] To ensure periodicity, the error is adjusted to the interval [-π,π]:

[0030] e(t)=arctan2(sin(θ t -θ a ),cos(θ t -θ a )))

[0031] Assume that the dynamic response capability is affected by the maximum yaw speed v of the unit max and the influence of system inertia, expressed by a first-order lag model:

[0032]

[0033] Where β>0 is the response sensitivity, sgn(e(t)) is the sign function of the error, which is used to represent the yaw direction;

[0034] The control command is combined with the proportional integral controller (PI) model and the wind speed weight w is added v , adjust the response speed:

[0035] Among them, K pand K i are proportional and integral gains respectively;

[0036] Considering the dynamic response capability, the actual adjustment speed is:

[0037]

[0038] in, is the wind speed normalization weight, γ>0 is the dynamic suppression parameter;

[0039] The yaw control angle is adjusted to:

[0040] θ a (t+Δt)=θ a (t)+v c (t)·Δt

[0041] Among them, θ t is the target yaw angle, θ a is the actual yaw angle, e(t) is the current yaw error, v max is the maximum yaw velocity, β is the sensitivity of dynamic response, sgn(e(t)) is the error direction sign function, K p and K i is the proportional and integral gain, u(t) is the control instruction, w v is the wind speed normalization weight, v wind is the current wind speed, v rated is the rated wind speed, γ is the dynamic suppression parameter, Δt is the time step, v c (t) is the control speed.

[0042] A yaw control system based on meteorological data using any method according to the present invention, characterized in that:

[0043] A collection unit, which obtains first environmental data around a first object;

[0044] a prediction unit, configured to predict first feature data in the first environment data based on the first environment data;

[0045] an analyzing unit, generating a first control target according to the first characteristic data;

[0046] The control unit generates a control instruction using the first control target to control the first object.

[0047] A computer device comprises: a memory and a processor; the memory stores a computer program, wherein: when the processor executes the computer program, the steps of any one of the methods of the present invention are implemented.

[0048] A computer-readable storage medium stores a computer program, wherein: when the computer program is executed by a processor, the steps of any one of the methods of the present invention are implemented.

[0049] The beneficial effects of this invention are as follows: The meteorological data-based yaw control method provided by this invention, by combining meteorological data predictions with the dynamic response characteristics of the wind turbine, can generate precise yaw control commands in real time, significantly improving the wind turbine's ability to capture the prevailing wind direction and enhancing power generation efficiency. Furthermore, the optimized control strategy effectively reduces the mechanical load and energy consumption of the yaw system, extending the equipment's service life. In extreme weather conditions, this invention offers greater stability and safety, avoids equipment wear caused by overly rapid or over-frequency adjustments, and further enhances the reliability and economic benefits of the wind power generation system. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0051] Figure 1 This is an overall flow chart of a yaw control method based on meteorological data provided in the first embodiment of the present invention. DETAILED DESCRIPTION

[0052] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0053] Example 1, reference Figure 1 , as one embodiment of the present invention, provides a yaw control method based on meteorological data, comprising:

[0054] S1: Acquire first environmental data around a first object.

[0055] The first characteristic data includes parameters that affect the optimal working state of the first object during operation. Real-time meteorological data is obtained through meteorological monitoring equipment installed around the wind turbine generator set; including but not limited to the following data types:

[0056] Wind speed data: Wind speed is measured using an ultrasonic anemometer or a traditional mechanical anemometer, typically in a range of 0-25 m / s. Instantaneous wind speed, average wind speed, and gust intensity can be recorded as needed. Wind direction data: A wind direction sensor measures the current prevailing wind direction in degrees (0°-360°), enabling real-time monitoring of wind direction trends. Atmospheric pressure: A pressure sensor monitors ambient pressure changes in hectopascals (hPa) for analyzing atmospheric stability and wind field characteristics. Temperature data: A temperature sensor measures ambient temperature in degrees Celsius (°C) for assessing the impact of airflow conditions on wind turbine operation. Humidity data: A humidity sensor records air humidity in percentage (%) for predicting the potential impact of condensation or icing on equipment. Precipitation (optional): A rain gauge monitors precipitation intensity in millimeters (mm), providing additional support for severe weather warnings. Turbulence intensity (optional): Eddy covariance analysis measures wind field turbulence characteristics for assessing wind turbine load conditions and optimizing control strategies.

[0057] All of this data is collected in a distributed manner through a network of sensors installed at various locations around the wind turbine. This data is then transmitted to the control system via wireless or wired communication protocols to ensure real-time and accurate data. After synchronous processing, this data provides the foundation for yaw control.

[0058] S2: Predicting first feature data in the first environmental data based on the first environmental data.

[0059] The first characteristic data includes parameters that affect the optimal working state of the first object when it is working.

[0060] In this embodiment, predicting the first characteristic data in the first environmental data includes preprocessing the collected meteorological data, eliminating abnormal values, and performing smoothing.

[0061] Furthermore, the current dominant wind direction and wind speed change trend are determined, and future wind direction changes are predicted. To improve the smoothness and robustness of the dominant wind direction, a weighted window filter w(i) and a nonlinear normalization function are introduced to determine the dominant wind direction.

[0062]

[0063] Among them, w(i)=e -σ|i-n / 2| , the weight of the control center data is high, σ>0 is the smoothing parameter;

[0064] Based on the sliding window linear regression, the second-order derivative and exponential smoothing are combined to achieve multi-scale fitting of wind speed trend:

[0065]

[0066] Among them, δ>0 is the second-order adjustment coefficient, γ>0 is the exponential smoothing coefficient;

[0067] Combining the prevailing wind direction and wind speed trends, a time series fusion model is constructed to achieve future wind direction prediction:

[0068]

[0069] Among them, the integral term is used to correct the cumulative prediction deviation; θ d is the prevailing wind direction angle; θ i is the wind direction angle at the i-th moment; v i is the wind speed at the i-th moment; Θ d is the improved dominant wind direction, t i is the time of moment i; t is the current time, and are the mean of time and wind speed respectively, w(i) is the weight function, γ is the exponential smoothing coefficient, is the autoregressive coefficient, ψ j is the moving average coefficient, ∈(tj) is the noise term, To predict future wind direction;

[0070] Θ d ∈[0,2π): represents the current dominant wind direction angle;

[0071] Indicates the changing trend of wind speed. A positive value indicates an increase in wind speed, while a negative value indicates a decrease in wind speed. Used to represent the set of real numbers;

[0072] The predicted future wind direction angle, periodically defined to conform to the physical properties of wind direction.

[0073] The first characteristic data point is wind direction. The power generation efficiency of a wind turbine is highly dependent on the ability of the nacelle to align with the prevailing wind direction. Only when the turbine blades are perpendicular to the wind direction can the turbine capture maximum wind energy. Therefore, determining the prevailing wind direction in real time and using it as a basis for adjusting the yaw angle is key to ensuring efficient operation of the turbine. Wind speed is another important factor affecting power generation efficiency, but its effectiveness depends on whether the turbine can accurately align with the wind direction. If the turbine deviates from the wind direction, even at high wind speeds, the wind energy cannot be fully utilized. Therefore, wind direction data plays a decisive role in wind speed utilization. The goal of yaw control is to adjust the angle between the turbine and the wind direction, so wind direction data directly determines the core input of the control algorithm. By predicting wind direction trends, forward-looking information can be provided for yaw control, making the system more intelligent and efficient.

[0074] Wind direction data was selected as the first characteristic data because it plays a core role in the operation of wind turbines and has a direct impact on multiple key indicators such as power generation efficiency, system load and equipment life. At the same time, the data is easy to collect and process, providing a reliable foundation for subsequent yaw control.

[0075] It's important to note that while wind direction is an independent meteorological variable, it is influenced by other environmental parameters. Comprehensive analysis of these parameters allows for effective wind direction prediction. These parameters exhibit certain correlations, and by integrating environmental parameters such as wind speed, air pressure, temperature, turbulence intensity, and topography, and utilizing physical models and machine learning algorithms, accurate wind direction prediction can be achieved. This multi-parameter fusion prediction method offers greater accuracy and robustness, making it particularly well-suited for the dynamic environmental conditions found in wind power generation scenarios.

[0076] In an optional embodiment, the first characteristic data may also be turbulence intensity. Turbulence reflects the stability of the wind farm. High turbulence typically leads to load fluctuations and reduced efficiency of the generator set. Turbulence intensity analysis can identify wind farm characteristics, optimize yaw control and operating modes, and avoid equipment losses caused by high turbulence.

[0077] In other optional embodiments, the collection and processing of environmental data is crucial for path planning and obstacle avoidance in drone swarm control. The first characteristic data can be ambient temperature and air pressure distribution (for optimizing flight endurance and flight efficiency). Characteristic analysis: Air pressure and temperature directly impact power output efficiency and battery life at different drone flight altitudes. Data processing: Combining temperature and air pressure distribution, a flight endurance model is constructed to select the most efficient flight path or altitude.

[0078] S3: Generate a first control target based on the first feature data.

[0079] The first control target includes a state in which the first object can achieve an optimal working state under the action of the first characteristic data.

[0080] In this embodiment, the first control target refers to the yaw angle (ie, the direction adjustment angle of the nacelle) at which the wind turbine generator set can achieve optimal power generation efficiency under the influence of the current wind direction (ie, the first characteristic data).

[0081] In an optional embodiment, the first control objective may also be that, in industrial production, a robotic arm needs to adjust its motion trajectory based on environmental data (such as position and obstacle distance) acquired by sensors to complete an operational task. The robotic arm's motion path and angle are adjusted to ensure the target action is completed with minimal energy consumption while avoiding collisions with obstacles in the environment. By optimizing the motion trajectory, movement time and energy consumption are reduced, thereby improving task efficiency.

[0082] S4: Generate a control instruction using the first control target to control the first object.

[0083] The control instruction includes adjusting the state of the first object itself to achieve an optimal working state by taking the first control target as a control target.

[0084] Specifically, based on the target wind direction, combined with the wind turbine's current actual yaw angle and dynamic response capability, a control command is generated. This command is sent to the yaw drive system, which adjusts the wind turbine's nacelle to align with the target wind direction. Real-time monitoring of turbine status and meteorological data determines whether the target yaw angle has been achieved. If not, the yaw control strategy is re-optimized based on feedback until the desired yaw angle is met.

[0085] The control instructions include generating control instructions based on the target wind direction in combination with the current actual yaw angle and dynamic response capability of the wind turbine generator set;

[0086] Target yaw angle θ t is the wind direction that the wind turbine needs to be aligned with, the actual yaw angle θ a is the direction of the current unit, and the error between the two is defined as:

[0087] e(t)=θ t -θ a

[0088] To ensure periodicity, the error is adjusted to the interval [-π,π]:

[0089] e(t)=arctan2(sin(θ t -θ a ),cos(θ t -θ a ))

[0090] Assume that the dynamic response capability is affected by the maximum yaw speed v of the unit max and the influence of system inertia, expressed by a first-order lag model:

[0091]

[0092] Where β>0 is the response sensitivity, sgn(e(t)) is the sign function of the error, which is used to represent the yaw direction;

[0093] The control command is combined with the proportional integral controller (PI) model and the wind speed weight w is added v , adjust the response speed:

[0094] Among them, K p and Ki are proportional and integral gains respectively;

[0095] Considering the dynamic response capability, the actual adjustment speed is:

[0096]

[0097] in, is the wind speed normalization weight, γ>0 is the dynamic suppression parameter;

[0098] The yaw control angle is adjusted to:

[0099] θ a (t+Δt)=θ a (t)+v c (t)·Δt

[0100] Among them, θ t is the target yaw angle, θ a is the actual yaw angle, e(t) is the current yaw error, v max is the maximum yaw velocity, β is the sensitivity of dynamic response, sgn(e(t)) is the error direction sign function, K p and K i is the proportional and integral gain, u(t) is the control instruction, w v is the wind speed normalization weight, v wind is the current wind speed, v rated is the rated wind speed, γ is the dynamic suppression parameter, Δt is the time step, v c (t) is the control speed.

[0101] Embodiment 2 provides a yaw control system based on meteorological data, comprising:

[0102] The acquisition unit acquires first environmental data around the first object.

[0103] The prediction unit predicts first feature data in the first environment data according to the first environment data.

[0104] The analyzing unit generates a first control target according to the first characteristic data.

[0105] The control unit generates a control instruction using the first control target to control the first object.

[0106] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0107] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0108] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0109] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0110] Example 3 is an embodiment of the present invention, which provides a yaw control method based on meteorological data. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0111] This experiment, focusing on the yaw control system of a wind turbine, aims to verify the effectiveness of an innovative method for optimizing yaw control through meteorological data analysis. A specific wind turbine model was selected for the experiment. Meteorological monitoring equipment, including ultrasonic wind speed and direction sensors, atmospheric pressure sensors, and temperature and humidity sensors, were deployed around the test site and connected to a real-time data acquisition and control platform.

[0112] The test site was located in a plain area with abundant wind resources. The experiment lasted three days and covered three typical weather conditions: sunny, light, and strong. First, a sensor network collected meteorological data such as wind speed, wind direction, atmospheric pressure, temperature, and humidity. Hourly averages and trends were recorded, and pre-processed to remove outliers and smooth the data. Then, a fitting algorithm was used to calculate the current prevailing wind direction based on the wind speed and direction data. The future wind direction was predicted based on the wind speed trend.

[0113] Next, based on the error between the calculated prevailing wind direction and the actual nacelle yaw angle, an improved dynamic response control algorithm was used to generate yaw control commands, adjusting the nacelle's orientation to align with the wind. During the experiment, the control system recorded the unit's power generation, yaw response time, yaw adjustment frequency, and mechanical energy consumption, and compared these results with those of a traditional yaw control system.

[0114] To ensure comprehensive data, the experiment was run under three wind speed conditions, each corresponding to a different magnitude and frequency of wind direction changes. Data reliability was ensured by repeating the test under the same conditions. All data was statistically processed using analytical tools, with averages, standard deviations, and trend charts calculated to clarify the technical advantages of the invention.

[0115] Table 1 Data comparison table

[0116]

[0117] It can be seen from the above test data table that the yaw control method based on meteorological data of the present invention shows obvious advantages in multiple key performance indicators, proving its innovation and practicality.

[0118] Improved Power Generation: Under all three wind speed conditions, the system's average power generation was approximately 11% higher than that of a conventional system. This result demonstrates that precise yaw control allows the wind turbine to more efficiently capture wind energy. The significant increase in power generation (1100kW vs. 950kW) in strong winds demonstrates the advantages of this invention in dynamic wind fields.

[0119] Shortened yaw response time: The system's yaw response time averaged 40 seconds, a 33% reduction compared to conventional systems. This demonstrates that the system's dynamic control algorithm can quickly adjust the nacelle's direction, reducing wind energy loss time.

[0120] Optimized yaw adjustment frequency: Conventional systems frequently adjust yaw direction (an average of 4 times / hour), increasing mechanical wear. The system of the present invention reduces unnecessary yaw adjustments (an average of 3 times / hour) by predicting wind direction changes, especially in light and moderate wind conditions.

[0121] Reduced system mechanical energy consumption: The system's yaw adjustment energy consumption averages 3.8 kWh, a 27% reduction compared to conventional systems. This energy optimization demonstrates the energy-saving benefits of the control algorithm and also extends the life of the yaw system.

[0122] Reduced prevailing wind direction error: This invention reduces prevailing wind direction error from 10.5° in conventional systems to 2.3° through wind direction prediction and optimized control, improving the accuracy of wind turbine yaw alignment. This improvement is the direct cause of the increased power generation efficiency.

[0123] Improved wind direction prediction accuracy: Through an improved wind direction prediction algorithm, the system achieves a 97.5% prediction accuracy in strong wind conditions, significantly higher than the 78.5% of conventional systems. This demonstrates that the system is better able to cope with dynamically changing wind conditions.

[0124] Enhanced turbulence adaptability: Under strong wind conditions with high turbulence intensity, the adaptability score of the system of the present invention reached 5 points (full score), significantly better than the 2 points of the traditional system. This shows that the present invention has stronger adaptability to complex wind field environments.

[0125] Based on the above data analysis, we conclude that this invention significantly improves the efficiency and reliability of yaw control by incorporating high-precision analysis and prediction of meteorological data. Compared to traditional technologies, this invention not only increases wind power output and energy savings, but also reduces equipment losses and demonstrates greater adaptability in dynamic wind fields and complex environments. These innovations fully demonstrate the invention's creativity and novelty in practical application.

[0126] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A yaw control method based on meteorological data, characterized in that: include: Acquire first environmental data around the first object; Predicting first characteristic data in the first environmental data according to the first environmental data; generating a first control target according to the first characteristic data; Using the first control target, a control instruction is generated to control the first object.

2. The yaw control method based on meteorological data according to claim 1, characterized in that: The first environmental data includes parameters of the environment surrounding the first object that can affect the first feature data.

3. The yaw control method based on meteorological data according to claim 2, characterized in that: The first characteristic data includes parameters that affect the optimal working state of the first object when it is working.

4. The yaw control method based on meteorological data according to claim 3, characterized in that: The first control target includes a state in which the first object can reach an optimal working state under the influence of the first characteristic data.

5. The yaw control method based on meteorological data according to claim 4, characterized in that: The control instruction includes taking the first control target as a control target and adjusting the state of the first object to achieve an optimal working state.

6. The yaw control method based on meteorological data according to claim 5, characterized in that: The predicting of the first characteristic data in the first environmental data includes preprocessing the collected meteorological data; determining the current dominant wind direction and wind speed change trend according to the preprocessed meteorological data, and predicting future wind direction changes; In order to improve the smoothness and robustness of the dominant wind direction, a weighted window filter w(i) and a nonlinear normalization function are introduced to determine the dominant wind direction; Among them, w(i)=e -σ|i-n / 2| , the weight of the control center data is high, σ>0 is the smoothing parameter; Based on the sliding window linear regression, the second-order derivative and exponential smoothing are combined to achieve multi-scale fitting of wind speed change trend: Among them, δ>0 is the second-order adjustment coefficient, and γ>0 is the exponential smoothing coefficient; Combining the trend of dominant wind direction and wind speed, a time series fusion model is constructed to achieve future wind direction prediction: Among them, the integral term is used to correct the cumulative prediction deviation; θ d is the dominant wind direction angle; θ i is the wind direction angle at the i-th moment; v i is the wind speed at the i-th moment; Θ d is the improved dominant wind direction, t i is the time of the i-th moment; t is the current time, and are the mean of time and wind speed respectively, w(i) is the weight function, γ is the exponential smoothing coefficient, is the autoregressive coefficient, ψ j is the moving average coefficient, ∈(tj) is the noise term, To predict future wind direction; Θ d ∈[0, 2π): represents the current dominant wind direction angle; Indicates the changing trend of wind speed. A positive value indicates an increase in wind speed, while a negative value indicates a decrease in wind speed. Used to represent the set of real numbers; The predicted future wind direction angle, periodically defined according to the physical properties of the wind direction.

7. The yaw control method based on meteorological data according to claim 6, characterized in that: The control instruction includes generating a control instruction based on the target wind direction in combination with the current actual yaw angle and dynamic response capability of the wind turbine generator set; Target yaw angle θ t is the wind direction that the wind turbine needs to be aligned with, the actual yaw angle θ a is the direction of the current unit, and the error between the two is defined as: e(t)=θ t -θ a To ensure periodicity, the error is adjusted to the interval [-π, π]: e(t)=arctan2(sin(θ t -θ a ),cos(θ t -θ a )) Assume that the dynamic response capability is subject to the maximum yaw speed v of the unit max and the system inertia effect, expressed by a first-order lag model: Among them, β>0 is the response sensitivity, sgn(e(t)) is the sign function of the error, which is used to indicate the yaw direction; The control command is combined with the proportional integral controller (PI) model and the wind speed weight w is added v , adjust the response speed: Among them, K p and K i are proportional and integral gains respectively; Considering the dynamic response capability, the actual adjustment speed is: in, is the wind speed normalization weight, γ>0 is the dynamic suppression parameter; The yaw control angle is adjusted to: θ a (t+Δt)=θ a (t)+v c (t)·Δt Among them, θ t is the target yaw angle, θ a is the actual yaw angle, e(t) is the current yaw error, v max is the maximum yaw velocity, β is the sensitivity of dynamic response, sgn(e(t)) is the error direction sign function, K p and K i is the proportional and integral gain, u(t) is the control command, w v is the wind speed normalization weight, v wind is the current wind speed, v rated is the rated wind speed, γ is the dynamic suppression parameter, Δt is the time step, v c (t) is the control speed.

8. A yaw control system based on meteorological data using the method according to any one of claims 1 to 7, characterized in that: A collection unit, which obtains first environmental data around a first object; A prediction unit, configured to predict first characteristic data in the first environment data according to the first environment data; An analysis unit, generating a first control target according to the first characteristic data; The control unit generates a control instruction using the first control target to control the first object.

9. A computer device comprising: A memory and a processor; the memory stores a computer program, wherein the processor implements the steps of any method as claimed in claim 1 when executing the computer program.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images