Fan optimization control method and system based on dynamic meteorological data

Abstract

The invention relates to the technical field of fan control, and discloses a fan optimization control method and system based on dynamic meteorological data, and the method comprises the steps: obtaining real-time meteorological information around a fan; constructing a wind speed prediction model according to the real-time meteorological information, and predicting the wind speed; and adjusting operation parameters of the fan according to the predicted wind speed change trend to realize optimal control of the fan. According to the method, meteorological information including the wind speed, the wind direction, the temperature, the humidity and the like is obtained in real time, the wind speed change trend in a short period in the future is predicted based on the constructed LSTM deep learning model, and the running parameters of the draught fan are dynamically adjusted in combination with the fluid dynamic model. The variable pitch system angle and the rotating speed gain of the fan can be optimized in real time, it is ensured that the wind wheel always keeps the optimal windward angle, and therefore the wind energy capturing efficiency is improved, and the equipment load is reduced.

Description

Technical Field

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

[0002] As a clean and renewable energy technology, wind power generation has been widely used around the world, and the operation control technology of wind turbines has also developed rapidly. Existing technologies usually use traditional methods based on fixed control parameters to adjust the operation of wind turbines to cope with changes in environmental conditions such as wind speed and wind direction. However, wind resources themselves have obvious intermittent and uncertain characteristics, and the operation status of wind turbines will be affected by complex meteorological conditions. For example, changes in temperature and increased humidity may cause fluctuations in wind turbine power output and increase equipment fatigue load. In order to solve the above problems, in recent years, wind turbine operation control technology has gradually developed in the direction of intelligence and adaptation. Some studies have attempted to dynamically adjust wind turbine operating parameters by real-time monitoring of environmental parameters such as wind speed and wind direction. However, most of the current control strategies are limited to simple proportional integral differential (PID) control or static optimization models, which are difficult to adapt to complex and changeable wind conditions and cannot fully tap the potential of wind resources. Summary of the invention

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

[0004] Therefore, the technical problem solved by the present invention is that the traditional wind turbine control technology has a slow response speed when facing large changes in wind speed or complex meteorological conditions, and it is difficult to adjust the operating parameters in real time.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: a fan optimization control method based on dynamic meteorological data, comprising: obtaining real-time meteorological information around the fan; constructing a wind speed prediction model according to the real-time meteorological information to predict the wind speed; adjusting the operating parameters of the fan according to the predicted wind speed change trend to achieve fan optimization control.

[0006] As a preferred solution of the wind turbine optimization control method based on dynamic meteorological data described in the present invention, the real-time meteorological information includes wind speed, wind direction, temperature and humidity data.

[0007] As a preferred solution of the wind turbine optimization control method based on dynamic meteorological data described in the present invention, the wind turbine load prediction model includes: building an LSTM model, inputting historical data of wind speed, wind direction, temperature and humidity; using the model for real-time training and prediction to predict the wind speed change trend within the next 15 minutes; calculating the dynamic changes of wind energy capture efficiency in combination with the prediction results, and using it as the basis for subsequent adjustments.

[0008] As a preferred solution of the wind turbine optimization control method based on dynamic meteorological data described in the present invention, wherein: the adjustment of the operating parameters of the wind turbine includes dynamically adjusting the angle of the pitch system, calculating the optimal windward angle using a fluid dynamics model based on wind speed and wind direction data; controlling the servo motor to adjust the pitch angle in real time to keep the wind wheel within the optimal angle range with the wind direction; when the wind speed changes drastically, adjusting the rate of change of the pitch angle by optimizing the control algorithm to ensure that its adjustment is synchronized with the wind speed change.

[0009] As a preferred solution of the fan optimization control method based on dynamic meteorological data described in the present invention, the control of the servo motor includes inputting real-time wind speed and wind direction data into the main controller, calculating the optimal windward angle through the fluid mechanics optimization module; generating a command signal for the servo motor according to the calculation result; when the wind speed changes drastically or exceeds the safety range, dynamically adjusting the servo motor to ensure the stability of the angle adjustment process.

[0010] As a preferred solution of the wind turbine optimization control method based on dynamic meteorological data described in the present invention, the adjustment of the servo motor includes dynamically adjusting the gain parameters of the generator using a PID controller according to the wind speed change trend; when the wind speed increases, the speed response capability of the generator is improved by increasing the gain parameters; when the wind speed decreases, the gain parameters are reduced to reduce mechanical stress and energy loss; combined with short-term wind speed prediction results, the speed gain parameters are optimized in advance to improve the accuracy and efficiency of the response.

[0011] As a preferred solution of the fan optimization control method based on dynamic meteorological data described in the present invention, wherein: the adjustment of the servo motor also includes controlling the output power of the inverter, dynamically adjusting the frequency output of the inverter, and optimizing the power distribution according to the real-time load demand; when the wind speed is low, the minimum power output is maintained through the low-speed mode of the inverter; when the wind speed is stable and reaches the optimal working range, the inverter is switched to the high-efficiency mode to improve the output efficiency of the fan; during the output power adjustment process, the generator vibration signal and temperature changes are monitored in real time to ensure operational stability.

[0012] A wind turbine optimization control system based on dynamic meteorological data using any of the methods described in the present invention, wherein: an acquisition module obtains real-time meteorological information around the wind turbine; a prediction module constructs a wind speed prediction model based on the real-time meteorological information to predict the wind speed; and a control module adjusts the operating parameters of the wind turbine based on the predicted wind speed change trend to achieve optimized control of the wind turbine.

[0013] A computer device comprises: a memory and a processor; the memory stores a computer program, comprising: the steps of implementing any one of the methods of the present invention when the processor executes the computer program.

[0014] A computer-readable storage medium stores a computer program, comprising: when the computer program is executed by a processor, the steps of implementing any one of the methods of the present invention are implemented.

[0015] Beneficial effects of the present invention: The method of the present invention obtains meteorological information including wind speed, wind direction, temperature, humidity, etc. in real time, predicts the wind speed change trend in the short term in the future based on the constructed LSTM deep learning model, and dynamically adjusts the wind turbine operating parameters in combination with the fluid dynamics model. The present invention can optimize the variable pitch system angle and speed gain of the wind turbine in real time, ensuring that the wind wheel always maintains the optimal windward angle, thereby improving the wind energy capture efficiency and reducing the equipment load. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing 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 creative work. Among them:

[0017] Figure 1 An overall flow chart of a wind turbine optimization control method based on dynamic meteorological data provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0019] Example 1, reference Figure 1 , is an embodiment of the present invention, and provides a fan optimization control method based on dynamic meteorological data, comprising:

[0020] S1: Obtain real-time meteorological information around the wind turbine.

[0021] Real-time meteorological data is collected through a high-precision sensor network. Sensors are placed at key locations of the wind turbine, including the top of the nacelle, the root of the blades, and near the wind rotor to ensure the comprehensiveness and accuracy of the data. Wind speed and direction data are collected by ultrasonic sensors or mechanical anemometers, which can provide high-frequency instantaneous values ​​and changing trends. These data are transmitted in real time through the communication module with the main control system to provide dynamic support for subsequent adjustments to the wind turbine operating parameters. Temperature and humidity data are collected through precision environmental sensors to monitor the thermodynamic properties and humidity changes of the air to ensure the system's adaptability to complex meteorological conditions.

[0022] During the data collection process, the sensors achieve synchronous collection through a unified sampling frequency (usually 5 to 10 times per second) to avoid affecting the accuracy of the prediction model due to data asynchrony. The collected data is preprocessed through the built-in filtering algorithm to remove outliers and noise interference. The processed data is transmitted to the main control system of the wind turbine in real time through the wireless transmission module to ensure the efficiency and stability of data transmission. At the same time, the system uniformly timestamps the collected wind speed, wind direction, temperature, and humidity data to achieve data fusion in subsequent analysis.

[0023] It should be noted that wind speed is the core variable of wind power generation, which determines the size and stability of wind turbine power output; wind direction directly affects the windward angle of the wind rotor and the efficiency of wind energy capture. Obtaining real-time wind speed and wind direction data is the basic prerequisite for dynamically adjusting wind turbine operating parameters.

[0024] Temperature not only affects the accuracy of the wind speed prediction model, but also affects the operating status of key wind turbine components (such as generators and gearboxes). Extreme temperatures may cause thermal expansion or contraction of components, thus affecting the normal operation of the wind turbine.

[0025] Humidity data reflects the water content in the air, which is important for predicting blade ice accumulation in low-temperature environments. In addition, changes in humidity may affect the dynamic viscosity of the air, thereby having a certain impact on the aerodynamic characteristics of the wind wheel.

[0026] By acquiring multi-dimensional meteorological information including wind speed, wind direction, temperature and humidity, the present invention provides comprehensive data support for the subsequent wind speed prediction model, avoiding the problem of large prediction errors caused by relying solely on wind speed and wind direction data in the prior art. The integration of multi-dimensional data enables the adjustment of wind turbine operating parameters to be more accurate and robust, thereby significantly improving the efficiency of wind energy utilization.

[0027] Compared with the prior art, the present invention solves the problems of prediction error and low fan control efficiency caused by incomplete meteorological data. By introducing temperature and humidity data, the wind speed prediction model of the present invention can better cope with changes in complex meteorological conditions, such as changes in aerodynamic characteristics caused by high humidity and degradation of mechanical component performance under extreme temperatures.

[0028] S2: Build a wind speed prediction model based on real-time meteorological information to predict wind speed.

[0029] The wind turbine load prediction model includes: building an LSTM model, inputting historical data of wind speed, wind direction, temperature and humidity; using the model for real-time training and prediction to predict the wind speed change trend within the next 15 minutes; calculating the dynamic change of wind energy capture efficiency based on the prediction results, and using it as the basis for subsequent adjustments.

[0030] Furthermore, by predicting wind speed in real time based on the LSTM model, the present invention introduces artificial intelligence technology in the field of wind turbine control, solving the problem that traditional methods are difficult to handle complex nonlinear meteorological data. Traditional prediction methods (such as those based on linear regression or simple statistical analysis) show obvious limitations when dealing with dynamic changes in multiple variables, especially under conditions of high fluctuating wind speeds, and are prone to large errors. The introduction of the LSTM model significantly improves the accuracy and reliability of wind speed prediction, making the adjustment of wind turbine operating parameters more accurate.

[0031] In this embodiment, the input variables include wind speed, wind direction, temperature, and humidity. These variables are highly correlated with the dynamic changes in wind speed and provide comprehensive environmental information support for the model.

[0032] The LSTM model is trained offline using a large amount of historical meteorological data to obtain the initial model parameters. In actual operation, the latest real-time meteorological data is used for online training to continuously update the model weights to adapt to the dynamic changes in meteorological conditions.

[0033] The input gate, forget gate, and output gate control the flow of information and adapt to the temporal characteristics of meteorological data. The hidden state and cell state jointly store historical information. Multi-layer stacked LSTM (such as 2-3 layers) is used to enhance the model's ability to capture nonlinear dynamic relationships.

[0034] The trained LSTM model is used to input the current multi-dimensional meteorological data sequence to predict the wind speed trend in the next T time steps. The model automatically adjusts the prediction range to cope with different wind speed change modes (such as low-frequency stability or high-frequency fluctuations).

[0035] Based on the predicted wind speed value, combined with the wind turbine's power curve and fluid dynamics model, the future wind energy capture efficiency is dynamically calculated, and the wind turbine operating parameters are optimized and adjusted according to the predicted wind speed changes and wind energy capture efficiency.

[0036] S3: Adjust the operating parameters of the fan according to the predicted wind speed change trend to achieve optimized control of the fan.

[0037] Furthermore, the adjustment of the operating parameters of the wind turbine includes dynamically adjusting the angle of the pitch system, calculating the optimal windward angle using a fluid dynamics model based on wind speed and wind direction data; controlling the servo motor to adjust the pitch angle in real time to keep the wind wheel within the optimal angle range with the wind direction; and when the wind speed changes drastically, adjusting the rate of change of the pitch angle by optimizing the control algorithm to ensure that its adjustment is synchronized with the wind speed change.

[0038] The control of the servo motor includes inputting real-time wind speed and wind direction data into a main controller, calculating the optimal windward angle through a fluid mechanics optimization module; generating a command signal for the servo motor according to the calculation result; and dynamically adjusting the servo motor when the wind speed changes drastically or exceeds a safe range to ensure the stability of the angle adjustment process.

[0039] The adjustment of the servo motor includes dynamically adjusting the gain parameters of the generator using a PID controller according to the wind speed change trend; when the wind speed increases, the gain parameters are increased to improve the speed response capability of the generator; when the wind speed decreases, the gain parameters are reduced to reduce mechanical stress and energy loss; combined with short-term wind speed prediction results, the speed gain parameters are optimized in advance to improve the accuracy and efficiency of the response.

[0040] The adjustment of the servo motor also includes controlling the output power of the inverter, dynamically adjusting the frequency output of the inverter, and optimizing power distribution according to real-time load demand; when the wind speed is low, maintaining the minimum power output through the low-speed mode of the inverter; when the wind speed is stable and reaches the optimal working range, switching the inverter to the high-efficiency mode to improve the output efficiency of the fan; during the output power adjustment process, real-time monitoring of the generator vibration signal and temperature changes to ensure operational stability.

[0041] Embodiment 2: In an exemplary embodiment, a wind turbine optimization control system based on dynamic meteorological data is also provided, including a collection module, a prediction module and a control module.

[0042] The acquisition module obtains real-time meteorological information around the wind turbine.

[0043] The prediction module builds a wind speed prediction model based on real-time meteorological information to predict wind speed.

[0044] The control module adjusts the operating parameters of the fan according to the predicted wind speed change trend to achieve optimized control of the fan.

[0045] 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, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0046] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0047] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a 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, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0048] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0049] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. 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 fan optimization control method based on dynamic meteorological data, characterized in that: include: Get real-time weather information around the wind turbine; Build a wind speed prediction model based on real-time meteorological information to predict wind speed; Adjust the operating parameters of the fan according to the predicted wind speed change trend to achieve optimized control of the fan.

2. The fan optimization control method based on dynamic meteorological data according to claim 1, characterized in that: The real-time meteorological information includes wind speed, wind direction, temperature and humidity data.

3. The fan optimization control method based on dynamic meteorological data according to claim 2, characterized in that: The wind turbine load prediction model includes building an LSTM model and inputting historical data of wind speed, wind direction, temperature and humidity; Use the model for real-time training and prediction to predict the wind speed trend in the next 15 minutes; The dynamic changes in wind energy capture efficiency are calculated in combination with the forecast results and used as the basis for subsequent adjustments.

4. The fan optimization control method based on dynamic meteorological data according to claim 3, characterized in that: The adjusting of the operating parameters of the wind turbine includes dynamically adjusting the angle of the variable pitch system and calculating the optimal windward angle using a fluid dynamics model according to wind speed and wind direction data; Control the servo motor to adjust the pitch angle in real time to keep the wind rotor within the optimal angle range with the wind direction; When the wind speed changes dramatically, the rate of change of the pitch angle is adjusted by optimizing the control algorithm to ensure that its adjustment is synchronized with the wind speed change.

5. The fan optimization control method based on dynamic meteorological data according to claim 4, characterized in that: The control servo motor comprises: The real-time wind speed and direction data are input into the main controller, and the optimal windward angle is calculated through the fluid mechanics optimization module; Generate a command signal for the servo motor according to the calculation result; When the wind speed changes dramatically or exceeds the safe range, the servo motor is dynamically adjusted to ensure the stability of the angle adjustment process.

6. The fan optimization control method based on dynamic meteorological data according to claim 5, characterized in that: The adjustment servo motor comprises: According to the wind speed change trend, the PID controller is used to dynamically adjust the generator gain parameters; When the wind speed increases, the speed response capability of the generator is improved by increasing the gain parameter; When the wind speed decreases, the gain parameter is reduced to reduce mechanical stress and energy loss; Combined with the short-term wind speed forecast results, the speed gain parameters are optimized in advance to improve the accuracy and efficiency of the response.

7. The fan optimization control method based on dynamic meteorological data according to claim 6, characterized in that: The adjusting the servo motor also includes controlling the output power of the frequency converter, dynamically adjusting the frequency output of the frequency converter, and optimizing power distribution according to real-time load demand; When the wind speed is low, the inverter's low speed mode is used to maintain minimum power output; When the wind speed is stable and reaches the optimal working range, the inverter is switched to high-efficiency mode to improve the fan output efficiency; During the output power adjustment process, the generator vibration signal and temperature changes are monitored in real time to ensure operational stability.

8. A fan optimization control system based on dynamic meteorological data using any one of the methods of claims 1 to 7, characterized in that: include, Acquisition module, to obtain real-time meteorological information around the wind turbine; The prediction module builds a wind speed prediction model based on real-time meteorological information to predict wind speed; The control module adjusts the operating parameters of the fan according to the predicted wind speed change trend to achieve optimized control of the fan.

9. A computer device comprising: Memory and processor; The memory stores a computer program, characterized in that when the processor executes the computer program, the steps of the wind turbine optimization control method based on dynamic meteorological data as described in any one of claims 1-7 are implemented.

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 wind turbine optimization control method based on dynamic meteorological data as described in any one of claims 1 to 7 are implemented.

Images