A wind power prediction device and system thereof

Abstract

The present invention discloses a wind power prediction device and a system thereof, comprising a support base, which can be installed on the ground or on a mobile device; a body is arranged on the top of the support base, a ventilation cavity is opened in the middle of the body, a micro generator is installed in the ventilation cavity, the micro generator is used to convert wind energy into mechanical energy, and convert mechanical energy into electrical energy output, so as to calculate and analyze the wind power generator power in proportion by detecting the output electrical energy power; a movable support mechanism is arranged on the body, and a plurality of monitoring devices are arranged on the support mechanism, and the monitoring devices move with the movement of the support mechanism, so as to be used for collecting meteorological parameters in different directions of the surrounding area. The present invention realizes the prediction of wind power by integrating multiple groups of meteorological prediction data and proportional wind turbine data, instead of relying solely on meteorological prediction data of a single numerical weather forecast system, thereby improving the prediction accuracy of wind power.

Description

Technical Field

[0001] The invention relates to the technical field of wind power generation, and in particular to a wind power prediction device and a system thereof. Background Art

[0002] As wind power technology matures, the capacity of wind turbines and the scale of grid-connected wind farms continue to expand, and the proportion of wind power in the total power generation of the power system increases year by year. The penetration power of wind farms continues to increase, and a series of problems brought to the power system are becoming increasingly prominent, seriously threatening the safe, stable, economical and reliable operation of the power system. Timely and accurate prediction of wind power can significantly enhance the safety, stability, economy and controllability of the power system.

[0003] When analyzing the access of wind farms to the power system, it is necessary to consider the large fluctuation range of the wind farm output power. Wind energy is intermittent and randomly volatile. Changes in wind speed directly lead to changes in the active power and reactive power of the wind farm. The output power is very unstable. Therefore, before construction, it is necessary to actively carry out wind power forecasting research to improve the accuracy of the forecast, which is conducive to the output forecast in the early stage of wind farm construction, that is, wind energy resource assessment and wind farm site selection, and then calculate whether the wind turbine is suitable for installation. Therefore, a wind turbine power forecasting device that can accurately collect data for analysis is needed. Summary of the invention

[0004] The object of the present invention is to provide a wind power prediction device and a system thereof to solve the problems raised in the above background technology.

[0005] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a wind power prediction device and a system thereof, comprising a support base, the support base can be installed on the ground or on a mobile device, a body is arranged on the top of the support base, a ventilation cavity is opened in the middle of the body, a micro-generator is installed in the ventilation cavity, the micro-generator is used to convert wind energy into mechanical energy, and convert mechanical energy into electrical energy output, so as to calculate and analyze the wind power generator power in equal proportion by detecting the output electrical energy power;

[0006] The machine body is provided with a movable supporting mechanism, and a plurality of monitoring devices are provided on the supporting mechanism. The monitoring devices move along with the movement of the supporting mechanism, so that the monitoring devices can be used to collect meteorological parameters in different directions of the surrounding area.

[0007] Furthermore, the supporting mechanism includes an annular frame and a plurality of supporting frames equidistantly mounted on the outer circumference of the annular frame, a slide groove is provided on the outer circumference of the body, the annular frame is rotatably embedded in the slide groove, a motor is provided in the body, and the motor is transmission-connected to the annular frame to drive the annular frame to rotate, a connecting frame is slidingly provided in each of the supporting frames, a power assembly is provided on the supporting frame, the power assembly is connected to the connecting frame to drive the connecting frame to telescopically move along the supporting frame, and the monitoring device is provided at the other end of the connecting frame.

[0008] Furthermore, the power assembly includes an electric motor and a spring, a pulley is sleeved on the output shaft of the electric motor, a steel rope is wound around the pulley, a support is provided on the upper part of the rear end surface of the connecting frame, the other end of the steel rope is fixedly connected to the support, a groove is provided on the front end surface of the connecting frame, the spring is provided in the groove, one end of the spring is connected to the top of the groove, and the other end is connected to the inner wall of the support frame, and the left and right ends of the connecting frame are slidably connected to the left and right inner walls of the support frame through guide rails.

[0009] Furthermore, a mounting seat is provided at one end of the connecting frame away from the supporting frame, and a mounting cavity for mounting the monitoring device is provided in the mounting seat. The mounting cavity is a circular structure and a slide is provided around the inner wall thereof. A base is slidably provided in the slide and the base can rotate along the axis of the mounting cavity. The monitoring device is mounted on the top of the base, and a plurality of counterweights are embedded in the lower part of the base, and the monitoring device is a micrometeorological instrument.

[0010] Furthermore, the outer wall of the annular frame is sleeved with a gear ring, the output shaft sleeve of the motor is sleeved with a gear, and the gear is meshed with the gear ring to drive the annular frame to rotate.

[0011] Furthermore, a battery is provided in the body, the micro-generator is electrically connected to the battery to charge it, a monitor is provided in the micro-generator to detect the power generated by the micro-generator, and the output end of the battery is electrically connected to various electrical components to provide power.

[0012] Also included is a wind power prediction system, including a data acquisition module, which is used to collect meteorological data through the above-mentioned wind power prediction device to obtain data to be predicted in multiple different directions;

[0013] A database storing historical operation data of wind turbines of other existing wind farms and meteorological data collected on site, wherein the database is trained based on a plurality of operation data and on-site meteorological data to obtain a power prediction model;

[0014] The power prediction module is used to input the data to be predicted into a pre-trained power prediction model to obtain power prediction data.

[0015] Furthermore, it also includes a post-processing module. The database also has a wind turbine correction model, which is trained based on the operating data of both micro-generators and wind turbine generator equipment in the same wind farm. The post-processing module inputs the collected micro-generator power curve parameters into the pre-trained wind turbine correction model to obtain wind turbine prediction data, and then compares and optimizes the wind turbine prediction data with the power prediction data to finally determine the target wind power prediction power.

[0016] Furthermore, a movable lifting device may be installed at the bottom of the support base.

[0017] Furthermore, the fan calibration model is constructed by taking the following steps:

[0018] S1. Arrange multiple micro wind turbines and an actual wind turbine in the same wind farm, and pair each micro wind turbine with an actual wind turbine to obtain several wind turbine combinations. For each wind turbine combination, calculate the power correlation coefficient and wind speed correlation coefficient of the wind turbine combination. Calculate the performance correlation coefficient based on the product of the power correlation coefficient and the wind speed correlation coefficient.

[0019] S2. Generate a performance correlation coefficient matrix of the Hadamard product of the power correlation coefficient matrix and the wind speed correlation coefficient matrix of each wind turbine combination; in the wind turbine power generation performance correlation matrix, the maximum coefficient value indicates that the power generation performance of the two wind turbines in the combination is closest.

[0020] S3. Take the micro wind turbine with the closest power generation performance as the target micro wind turbine, and establish a power ratio model between the target micro wind turbine and the actual wind turbine. The model can be expressed as:

[0021] Power ratio = /

[0022] in, and Represent the actual power of the micro fan and the actual fan respectively.

[0023] S4. The accuracy of the model is verified through multiple groups of actual operation data, and the power ratio model is optimized in combination with the ultra-short-term power prediction model of wind turbines based on LSTM-ELM to improve the prediction accuracy of the power ratio, and finally the wind turbine correction model is obtained.

[0024] Furthermore, the power prediction model is constructed by taking the following steps:

[0025] 1. Data collection: Collect existing wind power generation related data, including meteorological data (wind speed, wind direction, temperature, air pressure, etc.), historical power generation data, and wind turbine parameters (such as power curve, rated power, etc.);

[0026] 2. Data preprocessing: preprocess the collected data, including missing data filling, data smoothing and feature standardization, to improve the accuracy and robustness of the model;

[0027] 3. Feature engineering: Extract features that are helpful for power generation prediction, including time features (hours, months, seasons, etc.) and meteorological features (wind speed, temperature, etc.);

[0028] 4. Model selection and training: Select the prediction model: LSTM model and deep learning model: CNN-LSTM&GRU combination model, use historical data to train the model, and adjust the model parameters until the result is close to the test set;

[0029] 5. Prediction and evaluation: Use the trained model to make predictions and use the mean square error (MSE) indicator to evaluate model performance;

[0030] 6. Model optimization: According to the prediction results and error analysis, adjust the model parameters, add historical features, and increase the amount of training data to improve the prediction accuracy of the model.

[0031] Compared with the prior art, the present invention has the following beneficial effects:

[0032] The prediction device of the present invention

[0033] 1. The prediction device of the present invention is used to test the installation environment of the wind turbine before installing the wind turbine. The wind power conversion working condition of the wind turbine in the wind farm is simulated by a micro-generator, and the environmental parameters at different positions are collected by a movable monitoring device, which are then input into an advanced model to calculate the wind power conversion power of the wind turbine, and to detect whether the location is suitable for installing the wind turbine, thereby improving the practicality of use, realizing the comprehensive integration of multiple groups of meteorological forecast data and proportional wind turbine data to predict wind power, rather than relying solely on the meteorological forecast data of a single numerical weather forecast system, thereby improving the prediction accuracy of wind power.

[0034] 2. Two sets of prediction models (such as machine learning, deep learning, etc.) are established in the prediction system of the present invention, which calculate the input meteorological data and micro-generator characteristic data respectively, and perform deviation correction based on the two power prediction results to obtain the optimal power prediction result, thereby improving the prediction accuracy and enhancing the stability and field applicability of the power prediction results. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1A front structural diagram of a wind power prediction device according to the present invention;

[0036] Figure 2 A rear structural diagram of a wind power prediction device according to the present invention;

[0037] Figure 3 This is a front view of a wind power prediction device according to the present invention;

[0038] Figure 4 A side view of a wind power prediction device according to the present invention;

[0039] Figure 5 This is a structural diagram of a wind power prediction system of the present invention.

[0040] In the figure, supporting base-1, machine body-2, ventilation cavity-3, micro generator-4, monitoring equipment-5, annular frame-6, supporting frame-7, motor-8, connecting frame-9, electric motor-10, spring-11, reel-12, steel rope-13, support-14, mounting seat-15, mounting cavity-16, base-17, counterweight block-18, gear ring-19, gear-20. DETAILED DESCRIPTION

[0041] 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.

[0042] like Figure 1 and Figure 2 As shown, a wind power prediction device comprises a support base 1, the support base 1 can be installed on the ground or on a mobile device, a body 2 is arranged on the top of the support base 1, a ventilation cavity 3 is opened in the middle of the body 2, a micro generator 4 is installed in the ventilation cavity 3, the micro generator 4 is used to convert wind energy into mechanical energy, and convert mechanical energy into electrical energy output, so as to calculate and analyze the wind power generator power in equal proportion by detecting the output electrical energy power;

[0043] A movable supporting mechanism is provided on the body 2, and a plurality of monitoring devices 5 are provided on the supporting mechanism. The monitoring devices 5 move with the movement of the supporting mechanism, so that they can be used to collect meteorological parameters in different directions of the surrounding area.

[0044] See also Figures 1 to 3As shown, the support mechanism includes an annular frame 6 and three support frames 7 which are equally spaced and mounted on the outer circumference of the annular frame 6. A slide groove is provided on the outer circumference of the body 2. The annular frame 6 is rotatably embedded in the slide groove. A motor 8 is provided in the body 2, and the motor 8 is transmission-connected with the annular frame 6 to drive the annular frame 6 to rotate. A connecting frame 9 is slidably provided in each supporting frame 7. A power assembly is provided on the supporting frame 7. The power assembly is connected with the connecting frame 9 to drive the connecting frame 9 to telescopically move along the supporting frame 7. A monitoring device 5 is provided at the other end of the connecting frame 9.

[0045] First, the support frame 7 can rotate with the annular frame 6, and the connecting frame 9 thereon adopts a retractable structure. Therefore, under the coordinated rotation of the annular frame 6 and the retractable action of the connecting frame 9, the monitoring device 5 at the end can measure the temperature, humidity and wind speed around the wind farm at different X-axis and Y-axis positions, measure multiple groups of data, and conduct comprehensive summary. The measured data is relatively comprehensive. When predicting, the average value of multiple groups of data can be used as the basis for prediction, which effectively solves the problem that the data measured by the fixed-position micro-meteorological instrument during detection has certain limitations, and the measured data is not comprehensive enough, which leads to the defect of errors in wind power prediction;

[0046] At the same time, the three support frames 7 arranged on the annular frame 6 correspond to the three wind blades of the actual wind turbine, and can collect different data of factors such as temperature, humidity, wind speed and wind force around each wind blade of the wind turbine under the same conditions, so as to calculate more accurate results through more detailed data.

[0047] See also Figure 3 and Figure 4 As shown, (the power assembly can be replaced by a linear drive device such as a screw rod, a cylinder, etc.), the power assembly of this embodiment includes a motor 10 and a spring 11, a wire wheel 12 is sleeved on the output shaft of the motor 10, a steel rope 13 is wound and connected to the wire wheel 12, a support 14 is provided on the upper part of the rear end surface of the connecting frame 9, the other end of the steel rope 13 is fixedly connected to the support 14, a groove is provided on the front end surface of the connecting frame 9, and the spring 11 is arranged in the groove, and one end of the spring 11 is connected to the top of the groove, and the other end is connected to the inner wall of the support frame 7, and the left and right ends of the connecting frame 9 are slidably connected to the left and right inner walls of the support frame 7 through guide rails;

[0048] When it is necessary to adjust the telescopic length of the connecting frame 9, when it is necessary to extend the connecting frame 9, the motor 10 drives the wire wheel 12 to rotate counterclockwise, thereby releasing the steel rope 13. After the steel rope is relaxed and loses its restraint, the connecting frame 9 will move outward under the elastic force of the spring 11, so that the length of the steel rope 13 released by the wire wheel 12 and the spring 11 can be used to adjust the extension length of the connecting frame 9; similarly, when it is necessary to retract the connecting frame 9, it is only necessary to drive the wire wheel 12 clockwise to grab it first, retract the steel rope 13, and the steel rope 13 will turn back to pull the connecting frame 9 back and compress the spring 11.

[0049] The steel rope 13 design can make the structure of the connecting frame 9 more compact and simple, because there is only the monitoring equipment 5 on the connecting frame 9, and it does not need too strong a load capacity. If screws, cylinders and other devices are used, there are defects such as complex structure, large space occupation, large overall weight, and inconvenient movement and installation. The coordinated extension of the steel rope 13 and the spring 11 makes loading and unloading and maintenance more convenient and flexible, and can reduce the weight of the entire equipment, thereby reducing the burden of the rotation of the annular frame 6 and making it smoother.

[0050] See also Figure 2 and Figure 3 As shown, a mounting seat 15 is provided at one end of the connecting frame 9 away from the supporting frame 7, and a mounting cavity 16 for assembling the monitoring device 5 is provided in the mounting seat 15. The mounting cavity 16 is a circular structure and a slideway is provided around its inner wall. A base 17 is slidably provided in the slideway. The base 17 can rotate along the axis of the mounting cavity 16. The monitoring device 5 is mounted on the top of the base 17. A plurality of counterweights 18 are embedded in the lower part of the base 17, and the monitoring device 5 is a micro-meteorological instrument.

[0051] Since the base 17 is freely movable, when the annular frame 6 drives the connecting frame 9 to rotate, the base 17 will rotate and adjust itself under the gravity of the bottom counterweight block 18, and remain in a vertical state at all times, thereby ensuring that the micrometeorological instrument thereon is always in the upright position, ensuring that the direction and angle remain consistent when monitoring at different positions, thereby preventing the sensor from being affected by other factors and ensuring the accuracy of the readings.

[0052] See also Figure 2 and Figure 4 As shown, the outer wall of the annular frame 6 is provided with a gear ring 19, the output shaft sleeve of the motor 8 is provided with a gear 20, the gear 20 is meshed with the gear ring 19 to drive the annular frame 6 to rotate, a battery is provided in the body 2, the micro generator 4 is electrically connected to the battery to charge it, a monitor is provided in the micro generator 4 to detect the power generation of the micro generator 4, and the output end of the battery is electrically connected to various electrical components to supply power.

[0053] See also Figure 5 As shown, this embodiment also provides a wind power prediction system, including a data acquisition module, which is used to collect meteorological data through the above-mentioned wind power prediction device to obtain data to be predicted in multiple different directions;

[0054] A database storing historical operation data of wind turbines of other existing wind farms and meteorological data collected on site, wherein the database is trained based on multiple operation data and on-site meteorological data to obtain a power prediction model;

[0055] A power prediction module is used to input the data to be predicted into a pre-trained power prediction model to obtain power prediction data;

[0056] The post-processing module, the database also has a wind turbine correction model, which is trained based on the operating data of the micro-generator 4 and the wind turbine generator equipment in the same wind farm. The micro-generator 4 is pre-installed in the existing wind farm and placed under the same conditions as the actual wind turbine in the wind farm. The power generation of the micro-generator 4 is collected, and the power generation power and the power generation power of the actual wind turbine are input into the database. Multiple groups of historical power generation data of the micro-generator and the wind turbine generator are compared and analyzed to obtain the theoretical power ratio, and the power ratio curve is optimized in combination with the ultra-short-term power prediction model of the wind turbine based on LSTM-ELM, so as to obtain the wind turbine correction model;

[0057] The post-processing module inputs the collected power curve parameters of the micro-generator 4 into the pre-trained wind turbine correction model, so that the power curve parameters of the micro-generator 4 can be proportionally amplified to obtain the actual wind turbine power prediction data under the wind farm, and then the actual wind turbine power prediction data is compared and optimized with the power prediction data. If the difference between the two is large, the factors causing the problem are analyzed and the prediction is optimized again. If the difference between the two is within the rationality threshold, the target wind power prediction power can be finally determined.

[0058] Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A wind power prediction device, characterized in that: The device comprises a support base, which can be installed on the ground or on a mobile device. A body is arranged on the top of the support base, a ventilation cavity is opened in the middle of the body, and a micro-generator is installed in the ventilation cavity. The micro-generator is used to convert wind energy into mechanical energy and convert mechanical energy into electrical energy output, so as to calculate and analyze the power of the wind turbine generator in proportion by detecting the output electrical energy power. The machine body is provided with a movable supporting mechanism, and a plurality of monitoring devices are provided on the supporting mechanism. The monitoring devices move with the movement of the supporting mechanism, so that they can be used to collect meteorological parameters in different directions of the surrounding area; the supporting mechanism includes an annular frame and a plurality of supporting frames equidistantly installed on the outer peripheral surface of the annular frame, the outer peripheral surface of the machine body is provided with a slide groove, the annular frame is rotatably embedded in the slide groove, a motor is provided in the machine body, and the motor is transmission-connected to the annular frame to drive the annular frame to rotate, a connecting frame is slidably provided in each of the supporting frames, a power assembly is provided on the supporting frame, and the power assembly is connected to the connecting frame to drive the connecting frame to telescopically move along the supporting frame, and the monitoring device is provided at the other end of the connecting frame.

2. A wind power prediction device according to claim 1, characterized in that: The power assembly includes an electric motor and a spring, a pulley is sleeved on the output shaft of the electric motor, a steel rope is wound around the pulley, a support is provided on the upper part of the rear end surface of the connecting frame, the other end of the steel rope is fixedly connected to the support, a groove is provided on the front end surface of the connecting frame, the spring is provided in the groove, one end of the spring is connected to the top of the groove, and the other end is connected to the inner wall of the supporting frame, and the left and right ends of the connecting frame are slidably connected to the left and right inner walls of the supporting frame through guide rails.

3. A wind power prediction device according to claim 1, characterized in that: A mounting seat is provided at one end of the connecting frame away from the supporting frame, and a mounting cavity for mounting the monitoring device is provided in the mounting seat. The mounting cavity is a circular structure and a slide is provided around the inner wall thereof. A base is slidably provided in the slide and the base can rotate along the axis of the mounting cavity. The monitoring device is mounted on the top of the base, and a plurality of counterweight blocks are embedded in the lower part of the base. The monitoring device is a micrometeorological instrument.

4. A wind power prediction device according to claim 1, characterized in that: The outer wall of the annular frame is sleeved with a gear ring, and the output shaft sleeve of the motor is sleeved with a gear, and the gear is meshed with the gear ring for transmission, thereby driving the annular frame to rotate.

5. A wind power prediction device according to any one of claims 1 to 4, characterized in that: A storage battery is arranged in the body, the micro generator is electrically connected to the storage battery to charge it, a monitor is arranged in the micro generator to detect the power generated by the micro generator, and the output end of the storage battery is electrically connected to various electrical components to supply power.

6. A wind power prediction system, characterized in that: It comprises a data acquisition module, which is used to collect meteorological data through the wind power prediction device according to claim 5 to obtain data to be predicted in multiple different directions; A database storing historical operation data of wind turbines of other existing wind farms and meteorological data collected on site, wherein the database is trained based on a plurality of operation data and on-site meteorological data to obtain a power prediction model; A power prediction module is used to input the data to be predicted into a pre-trained power prediction model to obtain power prediction data, wherein the power prediction model is obtained by inputting relevant data of existing wind turbines into an LSTM model and a CNN-LSTM&GRU combined model for training; A post-processing module, wherein the database is also provided with a wind turbine correction model, wherein the wind turbine correction model is trained based on the operating data of both the micro-generator and the wind turbine generator equipment in the same wind farm, and multiple groups of historical power generation data of the micro-generator and the wind turbine generator are compared and analyzed to obtain a theoretical power ratio, and the power ratio curve is optimized in combination with an ultra-short-term power prediction model of a wind turbine generator set based on LSTM-ELM; the post-processing module inputs the collected micro-generator power curve parameters into the pre-trained wind turbine correction model to obtain wind turbine prediction data, and then compares and optimizes the wind turbine prediction data with the power prediction data to finally determine the target wind power prediction power.

Images