Data-based parallel auxiliary control method and system for wind turbine generator

Abstract

The invention discloses a wind turbine generator parallel auxiliary control method, system and device based on data, a medium and a program, and belongs to the technical field of new energy power. The method comprises the steps that a wind turbine generator controller PLC receives data of an external sensor of a wind turbine generator; preprocessing the received sensor data and an algorithm logic variable in a wind turbine generator PLC (Programmable Logic Controller) to obtain preprocessed data; extracting feature data based on the preprocessed data; a recommended set threshold value is calculated according to the feature data, the calculated set threshold value is sent to a wind turbine generator controller PLC, the wind turbine generator controller PLC carries out a new round of calculation according to the threshold value, and a control instruction CO is generated; and the wind turbine generator performs control motion according to the control instruction CO. According to the method, the control parameters and the logic judgment threshold are directly updated in real time through the actual unit operation data, and the occurrence of events of inaccurate control and greater risk caused by mismatching of the actual unit operation and the control parameters is avoided.

Description

Technical Field

[0001] The present invention relates to the field of new energy power technology, and in particular to a data-based wind turbine parallel auxiliary control method, system, equipment, medium and program. Background Art

[0002] The control target of a wind turbine is generally calculated by a programmable logic controller (PLC). The internal operation cycle of a traditional PLC is 20ms, and the operation data and instructions in the algorithm logic are calculated and updated every 20ms. As the control algorithms, sensors, and monitoring systems of wind turbines become more mature, traditional PLCs cannot further process massive amounts of operation data and cannot support refined control algorithm design. In addition, the control algorithms and parameters of wind turbines, judgment logic thresholds, etc. are generally determined through simulation during design. When the unit is officially put into operation, due to the inconsistency between the local environmental conditions and the design, the control parameters and judgment logic thresholds may not match the wind turbine with the local operating environment if they remain unchanged and the design parameters are used, increasing the risk of unsafe time, and the potential power generation performance is not effectively released. At present, wind turbine operators have strengthened the monitoring and analysis of operation data, but in view of the large number of wind turbines and massive operation data, only coarse-grained collection and analysis of power, faults, vibrations, etc. are performed, and the refined analysis of the operation data of a single unit is still insufficient.

[0003] Although current technology has achieved the upgrade of PLC computing power, in order to ensure control accuracy, the reliability and stability of the main control system loop are difficult to be fully guaranteed due to the large amount of calculation and data storage involved, which leads to unsatisfactory control effect. In addition, although information such as fault warning can be obtained through centralized monitoring and analysis, the control parameters and judgment logic thresholds of wind turbines based on the operating environment cannot be updated in time. The current update method can only refresh the main control program by shutting down each wind turbine in turn. This method cannot effectively improve the real-time operation control of wind turbines. Even if potential risks are discovered, they cannot be solved immediately. This situation may lead to inaccurate control and greater risk accidents due to insufficient simulation of simulation conditions, inaccurate models, and mismatch between the actual operation of wind turbines and control parameters. Summary of the invention

[0004] Aiming at the problem that the unit control parameters and judgment logic thresholds based on the operating environment in the prior art cannot be updated and can only be refreshed by shutting down each unit one by one to refresh the main control program, the present invention provides a data-based wind turbine parallel auxiliary control method, which directly updates the control parameters and logic judgment thresholds in real time through the actual unit operation data, avoiding the occurrence of inaccurate control and greater risk events caused by the mismatch between the actual operation of the unit and the control parameters.

[0005] In order to achieve the above object, the present invention provides the following technical solutions.

[0006] In a first aspect, the present invention provides a data-based wind turbine parallel auxiliary control method, comprising: The wind turbine controller PLC receives data from external sensors of the wind turbine; Preprocess the received sensor data with the algorithm logic variables inside the wind turbine controller PLC to obtain preprocessed data; Extract feature data based on the preprocessed data; The recommended threshold value is calculated based on the characteristic data, and the calculated threshold value is sent to the wind turbine controller PLC. The wind turbine controller PLC performs a new round of calculation based on the threshold value and generates a control instruction CO; The wind turbine performs control movements according to the control command CO.

[0007] As a further improvement of the present invention, the wind turbine controller PLC receives data from external sensors of the wind turbine, including: Collect external sensor data of the vibration monitoring system, pitch control system, current conversion system, load monitoring system, temperature monitoring system, blade clearance monitoring system, and lidar in the wind turbine to form the data of the external sensors of the wind turbine; The data from the wind turbine external sensors are received by the wind turbine controller PLC.

[0008] As a further improvement of the present invention, the received sensor data and the algorithm logic variables inside the wind turbine controller PLC are preprocessed to obtain the preprocessed data, including: The wind turbine controller PLC receives the data from the external sensors of the wind turbine and the algorithm logic variables inside the wind turbine controller PLC, performs sliding average preprocessing, and obtains preprocessed data.

[0009] As a further improvement of the present invention, the extracting characteristic data based on the preprocessed data includes: The preprocessed data is converted and processed to extract characteristic data; The characteristic data includes CI_sensor_avg_lookup, CS_state_avg_lookup, CI_sensor_avg_rate, CS_state_avg_rate, CS_state_avg_timer and CI_sensor_avg_time.

[0010] As a further improvement of the present invention, the recommended threshold value is calculated based on the characteristic data, and the calculated threshold value is sent to the controller PLC. The wind turbine controller PLC performs a new round of calculation based on the threshold value and generates a control instruction CO, including: Calculate the recommended setting threshold based on the feature data; Send the calculated set thresholds and algorithm parameters to the wind turbine controller PLC, and replace the original thresholds and parameters in the wind turbine controller PLC; The wind turbine controller PLC calculates the control instruction CO based on the calculated set thresholds and algorithm parameters.

[0011] As a further improvement of the present invention, the wind turbine set performs control movement according to the control instruction CO, including: The actuator in the wind turbine performs pitch, yaw and torque movements according to the control command CO; Among them, the data obtained from pitch, yaw and torque movement are fed back to the wind turbine controller PLC through the external sensors of the wind turbine.

[0012] In a second aspect, the present invention provides a data-based wind turbine parallel auxiliary control system, comprising: Data receiving module: used for the wind turbine controller PLC to receive data from external sensors of the wind turbine; Preprocessing data module: used to preprocess the received sensor data with the algorithm logic variables inside the wind turbine controller PLC to obtain preprocessed data; Feature extraction module: used to extract feature data based on preprocessed data; Generate instruction module: used to calculate the recommended threshold value according to the characteristic data, and send the calculated threshold value to the wind turbine controller PLC. The wind turbine controller PLC performs a new round of calculation according to the threshold value and generates the control instruction CO; Control motion module: used for wind turbines to perform control motion according to the control command CO.

[0013] In a third aspect, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the data-based wind turbine parallel auxiliary control method when executing the computer program.

[0014] In a fourth aspect, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the data-based parallel auxiliary control method for wind turbines are implemented.

[0015] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions, which, when executed by a processor, implement the steps of the data-based parallel auxiliary control method for wind turbines.

[0016] Compared with the prior art, the present invention has the following beneficial effects: The present invention realizes the instant optimization of the control strategy by directly using the real-time data of the external sensors of the wind turbine to dynamically adjust the control parameters and the logic judgment threshold. It ensures that the wind turbine can quickly adapt to the changes in the external environment, such as the fluctuations of natural factors such as wind speed, wind direction, temperature, and the changes of human or non-human factors such as power grid demand and equipment aging. Compared with the traditional static control strategy, the present invention significantly improves the response speed and flexibility of the control system, effectively avoids the problem of inaccurate control caused by the mismatch between the control parameters and the actual operating environment, thereby reducing equipment failures and downtime caused by control errors, and extending the service life of the wind turbine. Secondly, the parallel operation controller introduced in the present invention is an auxiliary tool, and its core value lies in being able to operate independently of the main control system, and based on big data analysis and machine learning algorithms, deeply mine and intelligently analyze massive operating data, so as to accurately calculate the optimal control parameters and logic judgment thresholds. In this process, the parallel operation controller not only takes into account the current operating status of the unit, but also combines historical data and future predictions to achieve the foresight and predictability of the control strategy. This data-based intelligent decision-making method effectively overcomes the limitations of idealized simulation conditions in the design stage and the subjectivity of the design engineer's personal experience, making the setting of control parameters closer to actual operation requirements and greatly improving control accuracy and efficiency. Furthermore, the application of parallel operation controllers also promotes the safety and stability of wind turbine operation. By real-time monitoring and analysis of the unit's operating status, the parallel controller can promptly detect and warn of potential fault risks, such as bearing overheating, blade imbalance, etc., providing a valuable time window for operation and maintenance personnel to carry out preventive maintenance, effectively reducing the probability of sudden failures, and ensuring the continuous and stable operation of the wind farm. At the same time, through the dynamic adjustment of control parameters, the present invention can also maximize the use of wind energy resources, improve the power generation efficiency and output power of the unit, reduce the hidden power generation loss caused by improper control, and bring significant economic benefits to the wind farm under the premise of ensuring safety. In addition, the large storage space equipped with the parallel operation controller provides rich data support for the refined control of wind turbines. By storing and analyzing historical data, we can establish more complete equipment health monitoring models, performance evaluation models, and fault prediction models, providing a scientific basis for long-term planning, equipment upgrades, and operation and maintenance optimization of wind farms. This data-driven management method not only improves the operational efficiency of wind farms, but also promotes the continuous advancement and innovative development of wind power technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are for illustrative purposes only and are not intended to limit the scope of the present disclosure in any way. In the drawings: Figure 1 It is a flow chart of a data-based wind turbine parallel auxiliary control method of the present invention; Figure 2 A control process schematic diagram of a data-based wind turbine parallel auxiliary control method of the present invention; Figure 3 A schematic diagram of a calculation flow in an embodiment of a data-based wind turbine parallel auxiliary control method of the present invention; Figure 4 It is a structural schematic diagram of a data-based wind turbine parallel auxiliary control system of the present invention; Figure 5 Schematic diagram of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the present invention will be clearly and completely described below in conjunction with the drawings in the present invention. The described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present invention.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0020] Aiming at the problem that the control parameters and judgment logic thresholds of the units based on the operating environment in the prior art cannot be updated, and the main control program can only be refreshed by shutting down each unit one by one. The present invention provides a data-based parallel auxiliary control method for wind turbines, such as Figure 1 As shown, the method includes: S100: The wind turbine controller PLC receives data from external sensors of the wind turbine; S200: preprocessing the received sensor data and the algorithm logic variables inside the wind turbine controller PLC to obtain preprocessed data; S300: extracting feature data based on the preprocessed data; S400: Calculate the recommended threshold value according to the characteristic data, send the calculated threshold value to the wind turbine controller PLC, and the wind turbine controller PLC performs a new round of calculation according to the threshold value to generate a control instruction CO; S500: The wind turbine generator system performs control movement according to the control instruction CO.

[0021] The present invention directly updates the control parameters and logic judgment thresholds in real time through the actual unit operation data, thereby avoiding the occurrence of inaccurate control and greater risk events caused by the mismatch between the actual unit operation and the control parameters.

[0022] The present invention is further explained below in conjunction with the specific drawings.

[0023] like Figure 2 As shown, the present invention provides a data-based wind turbine parallel auxiliary control method, comprising: S1: The wind turbine controller PLC receives data CI_sensor (external sensor data) provided by external sensors such as the vibration monitoring system, pitch control system, current conversion system, load monitoring system, temperature monitoring system, blade clearance monitoring system, and laser radar in the wind turbine, for example, sensor data with a period of 20ms; Specifically, the wind turbine controller PLC, as the brain of the entire wind turbine, is used to process real-time data from various subsystems to ensure stable operation and performance optimization of the wind turbine.

[0024] Vibration monitoring systems are used to collect data through vibration sensors installed in different parts of wind turbines to detect abnormal vibrations during wind turbine operation. This data is crucial for preventive maintenance and can help identify potential mechanical failures such as bearing damage or blade imbalance.

[0025] The pitch system is used to control the angle of the wind turbine blades to adjust the amount of wind energy captured and keep the wind turbine operating within a safe range. The wind turbine controller PLC receives data from the pitch system, including blade position, pitch speed, and system status information, which are critical for the power regulation and emergency shutdown strategy of the wind turbine.

[0026] The inverter system is responsible for converting the AC power generated by the wind turbine into a form of electrical energy suitable for transmission to the power grid. The wind turbine controller PLC monitors the status of the inverter, including key parameters such as voltage, current, and frequency, to ensure the quality and stability of power output.

[0027] The load monitoring system is used to measure various mechanical loads on wind turbines, such as the bending stress of the tower, the torque of the main shaft and the force of the blades. These data help to evaluate the structural integrity and life of the wind turbine and perform necessary load management.

[0028] Temperature monitoring systems are distributed in various key parts of wind turbines, such as generators, gearboxes and bearings, to monitor their operating temperatures. Excessive temperatures may be a precursor to equipment failure, so this data is critical to preventing overheating and planning maintenance strategies.

[0029] Blade clearance monitoring systems are used to monitor the distance between blades and the surrounding environment using laser sensors or other technologies, especially in areas with complex terrain or many obstacles. This data helps avoid collision accidents and ensure the safe operation of wind turbines.

[0030] LiDAR is used to measure key parameters such as wind speed and direction, and provide them to the wind turbine controller PLC for analysis. These data can optimize the operation strategy of wind turbines, improve energy capture efficiency, and predict the changing trend of wind energy resources.

[0031] After receiving the above data, the wind turbine controller PLC will process and analyze them in real time.

[0032] S2: The current external sensor data CI_sensor (external sensor data) received by the PLC and the algorithm logic variable CS_state (PLC internal algorithm logic variable) of the previous operation cycle inside the wind turbine controller PLC are transferred to the operation data preprocessing unit for sliding average. The sliding average of different time parameters is performed according to actual needs. For example, the wind speed can be averaged according to 1 minute, and the blade root load can be averaged according to 1 second to obtain CI_sensor_avg and CS_state_avg; Specifically, data directly obtained from sensors may contain noise and fluctuations, especially for parameters that are easily affected by the environment, such as wind speed. In addition, different sensors may have different sampling rates and data formats. Therefore, it is necessary to perform appropriate preprocessing steps before the data is used for any control decision. This can not only improve the quality of the data, but also improve the effectiveness of subsequent data analysis and control strategies.

[0033] In this step, by sliding the data, short-term fluctuations can be smoothed and more meaningful trend information can be extracted. For example, wind speed data may be collected at very short time intervals (such as a few seconds), but in order to reflect more stable wind conditions, you can choose to perform a 1-minute sliding average on it. Similarly, for data such as blade root load that may contain high-frequency vibrations, a 1-second sliding average may be a more appropriate choice. The window size used for the sliding average can be selected based on the physical characteristics and control requirements of the specific parameters. For parameters that require a quick response, a shorter window should be used; for scenarios that require higher stability, a longer window can be used.

[0034] Secondly, the pre-processing unit can also integrate data from different sources to form a unified and synchronized data set, which is convenient for comprehensive analysis and decision-making. In order to meet the processing requirements of the wind turbine controller PLC, the pre-processing unit also needs to convert data of different formats and dimensions into a standard form.

[0035] Before sliding average, the preprocessing unit should also clean the data, remove or correct outliers to avoid affecting the final control decision. Considering the dynamic changes in the wind energy environment, the preprocessing process must be fast enough to ensure that the processed data can reflect the status of the wind turbine in real time. The processed data (CI_sensor_avg and CS_state_avg) will be used in advanced control algorithms of wind turbines, such as adaptive control, fault detection and recovery strategies, life management, etc. Because these data have been properly preprocessed, they can more accurately represent the actual operating conditions, thereby helping the controller make more informed decisions and improving the overall performance and reliability of the wind turbine.

[0036] Through such a data preprocessing process, not only the adaptability of wind turbines to environmental changes is enhanced, but also a solid foundation is provided for the development of data analysis, machine learning model training and decision support systems in the wind energy industry.

[0037] S3: CI_sensor_avg and CS_state_avg are transferred to the operation data processing unit for further conversion, such as table lookup, that is, CI_sensor_avg_lookup and CS_state_avg_lookup are obtained by interpolation based on the set two-dimensional parameter table according to CI_sensor_avg and CS_state_avg. For example, the rate of change is obtained by dividing the difference between CI_sensor_avg at the previous moment and CI_sensor_avg at the current moment by the operation cycle or the difference between CS_state_avg at the previous moment and CS_state_avg at the current moment by the operation cycle to obtain CI_sensor_avg_rate or CS_state_avg_rate. For example, time accumulation is obtained by starting to accumulate time when CS_state_avg or CI_sensor_avg exceeds a certain threshold Threshold to obtain CS_state_avg_timer or CI_sensor_avg_timer; Specifically, in the advanced control strategy of wind turbines, it is not enough to simply perform basic sliding average processing on sensor data and the internal state of the wind turbine controller PLC. In order to achieve more sophisticated and intelligent control decisions, these initially processed data need to be further processed and analyzed. This includes functions such as table lookup interpolation based on two-dimensional parameter tables established based on experience or historical data, calculation of parameter change rates, and time accumulation for specific conditions.

[0038] Table lookup interpolation is a method based on a predefined two-dimensional parameter table to find and interpolate more accurate or more suitable values ​​for control decisions based on the current CI_sensor_avg and CS_state_avg. It can help the controller PLC understand the optimal operating state of the wind turbine under the current working conditions.

[0039] CI_sensor_avg_lookup is used to interpolate the corresponding reference wind speed at the best power generation efficiency for certain parameters, such as wind speed. This processing method enables the wind turbine to respond to changes in wind speed more effectively and optimize its operating status.

[0040] CS_state_avg_lookup is used to process the internal state of the PLC. The table interpolation can be used to determine the target output power or other key control parameters of the wind turbine under given operating conditions.

[0041] Monitoring the rate of change of parameters over time is critical to identifying sudden changes in the wind energy environment and equipment status. The rate of change can be calculated by comparing the parameter value at the current moment with the previous moment.

[0042] CI_sensor_avg_rateThe rate of change of wind speed can indicate the fluctuation of wind energy resources and help the controller to adjust the operation strategy of wind turbines in time.

[0043] CS_state_avg_rate: Similarly, the rate at which the PLC's internal state changes can reflect how fast the system responds, such as the update rate of control instructions.

[0044] In some cases, such as equipment maintenance or fault diagnosis, it is necessary to record the duration of a specific event. This requires the system to have the ability to start timing when a specific threshold is reached and stop timing when the condition returns to normal range.

[0045] CS_state_avg_time is the time the system starts to accumulate when the temperature of a critical component exceeds the preset threshold. This is crucial for predicting maintenance cycles and preventing potential overheating damage.

[0046] CI_sensor_avg_timer Some external environmental parameters, such as the duration of extreme wind speed events, can also be monitored in this way. This helps to assess the wind turbine's ability to withstand extreme conditions and develop corresponding countermeasures.

[0047] Combining these characteristic data (CI_sensor_avg_lookup, CS_state_avg_lookup, CI_sensor_avg_rate, CS_state_avg_rate, CS_state_avg_timer, CI_sensor_avg_timer) can provide more comprehensive and accurate information support for the control decision of the wind turbine. For example, by combining the table interpolation results of wind speed and its rate of change, the controller can more intelligently adjust the operating state of the wind turbine to achieve higher energy capture efficiency and lower equipment wear. At the same time, by monitoring the rate and duration of change of key state parameters, the system can obtain important insights into the health status and maintenance needs of the equipment.

[0048] S4: Calculate the algorithm parameters of the recommended threshold according to the specific algorithm; Specifically, specific algorithms, such as machine learning algorithms, statistical analysis methods, etc., are used to calculate recommended setting thresholds and algorithm parameters.

[0049] S5: The calculated setting threshold and algorithm parameters are transmitted to the PLC to replace the original parameters; Specifically, after completing the calculation of the recommended thresholds and algorithm parameters, these parameters need to be safely and accurately transmitted to the wind turbine controller PLC. While ensuring the accuracy and real-time nature of data transmission, it is also necessary to consider various problems that may arise during the parameter update process, such as data loss and transmission errors. In addition, when replacing the original parameters, verification should be performed first to ensure that the new parameters will not cause system instability or performance degradation.

[0050] S6: The wind turbine controller PLC uses this set threshold and algorithm parameters to perform a new round of operation calculations and gives a control instruction CO; Specifically, after the wind turbine controller PLC receives the new set thresholds and algorithm parameters, it will perform a new round of operation calculations based on these parameters. This process involves the processing and analysis of real-time data, as well as real-time monitoring and adjustment of the wind turbine operating status. The wind turbine controller PLC calculates the control instructions CO based on the new parameters and real-time data. These instructions are designed to make the wind turbine as close to the ideal operating state as possible while ensuring the safety and stability of the equipment.

[0051] S7: Control command CO is given to the actuator to perform actions, such as pitch change, yaw, and torque; Specifically, the control command CO calculated by the wind turbine controller PLC will be sent to the wind turbine's actuators, such as the pitch system, yaw system, and torque control system, to adjust the specific operating status of the wind turbine. For example, the pitch angle of the blades is adjusted according to changes in wind speed to optimize wind energy capture; or the direction of the wind turbine is adjusted according to changes in wind direction to ensure that the wind turbine is always aligned with the wind direction to maximize power generation efficiency. In addition, the control command CO may also include adjusting the torque of the generator to adapt to real-time changes in wind energy resources.

[0052] S8: Synchronizes and stores all data obtained in S4 in the storage unit, and can be set to clear data monthly, quarterly or annually as required; The present invention is further explained in conjunction with specific embodiments.

[0053] Example like Figure 3 As shown in the figure, the specific calculation process is explained by taking the optimal pitch control in the transition section as an example: S1: The wind turbine controller PLC receives the real-time data of blade root load CI_sensor1, CI_sensor2, CI_sensor3 (20ms cycle) provided by the load monitoring system; S2: CI_sensor1, CI_sensor2, CI_sensor3 and the optimal pitch position CS_state = 0.5 degrees of the algorithm logic variable of the previous operation cycle in the PLC are transferred to the operation data preprocessing unit for sliding average. To prevent the optimal pitch position from changing frequently, the blade root load is averaged according to 1 second to obtain CI_sensor1_avg, CI_sensor2_avg and CI_sensor3_avg. The optimal pitch position is currently a constant and does not require sliding average, that is, CS_state = CS_state_avg = 0.5 degrees; S3: CI_sensor1_avg, CI_sensor2_avg, CI_sensor3_avg and CS_state_avg are transferred to the operation data processing unit for further conversion. CI_sensor1_avg, CI_sensor2_avg and CI_sensor3_avg represent the root loads of the three blades respectively. Since different blades are located at different impeller azimuths, their root loads are also different at the same time. Therefore, the average method is taken to represent the overall force condition of the impeller. Since the wind conditions are changing in real time, in order to ensure the stability of the overall algorithm, when the average value of the root load of the three blades is greater than the set threshold Threshold5 seconds, the accumulated time is used to obtain CI_sensor_avg_timer; since the wind turbine impeller force is complex and changeable due to the failure to change the pitch and insufficient torque control near the rated wind speed of the wind turbine, it is easy to cause extreme load conditions. Here, the average value of the root load represents the force on the impeller. When the force exceeds a certain threshold, it means that the unit is in a more dangerous state. It is necessary to adjust the optimal pitch angle in time, and release the bending moment accumulated at the root of the blade by increasing the pitch angle, so as to avoid excessive force on the impeller through aerodynamic adjustment of the blades. However, due to the different temperatures throughout the year, the optimal pitch angle is also different, and the root load force is different. Maintaining the optimal pitch angle cannot ensure that the root load is instantaneously under the design load under extreme wind conditions. Therefore, the optimal pitch angle is controlled by the root load to achieve the release and retraction of the wind wheel energy and ensure the safe operation of the unit.

[0054] S4: If the average root load of the three blades (CI_sensor1_avg+CI_sensor2_avg+CI_sensor3_avg) / 3 is less than the set threshold Threshold, CO=0.5 degrees remains unchanged; S5: If the average root load of the three blades (CI_sensor1_avg+CI_sensor2_avg+CI_sensor3_avg) / 3 is greater than the set threshold Threshold, and the cumulative time CI_sensor_avg_timer is less than or equal to 5 seconds, CO=0.5 degrees remains unchanged; S6: If the average root load of the three blades (CI_sensor1_avg+CI_sensor2_avg+CI_sensor3_avg) / 3 is greater than the set threshold Threshold, and the accumulated time CI_sensor_avg_timer is greater than 5 seconds, CO=0.5 degrees is updated to 1.5 degrees; S7: Control command CO=1.5 degrees is given to the pitch actuator to perform pitch action; S8: Synchronously store the data in the above operation process, accumulate historical data in the function storage area, analyze whether the Threshold value and the 5-second value are reasonable on a quarterly basis, and provide setting values ​​under different temperature conditions in different quarters. After one year of operation, the data in the function storage area is cleared and the function operation data continues to be stored.

[0055] In summary, the embodiments of the present invention provide a data-based parallel auxiliary control method and system for wind turbines, which innovatively assists in updating control parameters and logic judgment thresholds by setting a parallel operation controller, effectively matches control parameters with the changing unit operating environment through algorithms, and matches the real operating environment through a large amount of actual operating data, thereby avoiding idealized simulation conditions and personal experience of design engineers in the design stage, and more objectively and practically matches control parameters from actual environmental conditions, thereby avoiding unsafe events and waste of hidden power generation caused by mismatch between the operating environment and control parameters. At the same time, since the parallel operation controller can be equipped with a large storage space, it provides a data foundation for the refined control of wind turbines.

[0056] In summary, the present invention directly uses actual unit operation data to update control parameters and logic judgment thresholds in real time, avoiding inaccurate control and greater risk events caused by insufficient simulation conditions, inaccurate models, and mismatch between actual unit operation and control parameters.

[0057] The present invention is based on the design of a parallel controller, which synchronously performs batch real-time analysis of operating data, better helps the main control loop to make control decisions based on actual operating data, and truly realizes one policy for one machine.

[0058] The present invention is different from traditional SCADA and centralized monitoring (minutes or seconds) in data granularity and precision (milliseconds), and supports intelligent and refined control of wind turbines with finer data granularity. It makes control decisions suitable for local environmental conditions based on external sensor input data and wind turbine controller's own variables, reducing load and increasing power generation.

[0059] The parallel controller proposed in the present invention has a powerful data storage capacity. Compared with the traditional PLC, its storage unit can store a large amount of wind turbine operating data, providing a solid basis for regularly updating the control strategy. The parallel controller and the main controller operate and are powered independently, ensuring that the normal operation of the main controller will not be interfered with when a fault occurs. The invention uses the real-time operation data of the unit to calculate the control parameters and logic judgment thresholds that are more suitable for local environmental conditions through advanced algorithms, covering all external sensors and millisecond-level variables involved in logic control inside the PLC. In the data preprocessing stage, a variety of calculation methods such as sliding average and time accumulation are used to meet the needs of different algorithms. The independent storage area supports operators to conduct refined analysis, lays a data foundation for intelligent control, and realizes multi-dimensional post-evaluation of the entire life cycle of wind turbines. In addition, the software and hardware framework of the present invention is highly scalable. The calculation process taking the optimal pitch control of the transition section as an example can be easily extended to all algorithms that require real-time changes in control parameters and logic judgment thresholds based on operating data. The operating data, main computing unit and storage unit can all be customized and expanded according to actual needs, and the operating data records can be uploaded to the wind farm SCADA system or centralized monitoring system on a periodic basis, realizing the intelligent and efficient control of wind turbines.

[0060] The second object of the present invention is to provide a data-based wind turbine parallel auxiliary control system, such as Figure 4 As shown, including: Data receiving module 101: used for the wind turbine controller PLC to receive data from external sensors of the wind turbine; The preprocessing data module 201 is used to preprocess the received sensor data and the algorithm logic variables inside the wind turbine controller PLC to obtain preprocessed data; Feature extraction module 301: used to extract feature data based on the preprocessed data; Generate instruction module 401: used to calculate the recommended setting threshold value according to the characteristic data, and send the calculated setting threshold value to the wind turbine controller PLC. The wind turbine controller PLC performs a new round of calculation according to the threshold value and generates a control instruction CO; Control motion module 501: used for the wind turbine to perform control motion according to the control instruction CO.

[0061] like Figure 5As shown, the third object of the present invention is to provide an electronic device, the electronic device comprising: a processor 601, a memory 602 and a display screen 603. Among them, the memory 602 and the display screen 603 are connected to the processor 601, such as through a bus 604. Optionally, the electronic device may also include a transceiver 605. It should be noted that in actual applications, the transceiver 605 is not limited to one, and the structure of the electronic device does not constitute a limitation on the embodiments of the present application.

[0062] Processor 601 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 601 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0063] The bus 604 may include a path to transmit information between the above components. The bus 604 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus 604 may be divided into an address bus, a data bus, a control bus, etc.

[0064] The memory 602 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0065] The memory 602 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 601. The processor 601 is used to execute the application code stored in the memory 602 to implement the content shown in the above method embodiment.

[0066] Figure 5 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0067] The fourth object of the present invention is to provide a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program is stored thereon, and when the program is executed by a processor, the aforementioned Figure 1 The various processes of the method embodiment shown in the figure include, for example, a memory including instructions, and the instructions can be executed by a processor of an electronic device to complete the method.

[0068] A computer-readable storage medium may be a tangible device that holds and stores instructions used by an instruction execution device. A computer-readable storage medium may be, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination thereof. Specifically, a computer-readable storage medium may be a portable computer disk, a hard disk, a USB flash drive, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a lectern random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, an optical disk, a magnetic disk, a mechanical encoding device, and any combination thereof.

[0069] A fifth object of the present invention is to provide a computer program product, comprising computer instructions, which, when executed by a processor, implement the above Figure 1 The various processes of the method embodiment shown can achieve the same technical effect, and will not be described again here to avoid repetition.

[0070] Many embodiments and many applications beyond the examples provided will be apparent to those skilled in the art upon reading the above description. Therefore, the scope of the present teachings should not be determined with reference to the above description, but rather with reference to the preceding claims and the full scope of equivalents to which such claims are entitled. For the purpose of comprehensiveness, all articles and references, including disclosures of patent applications and publications, are incorporated herein by reference. The omission of any aspect of the subject matter disclosed herein in the preceding claims is not intended to be a disclaimer of such subject matter, nor should it be considered that the applicants did not consider such subject matter to be part of the disclosed inventive subject matter.

[0071] The above content is a further detailed description of the present invention. It cannot be determined that the specific implementation methods of the present invention are limited to these. For ordinary technicians in the technical field to which the present invention belongs, without departing from the concept of the present invention, they can also make several simple deductions or substitutions, which should be regarded as belonging to the protection scope of the present invention determined by the submitted claims.

Claims

1. A data-based wind turbine parallel auxiliary control method, characterized in that: include: The wind turbine controller PLC receives data from external sensors of the wind turbine; Preprocess the received sensor data with the algorithm logic variables inside the wind turbine controller PLC to obtain preprocessed data; Extract feature data based on the preprocessed data; The recommended threshold value is calculated based on the characteristic data, and the calculated threshold value is sent to the wind turbine controller PLC. The wind turbine controller PLC performs a new round of calculation based on the threshold value and generates a control instruction CO; The wind turbine performs control movements according to the control command CO.

2. A data-based wind turbine parallel auxiliary control method according to claim 1, characterized in that: The wind turbine controller PLC receives data from external sensors of the wind turbine, including: Collect external sensor data of the vibration monitoring system, pitch control system, current conversion system, load monitoring system, temperature monitoring system, blade clearance monitoring system, and lidar in the wind turbine to form the data of the external sensors of the wind turbine; The data from the wind turbine external sensors are received by the wind turbine controller PLC.

3. The data-based wind turbine parallel auxiliary control method according to claim 1, characterized in that: The received sensor data is preprocessed with the algorithm logic variables in the wind turbine controller PLC to obtain the preprocessed data, including: The wind turbine controller PLC receives the data from the external sensors of the wind turbine and the algorithm logic variables inside the wind turbine controller PLC, performs sliding average preprocessing, and obtains preprocessed data.

4. The data-based wind turbine parallel auxiliary control method according to claim 1, characterized in that: The extracting of feature data based on the preprocessed data includes: The preprocessed data is converted and feature data is extracted; The characteristic data includes CI_sensor_avg_lookup, CS_state_avg_lookup, CI_sensor_avg_rate, CS_state_avg_rate, CS_state_avg_timer and CI_sensor_avg_time.

5. The data-based wind turbine parallel auxiliary control method according to claim 1, characterized in that: The method of calculating the recommended threshold value according to the characteristic data and sending the calculated threshold value to the controller PLC, the wind turbine controller PLC performs a new round of calculation according to the threshold value and generates a control instruction CO, including: Calculate the recommended setting threshold based on the characteristic data; Send the calculated set thresholds and algorithm parameters to the wind turbine controller PLC, and replace the original thresholds and parameters in the wind turbine controller PLC; The wind turbine controller PLC calculates the control instruction CO based on the calculated set thresholds and algorithm parameters.

6. The data-based wind turbine parallel auxiliary control method according to claim 1, characterized in that: The wind turbine set performs control movement according to the control instruction CO, including: The actuator in the wind turbine performs pitch, yaw and torque movements according to the control command CO; Among them, the data obtained from pitch, yaw and torque movement are fed back to the wind turbine controller PLC through the external sensors of the wind turbine.

7. A data-based wind turbine parallel auxiliary control system, characterized in that: include: Data receiving module: used for the wind turbine controller PLC to receive data from external sensors of the wind turbine; Preprocessing data module: used to preprocess the received sensor data with the algorithm logic variables inside the wind turbine controller PLC to obtain preprocessed data; Feature extraction module: used to extract feature data based on preprocessed data; Generate instruction module: used to calculate the recommended threshold value according to the characteristic data, send the calculated threshold value to the wind turbine controller PLC, and the wind turbine controller PLC performs a new round of calculation according to the threshold value and generates the control instruction CO; Control motion module: used for wind turbines to perform control motion according to the control command CO.

8. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of a data-based wind turbine parallel auxiliary control method as claimed in any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the data-based wind turbine parallel auxiliary control method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that It comprises computer instructions, which, when executed by a processor, implement the steps of a data-based wind turbine parallel auxiliary control method as claimed in any one of claims 1 to 6.

Images