Dedicated programmable controller for wind power generation control

Abstract

This application discloses a dedicated programmable controller for wind power generation control. The controller includes: an input interface for receiving wind speed values, pitch angles, and wind turbine generator speed values ​​at multiple predetermined time points; a memory for storing input vectors corresponding to the wind speed, pitch angle, and speed values; a central processing unit for calculating the full parameter correlation matrix and full-state posterior vectors corresponding to the wind speed, pitch angle, and speed input vectors, and calculating the current pitch angle and speed control value through logistic regression; and an output interface for outputting the pitch angle and speed control value to the relevant turbine control module. This controller can control the wind turbine generator speed based on the calculated pitch angle and speed control value at the current moment, improving the safety and adaptability of wind power generation.

Description

Technical Field

[0001] This application relates to the field of wind power generation technology, and more specifically, to a dedicated programmable controller for wind power generation control. Background Technology

[0002] Currently, wind power has become one of the main power generation methods, and the reasonable control of wind turbine generators to ensure the operation of wind power generation is attracting increasing attention.

[0003] In related technologies, the power generation control strategy for wind turbines, based on the rated wind speed, can include: when the wind speed is lower than the rated wind speed, torque control is used to maximize the power coefficient, i.e., the energy captured by the wind turbine. Among these, pitch control is one of the main means of wind turbine operation control, and it has significant characteristics such as aerodynamic nonlinearity, frequent operating condition switching, and numerous disturbance factors.

[0004] However, in the actual control of pitch control systems, the speed regulation and power output fluctuate greatly due to the interference of factors such as the uncertainty and volatility of wind speed, resulting in a large impact and load on the variable speed wind turbine generator set, which cannot be avoided by the wind power generation control methods in related technologies.

[0005] Therefore, there is an urgent need for an optimized wind power generation control scheme that can ensure the normal and safe operation of wind power generation in practical applications. Summary of the Invention

[0006] This application aims to at least partially address one of the technical problems in the related art.

[0007] To address the aforementioned technical problems, the first objective of this application is to provide a dedicated programmable controller for wind power generation control. This controller can control the speed of the wind turbine generator set based on the calculated pitch angle speed control value at the current moment, thereby improving the safety and adaptability of wind power generation.

[0008] The second objective of the application is to propose a method for controlling wind power generation.

[0009] According to one aspect of this application, a dedicated programmable controller for wind power generation control is provided, comprising:

[0010] The input interface is used to receive wind speed values, pitch angle, and wind turbine rotation speed values ​​at multiple predetermined time points.

[0011] The memory is used to store the wind speed input vector corresponding to the wind speed value, the pitch angle input vector corresponding to the pitch angle, and the rotational speed input vector corresponding to the rotational speed value.

[0012] The central processing unit is used to calculate the full parameter correlation matrix and full state posterior vector corresponding to the wind speed input vector, the pitch angle input vector and the speed input vector, and to calculate the current pitch angle speed control value through logistic regression based on the full parameter correlation matrix and the full state posterior vector.

[0013] The output interface is used to output the pitch angle and speed control values ​​to the relevant unit control module.

[0014] Optionally, in the above-mentioned dedicated programmable controller for wind power generation control, the central processing unit includes: a calculation unit and a logic regression unit, wherein the calculation unit is configured to: multiply the speed input vector by the wind speed input vector to obtain a speed-wind speed correlation parameter matrix; multiply the speed input vector by the pitch angle input vector to obtain a speed-pitch angle correlation parameter matrix; multiply the wind speed input vector by the pitch angle input vector to obtain a wind speed-pitch angle correlation parameter matrix; and fuse the speed-wind speed correlation parameter matrix, the speed-pitch angle correlation parameter matrix, and the wind speed... - Obtain the full parameter correlation matrix by generating the pitch angle correlation parameter matrix; convert the speed input vector, wind speed input vector, and pitch angle input vector into binary distributed speed state vectors, wind speed state vectors, and pitch angle state vectors, respectively; calculate the full-state posterior vectors of the speed state vectors, wind speed state vectors, and pitch angle state vectors using a Bayesian probability model; multiply the full parameter correlation matrix by the full-state posterior vectors to obtain the posterior feature vectors; the logistic regression unit is used to perform logistic regression on the posterior feature vectors to obtain the pitch angle speed control value.

[0015] Optionally, in the above-mentioned dedicated programmable controller for wind power generation control, the computing unit is specifically used to add the rotational speed-wind speed correlation parameter matrix, the rotational speed-pitch angle correlation parameter matrix, and the wind speed-pitch angle correlation parameter matrix through an array adder to obtain the full parameter correlation matrix.

[0016] Optionally, in the above-mentioned dedicated programmable controller for wind power generation control, the calculation unit includes: a state vector conversion subunit, used to input the rotational speed input vector, the wind speed input vector and the pitch angle input vector into multiple parallel switches based on a predetermined threshold, respectively, to obtain the corresponding rotational speed state vector, the wind speed state vector and the pitch angle state vector.

[0017] Optionally, in the above-mentioned dedicated programmable controller for wind power generation control, all of the plurality of parallel switches have the same control threshold, or each of the switches has an independent control threshold.

[0018] Optionally, in the aforementioned dedicated programmable controller for wind power generation control, the threshold of each of the plurality of parallel switches is the product of its own independent control threshold and a common basic control threshold.

[0019] Optionally, the dedicated programmable controller for wind power generation control described above further includes: a first intermediate value vector calculation subunit, used to input the rotational speed state vector and the wind speed state vector into a parallel AND gate to obtain a first intermediate value vector; a second intermediate value vector calculation subunit, used to input the pitch angle state vector into a parallel NOT gate to obtain a second intermediate value vector; and a posterior vector calculation subunit, used to input the first intermediate value vector and the second intermediate value vector into a parallel AND gate to obtain the full-state posterior vector.

[0020] Optionally, in the above-mentioned dedicated programmable controller for wind power generation control, the logic regression unit is specifically used to input the posterior feature vector into a parallel multiplier and adder to obtain the pitch angle speed control value.

[0021] Optionally, in the above-mentioned dedicated programmable controller for wind power generation control, in the parallel multiplier, each multiplier has an independent weight value and the sum of the weight values ​​of all the multipliers in the parallel multiplier is 1, and the weight values ​​of each multiplier in the parallel multiplier are equal.

[0022] According to another aspect of this application, a wind power generation control method is also provided, comprising:

[0023] Receives wind speed, pitch angle, and wind turbine rotation speed values ​​at multiple predetermined time points;

[0024] Store the wind speed input vector corresponding to the wind speed value, the pitch angle input vector corresponding to the pitch angle, and the rotational speed input vector corresponding to the rotational speed value;

[0025] Calculate the full parameter correlation matrix and full state posterior vector corresponding to the wind speed input vector, the pitch angle input vector, and the speed input vector, and calculate the current pitch angle speed control value through logistic regression based on the full parameter correlation matrix and the full state posterior vector;

[0026] The pitch angle and speed control values ​​are output to the relevant unit control module.

[0027] The dedicated programmable logic controller (PLC) for wind power generation control provided in this application offers at least the following advantages: This dedicated PLC includes components such as input interfaces, output interfaces, memory, and a central processing unit. Considering that wind power generation control is related to wind speed, pitch angle, and rotational speed, this dedicated PLC fully leverages the synergy and correlation information between wind speed, pitch angle, and rotational speed to obtain pitch angle and rotational speed control values. Based on these values, the rotational speed of the wind turbine is controlled, ensuring that the adjusted rotational speed is suitable for the current operating conditions. This reduces the impact on the wind turbine, ensuring that the expected power generation demand is met while also guaranteeing the normal and safe operation of the wind turbine, thus improving the safety and adaptability of wind power generation. Attached Figure Description

[0028] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0029] Figure 1 A schematic diagram of the structure of a dedicated programmable controller for wind power generation control is provided in an embodiment of this application;

[0030] Figure 2 A schematic diagram of the structure of a central processing unit provided in an embodiment of this application;

[0031] Figure 3 A schematic diagram of the structure of a specific programmable controller for wind power generation control provided in this application embodiment;

[0032] Figure 4 This is a schematic diagram illustrating the data interaction between modules in a dedicated programmable controller provided in an embodiment of this application.

[0033] Figure 5 A schematic diagram illustrating an application scenario of a dedicated programmable controller for wind power generation control, provided in an embodiment of this application;

[0034] Figure 6 A flowchart of a wind power generation control method provided in this application embodiment;

[0035] Figure 7 This is a flowchart illustrating a specific operation method of a dedicated programmable controller for wind power generation control, provided as an embodiment of this application. Detailed Implementation

[0036] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0037] It should be noted that in the actual control of pitch control systems, due to the uncertainty and fluctuation of wind speed, the speed regulation and power output fluctuate significantly, resulting in substantial impacts and loads on variable-speed wind turbine generators. Therefore, an optimized wind power generation control scheme is desired.

[0038] In the embodiments of this application, considering the special requirements of offshore wind turbines for control robustness and stability, a programmable logic controller (PLC) is selected as the speed and power controller. However, most current related technologies use foreign general-purpose PLC equipment, and the main research focus is on the wiring control system between PLC modules and field equipment. This fails to achieve controllability based on the data, algorithms, and control flow within the PLC module, and the optimization of algorithms and control processes based on this cannot be applied to the control of wind turbine generator sets. Therefore, this application proposes a dedicated programmable controller for wind power generation control to solve the problems existing in related technologies.

[0039] Specifically, in the embodiments of this application, considering that wind power generation control is related to wind speed, pitch angle and rotational speed, when designing a dedicated programmable controller to adaptively control the rotational speed of the wind turbine, the main focus is on the coordination and correlation between the above data.

[0040] The following describes in detail, with reference to the accompanying drawings, the dedicated programmable controller and method for wind power generation control proposed in the embodiments of this application.

[0041] Figure 1 A schematic diagram of a dedicated programmable controller for wind power generation control is provided as an embodiment of this application, as shown below. Figure 1 As shown, the programmable controller includes: an input interface 100, a memory 200, a central processing unit 300, and an output interface 400.

[0042] The input interface 100 is used to receive wind speed values, pitch angles, and wind turbine rotation speed values ​​at multiple predetermined time points.

[0043] Specifically, in the technical solution of this application, the wind speed values ​​at multiple predetermined time points within a predetermined time period are first received from the wind speed sensor through the input interface of the programmable logic controller, the pitch angle at multiple predetermined time points within the predetermined time period is received from the angle sensor, and the rotational speed values ​​of the wind turbine generator set at multiple predetermined time points within the predetermined time period are received from the rotational speed monitor.

[0044] The memory 200 is used to store the wind speed input vector corresponding to the wind speed value, the pitch angle input vector corresponding to the pitch angle, and the rotational speed input vector corresponding to the rotational speed value.

[0045] Specifically, the wind speed, pitch angle, and rotational speed values ​​at the aforementioned multiple predetermined time points are stored in the memory of a dedicated programmable controller. As one possible implementation, the numerical column vectors of the wind speed values ​​at the multiple predetermined time points, the numerical column vectors of the pitch angles at the multiple predetermined time points, and the numerical column vectors of the rotational speed values ​​of the wind turbine generator at the multiple predetermined time points are stored in the memory registers for easy subsequent data retrieval and calculation.

[0046] The central processing unit 300 is used to calculate the full parameter correlation matrix and full state posterior vector corresponding to the wind speed input vector, pitch angle input vector and speed input vector, and calculate the current pitch angle and speed control value through logistic regression based on the full parameter correlation matrix and full state posterior vector.

[0047] To more clearly illustrate the specific implementation process of the central processing unit 300 calculating the pitch angle and speed control value in the embodiments of this application, a specific central processing unit is provided as an example in the embodiments of this application below. Figure 2 A schematic diagram of a central processing unit provided in an embodiment of this application is shown below. Figure 2 As shown, the central processing unit 300 includes a computing unit 310 and a logic regression unit 320.

[0048] In this embodiment, when the central processing unit 300 calculates the pitch angle and rotational speed control value, it first performs the following operations through the calculation unit 310:

[0049] Multiplying the rotational speed input vector by the wind speed input vector yields the rotational speed-wind speed correlation parameter matrix; multiplying the rotational speed input vector by the pitch angle input vector yields the rotational speed-pitch angle correlation parameter matrix; and multiplying the wind speed input vector by the pitch angle input vector yields the wind speed-pitch angle correlation parameter matrix. Then, the rotational speed-wind speed correlation parameter matrix, the rotational speed-pitch angle correlation parameter matrix, and the wind speed-pitch angle correlation parameter matrix are fused at the central processing unit level to obtain the full parameter correlation matrix. This full parameter correlation matrix obtains the full parameter space representation in the sample-time series dimension by expressing the correlation between each parameter at predetermined time points.

[0050] Furthermore, at the central processing unit, the computing unit 310 is also used to convert the above-mentioned speed input vector, wind speed input vector and pitch angle input vector into speed state vector, wind speed state vector and pitch angle state vector with a binary distribution of (0,1) respectively.

[0051] As one possible implementation, in the technical solution of this application, the rotational speed input vector, wind speed input vector, and pitch angle input vector are respectively input to multiple parallel switches based on a predetermined threshold, so as to convert the rotational speed input vector, wind speed input vector, and pitch angle input vector into the aforementioned rotational speed state vector, wind speed state vector, and pitch angle state vector with values ​​distributed as 0 and 1, respectively.

[0052] In one specific example of this embodiment, each switch has the same control threshold, thus maintaining the consistency of the global state metric among wind speed values ​​at multiple time points, the consistency of the global state metric among pitch angles at multiple time points, and the consistency of the global state metric among rotational speed values ​​at multiple time points. In another specific example of this embodiment, each switch has a separate control threshold, thus maintaining the adaptability of the global state metric for wind speed values ​​(pitch angles or rotational speed values) at each time point; that is, the control threshold is adaptively determined based on the wind speed values ​​(pitch angles or rotational speed values) at different time points. In yet another specific example of this application, the confidence level of the state metric is increased for each time point, and the threshold for each switch is a separate control threshold multiplied by the same control threshold. In this way, not only can the consistency of the global state metric among wind speed values ​​(pitch angles or rotational speed values) at multiple time points be effectively maintained, but the adaptability of the global state metric for wind speed values ​​(pitch angles or rotational speed values) at each time point can also be taken into account.

[0053] Furthermore, at the central processing unit, the computing unit 310 is also used to: calculate the full-state posterior vectors of the rotational speed state vector, wind speed state vector, and pitch angle state vector using a Bayesian probability model. Specifically, in this embodiment, the rotational speed state vector and wind speed state vector are first input into a parallel AND gate to obtain a first intermediate value vector; then, the pitch angle state vector is input into a parallel NOT gate to obtain a second intermediate value vector; finally, the first and second intermediate value vectors are input into a parallel AND gate to obtain the full-state posterior vector. That is, in the technical solution of this application, a simple hardware approach using AND gates and NOT gates is used to calculate the Bayesian posterior probability of the states, thereby obtaining the full-state control vector.

[0054] Furthermore, at the central processing unit, the computing unit 310 is also used to multiply the full-parameter correlation matrix by the full-state posterior vector to obtain the posterior feature vector. Thus, by calculating the posterior state probability based on the Bayesian model, the state correlation between rotational speed, wind speed, and propeller pitch angle in the time-series dimension can be accurately expressed, thereby enabling more accurate state control of the full-parameter correlation matrix to filter correlation parameters and remove correlation parameter values ​​that contribute little to the posterior state, thereby improving the accuracy of the logistic regression calculation results.

[0055] Then, at the central processing unit, logistic regression is performed on the posterior feature vector by the logistic regression unit 320 to obtain the pitch angle and speed control value at the current time point. As one possible implementation, the aforementioned posterior feature vector is input into a parallel multiplier and adder to obtain the pitch angle and speed control value at the current time point, wherein each multiplier in the parallel multiplier has an independent weight value.

[0056] Output interface 400 is used to output pitch angle and speed control values ​​to the relevant unit control module.

[0057] Specifically, the pitch angle and speed control values ​​are finally output through the output interface of the dedicated programmable controller, and the speed of the wind turbine generator is controlled based on the pitch angle and speed control values.

[0058] Among them, the relevant unit control module can be a component in the wind turbine speed control system that controls the wind turbine speed. This application sends the calculated pitch angle speed control value to the wind turbine speed control module, so that the speed control system can control the speed according to the received instruction. Specifically, it controls the speed value of the wind turbine generator set based on the calculated pitch angle speed control value, so that the adjusted speed value of the wind turbine generator set is suitable for the current operating conditions.

[0059] In summary, the dedicated programmable controller for wind power generation control in this application includes components such as input interfaces, output interfaces, memory, and a central processing unit. Considering that wind power generation control is related to wind speed, pitch angle, and rotational speed, it fully explores and utilizes the synergy and correlation information between wind speed, pitch angle, and rotational speed to obtain pitch angle and rotational speed control values. Based on these pitch angle and rotational speed control values, the rotational speed of the wind turbine is controlled, thereby making the adjusted rotational speed of the wind turbine suitable for the current operating conditions. This reduces the impact on the wind turbine, ensuring that the expected power generation demand is met while also guaranteeing the normal and safe operation of the wind turbine, thus improving the safety and adaptability of wind power generation.

[0060] Based on the above embodiments, to more clearly illustrate the specific implementation and working process of the dedicated programmable controller for wind power generation control in practical applications, the following will illustrate... Figure 3 The illustration shows a specific dedicated programmable controller for wind power generation control and Figure 4 The interaction process of each module in the controller shown is illustrated by example.

[0061] Figure 3 This is a schematic diagram illustrating the structure of a specific programmable controller for wind power generation control, provided as an embodiment of this application. Figure 3 As shown, the dedicated programmable controller for wind power generation control in this embodiment includes: an input interface 110, a memory 120, a central processing unit 130, an output interface 140, a communication interface 150, and a power supply 160.

[0062] Figure 4 This illustration shows the functions implemented by each module and the data interaction between them in a practical application of a dedicated programmable controller for wind power generation control according to embodiments of this application. For example... Figure 4As shown, firstly, the system receives wind speed values ​​at multiple predetermined time points within a predetermined time period from a wind speed sensor, pitch angles at multiple predetermined time points within the same time period from an angle sensor, and wind turbine rotation speed values ​​at multiple predetermined time points within the same time period from a speed monitor via an input interface. Next, the system stores wind speed input vectors for the wind speed values ​​at multiple predetermined time points, pitch angle input vectors for the pitch angles at multiple predetermined time points, and wind turbine rotation speed input vectors for the wind turbine rotation speed values ​​at multiple predetermined time points via a memory. Then, data processing is performed by the central processing unit, including: multiplying the rotational speed input vector with the wind speed input vector to obtain a rotational speed-wind speed correlation parameter matrix; multiplying the rotational speed input vector with the pitch angle input vector to obtain a rotational speed-pitch angle correlation parameter matrix; multiplying the wind speed input vector with the pitch angle input vector to obtain a wind speed-pitch angle correlation parameter matrix; fusing the rotational speed-wind speed correlation parameter matrix, the rotational speed-pitch angle correlation parameter matrix, and the wind speed-pitch angle correlation parameter matrix to obtain a full parameter correlation matrix; converting the rotational speed input vector, wind speed input vector, and pitch angle input vector into rotational speed state vector, wind speed state vector, and pitch angle state vector with a binary distribution of (0, 1), respectively; using a Bayesian probability model to calculate the full-state posterior vector of the rotational speed state vector, the wind speed state vector, and the pitch angle state vector; and multiplying the full parameter correlation matrix by the full-state posterior vector to obtain a posterior feature vector; and performing logistic regression on the posterior feature vector through a logistic regression unit to obtain the pitch angle rotational speed control value at the current time point. Furthermore, the pitch angle and speed control values ​​at the current time point are output through the output interface.

[0063] The functions and data processing procedures performed by each module in the dedicated programmable controller for wind power generation control according to the embodiments of this application will be described in detail below.

[0064] In the aforementioned dedicated programmable controller for wind power generation control, input interface 110 is used to receive wind speed values ​​at multiple predetermined time points within a predetermined time period from a wind speed sensor, pitch angles at multiple predetermined time points within the predetermined time period from an angle sensor, and wind turbine rotational speed values ​​at multiple predetermined time points within the predetermined time period from a speed monitor. As mentioned above, in the actual control of pitch control systems, due to the uncertainty and fluctuation of wind speed, the fluctuations in speed regulation and power output are significant, leading to substantial impacts and loads on the variable-speed wind turbine generator set. Therefore, an optimized wind power generation control scheme is desired.

[0065] In the technical solution of this application, the wind speed values ​​at multiple predetermined time points within a predetermined time period are first received from the wind speed sensor through the input interface and / or communication interface of the programmable logic controller, the pitch angle at multiple predetermined time points within the predetermined time period is received from the angle sensor, and the rotational speed values ​​of the wind turbine generator set at multiple predetermined time points within the predetermined time period are received from the rotational speed monitor.

[0066] In the aforementioned dedicated programmable controller for wind power generation control, the memory 120 is a register used to store wind speed input vectors for wind speed values ​​at multiple predetermined time points, pitch angle input vectors for pitch angles at multiple predetermined time points, and speed input vectors for wind turbine generator speed values ​​at multiple predetermined time points. Optionally, the wind speed values, pitch angles, and speed values ​​at multiple predetermined time points are stored in the memory of the dedicated programmable controller. In a specific example of this application, the numerical column vectors of the wind speed values ​​at multiple predetermined time points, the numerical column vectors of the pitch angles at multiple predetermined time points, and the numerical column vectors of the wind turbine generator speed values ​​at multiple predetermined time points are stored in the registers of the memory for easy subsequent data retrieval and calculation.

[0067] In the aforementioned dedicated programmable controller for wind power generation control, the central processing unit 130 includes a computing unit and a logic regression unit.

[0068] Specifically, in this embodiment, the calculation unit is further configured to: multiply the rotational speed input vector by the wind speed input vector to obtain a rotational speed-wind speed correlation parameter matrix; multiply the rotational speed input vector by the pitch angle input vector to obtain a rotational speed-pitch angle correlation parameter matrix; multiply the wind speed input vector by the pitch angle input vector to obtain a wind speed-pitch angle correlation parameter matrix; and fuse the rotational speed-wind speed correlation parameter matrix, the rotational speed-pitch angle correlation parameter matrix, and the wind speed-pitch angle correlation parameter matrix to obtain a full parameter correlation matrix.

[0069] In a specific example, the rotational speed-wind speed correlation matrix, the rotational speed-pitch angle correlation matrix, and the wind speed-pitch angle correlation matrix can be added together using an array adder at the central processing unit to obtain the full parameter correlation matrix. Here, the full parameter correlation matrix obtains the full parameter space representation in the sample-time series dimension by expressing the correlation between each parameter at a predetermined time point.

[0070] Specifically, in the embodiments of this application, the calculation unit is further used to: convert the rotational speed input vector, wind speed input vector, and pitch angle input vector into rotational speed state vector, wind speed state vector, and pitch angle state vector with a binary distribution of (0, 1), respectively.

[0071] More specifically, in this embodiment, the calculation unit includes a state vector conversion subunit, used to input the rotational speed input vector, wind speed input vector, and pitch angle input vector to multiple parallel switches based on predetermined thresholds to convert the rotational speed input vector, wind speed input vector, and pitch angle input vector into rotational speed state vector, wind speed state vector, and pitch angle state vector with values ​​distributed as (0,1), respectively. That is, the numerical values ​​in the rotational speed input vector, wind speed input vector, and pitch angle input vector are converted into logical values ​​of 0 or 1 through a simple hardware circuit of the central processing unit, so as to represent the rotational speed input vector, wind speed input vector, and pitch angle input vector through a column vector of logical values.

[0072] In a specific example of this application, each switch has the same control threshold, thereby maintaining the consistency of the global state metric between wind speed values ​​at multiple time points, the consistency of the global state metric between pitch angles at multiple time points, and the consistency of the global state metric between rotational speed values ​​at multiple time points.

[0073] In another specific example of this application, each switch has an independent control threshold, which can maintain the adaptability of the global state measurement of wind speed values ​​(pitch angle or speed value) at various time points, that is, the control threshold is adaptively determined based on the wind speed values ​​(pitch angle or speed value) at different time points.

[0074] In another specific example of this application, the confidence of the state metric is increased for each time point. The threshold of each switch is a separate control threshold multiplied by the same control threshold (i.e., the basic control threshold common to all switches). In this way, not only can the consistency of the global state metric between wind speed values ​​(pitch angle or speed value) at multiple time points be effectively maintained, but the adaptability of the global state metric of wind speed values ​​(pitch angle or speed value) at each time point can also be taken into account.

[0075] Specifically, in the embodiments of this application, the calculation unit is further configured to: use a Bayesian probability model to calculate the full-state posterior vectors of the rotational speed state vector, wind speed state vector, and pitch angle state vector.

[0076] More specifically, in this embodiment, the calculation unit further includes: a first intermediate value vector calculation subunit, a second intermediate value vector calculation subunit, and a posterior vector calculation subunit. The first intermediate value vector calculation subunit is used to input the rotational speed state vector and the wind speed state vector into a parallel AND gate to obtain a first intermediate value vector; the second intermediate value vector calculation subunit is used to input the pitch angle state vector into a parallel NOT gate to obtain a second intermediate value vector; and the posterior vector calculation subunit is used to input the first intermediate value vector and the second intermediate value vector into a parallel AND gate to obtain a full-state posterior vector.

[0077] Specifically, in this embodiment, the calculation unit is further configured to: multiply the full-parameter correlation matrix by the full-state posterior vector to obtain the posterior feature vector. That is, by calculating the posterior state probability based on a Bayesian model, the state correlation between rotational speed, wind speed, and propeller pitch angle in the time series dimension can be accurately expressed, thereby enabling more accurate state control of the full-parameter correlation matrix to filter correlation parameters and remove correlation parameter values ​​that contribute little to the posterior state, thus improving the accuracy of the logistic regression calculation results.

[0078] Specifically, in this embodiment, the logistic regression unit is specifically used to: perform logistic regression on the posterior feature vector to obtain the pitch angle and speed control value at the current time point.

[0079] More specifically, in this embodiment, the logistic regression unit is further configured to input the posterior feature vector into a parallel multiplier and an adder to obtain the pitch angle speed control value at the current time point. In this embodiment, each multiplier has an independent weight value, the sum of the weight values ​​of all multipliers in the parallel multiplier is 1, and the weight values ​​of all multipliers are equal. That is, each multiplier implements an arithmetic average weighting.

[0080] In the aforementioned dedicated programmable controller for wind power generation control, output interface 140 is used to output the pitch angle and speed control values ​​at the current time. That is, the pitch angle and speed control values ​​are output through the dedicated programmable controller's output interface, and the speed of the wind turbine generator is controlled based on these values.

[0081] In summary, a dedicated programmable controller for wind power generation control based on the embodiments of this application is provided. It takes into account that wind power generation control is related to wind speed, pitch angle and rotational speed, fully explores and utilizes the synergy and correlation information between the above data to obtain pitch angle and rotational speed control values, and controls the rotational speed of the wind turbine generator set based on the pitch angle and rotational speed control values.

[0082] Based on the above embodiments, in order to more clearly illustrate the application of the dedicated programmable controller for wind power generation control in practical applications, the following description uses a specific application scenario proposed in the embodiments of this application. Figure 5 This is a schematic diagram illustrating an application scenario of a dedicated programmable controller for wind power generation control, provided as an embodiment of this application. For example... Figure 5 As shown, in the application scenario of a dedicated programmable controller for wind power generation control, the first step is to start with a wind speed sensor (e.g., such as...). Figure 5 The Se1 shown collects wind speed values ​​at multiple predetermined time points within a predetermined time period from an angle sensor (e.g., such as...). Figure 5The Se2 shown collects the pitch angle at multiple predetermined time points within the predetermined time period, and from the speed monitoring instrument (e.g., such as...) Figure 5 The Se3 shown collects data from wind turbine generators at multiple predetermined time points within the predetermined time period (e.g., such as...). Figure 5 The rotational speed value of G (as shown). Furthermore, the wind speed values ​​at multiple predetermined time points within the predetermined time period, the pitch angle at multiple predetermined time points within the predetermined time period, and the rotational speed values ​​of the wind turbine generator set at multiple predetermined time points within the predetermined time period are input through an interface (e.g., such as...). Figure 5 The input (as shown in the figure) is fed into a dedicated programmable controller (e.g., such as...) for wind power generation control. Figure 5 In the PLC shown, the dedicated programmable controller for wind power generation control can process the wind speed values ​​at multiple predetermined time points within the predetermined time period, the pitch angle at multiple predetermined time points within the predetermined time period, and the rotational speed values ​​of the wind turbine generator set at multiple predetermined time points within the predetermined time period to obtain pitch angle speed control values. These pitch angle speed control values ​​are output through an interface (e.g., such as...). Figure 5 The output is as shown in the diagram (Out).

[0083] To achieve the above embodiments, this application also proposes a wind power generation control method. Figure 6 A flowchart illustrating a wind power generation control method provided in an embodiment of this application. Figure 6 As shown, the method includes the following steps:

[0084] Step S101: Receive wind speed values, pitch angles, and wind turbine rotation speed values ​​at multiple predetermined time points.

[0085] Step S102: Store the wind speed input vector corresponding to the wind speed value, the pitch angle input vector corresponding to the pitch angle, and the rotational speed input vector corresponding to the rotational speed value.

[0086] Step S103: Calculate the full parameter correlation matrix and full state posterior vector corresponding to the wind speed input vector, pitch angle input vector and speed input vector, and calculate the current pitch angle and speed control value through logistic regression based on the full parameter correlation matrix and the full state posterior vector.

[0087] Step S104: Output the pitch angle and speed control values ​​to the relevant unit control module.

[0088] Based on the above method, in practical applications, when this control method is applied to a programmable controller to execute the method, a specific operation method of the programmable controller is also proposed in one embodiment of this application. Figure 7A flowchart illustrating a specific operation method of a dedicated programmable controller for wind power generation control, as provided in this application embodiment, is shown below. Figure 7 As shown, the method includes the following steps:

[0089] S110: Receive wind speed values ​​at multiple predetermined time points within a predetermined time period from a wind speed sensor via an input interface; receive pitch angles at multiple predetermined time points within the predetermined time period from an angle sensor; and receive wind turbine rotational speed values ​​at multiple predetermined time points within the predetermined time period from a speed monitoring device. S120: Store, via a memory, wind speed input vectors for the wind speed values ​​at the multiple predetermined time points, pitch angle input vectors for the pitch angles at the multiple predetermined time points, and rotational speed input vectors for the rotational speed values ​​of the wind turbine rotational speed at the multiple predetermined time points. S130: Perform data processing via a central processing unit, including: multiplying the rotational speed input vector by the wind speed input vector to obtain a rotational speed-wind speed correlation parameter matrix; multiplying the rotational speed input vector by the pitch angle input vector to obtain a rotational speed-pitch angle correlation parameter matrix; and multiplying the wind speed input vector by the pitch angle input vector. Vector multiplication is performed to obtain the wind speed-pitch angle correlation parameter matrix; the rotational speed-wind speed correlation parameter matrix, the rotational speed-pitch angle correlation parameter matrix, and the wind speed-pitch angle correlation parameter matrix are fused to obtain the full parameter correlation matrix; the rotational speed input vector, the wind speed input vector, and the pitch angle input vector are converted into rotational speed state vector, wind speed state vector, and pitch angle state vector with a binary distribution of (0, 1), respectively; a Bayesian probability model is used to calculate the full-state posterior vector of the rotational speed state vector, wind speed state vector, and pitch angle state vector; and the full parameter correlation matrix is ​​multiplied by the full-state posterior vector to obtain the posterior feature vector; and a logistic regression unit is used to perform logistic regression on the posterior feature vector to obtain the pitch angle rotational speed control value at the current time point; and, S140, the pitch angle rotational speed control value at the current time point is output through the output interface.

[0090] In one example, in the above-described operation method of a dedicated programmable controller for wind power generation control, the step of obtaining a full parameter correlation matrix by fusing the rotational speed-wind speed correlation parameter matrix, the rotational speed-pitch angle correlation parameter matrix, and the wind speed-pitch angle correlation parameter matrix through a calculation unit includes: adding the rotational speed-wind speed correlation parameter matrix, the rotational speed-pitch angle correlation parameter matrix, and the wind speed-pitch angle correlation parameter matrix through an array adder to obtain the full parameter correlation matrix.

[0091] In one example, in the above-described operation method of a dedicated programmable controller for wind power generation control, the step of converting the rotational speed input vector, the wind speed input vector, and the pitch angle input vector into a rotational speed state vector, a wind speed state vector, and a pitch angle state vector with a binary distribution of (0,1) by a calculation unit includes: inputting the rotational speed input vector, the wind speed input vector, and the pitch angle input vector into multiple parallel switches based on a predetermined threshold by a state vector conversion subunit to convert the rotational speed input vector, the wind speed input vector, and the pitch angle input vector into the rotational speed state vector, the wind speed state vector, and the pitch angle state vector with a distribution of (0,1) by a state vector conversion subunit.

[0092] In one example, in the above-described method of operating a dedicated programmable controller for wind power generation control, each of the plurality of parallel switches has the same control threshold.

[0093] In one example, in the above-described method of operating a dedicated programmable controller for wind power generation control, each of the plurality of parallel switches has an independent control threshold.

[0094] In one example, in the above-described method of operating a dedicated programmable controller for wind power generation control, in the plurality of parallel switches, the threshold of each of the switches is a separate control threshold multiplied by the same control threshold.

[0095] In one example, in the above-described operation method of a dedicated programmable controller for wind power generation control, the step of calculating the full-state posterior vector of the rotational speed state vector, the wind speed state vector, and the pitch angle state vector using a Bayesian probability model through a calculation unit includes: inputting the rotational speed state vector and the wind speed state vector into a parallel AND gate through a first intermediate value vector calculation subunit to obtain a first intermediate value vector; inputting the pitch angle state vector into a parallel NOT gate through a second intermediate value vector calculation subunit to obtain a second intermediate value vector; and inputting the first intermediate value vector and the second intermediate value vector into a parallel AND gate through a posterior vector calculation subunit to obtain the full-state posterior vector.

[0096] In one example, in the above-described method for operating a dedicated programmable controller for wind power generation control, the step of performing logistic regression on the posterior feature vector through a logistic regression unit to obtain the pitch angle and speed control value at the current time point includes: inputting the posterior feature vector into a parallel multiplier and adder to obtain the pitch angle and speed control value at the current time point.

[0097] In one example, in the above-described method of operating a dedicated programmable controller for wind power generation control, each of the parallel multipliers has an independent weight value, and the sum of the weight values ​​of the various multipliers in the parallel multiplier is 1.

[0098] In one example, in the above-described method of operating a dedicated programmable controller for wind power generation control, the weight values ​​of each multiplier are equal.

[0099] In summary, the operation method of the dedicated programmable controller for wind power generation control in the embodiments of this application takes into account that wind power generation control is related to wind speed, pitch angle and rotational speed. Therefore, the dedicated programmable logic controller fully explores and utilizes the synergy and correlation information between the above data to obtain the pitch angle and rotational speed control value, and controls the rotational speed value of the wind turbine generator set based on the pitch angle and rotational speed control value.

[0100] To implement the above embodiments, this application also proposes a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the wind power generation control method as described in any of the above embodiments.

[0101] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0102] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0103] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0104] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0105] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0106] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0107] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0108] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and alterations to the above embodiments within the scope of this application.

Claims

1. A dedicated programmable controller for wind power generation control, characterized in that, The method comprises the following steps: an input interface is configured to receive wind speed values, pitch angles and rotation speed values of a wind turbine at a plurality of predetermined time points; a memory is configured to store wind speed input vectors corresponding to the wind speed values, pitch angle input vectors corresponding to the pitch angles and rotation speed input vectors corresponding to the rotation speed values; a central processing unit is configured to calculate a full parameter correlation matrix corresponding to the wind speed input vectors, the pitch angle input vectors and the rotation speed input vectors and a full state posterior vector, and to calculate a current pitch angle rotation speed control value by logistic regression based on the full parameter correlation matrix and the full state posterior vector; wherein the central processing unit comprises a calculation unit and a logistic regression unit, wherein the calculation unit is configured to multiply the rotation speed input vectors by the wind speed input vectors to obtain a rotation speed-wind speed correlation parameter matrix, multiply the rotation speed input vectors by the pitch angle input vectors to obtain a rotation speed-pitch angle correlation parameter matrix, multiply the wind speed input vectors by the pitch angle input vectors to obtain a wind speed-pitch angle correlation parameter matrix, fuse the rotation speed-wind speed correlation parameter matrix, the rotation speed-pitch angle correlation parameter matrix and the wind speed-pitch angle correlation parameter matrix to obtain the full parameter correlation matrix, convert the rotation speed input vectors, the wind speed input vectors and the pitch angle input vectors into rotation speed state vectors, wind speed state vectors and pitch angle state vectors respectively in binary distribution, calculate the full state posterior vector of the rotation speed state vectors, the wind speed state vectors and the pitch angle state vectors by a Bayesian probability model, and multiply the full parameter correlation matrix by the full state posterior vector to obtain a posterior feature vector; the logistic regression unit is configured to perform logistic regression on the posterior feature vector to obtain the pitch angle rotation speed control value; the calculation unit comprises a state vector conversion subunit configured to input the rotation speed input vectors, the wind speed input vectors and the pitch angle input vectors into a plurality of parallel switches based on predetermined threshold values to obtain the rotation speed state vectors, the wind speed state vectors and the pitch angle state vectors respectively; the calculation unit further comprises a first intermediate value vector calculation subunit configured to input the rotation speed state vectors and the wind speed state vectors into a parallel AND gate to obtain a first intermediate value vector, a second intermediate value vector calculation subunit configured to input the pitch angle state vectors into a parallel NOT gate to obtain a second intermediate value vector, and a posterior vector calculation subunit configured to input the first intermediate value vector and the second intermediate value vector into a parallel AND gate to obtain the full state posterior vector; an output interface is configured to output the pitch angle rotation speed control value to a related turbine control module.

2. The dedicated programmable controller for wind power generation control according to claim 1, characterized in that, The calculation unit is specifically configured to add the rotation speed-wind speed correlation parameter matrix, the rotation speed-pitch angle correlation parameter matrix and the wind speed-pitch angle correlation parameter matrix by an array adder to obtain the full parameter correlation matrix.

3. The dedicated programmable controller for wind power generation control according to claim 1, characterized in that, In the plurality of parallel switches, all the switches have the same control threshold value, or each switch has an independent control threshold value.

4. The dedicated programmable controller for wind power generation control according to claim 1, characterized in that, In the plurality of parallel switches, a threshold value of each of the switches is a product of an independent control threshold value and a common basic control threshold value.

5. The dedicated programmable controller for wind power generation control according to claim 1, characterized in that, The logic regression unit is specifically configured to input the posterior feature vector into parallel multipliers and adders to obtain the pitch angle speed control value.

6. The dedicated programmable controller for wind power generation control according to claim 5, characterized in that, In the parallel multipliers, each of the multipliers has an independent weight value, and the sum of the weight values of all the multipliers in the parallel multipliers is 1, and the weight values of each of the multipliers in the parallel multipliers are equal.

7. A wind power generation control method characterized by, The method comprises: receiving wind speed values, pitch angles and speed values of a wind turbine generator set at a plurality of predetermined time points; storing wind speed input vectors corresponding to the wind speed values, pitch angle input vectors corresponding to the pitch angles and speed input vectors corresponding to the speed values; calculating a full parameter correlation matrix corresponding to the wind speed input vectors, the pitch angle input vectors and the speed input vectors and a full state posterior vector, and calculating a current pitch angle speed control value through logic regression based on the full parameter correlation matrix and the full state posterior vector; outputting the pitch angle speed control value to a relevant unit control module.

Images