Control Method, Device, System and Storage Medium of Wind Turbine Generator Set

Abstract

The present disclosure provides a control method, device, system, and storage medium for a wind turbine. The control method of the wind turbine includes: obtaining a preset value of a control parameter and a plurality of historical measurement signals of the wind turbine within a historical period; determining an estimated distribution parameter of a control signal at the current moment according to the preset value and the plurality of historical measurement signals; and determining the control signal at the current moment according to the estimated distribution parameter of the control signal at the current moment. The present disclosure can reflect the uncertainty of the measurement signal at the current moment by means of a plurality of historical measurement signals. Compared with the traditional scheme of directly determining the control signal at the current moment according to the measurement signal at the current moment, it is possible to give the control signal from the perspective of probability statistics while fully considering the uncertainty of the measurement signal, reduce the influence of the uncertainty of the traditional measurement sensor on the control accuracy, and there is no need to additionally replace expensive high-precision sensors, realizing the improvement of control accuracy at low cost.

Description

Technical Field

[0001] The present disclosure relates to the field of wind power generation, and more particularly, to a control method, device, system and storage medium for a wind turbine generator set. Background Art

[0002] The control systems of current wind turbine generator sets mostly adopt PID control, that is, proportional, integral and derivative control. The proportional, integral and derivative of the deviation between the preset value of the control parameter and the actual output value are linearly combined to form a control quantity to control the controlled object. However, the current actual output values are all measured by sensors, and there will be uncertainties, resulting in inaccurate control, and replacing high-precision sensors is often costly. Summary of the Invention

[0003] Therefore, how to improve the control accuracy of wind turbine generator sets at low cost is crucial.

[0004] In one general aspect, there is provided a control method for a wind turbine generator set, including: obtaining a preset value of a control parameter and a plurality of historical measurement signals of the wind turbine generator set within a historical period; determining an estimated distribution parameter of a control signal at a current moment according to the preset value and the plurality of historical measurement signals; and determining a control signal at the current moment according to the estimated distribution parameter of the control signal at the current moment.

[0005] Optionally, the determining an estimated distribution parameter of a control signal at a current moment according to the preset value and the plurality of historical measurement signals includes: obtaining a reference measurement signal according to the plurality of historical measurement signals; and determining the estimated distribution parameter of the control signal at the current moment according to each reference measurement signal and the preset value.

[0006] Optionally, the obtaining a reference measurement signal according to the plurality of historical measurement signals includes: performing a fitting process on the plurality of historical measurement signals to obtain distribution parameters of the historical measurement signals; and performing a discretization process on the distribution parameters of the historical measurement signals to obtain a plurality of reference measurement signals and a reference measurement signal probability of each reference measurement signal.

[0007] Optionally, the determining the estimated distribution parameter of the control signal at the current moment according to each reference measurement signal and the preset value includes: determining a reference control signal corresponding to the reference measurement signal according to each reference measurement signal and the preset value, and taking the reference measurement signal probability of the reference measurement signal as a reference control signal probability; and performing a fitting process on the determined plurality of reference control signals and the reference control signal probability of each reference control signal to obtain the estimated distribution parameter of the control signal at the current moment.

[0008] Optionally, the multiple historical measurement signals are measured by a measurement sensor. Wherein, the fitting process of the multiple historical measurement signals to obtain the distribution parameters of the historical measurement signals includes: fitting the multiple historical measurement signals according to a reference distribution type to obtain the distribution parameters of the historical measurement signals, where the reference distribution type is related to the measurement sensor; or the reference distribution type is obtained through the following steps: performing frequency statistics on the multiple historical measurement signals; based on the frequency statistics results of the multiple historical measurement signals, determining one from multiple candidate distribution types as the reference distribution type.

[0009] Optionally, before determining the control signal at the current moment according to the estimated distribution parameters of the control signal at the current moment, the control method further includes: obtaining the distribution parameters of the control deviation within a reference period, where the control deviation is the deviation between the measurement signal and the preset value; wherein, the determining the control signal at the current moment according to the estimated distribution parameters of the control signal at the current moment includes: based on the distribution parameters of the control deviation within the reference period, correcting the estimated distribution parameters of the control signal at the current moment to obtain the corrected distribution parameters of the control signal at the current moment; determining the control signal at the current moment according to the corrected distribution parameters of the control signal at the current moment.

[0010] Optionally, the obtaining the distribution parameters of the control deviation within a reference period includes: starting from the starting moment, determining a plurality of continuously arranged preset time lengths; performing frequency statistics on the control deviation within the first i preset time lengths to obtain the i-th statistical result; i is a positive integer; performing a fitting process on the i-th statistical result to obtain the distribution parameters of the i-th control deviation; in response to the distribution parameters of the i-th control deviation not satisfying a preset approximation condition with the distribution parameters of the (i - 1)-th control deviation, increasing i by 1, and then repeating the steps of performing frequency statistics, fitting process, and judgment of the preset approximation condition on the control deviation within the first i preset time lengths; in response to the distribution parameters of the i-th control deviation satisfying the preset approximation condition with the distribution parameters of the (i - 1)-th control deviation, taking the distribution parameters of the i-th control deviation as the distribution parameters of the control deviation within the reference period, taking the period corresponding to the first i preset time lengths as the reference period, and taking the end moment of the i-th preset time length as the starting moment of the new reference period, and repeating the steps of performing frequency statistics, fitting process, and judgment of the preset approximation condition on the control deviation within the first i preset time lengths for the new reference period.

[0011] Optionally, correcting the estimated distribution parameter of the control signal at the current moment based on the distribution parameter of the control deviation within the reference period to obtain the corrected distribution parameter of the control signal at the current moment includes: discretizing the estimated distribution parameter of the control signal at the current moment to obtain a plurality of control signals and the control signal probabilities of each control signal; discretizing the distribution parameter of the control deviation within the reference period to obtain a plurality of control deviations and the control deviation probabilities of each control deviation; performing superposition correction processing for each control signal and each control deviation to obtain the corresponding corrected control signal, and determining the product of the control signal probability of the control signal and the control deviation probability of the control deviation as the correction probability of the corresponding corrected control signal; performing fitting processing on the obtained plurality of corrected control signals and the correction probabilities of each corrected control signal to obtain the corrected distribution parameter of the control signal at the current moment.

[0012] Optionally, determining the control signal at the current moment according to the estimated distribution parameter of the control signal at the current moment includes: determining the control signal at the current moment according to the estimated distribution parameter of the control signal at the current moment, the correspondence between the control signal and the load, and the reference load range.

[0013] Optionally, determining the control signal at the current moment according to the estimated distribution parameter of the control signal at the current moment, the correspondence between the control signal and the load, and the reference load range includes: determining the probability that the load falls within the reference load range according to the estimated distribution parameter at the current moment, the correspondence between the control signal and the load, and the reference load range as the reference probability; in response to the reference probability being greater than or equal to the probability threshold, determining the reference control signal range corresponding to the reference load range; determining the generated power corresponding to a plurality of reference control signals within the reference control signal range according to the correspondence between the control signal and the generated power; determining the control signal at the current moment from the plurality of reference control signals according to the generated power corresponding to the plurality of reference control signals.

[0014] Optionally, determining the control signal at the current moment according to the estimated distribution parameter of the control signal at the current moment, the correspondence between the control signal and the load, and the reference load range further includes: in response to the reference probability being less than the probability threshold, determining the reference control signal corresponding to the upper limit value of the reference load range as the control signal at the current moment.

[0015] In another general aspect, there is provided a control device for a wind turbine generator, including: an acquisition unit configured to acquire a preset value of a control parameter of the wind turbine generator within a historical period and a plurality of historical measurement signals; a determination unit configured to determine an estimated distribution parameter of a control signal at the current moment according to the preset value and the plurality of historical measurement signals; and a control unit configured to determine the control signal at the current moment according to the estimated distribution parameter of the control signal at the current moment.

[0016] Optionally, the determination unit is further configured to: acquire a reference measurement signal according to the plurality of historical measurement signals; and determine the estimated distribution parameter of the control signal at the current moment according to each reference measurement signal and the preset value.

[0017] Optionally, the determination unit is further configured to: perform a fitting process on the plurality of historical measurement signals to obtain a distribution parameter of the historical measurement signals; and perform a discretization process on the distribution parameter of the historical measurement signals to obtain a plurality of reference measurement signals and a reference measurement signal probability of each reference measurement signal.

[0018] Optionally, the determination unit is further configured to: determine a reference control signal corresponding to the reference measurement signal according to each reference measurement signal and the preset value, and use the reference measurement signal probability of the reference measurement signal as a reference control signal probability; and perform a fitting process on the determined plurality of reference control signals and the reference control signal probability of each reference control signal to obtain the estimated distribution parameter of the control signal at the current moment.

[0019] Optionally, the plurality of historical measurement signals are measured by a measurement sensor, and the determination unit is further configured to: perform a fitting process on the plurality of historical measurement signals according to a reference distribution type to obtain the distribution parameter of the historical measurement signals, where the reference distribution type is related to the measurement sensor; or the reference distribution type is obtained through the following steps: perform a frequency statistics on the plurality of historical measurement signals; and determine one from a plurality of candidate distribution types based on the frequency statistics result of the plurality of historical measurement signals as the reference distribution type.

[0020] Optionally, the acquisition unit is further configured to: acquire a distribution parameter of a control deviation within a reference period, where the control deviation is a deviation between a measurement signal and a preset value; the control unit is further configured to: correct the estimated distribution parameter of the control signal at the current moment based on the distribution parameter of the control deviation within the reference period to obtain a corrected distribution parameter of the control signal at the current moment; and determine the control signal at the current moment according to the corrected distribution parameter of the control signal at the current moment.

[0021] Optionally, the obtaining unit is further configured to: determine a plurality of continuously arranged preset time periods starting from the starting moment; perform frequency statistics on the control deviation within the first i preset time periods to obtain the i-th statistical result, where i is a positive integer; perform fitting processing on the i-th statistical result to obtain the distribution parameter of the i-th control deviation; in response to the distribution parameter of the i-th control deviation not satisfying the preset approximation condition with the distribution parameter of the (i - 1)-th control deviation, increment i by 1, and then repeat the steps of performing frequency statistics, fitting processing, and judgment of the preset approximation condition on the control deviation within the first i preset time periods; in response to the distribution parameter of the i-th control deviation satisfying the preset approximation condition with the distribution parameter of the (i - 1)-th control deviation, use the distribution parameter of the i-th control deviation as the distribution parameter of the control deviation within the reference time period, use the time period corresponding to the first i preset time periods as the reference time period, and use the end moment of the i-th preset time period as the starting moment of the new reference time period, and for the new reference time period, repeat the steps of performing frequency statistics, fitting processing, and judgment of the preset approximation condition on the control deviation within the first i preset time periods.

[0022] Optionally, the control unit is further configured to: discretize the estimated distribution parameter of the control signal at the current moment to obtain a plurality of control signals and the control signal probability of each control signal; discretize the distribution parameter of the control deviation within the reference time period to obtain a plurality of control deviations and the control deviation probability of each control deviation; perform superposition correction processing on each control signal and each control deviation to obtain the corresponding corrected control signal, and determine the product of the control signal probability of the control signal and the control deviation probability of the control deviation as the correction probability of the corresponding corrected control signal; perform fitting processing on the obtained plurality of corrected control signals and the correction probability of each corrected control signal to obtain the corrected distribution parameter of the control signal at the current moment.

[0023] Optionally, the control unit is further configured to: determine the control signal at the current moment according to the estimated distribution parameter of the control signal at the current moment, the correspondence between the control signal and the load, and the reference load range.

[0024] Optionally, the control unit is further configured to: determine the probability that the load falls within the reference load range according to the estimated distribution parameter of the control signal at the current moment, the correspondence between the control signal and the load, and the reference load range, as the reference probability; in response to the reference probability being greater than or equal to the probability threshold, determine the reference control signal range corresponding to the reference load range; determine the generated power corresponding to a plurality of reference control signals within the reference control signal range according to the correspondence between the control signal and the generated power; determine the control signal at the current moment from the plurality of reference control signals according to the generated power corresponding to the plurality of reference control signals.

[0025] Optionally, the control unit is further configured to: in response to the reference probability being less than the probability threshold, determine a reference control signal corresponding to the upper limit value of the reference load range as the control signal at the current moment.

[0026] In another general aspect, a control system for a wind turbine is provided, including: a measurement sensor for collecting measurement signals of control parameters; a processor for: obtaining preset values of control parameters and a plurality of historical measurement signals of the wind turbine within a historical period; determining an estimated distribution parameter of the control signal at the current moment according to the preset values and the plurality of historical measurement signals; a control decision maker for determining the control signal at the current moment according to the estimated distribution parameter of the control signal at the current moment.

[0027] Optionally, the processor is further configured to: obtain a reference measurement signal according to the plurality of historical measurement signals; determine the estimated distribution parameter of the control signal at the current moment according to each reference measurement signal and the preset value.

[0028] Optionally, the processor includes: a first signal analyzer for performing fitting processing on the plurality of historical measurement signals to obtain distribution parameters of the historical measurement signals; a first controller for discretizing the distribution parameters of the historical measurement signals to obtain a plurality of reference measurement signals and a reference measurement signal probability of each reference measurement signal.

[0029] Optionally, the first controller is further configured to: determine a reference control signal corresponding to the reference measurement signal according to each reference measurement signal and the preset value, use the reference measurement signal probability of the reference measurement signal as the reference control signal probability; perform fitting processing on the determined plurality of reference control signals and the reference control signal probability of each reference control signal to obtain the estimated distribution parameter of the control signal at the current moment.

[0030] Optionally, the first signal analyzer is further configured to: perform fitting processing on the plurality of historical measurement signals according to a reference distribution type to obtain the distribution parameters of the historical measurement signals, where the reference distribution type is related to the measurement sensor; or the reference distribution type is obtained through the following steps: performing frequency statistics on the plurality of historical measurement signals; determining one from a plurality of candidate distribution types as the reference distribution type based on the frequency statistics result of the plurality of historical measurement signals.

[0031] Optionally, the processor further includes: a second signal analyzer configured to obtain distribution parameters of control deviations within a reference period, where the control deviation is the deviation between a measurement signal and a preset value; a second controller configured to correct the estimated distribution parameters of the control signal at the current moment based on the distribution parameters of the control deviations within the reference period to obtain corrected distribution parameters of the control signal at the current moment; and the control decision maker is further configured to determine the control signal at the current moment according to the corrected distribution parameters of the control signal at the current moment.

[0032] Optionally, the second signal analyzer is further configured to: determine a plurality of consecutive preset time lengths starting from the starting moment; perform frequency statistics on the control deviations within the first i preset time lengths to obtain the i-th statistical result, where i is a positive integer; perform fitting processing on the i-th statistical result to obtain distribution parameters of the i-th control deviation; in response to the distribution parameters of the i-th control deviation not satisfying a preset approximation condition with the distribution parameters of the (i - 1)-th control deviation, increment i by 1, and then repeat the steps of performing frequency statistics on the control deviations within the first i preset time lengths, fitting processing, and determination of the preset approximation condition; in response to the distribution parameters of the i-th control deviation satisfying the preset approximation condition with the distribution parameters of the (i - 1)-th control deviation, use the distribution parameters of the i-th control deviation as the distribution parameters of the control deviations within the reference period, use the period corresponding to the first i preset time lengths as the reference period, and use the end moment of the i-th preset time length as the starting moment of the new reference period, and for the new reference period, repeat the steps of performing frequency statistics on the control deviations within the first i preset time lengths, fitting processing, and determination of the preset approximation condition.

[0033] Optionally, the second controller is further configured to: perform discretization processing on the estimated distribution parameters of the control signal at the current moment to obtain a plurality of control signals and the control signal probabilities of each control signal; perform discretization processing on the distribution parameters of the control deviations within the reference period to obtain a plurality of control deviations and the control deviation probabilities of each control deviation; perform superposition correction processing for each control signal and each control deviation to obtain a corresponding corrected control signal, and determine the product of the control signal probability of the control signal and the control deviation probability of the control deviation as the correction probability of the corresponding corrected control signal; perform fitting processing on the obtained plurality of corrected control signals and the correction probabilities of each corrected control signal to obtain the corrected distribution parameters of the control signal at the current moment.

[0034] Optionally, the control decision maker is further configured to: determine the control signal at the current moment according to the estimated distribution parameters of the control signal at the current moment, the correspondence between the control signal and the load, and the reference load range.

[0035] Optionally, the control decision maker is further configured to: determine the probability that the load falls within the reference load range based on the predicted distribution parameter at the current moment, the correspondence between the control signal and the load, and the reference load range, as the reference probability; in response to the reference probability being greater than or equal to the probability threshold, determine the reference control signal range corresponding to the reference load range; determine the power generation amounts corresponding to multiple reference control signals within the reference control signal range according to the correspondence between the control signal and the power generation amount; and determine the control signal at the current moment from the multiple reference control signals according to the power generation amounts corresponding to the multiple reference control signals.

[0036] Optionally, the control decision maker is further configured to, in response to the reference probability being less than the probability threshold, determine the reference control signal corresponding to the upper limit value of the reference load range as the control signal at the current moment.

[0037] In another general aspect, there is provided a computer-readable storage medium, which, when instructions in the computer-readable storage medium are run by at least one processor, causes the at least one processor to execute the control method of the wind turbine generator as described above.

[0038] In another general aspect, there is provided a computer device, including: at least one processor; and at least one memory storing computer-executable instructions, wherein, when the computer-executable instructions are run by the at least one processor, the at least one processor is caused to execute the control method of the wind turbine generator as described above.

[0039] The present disclosure provides a control method, device, system and storage medium for a wind turbine generator. By obtaining the preset values of control parameters and multiple historical measurement signals within a historical period, the uncertainty of the measurement signal at the current moment can be reflected by means of the multiple historical measurement signals, and then the predicted distribution parameter of the control signal at the current moment can be obtained in combination with the preset values of the control parameters. Compared with the conventional solution of directly determining the control signal at the current moment based on the measurement signal at the current moment, the control signal can be given from the perspective of probability statistics while fully considering the uncertainty of the measurement signal, reducing the influence of the uncertainty of the conventional measurement sensor on the control accuracy, without the need to additionally replace expensive high-precision sensors, and achieving the improvement of control accuracy at low cost.

[0040] In addition, by obtaining the distribution parameter of the control deviation within a reference period, the possible control deviation of the new control signal can be predicted in advance from the perspective of probability statistics, and then the predicted distribution parameter of the control signal at the current moment can be correspondingly corrected, which can further improve the control accuracy.

[0041] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. Description of the Drawings

[0042] Figure 1 is a schematic diagram showing the control flow executed by the control system of a wind turbine according to a specific embodiment of the present disclosure;

[0043] Figure 2 is a flowchart showing the control method of a wind turbine according to an embodiment of the present disclosure;

[0044] Figure 3 is a schematic diagram showing the probability density function of a measurement signal according to an embodiment of the present disclosure;

[0045] Figure 4 is a schematic flowchart showing the control deviation analysis according to an embodiment of the present disclosure;

[0046] Figure 5 is a schematic diagram showing the control deviation statistics according to an embodiment of the present disclosure;

[0047] Figure 6 is a schematic diagram showing the control deviation distribution according to an embodiment of the present disclosure;

[0048] Figure 7 is a block diagram showing the control device of a wind turbine according to an embodiment of the present disclosure;

[0049] Figure 8 is a block diagram showing the computer device according to an embodiment of the present disclosure. Detailed Description of the Embodiments

[0050] The following detailed description is provided to assist the reader in obtaining a comprehensive understanding of the methods, apparatuses, and / or systems described herein. However, various changes, modifications, and equivalents of the methods, apparatuses, and / or systems described herein will be apparent after understanding the disclosure of the present application. For example, the order of operations described herein is merely exemplary and is not limited to those set forth herein, but may be changed as will be apparent after understanding the disclosure of the present application, except for operations that must occur in a specific order. Additionally, descriptions of features known in the art may be omitted for greater clarity and conciseness.

[0051] The features described herein may be implemented in different forms and should not be construed as limited to the examples described herein. Instead, the examples described herein are provided only to illustrate some of the many possible ways of implementing the methods, apparatuses, and / or systems described herein, which will be apparent after understanding the disclosure of the present application.

[0052] As used herein, the term "and / or" includes any one of the associated listed items and any combination of any two or more thereof.

[0053] Although terms such as "first", "second", and "third" may be used herein to describe various components, elements, regions, layers, or sections, these components, elements, regions, layers, or sections should not be limited by these terms. Instead, these terms are only used to distinguish one component, element, region, layer, or section from another. Thus, a first component, first element, first region, first layer, or first section described in an example herein may also be referred to as a second component, second element, second region, second layer, or second section without departing from the teachings of the example.

[0054] In the specification, when an element (such as a layer, region, or substrate) is described as "on", "connected to", or "coupled to" another element, the element can be directly "on", directly "connected to", or "coupled to" the other element, or there can be one or more other elements intervening therebetween. In contrast, when an element is described as "directly on", "directly connected to", or "directly coupled to" another element, there can be no other elements intervening therebetween.

[0055] The terms used herein are for the purpose of describing various examples only and are not intended to limit the disclosure. Unless the context clearly indicates otherwise, the singular forms are also intended to include the plural forms. The terms "comprising", "including", and "having" specify the presence of the stated features, quantities, operations, components, elements, and / or combinations thereof, but do not preclude the presence or addition of one or more other features, quantities, operations, components, elements, and / or combinations thereof.

[0056] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure pertains after understanding the disclosure. Unless explicitly defined as such herein, terms (such as those defined in a general dictionary) should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and this disclosure, and should not be interpreted in an idealized or overly formal manner.

[0057] Furthermore, in the description of the examples, when a detailed description of related structures or functions that are considered well-known would cause an unclear interpretation of the disclosure, such detailed descriptions will be omitted.

[0058] The present disclosure provides a control system for a wind turbine generator, including a measurement sensor, a processor, and a control decision maker. The measurement sensor is used to collect measurement signals of control parameters, and traditional measurement sensors can be used to reduce costs. The processor is used to obtain preset values of control parameters and a plurality of historical measurement signals during a historical period of the wind turbine generator, so as to reflect the uncertainty of the measurement signals, and determine the estimated distribution parameters of the control signal at the current moment according to the preset values and the plurality of historical measurement signals. A traditional PID control algorithm can be applied to determine the control signal based on the preset values and the measurement signals. On this basis, statistical algorithms can also be used to process the determined plurality of control signals, so as to obtain the estimated distribution parameters of the control signal at the current moment. The control decision maker is used to determine the control signal at the current moment according to the estimated distribution parameters of the control signal at the current moment, so as to give the control signal from the perspective of probability statistics, and further control the operation of the wind turbine generator based on the control signal.

[0059] Compared with the traditional control system that directly determines the control signal at the current moment according to the measurement signal at the current moment, the control system proposed by the present disclosure can give the control signal from the perspective of probability statistics while fully considering the uncertainty of the measurement signal, reduce the influence of the uncertainty of the traditional measurement sensor on the control accuracy, and there is no need to additionally replace expensive high-precision sensors, achieving an improvement in control accuracy at low cost.

[0060] It should be understood that the control system proposed by the present disclosure can be a single-unit control system of a wind turbine generator or a field-level control system of a wind farm. Among them, the measurement sensor is a separate sensor device, and both the processor and the control decision maker are used for data processing. They can be two separate chips and are connected to each other in a wired or wireless form (hereinafter directly simplified to connection, and unless otherwise specified, it means connected in a wired or wireless form) to achieve data transmission; they can also be integrated into the same chip. In addition, it is not difficult to find from the following description that the processor can further include a first signal analyzer and a first controller, and can further include a second signal analyzer and a second controller. In this regard, the devices included in the processor can be split and made into at least two chips. For example, the first signal analyzer, the first controller, the second signal analyzer, and the second controller are made into four independent and interconnected chips. Another example is to integrate the first signal analyzer and the second signal analyzer into a signal analyzer chip, and integrate the first controller and the second controller into a controller chip; further, the control decision maker can also be integrated with the first controller and / or the second controller into a chip. The above is an exemplary description of the implementation manners of the various devices in the control system of the present disclosure, and is not a limitation on the present disclosure.

[0061] Optionally, the processor is further configured to: obtain a reference measurement signal according to a plurality of historical measurement signals; and determine an estimated distribution parameter of the control signal at the current moment according to each reference measurement signal and a preset value.

[0062] Optionally, the processor includes: a first signal analyzer configured to perform a fitting process on a plurality of historical measurement signals to obtain a distribution parameter of the historical measurement signals; and a first controller configured to perform a discretization process on the distribution parameter of the historical measurement signals to obtain a plurality of reference measurement signals and a reference measurement signal probability of each reference measurement signal.

[0063] Optionally, the first controller is further configured to: determine a reference control signal corresponding to the reference measurement signal according to each reference measurement signal and a preset value, and use the reference measurement signal probability of the reference measurement signal as a reference control signal probability; and perform a fitting process on the determined plurality of reference control signals and the reference control signal probability of each reference control signal to obtain an estimated distribution parameter of the control signal at the current moment.

[0064] Optionally, the first signal analyzer is further configured to: perform a fitting process on a plurality of historical measurement signals according to a reference distribution type to obtain a distribution parameter of the historical measurement signals, where the reference distribution type is related to the measurement sensor; or the reference distribution type is obtained through the following steps: perform a frequency statistics on a plurality of historical measurement signals; and determine one from a plurality of candidate distribution types based on the frequency statistics result of the plurality of historical measurement signals as the reference distribution type.

[0065] Optionally, the processor further includes: a second signal analyzer configured to obtain a distribution parameter of a control deviation within a reference period, where the control deviation is a deviation between the measurement signal and a preset value; a second controller configured to correct the estimated distribution parameter of the control signal at the current moment based on the distribution parameter of the control deviation within the reference period to obtain a corrected distribution parameter of the control signal at the current moment; and a control decision maker further configured to determine the control signal at the current moment according to the corrected distribution parameter of the control signal at the current moment.

[0066] Optionally, the second signal analyzer is further configured to: determine a plurality of consecutive preset time durations starting from the starting moment; perform a frequency count on the control deviations within the first i preset time durations to obtain the i-th statistical result, where i is a positive integer; perform a fitting process on the i-th statistical result to obtain the distribution parameter of the i-th control deviation; in response to the distribution parameter of the i-th control deviation not satisfying the preset approximation condition with the distribution parameter of the (i - 1)-th control deviation, increment i by 1, and then repeat the steps of performing a frequency count on the control deviations within the first i preset time durations, performing a fitting process, and determining the preset approximation condition; in response to the distribution parameter of the i-th control deviation satisfying the preset approximation condition with the distribution parameter of the (i - 1)-th control deviation, use the distribution parameter of the i-th control deviation as the distribution parameter of the control deviation within the reference time period, use the time period corresponding to the first i preset time durations as the reference time period, and use the end moment of the i-th preset time duration as the starting moment of the new reference time period, and for the new reference time period, repeat the steps of performing a frequency count on the control deviations within the first i preset time durations, performing a fitting process, and determining the preset approximation condition.

[0067] Optionally, the second controller is further configured to: discretize the estimated distribution parameter of the control signal at the current moment to obtain a plurality of control signals and the control signal probability of each control signal; discretize the distribution parameter of the control deviation within the reference time period to obtain a plurality of control deviations and the control deviation probability of each control deviation; for each control signal and each control deviation, perform a superposition correction process to obtain the corresponding corrected control signal, and determine the product of the control signal probability of the control signal and the control deviation probability of the control deviation as the correction probability of the corresponding corrected control signal; perform a fitting process on the obtained plurality of corrected control signals and the correction probability of each corrected control signal to obtain the corrected distribution parameter of the control signal at the current moment.

[0068] Optionally, the control decision maker is further configured to: determine the control signal at the current moment according to the estimated distribution parameter of the control signal at the current moment, the correspondence between the control signal and the load, and the reference load range.

[0069] Optionally, the control decision maker is further configured to: determine the probability that the load falls within the reference load range according to the estimated distribution parameter at the current moment, the correspondence between the control signal and the load, and the reference load range, as the reference probability; in response to the reference probability being greater than or equal to the probability threshold, determine the reference control signal range corresponding to the reference load range; determine the generated power corresponding to a plurality of reference control signals within the reference control signal range according to the correspondence between the control signal and the generated power; determine the control signal at the current moment from the plurality of reference control signals according to the generated power corresponding to the plurality of reference control signals.

[0070] Optionally, the control decision maker is further configured to determine, in response to the reference probability being less than the probability threshold, a reference control signal corresponding to the upper limit value of the reference load range as the control signal at the current moment.

[0071] Figure 1 FIG. is a schematic diagram of a control flow executed by a control system of a wind turbine according to a specific embodiment of the present disclosure. In this specific embodiment, the control system includes traditional measurement sensors, and also includes a processor and a control decision maker. The processor includes a first signal analyzer, a first controller, a second signal analyzer, and a second controller, and the first signal analyzer and the second signal analyzer are integrated into a signal analyzer chip, and the first controller and the second controller are integrated into a controller chip.

[0072] Refer to Figure 1 , with the pitch angle, rotational speed, torque, and yaw angle as control parameters, and run the control system for any one of the control parameters. The reasons for inaccurate control can be divided into two categories. One is the uncertainty during the measurement process, and the other is the control deviation between the preset value of the control parameter and the measurement signal detected after the actual unit executes. Correspondingly, on the one hand, input the preset value of the control parameter and multiple historical measurement signals within the historical period into the first signal analyzer, and the first signal analyzer performs measurement uncertainty analysis to obtain the distribution parameters of the historical measurement signals; the first controller accordingly obtains the feedback data of the PID control algorithm, so that the measurement uncertainty that may be brought by the measurement sensor can be considered when running the PID control algorithm, and then outputs a control signal, and further statistically obtains the estimated distribution parameters of the control signal at the current moment, compensating for the influence of the measurement uncertainty. On the other hand, starting from the start time of the reference period, every preset time period, input the accumulated control deviation into the second signal analyzer, and the second signal analyzer performs control deviation analysis to obtain the distribution parameters of the control deviation within the reference period, and can accordingly perform lag correction on the estimated distribution parameters of the control signal obtained by the first controller to obtain the corrected distribution parameters of the control signal, which not only retains the robustness of the traditional PID control but also achieves the effect of predictive control.

[0073] On this basis, the control decision-maker combines the existing SCADATOLOAD method, that is, the method of deriving the load of the wind turbine through measurement signals such as the pitch angle, rotational speed, torque, and yaw angle of the unit, and the load distribution parameters corresponding to the correction distribution parameters of the control signal can be obtained. Given the reference load range of a certain key load component, the reference probability that the key load component falls within the reference load range can be calculated according to the load distribution parameters. Combining with the reference probability, if the reference probability is greater than or equal to the probability threshold, within the reference control signal range corresponding to the reference load range, the control scheme is optimized with the power generation as the reference to determine a control scheme with safe load and relatively better power generation, so that while ensuring the safe operation of the unit, the power generation is maximized; if the reference probability is less than the probability threshold, the control signal causing the load of the upper limit value to occur is directly deduced based on the upper limit value of the reference load range, and the final control scheme is determined, and the control scheme can be quickly determined and the unit control can be realized, making the control more accurate and timely.

[0074] Figure 2 is a flowchart showing a control method for a wind turbine according to an embodiment of the present disclosure.

[0075] Referring to Figure 2 , in step S101, the preset values of the control parameters of the wind turbine in the historical period and a plurality of historical measurement signals are obtained.

[0076] The control parameters are, for example, but not limited to, pitch angle, rotational speed, torque, and yaw angle. The preset value is the target value of the control parameter that is expected to be achieved through control. For example, if it is desired to adjust the pitch angle to 0°, the preset value of the pitch angle is 0°, and the preset value often remains unchanged for a period of time. As the name implies, the historical measurement signal is the measurement signal in the historical period. The measurement signal is an electrical signal corresponding to the control parameter and can be obtained by applying a measurement sensor to measure the control parameter. In the control process, the existing control method can output a control signal based on the preset value of the control parameter. When this control signal acts on the corresponding actuator, it can cause the corresponding control parameter of the actuator to change. By using a measurement sensor, the actual value of the corresponding control parameter can be measured as the measurement signal. It can be seen that at each moment, the preset value of the control parameter, the control signal, and the measurement signal correspond to each other, and both the control signal and the measurement signal fluctuate around the preset value. When the preset value changes, the control signal and the measurement signal also change accordingly.

[0077] By obtaining a plurality of historical measurement signals, the present disclosure can replace the measurement signal at the current moment with the plurality of historical measurement signals when performing control at the current moment, so as to reflect the uncertainty of the measurement signal at the current moment. It should be understood that in order to ensure that the plurality of historical measurement signals obtained can reflect the uncertainty of the measurement signal at the current moment, at least the preset values corresponding to the plurality of historical measurement signals need to be kept unchanged and consistent with the preset value at the current moment. Preferably, a historical period close to the current moment can be selected, for example, a historical period of 10 minutes before the current moment. Since it is close to the current moment, the possibility that the historical measurement signal is affected by other factors is relatively small, and thus it can better reflect the measurement uncertainty at the current moment.

[0078] Step S102: Determine the estimated distribution parameters of the control signal at the current moment according to the preset value and the plurality of historical measurement signals.

[0079] This step takes into account the uncertainty of the measurement signal at the current moment when performing control. Correspondingly, the determined are the estimated distribution parameters of the control signal at the current moment, rather than a single definite control signal, and can achieve probabilistic control. As an example, the plurality of historical measurement signals can be directly used as the input data of a traditional control algorithm. For example, as the feedback data in a PID algorithm, according to each historical measurement signal and the preset value, the control signal corresponding to each historical measurement signal is determined, and then the plurality of determined control signals are statistically analyzed, and the estimated distribution parameters of the control signal at the current moment can be obtained. This processing method not only continues the traditional control algorithm, but also can use the plurality of historical measurement signals to reflect the uncertainty of the measurement signal, thus fully considering the uncertainty of the measurement signal and giving the control signal from the perspective of probability statistics, which can reduce the influence of the uncertainty of the traditional measurement sensor on the control accuracy, without the need to replace expensive high-precision sensors, and realizes low-cost and high-precision control.

[0080] As an example, the estimated distribution parameters are the parameters in the Probability Density Function (PDF), such as the location parameter μ and the scale parameter σ in the normal distribution. Of course, other parameters that can reflect the distribution characteristics can also be used, and the present disclosure does not limit this. The various distribution parameters of other data are the same in principle and will not be elaborated one by one below.

[0081] Step S103: Determine the control signal at the current moment according to the estimated distribution parameters of the control signal at the current moment. Combining the estimated distribution parameters of the control signal at the current moment, the control signal can be given from the perspective of probability statistics, improving the accuracy of the obtained control signal.

[0082] Next, step S102 will be further introduced.

[0083] Optionally, step S102 includes: obtaining a reference measurement signal according to a plurality of historical measurement signals; determining an estimated distribution parameter of the control signal at the current moment according to each reference measurement signal and a preset value. By determining a plurality of reference measurement signals based on the historical measurement signals and using the reference measurement signals as the input data of the traditional control algorithm, the plurality of historical measurement signals can be further processed, thereby adjusting the accuracy of the estimated distribution parameter of the control signal at the current moment obtained.

[0084] Regarding how to obtain the reference measurement signal, in some embodiments, at least some of the historical measurement signals can be selected from the plurality of historical measurement signals as the reference measurement signal. For example, all of the plurality of historical measurement signals can be directly used as the reference measurement signal, or some signals can be screened out according to a certain rule as the reference measurement signal. The rule is, for example, but not limited to, removing the maximum value and the minimum value, and the present disclosure does not limit this.

[0085] In other embodiments, first perform a fitting process on the plurality of historical measurement signals to obtain the distribution parameter of the historical measurement signals; then perform a discretization process on the distribution parameter of the historical measurement signals to obtain a plurality of reference measurement signals and the reference measurement signal probability of each reference measurement signal. By first fitting to obtain the distribution parameter of the historical measurement signals, the distribution law followed by the historical measurement signals can be refined from a limited number of historical measurement signals, realizing the refinement from concrete data to abstract law. Then, by performing a discretization process on the refined distribution parameter, the obtained plurality of reference measurement signals can conform to the refined distribution parameter, that is, conform to the abstract law, improving the characterization accuracy of the measurement uncertainty, helping to improve the accuracy of the estimated distribution parameter of the control signal at the current moment obtained therefrom, and further improving the control accuracy.

[0086] For the above-mentioned other embodiments, correspondingly, the step of determining the estimated distribution parameters of the control signal at the current moment includes: determining the reference control signal corresponding to each reference measurement signal according to each reference measurement signal and a preset value, and using the reference measurement signal probability of the reference measurement signal as the reference control signal probability; performing a fitting process on the determined multiple reference control signals and the reference control signal probability of each reference control signal to obtain the estimated distribution parameters of the control signal at the current moment. Based on the distribution parameters of the refined historical measurement signals, the reference measurement signal probability of each reference measurement signal can be obtained. By using the reference measurement signal probability of each reference measurement signal as the reference control signal probability of the reference control signal corresponding to the reference measurement signal, a more accurate probability description of the determined multiple reference control signals can be made according to the analyzed measurement uncertainty, ensuring the accuracy of the estimated distribution parameters of the control signal at the current moment. It should be understood that since the values of the reference measurement signal and its corresponding reference control signal are often not exactly equal, the distribution type to which the estimated distribution parameters of the control signal at the current moment belong may be the same as or different from the distribution type to which the distribution parameters of the historical measurement signals belong. Here, the distribution type refers to the probability distribution type, such as the normal distribution and the Gaussian distribution.

[0087] In addition, the fitting process of the multiple historical measurement signals in the above-mentioned other embodiments can be performed according to the reference distribution type, so that the distribution parameters of the historical measurement signals can be relatively reliably obtained by determining the parameters in the reference distribution type, realizing the analysis of measurement uncertainty.

[0088] As an example, the reference distribution type is the triangular distribution. Using Measure to represent the measurement signal, the maximum and minimum values [Max Measure 、Min Measure of multiple historical measurement signals are obtained. According to [Max Measrure 、Min Measure , a symmetric triangular distribution can be constructed, and its probability density function f(Measure) is shown in the following formula, and the schematic diagram is as Figure 3 shown.

[0089]

[0090] Regarding the determination of the reference distribution type, since multiple historical measurement signals are obtained by measurement sensors, and the uncertainty is often caused by the errors existing in the used measurement sensors themselves, the distribution type of the measurement signals is very likely to be related to the measurement sensors. Based on this, in one example, the reference distribution type is related to the measurement sensors. By analyzing in advance the distribution types of the signals measured by different measurement sensors, and then determining the corresponding distribution type according to the measurement sensor used to detect the measurement signal as the reference distribution type, a relatively reliable reference distribution type can be determined quickly and conveniently, improving the data analysis efficiency. As an example, different distribution types can be matched according to the types of measurement sensors, and the accuracy of the measurement sensors can be further combined to match different distribution types for measurement sensors of the same type but with different accuracies. The present disclosure does not limit this.

[0091] In another example, the reference distribution type is obtained through the following steps: performing frequency statistics on multiple historical measurement signals; based on the frequency statistics results of the multiple historical measurement signals, determining one from multiple candidate distribution types as the reference distribution type. By actually analyzing the distribution of the multiple historical measurement signals obtained (i.e., performing frequency statistics) and then determining a similar one from multiple candidate distribution types, the measurement signals obtained each time can be analyzed independently, increasing the possibility that the determined reference distribution type conforms to the distribution characteristics of the historical measurement signals. As an example, according to the frequencies of each historical measurement signal (i.e., the number of occurrences of different historical measurement signal values), the values of the cumulative probability distribution (Cumulative Probability Distribution, abbreviated as CPD, which can be obtained by integrating the probability density function) corresponding to each value can be statistically calculated. Then, for each candidate distribution type, the cumulative probability distribution values of each measurement signal value are determined, and then a candidate distribution type that is relatively closest to the statistical result is selected as the reference distribution type. It is also possible to use the values of the historical measurement signals as the horizontal axis and the frequencies of each value as the vertical axis to draw a distribution schematic diagram of the historical measurement signals, and then compare it with the probability density function curves of each candidate distribution type. For example, calculate the coincidence degree of the curve change trend, and use the candidate distribution type with the relatively highest coincidence as the reference distribution type. The present disclosure does not limit this.

[0092] As mentioned above, the reasons for inaccurate control can be divided into two categories. One is the uncertainty in the measurement process, and the other is the control deviation between the preset value of the control parameter and the measurement signal detected after the actual unit executes. Step S102 solves the problem of uncertainty in the measurement process. Next, the correction of the control deviation will be introduced.

[0093] For the control deviation, before step S103, the control method of the embodiments of the present disclosure may further include: obtaining the distribution parameter of the control deviation within a reference period, where the control deviation is the deviation between the measurement signal and the preset value; correspondingly, step S103 includes: based on the distribution parameter of the control deviation within the reference period, correcting the estimated distribution parameter of the control signal at the current moment to obtain the corrected distribution parameter of the control signal at the current moment; determining the control signal at the current moment according to the corrected distribution parameter of the control signal at the current moment.

[0094] The control deviation is the deviation between the measurement signal and the preset value, which can be regarded as the deviation between the actual result and the expected result of the control. The larger the single control deviation, the further the corresponding measurement signal is from the preset value, the higher the degree of control lag, and the lower the accuracy. By obtaining the distribution parameter of the control deviation within the reference period, it is possible to predict in advance the possible lag of the control signal from the perspective of probability statistics, and then correct the lagged control signal, that is, correct the estimated distribution parameter of the control signal at the current moment to obtain the corrected distribution parameter of the control signal at the current moment, so as to achieve predictive control of the wind turbine in the face of complex and variable wind conditions and improve the control accuracy.

[0095] In terms of time, the current moment is the moment when the preset value of the control parameter is executed, that is, the moment when the control is determined according to the preset value and the lag correction is implemented according to the distribution parameter of the control deviation within the reference period. The end moment of the reference period should be earlier than or equal to the current moment, that is, at the earliest, the distribution parameter of the control deviation within the reference period is analyzed at the end moment of the reference period and immediately applied to the lag correction at the current moment, and then the distribution parameter can continue to be applied to the lag correction at subsequent moments; of course, it is also possible to analyze the distribution parameter of the control deviation within the reference period after a period of time after the reference period, or it takes a period of time to apply the analysis result to the current lag correction, so that the end moment of the reference period is always earlier than the current moment, and the present disclosure does not limit this.

[0096] Optionally, with reference to Figure 4 , the step of analyzing the control deviation, that is, the step of obtaining the distribution parameter of the control deviation within the reference period, further includes the following steps:

[0097] The first step is to determine a plurality of continuously arranged preset time periods starting from the starting moment. It should be understood that after accumulating a certain amount of control deviation data, the control deviation can be analyzed. The starting moment is the moment when the control deviation data starts to be recorded. By determining a plurality of continuously arranged preset time periods, for each subsequent step of accumulating the control deviation data for the preset time period, a statistical analysis of the existing control deviation data can be performed. The preset time period is, for example, but not limited to, 10 minutes. It should be noted that this step emphasizes the confirmation of the starting moment. In Figure 4There is no special display in

[0098] Second, perform a frequency statistics on the control deviation within the first i preset time periods to obtain the i-th statistical result; i is a positive integer. This step performs a frequency statistics on all the accumulated control deviation data from the starting moment to the current at every preset time period. Therefore, i will gradually increase starting from 1 to achieve periodic control deviation data statistics. It should be understood that for each statistics, the time period composed of the first i preset time periods is Figure 4 the continuous time period shown.

[0099] As an example, for the continuous time period of the first i preset time periods, take the measurement signals of pitch angle, rotational speed, torque, and yaw angle [PitchAngle mmeasure 、RotorSpeed measure 、Torque measure 、YawAngle measure and the value of a certain control parameter in the corresponding preset values [PitchAngle design 、RotorSpeed design 、Torque design 、YawAngle design as the input, calculate the control deviation between the measurement signal and the preset value, and the control parameter actually used can be selected according to the actual control requirements of the unit. As shown in the following formula, use Error to represent the control deviation, Measure to represent the measurement signal, and Design to represent the control set value.

[0100] Error = Measure - Design

[0101] Assume that the control deviation of a certain control parameter within this continuous time period is as Figure 5 shown. Statistically count the various values of the control deviation within this continuous time period and the frequency corresponding to each value as the current latest statistical result, and a schematic diagram of the control deviation distribution as Figure 6 shown can also be obtained.

[0102] Third, perform a fitting process on the i-th statistical result to obtain the distribution parameters of the i-th control deviation. The specific method of the fitting process can refer to the fitting process in the measurement uncertainty analysis part in the previous text. First, determine a distribution type, and then perform a fitting process according to this distribution type to determine the distribution parameters, which will not be elaborated here.

[0103] Step 4: Determine whether the distribution parameter of the i-th control deviation and the distribution parameter of the (i - 1)-th control deviation meet the preset approximation condition. It should be understood that the preset approximation condition represents a condition where the two compared distribution parameters are close enough. For example, but not limited to, the difference between the two compared distribution parameters is less than 5%. For cases involving multiple specific parameters, such as the parameters of a normal distribution including two specific parameters, the location parameter μ and the scale parameter σ, a data can be processed, such as converting multiple specific parameters into one parameter, or calculating the percentage difference of each specific parameter respectively, and then calculating the statistical value (such as mean, mode, median, etc.) of the percentage differences of each specific parameter. The present disclosure does not limit this.

[0104] After the above determination, if the result does not meet the preset approximation condition, it can be considered that the current accumulated data volume is still insufficient and no consistent distribution law is reflected. Then, increase i by 1 and repeat steps 2 to 4, that is, continue to perform periodic statistical analysis of control deviation data, fit the distribution parameter of the new control deviation, and determine again whether it meets the preset approximation condition. If the result meets the preset approximation condition, it can be considered that a stable and consistent distribution law has been statistically obtained. Then, use the distribution parameter of the i-th control deviation as the distribution parameter of the control deviation within the reference period, and use the period corresponding to the first i preset time lengths as the reference period. At this time, a round of control deviation analysis is completed. At the same time, use the end moment of the i-th preset time length as the start moment of the new reference period, and repeat steps 1 to 4 for the new reference period to achieve a new round of control deviation analysis.

[0105] It should be understood that in step 4, if i = 1, the distribution parameter of the (i - 1)-th control deviation can use the distribution parameter of the control deviation within the reference period obtained from the previous round of control deviation analysis.

[0106] It should also be understood that after completing a round of control deviation analysis, the distribution parameters of the control deviation within the obtained reference period can be applied to lag correction. At this time, data can be re-accumulated synchronously to conduct a new round of control deviation analysis until the distribution parameters of the control deviation within the new reference period are obtained. Then, the distribution parameters of the control deviation within the new reference period are used to perform lag correction. This process repeats continuously, and the latest distribution parameters of the control deviation within the reference period are continuously used to perform lag correction. It is precisely because the distribution parameters of the control deviation within the obtained reference period are used to perform control lag correction that theoretically, over time, the control deviation will show a decreasing trend and will not remain unchanged for a long time. By re-accumulating data in the new round of analysis, it is possible to avoid the situation where the control deviation data from the previous round dominates and quickly meets the preset approximation conditions in the early stage of the new round of analysis. This helps to effectively statistically analyze the control deviation data in the new round, thereby reducing the impact of large deviation data from the distant past on the analysis results of the recent control deviation, fully reflecting the recent control optimization effect, providing a more reliable basis for updating the analysis results of the control deviation, and further improving the control accuracy, forming a virtuous cycle.

[0107] Optionally, the result of applying control deviation analysis is used to implement the step of lag correction, that is, based on the distribution parameters of the control deviation within the reference period, the estimated distribution parameters of the control signal at the current moment are corrected to obtain the corrected distribution parameters of the control signal at the current moment. The step further includes: discretizing the estimated distribution parameters of the control signal at the current moment to obtain multiple control signals and the control signal probability of each control signal; discretizing the distribution parameters of the control deviation within the reference period to obtain multiple control deviations and the control deviation probability of each control deviation; for each control signal and each control deviation, performing superposition correction processing to obtain the corresponding corrected control signal, and determining the product of the control signal probability of the control signal and the control deviation probability of the control deviation as the corrected probability of the corresponding corrected control signal; fitting the obtained multiple corrected control signals and the corrected probability of each corrected control signal to obtain the corrected distribution parameters of the control signal at the current moment. The estimated distribution parameters of the control signal at the current moment and the distribution parameters of the control deviation within the reference period both belong to the parameters of continuous functions. By discretizing the two, multiple control signals and their probabilities, as well as multiple control deviations and their probabilities, can be obtained, which facilitates pairing each control signal with each control deviation one by one for superposition correction processing. The lag of a single control signal can be compensated by a single control deviation, ensuring the smooth progress of the correction process. It should be understood that assuming M control signals and N control deviations are obtained after discretization processing, then M×N data pairs can be obtained, and correspondingly M×N corrected control signals and corrected probabilities can be obtained. There may be cases where the values of the corrected control signals are equal among these corrected control signals, then the corrected control signals with equal values can be merged, and the sum of the corrected probabilities of the corrected control signals with equal values is used as the merged corrected probability.

[0108] As an example, for the embodiment in which multiple historical measurement signals are first fitted and then discretized in step S102 to obtain multiple reference measurement signals, the estimated distribution parameters of the control signal at the current moment are originally obtained by fitting multiple reference control signals corresponding to the multiple reference measurement signals. At this time, in step S102, the multiple reference control signals may not be fitted first, and these multiple reference control signals can be directly used when performing the lag correction in step S103, which can reduce the amount of data processing and improve the calculation efficiency. It should be understood that although the explicit estimated distribution parameters of the control signal at the current moment are not obtained at this time, the estimated distribution parameters essentially exist, so it still conforms to Figure 2 step S102 in. Of course, it is also possible to explicitly process and obtain the estimated distribution parameters of the control signal at the current moment in step S102, and then perform discretization processing during lag correction, so as to obtain multiple control signals according to the expected rule, such as obtaining multiple control signals in an arithmetic progression, to meet different requirements of superposition correction processing. The present disclosure does not limit this.

[0109] Next, a further introduction is made to how to determine the control signal at the current moment in step S103.

[0110] It should be understood that when the above-mentioned lag correction is not performed, the estimated distribution parameter of the control signal at the current moment can be directly used to determine the control signal at the current moment. When the above-mentioned lag correction is performed, the corrected distribution parameter of the control signal at the current moment can be used to determine the control signal at the current moment. For the convenience of description, the estimated distribution parameter of the control signal at the current moment is uniformly used below. For the case where the lag correction is performed, the estimated distribution parameter of the control signal at the current moment can be replaced with the corrected distribution parameter of the control signal at the current moment, which will not be elaborated further.

[0111] Optionally, the steps of determining the control signal at the current moment include: determining the control signal at the current moment according to the estimated distribution parameter of the control signal at the current moment, the correspondence between the control signal and the load, and the reference load range. Since specific control parameters are often related to specific load components, changes in the control parameters will cause corresponding changes in the load components. By introducing the reference load range and relying on the correspondence between the control signal and the load, a reasonable control signal can be determined based on the estimated distribution parameter of the control signal at the current moment with the reference load range as a reference. This can not only ensure that the determined control signal conforms to the lag correction, which helps to improve the accuracy of control, but also make the load component fall within the reference load range after the corresponding control is executed, ensuring the safe operation of the unit and fully improving the control efficiency. It should be understood that to ensure the safe operation, the reference load range must have an upper limit value greater than 0, and the lower limit value can be greater than or equal to 0. The lower limit value can be calculated and given, manually input by the operator, or default to 0. The present disclosure does not limit this.

[0112] Regarding the specific implementation of this step, in some embodiments, optionally, first determine the reference control signal range corresponding to the reference load range according to the correspondence between the control signal and the load; then select a value from the reference control signal range according to the estimated distribution parameter of the control signal at the current moment, for example, the value with the largest probability density value, as the control signal at the current moment.

[0113] In some other embodiments, optionally, first, based on the estimated distribution parameter at the current moment, the correspondence between the control signal and the load, and the reference load range, determine the probability that the load falls within the reference load range as the reference probability; then compare the reference probability with the probability threshold, and in response to the reference probability being greater than or equal to the probability threshold, determine the reference control signal range corresponding to the reference load range; according to the correspondence between the control signal and the power generation amount, determine the power generation amounts corresponding to multiple reference control signals within the reference control signal range; and based on the power generation amounts corresponding to the multiple reference control signals, determine the control signal at the current moment from the multiple reference control signals. By determining the reference probability that the load falls within the reference load range, the possibility of the unit operating safely can be clarified. If the reference probability is relatively large, it means that the possibility of the unit operating safely is relatively high. For example, if the calculated reference probability is 0.9, it indicates that 90% of the loads fall within the reference load range. At this time, the adjustable range of the control signal, that is, the reference control signal range, is relatively large, and the selection is more flexible. Since the load is derived from the control signal, at this time, the reference control signal range corresponding to the reference load range can be inversely derived according to the correspondence between the control signal and the load, and under this range, the control scheme is optimized with the power generation amount as the reference to search for the reference control signal that maximizes the power generation amount of the unit and does not exceed the reference load range as the optimal control scheme. This embodiment can, on the premise of ensuring the safety of the wind turbine generator set, calmly face the changing complex wind conditions with relatively high control accuracy, and achieve more power generation output, improving the economic benefits and contributing to comprehensively improving the control efficiency. It should be understood that the correspondence between the control signal and the power generation amount can be obtained through existing methods such as simulation, which belongs to the mature technology in this field, and the present disclosure does not limit this. As an example, the correspondence between the control signal and the load can be reflected in the existing SCADATOLOAD method, that is, when it is necessary to derive the load based on the control signal, the SCADATOLOAD method can be applied to process the control signal to obtain the load.

[0114] In the above-mentioned some other embodiments, further optionally, after completing the comparison of the reference probability with the probability threshold, in response to the reference probability being less than the probability threshold, determine the reference control signal corresponding to the upper limit value of the reference load range as the control signal at the current moment. When the reference probability is relatively small, it can be considered that the load is very likely to exceed the reference load range, and there is a relatively high risk. At this time, the adjustable range of the control signal is relatively small. By directly using the reference control signal corresponding to the upper limit value of the reference load range as the final control signal, there is no need to calculate the reference control signal range anymore, nor to optimize the control scheme based on the power generation amount, which can reasonably simplify the determination process of the control signal, reduce the calculation amount, improve the control efficiency, and reduce the risk of dangerous situations such as untimely control and load overlimit caused by excessive calculation time consumption, making the control more accurate and timely.

[0115] Regarding the determination of the reference probability, first, according to the estimated distribution parameters of the control signal at the current moment and the corresponding relationship between the control signal and the load, the distribution parameters of the load can be determined. Then, according to the distribution parameters of the load and the reference load range, the probability that the load falls within the reference load range can be determined. For example, the cumulative probability distribution value corresponding to the reference load range is calculated through the probability density function of the load and used as the reference probability. Alternatively, first, according to the corresponding relationship between the control signal and the load, the reference control signal range corresponding to the reference load range can be determined. Then, according to the estimated distribution parameters of the control signal at the current moment, the probability that the control signal falls within the reference control signal range can be determined. For example, the cumulative probability distribution value corresponding to the reference control signal range is calculated through the probability density function of the control signal and used as the reference probability. In other words, the reference probability can be directly calculated for the load or directly calculated for the control signal. Since there is a corresponding relationship between the control signal and the load, the two are theoretically equal, and the present disclosure does not limit this.

[0116] Figure 7 is a block diagram showing a control device of a wind turbine according to an embodiment of the present disclosure.

[0117] Referring to Figure 7 , the control device 700 of the wind turbine includes an acquisition unit 701, a determination unit 702, and a control unit 703.

[0118] The acquisition unit 701 can acquire the preset values of the control parameters of the wind turbine during the historical period and a plurality of historical measurement signals.

[0119] The determination unit 702 can determine the estimated distribution parameters of the control signal at the current moment according to the preset values and the plurality of historical measurement signals.

[0120] The control unit 703 can determine the control signal at the current moment according to the estimated distribution parameters of the control signal at the current moment.

[0121] Optionally, the determination unit 702 can also: acquire a reference measurement signal according to the plurality of historical measurement signals; determine the estimated distribution parameters of the control signal at the current moment according to each reference measurement signal and the preset value.

[0122] Optionally, the determination unit 702 can also: perform a fitting process on the plurality of historical measurement signals to obtain the distribution parameters of the historical measurement signals; perform a discretization process on the distribution parameters of the historical measurement signals to obtain a plurality of reference measurement signals and the reference measurement signal probability of each reference measurement signal.

[0123] Optionally, the determination unit 702 may further: determine a reference control signal corresponding to each reference measurement signal according to each reference measurement signal and a preset value, and use the reference measurement signal probability of the reference measurement signal as the reference control signal probability; perform a fitting process on the determined multiple reference control signals and the reference control signal probability of each reference control signal to obtain the estimated distribution parameters of the control signal at the current moment.

[0124] Optionally, the multiple historical measurement signals are measured by a measurement sensor, and the determination unit 702 may further: perform a fitting process on the multiple historical measurement signals according to a reference distribution type to obtain the distribution parameters of the historical measurement signals, where the reference distribution type is related to the measurement sensor; or the reference distribution type is obtained through the following steps: perform a frequency statistics on the multiple historical measurement signals; based on the frequency statistics result of the multiple historical measurement signals, determine one from multiple candidate distribution types as the reference distribution type.

[0125] Optionally, the acquisition unit 701 may further: acquire the distribution parameters of the control deviation within a reference period, where the control deviation is the deviation between the measurement signal and the preset value; the control unit 703 may further: correct the estimated distribution parameters of the control signal at the current moment based on the distribution parameters of the control deviation within the reference period to obtain the corrected distribution parameters of the control signal at the current moment; determine the control signal at the current moment according to the corrected distribution parameters of the control signal at the current moment.

[0126] Optionally, the acquisition unit 701 may further: determine a plurality of continuously arranged preset time periods starting from the starting moment; perform a frequency statistics on the control deviation within the first i preset time periods to obtain the i-th statistical result; i is a positive integer; perform a fitting process on the i-th statistical result to obtain the distribution parameters of the i-th control deviation; in response to the distribution parameters of the i-th control deviation not satisfying a preset approximation condition with the distribution parameters of the (i - 1)-th control deviation, increase i by 1, and then repeat the steps of performing a frequency statistics on the control deviation within the first i preset time periods, performing a fitting process, and determining the preset approximation condition; in response to the distribution parameters of the i-th control deviation satisfying the preset approximation condition with the distribution parameters of the (i - 1)-th control deviation, use the distribution parameters of the i-th control deviation as the distribution parameters of the control deviation within the reference period, use the time period corresponding to the first i preset time periods as the reference period, and use the end moment of the i-th preset time period as the starting moment of the new reference period, and repeat the steps of performing a frequency statistics on the control deviation within the first i preset time periods, performing a fitting process, and determining the preset approximation condition for the new reference period.

[0127] Optionally, the control unit 703 may further: discretize the estimated distribution parameters of the control signal at the current moment to obtain a plurality of control signals and the control signal probabilities of each control signal; discretize the distribution parameters of the control deviation within the reference period to obtain a plurality of control deviations and the control deviation probabilities of each control deviation; for each control signal and each control deviation, perform a superposition correction process to obtain a corresponding corrected control signal, and determine the product of the control signal probability of the control signal and the control deviation probability of the control deviation as the correction probability of the corresponding corrected control signal; perform a fitting process on the obtained plurality of corrected control signals and the correction probabilities of each corrected control signal to obtain the corrected distribution parameters of the control signal at the current moment.

[0128] Optionally, the control unit 703 may further: determine the control signal at the current moment according to the estimated distribution parameters of the control signal at the current moment, the correspondence between the control signal and the load, and the reference load range.

[0129] Optionally, the control unit 703 may further: determine the probability that the load falls within the reference load range according to the estimated distribution parameters at the current moment, the correspondence between the control signal and the load, and the reference load range, as the reference probability; in response to the reference probability being greater than or equal to the probability threshold, determine the reference control signal range corresponding to the reference load range; determine the generated power corresponding to a plurality of reference control signals within the reference control signal range according to the correspondence between the control signal and the generated power; determine the control signal at the current moment from the plurality of reference control signals according to the generated power corresponding to the plurality of reference control signals.

[0130] Optionally, the control unit 703 may further: in response to the reference probability being less than the probability threshold, determine the reference control signal corresponding to the upper limit value of the reference load range as the control signal at the current moment.

[0131] Regarding the device in the above embodiments, the specific manners in which each unit performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0132] The control method of a wind turbine according to an embodiment of the present disclosure can be written as a computer program and stored on a computer-readable storage medium. When the instructions corresponding to the computer program are executed by a processor, the control method of the wind turbine as described above can be implemented. Examples of computer-readable storage media include: read-only memory (ROM), random access programmable read-only memory (PROM), electrically erasable programmable read-only memory (EEPROM), random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), flash memory, non-volatile memory, CD-ROM, CD-R, CD+R, CD-RW, CD+RW, DVD-ROM, DVD-R, DVD+R, DVD-RW, DVD+RW, DVD-RAM, BD-ROM, BD-R, BD-R LTH, BD-RE, Blu-ray or optical disc memory, hard disk drive (HDD), solid state drive (SSD), cartridge memory (such as, multimedia card, secure digital (SD) card or extreme digital (XD) card), magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid state disk, and any other device that is configured to store a computer program and any associated data, data files, and data structures in a non-transitory manner and provide the computer program and any associated data, data files, and data structures to a processor or computer such that the processor or computer can execute the computer program. In one example, the computer program and any associated data, data files, and data structures are distributed across a networked computer system such that the computer program and any associated data, data files, and data structures are stored, accessed, and executed in a distributed manner by one or more processors or computers.

[0133] Figure 8 is a block diagram showing a computer device according to an embodiment of the present disclosure.

[0134] Referring to Figure 8 , the computer device 800 includes at least one memory 801 and at least one processor 802. A set of computer-executable instructions is stored in the at least one memory 801. When the set of computer-executable instructions is executed by the at least one processor 802, the control method of the wind turbine according to an exemplary embodiment of the present disclosure is executed.

[0135] As an example, the computer device 800 can be a PC computer, a tablet device, a personal digital assistant, a smart phone, or other devices capable of executing the above instruction set. Here, the computer device 800 does not have to be a single electronic device, and can also be a collection of devices or circuits that can execute the above instructions (or instruction sets) individually or jointly. The computer device 800 can also be a part of an integrated control system or a system manager, or can be configured as a portable electronic device that can be interconnected with a local or remote device (e.g., via wireless transmission).

[0136] In the computer device 800, the processor 802 can include a central processing unit (CPU), a graphics processing unit (GPU), a programmable logic device, a dedicated processor system, a microcontroller, or a microprocessor. As an example and not a limitation, the processor can also include an analog processor, a digital processor, a microprocessor, a multi-core processor, a processor array, a network processor, etc.

[0137] The processor 802 can run instructions or code stored in the memory 801, where the memory 801 can also store data. The instructions and data can also be sent and received via the network interface device over the network, where the network interface device can use any known transmission protocol.

[0138] It should be understood that the processor in the control system of the wind turbine generator set according to the embodiments of the present disclosure can have a hardware structure similar to that of the processor 802 here.

[0139] The memory 801 can be integrated with the processor 802. For example, RAM or flash memory can be arranged within an integrated circuit microprocessor, etc. In addition, the memory 801 can include independent devices, such as an external disk drive, a storage array, or other storage devices that can be used by any database system. The memory 801 and the processor 802 can be operatively coupled or can communicate with each other, for example, through an I / O port, a network connection, etc., so that the processor 802 can read the files stored in the memory.

[0140] In addition, the computer device 800 can also include a video display (such as a liquid crystal display) and a user interaction interface (such as a keyboard, a mouse, a touch input device, etc.). All components of the computer device 800 can be connected to each other via a bus and / or a network.

[0141] The present disclosure provides a control method, device, system, and storage medium for a wind turbine generator. By obtaining the preset values of control parameters and multiple historical measurement signals within a historical period, it is possible to reflect the uncertainty of the measurement signal at the current moment with the help of the multiple historical measurement signals, and then obtain the estimated distribution parameters of the control signal at the current moment in combination with the preset values of the control parameters. Compared with the traditional solution of directly determining the control signal at the current moment based on the measurement signal at the current moment, it is possible to give the control signal from the perspective of probability statistics while fully considering the uncertainty of the measurement signal, reducing the influence of the measurement uncertainty of the traditional measurement sensor on the control accuracy, without the need to additionally replace expensive high-precision sensors, and achieving an improvement in control accuracy at low cost. In addition, by obtaining the distribution parameters of the control deviation within a reference period, it is possible to predict in advance from the perspective of probability statistics the possible control deviation of the new control signal, and then correspondingly correct the estimated distribution parameters of the control signal at the current moment, which can further improve the control accuracy.

[0142] The specific embodiments of the present disclosure have been described in detail above. Although some embodiments have been shown and described, those skilled in the art should understand that these embodiments can be modified and varied without departing from the principles and spirit of the present disclosure defined by the claims and their equivalents, and these modifications and variations should also be within the protection scope of the claims of the present disclosure.

Claims

1. A control method for a wind turbine generator set, characterized in that, Including: Obtaining preset values of control parameters and multiple historical measurement signals of a wind turbine generator set within a historical period; Determining an estimated distribution parameter of a control signal at the current moment according to the preset values and the multiple historical measurement signals; Determining a probability that a load falls within the reference load range according to the estimated distribution parameter of the control signal at the current moment, the corresponding relationship between the control signal and the load, and the reference load range, as a reference probability; In response to the reference probability being greater than or equal to a probability threshold, determining a reference control signal range corresponding to the reference load range; Determining generated powers corresponding to multiple reference control signals within the reference control signal range according to the corresponding relationship between the control signal and the generated power; Determining a control signal at the current moment from the multiple reference control signals according to the generated powers corresponding to the multiple reference control signals; In response to the reference probability being less than the probability threshold, determining a reference control signal corresponding to the upper limit value of the reference load range as the control signal at the current moment.

2. The control method according to claim 1, wherein, The determining an estimated distribution parameter of a control signal at the current moment according to the preset values and the multiple historical measurement signals includes: Obtaining a reference measurement signal according to the multiple historical measurement signals; Determining an estimated distribution parameter of the control signal at the current moment according to each reference measurement signal and the preset values.

3. The control method according to claim 2, wherein The obtaining a reference measurement signal according to the multiple historical measurement signals includes: Performing a fitting process on the multiple historical measurement signals to obtain distribution parameters of the historical measurement signals; Performing a discretization process on the distribution parameters of the historical measurement signals to obtain multiple reference measurement signals and a reference measurement signal probability of each reference measurement signal.

4. The control method according to claim 3, wherein, The determining an estimated distribution parameter of the control signal at the current moment according to each reference measurement signal and the preset values includes: Determining a reference control signal corresponding to the reference measurement signal according to each reference measurement signal and the preset values, and using the reference measurement signal probability of the reference measurement signal as a reference control signal probability; Performing a fitting process on the determined multiple reference control signals and the reference control signal probability of each reference control signal to obtain an estimated distribution parameter of the control signal at the current moment.

5. The control method according to claim 3, characterized in that The multiple historical measurement signals are measured by measurement sensors, and the performing a fitting process on the multiple historical measurement signals to obtain distribution parameters of the historical measurement signals includes: Performing a fitting process on the multiple historical measurement signals according to a reference distribution type to obtain the distribution parameters of the historical measurement signals, wherein the reference distribution type is related to the measurement sensors; or The reference distribution type is obtained through the following steps: Performing a frequency statistics on the multiple historical measurement signals; Based on the frequency statistics result of the multiple historical measurement signals, determining one from multiple candidate distribution types as the reference distribution type.

6. The control method according to any one of claims 1 to 5, characterized in that, Before the determining a control signal at the current moment according to the estimated distribution parameter of the control signal at the current moment, the control method further includes: Obtaining distribution parameters of a control deviation within a reference period, where the control deviation is a deviation between a measurement signal and a preset value; Among them, determining the control signal at the current moment according to the estimated distribution parameter of the current moment control signal includes: Based on the distribution parameter of the control deviation within the reference period, correcting the estimated distribution parameter of the control signal at the current moment to obtain the corrected distribution parameter of the control signal at the current moment; Determining the control signal at the current moment according to the corrected distribution parameter of the control signal at the current moment.

7. The control method according to claim 6, wherein The obtaining the distribution parameter of the control deviation within the reference period includes: Determining a plurality of continuously arranged preset time lengths starting from the starting moment; Performing frequency statistics on the control deviations within the first i preset time lengths to obtain the i-th statistical result; i is a positive integer; Performing fitting processing on the i-th statistical result to obtain the distribution parameter of the i-th control deviation; In response to the distribution parameter of the i-th control deviation not satisfying the preset approximation condition with the distribution parameter of the (i - 1)-th control deviation, increasing i by 1, and then repeating the steps of performing frequency statistics, fitting processing, and judgment of the preset approximation condition on the control deviations within the first i preset time lengths; In response to the distribution parameter of the i-th control deviation satisfying the preset approximation condition with the distribution parameter of the (i - 1)-th control deviation, taking the distribution parameter of the i-th control deviation as the distribution parameter of the control deviation within the reference period, taking the time period corresponding to the first i preset time lengths as the reference period, and taking the end moment of the i-th preset time length as the starting moment of the new reference period, and for the new reference period, repeating the steps of performing frequency statistics, fitting processing, and judgment of the preset approximation condition on the control deviations within the first i preset time lengths.

8. The control method according to claim 6, characterized in that, The correcting the estimated distribution parameter of the control signal at the current moment based on the distribution parameter of the control deviation within the reference period to obtain the corrected distribution parameter of the control signal at the current moment includes: Performing discretization processing on the estimated distribution parameter of the control signal at the current moment to obtain a plurality of control signals and the control signal probability of each control signal; Performing discretization processing on the distribution parameter of the control deviation within the reference period to obtain a plurality of control deviations and the control deviation probability of each control deviation; Performing superposition correction processing on each control signal and each control deviation to obtain the corresponding corrected control signal, and determining the product of the control signal probability of the control signal and the control deviation probability of the control deviation as the corrected probability of the corresponding corrected control signal; Performing fitting processing on the obtained plurality of corrected control signals and the corrected probability of each corrected control signal to obtain the corrected distribution parameter of the control signal at the current moment.

9. A control device for a wind power generation unit, characterized in that, Including: An acquisition unit configured to acquire preset values of control parameters of the wind turbine generator within a historical period and a plurality of historical measurement signals; A determination unit configured to determine the estimated distribution parameter of the control signal at the current moment according to the preset value and the plurality of historical measurement signals; A control unit configured to: according to the estimated distribution parameter of the control signal at the current moment, the corresponding relationship between the control signal and the load, and the reference load range, determine the probability that the load falls within the reference load range as the reference probability; In response to the reference probability being greater than or equal to the probability threshold, determine a reference control signal range corresponding to the reference load range; according to the correspondence between the control signal and the power generation amount, determine the power generation amounts corresponding to multiple reference control signals within the reference control signal range; according to the power generation amounts corresponding to the multiple reference control signals, determine the control signal at the current moment from the multiple reference control signals; In response to the reference probability being less than the probability threshold, determine the reference control signal corresponding to the upper limit value of the reference load range as the control signal at the current moment.

10. A control system for a wind power generation set, characterized in that, Comprising: A measurement sensor for collecting measurement signals of control parameters; A processor for: Obtain the preset values of the control parameters and multiple historical measurement signals of the wind turbine generator set within a historical period; According to the preset values and the multiple historical measurement signals, determine the estimated distribution parameters of the control signal at the current moment; A control decision maker for: According to the estimated distribution parameters of the control signal at the current moment, the correspondence between the control signal and the load, and the reference load range, determine the probability that the load falls within the reference load range as the reference probability; In response to the reference probability being greater than or equal to the probability threshold, determine a reference control signal range corresponding to the reference load range; According to the correspondence between the control signal and the power generation amount, determine the power generation amounts corresponding to multiple reference control signals within the reference control signal range; According to the power generation amounts corresponding to the multiple reference control signals, determine the control signal at the current moment from the multiple reference control signals; In response to the reference probability being less than the probability threshold, determine the reference control signal corresponding to the upper limit value of the reference load range as the control signal at the current moment.

11. The control system according to claim 10, wherein The processor is further used for: Obtain reference measurement signals according to the multiple historical measurement signals; According to each reference measurement signal and the preset value, determine the estimated distribution parameters of the control signal at the current moment.

12. The control system according to claim 11, wherein The processor comprises: A first signal analyzer for performing fitting processing on the multiple historical measurement signals to obtain the distribution parameters of the historical measurement signals; A first controller for discretizing the distribution parameters of the historical measurement signals to obtain multiple reference measurement signals and the reference measurement signal probabilities of each reference measurement signal.

13. The control system according to claim 12, wherein, The first controller is further used for: According to each reference measurement signal and the preset value, determine the reference control signal corresponding to the reference measurement signal, and use the reference measurement signal probability of the reference measurement signal as the reference control signal probability; Perform fitting processing on the determined multiple reference control signals and the reference control signal probabilities of each reference control signal to obtain the estimated distribution parameters of the control signal at the current moment.

14. The control system according to claim 12, wherein The first signal analyzer is further used for: Perform fitting processing on the multiple historical measurement signals according to the reference distribution type to obtain the distribution parameters of the historical measurement signals, wherein the reference distribution type is related to the measurement sensor; or The reference distribution type is obtained through the following steps: Perform frequency statistics on the multiple historical measurement signals; Based on the frequency statistics result of the multiple historical measurement signals, determine one from multiple candidate distribution types as the reference distribution type.

15. The control system according to any one of claims 10 to 14, characterized in that, The processor further includes: A second signal analyzer, configured to obtain distribution parameters of a control deviation within a reference period, where the control deviation is the deviation between a measurement signal and a preset value; A second controller, configured to correct the estimated distribution parameters of the control signal at the current moment based on the distribution parameters of the control deviation within the reference period, to obtain corrected distribution parameters of the control signal at the current moment; The control decision maker is further configured to determine the control signal at the current moment according to the corrected distribution parameters of the control signal at the current moment.

16. The control system according to claim 15, characterized in that, The second signal analyzer is further configured to: Determine a plurality of continuously arranged preset time durations starting from the starting moment; Perform frequency statistics on the control deviation within the first i preset time durations to obtain the i-th statistical result; i is a positive integer; Perform fitting processing on the i-th statistical result to obtain distribution parameters of the i-th control deviation; In response to the distribution parameters of the i-th control deviation not satisfying a preset approximation condition with the distribution parameters of the (i - 1)-th control deviation, increment i by 1, and then repeat the steps of performing frequency statistics, fitting processing, and judgment of the preset approximation condition on the control deviation within the first i preset time durations; In response to the distribution parameters of the i-th control deviation satisfying the preset approximation condition with the distribution parameters of the (i - 1)-th control deviation, use the distribution parameters of the i-th control deviation as the distribution parameters of the control deviation within the reference period, use the time period corresponding to the first i preset time durations as the reference period, and use the end moment of the i-th preset time duration as the starting moment of the new reference period. For the new reference period, repeat the steps of performing frequency statistics, fitting processing, and judgment of the preset approximation condition on the control deviation within the first i preset time durations.

17. The control system according to claim 15, wherein The second controller is further configured to: Perform discretization processing on the estimated distribution parameters of the control signal at the current moment to obtain a plurality of control signals and the control signal probability of each control signal; Perform discretization processing on the distribution parameters of the control deviation within the reference period to obtain a plurality of control deviations and the control deviation probability of each control deviation; For each control signal and each control deviation, perform superposition correction processing to obtain a corresponding corrected control signal, and determine the product of the control signal probability of the control signal and the control deviation probability of the control deviation as the corrected probability of the corresponding corrected control signal; Perform fitting processing on the obtained plurality of corrected control signals and the corrected probability of each corrected control signal to obtain the corrected distribution parameters of the control signal at the current moment.

18. A computer-readable storage medium, characterized in that, When the instructions in the computer-readable storage medium are run by at least one processor, cause the at least one processor to execute the control method of the wind turbine generator set according to any one of claims 1 to 8.

19. A computer device, characterized in that, Including: At least one processor; At least one memory storing computer-executable instructions, wherein, when the computer-executable instructions are run by the at least one processor, cause the at least one processor to execute the control method of the wind turbine generator set according to any one of claims 1 to 8.

Images