Wind turbine generator control algorithm optimization method and device and storage medium

Abstract

The invention provides a wind turbine generator control algorithm optimization method and device and a storage medium, and belongs to the field of wind turbine generator control. The method comprises the following steps: acquiring typical operation data acted by a target control algorithm; determining a target simulation wind condition according to the typical operation data; adjusting a target control algorithm according to the typical operation data; and performing a simulation test on the new target control algorithm by using the target simulation wind condition until the difference between the simulation test data of the new target control algorithm and the control expected parameter is smaller than a first preset value, so that the obtained new target control algorithm is the optimized target control algorithm. The target simulation wind condition acted by the target control algorithm is obtained in a simulation mode, and then the target simulation wind condition is utilized to carry out simulation testing on the adjusted new target control algorithm, so that optimization of the target control algorithm based on the typical wind condition acted by the target control algorithm is realized. And therefore, the optimized target control algorithm can achieve a more ideal effect in practical application.

Description

Technical Field

[0001] The present invention relates to the field of wind turbine generator set control, and in particular to a wind turbine generator set control algorithm optimization method, a wind turbine generator set control algorithm optimization device and a machine-readable storage medium. Background Art

[0002] When the control algorithm is applied to the field environment, it is often necessary to optimize and adjust the control parameters according to the response of the program under the actual wind conditions on site, so that the control algorithm can present the best control effect in the actual operation on site. At the same time, in the application process of the algorithm, there are some sites or positions with special wind conditions, and the general control parameters cannot show good control effects under these special wind conditions. Therefore, more targeted and better matched control parameters are needed to achieve good control effects for specific wind fields or positions.

[0003] Since many control algorithms have a certain impact on the safety of the unit, and the actual wind conditions are relatively random, it is likely that the typical wind conditions for the target control algorithm will not appear for a long time, so simulation is often used to optimize the control parameters in actual applications. However, standard simulation conditions have great limitations in the optimization and adjustment of parameters of specific algorithms, mainly manifested in the fact that there is an undetermined difference between the response of the unit under standard simulation conditions and the response under actual conditions on site. The parameters that meet the expectations of the algorithm under simulation conditions may not achieve the ideal effect in actual applications. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a method, device and storage medium for optimizing the control algorithm of a wind turbine set. The method uses simulation to obtain the target simulated wind conditions under which the target control algorithm acts, and then uses the target simulated wind conditions to simulate and test the adjusted new target control algorithm, thereby optimizing the target control algorithm based on the typical wind conditions under which the target control algorithm acts, thereby ensuring that the optimized target control algorithm can achieve more ideal results in actual applications.

[0005] In order to achieve the above object, the first aspect of the present invention provides a wind turbine control algorithm optimization method, the wind turbine control algorithm optimization method comprising: Obtain typical operating data of the target control algorithm; Determine the target simulated wind condition based on typical operation data; The target control algorithm is adjusted according to typical operating data, and the new target control algorithm is simulated and tested using the target simulated wind conditions until the gap between the simulation test data of the new target control algorithm and the expected control parameters is less than a first preset value, and the obtained new target control algorithm is the optimized target control algorithm.

[0006] According to the above technical means, the target simulation wind conditions of the target control algorithm are obtained by simulation, and then the target simulation wind conditions are used to simulate and test the adjusted new target control algorithm, so as to optimize the target control algorithm based on the typical wind conditions of the target control algorithm, thereby ensuring that the optimized target control algorithm can achieve more ideal results in actual applications.

[0007] In the embodiment of the present application, typical operation data of the target control algorithm is obtained, including: Obtain actual operation data during the operation of the target control algorithm; Extracting the operation data of the time period in which the target control algorithm is effective from the actual operation data as the target operation data; The target operation data is integrated and extracted to obtain typical operation data.

[0008] According to the above technical means, the operating data of the target control algorithm's action time period is obtained from the actual operating data recorded during the operation of the wind turbine set, and the typical operating data obtained by integrating these operating data can better characterize the wind conditions and operating conditions when the target control algorithm takes effect.

[0009] In the embodiment of the present application, the target operation data is integrated and extracted to obtain typical operation data, including: Count the data characteristics of each parameter in the time series of each target operation data; grouping the target operation data according to the data characteristics of each target operation data; Typical operating data are determined based on each set of target operating data.

[0010] According to the above technical means, the data characteristics of different target operating data in time series are the key points of the algorithm operation within the time period. The change process of the data characteristics of the same group is similar. The typical operating data representing the key points of the group of characteristics is determined, which can better characterize the wind conditions and operating conditions when the target control algorithm takes effect.

[0011] In the embodiment of the present application, determining the target simulated wind condition according to typical operation data includes: Conduct wind condition simulation based on wind condition data in typical operation data; Use simulated wind conditions to simulate and test the target control algorithm; The simulation test results are compared with the key operating parameters in the typical operating data to adjust the setting parameters of the wind condition simulation until the difference between the simulation test results and the key operating parameters in the typical operating data is less than a second preset value, and the current simulated wind condition is determined to be the target simulated wind condition.

[0012] According to the above-mentioned technical means, wind condition simulation is performed according to the wind condition data in the typical operating data, and the target control algorithm is used as a fixed quantity. The setting parameters of the wind condition simulation are adjusted to make the simulation test results close to the key operating parameters in the typical operating data, thereby obtaining the simulated wind condition under which the target control algorithm takes effect as the target simulated wind condition, so as to provide a simulated wind condition that is closer to the actual operating state for optimizing and adjusting the target control algorithm.

[0013] In the embodiment of the present application, the wind condition simulation is performed according to the wind condition data in the typical operation data, including: Setting initial setting parameters of wind condition simulation according to wind condition data in typical operation data; The simulation software is used to simulate the wind conditions according to the initial setting parameters.

[0014] According to the above technical means, the initial setting parameters of the wind condition simulation are set according to the wind condition data in the typical operation data, so that the wind condition simulation process can be accelerated and the target simulated wind condition that meets the expected target can be simulated more quickly.

[0015] In the embodiment of the present application, adjusting the target control algorithm according to typical operation data includes: The target control algorithm is adjusted according to the gap between the key operating parameters in the typical operating data and the control expected parameters of the target control algorithm.

[0016] According to the above technical means, the expected control parameters are compared with the key operating parameters of the actual operation, so as to adjust the target control algorithm, which can make the adjustment of the algorithm more targeted.

[0017] In an embodiment of the present application, a new target control algorithm is simulated and tested using a target simulated wind condition until the difference between the simulation test data of the new target control algorithm and the control expected parameter is less than a first preset value, including: Use the target simulated wind condition to simulate and test the new target control algorithm to obtain simulation test data; Determine the difference direction according to the gap between the simulation test data and the control expected parameters and the gap between the key operating parameters in the typical operating data and the control expected parameters; Adjust the target control algorithm according to the difference direction; Repeat the above steps until the gap between the simulation test data of the new target control algorithm and the control expected parameters is smaller than the first preset value.

[0018] According to the above technical means, the difference direction can be determined according to the first control algorithm adjustment direction and the gap between the simulation test data and the expected control parameters after simulation. Further adjustment according to the difference direction can adjust and optimize more quickly to obtain the optimized target control algorithm.

[0019] In the embodiment of the present application, the difference direction is determined according to the gap between the simulation test data and the expected control parameters and the gap between the key operation parameters in the typical operation data and the expected control parameters, including: calculating a first gap between a key operating parameter in typical operating data and a control expected parameter of a target control algorithm; Calculating a second gap between the simulation test data and the control expected parameters; comparing the absolute value of the first disparity with the absolute value of the second disparity; If the absolute value of the first gap is smaller than the absolute value of the second gap, it is determined whether the current first gap and the second gap are of the same sign. If they are of the same sign, it is determined that the current adjustment direction of the target control algorithm is a difference increasing direction, and it is necessary to continue to adjust in the opposite direction of the current adjustment direction; if they are of different signs, it is determined that the current adjustment direction of the target control algorithm is a difference reducing direction, and it is necessary to continue to adjust in the opposite direction of the current adjustment direction; If the absolute value of the first gap is greater than the absolute value of the second gap, determine whether the current first gap and the second gap are of the same sign. If they are of the same sign, determine that the current adjustment direction of the target control algorithm is the direction of reducing the difference, and need to continue to adjust along the current adjustment direction; if they are of different signs, determine that the current adjustment direction of the target control algorithm is the direction of reducing the difference, and need to continue to adjust in the opposite direction of the current adjustment direction.

[0020] According to the above technical means, whether the current adjustment direction can optimize the algorithm can be determined based on whether the simulation test results obtained after the first control algorithm adjustment are closer to or further away from the expectation, so as to obtain the optimized target control algorithm more quickly.

[0021] A second aspect of the present application provides a wind turbine control algorithm optimization device, the wind turbine control algorithm optimization device comprising: A typical operation data acquisition unit, used to acquire typical operation data of the target control algorithm; A target simulated wind condition determination unit, used to determine a target simulated wind condition according to typical operation data; A target control algorithm adjustment unit, used for adjusting the target control algorithm according to typical operation data; The simulation test unit is used to perform simulation test on the new target control algorithm using the target simulated wind condition until the gap between the simulation test data of the new target control algorithm and the expected control parameters is less than a first preset value, and the obtained new target control algorithm is the optimized target control algorithm.

[0022] According to the above-mentioned technical means, the device uses simulation to obtain the target simulated wind conditions under which the target control algorithm acts, and then uses the target simulated wind conditions to simulate and test the adjusted new target control algorithm, thereby optimizing the target control algorithm based on the typical wind conditions under which the target control algorithm acts, thereby ensuring that the optimized target control algorithm can achieve more ideal results in actual applications.

[0023] A third aspect of the present application provides a machine-readable storage medium, on which instructions are stored, and the instructions are used to enable a machine to execute the wind turbine control algorithm optimization method.

[0024] Through the above technical scheme, the target simulation wind conditions of the target control algorithm are obtained by simulation, and then the target simulation wind conditions are used to simulate and test the adjusted new target control algorithm, so as to optimize the target control algorithm based on the typical wind conditions of the target control algorithm, thereby ensuring that the optimized target control algorithm can achieve more ideal results in actual applications.

[0025] This method uses hardware test simulation to find the simulation condition whose simulation result under the current program is closest to the actual response on site, and performs optimization test of the specific control algorithm under this simulation condition, making the control algorithm optimization process more concise and efficient, and the optimization can better present the expected control effect in the actual site.

[0026] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings: Figure 1 It is a flow chart of a wind turbine control algorithm optimization method provided by an embodiment of the present invention; Figure 2 It is a flow chart of wind turbine control algorithm optimization implementation provided by one embodiment of the present invention; Figure 3 It is a block diagram of a wind turbine control algorithm optimization device provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0028] The specific implementation of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the present invention, and is not used to limit the present invention.

[0029] In order to meet the actual operating conditions of the wind farm, a variety of control algorithms need to be added to the control system of the wind turbine to solve different problems, such as preventing overspeed, preventing clearance exceeding the limit or warning of special working conditions, etc. How to obtain the optimal algorithm parameters that can meet the safe operation of the unit and minimize the loss of power generation requires a lot of optimization and adjustment based on the actual wind conditions.

[0030] Taking into account the safety of unit operation and the randomness of on-site wind conditions, the optimization of the control algorithm generally first uses simulation to obtain the current optimal parameters and then applies them to the site. When optimizing the control algorithm through simulation, there are two critical points: 1. The reproduction of the typical actual wind conditions on site where the algorithm works; 2. The performance of the initial parameters of the control algorithm under the actual wind conditions on site. When the above two key issues are uncertain, it is difficult to complete the optimization of the control algorithm in a short time.

[0031] In order to solve the above problems, the present invention obtains a typical simulation condition that can represent the on-site wind speed, so that the optimization of the control algorithm can be more efficient and rapid.

[0032] Figure 1 FIG. 1 is a flow chart of a wind turbine control algorithm optimization method provided by an embodiment of the present invention. Figure 1 As shown, the wind turbine control algorithm optimization method includes: S1: Obtaining typical operating data of the target control algorithm. In the embodiment of the present application, the target control algorithm is an algorithm that needs to be optimized, such as an algorithm for preventing overspeed, preventing clearance exceeding the limit, or warning of special working conditions.

[0033] In the embodiment of the present application, typical operation data of the target control algorithm is obtained, including: The actual operation data during the operation of the target control algorithm is obtained. In the embodiment of the present application, the actual operation data is the data collected during the operation of the wind turbine group running the target control algorithm, including wind condition data and key operation parameters. The actual operation data can be directly read from the wind turbine group operation database.

[0034] The operation data of the target control algorithm action time period is extracted from the actual operation data as the target operation data. In the embodiment of the present application, the target control algorithm action time period refers to the time period when the target control algorithm takes effect or may take effect, for example, the overspeed algorithm focuses on the time period when the generator speed is high and close to the overspeed threshold.

[0035] The target operation data is integrated and extracted to obtain typical operation data.

[0036] In this embodiment, integrating and extracting the target operation data to obtain typical operation data specifically includes: Statistics are made on the time series data characteristics of each parameter in each target operation data. For each selected data segment, the wind conditions and key operation parameters such as wind speed, wind direction, generator speed, output power, blade angle and torque are observed and counted, including the size, change amplitude, duration of each stage and the corresponding relationship between each parameter in time, to obtain the data characteristics of each parameter in time series.

[0037] The target operation data are grouped according to the data characteristics of each target operation data, and the data with similar change processes are integrated into one group of data.

[0038] Typical operating data is determined according to each set of target operating data. Typical operating data refers to data that can characterize the wind conditions and key operating parameters in the set of target operating data.

[0039] In some embodiments, representative data can be determined from each set of target operation data as typical data, or the characteristic time series after adjusting specific parameters according to the overall law can be used as typical operation data. In some embodiments, the most representative 2-3 pieces of data can be determined from each set of target operation data as typical operation data.

[0040] The data characteristics of different target operating data in time series are the key points of the algorithm operation within the time period. The change process of the data characteristics of the same group is similar. The typical operating data representing the key points of the group's characteristics can be determined, which can better characterize the wind conditions and operating conditions when the target control algorithm takes effect.

[0041] The operation data of the target control algorithm's action period are obtained from the actual operation data recorded during the operation of the wind turbine. The typical operation data obtained by integrating these operation data can better characterize the wind conditions and operation status when the target control algorithm takes effect.

[0042] S2: Determine the target simulated wind condition according to the typical operation data. In the embodiment of the present application, the target simulated wind condition is the wind condition when the simulated target control algorithm takes effect.

[0043] In the embodiment of the present application, determining the target simulated wind condition according to typical operation data includes: 1) Perform wind simulation based on the wind data in typical operation data, specifically: First, the initial setting parameters of wind simulation are set according to the wind data in the typical operation data, and the initial setting parameters include: initial value of wind speed and direction, change amplitude, change process, change start time and change duration, etc. Then, the simulation software is used to simulate the wind according to the initial setting parameters.

[0044] Setting the initial setting parameters of the wind simulation according to the wind data in the typical operation data can speed up the wind simulation process and more quickly simulate the expected target simulation wind conditions.

[0045] 2) Use simulated wind conditions to simulate and test the target control algorithm.

[0046] 3) Compare the simulation test results with the key operating parameters in the typical operating data to adjust the setting parameters of the wind condition simulation until the difference between the simulation test results and the key operating parameters in the typical operating data is less than the second preset value, and determine that the current simulated wind condition is the target simulated wind condition. If the key parameter change process and characteristics differ greatly from the actual operating data change process and characteristics, adjust the setting parameters of the simulated wind condition and retest until the test results show that the difference between the change process and characteristics of the key operating parameters and the actual operating data is less than the second preset value. It is considered that the performance of the current simulated wind condition in the simulation process can reflect the wind condition when the target control algorithm takes effect. This wind condition is determined as the target simulated wind condition for the target control algorithm program optimization. In the embodiment of the present application, the smaller the difference between the simulation test results and the key operating parameters in the typical operating data, the closer the simulated wind condition is to the wind condition in the typical operating data. Therefore, the second preset value can be set according to the requirements for the degree of algorithm optimization.

[0047] Wind condition simulation is performed based on wind condition data in typical operating data. The target control algorithm is used as a fixed quantity, and the setting parameters of the wind condition simulation are adjusted to make the simulation test results close to the key operating parameters in the typical operating data, so as to obtain the simulated wind condition under which the target control algorithm takes effect as the target simulated wind condition, so as to provide a simulated wind condition that is closer to the actual operating state for optimizing and adjusting the target control algorithm.

[0048] S3: Adjust the target control algorithm based on typical operating data.

[0049] In the embodiment of the present application, adjusting the target control algorithm according to typical operation data includes: The target control algorithm is adjusted according to the gap between the key operating parameters in the typical operating data and the expected control parameters of the target control algorithm. The expected control parameters of the target control algorithm are the values ​​that the key operating parameters of the wind turbine are expected to reach when the target control algorithm is running when the target control algorithm is designed. The key operating parameters in the typical operating data are the actual measured values ​​of the key operating parameters of the wind turbine when the target control algorithm is running during the actual operation of the wind turbine. In order for the target control algorithm to achieve the ideal effect in practical applications, it is necessary to adjust the target control algorithm according to the gap between the key operating parameters and the expected control parameters. The gap between the key operating parameters and the expected control parameters can be the gap between some of the parameters or the gap between the overall data.

[0050] According to the above technical means, the expected control parameters are compared with the key operating parameters of the actual operation, so as to adjust the target control algorithm, which can make the adjustment of the algorithm more targeted.

[0051] S4: Performing simulation test on the new target control algorithm using the target simulated wind condition until the difference between the simulation test data of the new target control algorithm and the control expected parameter is less than the first preset value, and the obtained new target control algorithm is the optimized target control algorithm, specifically including: Use the target simulated wind condition to simulate and test the new target control algorithm to obtain simulation test data; Determine the difference direction according to the gap between the simulation test data and the control expected parameters and the gap between the key operating parameters in the typical operating data and the control expected parameters; Adjust the target control algorithm according to the difference direction; Repeat the above steps until the gap between the simulation test data of the new target control algorithm and the control expected parameters is less than the first preset value. In the embodiment of the present application, the smaller the gap between the simulation test data and the control expected parameters, the more the new target control algorithm meets expectations. Therefore, the first preset value can be set according to the requirements for algorithm optimization accuracy.

[0052] The difference direction can be determined based on the initial control algorithm adjustment direction and the gap between the simulation test data and the expected control parameters after simulation. Further adjustments based on the difference direction can more quickly adjust and optimize to obtain the optimized target control algorithm.

[0053] In the embodiment of the present application, the difference direction is determined according to the gap between the simulation test data and the expected control parameters and the gap between the key operation parameters in the typical operation data and the expected control parameters, including: calculating a first gap between a key operating parameter in typical operating data and a control expected parameter of a target control algorithm; Calculating a second gap between the simulation test data and the control expected parameters; comparing the absolute value of the first disparity with the absolute value of the second disparity; If the absolute value of the first gap is smaller than the absolute value of the second gap, it is determined whether the current first gap and the second gap are of the same sign. If they are of the same sign, it is determined that the current adjustment direction of the target control algorithm is a difference increasing direction, and it is necessary to continue to adjust in the opposite direction of the current adjustment direction; if they are of different signs, it is determined that the current adjustment direction of the target control algorithm is a difference reducing direction, and it is necessary to continue to adjust in the opposite direction of the current adjustment direction; If the absolute value of the first gap is greater than the absolute value of the second gap, determine whether the current first gap and the second gap are of the same sign. If they are of the same sign, determine that the current adjustment direction of the target control algorithm is the direction of reducing the difference, and need to continue to adjust along the current adjustment direction; if they are of different signs, determine that the current adjustment direction of the target control algorithm is the direction of reducing the difference, and need to continue to adjust in the opposite direction of the current adjustment direction.

[0054] For example, assuming that the absolute value of the first gap is 3 and the absolute value of the second gap is 6, it can be determined that the absolute value of the first gap is smaller than the absolute value of the second gap. If the first gap is -3 and the second gap is -6, it can be determined that the gap between the simulation test data of the new target control algorithm and the expected control parameters is getting bigger and bigger. It can be determined that the current adjustment direction of the target control algorithm is the direction of increasing difference. In order to narrow the gap between the simulation test data and the expected control parameters, it is necessary to continue to adjust in the opposite direction of the first adjustment, that is, if the first parameter exists and the first adjustment is to increase the first parameter, then the first parameter needs to be reduced when adjusting again, and the adjustment amount needs to be increased. The specific adjustment amount can be determined based on the ratio of the absolute value of the second gap to the change amount and the first The relationship between the parameter and the change is calculated. For example, the first gap is -3, the second gap is -6, the change from the first gap to the second gap is 3, and the ratio of the absolute value of the second gap to the change is 6 / 3=2 times. Then, the adjustment amount of the first parameter is calculated according to the relationship between the first parameter and the change. If the first adjustment is to reduce the first parameter, the first parameter needs to be increased when adjusting again, and the adjustment amount needs to be increased. The ratio of the absolute value of the second gap to the change is 6 / 3=2 times. Then, the adjustment amount of the first parameter is calculated according to the relationship between the first parameter and the change, until the gap between the simulation test data and the expected control parameter is less than the first preset value, that is, the absolute value of the second gap is less than the first preset value.

[0055] If the first gap is -3 and the second gap is +6, it can be determined that the gap between the simulation test data of the new target control algorithm and the expected control parameters first narrowed and then increased in the opposite direction, and the increase was greater than the absolute value of the first gap. At this time, in order to achieve the purpose of narrowing the gap between the simulation test data and the expected control parameters, it is necessary to continue adjusting in the opposite direction of the first adjustment, and at the same time, it is necessary to reduce the adjustment amount to avoid excessive adjustment again. That is, if there is a first parameter, and the first adjustment is to increase the first parameter, then the first parameter needs to be reduced when adjusting again, and the adjustment amount needs to be reduced. The specific adjustment amount can be calculated based on the ratio of the absolute value of the second gap to the change amount and the relationship between the first parameter and the change amount. As mentioned above, the first gap is -3, the second gap is +6, the change amount from the first gap to the second gap is 9, and the ratio of the absolute value of the second gap to the change amount is 2 / 3, and then the adjustment amount of the first parameter is calculated based on the relationship between the first parameter and the change amount; if the first adjustment is to reduce the first parameter, then the first parameter needs to be increased when adjusting again, and the adjustment amount needs to be reduced at this time. The ratio of the absolute value of the second gap to the change amount is 6 / 9=2 / 3 times, and then the adjustment amount of the first parameter is calculated based on the relationship between the first parameter and the change amount, until the gap between the simulation test data and the expected control parameter is less than the first preset value, that is, the absolute value of the second gap is less than the first preset value.

[0056] Assuming that the absolute value of the first gap is 3 and the absolute value of the second gap is 2, it can be determined that the absolute value of the first gap is greater than the absolute value of the second gap. If the first gap is -3 and the second gap is -2, it can be determined that the gap between the simulation test data of the new target control algorithm and the expected control parameters is getting smaller and smaller. It can be determined that the current adjustment direction of the target control algorithm is the direction of reducing the difference. In order to further reduce the gap between the simulation test data and the expected control parameters, it is necessary to continue to adjust along the first adjustment direction, that is, if the first parameter exists, the first adjustment is to increase the first parameter, then the first parameter needs to be further increased when adjusting again. The specific adjustment amount can be based on the ratio of the absolute value of the second gap to the change amount and the first parameter. The relationship between the number and the change is calculated, as mentioned above, the first gap is -3, the second gap is -2, the change from the first gap to the second gap is 1, the absolute value of the second gap is in the ratio of the change amount to 2 / 1=2 times, and then the adjustment amount of the first parameter is calculated according to the relationship between the first parameter and the change amount; if the first adjustment is to reduce the first parameter, the first parameter needs to be further reduced when adjusting again, and the absolute value of the second gap is in the ratio of the change amount to 2 / 1=2 times, and then the adjustment amount of the first parameter is calculated according to the relationship between the first parameter and the change amount, until the gap between the simulation test data and the expected control parameter is less than the first preset value, that is, the absolute value of the second gap is less than the first preset value.

[0057] If the first gap is -3 and the second gap is +2, it can be determined that the gap between the simulation test data of the new target control algorithm and the expected control parameters first narrowed and then increased in the opposite direction, and the increase was less than the absolute value of the first gap. At this time, in order to achieve the purpose of narrowing the gap between the simulation test data and the expected control parameters, it is necessary to continue adjusting in the opposite direction of the first adjustment, and at the same time, it is necessary to reduce the adjustment amount to avoid excessive adjustment again. That is, if there is a first parameter, and the first adjustment is to increase the first parameter, then the first parameter needs to be reduced when adjusting again, and the adjustment amount needs to be reduced. The specific adjustment amount can be calculated based on the ratio of the absolute value of the second gap to the change amount and the relationship between the first parameter and the change amount. As mentioned above, the first gap is -3, the second gap is +2, the change amount from the first gap to the second gap is 5, and the ratio of the absolute value of the second gap to the change amount is 2 / 5. Then, the adjustment amount of the first parameter is calculated based on the relationship between the first parameter and the change amount; if the first adjustment is to reduce the first parameter, then the first parameter needs to be increased when adjusting again. At this time, the adjustment amount needs to be reduced. The ratio of the absolute value of the second gap to the change amount is 2 / 5 times. Then, the adjustment amount of the first parameter is calculated based on the relationship between the first parameter and the change amount, until the gap between the simulation test data and the expected control parameter is less than the first preset value, that is, the absolute value of the second gap is less than the first preset value.

[0058] Whether the current adjustment direction can optimize the algorithm can be determined based on whether the simulation test results obtained after the first control algorithm adjustment are closer to or further away from expectations, thereby obtaining the optimized target control algorithm more quickly.

[0059] According to the above technical means, the target simulation wind conditions of the target control algorithm are obtained by simulation, and then the target simulation wind conditions are used to simulate and test the adjusted new target control algorithm, so as to optimize the target control algorithm based on the typical wind conditions of the target control algorithm, thereby ensuring that the optimized target control algorithm can achieve more ideal results in actual applications.

[0060] During the actual implementation of the wind turbine control algorithm optimization method of the present application, it is necessary to load the target control algorithm or the adjusted target control algorithm into the PLC controller for operation. The PLC controller needs to be the same as the PLC controller used by the on-site unit control system. At the same time, a host computer running wind turbine simulation software is also required to simulate the target simulated wind conditions based on typical operating data.

[0061] like Figure 2As shown, in the specific implementation process of the wind turbine control algorithm optimization method of the present application, the actual operating data during the operation of the target control algorithm is first obtained, and then the typical operating data of the target control algorithm action time period is extracted from the actual operating data, the typical operating data including wind condition data and key operating parameters; then, wind condition simulation is performed based on the wind condition data in the typical operating data; interactive simulation test is performed using the simulated wind condition and the PLC running the target control algorithm to determine whether the simulation test results are consistent with the key operating parameters in the typical operating data; if not, the setting parameters of the wind condition simulation are adjusted until the simulation test results are consistent with the key operating parameters in the typical operating data, and the target control algorithm is optimized using the target simulated wind condition obtained by the final simulation. During the optimization process of the target control algorithm, the target control algorithm is first adjusted according to the gap between the key operating parameters and the expected control parameters of the target control algorithm, the new target control algorithm is reloaded into the PLC, and the target simulated wind conditions are used to perform interactive simulation tests with the PLC to determine whether the simulation test results are consistent with the expected control parameters of the target control algorithm. If not, the target control algorithm is adjusted according to the gap between the simulation test data and the expected control parameters until the simulation test results are consistent with the expected control parameters of the target control algorithm. The optimization of the target control algorithm is completed, and a new version of the control program is formed for on-site application.

[0062] The second aspect of the present application provides a wind turbine control algorithm optimization device, such as Figure 3 As shown, the wind turbine control algorithm optimization device includes: A typical operation data acquisition unit, used to acquire typical operation data of the target control algorithm; A target simulated wind condition determination unit, used to determine a target simulated wind condition according to typical operation data; A target control algorithm adjustment unit, used for adjusting the target control algorithm according to typical operation data; The simulation test unit is used to perform simulation test on the new target control algorithm using the target simulated wind condition until the gap between the simulation test data of the new target control algorithm and the expected control parameters is less than a first preset value, and the obtained new target control algorithm is the optimized target control algorithm.

[0063] According to the above-mentioned technical means, the device uses simulation to obtain the target simulated wind conditions under which the target control algorithm acts, and then uses the target simulated wind conditions to simulate and test the adjusted new target control algorithm, thereby optimizing the target control algorithm based on the typical wind conditions under which the target control algorithm acts, thereby ensuring that the optimized target control algorithm can achieve more ideal results in actual applications.

[0064] A third aspect of the present application provides a machine-readable storage medium, on which instructions are stored, and the instructions are used to enable a machine to execute the wind turbine control algorithm optimization method.

[0065] Those skilled in the art will understand that all or part of the steps in the method for implementing the above-mentioned embodiments can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including several instructions for making a single-chip microcomputer, a chip or a processor execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0066] The optional embodiments of the present invention are described in detail above in conjunction with the accompanying drawings. However, the embodiments of the present invention are not limited to the specific details in the above embodiments. Within the technical concept of the embodiments of the present invention, the technical scheme of the embodiments of the present invention can be subjected to a variety of simple modifications, and these simple modifications all belong to the protection scope of the embodiments of the present invention. It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the embodiments of the present invention will not further describe various possible combinations.

[0067] In addition, various embodiments of the present invention may be arbitrarily combined, and as long as they do not violate the concept of the embodiments of the present invention, they should also be regarded as the contents disclosed in the embodiments of the present invention.

Claims

1. A wind turbine control algorithm optimization method, characterized in that: The wind turbine control algorithm optimization method comprises: Obtain typical operating data of the target control algorithm; Determine the target simulated wind condition based on typical operation data; The target control algorithm is adjusted according to typical operating data, and the new target control algorithm is simulated and tested using the target simulated wind conditions until the gap between the simulation test data of the new target control algorithm and the expected control parameters is less than a first preset value, and the obtained new target control algorithm is the optimized target control algorithm.

2. The wind turbine control algorithm optimization method according to claim 1, characterized in that: Obtain typical operating data of the target control algorithm, including: Obtain actual operation data during the operation of the target control algorithm; Extracting the operation data of the time period in which the target control algorithm is effective from the actual operation data as the target operation data; The target operation data is integrated and extracted to obtain typical operation data.

3. The wind turbine control algorithm optimization method according to claim 2, characterized in that: Integrate and extract the target operation data to obtain typical operation data, including: Count the data characteristics of each parameter in the time series of each target operation data; grouping the target operation data according to the data characteristics of each target operation data; Typical operating data are determined based on each set of target operating data.

4. The wind turbine control algorithm optimization method according to claim 1, characterized in that: Determine the target simulated wind conditions based on typical operating data, including: Conduct wind condition simulation based on wind condition data in typical operation data; Use simulated wind conditions to simulate and test the target control algorithm; The simulation test results are compared with the key operating parameters in the typical operating data to adjust the setting parameters of the wind condition simulation until the difference between the simulation test results and the key operating parameters in the typical operating data is less than a second preset value, and the current simulated wind condition is determined to be the target simulated wind condition.

5. The wind turbine control algorithm optimization method according to claim 4, characterized in that: Wind simulation is performed based on wind data from typical operating data, including: Setting initial setting parameters of wind condition simulation according to wind condition data in typical operation data; The simulation software is used to simulate the wind conditions according to the initial setting parameters.

6. The wind turbine control algorithm optimization method according to claim 1, characterized in that: Adjust the target control algorithm based on typical operating data, including: The target control algorithm is adjusted according to the gap between the key operating parameters in the typical operating data and the control expected parameters of the target control algorithm.

7. The wind turbine control algorithm optimization method according to claim 6, characterized in that: The new target control algorithm is simulated and tested using the target simulated wind condition until the difference between the simulation test data of the new target control algorithm and the control expected parameter is less than a first preset value, including: Use the target simulated wind condition to simulate and test the new target control algorithm to obtain simulation test data; Determine the difference direction according to the gap between the simulation test data and the control expected parameters and the gap between the key operating parameters in the typical operating data and the control expected parameters; Adjust the target control algorithm according to the difference direction; Repeat the above steps until the gap between the simulation test data of the new target control algorithm and the control expected parameters is smaller than the first preset value.

8. The wind turbine control algorithm optimization method according to claim 7, characterized in that: Determining the difference direction according to the gap between the simulation test data and the expected control parameters and the gap between the key operating parameters in the typical operating data and the expected control parameters includes: calculating a first gap between a key operating parameter in typical operating data and a control expected parameter of a target control algorithm; Calculating a second gap between the simulation test data and the control expected parameters; comparing the absolute value of the first disparity with the absolute value of the second disparity; If the absolute value of the first gap is smaller than the absolute value of the second gap, it is determined whether the current first gap and the second gap are of the same sign. If they are of the same sign, it is determined that the current adjustment direction of the target control algorithm is a difference increasing direction, and it is necessary to continue to adjust in the opposite direction of the current adjustment direction; if they are of different signs, it is determined that the current adjustment direction of the target control algorithm is a difference reducing direction, and it is necessary to continue to adjust in the opposite direction of the current adjustment direction; If the absolute value of the first gap is greater than the absolute value of the second gap, determine whether the current first gap and the second gap are of the same sign. If they are of the same sign, determine that the current adjustment direction of the target control algorithm is the direction of reducing the difference, and need to continue to adjust along the current adjustment direction; if they are of different signs, determine that the current adjustment direction of the target control algorithm is the direction of reducing the difference, and need to continue to adjust in the opposite direction of the current adjustment direction.

9. A wind turbine control algorithm optimization device, characterized in that: The wind turbine control algorithm optimization device comprises: A typical operation data acquisition unit, used to acquire typical operation data of the target control algorithm; A target simulated wind condition determination unit, used to determine a target simulated wind condition according to typical operation data; A target control algorithm adjustment unit, used for adjusting the target control algorithm according to typical operation data; The simulation test unit is used to perform simulation test on the new target control algorithm using the target simulated wind condition until the gap between the simulation test data of the new target control algorithm and the expected control parameters is less than a first preset value, and the obtained new target control algorithm is the optimized target control algorithm.

10. A machine-readable storage medium having instructions stored thereon, characterized in that: The instruction is used to enable the machine to execute the wind turbine control algorithm optimization method described in any one of claims 1 to 8 of the present application.

Images