Electrical automation control system and method

Abstract

The invention provides an electrical automation control system and method. The method comprises the steps that multi-source heterogeneous data in the operation process of a wind driven generator is collected; performing feature coupling processing on the multi-source heterogeneous data to obtain dynamic association features among different state parameters during power generation of the motor rotor; determining stability margins of different control loops in the wind driven generator based on the time-varying characteristic of each dynamic correlation characteristic, and performing cooperative compensation on each control signal in the wind driven generator based on all the stability margins to obtain a multi-stage compensation control signal of the wind driven generator; according to the interference gradient determined by the multi-source heterogeneous data, the cooperation coefficient of each compensation control signal in the multi-stage compensation control signals is adjusted; and performing cooperative control on each control loop based on the multi-stage compensation control signal and the adjusted cooperative coefficient of each compensation control signal. According to the scheme provided by the invention, different control loops in the wind driven generator can be cooperatively controlled under the influence of the dynamic coupling relationship of the different control loops.

Description

Technical Field

[0001] This application relates to the technical field of wind turbines. More specifically, this application relates to an electrical automation control system and method. Background Art

[0002] With the increasing global demand for clean energy, wind power generation, as a renewable and pollution-free energy utilization method, has received extensive attention. Wind turbines are key devices for converting wind energy into electrical energy. Their technology has evolved from small-scale to large-scale and from low efficiency to high efficiency. Early wind turbines had relatively small power and low efficiency, mainly used for small-scale power supply. With the progress of materials science, aerodynamics, and power electronics technology, the single-unit capacity of modern wind turbines has been continuously increasing, the blade design has been more optimized, with higher wind energy capture capabilities and power generation efficiency, and they can adapt to different wind speeds and environmental conditions. At the same time, the development of intelligent control systems has made their operation more stable and reliable, and the maintenance cost has been reduced.

[0003] In existing wind turbines, the control of existing wind turbines mainly includes pitch control and variable speed control. Pitch control changes the windward angle of the blades by adjusting the pitch angle of the blades, thereby regulating the aerodynamic torque. Variable speed control adjusts the speed of the generator through a power electronic converter to synchronize it with the grid frequency and optimize the power output. The combination of these control methods can achieve the efficient operation and safety protection of wind turbines under different wind speeds. However, in the control of wind turbines, there is usually a dynamic coupling relationship between different control loops (that is, the control behavior of one loop may affect the control effect of other loops). This coupling relationship changes with the change of the operating state of the wind turbine and cannot perform coordinated control on each control loop in wind power generation, resulting in a response lag during the control process of the wind turbine. Therefore, how to achieve coordinated control of different control loops in a wind turbine under the influence of the dynamic coupling relationship between different control loops has become a difficult problem faced by the industry. Summary of the Invention

[0004] This application provides an electrical automation control system and method, which can achieve coordinated control of different control loops in a wind turbine under the influence of the dynamic coupling relationship between different control loops.

[0005] In a first aspect, this application provides an electrical automation control method for automatically controlling a wind turbine. The method includes the following steps: Collect multi-source heterogeneous data at the motor rotor during the operation of the wind turbine and upload the multi-source heterogeneous data to the edge computing gateway; The edge computing gateway performs feature coupling processing on the multi-source heterogeneous data to obtain the dynamic association features between different state parameters during the power generation of the motor rotor; Based on the time-varying characteristics of each dynamic association feature under the change of the time period, the stability margin of different control loops in the wind turbine is determined, and then based on the stability margin of each control loop, each control signal in the wind turbine is cooperatively compensated to obtain the multi-level compensation control signal of the wind turbine; The multi-source heterogeneous data is analyzed to obtain the interference gradient of the wind turbine during operation affected by the environment, and the cooperation coefficient of each compensation control signal in the multi-level compensation control signal is adjusted according to the interference gradient; The edge computing gateway performs cooperative control on each control loop in the wind turbine based on the multi-level compensation control signal and the adjusted cooperation coefficient of each compensation control signal.

[0006] In some embodiments, the edge computing gateway performs feature coupling processing on the multi-source heterogeneous data to obtain the dynamic association features between different state parameters during the power generation of the motor rotor, which specifically includes: The multi-source heterogeneous data is normalized to obtain the normalized multi-source heterogeneous data; The normalized heterogeneous data corresponding to each state parameter during the operation of the wind turbine is extracted from the normalized multi-source heterogeneous data; The normalized heterogeneous data of different state parameters is subjected to association calculation through a preset association model, and then the dynamic association features between different state parameters during the power generation of the motor rotor are obtained.

[0007] In some embodiments, determining the stability margin of different control loops in the wind turbine based on the time-varying characteristics of each dynamic association feature under the change of the time period specifically includes: The dynamic association features between different state parameters during the operation of the wind turbine under different historical time periods are obtained to obtain the dynamic association feature sequence corresponding to different state parameters; According to the dynamic association feature sequence corresponding to each different state parameter, the time-varying characteristics of each dynamic association feature under the change of the time period are calculated; The steady-state parameters during the operation of the wind turbine are determined through all the time-varying characteristics; The parameter change data of different control loops during the operation of the wind turbine is obtained; One control loop is selected as the selected control loop, and the response fluctuation trend of the selected control loop is calculated through the parameter change data of the selected control loop; Determine the stability margin of the selected control loop in the wind turbine according to the response fluctuation trend and the steady-state parameters; Continue to determine the stability margins of the remaining control loops in the wind turbine.

[0008] In some embodiments, performing collaborative compensation on each control signal in the wind turbine based on the stability margins of the respective control loops to obtain the multi-level compensation control signal of the wind turbine specifically includes: Obtain the control signals of each control loop in the wind turbine to obtain all the control signals in the wind turbine; Determine the anti-interference ability of each control loop during the operation of the wind turbine; Divide all the control loops into multiple control levels according to the anti-interference ability of each control loop, and each control level includes multiple control loops; Select a control level as the selected control level, and determine the signal compensation coefficient of the selected control level according to the stability margin of each control loop in the selected control level; Continue to determine the signal compensation coefficients of the remaining control levels; Compensate the control signals of each control loop according to the signal compensation coefficient of each control level to obtain the compensated control signals corresponding to each control loop; Generate the multi-level compensation control signal of the wind turbine according to all the compensated control signals.

[0009] In some embodiments, parsing the multi-source heterogeneous data to obtain the interference gradient of the wind turbine affected by environmental interference specifically includes: Separate multiple environment-sensitive signal components from the multi-source heterogeneous data; Construct an environmental interference observation matrix based on all the environment-sensitive signal components; Generate the interference gradient of the wind turbine affected by environmental interference through the environmental interference observation matrix.

[0010] In some embodiments, the edge computing gateway performs collaborative control on each control loop in the wind turbine based on the multi-level compensation control signal and the adjusted collaborative coefficients of each compensated control signal specifically includes: Obtain the multi-level compensation control signal of the wind turbine through the edge computing gateway, and extract the initial control parameters of each compensated control signal in the multi-level compensation control signal; Select a compensated control signal as the selected compensated control signal, and determine the collaborative control parameter of the selected compensated control signal from the initial control parameter and the adjusted collaborative coefficient of the selected compensated control signal; Continue to determine the cooperative control parameters of the remaining compensation control signals; Correspondingly allocate the cooperative control parameters of each compensation control signal to each execution loop of the wind turbine for control.

[0011] In some embodiments, the multi-source heterogeneous data is composed of data with multiple different physical characteristics.

[0012] In a second aspect, the present application provides an electrical automation control system for automatically controlling a wind turbine, including: An acquisition module, configured to acquire multi-source heterogeneous data at the motor rotor during the operation of the wind turbine and upload the multi-source heterogeneous data to the edge computing gateway; A processing module, configured to perform feature coupling processing on the multi-source heterogeneous data through the edge computing gateway to obtain the dynamic association features between different state parameters during the power generation of the motor rotor; The processing module is further configured to determine the stability margin of different control loops in the wind turbine based on the time-varying characteristics of each dynamic association feature under the change of the time period, and then perform cooperative compensation on each control signal in the wind turbine based on the stability margin of each control loop to obtain the multi-level compensation control signals of the wind turbine; The processing module is further configured to analyze the multi-source heterogeneous data to obtain the interference gradient of the wind turbine affected by environmental interference during operation, and adjust the cooperative coefficient of each compensation control signal in the multi-level compensation control signal according to the interference gradient; An execution module, configured to perform cooperative control on each control loop in the wind turbine by the edge computing gateway based on the multi-level compensation control signal and the adjusted cooperative coefficient of each compensation control signal.

[0013] In a third aspect, the present application provides a computer device, which includes a memory and a processor. The memory stores code, and the processor is configured to obtain the code and execute the above electrical automation control method.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above electrical automation control method is implemented.

[0015] The technical solutions provided by the disclosed embodiments of the present application have the following beneficial effects: In the electrical automation control system and method provided by the present application, first, multi-source heterogeneous data at the motor rotor during the operation of the wind turbine is collected and uploaded to the edge computing gateway; secondly, the edge computing gateway performs feature coupling processing on the multi-source heterogeneous data to obtain the dynamic association features between different state parameters during the power generation of the motor rotor; further, based on the time-varying characteristics of each dynamic association feature under the change of the time period, the stability margin of different control loops in the wind turbine is determined, and then each control signal in the wind turbine is co-compensated based on the stability margin of each control loop to obtain the multi-level compensation control signal of the wind turbine; then, the multi-source heterogeneous data is parsed to obtain the interference gradient affected by the environment during the operation of the wind turbine, and the cooperation coefficient of each compensation control signal in the multi-level compensation control signal is adjusted according to the interference gradient; finally, the edge computing gateway performs cooperative control on each control loop in the wind turbine based on the multi-level compensation control signal and the adjusted cooperation coefficient of each compensation control signal.

[0016] It can be seen that the present application can achieve coordinated control of different control loops in a wind turbine under the influence of the dynamic coupling relationship of different control loops. First, multi-source heterogeneous data during the operation of the wind turbine is obtained to provide data conditions for comprehensively analyzing the equipment status and optimizing control signals. Second, the edge computing gateway performs feature coupling processing on the multi-source heterogeneous data to obtain the dynamic association features between different state parameters during the operation of the wind turbine, enabling the control system to not only effectively focus on the changes of individual variables but also identify the association relationships between variables, and perform more accurate adjustment of the wind turbine according to the association relationships between variables to improve the anti-interference ability of the control system, thereby avoiding the response lag caused by the insensitivity of edge computing to data processing in the control of the wind turbine. Further, based on the time-varying characteristics of each dynamic association feature, the stability margin of different control loops in the wind turbine is determined to measure the ability of the control loop to maintain stable operation, and further ensure that the system has fast response ability without causing excessive oscillation, thereby avoiding the control lag problem caused by the dynamic coupling relationship between different control loops. Then, based on the stability margin of each control loop, each control signal of the wind turbine is coordinately compensated to obtain the multi-level compensation control signal of the wind turbine, enabling coordinated optimization between different control loops and improving the overall performance and anti-interference ability of the system. Then, according to the interference gradient of the environmental interference during the operation of the wind turbine, the coordination coefficient of each compensation control signal in the multi-level compensation control signal is adjusted to ensure stable coordination between different control loops. Finally, the edge computing gateway coordinately controls each control loop in the wind turbine based on the multi-level compensation control signal and the adjusted coordination coefficient of each compensation control signal to achieve coordinated control of different control loops in the wind turbine. In summary, the technical solution provided by the present application can achieve coordinated control of different control loops in a wind turbine under the influence of the dynamic coupling relationship of different control loops. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is an exemplary flowchart of an electrical automation control method shown in some embodiments of the present application; Figure 2 is an exemplary flowchart of determining dynamic association features shown in some embodiments of the present application; Figure 3 is an exemplary flowchart of determining a multi-level compensation control signal shown in some embodiments of the present application; Figure 4 is a schematic structural diagram of an electrical automation control system shown in some embodiments of the present application; Figure 5 is a schematic structural diagram of a computer device for implementing an electrical automation control method shown in some embodiments of the present application. Detailed implementation manners

[0018] To better understand the technical solution of the present application, the technical solution of the present application will be described in detail below in conjunction with the accompanying drawings of the specification and specific implementation manners.

[0019] Refer to Figure 1 , which is an exemplary flowchart of an electrical automation control method shown according to some embodiments of the present application. This method is used for automatic control of a wind turbine. Specifically, when implemented, the electrical automation control method 100 mainly includes the following steps: In step 101, multi-source heterogeneous data at the motor rotor during the operation of the wind turbine is collected, and the multi-source heterogeneous data is uploaded to the edge computing gateway.

[0020] Specifically, when implemented, first, multiple types of sensors are deployed at the motor rotor of the wind turbine. During the operation of the wind turbine, different types of data at the motor rotor during the operation of the wind turbine are collected through multiple types of sensors, such as voltage data, temperature data, and rotational speed data. Secondly, each type of data collected is time-synchronized through a clock synchronization protocol, that is, the observed values of the voltage data, temperature data, and rotational speed data are kept synchronized. Then, each type of time-synchronized data is combined to obtain multi-source heterogeneous data at the motor rotor during the operation of the wind turbine. Finally, the multi-source heterogeneous data is uploaded to the edge computing gateway through an adapted communication protocol (such as Modbus, MQTT).

[0021] It should be noted that in the present application, multi-source heterogeneous data represents a combination of data with multiple different physical characteristics. Specifically, the multi-source heterogeneous data is composed of data with multiple different physical characteristics. The multi-source heterogeneous data includes heterogeneous data corresponding to different state parameters, that is, voltage data corresponding to voltage parameters, temperature data corresponding to temperature parameters, and rotational speed data corresponding to rotational speed parameters. In the present application, voltage, temperature, and rotational speed are respectively used as state parameters when the motor rotor of the wind turbine generates electricity during operation; these data are obtained through multiple sensors during the operation of the wind turbine and can be effectively used for comprehensive analysis of the equipment state and optimization of control signals; in the present application, the edge computing gateway represents an intermediate node for data processing in the wind turbine, that is, real-time analysis and preliminary processing of the collected data, and further transmission of key information or processing results to the cloud, so as to realize real-time monitoring and intelligent management of the operation state of the wind turbine. By obtaining multi-source heterogeneous data, data conditions are provided for comprehensive analysis of the equipment state and optimization of control signals.

[0022] In step 102, the multi-source heterogeneous data is subjected to feature coupling processing through the edge computing gateway to obtain dynamic association features between different state parameters when the motor rotor generates electricity.

[0023] In some embodiments, with reference to Figure 2 As shown, the figure is an exemplary flowchart for determining dynamic association features according to some embodiments of the present application. In this embodiment, the edge computing gateway performs feature coupling processing on the multi-source heterogeneous data to obtain the dynamic association features between different state parameters during the power generation of the motor rotor, which can be implemented by the following steps: First, in step 1021, the multi-source heterogeneous data is normalized to obtain the normalized multi-source heterogeneous data; Then, in step 1022, the normalized heterogeneous data corresponding to each state parameter during the operation of the wind turbine is extracted from the normalized multi-source heterogeneous data; Finally, in step 1023, the normalized heterogeneous data of different state parameters is subjected to association calculation through a preset association model, and thus the dynamic association features between different state parameters during the power generation of the motor rotor are obtained.

[0024] In specific implementation, first, normalize the multi-source heterogeneous data to obtain the normalized multi-source heterogeneous data, that is: perform maximum-minimum normalization on each heterogeneous data in the multi-source heterogeneous data respectively to obtain all normalized heterogeneous data, and combine all the normalized heterogeneous data to obtain the normalized multi-source heterogeneous data. For example, for each heterogeneous data, take each value in the heterogeneous data as the variable parameter of the maximum-minimum normalization, and replace the original value with each result obtained by the maximum-minimum normalization calculation, so as to obtain all the normalized heterogeneous data. In addition, in other embodiments, other normalization methods can also be used, such as Z-score standardization, etc., which are not limited here; then, use the data processing tool Python to extract the normalized heterogeneous data corresponding to each state parameter during the operation of the wind turbine from the normalized multi-source heterogeneous data, that is, extract the normalized voltage data corresponding to the voltage parameter, the normalized temperature data corresponding to the temperature parameter, and the normalized speed data corresponding to the speed parameter in the multi-source heterogeneous data, which will not be elaborated here; finally, perform correlation calculation on the normalized heterogeneous data of different state parameters through a preset correlation model, so as to obtain the dynamic correlation characteristics between different state parameters during the power generation of the motor rotor, that is: obtain the preset correlation model. For every two state parameters, take the normalized heterogeneous data corresponding to the two state parameters as input parameters and input them into the preset correlation model, and take the result output by the correlation model as the dynamic correlation characteristic between the two state parameters, so as to obtain the dynamic correlation characteristics between different state parameters during the power generation of the motor rotor. The preset correlation model uses the Pearson correlation coefficient model, that is, take the two state parameters as variables of the Pearson correlation coefficient model respectively, and calculate the covariance of the two variables and the standard deviation of each variable by the Pearson correlation coefficient model, calculate the product of the standard deviations of the two variables, and then take the quotient of the covariance and the product result of the standard deviations as the output result of the Pearson correlation coefficient model. In addition, in other embodiments, other correlation models can also be used, which are not limited here.

[0025] It should be noted that in this embodiment, the normalized heterogeneous data represents the heterogeneous data after normalization processing, and the heterogeneous data is the data collected by different types of sensors; in this application, the dynamic correlation characteristic represents the correlation relationship that changes with time between different state parameters. The dynamic correlation characteristic reflects the coupling characteristics, change trends, and the degree of mutual influence between the operating states of the device. By determining the dynamic correlation characteristic, the control system can not only effectively pay attention to the changes of individual variables, but also identify the correlation relationship between variables, and perform more accurate adjustment on the wind turbine according to the correlation relationship between variables, so as to improve the anti-interference ability of the control system and avoid the response lag in the control of the wind turbine.

[0026] It should also be noted that in this application, feature coupling processing represents the process of analyzing the correlation relationship between different state parameters. Among them, the edge computing gateway performs feature coupling processing on the multi-source heterogeneous data, that is: normalizing the multi-source heterogeneous data to obtain the normalized multi-source heterogeneous data; extracting the normalized heterogeneous data corresponding to each state parameter during the operation of the wind turbine from the normalized multi-source heterogeneous data; performing correlation calculation on the normalized heterogeneous data of different state parameters through a preset correlation model, and then obtaining the dynamic correlation features between different state parameters during the power generation of the motor rotor, that is, taking the dynamic correlation features as the result of feature coupling processing, so as to complete the feature coupling processing of the multi-source heterogeneous data.

[0027] In step 103, based on the time-varying characteristics of each dynamic correlation feature under the change of the time period, the stability margin of different control loops in the wind turbine is determined. Then, based on the stability margin of each control loop, each control signal in the wind turbine is coordinately compensated to obtain the multi-level compensation control signal of the wind turbine.

[0028] In some embodiments, determining the stability margin of different control loops in the wind turbine based on the time-varying characteristics of each dynamic correlation feature under the change of the time period can be implemented by the following steps, that is: Obtain the dynamic correlation features between different state parameters during the operation of the wind turbine under different historical time periods to obtain the dynamic correlation feature sequence corresponding to different state parameters; Calculate the time-varying characteristics of each dynamic correlation feature under the change of the time period according to the dynamic correlation feature sequence corresponding to each different state parameter; Determine the steady-state parameters during the operation of the wind turbine through all the time-varying characteristics; Obtain the parameter change data of different control loops during the operation of the wind turbine; Select a control loop as the selected control loop, and calculate the response fluctuation trend of the selected control loop through the parameter change data of the selected control loop; Determine the stability margin of the selected control loop in the wind turbine according to the response fluctuation trend and the steady-state parameters; Continue to determine the stability margin of the remaining control loops in the wind turbine.

[0029] In specific implementation, first, obtain the dynamic correlation characteristics between various different state parameters during the operation of the wind turbine in different historical time periods through the electrical automation monitoring database, and then arrange the dynamic correlation characteristics between various different state parameters into corresponding dynamic correlation characteristic sequences in chronological order. The different historical time periods are pre-divided according to actual needs. For example, one time period is set as 1 minute. In addition, in other embodiments, other time periods can also be set, which is not limited here. The electrical automation monitoring database refers to an intelligent database used to store, manage, and analyze the operation data of the wind turbine. This intelligent database can collect and store various monitoring data in the electrical automation system in real time, and support querying, processing, and analyzing these data to provide functions such as state monitoring, fault diagnosis, and control optimization of the wind turbine. Secondly, calculate the time-varying characteristics of each dynamic correlation feature under the change of the time period according to the corresponding dynamic correlation characteristic sequence between each different state parameter, that is: for the corresponding dynamic correlation characteristic sequence between each different state parameter, calculate the variance of all dynamic correlation features in the corresponding dynamic correlation characteristic sequence between different state parameters, and use the variance calculation result as the time-varying characteristic of the corresponding dynamic correlation feature between different state parameters, so as to obtain the time-varying characteristics of each dynamic correlation feature under the change of the time period. Among them, one corresponding dynamic correlation characteristic sequence exists between different state parameters, one time-varying characteristic corresponds to one dynamic correlation characteristic sequence, and one time-varying characteristic corresponds to the dynamic correlation feature between different state parameters. In addition, in other embodiments, other calculation methods can also be used to calculate the time-varying characteristics of each dynamic correlation feature, which is not limited here. Further, determine the steady-state parameters during the operation of the wind turbine through all the time-varying characteristics, that is: calculate the mean value of all the time-varying characteristics, and use the mean value calculation result as the steady-state parameters during the operation of the wind turbine. In addition, in other embodiments, other calculation methods can also be used to calculate the steady-state parameters during the operation of the wind turbine, which is not limited here. Still further, obtain the parameter change data corresponding to different control loops through the sensors set in different control loops. The parameter change data represents the control parameter combinations in the control loops at different times. The parameter change data includes multiple parameter change values. For example, in the yaw control loop, an angle sensor is used to obtain the parameter change data of the yaw control loop during the operation of the wind turbine. Among them, the parameter change data is the yaw angle data, and the parameter change value is the yaw angle. In addition, the parameter change data of other control loops will not be elaborated here. The different control loops during the operation of the wind turbine include a yaw control loop, a speed control loop, and a pitch control loop.In addition, select a control loop as the selected control loop, and calculate the response fluctuation trend of the selected control loop based on the parameter change data of the selected control loop, that is: select a control loop as the selected control loop, perform normalization on the parameter change data of the selected control loop using maximum-minimum normalization, then calculate the variance of the normalized parameter change data, and use the variance calculation result as the response fluctuation trend of the selected control loop; then, determine the stability margin of the selected control loop in the wind turbine according to the response fluctuation trend and the steady-state parameter, that is: calculate the absolute difference between the steady-state parameter and the response fluctuation trend, and use the absolute difference calculation result as the stability margin of the selected control loop in the wind turbine. In addition, in other embodiments, other calculation methods may also be used to calculate the stability margin of the selected control loop in the wind turbine, and the types are not limited. Both the steady-state parameter and the response fluctuation trend are dimensionless parameters; finally, continue to determine the stability margins of the remaining control loops in the wind turbine by the determination method of "determining the stability margin of the selected control loop in the wind turbine according to the response fluctuation trend and the steady-state parameter", which will not be elaborated here.;

[0030] It should be noted that in this embodiment, the dynamic correlation feature sequence represents a set containing multiple dynamic correlation features; in this application, the time-varying characteristic represents the dynamic change characteristics of the dynamic correlation features in the time dimension. The time-varying characteristic describes the evolution of the dynamic correlation features between different state parameters over time. The time-varying characteristic is an important factor affecting the operation reliability and control accuracy of the device. Accurately depicting and analyzing the time-varying characteristic can effectively improve the adaptive ability and stability of the wind turbine control. In this embodiment, the steady-state parameter represents a parameter that describes the stable characteristics of the device operation state. The steady-state parameter can effectively measure the stability, error characteristics, and response ability of the wind turbine or control system during long-term operation, and provide a basis for control signal optimization and fault diagnosis. In this embodiment, the response fluctuation trend represents the dynamic characteristic of the parameter change data over time. The response fluctuation trend is used to describe the stability of the device operation state. In this application, the stability margin represents the ability to measure the control loop's ability to maintain stable operation. Specifically, in this application, the stability margin refers to the ability of each control loop to still maintain stable operation when the wind turbine is disturbed or the parameters change during operation. The stability margin measures the stability of different control loops. By determining the stability margin, it can effectively ensure that the system has a fast response ability without causing excessive oscillation. In addition, determining the stability margin of each control loop to measure the control loop's ability to maintain stable operation, and then ensuring that the system has a fast response ability without causing excessive oscillation, so as to avoid the control deviation problem caused by the dynamic coupling relationship between different control loops. In addition, it can also effectively formulate hierarchical compensation control signals, that is, enhance the compensation for the loop with a smaller stability margin, and reduce the control intervention for the loop with a larger stability margin, thereby improving the coordination of the overall system.

[0031] In some embodiments, referring to Figure 3 as shown, this figure is an exemplary flowchart for determining multi-level compensation control signals according to some embodiments of the present application. In this embodiment, based on the stability margin of each control loop, collaborative compensation is performed on each control signal in the wind turbine to obtain the multi-level compensation control signal of the wind turbine, which can be implemented by the following steps: In step 1031, obtain the control signals of each control loop in the wind turbine to obtain all the control signals in the wind turbine; In step 1032, determine the anti-interference ability of each control loop during the operation of the wind turbine; In step 1033, divide all the control loops into multiple control levels according to the anti-interference ability of each control loop. The control level contains multiple control loops; In step 1034, select a control level as the selected control level, and determine the signal compensation coefficient of the selected control level according to the stability margin of each control loop in the selected control level; In step 1035, continue to determine the signal compensation coefficients of the remaining control levels; In step 1036, compensate the control signals of each control loop according to the signal compensation coefficient of each control level to obtain the compensated control signals corresponding to each control loop; In step 1037, generate the multi-level compensated control signal of the wind turbine according to all the compensated control signals.

[0032] In specific implementation, first, control signals corresponding to each control loop in the wind turbine are obtained through the controllers of each control loop in the wind turbine. For example, the control signal of the yaw control loop is the yaw angle signal, the control signal of the speed control loop is the speed signal, and the control signal of the pitch control loop is the pitch angle signal, which will not be elaborated here. Secondly, the anti-interference ability of each control loop during the operation of the wind turbine is determined, that is: during the operation of the wind turbine, the wavelet transform in the time-frequency analysis method is used to calculate the anti-interference ability of each control loop. That is, for each control loop, the output signal of the control loop is decomposed into different frequency bands by wavelet transform, and the signal energy in each frequency band is calculated. Then, the ratio of the signal energy in the highest frequency band to the total signal energy is used as the anti-interference ability of the control loop, so as to obtain the anti-interference ability of each control loop during the operation of the wind turbine. Further, all control loops are divided into multiple control levels according to the anti-interference ability of each control loop. The control level contains multiple control loops, that is: based on all anti-interference abilities, all control loops are divided into multiple control levels (that is: high control level, medium control level and low control level) by the hierarchical clustering method. In addition, in other embodiments, other clustering methods can also be used to divide each control loop into multiple control levels. For example, K-means clustering and fuzzy C-means clustering methods, which will not be elaborated here. Furthermore, a control level is selected as the selected control level, and the signal compensation coefficient of the selected control level is determined according to the stability margin of each control loop in the selected control level, that is: the stability margin of each control loop in the selected control level is extracted, the mean value of all stability margins is calculated, and the result of the mean value calculation is used as the signal compensation coefficient of the selected control level. In addition, in other embodiments, other calculation methods can also be used to calculate the signal compensation coefficient of the selected control level, which is not limited here. Then, the signal compensation coefficients of the remaining control levels are continuously determined by the determination method of "determining the signal compensation coefficient of the selected control level according to the stability margin of each control loop in the selected control level". Then, according to the signal compensation coefficient of each control level, the control signals of each control loop are compensated to obtain the compensated control signals corresponding to each control loop, that is: for each control loop, the signal compensation coefficient corresponding to the control level of the control loop is extracted, and the compensation coefficient is multiplied by the control signal corresponding to the control loop to obtain the compensated control signal corresponding to the control loop, so as to obtain the compensated control signals corresponding to each control loop. Finally, all the compensated control signals are combined to obtain the multi-level compensated control signal of the wind turbine.

[0033] It should be noted that in this application, the control signal represents the input signal used to adjust the output of each control loop; in this embodiment, the anti-interference ability represents the ability of the control loop to maintain stable operation under external interference. The anti-interference ability reflects the ability of the control loop to resist disturbances and maintain the expected control target, and is usually used to evaluate the robustness and anti-interference performance of the system; in this embodiment, the control hierarchy represents the structure for hierarchical division of the control loop; in this embodiment, the signal compensation coefficient represents a coefficient for adjusting the control signal. Through this signal compensation coefficient, the signal can be appropriately amplified or attenuated according to the state of the control loop or the interference of the external environment, so as to improve the performance of the control system and ensure that the system reaches the predetermined control target; in this embodiment, the compensated control signal represents the control signal after signal compensation. The compensated control signal carries different control information according to different control hierarchies of the system, and finally realizes cooperative control in the whole system to ensure the overall function and stability of the system; in this application, the multi-level compensated control signal represents the signal set formed after hierarchical compensation and optimization of the control signals of the control loop. Through multi-level cooperative control, the multi-level compensated control signal enables coordinated optimization between different control loops, can effectively achieve precise adjustment of the wind turbine, optimize stability, and improve the overall performance and anti-interference ability of the system, ensuring that the system can operate efficiently and stably in a dynamic environment.

[0034] In step 104, the multi-source heterogeneous data is parsed to obtain the interference gradient of the wind turbine during operation affected by the environment, and the cooperation coefficient of each compensated control signal in the multi-level compensated control signal is adjusted according to the interference gradient.

[0035] In some embodiments, parsing the multi-source heterogeneous data to obtain the interference gradient of the wind turbine during operation affected by the environment can be achieved by the following steps, that is: Separate multiple environment-sensitive signal components from the multi-source heterogeneous data; Construct an environment interference observation matrix based on all the environment-sensitive signal components; Generate the interference gradient of the wind turbine during operation affected by the environment through the environment interference observation matrix.

[0036] In specific implementation, first, multiple environment-sensitive signal components are separated from the multi-source heterogeneous data, that is, multiple environment-sensitive signal components are separated from the preprocessed multi-source heterogeneous data by using principal component analysis. For example, a covariance matrix is constructed from the multi-source heterogeneous data, the eigenvalues and eigenvectors of the covariance matrix are solved, and they are sorted according to the eigenvalue magnitudes. The eigenvectors corresponding to the first 2 largest eigenvalues are selected as the environment-sensitive signal components, thereby completing the separation of multiple environment-sensitive signal components from the multi-source heterogeneous data by principal component analysis. Secondly, an environmental interference observation matrix is constructed based on all the environment-sensitive signal components, that is, each environment-sensitive signal component is arranged by column to obtain the environmental interference observation matrix. Finally, the interference gradient of the wind turbine affected by environmental interference during operation is generated through the environmental interference observation matrix, that is, the change rate of adjacent elements in each column of the environmental interference observation matrix is calculated, and the mean value of all the calculated change rates is used as the interference gradient of the wind turbine affected by environmental interference during operation. In addition, other methods can also be used to calculate the interference gradient of the wind turbine affected by environmental interference during operation, which is not limited here.

[0037] It should be noted that in this embodiment, the environment-sensitive signal component refers to a signal component that can reflect the influence of environmental interference factors on the wind turbine. These signal components are usually highly correlated with environmental variables and may have a direct or indirect impact on the operating state of the wind turbine. In this embodiment, the environmental interference observation matrix refers to a matrix constructed from multiple environment-sensitive signal components, which is used to characterize the environmental interference situation during the operation of the wind turbine. This matrix can quantify the influence of different environmental factors on the state of the wind turbine and is used to calculate the gradient change trend of environmental interference. In this application, the interference gradient refers to the gradient change describing the environmental influence on the wind turbine. By calculating the interference gradient, the influence of environmental factors on the control stability of the equipment can be more accurately evaluated and predicted, so as to optimize the control strategy, improve the anti-interference ability of the system, and achieve intelligent adjustment.

[0038] In some embodiments, adjusting the cooperation coefficients of the respective compensation control signals in the multi-stage compensation control signal according to the interference gradient can be implemented by the following steps, that is: Obtain the cooperation coefficients of the respective compensation control signals in the multi-stage compensation control signal and the prior interference amounts of the respective compensation control signals during the operation of the wind turbine; Determine the adjustment value of each compensation control signal according to the prior interference amount of each compensation control signal and the interference gradient; Determine the adjusted cooperation coefficient of each compensation control signal through the adjustment value and the cooperation coefficient of each compensation control signal.

[0039] In specific implementation, first, obtain the cooperation coefficient of each compensation control signal in the multi-level compensation control signal and the prior interference amount of each compensation control signal during the operation of the wind turbine through the electrical automation monitoring database. The cooperation coefficient of each compensation control signal in the multi-level compensation control signal is set between 0 and 1 in advance according to the control sensitivity of each compensation control signal in the wind turbine. The prior interference amount of each compensation control signal is set through historical experiment simulation, which will not be elaborated here. Secondly, determine the adjustment value of each compensation control signal according to the prior interference amount of each compensation control signal and the interference gradient, that is: for each compensation control signal, take the difference between the interference gradient and the prior interference amount of the compensation control signal as the adjustment value of the compensation control signal, and then obtain the adjustment value of each compensation control signal. In addition, in other embodiments, other calculation methods can also be used to calculate the adjustment value of each compensation control signal, which is not limited here. Finally, determine the adjusted cooperation coefficient of each compensation control signal through the adjustment value and cooperation coefficient of each compensation control signal, that is: for each compensation control signal, sum and take the absolute value of the adjustment value and the cooperation coefficient of the compensation control signal, and use the calculation result as the adjusted cooperation coefficient of the compensation control signal, and then obtain the adjusted cooperation coefficient of each compensation control signal. In addition, in other embodiments, other calculation methods can also be used to calculate the adjusted cooperation coefficient of each compensation control signal, which is not limited here.

[0040] It should be noted that in this embodiment, the cooperation coefficient represents the weight factor for the cooperation between the control signals of different control loops, and is used to quantify the contribution of each compensation control signal to the control of the wind turbine. The cooperation coefficient reflects the relative influence of each control signal in the system coordination process and is used to ensure the stable cooperation between different control loops. In this embodiment, the prior interference amount represents the environmental interference amount that each compensation control signal of each control loop is estimated to receive during operation, and is used as a reference value to compare with the interference gradient calculated in real time to adjust the compensation strategy of the control system. In this embodiment, the adjustment value represents the correction value of the cooperation coefficient of each compensation control signal and is used to adjust the compensation strategy of the control system to make the system adapt to the current interference situation.

[0041] In step 105, the edge computing gateway performs cooperative control on each control loop in the wind turbine based on the multi-level compensation control signal and the adjusted cooperation coefficient of each compensation control signal.

[0042] In some embodiments, the edge computing gateway can perform cooperative control on each control loop in the wind turbine based on the multi-level compensation control signal and the adjusted cooperation coefficient of each compensation control signal by the following steps, that is: Obtain the multi-level compensation control signal of the wind turbine through the edge computing gateway, and extract the initial control parameters of each compensation control signal in the multi-level compensation control signal; Select a compensation control signal as the selected compensation control signal, and determine the collaborative control parameter of the selected compensation control signal from the initial control parameter of the selected compensation control signal and the adjusted collaborative coefficient; Continue to determine the collaborative control parameters of the remaining compensation control signals; Correspondingly allocate the collaborative control parameters of each compensation control signal to each execution loop of the wind turbine for control.

[0043] In specific implementation, first, the edge computing gateway obtains the multi-level compensation control signal of the wind turbine, and extracts the initial control parameters of each compensation control signal from the multi-level compensation control signal through the MQTT protocol in the protocol parsing method. For example, the control voltage, in addition, it can also be other parameters, such as current, frequency, power factor and other parameters, which are not limited here; Secondly, select a compensation control signal as the selected compensation control signal, and determine the collaborative control parameter of the selected compensation control signal from the initial control parameter of the selected compensation control signal and the collaborative coefficient, that is: take the collaborative coefficient as the dynamic compensation factor, and use the proportional adjustment method to adjust the initial control parameter to obtain the collaborative control parameter of the selected compensation control signal, that is, collaborative control parameter = initial control parameter × (1 + adjusted collaborative coefficient). In addition, in other embodiments, other calculation methods can also be used to calculate the collaborative control parameter of the selected compensation control signal, which is not limited here; Then, continue to determine the collaborative control parameters of the remaining compensation control signals through the determination method of "determining the collaborative control parameter of the selected compensation control signal from the initial control parameter of the selected compensation control signal and the adjusted collaborative coefficient", which will not be elaborated here; Finally, correspondingly allocate the collaborative control parameters of each compensation control signal to each execution loop of the wind turbine for control, that is: use the allocation rule of the mapping matrix to map the collaborative control parameters of each compensation control signal to each execution loop of the wind turbine. For example, first construct a mapping matrix, where the rows represent each compensation control signal, the columns represent the execution loops of the wind turbine, and the matrix elements represent the collaborative control parameters. Obtain the collaborative control parameters of all compensation control signals, and allocate the collaborative control parameters to the corresponding execution loops according to the allocation rule of the mapping matrix, that is, the position where the compensation control signal intersects with the execution loop is the mapping position of the corresponding collaborative control parameter. When the collaborative control parameters of each control loop are allocated, each control loop performs corresponding control according to the corresponding collaborative control parameter. For example, the yaw control loop performs yaw control, the speed control loop performs speed control, and the pitch control loop performs pitch angle control.

[0044] It should be noted that in this embodiment, the initial control parameter represents the initial control signal of the control loop. The initial control parameter is usually set at the start or in the initial stage of system operation and serves as the basis for the control strategy. In this embodiment, the coordinated control parameter represents the parameter used to coordinate the control of each control loop. The role of these coordinated control parameters is to adjust the mutual cooperation between each loop, enable each part of the system to work in coordination, and optimize the overall performance. Since the wind turbine may be affected by factors such as environmental changes, load fluctuations, and interference during operation, traditional fixed-parameter control is difficult to meet the dynamic requirements. By determining the coordinated control parameters of each control loop, the wind turbine can adapt to different operating states and improve the overall stability.

[0045] In addition, on the other hand of the present application, in some embodiments, the present application provides an electrical automation control system for automatically controlling a wind turbine. Refer to Figure 4 , which is a schematic structural diagram of the electrical automation control system shown according to some embodiments of the present application. The electrical automation control system 200 includes: a collection module 201, a processing module 202, and an execution module 203, which are described as follows: Collection module 201. In the present application, the collection module 201 is mainly used to collect multi-source heterogeneous data at the motor rotor during the operation of the wind turbine and upload the multi-source heterogeneous data to the edge computing gateway. Processing module 202. In the present application, the processing module 202 is mainly used to perform feature coupling processing on the multi-source heterogeneous data through the edge computing gateway to obtain the dynamic association features between different state parameters during the power generation of the motor rotor. The processing module 202 is further used to determine the stability margin of different control loops in the wind turbine based on the time-varying characteristics of each dynamic association feature under the change of the time period, and then perform coordinated compensation on each control signal in the wind turbine based on the stability margin of each control loop to obtain the multi-level compensation control signal of the wind turbine. In addition, the processing module 202 is further used to analyze the multi-source heterogeneous data to obtain the interference gradient of the wind turbine affected by environmental interference during operation, and adjust the coordination coefficient of each compensation control signal in the multi-level compensation control signal according to the interference gradient. Execution module 203. In the present application, the execution module 203 is mainly used for the edge computing gateway to perform coordinated control on each control loop in the wind turbine based on the multi-level compensation control signal and the adjusted coordination coefficient of each compensation control signal.

[0046] In addition, the present application also provides a computer device, which includes a memory and a processor. The memory stores code, and the processor is configured to obtain the code and execute the above-mentioned electrical automation control method.

[0047] In some embodiments, referring to Figure 5 , this figure is a schematic structural diagram of a computer device for implementing the electrical automation control method according to some embodiments of the present application. The electrical automation control method in the above embodiments can be implemented by Figure 5 the computer device shown. The computer device 300 includes at least one processor 301, a communication bus 302, a memory 303, and at least one communication interface 304.

[0048] The processor 301 can be a general-purpose central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more for controlling the execution of the electrical automation control method in the present application.

[0049] The communication bus 302 can be used to transfer information between the above components.

[0050] The memory 303 can be a read-only memory (ROM), or other types of static storage devices that can store static information and instructions, a random access memory (RAM), or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disks, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 303 can exist independently and be connected to the processor 301 through the communication bus 302. The memory 303 can also be integrated with the processor 301.

[0051] Among them, the memory 303 is used to store the program code for executing the solution of this application, and is controlled by the processor 301 for execution. The processor 301 is used to execute the program code stored in the memory 303. The program code may include one or more software modules. The determination of the electrical automation control method in the above embodiments can be implemented by one or more software modules in the processor 301 and the program code in the memory 303.

[0052] The communication interface 304 uses any device such as a transceiver for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0053] In a specific implementation, as an embodiment, the computer device may include multiple processors, and each of these processors may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0054] The above computer device may be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device may be a desktop computer, a laptop computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. The embodiments of this application do not limit the type of the computer device.

[0055] In addition, this application also provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the above electrical automation control method is implemented.

[0056] Although the preferred embodiments of this application have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concept. Therefore, the appended claims are intended to be interpreted to include the preferred embodiments and all changes and modifications falling within the scope of this application.

[0057] Obviously, those skilled in the art can make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalent technologies, this application is also intended to include these changes and modifications.

Claims

1. An electrical automation control method for automatically controlling a wind turbine, characterized in that, The method includes the following steps: Collect multi-source heterogeneous data at the motor rotor during the operation of the wind turbine, and upload the multi-source heterogeneous data to the edge computing gateway; Perform feature coupling processing on the multi-source heterogeneous data through the edge computing gateway to obtain the dynamic correlation features between different state parameters during the power generation of the motor rotor; Determine the stability margin of different control loops in the wind turbine based on the time-varying characteristics of each dynamic correlation feature under the change of the time period, and then perform collaborative compensation on each control signal in the wind turbine based on the stability margin of each control loop to obtain the multi-level compensation control signal of the wind turbine; Analyze the multi-source heterogeneous data to obtain the interference gradient affected by the environment during the operation of the wind turbine, and adjust the collaborative coefficient of each compensation control signal in the multi-level compensation control signal according to the interference gradient; The edge computing gateway performs collaborative control on each control loop in the wind turbine based on the multi-level compensation control signal and the adjusted collaborative coefficient of each compensation control signal.

2. The method according to claim 1, wherein Performing feature coupling processing on the multi-source heterogeneous data through the edge computing gateway to obtain the dynamic correlation features between different state parameters during the power generation of the motor rotor specifically includes: Normalize the multi-source heterogeneous data to obtain the normalized multi-source heterogeneous data; Extract the normalized heterogeneous data corresponding to each state parameter during the operation of the wind turbine from the normalized multi-source heterogeneous data; Perform correlation calculation on the normalized heterogeneous data of different state parameters through a preset correlation model, and then obtain the dynamic correlation features between different state parameters during the power generation of the motor rotor.

3. The method according to claim 1, characterized in that, Determining the stability margin of different control loops in the wind turbine based on the time-varying characteristics of each dynamic correlation feature under the change of the time period specifically includes: Obtain the dynamic correlation features between different state parameters during the operation of the wind turbine under different historical time periods to obtain the dynamic correlation feature sequence corresponding to different state parameters; Calculate the time-varying characteristics of each dynamic correlation feature under the change of the time period according to the dynamic correlation feature sequence corresponding to each different state parameter; Determine the steady-state parameters during the operation of the wind turbine through all the time-varying characteristics; Obtain the parameter change data of different control loops during the operation of the wind turbine; Select a control loop as the selected control loop, and calculate the response fluctuation trend of the selected control loop through the parameter change data of the selected control loop; Determine the stability margin of the selected control loop in the wind turbine according to the response fluctuation trend and the steady-state parameters; Continue to determine the stability margin of the remaining control loops in the wind turbine.

4. The method according to claim 1, characterized in that, Performing collaborative compensation on each control signal in the wind turbine based on the stability margin of each control loop to obtain the multi-level compensation control signal of the wind turbine specifically includes: Obtain the control signals of each control loop in the wind turbine to obtain all the control signals in the wind turbine; Determine the anti-interference ability of each control loop during the operation of the wind turbine; All control loops are divided into multiple control levels according to the anti-interference ability of each control loop, and each control level contains multiple control loops. Select one control level as the selected control level, and determine the signal compensation coefficient of the selected control level according to the stability margin of each control loop in the selected control level. Continue to determine the signal compensation coefficients of the remaining control levels. Compensate the control signals of each control loop according to the signal compensation coefficient of each control level to obtain the compensated control signals corresponding to each control loop. Generate the multi-level compensated control signal of the wind turbine according to all the compensated control signals.

5. The method according to claim 1, characterized in that, Parsing the multi-source heterogeneous data to obtain the interference gradient of the wind turbine affected by the environment during operation specifically includes: Separate multiple environment-sensitive signal components from the multi-source heterogeneous data. Construct an environment interference observation matrix based on all the environment-sensitive signal components. Generate the interference gradient of the wind turbine affected by the environment during operation through the environment interference observation matrix.

6. The method according to claim 1, wherein The edge computing gateway performs cooperative control on each control loop in the wind turbine based on the multi-level compensated control signal and the cooperative coefficient after adjustment of each compensated control signal, specifically including: Obtain the multi-level compensated control signal of the wind turbine through the edge computing gateway, and extract the initial control parameters of each compensated control signal in the multi-level compensated control signal. Select one compensated control signal as the selected compensated control signal, and determine the cooperative control parameter of the selected compensated control signal from the initial control parameter of the selected compensated control signal and the adjusted cooperative coefficient. Continue to determine the cooperative control parameters of the remaining compensated control signals. Correspondingly allocate the cooperative control parameters of each compensated control signal to each execution loop of the wind turbine for control.

7. The method according to claim 1, characterized in that, The multi-source heterogeneous data consists of multiple data with different physical characteristics.

8. An electrical automation control system for automatically controlling a wind turbine, characterized in that, Including: A collection module for collecting multi-source heterogeneous data at the motor rotor during the operation of the wind turbine and uploading the multi-source heterogeneous data to the edge computing gateway. A processing module for performing feature coupling processing on the multi-source heterogeneous data through the edge computing gateway to obtain the dynamic association features between different state parameters during the power generation of the motor rotor. The processing module is further configured to determine the stability margin of different control loops in the wind turbine based on the time-varying characteristics of each dynamic association feature under the change of the time period, and then perform cooperative compensation on each control signal in the wind turbine based on the stability margin of each control loop to obtain the multi-level compensated control signal of the wind turbine. The processing module is further configured to parse the multi-source heterogeneous data to obtain the interference gradient of the wind turbine affected by the environment during operation, and adjust the cooperative coefficient of each compensated control signal in the multi-level compensated control signal according to the interference gradient. An execution module for the edge computing gateway to perform cooperative control on each control loop in the wind turbine based on the multi-level compensated control signal and the cooperative coefficient after adjustment of each compensated control signal.

9. A computer device, characterized in that, The computer device includes a memory and a processor, the memory stores code, and the processor is configured to obtain the code and execute the electrical automation control method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the electrical automation control method according to any one of claims 1 to 7.

Images