A wind turbine generator control system and method based on PLC

Abstract

The present application discloses a PLC-based wind turbine generator control system and method, the system comprising: an acquisition module, used to set a plurality of monitoring points, acquire real-time monitoring data of each monitoring point, and generate an operation evaluation value of each monitoring point; a generation module, used to generate a first control strategy according to the operation evaluation value of each monitoring point and a preset control model of a device associated with each monitoring point; a determination module, used to construct an influence model according to the influence relationship between the monitoring points, integrate the first control strategies of the devices involved in the corresponding monitoring points according to the influence model, and determine the comprehensive control strategy of the wind turbine generator; a control module, used to perform control simulation on the comprehensive control strategy, generate an application evaluation value of the comprehensive control strategy according to the virtual monitoring data of each monitoring point after simulation, and judge whether to generate a correction instruction for the comprehensive control strategy according to the application evaluation value, thereby greatly improving the control efficiency of the wind turbine generator control system.

Description

Technical Field

[0001] The present application relates to the technical field of wind turbine generator sets, and in particular to a PLC-based wind turbine generator set control system and method. Background Art

[0002] A wind turbine is a system that converts the kinetic energy of wind into electrical energy. The function of the wind turbine control system is to realize the functions of parameter alarm, status monitoring, automatic control and equipment protection of the unit. With the gradual expansion of the scale of wind turbines and the improvement of unit safety protection, the requirements for wind turbine control systems are getting higher and higher. Therefore, in order to improve the control efficiency of wind turbine control systems, a PLC-based wind turbine control system and method are urgently needed. Summary of the invention

[0003] To solve the above technical problems, the present application provides a PLC-based wind turbine control system and method, which determines the real-time operating status of the wind turbine by setting multiple monitoring points and calculating the operating evaluation value of each monitoring point, determines a first control strategy based on the operating evaluation value and a preset control model of a device associated with the monitoring point, constructs an influence model based on the relationship between the monitoring points, constructs an influence relationship diagram based on the influence model, aggregates the first control strategies based on the connection relationship of the monitoring points in the influence relationship diagram, and determines a comprehensive control strategy, thereby greatly improving the control efficiency of the wind turbine control system.

[0004] In some embodiments of the present application, a PLC-based wind turbine generator control system is provided, comprising: An acquisition module is used to set multiple monitoring points according to the equipment parameters of the wind turbine generator set, obtain real-time monitoring data of each monitoring point, and generate an operation evaluation value of each monitoring point; A generating module, used for generating a first control strategy for a device associated with each monitoring point according to an operation evaluation value of each monitoring point and a preset control model of a device associated with each monitoring point; A determination module, used to construct an influence model according to the influence relationship between the monitoring points, integrate the first control strategies of the equipment involved in the corresponding monitoring points according to the influence model, and determine the comprehensive control strategy of the wind turbine generator set; The control module is used to perform control simulation on the comprehensive control strategy, generate an application evaluation value of the comprehensive control strategy according to the virtual monitoring data of each monitoring point after simulation, and determine whether to generate a correction instruction for the comprehensive control strategy according to the application evaluation value.

[0005] In some embodiments of the present application, multiple monitoring points are set according to the equipment parameters of the wind turbine generator set, including: Acquire equipment parameters of each equipment in the wind turbine generator set, wherein the equipment parameters include preset important coefficients, application coefficients, cost coefficients, and correlation coefficients; Generate an influence coefficient of the corresponding device according to the device parameters of each device, and set the device with an influence coefficient greater than a preset influence coefficient as a concerned device; Generate a reference map of interest based on location parameters of multiple devices of interest, and set corresponding monitoring points and the number of monitoring points based on the comprehensive influence coefficient and aggregation degree within a preset area in the reference map of interest; A historical operation evaluation value of the corresponding monitoring point is generated based on the historical monitoring data at each monitoring point, and the equipment associated with each monitoring point is determined based on the degree of synchronization between the historical operation evaluation value and the historical characteristic operation data of the equipment of interest within a preset area of ​​the corresponding monitoring point.

[0006] In some embodiments of the present application, determining the device associated with each monitoring point includes: Pre-set multiple operation evaluation indicators; Determine the historical characteristic operation data corresponding to the operation evaluation index according to the correlation degree between the operation evaluation index and the historical operation data of each concerned device; According to the fluctuation degree of the historical monitoring data of each monitoring point, the monitoring time interval of the historical monitoring data of the corresponding monitoring point is set; Generate multiple historical operation evaluation values ​​of historical monitoring data of corresponding monitoring points according to monitoring time intervals; A monitoring point is randomly selected in the preset area and set as the target monitoring point; Based on the preset time period as the time reference line, historical characteristic operation data of the concerned equipment whose relative distance to the target monitoring point is less than the preset relative distance is collected according to the monitoring time interval within the preset time period; Mapping the historical characteristic operation data collected at each monitoring time interval within a preset period and the historical operation evaluation value of the target monitoring point onto the time reference line; Calculate the first change value of the historical operation evaluation value of each monitoring time interval in the time reference line, set the monitoring time interval whose first change value is greater than the preset first change value threshold as the attention time interval, obtain the second change value of the historical characteristic operation data of each attention time interval, and generate the degree of synchronous change of the same historical characteristic operation data and the historical operation evaluation value according to the second change value difference value of the second change value greater than the preset second change value threshold and the number of attention time intervals whose second change value is greater than the preset second change value threshold; If the synchronization change degree is greater than a preset synchronization change degree threshold, the focus device corresponding to the current historical characteristic operation data is set as the device associated with the target monitoring point.

[0007] In some embodiments of the present application, the calculation formula for the operation correlation degree is: ; Among them, Y is the degree of operation relevance, n is the number of attention time intervals whose second change value is greater than the preset second change value threshold, m is the total number of attention time intervals, Di is the second change value of the i-th attention time interval whose second change value is greater than the preset second change value threshold, and D0 is the preset second change value threshold.

[0008] In some embodiments of the present application, real-time monitoring data of each monitoring point is obtained, and an operation evaluation value of each monitoring point is generated, including: Obtain real-time monitoring data from each monitoring point; Preset multiple standard monitoring data intervals, and each standard monitoring data interval includes multiple standard monitoring data sub-intervals, and each standard monitoring data sub-interval is configured with a corresponding preset operation evaluation value; Compare the real-time monitoring data with the corresponding standard monitoring data intervals to determine the standard monitoring data sub-interval in which the real-time monitoring data is located; The preset operation evaluation values ​​of the standard monitoring data sub-intervals in which all real-time monitoring data are located are averaged to obtain the operation evaluation values ​​of the corresponding monitoring points.

[0009] In some embodiments of the present application, a first control strategy for a device associated with each monitoring point is generated according to the operation evaluation value of each monitoring point and a preset control model of the device associated with each monitoring point, including: Compare the operation evaluation value of each monitoring point with the corresponding standard operation evaluation value to obtain the difference of the operation evaluation value of each monitoring point; Obtain a control strategy reference library of the equipment associated with each monitoring point, wherein the control strategy reference library includes a preset operation evaluation value difference of the current monitoring point, and each preset operation evaluation value difference is mapped with a preset control strategy of the equipment associated with the corresponding monitoring point; According to the preset operation evaluation value difference in the control strategy reference library of the equipment associated with each monitoring point as the training input data set, the preset control strategy mapped to the preset operation evaluation value difference is used as the training output data set, and the neural network training is performed to generate the preset control model of the equipment associated with each monitoring point; The difference in the operation evaluation values ​​of each monitoring point is input into a preset control model corresponding only to the equipment associated with the monitoring point, so as to obtain the first control strategy for the equipment associated with each monitoring point.

[0010] In some embodiments of the present application, an influence model is constructed according to the influence relationship between monitoring points, including: Obtain the historical control log of each monitoring point, analyze the historical control log, and filter out the historical operation evaluation value corresponding to each historical control log; Obtain the historical operation evaluation value change and historical change nodes in the historical control log of each monitoring point, and determine the degree of dependence of the remaining monitoring points at each historical change node on the current monitoring point, set the remaining monitoring points with a degree of dependence greater than a preset dependence threshold as the influencing monitoring points of the current monitoring point, and obtain the historical monitoring data change of the influencing monitoring points at each historical change node; The historical operation evaluation value change of each monitoring point is used as the first training input data set, the influencing monitoring point at the same historical change node of each historical operation evaluation value change is used as the first training output data set, and the historical monitoring data change at the same historical change node of each influencing monitoring point is used as the second training output data set; A neural network training is performed according to the first training input data set, the first training output data set and the second training output data set to obtain an influence model between the monitoring points involved.

[0011] In some embodiments of the present application, determining a comprehensive control strategy for a wind turbine generator system includes: Constructing an influence relationship diagram of all monitoring points according to the influence model between different monitoring points, wherein the influence relationship diagram includes all monitoring points, and the connection distance between each monitoring point is set according to the influence model; Generate a central coefficient of the corresponding monitoring point according to the connection distance and the number of connections of the direct connection of each monitoring point, and set the monitoring point whose central coefficient is greater than the preset central coefficient threshold as the central point of the monitoring point in the influence relationship diagram; Acquire the monitoring points in the influence relationship diagram whose connection distances with the center point of each monitoring point are within a preset connection distance interval and the first control strategies of the devices associated with the corresponding monitoring points, and form a first control strategy library for the center point of each monitoring point; Analyze the first control strategies in the same first control strategy library, obtain the commensurable factors between different first control strategies in the same control strategy library, and obtain the second control strategy for the center point of each monitoring point; The second control strategies of the center points of multiple monitoring points are subjected to conflict analysis. If there is a conflict, they are coordinated according to the corresponding second control strategies, and the coordinated second control strategies are subjected to integrated learning, and the comprehensive control strategy is determined according to the integrated learning results.

[0012] In some embodiments of the present application, generating an application evaluation value of the comprehensive control strategy according to the simulated virtual monitoring data of each monitoring point includes: Construct a simulation model of the wind turbine generator set, simulate the comprehensive control strategy based on the simulation model, and obtain virtual monitoring data of each monitoring point after simulation; Generate a virtual operation evaluation value for each monitoring point based on virtual monitoring data; Compare the virtual operation evaluation value of each monitoring point with the operation evaluation value before simulation to obtain the change characteristics of the operation evaluation value of each monitoring point, wherein the change characteristics include the change trend, change rate and change value of the operation evaluation value; The application evaluation value of the comprehensive control strategy is based on the change characteristics of the operation evaluation values ​​of all monitoring points; Pre-set application evaluation value threshold; When the application evaluation value is less than the application evaluation value threshold, a correction instruction of the comprehensive control strategy is generated; When the application evaluation value is greater than the application evaluation value threshold, no correction instruction for the comprehensive control strategy is generated.

[0013] In some embodiments of the present application, a PLC-based wind turbine generator control method is also included: Set multiple monitoring points according to the equipment parameters of the wind turbine generator set, obtain real-time monitoring data of each monitoring point, and generate operation evaluation values ​​of each monitoring point; Generate a first control strategy for the equipment associated with each monitoring point according to the operation evaluation value of each monitoring point and the preset control model of the equipment associated with each monitoring point; An influence model is constructed according to the influence relationship between the monitoring points, and the first control strategies of the equipment involved in the corresponding monitoring points are integrated according to the influence model to determine the comprehensive control strategy of the wind turbine generator set; A control simulation is performed on the comprehensive control strategy, and an application evaluation value of the comprehensive control strategy is generated according to the virtual monitoring data of each monitoring point after the simulation. It is determined whether to generate a correction instruction for the comprehensive control strategy according to the application evaluation value.

[0014] Compared with the prior art, the PLC-based wind turbine generator control system and method of the present application have the following beneficial effects: By setting multiple monitoring points and calculating the operation evaluation value of each monitoring point, the real-time operation status of the wind turbine generator set is judged, and the first control strategy is determined according to the operation evaluation value and the preset control model of the equipment associated with the monitoring point. An influence model is constructed according to the relationship between the monitoring points, and an influence relationship diagram is constructed according to the influence model. The first control strategy is aggregated according to the connection relationship of the monitoring points in the influence relationship diagram to determine the comprehensive control strategy, thereby greatly improving the control efficiency of the wind turbine generator set control system. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1It is a schematic diagram of a PLC-based wind turbine control system in a preferred embodiment of the present application; Figure 2 It is a flow chart of a PLC-based wind turbine generator control method in a preferred embodiment of the present application. DETAILED DESCRIPTION

[0016] The specific implementation methods of the present application are further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present application but are not intended to limit the scope of the present application.

[0017] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0018] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0019] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0020] like Figure 1 As shown, a PLC-based wind turbine generator control system according to a preferred embodiment of the present application includes: An acquisition module is used to set multiple monitoring points according to the equipment parameters of the wind turbine generator set, obtain real-time monitoring data of each monitoring point, and generate an operation evaluation value of each monitoring point; A generating module, used for generating a first control strategy for a device associated with each monitoring point according to an operation evaluation value of each monitoring point and a preset control model of a device associated with each monitoring point; A determination module, used to construct an influence model according to the influence relationship between the monitoring points, integrate the first control strategies of the equipment involved in the corresponding monitoring points according to the influence model, and determine the comprehensive control strategy of the wind turbine generator set; The control module is used to perform control simulation on the comprehensive control strategy, generate an application evaluation value of the comprehensive control strategy according to the virtual monitoring data of each monitoring point after simulation, and determine whether to generate a correction instruction for the comprehensive control strategy according to the application evaluation value.

[0021] In some embodiments of the present application, multiple monitoring points are set according to the equipment parameters of the wind turbine generator set, including: Acquire equipment parameters of each equipment in the wind turbine generator set, wherein the equipment parameters include preset important coefficients, application coefficients, cost coefficients, and correlation coefficients; Generate an influence coefficient of the corresponding device according to the device parameters of each device, and set the device with an influence coefficient greater than a preset influence coefficient as a concerned device; Generate a reference map of interest based on location parameters of multiple devices of interest, and set corresponding monitoring points and the number of monitoring points based on the comprehensive influence coefficient and aggregation degree within a preset area in the reference map of interest; A historical operation evaluation value of the corresponding monitoring point is generated based on the historical monitoring data at each monitoring point, and the equipment associated with each monitoring point is determined based on the degree of synchronization between the historical operation evaluation value and the historical characteristic operation data of the equipment of interest within a preset area of ​​the corresponding monitoring point.

[0022] In this embodiment, the preset importance coefficient refers to the coefficient set before each device is put into operation, the application coefficient refers to the application frequency of each device after the wind turbine receives an instruction each time, the cost coefficient refers to the cost of maintenance and replacement of each device, the association coefficient refers to the number of other devices associated with each device, and the influence coefficient refers to the degree of influence of each device on the wind turbine. That is, the larger the preset importance coefficient, the larger the application coefficient, the larger the cost coefficient and the larger the association coefficient, the larger the influence coefficient.

[0023] In this embodiment, the comprehensive influence coefficient refers to the sum of the influence coefficients of the devices of interest within a preset area, and the degree of aggregation refers to the number of devices of interest within the preset area. The more devices of interest there are, the greater the degree of aggregation. When the comprehensive influence coefficient is larger and the degree of aggregation is larger, the number of monitoring points is larger, and most of them are set at the aggregation points.

[0024] In this embodiment, by setting monitoring points and determining the associated equipment of each monitoring point, the operating status of the wind turbine generator set is quickly determined and the corresponding control strategy is configured, thereby improving the control efficiency and control effect of the wind turbine generator set.

[0025] In some embodiments of the present application, determining the device associated with each monitoring point includes: Pre-set multiple operation evaluation indicators; Determine the historical characteristic operation data corresponding to the operation evaluation index according to the correlation degree between the operation evaluation index and the historical operation data of each concerned device; According to the fluctuation degree of the historical monitoring data of each monitoring point, the monitoring time interval of the historical monitoring data of the corresponding monitoring point is set; Generate multiple historical operation evaluation values ​​of historical monitoring data of corresponding monitoring points according to monitoring time intervals; A monitoring point is randomly selected in the preset area and set as the target monitoring point; Based on the preset time period as the time reference line, historical characteristic operation data of the concerned equipment whose relative distance to the target monitoring point is less than the preset relative distance is collected according to the monitoring time interval within the preset time period; Mapping the historical characteristic operation data collected at each monitoring time interval within a preset period and the historical operation evaluation value of the target monitoring point onto the time reference line; Calculate the first change value of the historical operation evaluation value of each monitoring time interval in the time reference line, set the monitoring time interval whose first change value is greater than the preset first change value threshold as the attention time interval, obtain the second change value of the historical characteristic operation data of each attention time interval, and generate the degree of synchronous change of the same historical characteristic operation data and the historical operation evaluation value according to the second change value difference value of the second change value greater than the preset second change value threshold and the number of attention time intervals whose second change value is greater than the preset second change value threshold; If the synchronization change degree is greater than a preset synchronization change degree threshold, the focus device corresponding to the current historical characteristic operation data is set as the device associated with the target monitoring point.

[0026] In this embodiment, the operation evaluation indicators include but are not limited to operation status evaluation indicators, operation efficiency evaluation indicators, operation energy consumption evaluation indicators, etc. The historical characteristic operation data refers to data associated with multiple operation evaluation indicators. The greater the fluctuation degree of the historical monitoring data, the smaller the monitoring time interval of the corresponding monitoring point. When the fluctuation degree is smaller, the monitoring time interval of the corresponding monitoring point is larger.

[0027] In this embodiment, the degree of synchronous change refers to that the second change value changes with the first change value and the degree of change is large. When the second change value is greater than the preset second change value threshold, it means that the degree of synchronous change of the historical characteristic operation data of the corresponding time interval of interest is large. If the degree of synchronous change of the historical characteristic operation data of all time intervals of interest is large, then the current historical characteristic operation data is highly correlated with the operation of the corresponding monitoring point.

[0028] In this embodiment, by determining the historical characteristic operation data of the device of interest, and determining the associated device of each monitoring point according to the degree of synchronization change between the monitoring point and the historical characteristic operation data of the device of interest within a shorter distance, the wind turbine is divided into multiple monitoring point associated devices, and corresponding control strategies are determined respectively, thereby improving the precise regulation of the control strategy and achieving the control efficiency and control effect of the wind turbine.

[0029] In some embodiments of the present application, the calculation formula for the operation correlation degree is: ; Among them, Y is the degree of operation relevance, n is the number of attention time intervals whose second change value is greater than the preset second change value threshold, m is the total number of attention time intervals, Di is the second change value of the i-th attention time interval whose second change value is greater than the preset second change value threshold, and D0 is the preset second change value threshold.

[0030] In some embodiments of the present application, real-time monitoring data of each monitoring point is obtained, and an operation evaluation value of each monitoring point is generated, including: Obtain real-time monitoring data from each monitoring point; Preset multiple standard monitoring data intervals, and each standard monitoring data interval includes multiple standard monitoring data sub-intervals, and each standard monitoring data sub-interval is configured with a corresponding preset operation evaluation value; Compare the real-time monitoring data with the corresponding standard monitoring data intervals to determine the standard monitoring data sub-interval in which the real-time monitoring data is located; The preset operation evaluation values ​​of the standard monitoring data sub-intervals in which all real-time monitoring data are located are averaged to obtain the operation evaluation values ​​of the corresponding monitoring points.

[0031] In this embodiment, multiple standard monitoring data intervals are set based on the historical monitoring data of each monitoring point, and the standard monitoring data interval is divided into multiple standard monitoring data sub-intervals, and the preset operation evaluation value of the labeled monitoring data sub-interval that is closer to the optimal monitoring data is larger.

[0032] In some embodiments of the present application, a first control strategy for a device associated with each monitoring point is generated according to the operation evaluation value of each monitoring point and a preset control model of the device associated with each monitoring point, including: Compare the operation evaluation value of each monitoring point with the corresponding standard operation evaluation value to obtain the difference of the operation evaluation value of each monitoring point; Obtain a control strategy reference library of the equipment associated with each monitoring point, wherein the control strategy reference library includes a preset operation evaluation value difference of the current monitoring point, and each preset operation evaluation value difference is mapped with a preset control strategy of the equipment associated with the corresponding monitoring point; According to the preset operation evaluation value difference in the control strategy reference library of the equipment associated with each monitoring point as the training input data set, the preset control strategy mapped to the preset operation evaluation value difference is used as the training output data set, and the neural network training is performed to generate the preset control model of the equipment associated with each monitoring point; The difference in the operation evaluation values ​​of each monitoring point is input into a preset control model corresponding only to the equipment associated with the monitoring point, so as to obtain the first control strategy for the equipment associated with each monitoring point.

[0033] In this embodiment, the control strategy reference library is constructed based on the difference in historical operation evaluation values ​​of each monitoring point and the historical preferred control strategy of the equipment associated with the corresponding monitoring point. The historical preferred control strategy refers to a control strategy in which the historical characteristic operation data of the equipment associated with the monitoring point after regulation meets the corresponding operation evaluation index.

[0034] In this embodiment, by constructing a preset control model of the equipment associated with each monitoring point, a first control strategy for the difference in the operating evaluation value of the current monitoring point is obtained, that is, the first control strategy for the equipment associated with all monitoring points, thereby laying the foundation for the subsequent determination of a comprehensive control strategy, improving the control efficiency and control effect of the wind turbine control strategy, ensuring the normal operation of the wind turbine and improving the operating efficiency.

[0035] In some embodiments of the present application, an influence model is constructed according to the influence relationship between monitoring points, including: Obtain the historical control log of each monitoring point, analyze the historical control log, and filter out the historical operation evaluation value corresponding to each historical control log; Obtain the historical operation evaluation value change and historical change nodes in the historical control log of each monitoring point, and determine the degree of dependence of the remaining monitoring points at each historical change node on the current monitoring point, set the remaining monitoring points with a degree of dependence greater than a preset dependence threshold as the influencing monitoring points of the current monitoring point, and obtain the historical monitoring data change of the influencing monitoring points at each historical change node; The historical operation evaluation value change of each monitoring point is used as the first training input data set, the influencing monitoring point at the same historical change node of each historical operation evaluation value change is used as the first training output data set, and the historical monitoring data change at the same historical change node of each influencing monitoring point is used as the second training output data set; A neural network training is performed according to the first training input data set, the first training output data set and the second training output data set to obtain an influence model between the monitoring points involved.

[0036] In this embodiment, the degree of dependence refers to the degree to which the change in historical monitoring data of the remaining monitoring points changes with the change in the historical operation evaluation value of the current monitoring point. When the change in historical monitoring data of the remaining monitoring points at each historical change node of the historical operation evaluation value change is greater than the preset monitoring data change threshold, the degree of dependence is greater, otherwise it is smaller.

[0037] In this embodiment, by determining the historical change node of each monitoring point, determining other affected monitoring points at the same historical change node, and obtaining the change in monitoring data of other affected monitoring points, an impact model between the monitoring points involved is constructed to provide a basis for the subsequent determination of the comprehensive control strategy, thereby ensuring the rationality and effectiveness of the comprehensive control strategy.

[0038] In some embodiments of the present application, determining a comprehensive control strategy for a wind turbine generator system includes: Constructing an influence relationship diagram of all monitoring points according to the influence model between different monitoring points, wherein the influence relationship diagram includes all monitoring points, and the connection distance between each monitoring point is set according to the influence model; Generate a central coefficient of the corresponding monitoring point according to the connection distance and the number of connections of the direct connection of each monitoring point, and set the monitoring point whose central coefficient is greater than the preset central coefficient threshold as the central point of the monitoring point in the influence relationship diagram; Acquire the monitoring points in the influence relationship diagram whose connection distances with the center point of each monitoring point are within a preset connection distance interval and the first control strategies of the devices associated with the corresponding monitoring points, and form a first control strategy library for the center point of each monitoring point; Analyze the first control strategies in the same first control strategy library, obtain the commensurable factors between different first control strategies in the same control strategy library, and obtain the second control strategy for the center point of each monitoring point; The second control strategies of the center points of multiple monitoring points are subjected to conflict analysis. If there is a conflict, they are coordinated according to the corresponding second control strategies, and the coordinated second control strategies are subjected to integrated learning, and the comprehensive control strategy is determined according to the integrated learning results.

[0039] In this embodiment, conflict refers to the phenomenon that control strategies at the same time conflict with each other. If there is a conflict in the second control strategy, a coordination method will be set according to the importance of the center point of the monitoring point involved and the specific second control strategy. The coordinated second control strategy ensures that the impact on the center points of other monitoring points is minimized and the operating efficiency of the wind turbine is maximized.

[0040] In this embodiment, the relationship between the monitoring points is determined by constructing an influence relationship diagram, and the center point of the monitoring point in the influence relationship diagram is set. The first control strategy of the center point of the monitoring point and the monitoring point that is closer are merged to obtain multiple second control strategies. The multiple second control strategies are integrated and learned to generate a comprehensive control strategy and predict the corresponding control results. The optimal control strategy is screened out to ensure the normal operation of the wind turbine and improve the operating efficiency of the wind turbine, thereby improving the control accuracy and control efficiency of the wind turbine control system.

[0041] In some embodiments of the present application, generating an application evaluation value of the comprehensive control strategy according to the simulated virtual monitoring data of each monitoring point includes: Construct a simulation model of the wind turbine generator set, simulate the comprehensive control strategy based on the simulation model, and obtain virtual monitoring data of each monitoring point after simulation; Generate a virtual operation evaluation value for each monitoring point based on virtual monitoring data; Compare the virtual operation evaluation value of each monitoring point with the operation evaluation value before simulation to obtain the change characteristics of the operation evaluation value of each monitoring point, wherein the change characteristics include the change trend, change rate and change value of the operation evaluation value; The application evaluation value of the comprehensive control strategy is based on the change characteristics of the operation evaluation values ​​of all monitoring points; Pre-set application evaluation value thresholds; When the application evaluation value is less than the application evaluation value threshold, a correction instruction of the comprehensive control strategy is generated; When the application evaluation value is greater than the application evaluation value threshold, no correction instruction for the comprehensive control strategy is generated.

[0042] In this embodiment, when the changing trend in the changing characteristics of all monitoring points is an upward trend, the changing rate is greater than the preset changing rate, and the changing value is greater than the preset changing value, the application evaluation value is larger; when the changing trend in the changing characteristics of all monitoring points is an upward trend or the changing rate is greater than the preset changing rate or the changing value is greater than the preset changing value, the application evaluation value is smaller.

[0043] In this embodiment, by simulating the comprehensive control strategy, the corresponding application evaluation value is obtained, and whether to correct the comprehensive control strategy is determined according to the application evaluation value, thereby achieving precise regulation of the comprehensive control strategy, ensuring the control accuracy of the wind turbine control system, and improving the control efficiency and operation efficiency of the wind turbine.

[0044] In some embodiments of the present application, Figure 2 As shown, a wind turbine generator control method based on PLC is also included: Step S201: setting a plurality of monitoring points according to the equipment parameters of the wind turbine generator set, acquiring real-time monitoring data of each monitoring point, and generating an operation evaluation value of each monitoring point; Step S202: generating a first control strategy for the equipment associated with each monitoring point according to the operation evaluation value of each monitoring point and the preset control model of the equipment associated with each monitoring point; Step S203: constructing an influence model according to the influence relationship between the monitoring points, integrating the first control strategies of the equipment involved in the corresponding monitoring points according to the influence model, and determining the comprehensive control strategy of the wind turbine generator set; Step S204: performing control simulation on the comprehensive control strategy, generating an application evaluation value of the comprehensive control strategy according to the virtual monitoring data of each monitoring point after simulation, and determining whether to generate a correction instruction for the comprehensive control strategy according to the application evaluation value.

[0045] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and substitutions can be made without departing from the technical principles of the present application. These improvements and substitutions should also be regarded as the scope of protection of the present application.

Claims

1. A PLC-based wind turbine control system, characterized in that: include: An acquisition module is used to set multiple monitoring points according to the equipment parameters of the wind turbine generator set, obtain real-time monitoring data of each monitoring point, and generate an operation evaluation value of each monitoring point; A generating module, used for generating a first control strategy for a device associated with each monitoring point according to an operation evaluation value of each monitoring point and a preset control model of a device associated with each monitoring point; A determination module, used to construct an influence model according to the influence relationship between the monitoring points, integrate the first control strategies of the equipment involved in the corresponding monitoring points according to the influence model, and determine the comprehensive control strategy of the wind turbine generator set; The control module is used to perform control simulation on the comprehensive control strategy, generate an application evaluation value of the comprehensive control strategy according to the virtual monitoring data of each monitoring point after simulation, and determine whether to generate a correction instruction for the comprehensive control strategy according to the application evaluation value.

2. The PLC-based wind turbine control system according to claim 1, characterized in that: Multiple monitoring points are set according to the equipment parameters of the wind turbine, including: Acquire equipment parameters of each equipment in the wind turbine generator set, wherein the equipment parameters include preset important coefficients, application coefficients, cost coefficients, and correlation coefficients; Generate an influence coefficient of the corresponding device according to the device parameters of each device, and set the device with an influence coefficient greater than a preset influence coefficient as a concerned device; Generate a reference map of interest based on location parameters of multiple devices of interest, and set corresponding monitoring points and the number of monitoring points based on the comprehensive influence coefficient and aggregation degree within a preset area in the reference map of interest; A historical operation evaluation value of the corresponding monitoring point is generated based on the historical monitoring data at each monitoring point, and the equipment associated with each monitoring point is determined based on the degree of synchronization between the historical operation evaluation value and the historical characteristic operation data of the equipment of interest within a preset area of ​​the corresponding monitoring point.

3. The PLC-based wind turbine control system according to claim 2, characterized in that: Determine the equipment associated with each monitoring point, including: Pre-set multiple operation evaluation indicators; Determine the historical characteristic operation data corresponding to the operation evaluation index according to the correlation degree between the operation evaluation index and the historical operation data of each concerned device; According to the fluctuation degree of the historical monitoring data of each monitoring point, the monitoring time interval of the historical monitoring data of the corresponding monitoring point is set; Generate multiple historical operation evaluation values ​​of historical monitoring data of corresponding monitoring points according to monitoring time intervals; A monitoring point is randomly selected in the preset area and set as the target monitoring point; Based on the preset time period as the time reference line, historical characteristic operation data of the concerned equipment whose relative distance to the target monitoring point is less than the preset relative distance is collected according to the monitoring time interval within the preset time period; Mapping the historical characteristic operation data collected at each monitoring time interval within a preset period and the historical operation evaluation value of the target monitoring point onto the time reference line; Calculate the first change value of the historical operation evaluation value of each monitoring time interval in the time reference line, set the monitoring time interval whose first change value is greater than the preset first change value threshold as the attention time interval, obtain the second change value of the historical characteristic operation data of each attention time interval, and generate the degree of synchronous change of the same historical characteristic operation data and the historical operation evaluation value according to the second change value difference value of the second change value greater than the preset second change value threshold and the number of attention time intervals whose second change value is greater than the preset second change value threshold; If the synchronization change degree is greater than a preset synchronization change degree threshold, the focus device corresponding to the current historical characteristic operation data is set as the device associated with the target monitoring point.

4. The PLC-based wind turbine control system according to claim 3, characterized in that: The calculation formula of the operation correlation degree is: ； Among them, Y is the degree of operation relevance, n is the number of attention time intervals whose second change value is greater than the preset second change value threshold, m is the total number of attention time intervals, Di is the second change value of the i-th attention time interval whose second change value is greater than the preset second change value threshold, and D0 is the preset second change value threshold.

5. The PLC-based wind turbine control system according to claim 3, characterized in that: Obtain real-time monitoring data from each monitoring point and generate operation evaluation values ​​for each monitoring point, including: Obtain real-time monitoring data from each monitoring point; Preset multiple standard monitoring data intervals, and each standard monitoring data interval includes multiple standard monitoring data sub-intervals, and each standard monitoring data sub-interval is configured with a corresponding preset operation evaluation value; Compare the real-time monitoring data with the corresponding standard monitoring data intervals to determine the standard monitoring data sub-interval in which the real-time monitoring data is located; The preset operation evaluation values ​​of the standard monitoring data sub-intervals in which all real-time monitoring data are located are averaged to obtain the operation evaluation values ​​of the corresponding monitoring points.

6. The PLC-based wind turbine control system according to claim 5, characterized in that: Generate a first control strategy for the equipment associated with each monitoring point according to the operation evaluation value of each monitoring point and the preset control model of the equipment associated with each monitoring point, including: Compare the operation evaluation value of each monitoring point with the corresponding standard operation evaluation value to obtain the difference of the operation evaluation value of each monitoring point; Obtain a control strategy reference library of the equipment associated with each monitoring point, wherein the control strategy reference library includes a preset operation evaluation value difference of the current monitoring point, and each preset operation evaluation value difference is mapped with a preset control strategy of the equipment associated with the corresponding monitoring point; According to the preset operation evaluation value difference in the control strategy reference library of the equipment associated with each monitoring point as the training input data set, the preset control strategy mapped to the preset operation evaluation value difference is used as the training output data set, and the neural network training is performed to generate the preset control model of the equipment associated with each monitoring point; The difference in the operation evaluation values ​​of each monitoring point is input into a preset control model corresponding only to the equipment associated with the monitoring point, so as to obtain the first control strategy for the equipment associated with each monitoring point.

7. The PLC-based wind turbine control system according to claim 6, characterized in that: The impact model is constructed based on the impact relationship between monitoring points, including: Obtain the historical control log of each monitoring point, analyze the historical control log, and filter out the historical operation evaluation value corresponding to each historical control log; Obtain the historical operation evaluation value change and historical change nodes in the historical control log of each monitoring point, and determine the degree of dependence of the remaining monitoring points at each historical change node on the current monitoring point, set the remaining monitoring points with a degree of dependence greater than a preset dependence threshold as the influencing monitoring points of the current monitoring point, and obtain the historical monitoring data change of the influencing monitoring points at each historical change node; The historical operation evaluation value change of each monitoring point is used as the first training input data set, the influencing monitoring point at the same historical change node of each historical operation evaluation value change is used as the first training output data set, and the historical monitoring data change at the same historical change node of each influencing monitoring point is used as the second training output data set; A neural network training is performed according to the first training input data set, the first training output data set and the second training output data set to obtain an influence model between the monitoring points involved.

8. The PLC-based wind turbine generator control system according to claim 7, characterized in that: Determine the comprehensive control strategy for the wind turbine, including: Constructing an influence relationship diagram of all monitoring points according to the influence model between different monitoring points, wherein the influence relationship diagram includes all monitoring points, and the connection distance between each monitoring point is set according to the influence model; Generate a central coefficient of the corresponding monitoring point according to the connection distance and the number of connections of the direct connection of each monitoring point, and set the monitoring point whose central coefficient is greater than the preset central coefficient threshold as the central point of the monitoring point in the influence relationship diagram; Acquire the monitoring points in the influence relationship diagram whose connection distances with the center point of each monitoring point are within a preset connection distance interval and the first control strategies of the devices associated with the corresponding monitoring points, and form a first control strategy library for the center point of each monitoring point; Analyze the first control strategies in the same first control strategy library, obtain the commensurable factors between different first control strategies in the same control strategy library, and obtain the second control strategy for the center point of each monitoring point; The second control strategies of the center points of multiple monitoring points are subjected to conflict analysis. If there is a conflict, they are coordinated according to the corresponding second control strategies, and the coordinated second control strategies are subjected to integrated learning, and the comprehensive control strategy is determined according to the integrated learning results.

9. The PLC-based wind turbine generator control system according to claim 7, characterized in that: Generate application evaluation values ​​of comprehensive control strategies based on virtual monitoring data of each monitoring point after simulation, including: Construct a simulation model of the wind turbine generator set, simulate the comprehensive control strategy based on the simulation model, and obtain virtual monitoring data of each monitoring point after simulation; Generate a virtual operation evaluation value for each monitoring point based on virtual monitoring data; Compare the virtual operation evaluation value of each monitoring point with the operation evaluation value before simulation to obtain the change characteristics of the operation evaluation value of each monitoring point, wherein the change characteristics include the change trend, change rate and change value of the operation evaluation value; The application evaluation value of the comprehensive control strategy is based on the change characteristics of the operation evaluation values ​​of all monitoring points; Pre-set application evaluation value thresholds; When the application evaluation value is less than the application evaluation value threshold, a correction instruction of the comprehensive control strategy is generated; When the application evaluation value is greater than the application evaluation value threshold, no correction instruction for the comprehensive control strategy is generated.

10. A PLC-based wind turbine control method, characterized in that: include: Set multiple monitoring points according to the equipment parameters of the wind turbine generator set, obtain real-time monitoring data of each monitoring point, and generate operation evaluation values ​​of each monitoring point; Generate a first control strategy for the equipment associated with each monitoring point according to the operation evaluation value of each monitoring point and the preset control model of the equipment associated with each monitoring point; An influence model is constructed according to the influence relationship between the monitoring points, and the first control strategies of the equipment involved in the corresponding monitoring points are integrated according to the influence model to determine the comprehensive control strategy of the wind turbine generator set; A control simulation is performed on the comprehensive control strategy, and an application evaluation value of the comprehensive control strategy is generated according to the virtual monitoring data of each monitoring point after the simulation. It is determined whether to generate a correction instruction for the comprehensive control strategy according to the application evaluation value.

Images