Heat dissipation control method and device of offshore wind generating set and storage medium

Abstract

The invention provides a heat dissipation control method and device of an offshore wind generating set and a storage medium. The method comprises the following steps: acquiring temperature values of a wind wheel at a plurality of preset time points, flow velocity values of cooling water and heat input values of a plurality of heat increasing factors; obtaining a cooling input vector according to the temperature value and the flow velocity value; obtaining a heat increase input vector according to the heat input values of the plurality of heat increase factors; calculating responsiveness estimation of the cooling input vector relative to the heat increasing input vector to obtain a response feature vector, and correcting a numerical value of the response feature vector; and logistic regression is carried out to obtain a flow velocity control value for representing cooling water at the current time point so as to carry out heat dissipation control according to the flow velocity control value. According to the method, the real-time temperature of the heat dissipation wind wheel is considered, the additional heat increment condition is also considered, and the interaction relation between the cooling capacity and the heat increment is obtained, so that the accuracy of responsive control of heat dissipation control is improved.

Description

Technical Field

[0001] The present application relates to the field of offshore wind power generation heat dissipation technology, and in particular to a heat dissipation control method, device and storage medium for an offshore wind power generator set. Background Art

[0002] Wind turbines are mainly composed of towers, nacelles and rotors. For offshore wind turbines, in order to prevent erosion by salt spray and rain, the rotors are generally completely isolated from the outside world by using a sealed structure. Since there are heat-generating components such as the variable pitch shaft control cabinet, supercapacitor cabinet, variable pitch motor, main shaft and cables in the rotor, when the unit is running, the heat emitted from the surface of the heat-generating components in the rotor will be discharged into the hub. Especially in the high temperature environment in summer, the heat transferred from the external solar radiation to the inside of the rotor will also increase, causing the ambient temperature in the hub to be too high, affecting the normal operation of the unit, and even causing the unit to shut down due to overheating, resulting in loss of power generation.

[0003] The industry mainly uses water cooling system solutions for wind rotor heat dissipation, but the cooling effect of existing water cooling solutions often cannot meet application requirements. Because the existing water cooling system for offshore wind turbines usually transports coolant at a predetermined flow rate for heat exchange, but due to the different working conditions and working environments of offshore wind turbines, the constant flow rate heat dissipation solution cannot meet the heat dissipation requirements of changing working conditions and environments. Therefore, an optimized heat dissipation control solution for offshore wind turbines is expected. Summary of the invention

[0004] The present application provides a heat dissipation control method, device and system for an offshore wind turbine generator set to improve the cooling effect of a water cooling system. The technical solution of the present application is as follows:

[0005] In a first aspect, an embodiment of the present application provides a heat dissipation control method for an offshore wind turbine generator set, comprising:

[0006] Obtaining temperature values ​​of the wind wheel at multiple predetermined time points including the current time point, flow rate values ​​of cooling water of the water cooling system, and heat input values ​​of multiple heat increase factors of the wind wheel;

[0007] Arranging the temperature values ​​of the wind wheel at the plurality of predetermined time points including the current time point and the flow rate values ​​of the cooling water of the water cooling system into a temperature input vector and a flow rate input vector respectively, and calculating the position difference between the temperature input vector and the flow rate input vector to obtain a cooling input vector;

[0008] Arranging heat input values ​​of a plurality of heat increase factors of the wind wheel at a plurality of predetermined time points including the current time point into heat increase input vectors respectively, and calculating a position-weighted sum of the plurality of heat increase input vectors to obtain a heat increase input vector;

[0009] Calculating the responsiveness estimate of the temperature reduction input vector relative to the heat increase input vector to obtain a response characteristic vector; and correcting the value of the response characteristic vector based on a Markov chain-like state transfer method to obtain a regression characteristic vector;

[0010] The regression feature vector is subjected to a logistic regression to obtain a flow rate control value of cooling water of the water cooling system used to characterize the current time point, so as to perform heat dissipation control according to the flow rate control value.

[0011] In some implementations, the method of modifying the value of the response feature vector based on a Markov chain-like state transition to obtain a regression feature vector includes:

[0012] Respectively converting the numerical values ​​in the temperature input vector, the flow rate input vector and the heat gain input vector into switch state values ​​to obtain a first switch control vector, a second switch control vector and a third switch control vector;

[0013] Passing the first switch control vector and the second switch control vector through a matrix array of XNOR gates to obtain a same state control matrix;

[0014] Passing the first switch control vector and the third switch control vector through a matrix array of XNOR gates to obtain a first response control matrix;

[0015] Passing the second switch control vector and the third switch control vector through a matrix array of XNOR gates to obtain a second response control matrix;

[0016] Calculating a set union of the first response control matrix and the second response control matrix, and calculating a set intersection of the set union and the same state control matrix to obtain a response state matrix;

[0017] The response state matrix is ​​multiplied by the response eigenvector to obtain a regression eigenvector.

[0018] In some implementations, converting the values ​​in the temperature input vector, the flow rate input vector, and the heat gain input vector into switch state values ​​to obtain a first switch control vector, a second switch control vector, and a third switch control vector includes:

[0019] The temperature input vector, the flow rate input vector and the heat gain input vector are respectively input into a plurality of parallel switches based on a predetermined threshold value, so as to convert the temperature input vector, the flow rate input vector and the heat gain input vector into the first switch control vector, the second switch control vector and the third switch control vector having values ​​of 0 and 1 respectively; wherein the plurality of parallel switches have the same predetermined threshold value, or the plurality of parallel switches each have an independent predetermined threshold value.

[0020] In some implementations, calculating the position difference between the temperature input vector and the flow rate input vector to obtain the temperature reduction input vector includes:

[0021] The temperature input vector and the flow rate input vector are input into a plurality of parallel subtractors to obtain the temperature reduction input vector.

[0022] In some implementations, calculating the position-weighted sum of the plurality of heat gain input vectors to obtain the heat gain input vector includes:

[0023] The heat increase input vectors are input into a plurality of parallel multipliers and a plurality of parallel adders connected in series with the plurality of parallel multipliers to obtain the heat increase input vectors.

[0024] In some implementations, calculating the responsiveness estimate of the temperature reduction input vector relative to the heat increase input vector to obtain a response characteristic vector includes:

[0025] The temperature reduction input vector and the heat increase input vector are input into a plurality of parallel dividers for position division to obtain the response characteristic vector.

[0026] In some implementations, performing a logistic regression on the regression feature vector to obtain a flow rate control value of cooling water of the water cooling system for characterizing the current time point includes:

[0027] Inputting the regression feature vector into a plurality of parallel multipliers and an adder connected in series with the plurality of parallel multipliers to obtain a regression value;

[0028] The regression value is input into a control switch based on a predetermined threshold to obtain a flow rate control value of cooling water in the water cooling system that is used to characterize the current time point; wherein the flow rate control value is a logical value indicating whether the flow rate value should be increased or decreased.

[0029] In a second aspect, an embodiment of the present application provides a heat dissipation control device for an offshore wind turbine generator set, comprising:

[0030] A wind power data acquisition module, used to acquire the temperature value of the wind wheel at multiple predetermined time points including the current time point, the flow rate value of the cooling water of the water cooling system, and the heat input value of multiple heat increase factors of the wind wheel;

[0031] a cooling vector acquisition module, used to arrange the temperature values ​​of the wind wheel at a plurality of predetermined time points including the current time point and the flow rate values ​​of the cooling water of the water cooling system as a temperature input vector and a flow rate input vector, respectively, and calculate the position difference between the temperature input vector and the flow rate input vector to obtain a cooling input vector;

[0032] a heat increase vector acquisition module, used to arrange the heat input values ​​of the multiple heat increase factors of the wind wheel at multiple predetermined time points including the current time point into heat increase input vectors, and calculate the position-weighted sum of the multiple heat increase input vectors to obtain the heat increase input vector;

[0033] a response feature acquisition module, used to calculate the responsiveness estimate of the temperature reduction input vector relative to the heat increase input vector to obtain a response feature vector; and based on a Markov chain-like state transfer method, to correct the value of the response feature vector to obtain a regression feature vector;

[0034] The flow rate value acquisition module is used to perform logistic regression on the regression feature vector to obtain a flow rate control value of cooling water of the water cooling system used to characterize the current time point, so as to perform heat dissipation control according to the flow rate control value.

[0035] In some implementations, the response feature acquisition module corrects the value of the response feature vector based on a Markov chain-like state transition to obtain a regression feature vector, specifically for:

[0036] Respectively converting the numerical values ​​in the temperature input vector, the flow rate input vector and the heat gain input vector into switch state values ​​to obtain a first switch control vector, a second switch control vector and a third switch control vector;

[0037] Passing the first switch control vector and the second switch control vector through a matrix array of XNOR gates to obtain a same state control matrix;

[0038] Passing the first switch control vector and the third switch control vector through a matrix array of XNOR gates to obtain a first response control matrix;

[0039] Passing the second switch control vector and the third switch control vector through a matrix array of XNOR gates to obtain a second response control matrix;

[0040] Calculating a set union of the first response control matrix and the second response control matrix, and calculating a set intersection of the set union and the same state control matrix to obtain a response state matrix;

[0041] The response state matrix is ​​multiplied by the response eigenvector to obtain a regression eigenvector.

[0042] In some implementations, when the response characteristic acquisition module converts the numerical values ​​in the temperature input vector, the flow rate input vector, and the heat gain input vector into switch state values ​​respectively to obtain the first switch control vector, the second switch control vector, and the third switch control vector, it is specifically used to:

[0043] The temperature input vector, the flow rate input vector and the heat gain input vector are respectively input into a plurality of parallel switches based on a predetermined threshold value, so as to convert the temperature input vector, the flow rate input vector and the heat gain input vector into the first switch control vector, the second switch control vector and the third switch control vector having values ​​of 0 and 1 respectively; wherein the plurality of parallel switches have the same predetermined threshold value, or the plurality of parallel switches each have an independent predetermined threshold value.

[0044] In some implementations, when the temperature reduction vector acquisition module calculates the position difference between the temperature input vector and the flow rate input vector to obtain the temperature reduction input vector, it is specifically used to:

[0045] The temperature input vector and the flow rate input vector are input into a plurality of parallel subtractors to obtain the temperature reduction input vector.

[0046] In some implementations, when the heat increase vector acquisition module calculates the position-weighted sum of the plurality of heat increase input vectors to obtain the heat increase input vector, it is specifically used to:

[0047] The heat increase input vectors are input into a plurality of parallel multipliers and a plurality of parallel adders connected in series with the plurality of parallel multipliers to obtain the heat increase input vectors.

[0048] In some implementations, when the response characteristic acquisition module calculates the responsiveness estimate of the temperature reduction input vector relative to the heat increase input vector to obtain the response characteristic vector, it is specifically used to:

[0049] The temperature reduction input vector and the heat increase input vector are input into a plurality of parallel dividers for position division to obtain the response characteristic vector.

[0050] In some implementations, when the flow rate value acquisition module performs logistic regression on the regression feature vector to obtain the flow rate control value of the cooling water of the water cooling system for characterizing the current time point, it is specifically used to:

[0051] Inputting the regression feature vector into a plurality of parallel multipliers and an adder connected in series with the plurality of parallel multipliers to obtain a regression value;

[0052] The regression value is input into a control switch based on a predetermined threshold to obtain a flow rate control value of cooling water in the water cooling system that is used to characterize the current time point; wherein the flow rate control value is a logical value indicating whether the flow rate value should be increased or decreased.

[0053] In a third aspect, an embodiment of the present application provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the heat dissipation control method for an offshore wind turbine generator set described in the embodiment of the first aspect of the present application.

[0054] In a fourth aspect, an embodiment of the present application provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to execute the heat dissipation control method for an offshore wind turbine generator set described in the embodiment of the first aspect of the present application.

[0055] In a fifth aspect, an embodiment of the present application provides a computer program product, including computer instructions, which, when executed by a processor, implement the steps of the heat dissipation control method for an offshore wind turbine generator set described in the embodiment of the first aspect of the present application.

[0056] The technical solution provided by the embodiments of the present application brings at least the following beneficial effects:

[0057] Not only the real-time temperature of the cooling fan wheel is taken into account, but also the additional heat gain is taken into account. The differential vector between the time series vector of the fan wheel temperature and the time series vector of the cooling water flow rate is used as the cooling input vector to represent the cooling capacity; the position-weighted sum of multiple heat gain input vectors is used as the heat gain input vector to represent the heat gain capacity. The responsiveness of the cooling input vector relative to the heat gain input vector is estimated to represent the interaction between the cooling capacity and the heat gain, so as to improve the accuracy of the responsiveness control of the heat dissipation control. The numerical value of the response characteristic vector is further corrected based on the Markov chain-like state transition method to further improve the accuracy of the heat dissipation control.

[0058] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application, and do not constitute an improper limitation on the present application.

[0060] Figure 1 The present invention is a flow chart showing a heat dissipation control method for an offshore wind turbine generator set according to an exemplary embodiment.

[0061] Figure 2 The present invention is a flow chart showing a heat dissipation control method for an offshore wind turbine generator set according to another exemplary embodiment.

[0062] Figure 3 It is an application scenario diagram of a heat dissipation control method for an offshore wind turbine generator set according to an exemplary embodiment.

[0063] Figure 4 The present invention is a block diagram of a heat dissipation control device for an offshore wind turbine generator set according to an exemplary embodiment.

[0064] Figure 5 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0065] In order to enable ordinary persons in the art to better understand the technical solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0066] It should be noted that the terms "first", "second", etc. in this application are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the application described here can be implemented in an order other than those illustrated or described here. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0067] Figure 1 : is a flow chart of a heat dissipation control method for an offshore wind turbine generator set according to an embodiment of the present application. It should be noted that the heat dissipation control method for an offshore wind turbine generator set according to an embodiment of the present application can be applied to a heat dissipation control device for an offshore wind turbine generator set according to an embodiment of the present application. The heat dissipation control device for an offshore wind turbine generator set can be configured on an electronic device such as a dedicated programmable controller. Figure 1 As shown, the heat dissipation control method of the offshore wind turbine generator set may include the following steps.

[0068] Step S101, obtaining the temperature value of the wind wheel at multiple predetermined time points including the current time point, the flow rate value of cooling water in the water cooling system, and the heat input values ​​of multiple heat increase factors of the wind wheel.

[0069] Considering that when performing heat dissipation control, that is, controlling the flow rate of cooling water, it is necessary to consider not only the real-time temperature of the heat dissipation object, that is, the real-time temperature of the heat dissipation fan, but also the heat gain, that is, the additional heat input. Therefore, while obtaining the temperature value of the fan and the flow rate value of the cooling water of the water cooling system, it is also necessary to obtain the heat input values ​​of multiple heat gain factors of the fan at the corresponding time point.

[0070] The temperature value of the wind wheel at a plurality of predetermined time points including the current time point and the flow rate value of the cooling water of the water cooling system are collected by a temperature sensor and a flow meter respectively.

[0071] As an example, the multiple heat increase factors include solar heat load, hub heat load, convection heat load and thermal radiation. That is, the solar heat load, hub heat load, convection heat load and thermal radiation at multiple predetermined time points including the current time point are obtained. These data can be collected by heat load sensors and thermal radiation sensors.

[0072] It should be noted that, considering the complex and harsh working conditions of offshore wind turbines, it is expected that offshore wind turbines have relatively high robustness of control and monitoring. Therefore, in this embodiment, an industrial controller of a programmable logic controller (PLC) is used to perform heat dissipation control, so as to construct a dedicated edge-side control chip adapted for heat dissipation control of offshore wind turbines through the programmable logic controller.

[0073] As a specific implementation example, the temperature value of the wind rotor at multiple predetermined time points including the current time point, the flow rate value of the cooling water of the water cooling system, and the heat input value of multiple heat increase factors of the wind rotor can be received through the input interface and / or communication interface of the dedicated programmable controller for heat dissipation control of the offshore wind turbine generator set. The dedicated programmable logic controller includes an input interface, a communication interface, an output interface, a storage, a central processing unit, etc.

[0074] Step S102, arrange the temperature values ​​of the wind wheel at multiple predetermined time points including the current time point and the flow rate values ​​of the cooling water of the water cooling system into a temperature input vector and a flow rate input vector respectively, and calculate the position difference between the temperature input vector and the flow rate input vector to obtain a cooling input vector.

[0075] According to the time dimension, the temperature value of the wind wheel at a plurality of predetermined time points including the current time point and the flow rate value of the cooling water of the water cooling system are constructed as a temperature input vector and a flow rate input vector respectively.

[0076] The cooling capacity is represented by the difference vector between the time series vector of the wind wheel temperature and the time series vector of the cooling water flow rate, and is represented by the cooling input vector.

[0077] Optionally, the temperature input vector and the flow rate input vector may be stored in the memory of a dedicated programmable controller.

[0078] At the central processing unit end of the dedicated programmable controller, the position difference between the temperature input vector and the flow rate input vector is calculated to obtain a cooling input vector. As an example, the temperature input vector and the flow rate input vector are input into a plurality of parallel subtractors to obtain the cooling input vector. That is, the temperature input vector and the flow rate input vector are input into a plurality of parallel subtractors to perform position difference on the temperature input vector and the flow rate input vector through the plurality of parallel subtractors to obtain the cooling input vector.

[0079] Step S103, arranging the heat input values ​​of multiple heat increase factors of the wind wheel at multiple predetermined time points including the current time point into heat increase input vectors, and calculating the position-weighted sum of the multiple heat increase input vectors to obtain the heat increase input vector.

[0080] Taking multiple heat increase factors including solar heat load, hub heat load, convection heat load and thermal radiation as examples, the heat input values ​​of the multiple heat increase factors of the wind wheel at multiple predetermined time points including the current time point are respectively arranged as a first heat increase input vector, a second heat increase input vector, a third heat increase input vector and a fourth heat increase input vector.

[0081] Optionally, the first heat increase input vector, the second heat increase input vector, the third heat increase input vector and the fourth heat increase input vector may be stored in a memory of a dedicated programmable controller.

[0082] At the central processing unit end of the dedicated programmable controller, the position-weighted sum of the first heat increase input vector, the second heat increase input vector, the third heat increase input vector and the fourth heat increase input vector is calculated to obtain the heat increase input vector. As an example, the first heat increase input vector, the second heat increase input vector, the third heat increase input vector and the fourth heat increase input vector are input into a plurality of parallel multipliers and a plurality of parallel adders connected in series with the plurality of parallel multipliers to obtain the heat increase input vector. Here, the weight values ​​of the plurality of multipliers are obtained based on statistical analysis and are predetermined weight values.

[0083] Step S104, calculating the responsiveness estimate of the temperature reduction input vector relative to the heat increase input vector to obtain a response characteristic vector; and based on a Markov chain-like state transition method, correcting the value of the response characteristic vector to obtain a regression characteristic vector.

[0084] In this embodiment, the responsiveness of the temperature reduction input vector relative to the heat increase input vector is estimated to represent the interaction relationship between the temperature reduction capability and the heat increase, so as to improve the accuracy of the responsiveness control of the heat dissipation control.

[0085] At the central processing unit of the dedicated programmable controller, the responsiveness estimation of the cooling input vector relative to the heat increase input vector is calculated to obtain a response characteristic vector. As an example, the cooling input vector and the heat increase input vector are input into a plurality of parallel dividers for positional division to obtain the response characteristic vector. In other words, the cooling input vector and the heat increase input vector are input into a plurality of parallel dividers to divide the cooling input vector and the heat increase input vector by position through the plurality of parallel dividers to obtain the response characteristic vector.

[0086] Step S105 , performing a logistic regression on the regression feature vector to obtain a flow rate control value of cooling water of the water cooling system for characterizing the current time point, so as to perform heat dissipation control according to the flow rate control value.

[0087] On the central processing unit side of the dedicated programmable controller, the regression feature vector is subjected to logistic regression to obtain a flow rate control value of cooling water of the water cooling system for characterizing the current time point, including:

[0088] The regression feature vector is input into a plurality of parallel multipliers and an adder connected in series with the plurality of parallel multipliers to obtain a regression value; and the regression value is input into a control switch based on a predetermined threshold to obtain a flow rate control value of cooling water of the water cooling system for characterizing the current time point; wherein the flow rate control value is a logical value indicating whether the flow rate value should be increased or decreased.

[0089] As an example, the dedicated programmable controller can output a heat dissipation control instruction through its output interface based on the logic value used to characterize whether the flow rate value of the cooling water at the current time point should be increased or decreased.

[0090] The heat dissipation control method of the offshore wind turbine generator set in the embodiment of the present application not only takes into account the real-time temperature of the heat dissipation wind wheel, but also takes into account the additional heat gain. The differential vector between the time series vector of the wind wheel temperature and the time series vector of the cooling water flow rate is used as the cooling input vector to represent the cooling capacity; the position-weighted sum between multiple heat gain input vectors is used as the heat gain input vector to represent the heat gain capacity. The interaction relationship between the cooling capacity and the heat gain is represented by estimating the responsiveness of the cooling input vector relative to the heat gain input vector, so as to improve the accuracy of the responsiveness control of the heat dissipation control. The numerical value of the response characteristic vector is further corrected based on the Markov chain-like state transition method to further improve the accuracy of the heat dissipation control.

[0091] Considering that there will be data deviation at the original data acquisition end, that is, due to the data acquisition capability of the sensor itself or noise interference, there will be errors in the original data acquisition, and this error will be amplified with the differential calculation and responsiveness estimation calculation, which will lead to the direct logical regression of the response feature vector to obtain a logical value indicating that the flow rate value of the cooling water at the current time point should be increased or decreased, which will reduce the accuracy of responsiveness control. In response to the above technical problems, the embodiment of the present application is based on a Markov chain-like state transition method, and obtains a set representation of the state transition response based on the response form of the response state set relative to the control state set, and uses this to correct the value of the response feature vector to obtain a mapping representation of the response value in the state transition space, thereby exploring the changing relationship of the value under the chain time series expression, so as to further explore the deep transfer state representation between the values ​​in addition to the numerical information, and improve the accuracy of the logical regression.

[0092] Based on the above embodiments, Figure 2 As shown, the Markov chain-like state transfer method described in step S104 is used to correct the value of the response feature vector to obtain a regression feature vector, including:

[0093] Step S201 , converting the values ​​in the temperature input vector, the flow rate input vector and the heat gain input vector into switch state values ​​respectively, to obtain a first switch control vector, a second switch control vector and a third switch control vector.

[0094] Optionally, the temperature input vector, the flow rate input vector and the heat gain input vector are respectively input into a plurality of parallel switches based on a predetermined threshold value to convert the temperature input vector, the flow rate input vector and the heat gain input vector into the first switch control vector, the second switch control vector and the third switch control vector having a numerical distribution of (0, 1), respectively.

[0095] In one embodiment, each switch in the plurality of parallel switches has the same control threshold, thereby maintaining the consistency of the global state metric between the temperature values ​​at the plurality of time points, the consistency of the global state metric between the flow rate values ​​at the plurality of time points, and the consistency of the global state metric of the heat gain at the plurality of time points, respectively.

[0096] In another embodiment, each of the multiple parallel switches has a separate control threshold, so that the adaptability of the global state measurement of the temperature value (flow rate value or heat gain) at each time point can be maintained, that is, the control threshold is adaptively determined based on the temperature value (flow rate value or heat gain) at different time points.

[0097] In another embodiment, in order to improve the confidence of the state metric at each time point, the threshold of each switch is a separate control threshold multiplied by the same control threshold. In this way, not only can the consistency of the global state metric between the wind direction angle temperature values ​​(flow rate values ​​or heat added value) at multiple time points be effectively maintained, but also the adaptability of the global state metric of the temperature value (flow rate value or heat added value) at each time point can be taken into account.

[0098] Optionally, at the central processing unit end of the dedicated programmable controller, the temperature input vector, the flow rate input vector and the heat gain input vector are respectively converted into a first switch control vector, a second switch control vector and a third switch control vector whose characteristic values ​​are distributed in (0, 1). As an example, the temperature input vector, the flow rate input vector and the heat gain input vector are converted into a switch state value vector through a switch state control line. It should be understood that converting the temperature value, flow rate value and heat gain value at each predetermined time point into a logical value distributed in 0, 1 can reduce the error transmission probability at the original data end.

[0099] Step S202: The first switch control vector and the second switch control vector are passed through a matrix array of XEN_OR gates to obtain a same state control matrix.

[0100] At the central processing unit end of the dedicated programmable controller, the first switch control vector and the second switch control vector are passed through a matrix array of XNOR gates to obtain a same-state control matrix. Here, the same-state control matrix expresses an associated set of wind direction angles and rotation angles in the same state.

[0101] Step S203: Pass the first switch control vector and the third switch control vector through a matrix array of XNOR gates to obtain a first response control matrix.

[0102] Step S204: The second switch control vector and the third switch control vector are passed through a matrix array of XNOR gates to obtain a second response control matrix.

[0103] It can be understood that the first response control matrix and the second response control matrix are used to express the forward response set of the output power relative to the wind direction angle and the rotation angle respectively.

[0104] Step S205, calculating the set union of the first response control matrix and the second response control matrix, and calculating the set intersection of the set union and the same state control matrix to obtain a response state matrix.

[0105] Step S206: multiply the response state matrix by the response eigenvector to obtain a regression eigenvector.

[0106] At the central processing unit end of the dedicated programmable controller, the response state matrix is ​​multiplied by the response eigenvector to obtain a regression eigenvector.

[0107] In this embodiment, based on a Markov chain-like state transfer method, a set representation of the state transfer response is obtained based on the response form of the response state set relative to the control state set, and the value of the response feature vector is corrected to obtain a mapping representation of the response value in the state transfer space, thereby exploring the changing relationship of the value under the chain time series expression, and further exploring the deep transfer state representation between the values ​​in addition to the numerical information, thereby improving the accuracy of logistic regression.

[0108] Figure 3 Schematic diagram of an application scenario of a method for controlling heat dissipation of an offshore wind turbine generator set according to a specific embodiment of the present application. Figure 3As shown, in the application scenario of a dedicated programmable controller for heat dissipation control of an offshore wind turbine generator set, first, the temperature value of the wind wheel Wh at a plurality of predetermined time points including the current time point is collected from the temperature sensor Se1, and the flow rate value of the cooling water Wa of the water cooling system Sy at a plurality of predetermined time points including the current time point is collected from the flow meter Se2, the solar heat load, the hub H heat load, and the convection heat load at a plurality of predetermined time points including the current time point are collected from the heat load sensor Se3, and the thermal radiation at a plurality of predetermined time points including the current time point is collected from the thermal radiation sensor Se4. Furthermore, the temperature value, flow rate value, solar heat load, hub heat load, convective heat transfer heat load and thermal radiation of the wind wheel at multiple predetermined time points including the current time point are input into a dedicated programmable controller PLC for heat dissipation control of the offshore wind turbine generator set through the input interface In and the communication interface Co, wherein the dedicated programmable controller is capable of processing the temperature value, flow rate value, solar heat load, hub heat load, convective heat transfer heat load and thermal radiation of the wind wheel at multiple predetermined time points including the current time point to obtain a logical value indicating that the flow rate value of the cooling water at the current time point should be increased or decreased, and outputs a heat dissipation control instruction based on the logical value indicating that the flow rate value of the cooling water at the current time point should be increased or decreased, wherein the heat dissipation control instruction is output through the output interface Out.

[0109] Corresponding to the above method embodiment, Figure 4 is a block diagram of a heat dissipation control device for an offshore wind turbine generator set according to an exemplary embodiment. Figure 4 The heat dissipation control device of the offshore wind turbine generator set may include: a wind power data acquisition module 401, a temperature drop vector acquisition module 402, a heat increase vector acquisition module 403, a response characteristic acquisition module 404 and a flow rate value acquisition module 405.

[0110] Specifically, the wind power data acquisition module 401 is used to acquire the temperature value of the wind rotor at multiple predetermined time points including the current time point, the flow rate value of the cooling water of the water cooling system, and the heat input values ​​of multiple heat increase factors of the wind rotor;

[0111] A cooling vector acquisition module 402 is used to arrange the temperature values ​​of the wind wheel at a plurality of predetermined time points including the current time point and the flow rate values ​​of the cooling water of the water cooling system into a temperature input vector and a flow rate input vector, respectively, and calculate the position difference between the temperature input vector and the flow rate input vector to obtain a cooling input vector;

[0112] The heat increase vector acquisition module 403 is used to arrange the heat input values ​​of the multiple heat increase factors of the wind wheel at multiple predetermined time points including the current time point into heat increase input vectors, and calculate the position-weighted sum of the multiple heat increase input vectors to obtain the heat increase input vector;

[0113] The response feature acquisition module 404 is used to calculate the responsiveness estimation of the temperature reduction input vector relative to the heat increase input vector to obtain a response feature vector; and based on a Markov chain-like state transfer method, correct the value of the response feature vector to obtain a regression feature vector;

[0114] The flow rate value acquisition module 405 is used to perform a logistic regression on the regression feature vector to obtain a flow rate control value of the cooling water of the water cooling system for characterizing the current time point, so as to perform heat dissipation control according to the flow rate control value.

[0115] In some implementations, the response feature acquisition module 404 corrects the value of the response feature vector based on a Markov chain-like state transition to obtain a regression feature vector, specifically for:

[0116] Respectively converting the values ​​in the temperature input vector, the flow rate input vector and the heat gain input vector into switch state values ​​to obtain a first switch control vector, a second switch control vector and a third switch control vector;

[0117] Passing the first switch control vector and the second switch control vector through a matrix array of XNOR gates to obtain a same state control matrix;

[0118] Passing the first switch control vector and the third switch control vector through a matrix array of XNOR gates to obtain a first response control matrix;

[0119] Passing the second switch control vector and the third switch control vector through a matrix array of XNOR gates to obtain a second response control matrix;

[0120] Calculating a set union of the first response control matrix and the second response control matrix, and calculating a set intersection of the set union and the same state control matrix to obtain a response state matrix;

[0121] The response state matrix is ​​multiplied by the response eigenvector to obtain a regression eigenvector.

[0122] In some implementations, when the response characteristic acquisition module 404 converts the numerical values ​​in the temperature input vector, the flow rate input vector, and the heat gain input vector into switch state values ​​respectively to obtain the first switch control vector, the second switch control vector, and the third switch control vector, it is specifically used to:

[0123] The temperature input vector, the flow rate input vector and the heat gain input vector are respectively input into a plurality of parallel switches based on a predetermined threshold value, so as to convert the temperature input vector, the flow rate input vector and the heat gain input vector into the first switch control vector, the second switch control vector and the third switch control vector having values ​​of 0 and 1 respectively; wherein the plurality of parallel switches have the same predetermined threshold value, or the plurality of parallel switches each have an independent predetermined threshold value.

[0124] In some implementations, when the cooling vector acquisition module 402 calculates the position difference between the temperature input vector and the flow rate input vector to obtain the cooling input vector, it is specifically used to:

[0125] The temperature input vector and the flow rate input vector are input into a plurality of parallel subtractors to obtain the temperature reduction input vector.

[0126] In some implementations, when the heat increase vector acquisition module 403 calculates the position-weighted sum of the plurality of heat increase input vectors to obtain the heat increase input vector, it is specifically used to:

[0127] The heat increase input vectors are input into a plurality of parallel multipliers and a plurality of parallel adders connected in series with the plurality of parallel multipliers to obtain the heat increase input vectors.

[0128] In some implementations, when the response characteristic acquisition module 404 calculates the responsiveness estimate of the temperature reduction input vector relative to the heat increase input vector to obtain the response characteristic vector, it is specifically used to:

[0129] The temperature reduction input vector and the heat increase input vector are input into a plurality of parallel dividers for position division to obtain the response characteristic vector.

[0130] In some implementations, when the flow rate value acquisition module 405 performs a logistic regression on the regression feature vector to obtain a flow rate control value of cooling water of the water cooling system for characterizing the current time point, it is specifically used to:

[0131] Inputting the regression feature vector into a plurality of parallel multipliers and an adder connected in series with the plurality of parallel multipliers to obtain a regression value;

[0132] The regression value is input into a control switch based on a predetermined threshold to obtain a flow rate control value of cooling water in the water cooling system that is used to characterize the current time point; wherein the flow rate control value is a logical value indicating whether the flow rate value should be increased or decreased.

[0133] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0134] The heat dissipation control device of the offshore wind turbine generator set of the embodiment of the present application not only takes into account the real-time temperature of the heat dissipation wind wheel, but also takes into account the additional heat gain situation. The differential vector between the time series vector of the wind wheel temperature and the time series vector of the cooling water flow rate is used as the cooling input vector to represent the cooling capacity; the position-weighted sum between multiple heat gain input vectors is used as the heat gain input vector to represent the heat gain capacity. The interaction relationship between the cooling capacity and the heat gain is represented by estimating the responsiveness of the cooling input vector relative to the heat gain input vector, so as to improve the accuracy of the responsiveness control of the heat dissipation control. Further based on the Markov chain-like state transfer method, the set representation of the state transfer response is obtained based on the response form of the response state set relative to the control state set, and the numerical value of the response characteristic vector is corrected to obtain the mapping representation of the response numerical value in the state transfer space, so as to explore the change relationship of the numerical value under the chain time series expression, so as to further explore the deep transfer state representation between the numerical values ​​in addition to the numerical information, and improve the accuracy of the logistic regression.

[0135] According to an embodiment of the present application, the present application also provides an electronic device and a readable storage medium.

[0136] like Figure 5 , is a block diagram of an electronic device for implementing a method for heat dissipation control of an offshore wind turbine generator set according to an embodiment of the present application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0137] like Figure 5As shown, the electronic device includes: one or more processors 501, a memory 502, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are interconnected using different buses and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the electronic device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In other embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 5 A processor 501 is taken as an example.

[0138] The memory 502 is a non-transitory computer-readable storage medium provided in the present application. The memory stores instructions executable by at least one processor to enable the at least one processor to perform the method for heat dissipation control of an offshore wind turbine generator set provided in the present application. The non-transitory computer-readable storage medium of the present application stores computer instructions, which are used to enable a computer to perform the method for heat dissipation control of an offshore wind turbine generator set provided in the present application.

[0139] The memory 502 is a non-transient computer-readable storage medium that can be used to store non-transient software programs, non-transient computer executable programs and modules, such as the program instructions / modules corresponding to the method for heat dissipation control of an offshore wind turbine generator set in the embodiment of the present application (for example, the attached Figure 4 The processor 501 executes various functional applications and data processing of the server by running the non-transient software programs, instructions and modules stored in the memory 502, that is, the method for heat dissipation control of the offshore wind turbine generator set in the above method embodiment.

[0140] The memory 502 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created according to the use of electronic devices for heat dissipation control of offshore wind turbines, etc. In addition, the memory 502 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage devices. In some embodiments, the memory 502 may optionally include a memory remotely arranged relative to the processor 501, and these remote memories may be connected to the electronic devices for heat dissipation control of offshore wind turbines via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0141] The electronic device of the method for controlling the heat dissipation of an offshore wind turbine generator set may further include: an input device 503 and an output device 504. The processor 501, the memory 502, the input device 503 and the output device 504 may be connected via a bus or other means. Figure 5 The example of connecting through bus is taken in the following.

[0142] The input device 503 can receive input digital or character information, and generate key signal input related to user settings and function control of electronic equipment for heat dissipation control of offshore wind turbines, such as input devices such as touch screen, keypad, mouse, track pad, touch pad, indicator bar, one or more mouse buttons, trackball, joystick, etc. The output device 504 may include a display device, an auxiliary lighting device (e.g., LED) and a tactile feedback device (e.g., a vibration motor), etc. The display device may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display, and a plasma display. In some embodiments, the display device may be a touch screen.

[0143] Various implementations of the systems and techniques described herein can be realized in digital electronic circuit systems, integrated circuit systems, dedicated ASICs (application specific integrated circuits), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0144] These computer programs (also referred to as programs, software, software applications, or code) include machine instructions for programmable processors and can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, device, and / or means (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0145] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0146] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0147] A computer system may include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship to each other.

[0148] In an exemplary embodiment, a computer program product is also provided. When instructions in the computer program product are executed by a processor of an electronic device, the electronic device is enabled to perform the above method.

[0149] It should also be noted that the exemplary embodiments mentioned in the present invention describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiments, or in a different order from the embodiments, or several steps can be performed simultaneously.

[0150] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only.

[0151] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A heat dissipation control method for an offshore wind turbine generator set, characterized in that: include: Obtaining temperature values ​​of the wind wheel at multiple predetermined time points including the current time point, flow rate values ​​of cooling water of the water cooling system, and heat input values ​​of multiple heat increase factors of the wind wheel; Arranging the temperature values ​​of the wind wheel at the plurality of predetermined time points including the current time point and the flow rate values ​​of the cooling water of the water cooling system into a temperature input vector and a flow rate input vector respectively, and calculating the position difference between the temperature input vector and the flow rate input vector to obtain a cooling input vector; Arranging heat input values ​​of a plurality of heat increase factors of the wind wheel at a plurality of predetermined time points including the current time point into heat increase input vectors respectively, and calculating a position-weighted sum of the plurality of heat increase input vectors to obtain a heat increase input vector; Calculating a responsiveness estimate of the temperature reduction input vector relative to the heat increase input vector to obtain a response characteristic vector; Based on a Markov chain-like state transfer method, the value of the response feature vector is corrected to obtain a regression feature vector; The regression feature vector is subjected to a logistic regression to obtain a flow rate control value of cooling water of the water cooling system used to characterize the current time point, so as to perform heat dissipation control according to the flow rate control value.

2. The method according to claim 1, characterized in that The method based on the Markov chain-like state transfer is used to correct the value of the response feature vector to obtain the regression feature vector, including: Respectively converting the numerical values ​​in the temperature input vector, the flow rate input vector and the heat gain input vector into switch state values ​​to obtain a first switch control vector, a second switch control vector and a third switch control vector; Passing the first switch control vector and the second switch control vector through a matrix array of XNOR gates to obtain a same state control matrix; Passing the first switch control vector and the third switch control vector through a matrix array of XNOR gates to obtain a first response control matrix; Passing the second switch control vector and the third switch control vector through a matrix array of XNOR gates to obtain a second response control matrix; Calculating a set union of the first response control matrix and the second response control matrix, and calculating a set intersection of the set union and the same state control matrix to obtain a response state matrix; The response state matrix is ​​multiplied by the response eigenvector to obtain a regression eigenvector.

3. The method according to claim 2, characterized in that The converting the values ​​in the temperature input vector, the flow rate input vector and the heat gain input vector into switch state values ​​respectively to obtain a first switch control vector, a second switch control vector and a third switch control vector comprises: The temperature input vector, the flow rate input vector and the heat gain input vector are respectively input into a plurality of parallel switches based on a predetermined threshold value, so as to convert the temperature input vector, the flow rate input vector and the heat gain input vector into the first switch control vector, the second switch control vector and the third switch control vector having values ​​of 0 and 1 respectively; wherein the plurality of parallel switches have the same predetermined threshold value, or the plurality of parallel switches each have an independent predetermined threshold value.

4. The method according to claim 1, characterized in that The calculating the position difference between the temperature input vector and the flow rate input vector to obtain the temperature reduction input vector comprises: The temperature input vector and the flow rate input vector are input into a plurality of parallel subtractors to obtain the temperature reduction input vector.

5. The method according to claim 1, characterized in that The calculating the position-weighted sum of the plurality of heat increase input vectors to obtain the heat increase input vector comprises: The heat increase input vectors are input into a plurality of parallel multipliers and a plurality of parallel adders connected in series with the plurality of parallel multipliers to obtain the heat increase input vectors.

6. The method according to claim 1, characterized in that The calculating the responsiveness estimate of the temperature reduction input vector relative to the heat increase input vector to obtain a response characteristic vector includes: The temperature reduction input vector and the heat increase input vector are input into a plurality of parallel dividers for position division to obtain the response characteristic vector.

7. The method according to claim 1, characterized in that The step of performing a logistic regression on the regression feature vector to obtain a flow rate control value of cooling water of the water cooling system for characterizing the current time point includes: Inputting the regression feature vector into a plurality of parallel multipliers and an adder connected in series with the plurality of parallel multipliers to obtain a regression value; The regression value is input into a control switch based on a predetermined threshold to obtain a flow rate control value of cooling water in the water cooling system that is used to characterize the current time point; wherein the flow rate control value is a logical value indicating whether the flow rate value should be increased or decreased.

8. A heat dissipation control device for an offshore wind turbine generator set, characterized in that: include: A wind power data acquisition module, used to acquire the temperature value of the wind wheel at multiple predetermined time points including the current time point, the flow rate value of the cooling water of the water cooling system, and the heat input value of multiple heat increase factors of the wind wheel; a cooling vector acquisition module, used to arrange the temperature values ​​of the wind wheel at a plurality of predetermined time points including the current time point and the flow rate values ​​of the cooling water of the water cooling system as a temperature input vector and a flow rate input vector, respectively, and calculate the position difference between the temperature input vector and the flow rate input vector to obtain a cooling input vector; a heat increase vector acquisition module, used to arrange the heat input values ​​of the multiple heat increase factors of the wind wheel at multiple predetermined time points including the current time point into heat increase input vectors, and calculate the position-weighted sum of the multiple heat increase input vectors to obtain the heat increase input vector; a response feature acquisition module, used to calculate the responsiveness estimate of the temperature reduction input vector relative to the heat increase input vector to obtain a response feature vector; and based on a Markov chain-like state transfer method, to correct the value of the response feature vector to obtain a regression feature vector; The flow rate value acquisition module is used to perform logistic regression on the regression feature vector to obtain a flow rate control value of cooling water of the water cooling system used to characterize the current time point, so as to perform heat dissipation control according to the flow rate control value.

9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the heat dissipation control method for an offshore wind turbine generator set according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to enable the computer to execute the heat dissipation control method for an offshore wind turbine generator set according to any one of claims 1 to 7.

Images