Method and device for predicting icing risk of fan and storage medium

Abstract

The invention discloses a method and device for predicting the icing risk of a fan and a storage medium, and belongs to the technical field of power grid disaster prediction. The method comprises the steps that the liquid water content, the water-ice ratio and the temperature gradient corresponding to a plurality of regional grid units and real-time operation parameters corresponding to a draught fan are obtained, and the regional grid units are obtained after a wind power plant region is divided; determining a comprehensive phase index corresponding to each regional grid unit according to the liquid water content, the water-ice ratio and the temperature gradient corresponding to each regional grid unit; according to the comprehensive phase state index and the real-time operation parameter of each regional grid unit, determining a unit icing risk index corresponding to each regional grid unit; and predicting the icing risk of the fan according to the plurality of unit icing risk indexes. According to the method and the device, the problem of low prediction accuracy of the icing risk of the fan in the prior art can be solved.

Description

Technical Field

[0001] This application relates to the field of power grid disaster prediction technology, specifically to a method, apparatus, and storage medium for predicting the icing risk of wind turbines. Background Technology

[0002] In recent years, under the broader energy context, there has been a strong emphasis on supporting the development of renewable energy industries (such as wind power) to achieve sustainable energy development. For the wind power industry, the normal operation of wind turbines is crucial. However, in high-altitude or low-temperature, high-humidity environments, the low temperatures and high humidity can cause icing on the turbine blades, thus affecting the safe operation of the wind turbines.

[0003] Existing technologies typically rely on temperature and humidity observations from ground-based weather stations to obtain two-dimensional planar data. This data is then used to determine the phase transition probability of ice and water, thus predicting icing risk. However, for more complex icing scenarios, accurate prediction of wind turbine icing risk based solely on two-dimensional planar data is difficult. Therefore, existing technologies suffer from low accuracy in predicting wind turbine icing risk. Summary of the Invention

[0004] The purpose of this application is to provide a method, apparatus, and storage medium for predicting the icing risk of wind turbines, so as to solve the problem of low accuracy in predicting the icing risk of wind turbines in the prior art.

[0005] To achieve the above objectives, the first aspect of this application provides a method for predicting the icing risk of wind turbines located in a wind farm area, the method comprising: The liquid water content, water-to-ice ratio, temperature gradient, and real-time operating parameters of the wind turbines corresponding to multiple regional grid cells are obtained. The multiple regional grid cells are obtained after dividing the wind farm area. The comprehensive phase index of each grid cell is determined based on the liquid water content, water-ice ratio, and temperature gradient of each grid cell. Based on the comprehensive phase state index and real-time operating parameters of each regional grid unit, the unit icing risk index corresponding to each regional grid unit is determined; The icing risk of wind turbines is predicted based on multiple unit icing risk indices.

[0006] In this embodiment of the application, obtaining the water-ice ratio includes: obtaining the differential propagation phase shift rate and differential reflectivity corresponding to each region grid cell collected by dual polarization radar; and determining the water-ice ratio corresponding to each region grid cell based on the differential propagation phase shift rate and differential reflectivity.

[0007] In this embodiment of the application, the water-ice ratio corresponding to each region grid cell is determined based on the differential propagation phase shift rate and differential reflectivity, including: determining the water-ice ratio corresponding to each region grid cell using the following formula:

[0008] in, For the water-to-ice ratio, The phase shift rate of differential propagation, Differential reflectivity, To preset the differential propagation phase shift rate reference value, To preset the differential reflectivity reference value, For preset coefficients, This is the preset index.

[0009] In this embodiment, the comprehensive phase index corresponding to each grid cell is determined based on the liquid water content, water-to-ice ratio, and temperature gradient of each grid cell. This includes: determining the ratios of the liquid water content to the corresponding preset liquid water content benchmark, the water-to-ice ratio to the corresponding preset water-to-ice ratio benchmark, and the temperature gradient to the corresponding preset temperature gradient benchmark for each grid cell, to obtain the liquid water content ratio, water-to-ice ratio, and temperature gradient ratio for each grid cell; determining the product of the liquid water content ratio, water-to-ice ratio, and temperature gradient ratio for each grid cell with the corresponding preset weighting coefficient, to obtain the liquid water content parameter, water-to-ice ratio parameter, and temperature gradient parameter for each grid cell; and determining the sum of the liquid water content parameter, water-to-ice ratio parameter, and temperature gradient parameter for each grid cell, to obtain the comprehensive phase index for each grid cell.

[0010] In this embodiment, the real-time operating parameters include the real-time output power of the wind turbine and the real-time vibration amplitude of the blades. Based on the comprehensive phase state index of each grid cell and the real-time operating parameters, the unit icing risk index corresponding to each grid cell is determined, including: determining a power feedback term based on the comprehensive phase state index and the real-time output power of the wind turbine, wherein the power feedback term is directly proportional to the comprehensive phase state index and inversely proportional to the real-time output power of the wind turbine; determining a vibration feedback term based on the real-time vibration amplitude of the blades and a preset vibration weight coefficient, wherein the vibration feedback term is directly proportional to the real-time vibration amplitude of the blades and the preset vibration weight coefficient; and determining the sum of the power feedback term and the vibration feedback term to obtain the unit icing risk index corresponding to each grid cell.

[0011] In this embodiment of the application, the power feedback term is determined based on the comprehensive phase state index and the real-time output power of the wind turbine, including: determining the ratio of the real-time output power of the wind turbine to the rated output power of the wind turbine to obtain the energy conversion efficiency of the wind turbine; determining the energy conversion loss rate based on the energy conversion efficiency, wherein the sum of the energy conversion efficiency and the energy conversion loss rate is 1; and determining the product of the energy conversion loss rate and the comprehensive phase state index to obtain the power feedback term.

[0012] In this embodiment of the application, the vibration feedback item is determined based on the real-time vibration amplitude of the blade and the preset vibration weight coefficient, including: determining the ratio of the real-time vibration amplitude of the blade to the preset blade vibration amplitude threshold to obtain the blade vibration amplitude balance value; and determining the product of the blade vibration amplitude balance value and the preset vibration weight coefficient to obtain the vibration feedback item.

[0013] In this embodiment of the application, predicting the icing risk of a wind turbine based on multiple unit icing risk indices includes: determining the largest among the multiple unit icing risk indices to obtain the target unit icing risk index; and predicting the icing risk of the wind turbine based on the target unit icing risk index and a preset icing risk index threshold.

[0014] A second aspect of this application provides an apparatus for predicting the icing risk of a wind turbine, comprising: a memory configured to store instructions; and a processor configured to retrieve instructions from the memory and, when executing the instructions, to implement the method for predicting the icing risk of a wind turbine as described above.

[0015] A third aspect of this application provides a machine-readable storage medium storing instructions for causing a machine to perform the method described above for predicting the icing risk of a wind turbine.

[0016] The above technical solution acquires the liquid water content, water-to-ice ratio, and temperature gradient of multiple regional grid units, as well as the real-time operating parameters of the wind turbine. These multiple regional grid units are obtained by dividing the wind farm area. Based on the liquid water content, water-to-ice ratio, and temperature gradient of each regional grid unit, a comprehensive phase index is determined. Then, based on the comprehensive phase index and real-time operating parameters of each regional grid unit, a unit icing risk index is determined. The icing risk of the wind turbine is predicted based on these multiple unit icing risk indices. Compared to existing technologies, this application is not limited to two-dimensional planar data; it uses the liquid water content, water-to-ice ratio, and temperature gradient of multiple regional grid units to acquire the vertical distribution characteristics of atmospheric phases, thereby improving the accuracy of predicting wind turbine icing risk.

[0017] Other features and advantages of the embodiments of this application will be described in detail in the following detailed description section. Attached Figure Description

[0018] The accompanying drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the following detailed description to explain the embodiments of this application, but do not constitute a limitation on the embodiments of this application. In the drawings: Figure 1 The illustration shows a flowchart of a method for predicting the icing risk of a wind turbine according to an embodiment of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for illustration and explanation of the embodiments of this application and are not intended to limit the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0020] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application all comply with relevant laws and regulations. In the embodiments of this application, certain existing industry solutions such as software, components, and models may be mentioned. These should be considered exemplary, intended only to illustrate the feasibility of implementing the technical solution of this application, and do not imply that the applicant has already used or necessarily used such solutions.

[0021] It should be noted that if the embodiments of this application involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.

[0022] Furthermore, if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0023] Figure 1The illustration schematically shows a flowchart of a method for predicting the icing risk of a wind turbine according to an embodiment of this application. Figure 1 As shown in the illustration, this application provides a method for predicting the icing risk of wind turbines located in a wind farm area. Taking the application of this method to a processor as an example, the method may include the following steps: Step S101: Obtain the liquid water content, water-to-ice ratio, temperature gradient, and real-time operating parameters of the wind turbine corresponding to multiple regional grid cells. The multiple regional grid cells are obtained after dividing the wind farm area.

[0024] Step S102: Determine the comprehensive phase index corresponding to each grid cell based on the liquid water content, water-ice ratio, and temperature gradient of each grid cell.

[0025] Step S103: Determine the cell icing risk index corresponding to each regional grid cell based on the comprehensive phase state index and real-time operating parameters of each regional grid cell.

[0026] Step S104: Predict the icing risk of the wind turbine based on multiple unit icing risk indices.

[0027] As we understand it, a wind turbine is a device used to convert wind energy into electrical energy. A wind farm area is a specific geographical area used for large-scale development of wind energy and its conversion into electricity. Wind turbines are located within wind farm areas and are crucial devices within those areas. Icing risk refers to the potential for supercooled water droplets to freeze into ice on the surface of wind turbine blades. A regional grid cell is a grid cell obtained by dividing the wind farm area into regions. Liquid water content is the total mass of liquid water droplets in a unit volume of air or cloud above a regional grid cell. The water-to-ice ratio is the ratio of liquid water droplets to solid ice crystals. The temperature gradient is the rate of change of temperature above a regional grid cell. The comprehensive phase index is a comprehensive indicator used to quantify the phase distribution and phase transition conditions of substances (such as water vapor, ice, and liquid water in the atmosphere). The cell icing risk index is an indicator used to quantify the icing risk at a regional grid cell.

[0028] Specifically, since the icing risk of wind turbines is closely related to three-dimensional phase state, temperature, and the turbine's operating parameters, the processor can acquire these parameters to accurately predict the icing risk. The processor can obtain the liquid water content, water-to-ice ratio, and temperature gradient corresponding to multiple regional grid cells using meteorological data acquisition devices (such as dual-polarization radar and microwave radiometers). By combining the multi-parameter detection advantages of dual-polarization radar with the high-precision temperature inversion capability of microwave radiometers, the identification accuracy of the vertical atmospheric phase structure corresponding to each regional grid cell can be improved. Furthermore, by fusing multi-dimensional parameters (liquid water content, water-to-ice ratio, and temperature gradient), a solid data foundation is laid for predicting the icing risk of wind turbines. The processor can also acquire real-time operating parameters of the wind turbines through sensors or other operational data acquisition devices. The processor can pre-divide the wind farm area into multiple regional grid cells according to a preset area size. The processor can determine the comprehensive phase state index of each grid cell based on its liquid water content, water-to-ice ratio, and temperature gradient. Then, based on the comprehensive phase state index and real-time operating parameters, the processor can determine the cell icing risk index for each grid cell, thereby predicting the icing risk of each grid cell. Furthermore, the processor can predict the icing risk of wind turbines based on multiple cell icing risk indices, thus achieving accurate prediction of the icing risk of wind turbines in a wind farm area.

[0029] The above technical solution acquires the liquid water content, water-to-ice ratio, and temperature gradient of multiple regional grid units, as well as the real-time operating parameters of the wind turbine. These multiple regional grid units are obtained by dividing the wind farm area. Based on the liquid water content, water-to-ice ratio, and temperature gradient of each regional grid unit, a comprehensive phase index is determined. Then, based on the comprehensive phase index and real-time operating parameters of each regional grid unit, a unit icing risk index is determined. The icing risk of the wind turbine is predicted based on these multiple unit icing risk indices. Compared to existing technologies, this application is not limited to two-dimensional planar data; it uses the liquid water content, water-to-ice ratio, and temperature gradient of multiple regional grid units to acquire the vertical distribution characteristics of atmospheric phases, thereby improving the accuracy of predicting wind turbine icing risk.

[0030] In this embodiment of the application, the differential propagation phase shift rate and differential reflectivity of each region grid cell are obtained by dual polarization radar; based on the differential propagation phase shift rate and differential reflectivity, the water-ice ratio of each region grid cell is determined.

[0031] Dual-polarization radar is a meteorological data acquisition device that alternately transmits horizontally and vertically polarized electromagnetic waves and receives signals in the polarization direction. It can be used to obtain differential propagation phase shift rate and differential reflectivity. Differential propagation phase shift rate (KDP) is a physical quantity characterizing the rate of change of the phase difference between the horizontal and vertical polarization directions per unit distance, used to reflect the liquid water content and particle shape. Differential reflectivity (ZDR) is a physical quantity characterizing the difference in reflectivity of radar echo signals in the horizontal (H) and vertical (V) polarization directions, used to distinguish between the liquid and ice phases of water. The water-to-ice ratio (IWR) refers to the mass or volume ratio of liquid water to solid ice.

[0032] Specifically, the processor can acquire the differential propagation phase shift rate and differential reflectivity corresponding to each regional grid cell collected by dual-polarization radar. By analyzing the differential propagation phase shift rate and differential reflectivity corresponding to each regional grid cell, the processor can obtain the water-ice ratio corresponding to each regional grid cell. The higher the water-ice ratio, the higher the liquid water content and the larger the raindrop size in the atmospheric environment corresponding to each regional grid cell, the higher the humidity, and the greater the risk of icing of the wind turbine.

[0033] By acquiring the differential propagation phase shift rate and differential reflectivity, the processor can further determine the water-ice ratio, enabling a refined diagnosis of the water-ice mixture in the atmosphere.

[0034] In this embodiment of the application, the water-ice ratio corresponding to each region grid cell is determined based on the differential propagation phase shift rate and differential reflectivity, including: determining the water-ice ratio corresponding to each region grid cell using the following formula:

[0035] in, For the water-to-ice ratio, The phase shift rate of differential propagation, Differential reflectivity, To preset the differential propagation phase shift rate reference value, To preset the differential reflectivity reference value, For preset coefficients, This is the preset index.

[0036] It can be understood that the preset differential propagation phase shift rate reference value is a pre-set reference value for the differential propagation phase shift rate, for example... =1° / km. The preset differential reflectance reference value is a pre-set reference value for differential reflectance, for example... =1dB. The preset coefficient is a pre-set coefficient, for example... =0.6. The preset index is a pre-set index, for example, =0.8.

[0037] Specifically, the processor can determine the water-ice ratio corresponding to each grid cell using the following formula:

[0038] in, For the water-to-ice ratio, The phase shift rate of differential propagation, Differential reflectivity, To preset the differential propagation phase shift rate reference value, To preset the differential reflectivity reference value, For preset coefficients, This is the preset index.

[0039] In addition, the processor can also determine the water-ice ratio corresponding to each grid cell based on other water-ice ratios, such as remote sensing data inversion, which is not limited here.

[0040] Based on the above formula, the processor can further determine the water-ice ratio by obtaining the differential propagation phase shift rate and differential reflectivity, thereby achieving a refined diagnosis of the ice-water mixed phase in the atmosphere and improving the accuracy of predicting the icing risk of wind turbines.

[0041] In this embodiment, the comprehensive phase index corresponding to each grid cell is determined based on the liquid water content, water-to-ice ratio, and temperature gradient of each grid cell. This includes: determining the ratios of the liquid water content to the corresponding preset liquid water content benchmark, the water-to-ice ratio to the corresponding preset water-to-ice ratio benchmark, and the temperature gradient to the corresponding preset temperature gradient benchmark for each grid cell, to obtain the liquid water content ratio, water-to-ice ratio, and temperature gradient ratio for each grid cell; determining the product of the liquid water content ratio, water-to-ice ratio, and temperature gradient ratio for each grid cell with the corresponding preset weighting coefficient, to obtain the liquid water content parameter, water-to-ice ratio parameter, and temperature gradient parameter for each grid cell; and determining the sum of the liquid water content parameter, water-to-ice ratio parameter, and temperature gradient parameter for each grid cell, to obtain the comprehensive phase index for each grid cell.

[0042] It can be understood that the preset liquid water content benchmark value is a pre-set benchmark value for liquid water content, for example, 1 g / m³. The preset water-to-ice ratio benchmark value is a pre-set benchmark value for the water-to-ice ratio, for example, 1. The preset temperature gradient benchmark value is a pre-set benchmark value for the temperature gradient, for example, 1°C / km. The preset liquid water content benchmark value, preset water-to-ice ratio benchmark value, and preset temperature gradient benchmark value are all used to eliminate dimensions. The liquid water content ratio is the ratio of liquid water content to the preset liquid water content benchmark value. The water-to-ice ratio is the ratio of the water-to-ice ratio to the preset water-to-ice ratio benchmark value. The temperature gradient ratio is the ratio of the temperature gradient to the corresponding preset temperature gradient benchmark value. The preset weighting coefficient is a pre-set weighting coefficient; each of the liquid water content ratio, water-to-ice ratio, and temperature gradient ratio has a corresponding preset weighting coefficient. The liquid water content parameter is a parameter related to the liquid water content. The water-to-ice ratio parameter is a parameter related to the water-to-ice ratio. The temperature gradient parameter is a parameter related to the temperature gradient.

[0043] Specifically, the processor can acquire preset reference values ​​for liquid water content, water-to-ice ratio, and temperature gradient, thereby determining the ratios of liquid water content to the corresponding preset reference values, water-to-ice ratio to the corresponding preset reference values, and temperature gradient to the corresponding preset reference values ​​for each grid cell in the region. This yields the liquid water content ratio, water-to-ice ratio, and temperature gradient ratio for each grid cell in the region. The processor can also acquire preset weighting coefficients corresponding to these ratios, thereby determining the products of these ratios with their respective preset weighting coefficients. This yields the liquid water content parameter, water-to-ice ratio parameter, and temperature gradient parameter for each grid cell in the region. Finally, the processor determines the sum of these parameters, resulting in the comprehensive phase index for each grid cell in the region. The above technical solution comprehensively considers the liquid water content, water-ice ratio and temperature gradient of each grid cell to determine the comprehensive phase index of each grid cell. The processor can use the comprehensive phase index to assess the impact of the atmospheric environment on the wind turbine's icing risk.

[0044] In this embodiment, the real-time operating parameters include the real-time output power of the wind turbine and the real-time vibration amplitude of the blades. Based on the comprehensive phase state index of each grid cell and the real-time operating parameters, the unit icing risk index corresponding to each grid cell is determined, including: determining a power feedback term based on the comprehensive phase state index and the real-time output power of the wind turbine, wherein the power feedback term is directly proportional to the comprehensive phase state index and inversely proportional to the real-time output power of the wind turbine; determining a vibration feedback term based on the real-time vibration amplitude of the blades and a preset vibration weight coefficient, wherein the vibration feedback term is directly proportional to the real-time vibration amplitude of the blades and the preset vibration weight coefficient; and determining the sum of the power feedback term and the vibration feedback term to obtain the unit icing risk index corresponding to each grid cell.

[0045] It is understood that real-time operating parameters may include, but are not limited to, the real-time output power of the wind turbine and the real-time vibration amplitude of the blades. The real-time output power of the wind turbine is the actual output power of the wind turbine. The real-time vibration amplitude of the blades is the real-time vibration frequency of the wind turbine blades. The unit icing risk index is the icing risk corresponding to each grid unit in each region. The power feedback item is a feedback item related to the real-time output power of the wind turbine; the power feedback item is directly proportional to the comprehensive phase state index and inversely proportional to the real-time output power of the wind turbine. The vibration feedback item is a feedback item related to the real-time vibration amplitude of the blades; the vibration feedback item is directly proportional to the real-time vibration amplitude of the blades and the preset vibration weight coefficient, which is a pre-set vibration weight coefficient.

[0046] Specifically, the processor can process the comprehensive phase state index and the real-time output power of the wind turbine, and determine the power feedback term based on the comprehensive phase state index and the real-time output power of the wind turbine. In addition, the processor can obtain a preset vibration weighting coefficient and determine a vibration feedback term based on the real-time vibration amplitude of the blades and the preset vibration weighting coefficient. Furthermore, the processor can determine the sum of the power feedback term and the vibration feedback term, thereby obtaining the unit icing risk index corresponding to each grid cell. This technical solution, by comprehensively considering the comprehensive phase state index, the real-time output power of the wind turbine in the real-time operating parameters, and the real-time vibration amplitude of the blades, constructs the correlation between the comprehensive phase state index, the real-time output power of the wind turbine in the real-time operating parameters, and the real-time vibration amplitude of the blades, thereby determining the unit icing risk index corresponding to each grid cell, realizing the quantitative processing of the wind turbine icing risk, and improving the prediction accuracy of the wind turbine icing risk.

[0047] In this embodiment of the application, the power feedback term is determined based on the comprehensive phase state index and the real-time output power of the wind turbine, including: determining the ratio of the real-time output power of the wind turbine to the rated output power of the wind turbine to obtain the energy conversion efficiency of the wind turbine; determining the energy conversion loss rate based on the energy conversion efficiency, wherein the sum of the energy conversion efficiency and the energy conversion loss rate is 1; and determining the product of the energy conversion loss rate and the comprehensive phase state index to obtain the power feedback term.

[0048] It can be understood that the rated output power of a wind turbine is the mechanical power that the turbine can continuously and stably output. Energy conversion efficiency is the efficiency with which the turbine converts energy. Energy conversion loss rate is the efficiency lost by the turbine during energy conversion. The sum of energy conversion efficiency and energy conversion loss rate is 1.

[0049] Specifically, the processor can pre-obtain the rated output power of the wind turbine, thereby determining the ratio of the wind turbine's real-time output power to its rated output power, thus obtaining the wind turbine's energy conversion efficiency. Furthermore, based on the energy conversion efficiency, the energy conversion loss rate can be determined, and then the product of the energy conversion loss rate and the comprehensive phase state index can be calculated to obtain the power feedback term. This technical solution, through a comprehensive evaluation of the wind turbine's real-time output power and comprehensive phase state index—its real-time operating parameters—achieves accurate prediction of the wind turbine's icing risk.

[0050] In this embodiment of the application, the vibration feedback item is determined based on the real-time vibration amplitude of the blade and the preset vibration weight coefficient, including: determining the ratio of the real-time vibration amplitude of the blade to the preset blade vibration amplitude threshold to obtain the blade vibration amplitude balance value; and determining the product of the blade vibration amplitude balance value and the preset vibration weight coefficient to obtain the vibration feedback item.

[0051] It can be understood that the preset blade vibration amplitude threshold is a pre-set threshold for blade vibration amplitude. The blade vibration amplitude balance value is used to characterize the degree of balance of blade vibration.

[0052] Specifically, the processor can obtain a preset blade vibration amplitude threshold, thereby determining the ratio of the real-time blade vibration amplitude to the preset blade vibration amplitude threshold, thus obtaining the blade vibration amplitude balance value. Furthermore, the processor can also determine the product of the blade vibration amplitude balance value and a preset vibration weighting coefficient, thereby obtaining the vibration feedback term. In this way, by analyzing and processing the real-time blade vibration amplitude in the real-time operating parameters of the wind turbine, accurate prediction of the wind turbine's icing risk based on the real-time blade vibration amplitude is achieved.

[0053] In this embodiment of the application, predicting the icing risk of a wind turbine based on multiple unit icing risk indices includes: determining the largest among the multiple unit icing risk indices to obtain the target unit icing risk index; and predicting the icing risk of the wind turbine based on the target unit icing risk index and a preset icing risk index threshold.

[0054] It is understood that the target unit icing risk index is obtained by processing the icing risk indices of multiple units. The preset icing risk index threshold is a pre-set threshold for icing risk, and there can be one or more preset icing risk index thresholds.

[0055] Specifically, the processor can determine the largest among multiple unit icing risk indices and use it as the target unit's icing risk index. If there is only one preset icing risk index threshold, the processor can compare the target unit's icing risk index with the preset threshold. If the target unit's icing risk index is greater than or equal to the preset threshold, the processor predicts that the wind turbine has a certain icing risk; if the target unit's icing risk index is less than the preset threshold, the processor predicts that the wind turbine has no icing risk. If there are multiple preset icing risk index thresholds, the processor determines the threshold range to which the target unit's icing risk index belongs, thereby predicting the degree of icing risk for the wind turbine.

[0056] In one specific embodiment, the processor can pre-divide the wind farm area into multiple regional grid cells. The processor can obtain the liquid water content, water-to-ice ratio, and temperature gradient corresponding to each regional grid cell. Specifically, the liquid water content acquisition process is as follows: the reflectivity factor and inversion temperature corresponding to each of the multiple regional grid cells are obtained through dual-polarization radar or other meteorological data acquisition devices. After correcting the inversion temperature, the corrected inversion temperature can be obtained based on a temperature adjustment function. Thus, the liquid water content corresponding to each of the multiple regional grid cells is determined based on the adjusted inversion temperature and reflectivity factor.

[0057] The processor can also determine the liquid water content using the following formula:

[0058] in, Liquid water content, Here, b is the preset liquid water content coefficient, and b is the preset liquid water content index. Reflectance factor (unit: mm) 6 / m 3 ), This is a temperature adjustment function. This is the inversion temperature.

[0059] The temperature adjustment function can be determined using the following formula:

[0060] in, This is a temperature adjustment function. This is the inversion temperature.

[0061] The process of obtaining the temperature gradient involves acquiring the temperature difference between adjacent height layers corresponding to multiple regional grid cells using a microwave radiometer or other temperature acquisition device, determining the ratio of this temperature difference to the height difference corresponding to the adjacent height layers, and thus obtaining the temperature gradient corresponding to each of the multiple regional grid cells.

[0062] The processor can also determine the temperature gradient using the following formula:

[0063] in, For temperature gradient, This represents the inversion temperature of the upper levels in adjacent height layers. The inversion temperature is the lower layer in the adjacent height layer. This represents the vertical height difference between adjacent height levels.

[0064] exist A positive value indicates the presence of an inversion layer in the atmosphere, which is conducive to the formation of supercooled water, prolongs the icing time, and increases the risk of icing for the wind turbine.

[0065] And in A negative value indicates that there is no temperature inversion layer in the atmosphere or the temperature inversion layer is thin, which is not conducive to the formation of supercooled water and reduces the risk of icing of the wind turbine.

[0066] The process of obtaining the water-ice ratio involves acquiring the differential reflectivity and differential propagation phase shift rate corresponding to multiple regional grid cells using dual-polarization radar or other data acquisition devices. Based on these differential reflectivity and phase shift rate, the water-ice ratio corresponding to each of the multiple regional grid cells is determined. Specifically, the water-ice ratio can be determined using the following formula:

[0067] in, For the water-to-ice ratio, The phase shift rate of differential propagation, Differential reflectivity, To preset the differential propagation phase shift rate reference value, To preset the differential reflectivity reference value, For preset coefficients, This is the preset index.

[0068] At the same time, the processor can also obtain the real-time operating parameters of the wind turbine, which may include, but are not limited to, the real-time output power of the wind turbine and the real-time vibration amplitude of the blades, thus forming a data basis for predicting the icing risk of the wind turbine.

[0069] Based on this, the processor can determine the comprehensive phase state index corresponding to each grid cell based on the liquid water content, water-ice ratio, and temperature gradient of each grid cell. The processor obtains the liquid water content ratio, water-ice ratio ratio, and temperature gradient ratio of each grid cell by determining the ratios of the liquid water content to the corresponding preset liquid water content benchmark, the water-ice ratio to the corresponding preset water-ice ratio benchmark, and the temperature gradient to the corresponding preset temperature gradient benchmark. It then determines the products of these ratios with their corresponding preset weighting coefficients to obtain the liquid water content parameter, water-ice ratio parameter, and temperature gradient parameter for each grid cell. Finally, it determines the sum of these parameters to obtain the comprehensive phase state index for each grid cell. Furthermore, the processor can specifically determine the comprehensive phase state index of each grid cell using the following formula:

[0070] Where S is the comprehensive phase index, Liquid water content, For the water-to-ice ratio, For temperature gradient, To preset the baseline value for liquid water content, To preset the water-to-ice ratio baseline value, To preset the temperature gradient reference value, as well as These are the preset weighting coefficients corresponding to the ratios of liquid water content, water-ice ratio, and temperature gradient. The ratio of liquid water content, For water-ice ratio and This represents the temperature gradient ratio.

[0071] Furthermore, the processor can also determine the cell icing risk index corresponding to each grid cell based on the comprehensive phase state index and real-time operating parameters of each region's grid cells. Specifically, the cell icing risk index can be determined according to the following formula:

[0072] in, This is the unit icing risk index. To synthesize the phase index, This refers to the real-time output power of the fan. This refers to the rated output power of the fan. This represents the real-time vibration amplitude of the blade. To preset the blade vibration amplitude threshold, This is the preset vibration weighting coefficient.

[0073] The comprehensive phase state index is used to characterize the impact of the atmospheric environment on the risk of icing. The power feedback term and vibration feedback term are used to characterize the real-time operating parameters of the wind turbine that reflect the risk of icing. If the wind turbine blades are iced, it will lead to a decrease in the wind turbine's output power (aerodynamic efficiency), indicating a greater risk of icing. If the wind turbine blades are iced, it will lead to a larger balance value of the blade vibration amplitude (increased blade unbalanced vibration), indicating a greater risk of icing.

[0074] The processor can determine the largest among multiple unit icing risk indices and use it as the target unit's icing risk index. When there is only one preset icing risk index threshold, the processor compares the target unit's icing risk index with the preset threshold. If the target unit's icing risk index is greater than or equal to the preset threshold, the processor predicts a certain icing risk for the wind turbine; otherwise, it predicts no icing risk. When there are multiple preset icing risk index thresholds, the processor determines the threshold range to which the target unit's icing risk index falls, thereby predicting the degree of icing risk for the wind turbine. Based on this risk level, relevant early warning measures are set for timely alerts, allowing for appropriate actions to be taken to minimize wind turbine blade icing.

[0075] The above-mentioned technical methods improve the identification accuracy of the vertical structure of atmospheric phase state by combining the multi-parameter detection advantages of pinned polarization radar with the high-precision temperature inversion capability of microwave radiometer. Furthermore, by fusing multiple parameters such as liquid water content, water-ice ratio, and temperature gradient, a three-dimensional phase state discrimination index model is constructed, which enables the determination of the comprehensive phase state index. Additionally, a dynamic risk assessment model is constructed to predict the icing risk of wind turbine blades.

[0076] The technical effects achieved by this application are as follows: First, this application overcomes the limitations of traditional two-dimensional planar data by introducing the water-to-ice ratio and temperature gradient to quantify the spatial distribution of phase states, thus achieving a three-dimensional, refined diagnosis of the mixed phase state of ice and water in the atmosphere. Second, this application combines dual-polarization radar, microwave radiometer, and wind turbine operating parameters, and through the synergistic inversion of polarization parameters and temperature vertical profiles, solves the problem of high false alarm rate caused by environmental noise from a single sensor, thereby improving the accuracy of data acquisition. Third, based on three-dimensional phase discrimination indicators (water-to-ice ratio, liquid water content, and temperature gradient), a risk prediction model is constructed to achieve accurate prediction of the icing risk of wind turbines.

[0077] This application also provides an apparatus for predicting the icing risk of a wind turbine, which may include: a memory configured to store instructions; and a processor configured to retrieve instructions from the memory and, when executing the instructions, to implement the method for predicting the icing risk of a wind turbine as described above.

[0078] This application also provides a machine-readable storage medium storing instructions for causing a machine to perform the above-described method for predicting the icing risk of a wind turbine.

[0079] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0080] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0081] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0082] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1The steps of the function specified in one or more boxes.

[0083] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0084] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0085] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0086] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0087] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for predicting the icing risk of wind turbines, characterized in that, The wind turbine is located in the wind farm area, and the method includes: The liquid water content, water-to-ice ratio, and temperature gradient corresponding to multiple regional grid cells, as well as the real-time operating parameters of the wind turbine, are obtained. The multiple regional grid cells are obtained by dividing the wind farm area. The comprehensive phase index corresponding to each of the aforementioned regional grid units is determined based on the liquid water content, water-to-ice ratio, and temperature gradient. Based on the comprehensive phase index and the real-time operating parameters of each of the aforementioned regional grid units, the unit icing risk index corresponding to each of the aforementioned regional grid units is determined; The icing risk of the wind turbine is predicted based on multiple unit icing risk indices.

2. The method according to claim 1, characterized in that, The water-to-ice ratio is obtained by: Obtain the differential propagation phase shift rate and differential reflectivity corresponding to each grid cell in the region acquired by the dual-polarization radar; The water-ice ratio corresponding to each of the aforementioned regional grid cells is determined based on the differential propagation phase shift rate and the differential reflectivity.

3. The method according to claim 2, characterized in that, The step of determining the water-ice ratio corresponding to each regional grid cell based on the differential propagation phase shift rate and the differential reflectivity includes: The water-ice ratio corresponding to each grid cell in the aforementioned region is determined using the following formula: in, For the water-to-ice ratio, The phase shift rate of differential propagation, Differential reflectivity, To preset the differential propagation phase shift rate reference value, To preset the differential reflectivity reference value, For preset coefficients, This is the preset index.

4. The method according to claim 1, characterized in that, The determination of the comprehensive phase index corresponding to each of the aforementioned regional grid cells based on the liquid water content, water-to-ice ratio, and temperature gradient includes: The ratios of the liquid water content to the corresponding preset liquid water content benchmark value, the water-ice ratio to the corresponding preset water-ice ratio benchmark value, and the temperature gradient to the corresponding preset inversion layer temperature gradient benchmark value for each of the aforementioned regional grid units are determined respectively, so as to obtain the liquid water content ratio, water-ice ratio, and temperature gradient ratio corresponding to each of the aforementioned regional grid units. The product values ​​of the liquid water content ratio, the water-ice ratio, and the temperature gradient ratio corresponding to each of the aforementioned regional grid cells are determined with their respective preset weight coefficients, so as to obtain the liquid water content parameter, water-ice ratio parameter, and temperature gradient parameter corresponding to each of the aforementioned regional grid cells; The sum of the liquid water content parameter, the water-to-ice ratio parameter, and the temperature gradient parameter corresponding to each of the aforementioned regional grid cells is determined to obtain the comprehensive phase index corresponding to each of the aforementioned regional grid cells.

5. The method according to claim 1, characterized in that, The real-time operating parameters include the real-time output power of the wind turbine and the real-time vibration amplitude of the blades. The determination of the unit icing risk index corresponding to each of the aforementioned regional grid units, based on the comprehensive phase state index and the real-time operating parameters, includes: A power feedback term is determined based on the comprehensive phase state index and the real-time output power of the wind turbine, wherein the power feedback term is directly proportional to the comprehensive phase state index and inversely proportional to the real-time output power of the wind turbine. The vibration feedback term is determined based on the real-time vibration amplitude of the blade and the preset vibration weight coefficient, wherein the vibration feedback term is proportional to the real-time vibration amplitude of the blade and the preset vibration weight coefficient. The sum of the power feedback term and the vibration feedback term is determined to obtain the cell icing risk index corresponding to each of the regional grid cells.

6. The method according to claim 5, characterized in that, The step of determining the power feedback term based on the comprehensive phase state index and the real-time output power of the wind turbine includes: The ratio of the real-time output power of the fan to the rated output power of the fan is determined to obtain the energy conversion efficiency of the fan. The energy conversion loss rate is determined based on the energy conversion efficiency, wherein the sum of the energy conversion efficiency and the energy conversion loss rate is 1; The power feedback term is obtained by determining the product of the energy conversion loss rate and the comprehensive phase index.

7. The method according to claim 5, characterized in that, The step of determining the vibration feedback item based on the real-time vibration amplitude of the blade and a preset vibration weighting coefficient includes: The ratio of the real-time vibration amplitude of the blade to a preset blade vibration amplitude threshold is determined to obtain the blade vibration amplitude balance value. The product of the blade vibration amplitude balance value and the preset vibration weighting coefficient is determined to obtain the vibration feedback term.

8. The method according to claim 1, characterized in that, The method of predicting the icing risk of the wind turbine based on multiple unit icing risk indices includes: The largest of the multiple unit icing risk indices is determined to obtain the target unit icing risk index; The icing risk of the wind turbine is predicted based on the target unit icing risk index and the preset icing risk index threshold.

9. A device for predicting the icing risk of wind turbines, characterized in that, include: The memory is configured to store instructions; as well as The processor is configured to retrieve the instructions from the memory and, when executing the instructions, to implement the method for predicting the icing risk of a wind turbine according to any one of claims 1 to 8.

10. A machine-readable storage medium, characterized in that, The machine-readable storage medium stores instructions for causing the machine to perform the method for predicting the icing risk of a wind turbine according to any one of claims 1 to 8.

Images