A multi-timescale ice cover prediction method, system and related device

Abstract

The present invention provides a multi-timescale icing prediction method, system, and related device, including building a WRF forecast model based on a combination of parameterized schemes with the best meteorological element simulation effects; determining the optimal precipitation phase forecast model based on the WRF forecast model and different precipitation phase identification models; using the precipitation phase forecast model to analyze historical icing event precipitation phase return data, establishing a short-term icing prediction model based on the Makkonen model and the Jones model, and performing icing simulation to obtain a daily maximum icing thickness forecast; using the precipitation phase forecast model and the short-term icing prediction model to reconstruct historical icing data within a set timescale; and using artificial intelligence technology to establish a long-term icing prediction model based on the reconstructed historical icing data to achieve icing prediction for the set timescale. The present invention can achieve icing prediction at multiple timescales, including short, medium, and long term, thus addressing the shortcomings of existing prediction models.

Description

Technical Field

[0001] The present invention belongs to the technical field of transmission line icing prediction, and in particular relates to a multi-time-scale icing prediction method, system and related devices. Background Art

[0002] Icing, a unique meteorological disaster, has severely impacted the safe operation of many power grids around the world. Researchers at home and abroad have conducted extensive research on the meteorological conditions and physical mechanisms of power grid icing, developing a variety of theoretical models for predicting ice thickness.

[0003] Scholars both domestically and internationally have conducted extensive research on the formation and evolution of icing, and have proposed a variety of icing thickness prediction models based on extensive observational and laboratory data. Initially, due to a lack of fundamental understanding of the icing formation process, numerous empirical models were developed to describe the evolution of icing based on the statistical relationship between meteorological conditions and icing observations. However, icing accidents, as relatively rare meteorological events, may not simply follow the principles of probability distribution, and empirical models are highly localized. Therefore, using these empirical models to estimate icing thickness often fails to meet actual operational needs.

[0004] Later, people parameterized the formation process of ice thickness based on the thermodynamic and physical characteristics of ice accumulation on power lines. Makkonen, based on the assumption that the shape of ice is cylindrical, considered the microphysical process and thermal equilibrium process of the collision between hydroparticles and conductors, and established a set of ice forecast models applicable to various icing conditions, which are recommended for use by most organizations and scholars. Jones simplified the physical process of freezing rain icing and proposed a simple model for calculating standard ice thickness. This model is only applicable to freezing rain icing processes. It only requires two meteorological factors, precipitation and wind speed, to more accurately simulate the growth of ice thickness during freezing rain. The simulation effect is not much different from the Makkonen model, so it is also widely used to simulate ice thickness under freezing rain conditions.

[0005] Currently, the Makkonen model and the Jones model are two icing physical models with good application effects. They are often combined with short-term meteorological forecasts to achieve short-term ice thickness predictions. However, there is less research on long-term predictions of monthly and quarterly ice cover. It is necessary to improve the ice cover prediction technology covering multiple time scales of short, medium and long terms. Summary of the Invention

[0006] In view of this, the present invention aims to provide a multi-time-scale icing prediction method, system and related devices, which can realize short-, medium- and long-term multi-time-scale icing prediction.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] A first aspect of the present invention provides a multi-time-scale ice cover prediction method, comprising the following steps:

[0009] The WRF forecast model is built based on the parameterized scheme combination with the best meteorological element simulation effect;

[0010] Determine the optimal precipitation phase forecast model based on the WRF forecast model and different precipitation phase identification models;

[0011] Using the precipitation phase forecast model and historical icing event precipitation phase report data, a short-term icing prediction model was established based on the Makkonen model and the Jones model, and icing simulation was performed to obtain the daily maximum ice thickness forecast.

[0012] The precipitation phase forecast model and the short-term ice cover prediction model are used to reconstruct the historical ice cover data within the set time scale. Based on the reconstructed historical ice cover data, artificial intelligence technology is used to establish a long-term ice cover prediction model to achieve ice cover prediction on the set time scale.

[0013] Furthermore, a WRF forecast model is built based on the combination of parameterized schemes with the best meteorological element simulation effects, including:

[0014] The WRF model is driven by ERA reanalysis data to simulate meteorological elements of historical icing events;

[0015] Evaluate the simulation effects of different parameterization scheme combinations, select the parameterization scheme combination with the best meteorological element simulation effect, and build the WRF forecast model.

[0016] Furthermore, meteorological elements include: ground elements and high-altitude elements.

[0017] Furthermore, precipitation phase identification models include: thermodynamic model, empirical model and AI model.

[0018] Furthermore, the optimal precipitation phase forecast model is determined based on the WRF forecast model and different precipitation phase identification models, including:

[0019] Using the WRF forecast model's upper-air and surface meteorological report data on historical icing events;

[0020] The precipitation phase of historical icing events is simulated and reported using different precipitation phase identification models;

[0021] The simulation effects of different models are evaluated, and the optimal integrated model of precipitation phase is obtained through statistical calculation, which is used as the optimal precipitation phase forecast model.

[0022] Furthermore, a short-term icing prediction model was established based on the Makkonen model and the Jones model, and icing simulation was performed, including:

[0023] When freezing rain occurs, ice cover simulation is performed based on the Makkonen model and the Jones model, and the ice cover simulation effects of different models are evaluated;

[0024] Based on the icing simulation results of different models, statistical integration of each model is performed to obtain the optimal short-term icing prediction model;

[0025] The short-term ice cover prediction model is used to predict the daily maximum ice cover thickness.

[0026] Furthermore, the precipitation phase forecast model and the short-term ice cover prediction model are used to reconstruct historical ice cover data within a set time scale, including:

[0027] Based on the ERA5 reanalysis data and precipitation phase forecast model within the set period, the freezing rain data within the set period is reconstructed;

[0028] Based on the short-term ice cover prediction model, the historical ice cover data within the set period is reconstructed and the data is processed into data within the set time scale.

[0029] A second aspect of the present invention further provides a multi-time-scale ice cover prediction system, comprising:

[0030] The forecast model building unit is used to build the WRF forecast model based on the parameterized scheme combination with the best meteorological element simulation effect;

[0031] The precipitation phase forecast model establishment unit is used to determine the optimal precipitation phase forecast model based on the WRF forecast model and different precipitation phase identification models;

[0032] The short-term icing prediction model building unit is used to use the precipitation phase forecast model to calculate the precipitation phase report data of historical icing events, establish a short-term icing prediction model based on the Makkonen model and the Jones model, and perform icing simulation to obtain the daily maximum ice thickness forecast;

[0033] The long-term ice cover prediction model establishment unit is used to reconstruct the historical ice cover data within a set time scale using the precipitation phase forecast model and the short-term ice cover prediction model. Based on the reconstructed historical ice cover data, artificial intelligence technology is used to establish a long-term ice cover prediction model to achieve ice cover prediction on a set time scale.

[0034] Accordingly, the present invention also provides a computer device, comprising: a memory and a processor and a computer program stored in the memory, and when the computer program is executed on the processor, a multi-time-scale icing prediction method as described in the first aspect is implemented.

[0035] Correspondingly, the present invention also provides a computer storage medium having a computer program stored thereon, and when the computer program is executed by a processor, a multi-time-scale icing prediction method according to the first aspect is implemented.

[0036] In summary, the present invention provides a multi-time-scale icing prediction method, system, and related device, including building a WRF forecast model based on a combination of parameterized schemes with the best meteorological element simulation effects; determining the optimal precipitation phase forecast model based on the WRF forecast model and different precipitation phase identification models; using the precipitation phase forecast model to report precipitation phase data of historical icing events, establishing a short-term icing prediction model based on the Makkonen model and the Jones model, and performing icing simulation to obtain a daily maximum icing thickness forecast; using the precipitation phase forecast model and the short-term icing prediction model to reconstruct historical icing data within a set time scale, and using artificial intelligence technology to establish a long-term icing prediction model based on the reconstructed historical icing data to achieve icing prediction for the set time scale. The present invention can achieve icing prediction at multiple time scales, short, medium, and long term, and supplements the shortcomings of existing prediction models. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0038] Figure 1 A flowchart of a multi-time-scale icing prediction method provided by an embodiment of the present invention;

[0039] Figure 2 A technical roadmap for short-, medium-, and long-term icing prediction based on meteorological forecasts provided by an embodiment of the present invention;

[0040] Figure 3 This is a structural block diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to make the purposes, features, and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0042] The following is a further introduction to the ice covering model in the prior art.

[0043] As mentioned above, scholars both domestically and internationally have conducted extensive research on the formation and evolution of ice cover, proposing a variety of ice thickness prediction models based on extensive observational and laboratory data. Initially, due to a lack of fundamental understanding of the ice formation process, numerous empirical models were developed to describe the evolution of ice accumulation based on the statistical relationship between meteorological conditions and ice accumulation observations. For example, the icing model established by Imai et al. assumes that the conductor icing process is proportional to -T and independent of precipitation, but ignores the influence of conductor roughness and ice evaporation, and therefore underestimates the ice thickness; Lenhard established an empirical model based on the correlation between ice thickness and precipitation. The model parameters are relatively simple, but it only considers the influence of precipitation, so the error is large; Wu Xi et al. used observation data from the Erlang Mountain Ice Observation Station in Sichuan from 2006 to 2009 to establish a conductor icing model with conventional meteorological elements as parameters, and found that the correlation coefficient between the simulation results and the observation values ​​was high; McComber et al. used observation data of meteorological elements and icing load to establish a neural network scheme, and used ice observation records in Canada from 1994 to 1997 to verify it. The results showed that the scheme had a good simulation effect on the ice thickness of rime, but a poor simulation effect on freezing rain. Makkonen et al. pointed out that icing accidents, as relatively rare meteorological events, may not simply follow the principle of probability distribution, and the empirical model is too localized. Therefore, using empirical models to estimate ice thickness often fails to meet actual business needs.

[0044] Later, researchers parameterized the ice thickness formation process based on the thermodynamic and physical characteristics of ice accumulation on power lines. Chaine et al. comprehensively considered the effects of atmospheric humidity, precipitation, temperature, and wind speed, and established a freezing rain icing model assuming dry growth. This model primarily calculated the horizontal and vertical thickness of ice using wind speed, volume, and precipitation during the icing process, and then used correction coefficients to calculate the equivalent ice thickness. However, this approach has significant limitations due to the difficulty in determining the correction coefficients. Makkonen, assuming a cylindrical ice shape, considered the microphysical processes of collision and thermal equilibrium between hydroparticles and conductors, establishing an icing forecast model applicable to various icing conditions and recommended by most organizations and scholars. Jones simplified the physical process of freezing rain icing and proposed a simple model for calculating standard ice thickness. This model is applicable only to freezing rain icing processes and requires only two meteorological factors: precipitation and wind speed. It can accurately simulate the growth of ice thickness during freezing rain, with simulation results comparable to those of the Makkonen model. Therefore, it has also been widely used to simulate ice thickness under freezing rain conditions.

[0045] There are a large number of micro-topography such as passes and windward slopes in the high-altitude areas of Yunnan and Guizhou. The current ice cover physical model has poor universality in the above areas, resulting in low accuracy in short-term predictions of the presence and thickness of ice cover. At the same time, there is currently no mature technology to predict long-term monthly and quarterly ice cover conditions.

[0046] Therefore, based on the concept of meteorological forecasting, this paper considers that numerical models have higher prediction accuracy for high-altitude meteorological elements than for ground-based meteorological elements, and that changes in high-altitude meteorological elements directly determine the phase of ground precipitation, and thus whether the ground will be covered with ice. Therefore, a short-term ice cover prediction method combining "precipitation phase state + physical model" is proposed. Furthermore, based on climate mechanisms, a long-term ice cover trend prediction technology is proposed, constructing a technical system for ice cover prediction covering multiple time scales, including short, medium, and long term.

[0047] See also Figure 1 This embodiment provides a multi-time-scale ice cover prediction method, comprising the following steps:

[0048] S1: Build the WRF forecast model based on the parameterized scheme combination with the best meteorological element simulation effect.

[0049] It should be noted that the WRF (Weather Research and Forecasing) meteorological numerical model is an atmospheric model used for weather and climate forecasting. It can simulate various physical and chemical processes in the atmosphere, including radiation transfer, turbulence, cloud microphysics, precipitation, surface processes, etc., and can be used to predict various weather phenomena such as precipitation, temperature, wind speed, etc.

[0050] This step is to select the best combination of simulation effects from a variety of meteorological elements and build a WRF forecast model.

[0051] S2: Determine the optimal precipitation phase forecast model based on the WRF forecast model and different precipitation phase identification models.

[0052] It should be noted that the existing technology has proposed several precipitation phase identification models based on different technical routes. In this step, the WRF forecast model constructed in the previous step is combined with different precipitation phase identification models to determine the optimal integrated model based on the final simulation effect.

[0053] S3: Using the precipitation phase forecast model to analyze the precipitation phase report data of historical icing events, a short-term icing prediction model was established based on the Makkonen model and the Jones model, and icing simulation was performed to obtain the daily maximum ice thickness forecast.

[0054] S4: Use the precipitation phase forecast model and the short-term ice cover prediction model to reconstruct the historical ice cover data within the set time scale. Based on the reconstructed historical ice cover data, use artificial intelligence technology to establish a long-term ice cover prediction model to achieve ice cover prediction on the set time scale.

[0055] The present invention provides a multi-time-scale ice cover prediction method, which can realize short-, medium- and long-term multi-time-scale ice cover prediction, and makes up for the shortcomings of existing prediction models.

[0056] The following combination Figure 2 The technical roadmap for short-, medium- and long-term ice cover prediction based on meteorological forecasts shown in the figure further introduces a multi-time-scale ice cover prediction method of the present invention.

[0057] 1. Weather data report

[0058] First, the WRF model is built, and the meteorological element reports of historical icing time are carried out based on the EAR initial field and parameterized scheme combination. The parameterized scheme combination with the best meteorological element simulation effect is selected from ground elements such as temperature, wind speed, precipitation, and high-altitude elements such as cloud top temperature, temperature at different altitudes, and humidity to build the WRF forecast model.

[0059] Therefore, in a preferred embodiment of the present invention, carrying out meteorological numerical reporting includes driving the WRF model to simulate the meteorological elements of historical icing events through ERA reanalysis data, evaluating the simulation effects of different parameterization scheme combinations, selecting the parameterization scheme combination with the best meteorological element simulation effect, and building a WRF forecast model.

[0060] 2. Precipitation phase forecast model

[0061] The WRF forecast model built in the previous steps is combined with the thermodynamic model, empirical model and AI model to perform multi-model integration to obtain the optimal integrated model for phase forecasting of rain, snow, freezing rain, sleet and ice pellet precipitation.

[0062] Therefore, in a preferred embodiment of the present invention, establishing a precipitation phase forecast model includes simulating and reporting the high-altitude and ground meteorological data of historical icing events based on the first-step model, using precipitation phase identification models such as thermodynamic models, empirical models, and AI models to simulate and report the precipitation phase of historical icing events, evaluating the simulation effect of each model, and obtaining the optimal integrated model of precipitation phase through statistical algorithms.

[0063] Among them, the statistical algorithm process is to evaluate the return effect of various models by simulating the precipitation phase of the historical icing process and calculating the TS score of the freezing rain return respectively, and then use equal-weighted average and weighted average (the weight coefficient of each model is obtained by the TS score of the single model / the sum of the TS scores of each model) to statistically integrate each model to obtain the optimal integrated model of precipitation phase.

[0064] 3. Short-term ice cover forecast model

[0065] In a preferred embodiment of the present invention, establishing a short-term icing prediction model includes, based on the second step, reporting data on the precipitation phase of historical icing events, performing icing simulation based on the Makkonen model and the Jones model, respectively, when freezing rain occurs, and improving the rime model by combining the two; when rime occurs, performing icing simulation based on the rime model to obtain a daily maximum icing thickness forecast.

[0066] The combined improvements to the rime model included calculating the TS score for ice thickness simulation to evaluate the icing performance of the two models. The models were statistically integrated using equal-weighted and weighted averages (the weight coefficients of the two models were calculated by dividing the TS score of each model by the sum of the TS scores of each model) to obtain the optimal integrated model for ice thickness. The rime model used the rime growth component of the Makkonen model.

[0067] 4. Long-term ice cover forecast model

[0068] In a preferred embodiment of the present invention, establishing a long-term icing forecast model involves reconstructing nearly 50 years of historical freezing rain data based on the ERA5 reanalysis data from the second step and the precipitation phase forecast model from the second step. Furthermore, the data is reconstructed based on the short-term icing forecast model from the third step, and processed into monthly and quarterly data. Correlations between all climate index factors and historical monthly and quarterly icing data are analyzed, and long-term monthly and quarterly icing forecast models are established using artificial intelligence technology to predict monthly and quarterly icing intensity and anomalies. The reconstructed time period and time scale can be determined based on actual conditions to determine the long-term forecast model.

[0069] This paper proposes a short-term icing forecast model based on precipitation phase identification. Meteorological numerical models predict upper-air meteorological elements with higher accuracy than ground-based meteorological elements. Changes in upper-air meteorological elements directly determine the ground-based precipitation phase, and thus whether or not ice will form on the ground. Compared to existing prediction methods that directly combine ground-based meteorological elements with physical models of icing, this model offers more scientific logic and higher prediction accuracy.

[0070] Based on the same inventive concept, the present application also provides a multi-timescale icing prediction system for implementing the multi-timescale icing prediction method described above. The solution provided by this system is similar to the solution described in the method described above. Therefore, the specific limitations in the multi-timescale icing prediction system embodiment provided below can be found in the limitations of the multi-timescale icing prediction method described above and are not further elaborated here.

[0071] This embodiment provides a multi-timescale ice cover prediction system, including:

[0072] The forecast model building unit is used to build the WRF forecast model based on the parameterized scheme combination with the best meteorological element simulation effect;

[0073] The precipitation phase forecast model establishment unit is used to determine the optimal precipitation phase forecast model based on the WRF forecast model and different precipitation phase identification models;

[0074] The short-term icing prediction model building unit is used to use the precipitation phase forecast model to calculate the precipitation phase report data of historical icing events, establish a short-term icing prediction model based on the Makkonen model and the Jones model, and perform icing simulation to obtain the daily maximum ice thickness forecast;

[0075] The long-term ice cover prediction model establishment unit is used to reconstruct the historical ice cover data within a set time scale using the precipitation phase forecast model and the short-term ice cover prediction model. Based on the reconstructed historical ice cover data, artificial intelligence technology is used to establish a long-term ice cover prediction model to achieve ice cover prediction on a set time scale.

[0076] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0077] Reference Figure 3An embodiment of the present invention further provides a computer device 3, comprising: a memory 302, a processor 301, and a computer program 303 stored in the memory 302. When the computer program 303 is executed on the processor 301, a multi-time-scale ice prediction method as described in any one of the above methods is implemented.

[0078] The computer device 3 may be a desktop computer, a notebook computer, a PDA, a cloud server or other computing devices. The computer device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art will understand that Figure 3 This is merely an example of the computer device 3 and does not constitute a limitation on the computer device 3 . The computer device 3 may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the computer device 3 may also include input and output devices, network access devices, etc.

[0079] The processor 301 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor may be a microprocessor or any conventional processor.

[0080] In some embodiments, the memory 302 may be an internal storage unit of the computer device 3, such as a hard disk or memory of the computer device 3. In other embodiments, the memory 302 may also be an external storage device of the computer device 3, such as a plug-in hard disk, a SmartMediaCard (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the computer device 3. Furthermore, the memory 302 may include both an internal storage unit of the computer device 3 and an external storage device. The memory 302 is used to store an operating system, application programs, a boot loader, data, and other programs, such as the program code of the computer program. The memory 302 may also be used to temporarily store data that has been output or is about to be output.

[0081] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the multi-time-scale icing prediction method as described in any one of the above methods is implemented.

[0082] In this embodiment, if the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the process of the above-mentioned method embodiment by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, mobile hard drive, magnetic disk, or optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals or telecommunication signals.

[0083] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0084] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0085] In the embodiments disclosed in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are merely schematic. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0086] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A multi-time scale ice cover prediction method, characterized in that: The steps include: The WRF forecast model is built based on the parameterized scheme combination with the best meteorological element simulation effect; Determining an optimal precipitation phase forecast model based on the WRF forecast model and different precipitation phase identification models; Using the precipitation phase forecast model and the historical icing event precipitation phase report data, a short-term icing prediction model was established based on the Makkonen model and the Jones model, and icing simulation was performed to obtain the daily maximum icing thickness forecast; The precipitation phase forecast model and the short-term icing prediction model are used to reconstruct historical icing data within a set time scale. Based on the reconstructed historical icing data, an artificial intelligence technology is used to establish a long-term icing prediction model to achieve icing prediction within a set time scale.

2. The multi-time scale ice cover prediction method according to claim 1, characterized in that: The WRF forecast model is built based on the parameterized scheme combination with the best meteorological element simulation effect, including: The WRF model is driven by ERA reanalysis data to simulate meteorological elements of historical icing events; Evaluate the simulation effects of different parameterization scheme combinations, select the parameterization scheme combination with the best meteorological element simulation effect, and build the WRF forecast model.

3. A multi-time-scale ice cover prediction method according to claim 1 or 2, characterized in that: The meteorological elements include ground elements and high-altitude elements.

4. The multi-time-scale ice cover prediction method according to claim 1, characterized in that: Precipitation phase identification models include: thermodynamic model, empirical model and AI model.

5. The multi-time scale ice cover prediction method according to claim 1, characterized in that: The optimal precipitation phase forecast model is determined based on the WRF forecast model and different precipitation phase identification models, specifically including: Using the WRF forecast model's upper-air and surface meteorological report data on historical icing events; Simulating and reporting the precipitation phases of historical icing events using different precipitation phase identification models; The simulation effects of different models are evaluated, and the optimal integrated model of precipitation phase state is obtained through statistical calculation, which is used as the optimal precipitation phase state forecast model.

6. The multi-time-scale ice cover prediction method according to claim 1, characterized in that: Based on the Makkonen model and the Jones model, a short-term icing prediction model is established and an icing simulation is performed, specifically including: When freezing rain occurs, ice cover simulation is performed based on the Makkonen model and the Jones model, and the ice cover simulation effects of different models are evaluated; Based on the ice cover simulation effects of different models, statistical integration of the models is performed to obtain the optimal short-term ice cover prediction model; The short-term ice cover prediction model is used to predict the maximum ice cover thickness on a daily basis.

7. The multi-time-scale ice cover prediction method according to claim 1, characterized in that: Reconstructing historical ice cover data within a set time scale using the precipitation phase forecast model and the ice cover short-term forecast model specifically includes: Reconstructing freezing rain data within a set period based on ERA5 reanalysis data within the set period and the precipitation phase forecast model; The historical ice coverage data within the set time period is reconstructed based on the short-term ice coverage prediction model, and the data is processed into data within the set time scale.

8. A multi-time scale ice cover prediction system, characterized in that: include: The forecast model building unit is used to build the WRF forecast model based on the parameterized scheme combination with the best meteorological element simulation effect; A precipitation phase forecast model establishment unit, configured to determine an optimal precipitation phase forecast model based on the WRF forecast model and different precipitation phase identification models; An icing short-term prediction model establishment unit is used to use the precipitation phase forecast model to calculate the precipitation phase report data of historical icing events, establish a short-term icing prediction model based on the Makkonen model and the Jones model, and perform icing simulation to obtain a daily maximum icing thickness forecast; The long-term icing prediction model establishment unit is used to use the precipitation phase forecast model and the short-term icing prediction model to reconstruct historical icing data within a set time scale, and based on the reconstructed historical icing data, use artificial intelligence technology to establish a long-term icing prediction model to achieve icing prediction on a set time scale.

9. A computer device, characterized in that: include: A memory, a processor, and a computer program stored in the memory, which, when executed on the processor, implements a multi-time-scale ice cover prediction method according to any one of claims 1 to 7.

10. A computer storage medium, characterized in that The computer storage medium stores a computer program, which, when executed by a processor, implements a multi-time-scale icing prediction method according to any one of claims 1 to 7.

Images