Method, processor and device for predicting icing of overhead line system, and storage medium

Abstract

The embodiment of the invention provides an overhead line system icing prediction method, a processor, a device and a storage medium, and belongs to the field of icing prediction. The method for predicting icing of the overhead line system comprises the following steps: acquiring meteorological data of an area where the overhead line system is located, operation data of the overhead line system, spatial information of the area where the overhead line system is located and data acquisition time information of the overhead line system; physical data corresponding to the contact network are determined according to the meteorological data and the operation data, and the physical data comprise the temperature gradient, the heat conduction rate and the water vapor content change rate; and inputting the temperature gradient, the heat conduction rate, the water vapor content change rate, the meteorological data, the operation data, the spatial information and the data acquisition time information into a preset icing prediction model to obtain an icing prediction result corresponding to the contact network. According to the invention, the accuracy of overhead line system icing prediction can be improved.

Description

Technical Field

[0001] This application relates to the field of icing prediction, and particularly to a method, a processor, a device and a storage medium for predicting catenary icing. Background Art

[0002] In cold seasons, the railway catenary system in China is vulnerable to low-temperature and humid weather, and icing is common. Icing may cause power outages in the catenary system, affect the normal operation of trains, and even pose safety hazards.

[0003] Existing icing prediction methods mainly rely on traditional meteorological models or empirical formulas. On the one hand, the prediction accuracy of these methods is limited, especially in dealing with complex and dynamic meteorological condition changes. On the other hand, icing data is scarce, especially icing data under extreme weather conditions is difficult to obtain, which further affects the prediction ability of the model.

[0004] Therefore, how to improve the accuracy of catenary icing prediction is a technical problem to be solved urgently. Summary of the Invention

[0005] The purpose of the embodiments of this application is to provide a method, a processor, a device and a storage medium for predicting catenary icing, so as to solve the problem of how to improve the accuracy of catenary icing prediction in the prior art.

[0006] To achieve the above purpose, the first aspect embodiment of this application provides a method for predicting catenary icing, and the method includes:

[0007] Obtain meteorological data of the area where the catenary is located, operation data of the catenary, spatial information of the area where the catenary is located, and data acquisition time information of the catenary;

[0008] Determine the physical data corresponding to the catenary according to the meteorological data and the operation data, where the physical data includes temperature gradient, heat conduction rate, and water vapor content change rate;

[0009] Input the temperature gradient, heat conduction rate, water vapor content change rate, meteorological data, operation data, spatial information, and data acquisition time information into a preset icing prediction model to obtain an icing prediction result corresponding to the catenary.

[0010] In the embodiments of the present application, the meteorological data includes humidity, saturated water vapor content, and humidity change rate, and the operation data includes the internal temperature of the catenary, the external temperature of the catenary, the thickness of the catenary, the thermal conductivity of the catenary, and the surface area of the catenary; the physical data corresponding to the catenary is determined according to the meteorological data and the operation data, including: determining the temperature gradient according to the internal temperature of the catenary, the external temperature of the catenary, and the thickness of the catenary; determining the heat conduction rate according to the thermal conductivity of the catenary, the surface area of the catenary, and the temperature gradient; determining the water vapor content change rate according to the humidity, the saturated water vapor content, and the humidity change rate.

[0011] In the embodiments of the present application, determining the temperature gradient according to the internal temperature of the catenary, the external temperature of the catenary, and the thickness of the catenary includes determining the temperature gradient according to the following formula:

[0012]

[0013] Wherein, is the temperature gradient, T in is the internal temperature of the catenary, T out is the external temperature of the catenary, and d is the thickness of the catenary.

[0014] In the embodiments of the present application, determining the heat conduction rate according to the thermal conductivity, the surface area of the catenary, and the temperature gradient includes determining the heat conduction rate according to the following formula:

[0015]

[0016] Wherein, k is the thermal conductivity of the catenary, A is the surface area of the catenary, is the temperature gradient, and Q cond is the heat conduction rate.

[0017] In the embodiments of the present application, determining the water vapor content change rate according to the thermal conductivity, the surface area of the catenary, and the temperature gradient includes determining the water vapor content change rate according to the following formula:

[0018]

[0019] Wherein, is the water vapor content change rate, q v is the humidity, q sat is the saturated water vapor content, k h is the humidity change rate.

[0020] In the embodiments of the present application, after obtaining the meteorological data of the area where the catenary is located and the operation data of the catenary, it further includes: based on the generative adversarial network, performing data enhancement processing on the meteorological data and the operation data to obtain enhanced meteorological data and equipment operation data.

[0021] In an embodiment of the present application, after inputting the temperature gradient, heat conduction rate, water vapor content change rate, meteorological data, operation data, spatial information, and data collection time information into a preset icing prediction model to obtain the icing prediction result corresponding to the catenary, the following steps are further included: obtaining a preset icing result; obtaining an error value based on the difference between the preset icing result and the icing prediction result; and adjusting the adversarial generation network and the preset icing prediction model according to the error value.

[0022] A second aspect of the embodiments of the present application provides a processor configured to execute the method for catenary icing prediction described above.

[0023] A third aspect of the embodiments of the present application provides a device for catenary icing prediction, including:

[0024] A data acquisition module, configured to acquire meteorological data of the area where the catenary is located, operation data of the catenary, spatial information of the area where the catenary is located, and data collection time information of the catenary;

[0025] A physical data determination module, configured to determine the physical data corresponding to the catenary according to the meteorological data and the operation data, where the physical data includes a temperature gradient, a heat conduction rate, and a water vapor content change rate;

[0026] An icing prediction result determination module, configured to input the temperature gradient, heat conduction rate, water vapor content change rate, meteorological data, operation data, spatial information, and data collection time information into a preset icing prediction model to obtain the icing prediction result corresponding to the catenary.

[0027] A fourth aspect of the embodiments of the present application provides a machine-readable storage medium, on which instructions are stored, and the instructions are used to cause a machine to execute the method for catenary icing prediction described above.

[0028] Through the above technical solutions, the combination of physical data, meteorological data, operation data, data collection time information, and spatial information with the preset icing prediction model is considered. Among them, the physical data reflects the macroscopic physical mechanism, and the meteorological data, operation data, data collection time information, and spatial information reflect the microscopic meteorological characteristics. Therefore, the present application realizes multi-scale collaborative prediction from microscopic meteorological characteristics to macroscopic physical mechanisms. Through the above multi-scale collaborative prediction, the prediction accuracy of the preset icing prediction model is improved, and it can cope with complex and dynamic meteorological condition changes.

[0029] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent specific implementation part. Description of the Drawings

[0030] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention, and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the embodiments of the present invention, but do not constitute a limitation to the embodiments of the present invention. In the accompanying drawings:

[0031] Figure 1 Schematically shows a flowchart of a method for predicting catenary icing according to an embodiment of the present application;

[0032] Figure 2 Schematically shows a schematic block diagram of a device for predicting catenary icing according to an embodiment of the present application. Specific Embodiments

[0033] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. It should be understood that the specific embodiments described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0034] It should be noted that the acquisition, transmission, storage, use, processing, etc. of data in the technical solutions of the present application all comply with the relevant regulations of national laws and regulations. In the embodiments of the present application, some industry-existing solutions such as certain software, components, models, etc. may be mentioned. They should be regarded as exemplary, and their purpose is only to illustrate the feasibility in the implementation of the technical solutions of the present application, but it does not mean that the applicant has already or necessarily used this solution.

[0035] It should be noted that if there are directional indications (such as up, down, left, right, front, back...) involved in the embodiments of the present application, then the directional indications are only used to explain the relative positional relationship and movement conditions between components in a specific posture (as shown in the accompanying drawings). If this specific posture changes, then the directional indications will also change accordingly.

[0036] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, then the descriptions of "first", "second", etc. are only for descriptive purposes, and cannot be understood as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between various embodiments can be combined with each other, but it must be based on the ability of those of ordinary skill in the art to implement. When the combination of technical solutions results in contradictions or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present application.

[0037] Figure 1 Schematically shows a flow diagram for predicting icing on catenaries in an embodiment of the present invention. As Figure 1 shown, an embodiment of the present application provides a method for predicting icing on catenaries. Taking the application of this method to a processor as an example, this method may include the following steps:

[0038] Step S101, obtain meteorological data of the area where the catenary is located, operating data of the catenary, spatial information of the area where the catenary is located, and data acquisition time information of the catenary.

[0039] Step S102, determine the physical data corresponding to the catenary according to the meteorological data and the operating data, where the physical data includes temperature gradient, heat conduction rate, and water vapor content change rate.

[0040] Step S103, input the temperature gradient, heat conduction rate, water vapor content change rate, meteorological data, operating data, spatial information, and data acquisition time information into a preset icing prediction model to obtain an icing prediction result corresponding to the catenary.

[0041] It can be understood that the catenary refers to the high-voltage transmission line that is erected in a "zigzag" shape above the rails in an electrified railway for the pantograph to draw current. Meteorological data refers to data related to meteorology such as temperature, humidity, wind speed, wind direction, atmospheric pressure, precipitation, and ice crystal content. The operating data of the catenary refers to data related to the operation of the catenary such as catenary voltage, current, conductor temperature, and tension. Spatial information refers to information about the space where the monitoring station is located, such as the longitude, latitude, and altitude of the monitoring station. Data acquisition time information refers to the time when meteorological data of the area where the catenary is located, operating data of the catenary, spatial information of the area where the catenary is located, and other information are collected. Physical data refers to objective environmental data that affects catenary icing. For example, temperature gradient, heat conduction rate, and water vapor content change rate. Temperature gradient refers to the phenomenon of stepwise increase or decrease of temperature as the distance from the surface of the catenary inside the catenary increases. Heat conduction rate refers to the amount of heat transferred per unit area per unit time. Water vapor content change rate refers to the change rate of the ratio of the mass of water vapor in moist air to the total mass of moist air. The icing prediction result refers to the prediction result of the catenary icing situation. The preset icing prediction model refers to a model that is pre-determined for predicting catenary icing. Optionally, the preset icing prediction model of the present invention can adopt a deep learning model, and a self-attention mechanism can be selected in the deep learning model. The self-attention mechanism can dynamically capture the impact of changes in meteorological conditions over time on icing. Through the self-attention module, the model can assign different weights to meteorological elements at different time steps, automatically adjust its impact on icing prediction, making the prediction more flexible and accurate, especially in the processing of complex time-series data.

[0042] Specifically, the processor first collects multi-dimensional meteorological data, equipment operation data, spatial information of the area where the catenary is located, and data acquisition time information of the catenary from the railway catenary monitoring system, including longitude and latitude, altitude, temperature, humidity, wind speed, supercooled water content, saturated water vapor content, humidity change rate, internal temperature of the catenary, external temperature of the catenary, thickness of the catenary, thermal conductivity of the catenary, surface area of the catenary, longitude and latitude of the monitoring station, altitude, etc. The operation state of the catenary is monitored through these data and associated with icing events. Then, physical data corresponding to the catenary is determined based on the meteorological data and operation data, and the physical data reflects the key processes of ice formation, including phase change of water, heat transfer, air flow, etc. These physical data can usually provide macroscopic trend predictions. Subsequently, the meteorological data of the area where the catenary is located, the operation data of the catenary, the spatial information of the area where the catenary is located, and the data acquisition time information of the catenary obtained in advance are input into a preset icing prediction model together with the physical data corresponding to the catenary determined based on the meteorological data and operation data, and the preset icing prediction model can output an icing prediction result.

[0043] Through the above technical solution, the combination of physical data, meteorological data, operation data, data acquisition time information, and spatial information with the preset icing prediction model is considered. Among them, the physical data reflects the macroscopic physical mechanism, and the meteorological data, operation data, data acquisition time information, and spatial information reflect the microscopic meteorological characteristics. Therefore, the present application realizes multi-scale collaborative prediction from microscopic meteorological characteristics to macroscopic physical mechanisms. Through the above multi-scale collaborative prediction, the prediction accuracy of the preset icing prediction model is improved, and it can cope with complex and dynamic meteorological condition changes.

[0044] In the embodiment of the present application, the meteorological data includes humidity, saturated water vapor content, and humidity change rate, and the operation data includes the internal temperature of the catenary, the external temperature of the catenary, the thickness of the catenary, the thermal conductivity of the catenary, and the surface area of the catenary; the physical data corresponding to the catenary is determined based on the meteorological data and operation data, including: determining the temperature gradient according to the internal temperature of the catenary, the external temperature of the catenary, and the thickness of the catenary; determining the heat conduction rate according to the thermal conductivity of the catenary, the surface area of the catenary, and the temperature gradient; determining the water vapor content change rate according to the humidity, saturated water vapor content, and humidity change rate.

[0045] It can be understood that humidity refers to the content of water vapor in the air. The saturated water vapor content refers to the ratio of the mass of water vapor in moist air to the total mass of the moist air. The humidity change rate refers to the change rate of the content of water vapor in the air. The internal temperature of the catenary refers to the temperature of the catenary itself. The external temperature of the catenary refers to the temperature of the environment where the catenary is located. The thickness of the catenary refers to the vertical distance directly between the two main surfaces of the catenary, top and bottom. The thermal conductivity of the catenary refers to the amount of heat transferred through an area of 1 square meter in 1 second when the temperature difference between the two surfaces of the catenary is 1 degree Celsius under steady heat transfer conditions for a 1-meter-thick catenary. The surface area of the catenary refers to the area of the catenary that is exposed externally.

[0046] Specifically, the processor determines the temperature gradient by selecting the internal temperature of the catenary, the external temperature of the catenary, and the thickness of the catenary from the catenary operation data. The processor determines the heat transfer rate by selecting the thermal conductivity of the catenary, the surface area of the catenary, and the temperature gradient determined based on the operation data. The processor determines the water vapor content change rate by selecting the humidity, the saturated water vapor content, and the humidity change rate from the meteorological data of the area where the catenary is located.

[0047] In the embodiments of the present application, determining the temperature gradient based on the internal temperature of the catenary, the external temperature of the catenary, and the thickness of the catenary includes determining the temperature gradient according to the following formula:

[0048]

[0049] wherein, is the temperature gradient, T in is the internal temperature of the catenary, T out is the external temperature of the catenary, and d is the thickness of the catenary.

[0050] It can be understood that the temperature gradient refers to the phenomenon of a stepwise increase or decrease in temperature as the distance from the surface of the catenary increases within the catenary. The internal temperature of the catenary refers to the temperature of the catenary itself. The external temperature of the catenary refers to the temperature of the environment where the catenary is located. The thickness of the catenary refers to the vertical distance directly between the two main surfaces of the catenary, top and bottom.

[0051] It can be understood that the processor first obtains the difference between the external temperature of the catenary and the internal temperature of the catenary, and then obtains the ratio of the difference to the thickness of the catenary to determine the temperature gradient in the physical data.

[0052] In the embodiments of the present application, determining the heat transfer rate based on the thermal conductivity, the surface area of the catenary, and the temperature gradient includes determining the heat transfer rate according to the following formula:

[0053]

[0054] wherein, k is the thermal conductivity of the catenary, A is the surface area of the catenary, is the temperature gradient, Q cond is the heat conduction rate.

[0055] It can be understood that the thermal conductivity of the catenary refers to the amount of heat transferred through an area of 1 square meter in 1 second when the temperature difference between the two surfaces of the catenary with a thickness of 1 meter is 1 degree under the condition of stable heat transfer of the catenary. The surface area of the catenary refers to the externally exposed area of the catenary. The temperature gradient refers to the phenomenon of stepwise increase or decrease in temperature that occurs as the distance from the surface of the catenary inside the catenary increases. The heat conduction rate refers to the amount of heat transferred per unit area per unit time.

[0056] Specifically, the processor multiplies the thermal conductivity of the catenary, the surface area of the catenary, and the temperature gradient obtained from the catenary operation data source to obtain the heat conduction rate.

[0057] In the embodiments of the present application, determining the heat conduction rate based on the thermal conductivity, the surface area of the catenary, and the temperature gradient includes determining the rate of change of water vapor content according to the following formula:

[0058]

[0059] where is the rate of change of water vapor content, q v is the humidity, q sat is the saturated water vapor content, k h is the rate of change of humidity.

[0060] It can be understood that the rate of change of water vapor content refers to the rate of change of the ratio of the mass of water vapor in moist air to the total mass of moist air. Humidity refers to the content of water vapor in the air. The saturated water vapor content refers to the ratio of the mass of water vapor in moist air to the total mass of moist air. The rate of change of humidity refers to the rate of change of the content of water vapor in the air.

[0061] Specifically, the processor multiplies the difference between the saturated water vapor content and the humidity in the meteorological data in the area where the catenary is located by the rate of change of humidity to obtain the rate of change of water vapor content in the physical data.

[0062] In the embodiments of the present application, after obtaining the meteorological data in the area where the catenary is located and the operation data of the catenary, it further includes: based on the generative adversarial network, performing data enhancement processing on the meteorological data and the operation data to obtain enhanced meteorological data and equipment operation data.

[0063] Specifically, for scarce icing data, especially data under extreme weather conditions, due to the scarcity of icing data, the prediction accuracy of the preset icing prediction model for icing conditions will be affected. Therefore, it is necessary to use a generative adversarial network for data augmentation. The generative adversarial network generates a simulated icing data set through a generative adversarial mechanism, especially icing data under extreme meteorological conditions. The generated simulated icing data set can be used to fill in the scarce icing data, thereby improving the model's prediction ability for rare events.

[0064] In the embodiment of the present application, after inputting the temperature gradient, heat conduction rate, water vapor content change rate, meteorological data, operation data, spatial information, and data acquisition time information into the preset icing prediction model to obtain the icing prediction result corresponding to the catenary, it further includes: obtaining a preset icing result; obtaining an error value according to the difference between the preset icing result and the icing prediction result; adjusting the generative adversarial network and the preset icing prediction model according to the error value.

[0065] It can be understood that the preset icing result refers to the actual icing result obtained.

[0066] Specifically, the processor inputs the meteorological data, operation data, spatial information, data acquisition time information, and physical data processed by the generative adversarial network into the preset icing prediction model to generate a prediction result of catenary icing. Compare the preset icing result with the icing prediction result and calculate the difference between them, that is, the difference between the icing prediction result and the prepared result. Evaluate the prediction accuracy through the error value, especially conduct error analysis for rare icing events. After the error analysis, optimize the preset icing prediction model. Optionally, the present invention can further improve the model performance by adjusting the parameters of the generator in the generative adversarial network, changing the number of layers of the preset deep learning model, or improving the self-attention mechanism of the preset deep learning model to reduce the error value until an accurate prediction of the icing result is achieved.

[0067] In a specific embodiment, a method for predicting catenary icing is provided, which will be described in detail below.

[0068] Step 1: Data collection and preprocessing;

[0069] Collect multi-dimensional meteorological data of the area where the catenary is located and the operation data of the catenary from the railway catenary monitoring system, meteorological stations, and other data sources.

[0070] Typical features of the data include:

[0071] (1) Meteorological data: temperature, humidity, wind speed, wind direction, atmospheric pressure, precipitation, ice crystal content, etc.

[0072] (2) Equipment data: catenary voltage, current, conductor temperature, tension, etc.

[0073] (3) Time and space information: data acquisition time, longitude and latitude of the monitoring station, altitude, etc.

[0074] Data preprocessing includes missing value handling, data normalization, and feature selection, etc. Normalization is to make data with different dimensions have the same scale, facilitating model training and processing. For time series data, a sliding window mechanism is adopted to construct training samples, that is, mapping a multi-step meteorological data sequence into the input data for icing prediction.

[0075] Step 2: Data augmentation based on the generative adversarial network For the problem of scarce icing data, especially under extreme weather conditions, this application introduces a generative adversarial network for data augmentation. The generative adversarial network is designed as follows:

[0076] (1) Generator design: The generator is responsible for generating simulated icing data from random noise. Its input is a random noise vector, and the output is simulated meteorological data and operation data.

[0077] (2) Discriminator design: The discriminator is used to distinguish real data and generated data. Its input is meteorological data and operation data, and the output is the probability of true and false labels. By alternately training the generator and the discriminator, the goal of the generator is to generate more realistic data to deceive the discriminator; while the discriminator learns to better distinguish real data and forged data. After several rounds of training, the generator can generate icing data very close to the actual meteorological data and operation data. The finally generated augmented data and the original data together constitute an extended training dataset, thus alleviating the problem of insufficient rare event data and improving the training effect of the model.

[0078] Step 3: Fusion of physical data and deep learning To better predict catenary icing, this application not only relies on meteorological data and operation data, but also combines the physical mechanism of catenary icing. For example, the key processes of ice formation include water phase change, heat transfer, air flow, etc. These physical mechanisms can usually provide macroscopic trend predictions, while deep learning models can capture details at the micro feature level.

[0079] (1) Physical data design: Based on water phase change (such as the transformation between liquid water and ice) and heat exchange process, establish the energy conservation equation and mass conservation equation to simulate the formation process of catenary icing. The temperature gradient describes the rate of temperature change inside and outside the conductor, and is a key factor affecting heat conduction and icing rate.

[0080] It can be calculated through the temperature distribution on the conductor surface where is the temperature gradient, T inis the internal temperature of the catenary, T out is the external temperature of the catenary, and d is the thickness of the catenary.

[0081] The heat conduction rate of the wire can be further calculated through the temperature gradient and determined according to the following formula: where k is the thermal conductivity of the catenary, A is the surface area of the catenary, is the temperature gradient, and Q cond is the heat conduction rate.

[0082] The change in humidity in the air is a direct factor affecting water vapor condensation and ice formation. Through the humidity change rate, the water vapor condensation rate in the air can be predicted, and thus the ice formation rate can be estimated. Combining with the temperature distribution of the wire, the ice formation speed and its influence can be dynamically predicted. The air humidity can be described by relative humidity and water vapor pressure: where, is the change rate of water vapor content, q v is the humidity, q sat is the saturated water vapor content, k h is the humidity change rate.

[0083] (2)Combination of physical data and deep learning: Use physical data as input features of the deep learning model, especially input it into the deep learning model together with meteorological data. Through the combination of physical data and deep learning, multi-scale collaborative prediction from macro to micro is achieved.

[0084] Step 4: Dynamic weighted prediction based on deep learning. This application uses a deep learning model to process time-series meteorological data; and through the self-attention mechanism, dynamically weight the time-series changes of meteorological elements. The deep learning model consists of an encoder and a decoder, and the specific steps are as follows:

[0085] (1)Input embedding: Convert the meteorological feature sequence (such as temperature, humidity, wind speed, etc.) into feature vectors and input them into the deep learning model.

[0086] (2)Self-attention mechanism: Dynamically allocate weights to each time step and meteorological feature inside the model through the self-attention mechanism. This mechanism can automatically adjust the weights according to the influence degree of meteorological elements on icing, assign higher weights to more important features, so as to enhance the accuracy and flexibility of prediction.

[0087] (3)Output prediction: The time-series data after self-attention weighting is passed to the fully connected layer, and finally the prediction result of catenary icing is output.

[0088] Step 5: Ice accretion prediction and error analysis After data augmentation and model training, the test dataset is used to evaluate the prediction performance of the model. For each moment, the model outputs the ice accretion risk value of the catenary (usually a probability or a classification label), and then error analysis is carried out through indicators such as absolute error, relative error, and confidence interval analysis. According to the results of the error analysis, the model is optimized, for example, by adjusting the parameters of the adversarial generative network generator, changing the number of layers of the deep learning model, or improving the self-attention mechanism to further improve the model performance.

[0089] An embodiment of the present application provides a processor configured to execute the above method for catenary ice accretion prediction.

[0090] An embodiment of the present application provides a device 200 for catenary ice accretion prediction, including:

[0091] A data acquisition module 210, configured to acquire meteorological data of the area where the catenary is located, operation data of the catenary, spatial information of the area where the catenary is located, and data acquisition time information of the catenary;

[0092] A physical data determination module 220, configured to determine physical data corresponding to the catenary according to the meteorological data and the operation data, where the physical data includes a temperature gradient, a heat conduction rate, and a water vapor content change rate;

[0093] An ice accretion prediction result determination module 230, configured to input the temperature gradient, the heat conduction rate, the water vapor content change rate, the meteorological data, the operation data, the spatial information, and the data acquisition time information into a preset ice accretion prediction model to obtain an ice accretion prediction result corresponding to the catenary.

[0094] The combination of physical data, meteorological data, operation data, data acquisition time information, and spatial information with a preset ice accretion prediction model is considered. The physical data reflects the macroscopic physical mechanism, and the meteorological data, operation data, data acquisition time information, and spatial information reflect the microscopic meteorological characteristics. Therefore, the present application realizes multi-scale collaborative prediction from microscopic meteorological characteristics to macroscopic physical mechanisms. Through the above multi-scale collaborative prediction, the prediction accuracy of the preset ice accretion prediction model is improved, and it can cope with complex and dynamic meteorological condition changes.

[0095] In one embodiment, the physical data determination module 220 is further configured to determine the temperature gradient according to the internal temperature of the catenary, the external temperature of the catenary, and the thickness of the catenary; determine the heat conduction rate according to the thermal conductivity of the catenary, the surface area of the catenary, and the temperature gradient; and determine the water vapor content change rate according to the humidity, the saturated water vapor content, and the humidity change rate.

[0096] In one embodiment, the physical data determination module 220 is further configured to determine a temperature gradient based on the internal temperature of the catenary, the external temperature of the catenary, and the thickness of the catenary, including determining the temperature gradient according to the following formula:

[0097]

[0098] Wherein, is the temperature gradient, T in is the internal temperature of the catenary, T out is the external temperature of the catenary, and d is the thickness of the catenary.

[0099] In one embodiment, the physical data determination module 220 is further configured to determine the heat conduction rate based on the thermal conductivity, the surface area of the catenary, and the temperature gradient, including determining the heat conduction rate according to the following formula:

[0100]

[0101] Wherein, k is the thermal conductivity of the catenary, A is the surface area of the catenary, is the temperature gradient, and Q cond is the heat conduction rate.

[0102] In one embodiment, the physical data determination module 220 is further configured to determine the heat conduction rate based on the thermal conductivity, the surface area of the catenary, and the temperature gradient, including determining the rate of change of water vapor content according to the following formula:

[0103]

[0104] Wherein, is the rate of change of water vapor content, q v is the humidity, q sat is the saturated water vapor content, and k h is the rate of change of humidity.

[0105] In one embodiment, after obtaining the meteorological data of the area where the catenary is located and the operation data of the catenary, it further includes: based on the generative adversarial network, performing data enhancement processing on the meteorological data and the operation data to obtain enhanced meteorological data and equipment operation data.

[0106] In one embodiment, after inputting the temperature gradient, the heat conduction rate, the rate of change of water vapor content, the meteorological data, the operation data, the spatial information, and the data acquisition time information into a preset icing prediction model to obtain the icing prediction result corresponding to the catenary, it further includes: obtaining a preset icing result; obtaining an error value according to the difference between the preset icing result and the icing prediction result; and adjusting the generative adversarial network and the preset icing prediction model according to the error value.

[0107] An embodiment of the present application provides a machine-readable storage medium, on which instructions are stored, and the instructions are used to cause a machine to execute the method for predicting catenary icing according to the above embodiment.

[0108] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent in such process, method, commodity or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, commodity or device including the element.

[0109] The above are only embodiments of the present application and are not used to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A method for predicting catenary icing, characterized in that: The method comprises: Acquiring meteorological data of the area where the contact network is located, operation data of the contact network, spatial information of the area where the contact network is located, and data collection time information of the contact network; Determining physical data corresponding to the contact network according to the meteorological data and the operating data, wherein the physical data includes temperature gradient, heat conduction rate and water vapor content change rate; The temperature gradient, the heat conduction rate, the water vapor content change rate, the meteorological data, the operation data, the spatial information and the data collection time information are input into a preset icing prediction model to obtain an icing prediction result corresponding to the contact network.

2. The method according to claim 1, characterized in that The meteorological data include humidity, saturated water vapor content and humidity change rate, and the operation data include contact network internal temperature, contact network external temperature, contact network thickness, contact network thermal conductivity and contact network surface area; The determining of the physical data corresponding to the contact network according to the meteorological data and the operation data comprises: Determining the temperature gradient according to the internal temperature of the contact network, the external temperature of the contact network and the thickness of the contact network; Determining the heat transfer rate according to the contact network thermal conductivity, the contact network surface area and the temperature gradient; The water vapor content change rate is determined according to the humidity, the saturated water vapor content, and the humidity change rate.

3. The method according to claim 2, characterized in that Determining the temperature gradient according to the internal temperature of the contact network, the external temperature of the contact network and the thickness of the contact network includes determining the temperature gradient according to the following formula: in, is the temperature gradient, T in is the internal temperature of the contact network, T out is the external temperature of the contact network, and d is the thickness of the contact network.

4. The method according to claim 2, characterized in that: Determining the heat conduction rate according to the thermal conductivity, the surface area of ​​the contact network and the temperature gradient includes determining the heat conduction rate according to the following formula: Wherein, k is the thermal conductivity of the contact network, A is the surface area of ​​the contact network, is the temperature gradient, Q cond is the heat transfer rate.

5. The method according to claim 2, characterized in that: Determining the heat transfer rate according to the thermal conductivity, the surface area of ​​the contact network and the temperature gradient includes determining the water vapor content change rate according to the following formula: q` v =k h ×(q sat -q v ) Among them, q` v is the rate of change of the water vapor content, q v is the humidity, q sat is the saturated water vapor content, k h is the humidity change rate.

6. The method according to claim 1, characterized in that After obtaining the meteorological data of the area where the contact network is located and the operation data of the contact network, the method further includes: Based on a generative adversarial network, data enhancement processing is performed on the meteorological data and the operation data to obtain enhanced meteorological data and equipment operation data.

7. The method according to claim 6, characterized in that After inputting the temperature gradient, the heat transfer rate, the water vapor content change rate, the meteorological data, the operation data, the spatial information and the data acquisition time information into a preset icing prediction model to obtain an icing prediction result corresponding to the contact network, the method further includes: Get the preset icing result; Obtaining an error value according to a difference between the preset icing result and the icing prediction result; The generative adversarial network and the preset icing prediction model are adjusted according to the error value.

8. A processor, characterized in that: The method is configured to execute the method for predicting catenary icing according to any one of claims 1 to 7.

9. A device for predicting catenary icing, characterized in that: include: A data acquisition module, used to acquire meteorological data of the area where the contact network is located, operation data of the contact network, spatial information of the area where the contact network is located, and data collection time information of the contact network; A physical data determination module, used to determine the physical data corresponding to the contact network according to the meteorological data and the operation data, wherein the physical data includes temperature gradient, heat conduction rate and water vapor content change rate; An icing prediction result determination module is used to input the temperature gradient, the heat conduction rate, the water vapor content change rate, the meteorological data, the operation data, the spatial information and the data collection time information into a preset icing prediction model to obtain an icing prediction result corresponding to the contact network.

10. A machine-readable storage medium, characterized in that: The machine-readable storage medium stores instructions, and the instructions are used to enable a machine to execute the method for predicting catenary icing according to any one of claims 1 to 7.

Images