Method for predicting temperature rise of power transmission channel under action of forest fire based on multi-scale experiment

Abstract

The invention belongs to the technical field of operation and maintenance of overhead transmission lines, and particularly relates to a method for predicting temperature rise of a transmission channel under the action of forest fire based on a multi-scale experiment, comprising the following steps: collecting forest fire data of a target area; based on the forest fire data of the target area, utilizing a pre-established temperature prediction model to predict a temperature field corresponding to the power transmission channel of the target area; performing statistical analysis on the temperature field corresponding to the power transmission channel of the target area to obtain temperature rise change of the power transmission channel of the target area; the temperature prediction model is constructed based on coupling of small-scale laboratory data and large-scale field experiment data. According to the technical scheme provided by the invention, an efficient and accurate temperature rise prediction method is provided for operation and maintenance of the electric power system and forest fire risk management, so that increasingly severe forest fire threats are dealt with, and safe and stable operation of the electric power system is ensured.

Description

Technical Field

[0001] The present invention belongs to the technical field of operation and maintenance of overhead transmission lines, and particularly relates to a method for predicting the temperature rise of a transmission corridor under the action of wildfires based on multi-scale experiments. Background Art

[0002] The power system is an indispensable infrastructure in modern society, but it faces challenges from various natural disasters and extreme weather events. Among them, wildfires, as an extreme meteorological event, have become one of the important threats to the safe operation of the power system. Wildfires not only cause direct damage to power facilities, but also affect the temperature of the transmission corridor, leading to an increase in the temperature of the transmission line, and even causing power equipment failures and system collapses. Therefore, predicting the temperature rise of the transmission corridor is of great significance for ensuring the safe and stable operation of the power system.

[0003] At present, some have improved the wildfire forecasting accuracy by using empirical formulas based on the real-time monitored wildfire situation (number of fire points, vegetation type, and precipitation on the forecast day) on the starting date. However, this method does not consider factors such as terrain and wind direction, which may lead to certain limitations in the prediction accuracy. There are also methods that monitor fire points, terrain, and meteorological data through equipment such as remote sensing satellites, unmanned aerial vehicles / helicopters, and calculate the wildfire development trend vector map using the Rothermel model and the Huygens model. However, this method does not consider the influencing factors at different scales.

[0004] In summary, the current prediction methods for the temperature rise of the transmission corridor under the action of wildfires mainly focus on theoretical analysis based on empirical formulas and simplified models, lacking the accuracy of comprehensively considering the influencing factors at different scales, and unable to accurately predict the comprehensive influence of various factors such as wildfire intensity, wind speed, and environmental conditions on the temperature rise of the transmission corridor. Summary of the Invention

[0005] To overcome the problems existing in the above related technologies, the present application provides a method for predicting the temperature rise of a transmission corridor under the action of wildfires based on multi-scale experiments.

[0006] According to the first aspect of the embodiments of the present application, there is provided a method for predicting the temperature rise of a transmission corridor under the action of wildfires based on multi-scale experiments, including:

[0007] Collect wildfire data of the target area;

[0008] Based on the wildfire data of the target area, use a pre-established temperature prediction model to predict the temperature field corresponding to the transmission corridor in the target area;

[0009] Determine the temperature rise change of the transmission corridor in the target area based on the temperature field corresponding to the transmission corridor in the target area;

[0010] The temperature prediction model is constructed based on the coupling of small-scale laboratory data and large-scale field experiment data.

[0011] Preferably, the establishment process of the temperature prediction model includes:

[0012] Collect the small-scale laboratory data and the large-scale field data;

[0013] Perform data processing on the small-scale laboratory data and the large-scale field experiment data in the multi-scale experimental data to obtain the processed small-scale laboratory data and the processed large-scale field data;

[0014] Extract features from the processed small-scale laboratory data to obtain the first key feature;

[0015] Extract features from the processed large-scale field data to obtain the second key feature;

[0016] Use the first key feature to train the heat conduction model to obtain the trained heat conduction model;

[0017] Use the second key feature to verify the trained heat conduction model. When the verification passes, obtain the temperature prediction model.

[0018] Preferably, the small-scale laboratory data includes: indoor wildfire intensity image data, indoor wind speed data, indoor wind direction data, temperature distribution on the indoor transmission line channel, and structural parameters of the indoor transmission line channel;

[0019] The large-scale field data includes: outdoor wildfire intensity image data, outdoor wind speed data, outdoor wind direction data, temperature distribution on the outdoor transmission line channel, and structural parameters of the outdoor transmission line channel.

[0020] Preferably, the collection of the small-scale laboratory data and the large-scale field data includes:

[0021] Simulate a wildfire scene in the laboratory and collect the small-scale laboratory data;

[0022] Simulate a wildfire scene in the field experiment site and collect the large-scale field experiment data.

[0023] Preferably, the data processing of the small-scale laboratory data and the large-scale field experiment data in the multi-scale experimental data includes:

[0024] Perform data cleaning on both the small-scale laboratory data and the large-scale field experiment data;

[0025] Both the small-scale laboratory data and the large-scale field experiment data after data cleaning are normalized to obtain the small-scale experimental data after data processing and the large-scale experimental data after data processing.

[0026] Preferably, the first key features include: the first flame height, the first fire source area, the first heat radiation flux density, the first wind speed, the first wind direction, the first temperature field, and the structural parameters of the indoor power transmission channel;

[0027] The second key features include: the second flame height, the second fire source area, the second heat radiation flux density, the second wind speed, the second wind direction, the second temperature field, and the structural parameters of the outdoor power transmission channel.

[0028] Preferably, feature extraction is performed on the small-scale laboratory data after data processing to obtain the first key features, including:

[0029] Extract the wind speed data, wind direction data, and structural parameters of the power transmission channel from the small-scale laboratory data after data processing to obtain the first wind speed, the first wind direction, and the structural parameters of the indoor power transmission channel;

[0030] Remove noise, enhance the image, and perform radiation correction on the indoor wildfire intensity image data in the small-scale laboratory data after data processing to obtain the processed indoor wildfire intensity image data;

[0031] Use an object detection model to identify the fire source in the processed indoor wildfire intensity image data to obtain the first flame height and the first fire source area;

[0032] Based on the indoor wildfire intensity image data, determine the first heat radiation flux density corresponding to the indoor wildfire intensity image data according to the radiation standard;

[0033] Based on the temperature distribution on the indoor power transmission channel in the small-scale laboratory data after data processing, use a geostatistical model to generate the first temperature field.

[0034] Preferably, feature extraction is performed on the large-scale field data after data processing to obtain the second key features, including:

[0035] Extract the wind speed data, wind direction data, and structural parameters of the power transmission channel from the large-scale field data after data processing to obtain the second wind speed, the second wind direction, and the structural parameters of the outdoor power transmission channel;

[0036] Remove noise, enhance the image, and perform radiation correction on the outdoor wildfire intensity image data in the large-scale field data after data processing to obtain the processed outdoor wildfire intensity image data;

[0037] Using the object detection model, identify the fire source from the processed wildfire intensity image data, and obtain the second flame height and the second fire source area;

[0038] Based on the wildfire intensity image data, determine the second heat radiation flux density corresponding to the wildfire intensity image data according to the radiation standard;

[0039] Based on the temperature distribution on the wild transmission line channel in the large-scale wild data after data processing, use the geostatistical model to generate the second temperature field.

[0040] Preferably, the training of the heat conduction model using the first key feature to obtain the trained heat conduction model includes:

[0041] Using the key features other than the first temperature field in the first key feature as the input layer training samples of the heat conduction model, and using the first temperature field as the output layer training samples of the heat conduction model to train the heat conduction model, so as to obtain the trained heat conduction model.

[0042] Preferably, the verification of the trained heat conduction model using the second key feature, when the verification passes, obtain the temperature prediction model, including:

[0043] Using the key features other than the second temperature field in the first key feature as the input of the trained heat conduction model to obtain the predicted temperature field;

[0044] Based on the predicted temperature field and the second temperature field, determine the accuracy of the predicted temperature field. If the accuracy reaches the preset threshold, the trained heat conduction model is the temperature prediction model; if the accuracy does not reach the preset threshold, re-collect the small-scale laboratory data and re-obtain the first key feature based on the small-scale laboratory data, and use the re-obtained first key feature to train the heat conduction model until the accuracy of the predicted temperature field reaches the preset threshold.

[0045] Preferably, the wildfire data of the target area includes:

[0046] The wildfire intensity image data of the target area, the wind speed data of the target area, the wind direction data of the target area, and the structural parameters of the transmission line channel in the target area.

[0047] Preferably, based on the wildfire data of the target area, use the pre-established temperature prediction model to predict the temperature rise change of the transmission line channel in the target area, including:

[0048] Perform data processing on the wildfire data of the target area to obtain the wildfire data of the target area after data processing;

[0049] Extract the key features of the wildfire data in the target area after the data processing to obtain the target key features;

[0050] Use the target key features as the input of the temperature prediction model, and output the temperature field corresponding to the transmission channel in the target area.

[0051] Preferably, the data processing of the wildfire data in the target area to obtain the wildfire data in the target area after data processing includes:

[0052] Clean the wildfire data in the target area;

[0053] Normalize all the wildfire data in the target area after data cleaning to obtain the wildfire data in the target area after data processing.

[0054] Preferably, the target key features include:

[0055] The first flame height, the first fire source area, the first heat radiation flux density, the first wind speed, the first wind direction, and the structural parameters of the transmission channel in the target area.

[0056] Preferably, the feature extraction of the wildfire data in the target area after the data processing to obtain the target key features includes:

[0057] Extract the wind speed data, wind direction data, and structural parameters of the transmission channel from the wildfire data in the target area after the data processing to obtain the first wind speed, the first wind direction, and the structural parameters of the transmission channel in the target area;

[0058] Remove noise, enhance the image, and perform radiation correction on the wildfire intensity image data in the target area in the small-scale laboratory data after the data processing to obtain the processed wildfire intensity image data in the target area;

[0059] Use the target detection model to identify the fire source in the processed wildfire intensity image data in the target area to obtain the first flame height and the first fire source area;

[0060] Based on the wildfire intensity image data in the target area, determine the first heat radiation flux density corresponding to the wildfire intensity image data in the target area according to the radiation standard.

[0061] According to the second aspect of the embodiments of the present application, a device for predicting the temperature rise of a transmission channel under the action of a wildfire based on multi-scale experiments is provided, including:

[0062] An acquisition unit for acquiring wildfire data in the target area;

[0063] A prediction unit, configured to predict a temperature field corresponding to a power transmission channel in a target area by using a pre-established temperature prediction model based on wildfire data in the target area;

[0064] A determination unit, configured to determine a temperature rise change of the power transmission channel in the target area based on the temperature field corresponding to the power transmission channel in the target area;

[0065] The pre-established temperature prediction model is constructed with laboratory data as small-scale laboratory data and verified with experimental data as large-scale field experimental data.

[0066] According to a third aspect of the embodiments of the present application, there is provided a computer device, including: one or more processors;

[0067] The processor is configured to store one or more programs;

[0068] When the one or more programs are executed by the one or more processors, the method for predicting the temperature rise of a power transmission channel under the action of a wildfire based on multi-scale experiments is implemented.

[0069] According to a fourth aspect of the embodiments of the present application, there is provided a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed, the method for predicting the temperature rise of a power transmission channel under the action of a wildfire based on multi-scale experiments is implemented.

[0070] The present invention has the following beneficial effects:

[0071] The present invention provides a method for predicting the temperature rise of a power transmission channel under the action of a wildfire based on multi-scale experiments, including: collecting wildfire data in a target area; predicting a temperature field corresponding to the power transmission channel in the target area by using a pre-established temperature prediction model based on the wildfire data in the target area; performing statistical analysis on the temperature field corresponding to the power transmission channel in the target area to obtain a temperature rise change of the power transmission channel in the target area; the pre-established temperature prediction model is constructed by using multi-scale experimental data. The present invention provides an efficient and accurate method for predicting temperature rise for power system operation and maintenance and wildfire risk management to cope with the increasingly severe wildfire threat and ensure the safe and stable operation of the power system. Description of the Drawings

[0072] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings without creative efforts.

[0073] Figure 1It is a flowchart of a method for predicting the temperature rise of a transmission channel under wildfire based on multi-scale experiments provided by an embodiment of the present invention;

[0074] Figure 2 It is a structural block diagram of a device for predicting the temperature rise of a transmission channel under wildfire based on multi-scale experiments provided by an embodiment of the present invention. Detailed implementation manners

[0075] To make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the following embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0076] Embodiment 1

[0077] The present invention provides a method for predicting the temperature rise of a transmission channel under wildfire based on multi-scale experiments. As Figure 1 shown, it includes the following steps:

[0078] Step 101: Collect wildfire data of the target area;

[0079] Step 102: Based on the wildfire data of the target area, use the pre-established temperature prediction model to predict the temperature field corresponding to the transmission channel in the target area;

[0080] Step 103: Determine the temperature rise change of the transmission channel in the target area based on the temperature field corresponding to the transmission channel in the target area;

[0081] The temperature prediction model is constructed by coupling small-scale laboratory data and large-scale field experiment data.

[0082] In some embodiments, after obtaining the temperature field corresponding to the transmission channel in the target area, the change law of the temperature rise can be captured by calculating, but not limited to, the average temperature, maximum temperature, minimum temperature, etc. at different positions, as well as the standard deviation, skewness, etc. of the temperature distribution, based on the temperature field corresponding to the transmission channel in the target area.

[0083] Furthermore, the method further includes: Step 100: Establish a temperature prediction model; Step 100 includes:

[0084] Step 1001: Collect small-scale laboratory data and large-scale field data;

[0085] Step 1002: Process the small-scale laboratory data and large-scale field experiment data in the multi-scale experiment data to obtain the processed small-scale laboratory data and the processed large-scale field data;

[0086] Step 1003: Extract features from the small-scale laboratory data after data processing to obtain the first key feature;

[0087] Step 1004: Extract features from the large-scale field data after data processing to obtain the second key feature;

[0088] Step 1005: Use the first key feature to train the heat conduction model to obtain the trained heat conduction model;

[0089] Step 1006: Use the second key feature to verify the trained heat conduction model. When the verification passes, obtain the temperature prediction model.

[0090] Through key technologies such as experimental data, multi-scale model construction, and feature extraction, the present invention proposes a comprehensive and accurate prediction method for the temperature rise of transmission channels under wildfires, which significantly improves the power system's prediction ability for wildfire risks and provides an effective means to ensure the stable operation of the power system.

[0091] Further, the small-scale laboratory data includes: indoor wildfire intensity image data, indoor wind speed data, indoor wind direction data, temperature distribution on the indoor transmission channel, and structural parameters of the indoor transmission channel;

[0092] The large-scale field data includes: outdoor wildfire intensity image data, outdoor wind speed data, outdoor wind direction data, temperature distribution on the outdoor transmission channel, and structural parameters of the outdoor transmission channel.

[0093] Traditional methods often ignore the comprehensive influence of different scale factors, resulting in incomplete prediction results. By establishing a model that can comprehensively consider small-scale and large-scale experimental data, the present invention makes the temperature rise prediction more comprehensive and accurate. This comprehensive consideration helps to better capture the influencing factors at different scales and improves the reliability of the prediction.

[0094] Further, Step 1001 includes:

[0095] Step 1001a: Simulate the wildfire scene in the laboratory and collect small-scale laboratory data;

[0096] Step 1001b: Simulate the wildfire scene in the field experimental site and collect large-scale field experimental data.

[0097] In some embodiments, after simulating the wildfire scene in the laboratory, collecting the small-scale laboratory data includes:

[0098] Wildfire scale: Use a suitable heat source to simulate the wildfire, and determine the wildfire intensity by measuring the fire source temperature and heat radiation intensity;

[0099] Wind speed and direction: Use a wind turbine array or other equipment to simulate different wind speed and direction conditions, measure and record the wind speed and direction;

[0100] Temperature distribution and channel structure: Set up multiple temperature sensors on the transmission channel, measure the temperature changes at different positions, and the measurement positions cover the entire transmission channel; and record the structural parameters of the channel in the experimental setup;

[0101] The small-scale laboratory data can be recorded in, but not limited to, the form of a data table. Each row represents an experiment, and each column includes information such as time, wildfire intensity, wind speed, temperature values at different positions, and the structural parameters of the transmission channel.

[0102] In some embodiments, after simulating the wildfire site in the field experiment site, large-scale field experiment data is collected, including:

[0103] Wildfire intensity: Use remote sensing equipment such as satellites or drones to obtain high-resolution images and infrared image data of the wildfire site;

[0104] Wind speed and direction: Use equipment such as weather stations to measure the on-site wind speed and direction data;

[0105] Temperature distribution and channel structure: Set up multiple temperature sensors on the transmission channel, measure the temperature changes at different positions, and the measurement positions cover the entire transmission channel; at the same time, use on-site measurement methods to record the structural parameters of the channel, such as tower height, conductor spacing, etc.;

[0106] The large-scale experimental data can be recorded in, but not limited to, the form of a data table. Each row represents an experiment, and each column includes information such as time, wildfire intensity, wind speed, temperature distribution, and channel structure. The large-scale field experiment data is closer to the actual environment and covers more complex factors.

[0107] Further, step 1002 includes:

[0108] Step 1002a: Perform data cleaning on both the small-scale laboratory data and the large-scale field experiment data;

[0109] In some embodiments, performing data cleaning includes: detecting and processing outliers, missing values, and error values in the data, and using statistical methods or interpolation methods to fill in the missing values and correct the error values;

[0110] Step 1002b: Perform normalization processing on the small-scale laboratory data and the large-scale field experiment data after data cleaning to obtain the processed small-scale experimental data and the processed large-scale experimental data.

[0111] In some embodiments, Z-score normalization is adopted to map data in different scale ranges to the same scale to eliminate differences between different data.

[0112] The present invention performs data cleaning and normalization on experimental data to ensure the quality and consistency of the data and further improve the reliability of the model.

[0113] Furthermore, the first key features include: the first flame height, the first fire source area, the first heat radiation flux density, the first wind speed, the first wind direction, the first temperature field, and the structural parameters of the indoor power transmission channel;

[0114] The second key features include: the second flame height, the second fire source area, the second heat radiation flux density, the second wind speed, the second wind direction, the second temperature field, and the structural parameters of the outdoor power transmission channel.

[0115] Furthermore, step 1003 includes:

[0116] Step 1003a: Extract the wind speed data, wind direction data, and the structural parameters of the power transmission channel from the small-scale laboratory data after data processing to obtain the first wind speed, the first wind direction, and the structural parameters of the indoor power transmission channel;

[0117] Step 1003b: Remove noise, enhance the image, and perform radiation correction on the indoor wildfire intensity image data in the small-scale laboratory data after data processing to obtain the processed indoor wildfire intensity image data;

[0118] Step 1003c: Use the object detection model to identify the fire source in the processed indoor wildfire intensity image data to obtain the first flame height and the first fire source area;

[0119] Step 1003d: Based on the indoor wildfire intensity image data, determine the corresponding first heat radiation flux density according to the radiation standard;

[0120] Step 1003e: Based on the temperature distribution on the indoor power transmission channel in the small-scale laboratory data after data processing, use the geostatistical model to generate the first temperature field.

[0121] Furthermore, step 1004 includes:

[0122] Step 1004a: Extract the wind speed data, wind direction data, and the structural parameters of the power transmission channel from the large-scale outdoor data after data processing to obtain the second wind speed, the second wind direction, and the structural parameters of the outdoor power transmission channel;

[0123] Step 1004b: Remove noise, enhance the image, and perform radiation correction on the wildfire intensity image data in the large-scale field data after data processing to obtain the processed wildfire intensity image data;

[0124] Step 1004c: Use the object detection model to identify the fire source in the processed wildfire intensity image data and obtain the second flame height and the second fire source area;

[0125] Step 1004d: Based on the wildfire intensity image data, determine the corresponding second heat radiation flux density of the wildfire intensity image data according to the radiation standard;

[0126] Step 1004e: Based on the temperature distribution on the wild transmission line channel in the large-scale field data after data processing, use the geostatistical model to generate the second temperature field.

[0127] In the present invention, noise removal, image enhancement, and radiation correction are performed on the indoor wildfire intensity image data and the outdoor wildfire intensity image data to ensure the quality of the data.

[0128] Further, step 1005 includes:

[0129] Using the key features other than the first temperature field in the first key features as the input layer training samples of the heat conduction model, and using the first temperature field as the output layer training samples of the heat conduction model to train the heat conduction model to obtain the trained heat conduction model.

[0130] In some embodiments, the parameters of the heat conduction model can be optimized by, but not limited to, using a loss function. The loss function uses the mean square error and minimizes the difference between the predicted value and the actual value. Then, the large-scale field experimental data is used to update and improve the model.

[0131] Further, step 1006 includes:

[0132] Step 1006a: Use the key features other than the second temperature field in the first key features as the input of the trained heat conduction model to obtain the predicted temperature field;

[0133] Step 1006b: Based on the predicted temperature field and the second temperature field, determine the accuracy of the predicted temperature field. If the accuracy reaches the preset threshold, the trained heat conduction model is the temperature prediction model; if the accuracy does not reach the preset threshold, re-collect the small-scale laboratory data and re-obtain the first key features based on the small-scale laboratory data, and use the re-obtained first key features to train the heat conduction model until the accuracy of the predicted temperature field reaches the preset threshold.

[0134] The present invention validates the temperature prediction model by using large-scale field experiment data, improving the model prediction accuracy.

[0135] Furthermore, the wildfire data of the target area includes:

[0136] The wildfire intensity image data of the target area, the wind speed data of the target area, the wind direction data of the target area, and the structural parameters of the power transmission channels in the target area.

[0137] Furthermore, step 102 includes:

[0138] Step 1021: Process the wildfire data of the target area to obtain the processed wildfire data of the target area;

[0139] Step 1022: Extract features from the processed wildfire data of the target area to obtain the target key features;

[0140] Step 1023: Use the target key features as the input of the temperature prediction model and output the temperature field corresponding to the power transmission channels in the target area.

[0141] By accurately predicting the temperature rise of the power transmission channels under wildfires, the present invention can provide real-time early warnings and support for the operation and maintenance decision-making of the power system, help operators take appropriate measures, and ensure the stable operation of the power system. At the same time, it promotes the improvement of the disaster resistance ability of the power system in extreme weather events such as wildfires, and enhances the reliability and resilience of power supply.

[0142] The prediction results can reflect the temperature change of the power transmission channels under wildfires. In practical applications, it can be presented in a visualized form such as, but not limited to, a temperature distribution map, curve, or report, which can help users better understand the impact of wildfires on the power transmission channels.

[0143] Furthermore, step 1021 includes:

[0144] Step 1021a: Clean the wildfire data of the target area;

[0145] Step 1021b: Normalize the wildfire data of the target area after data cleaning to obtain the processed wildfire data of the target area.

[0146] Furthermore, the target key features include:

[0147] The first flame height, the first fire source area, the first heat radiation flux density, the first wind speed, the first wind direction, and the structural parameters of the power transmission channels in the target area.

[0148] Furthermore, step 1022 includes:

[0149] Step 1022a: Extract the wind speed data, wind direction data, and the structural parameters of the transmission channel from the wildfire data of the target area after data processing, to obtain the first wind speed, the first wind direction, and the structural parameters of the transmission channel in the target area;

[0150] Step 1022b: Remove noise, enhance the image, and perform radiation correction on the wildfire intensity image data of the target area in the small-scale laboratory data after data processing, to obtain the processed wildfire intensity image data of the target area;

[0151] Step 1022c: Use the target detection model to identify the fire source in the processed wildfire intensity image data of the target area, and obtain the first flame height and the first fire source area;

[0152] Step 1022d: Based on the wildfire intensity image data of the target area, determine the first heat radiation flux density corresponding to the wildfire intensity image data of the target area according to the radiation standard.

[0153] The present invention provides a method for predicting the temperature rise of a transmission channel under the action of a wildfire based on multi-scale experiments. By collecting the wildfire data of the target area, using the pre-established temperature prediction model based on the wildfire data of the target area, predicting the temperature field corresponding to the transmission channel in the target area, and performing statistical analysis on the temperature field corresponding to the transmission channel in the target area, the temperature rise change of the transmission channel in the target area is obtained. The pre-established temperature prediction model is constructed using multi-scale experimental data, providing an efficient and accurate temperature rise prediction method for power system operation and maintenance and wildfire risk management, to cope with the increasingly severe wildfire threat and ensure the safe and stable operation of the power system.

[0154] Embodiment 2

[0155] The present invention also provides a device for predicting the temperature rise of a transmission channel under the action of a wildfire based on multi-scale experiments, as Figure 2 shown, including:

[0156] A collection unit, configured to collect the wildfire data of the target area;

[0157] A prediction unit, configured to predict the temperature field corresponding to the transmission channel in the target area based on the wildfire data of the target area by using the pre-established temperature prediction model;

[0158] A determination unit, configured to determine the temperature rise change of the transmission channel in the target area based on the temperature field corresponding to the transmission channel in the target area;

[0159] The pre-established temperature prediction model is constructed using the laboratory data as small-scale laboratory data and verified using the experimental data as large-scale field experimental data.

[0160] Furthermore, the device further includes: a building unit configured to build a temperature prediction model; the building unit includes:

[0161] a collection module configured to collect small-scale laboratory data and large-scale field data;

[0162] a first acquisition module configured to process the small-scale laboratory data and the large-scale field experimental data in the multi-scale experimental data to obtain the processed small-scale laboratory data and the processed large-scale field data;

[0163] a second acquisition module configured to extract features from the processed small-scale laboratory data to obtain first key features;

[0164] a third acquisition module configured to extract features from the processed large-scale field data to obtain second key features;

[0165] a fourth acquisition module configured to train a heat conduction model using the first key features to obtain a trained heat conduction model;

[0166] a fifth acquisition module configured to verify the trained heat conduction model using the second key features, and when the verification passes, obtain a temperature prediction model.

[0167] Furthermore, the small-scale laboratory data includes: indoor wildfire intensity image data, indoor wind speed data, indoor wind direction data, temperature distribution on the indoor power transmission channel, and structural parameters of the indoor power transmission channel;

[0168] The large-scale field data includes: outdoor wildfire intensity image data, outdoor wind speed data, outdoor wind direction data, temperature distribution on the outdoor power transmission channel, and structural parameters of the outdoor power transmission channel.

[0169] Furthermore, the collection module is specifically configured to:

[0170] simulate a wildfire site in the laboratory and collect small-scale laboratory data;

[0171] simulate a wildfire site in the field experimental site and collect large-scale field experimental data.

[0172] Furthermore, the first acquisition module is specifically configured to:

[0173] perform data cleaning on both the small-scale laboratory data and the large-scale field experimental data;

[0174] perform normalization processing on the small-scale laboratory data and the large-scale field experimental data after data cleaning to obtain the processed small-scale experimental data and the processed large-scale experimental data.

[0175] Further, the first key features include: the first flame height, the first fire source area, the first heat radiation flux density, the first wind speed, the first wind direction, the first temperature field, and the structural parameters of the indoor power transmission channel;

[0176] The second key features include: the second flame height, the second fire source area, the second heat radiation flux density, the second wind speed, the second wind direction, the second temperature field, and the structural parameters of the outdoor power transmission channel.

[0177] Further, the second acquisition module is specifically configured to:

[0178] Extract the wind speed data, wind direction data, and the structural parameters of the power transmission channel from the small-scale laboratory data after data processing to obtain the first wind speed, the first wind direction, and the structural parameters of the indoor power transmission channel;

[0179] Remove noise, enhance the image, and perform radiation correction on the indoor wildfire intensity image data in the small-scale laboratory data after data processing to obtain the processed indoor wildfire intensity image data;

[0180] Use the object detection model to identify the fire source in the processed indoor wildfire intensity image data to obtain the first flame height and the first fire source area;

[0181] Based on the indoor wildfire intensity image data, determine the first heat radiation flux density corresponding to the indoor wildfire intensity image data according to the radiation standard;

[0182] Based on the temperature distribution on the indoor power transmission channel in the small-scale laboratory data after data processing, use the geostatistical model to generate the first temperature field.

[0183] Further, the third acquisition module is specifically configured to:

[0184] Extract the wind speed data, wind direction data, and the structural parameters of the power transmission channel from the large-scale outdoor data after data processing to obtain the second wind speed, the second wind direction, and the structural parameters of the outdoor power transmission channel;

[0185] Remove noise, enhance the image, and perform radiation correction on the outdoor wildfire intensity image data in the large-scale outdoor data after data processing to obtain the processed outdoor wildfire intensity image data;

[0186] Use the object detection model to identify the fire source in the processed outdoor wildfire intensity image data to obtain the second flame height and the second fire source area;

[0187] Based on the outdoor wildfire intensity image data, determine the second heat radiation flux density corresponding to the outdoor wildfire intensity image data according to the radiation standard;

[0188] Based on the temperature distribution on the field power transmission channels in the large-scale field data after data processing, a geostatistical model is used to generate a second temperature field.

[0189] Furthermore, the fourth acquisition module is specifically used for:

[0190] Using the key features in the first key features except the first temperature field as the input layer training samples of the heat conduction model, and using the first temperature field as the output layer training samples of the heat conduction model to train the heat conduction model, so as to obtain the trained heat conduction model.

[0191] Furthermore, the fifth acquisition module is specifically used for:

[0192] Using the key features in the first key features except the second temperature field as the input of the trained heat conduction model to obtain a predicted temperature field;

[0193] Based on the predicted temperature field and the second temperature field, determine the accuracy of the predicted temperature field. If the accuracy reaches the preset threshold, the trained heat conduction model is the temperature prediction model; if the accuracy does not reach the preset threshold, re-collect the small-scale laboratory data and re-obtain the first key features based on the small-scale laboratory data, and use the re-obtained first key features to train the heat conduction model until the accuracy of the predicted temperature field reaches the preset threshold.

[0194] Furthermore, the wildfire data of the target area includes:

[0195] The wildfire intensity image data of the target area, the wind speed data of the target area, the wind direction data of the target area, and the structural parameters of the power transmission channels in the target area.

[0196] Furthermore, the prediction unit includes:

[0197] The sixth acquisition module is used to perform data processing on the wildfire data of the target area to obtain the wildfire data of the target area after data processing;

[0198] The seventh acquisition module is used to perform feature extraction on the wildfire data of the target area after data processing to obtain target key features;

[0199] The eighth acquisition module is used to use the target key features as the input of the temperature prediction model and output the temperature field corresponding to the power transmission channels in the target area.

[0200] Furthermore, the sixth acquisition module is specifically used for:

[0201] Perform data cleaning on the wildfire data of the target area;

[0202] Normalize the wildfire data of the target area after data cleaning to obtain the wildfire data of the target area after data processing.

[0203] Furthermore, the target key features include:

[0204] The first flame height, the first fire source area, the first heat radiation flux density, the first wind speed, the first wind direction, and the structural parameters of the power transmission channel in the target area.

[0205] Furthermore, the seventh acquisition module is specifically used for:

[0206] Extract the wind speed data, wind direction data, and the structural parameters of the power transmission channel from the wildfire data of the target area after data processing to obtain the first wind speed, the first wind direction, and the structural parameters of the power transmission channel in the target area;

[0207] Remove noise, enhance the image, and perform radiation correction on the wildfire intensity image data of the target area in the small-scale laboratory data after data processing to obtain the processed wildfire intensity image data of the target area;

[0208] Use the target detection model to identify the fire source in the processed wildfire intensity image data of the target area to obtain the first flame height and the first fire source area;

[0209] Based on the wildfire intensity image data of the target area, determine the first heat radiation flux density corresponding to the wildfire intensity image data of the target area according to the radiation standard.

[0210] It can be understood that the above-provided device embodiments correspond to the above method embodiments, and the corresponding specific contents can be referred to each other, and will not be elaborated here.

[0211] It can be understood that the same or similar parts in the above embodiments can be referred to each other, and the content not detailed in some embodiments can be seen in the same or similar content of other embodiments.

[0212] Embodiment III

[0213] Based on the same inventive concept, the present invention also provides a computer device, which includes a processor and a memory. The memory is used to store a computer program, and the computer program includes program instructions. The processor is used to execute the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, and is suitable for implementing one or more instructions. Specifically, it is suitable for loading and executing one or more instructions in the computer storage medium to implement the corresponding method flow or corresponding function, so as to implement the steps of a method for predicting the temperature rise of a transmission channel under wildfire based on multi-scale experiments in the above embodiments.

[0214] Embodiment 4

[0215] Based on the same inventive concept, the present invention also provides a storage medium, specifically a computer-readable storage medium (Memory). The computer-readable storage medium is a memory device in a computer device and is used to store programs and data. It can be understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and, of course, the extended storage medium supported by the computer device. The computer-readable storage medium provides a storage space, and this storage space stores the operating system of the terminal. And, one or more instructions suitable for being loaded and executed by the processor are also stored in this storage space. These instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. One or more instructions stored in the computer-readable storage medium can be loaded and executed by the processor to implement the steps of a method for predicting the temperature rise of a transmission channel under wildfire based on multi-scale experiments in the above embodiments.

[0216] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0217] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices produce means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0218] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including instruction means that implement the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0219] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0220] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: still modifications or equivalent replacements can be made to the specific embodiments of the present invention, and any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the protection scope of the claims of the present invention.

Claims

1. A method for predicting the temperature rise of a transmission channel under wildfire based on multi-scale experiments, characterized in that, Including: Collecting wildfire data of the target area; Based on the wildfire data of the target area, using a pre-established temperature prediction model to predict the temperature field corresponding to the transmission channel in the target area; Determining the temperature rise change of the transmission channel in the target area based on the temperature field corresponding to the transmission channel in the target area; The temperature prediction model is constructed by coupling small-scale laboratory data and large-scale field experiment data.

2. The method according to claim 1, characterized in that, The establishment process of the temperature prediction model includes: Collecting the small-scale laboratory data and the large-scale field data; Performing data processing on the small-scale laboratory data and the large-scale field experiment data in the multi-scale experimental data to obtain the processed small-scale laboratory data and the processed large-scale field data; Performing feature extraction on the processed small-scale laboratory data to obtain the first key features; Performing feature extraction on the processed large-scale field data to obtain the second key features; Using the first key features to train the heat conduction model to obtain the trained heat conduction model; Using the second key features to verify the trained heat conduction model, and when the verification passes, obtaining the temperature prediction model.

3. The method according to claim 2, characterized in that, The small-scale laboratory data includes: indoor wildfire intensity image data, indoor wind speed data, indoor wind direction data, temperature distribution on the indoor transmission channel, and structural parameters of the indoor transmission channel; The large-scale field data includes: outdoor wildfire intensity image data, outdoor wind speed data, outdoor wind direction data, temperature distribution on the outdoor transmission channel, and structural parameters of the outdoor transmission channel.

4. The method according to claim 2, characterized in that, The collection of the small-scale laboratory data and the large-scale field data includes: Simulating a wildfire scene in the laboratory and collecting the small-scale laboratory data; Simulating a wildfire scene in the field experiment site and collecting the large-scale field experiment data.

5. The method according to claim 2, characterized in that, The data processing of the small-scale laboratory data and the large-scale field experiment data in the multi-scale experimental data includes: Performing data cleaning on both the small-scale laboratory data and the large-scale field experiment data; Performing normalization processing on the small-scale laboratory data and the large-scale field experiment data after data cleaning to obtain the processed small-scale experimental data and the processed large-scale experimental data.

6. The method according to claim 3, wherein The first key features include: the first flame height, the first fire source area, the first heat radiation flux density, the first wind speed, the first wind direction, the first temperature field, and the structural parameters of the indoor transmission channel; The second key features include: the second flame height, the second fire source area, the second heat radiation flux density, the second wind speed, the second wind direction, the second temperature field, and the structural parameters of the outdoor transmission channel.

7. The method according to claim 6, wherein The feature extraction of the processed small-scale laboratory data to obtain the first key features includes: Extracting the wind speed data, wind direction data, and structural parameters of the transmission channel from the processed small-scale laboratory data to obtain the first wind speed, the first wind direction, and the structural parameters of the indoor transmission channel; Perform noise removal, image enhancement, and radiometric correction on the indoor wildfire intensity image data in the small-scale laboratory data after data processing to obtain the processed indoor wildfire intensity image data; Use the object detection model to identify the fire source in the processed indoor wildfire intensity image data and obtain the first flame height and the first fire source area; Based on the indoor wildfire intensity image data, determine the first heat radiation flux density corresponding to the indoor wildfire intensity image data according to the radiation standard; Based on the temperature distribution on the indoor transmission channel in the small-scale laboratory data after data processing, use the geostatistical model to generate the first temperature field.

8. The method according to claim 6, wherein Perform feature extraction on the large-scale field data after data processing to obtain the second key features, including: Extract the wind speed data, wind direction data, and the structural parameters of the transmission channel in the large-scale field data after data processing to obtain the second wind speed, the second wind direction, and the structural parameters of the outdoor transmission channel; Perform noise removal, image enhancement, and radiometric correction on the outdoor wildfire intensity image data in the large-scale field data after data processing to obtain the processed outdoor wildfire intensity image data; Use the object detection model to identify the fire source in the processed outdoor wildfire intensity image data and obtain the second flame height and the second fire source area; Based on the outdoor wildfire intensity image data, determine the second heat radiation flux density corresponding to the outdoor wildfire intensity image data according to the radiation standard; Based on the temperature distribution on the outdoor transmission channel in the large-scale field data after data processing, use the geostatistical model to generate the second temperature field.

9. The method according to claim 6, wherein Train the heat conduction model using the first key features to obtain the trained heat conduction model, including: Use the key features in the first key features except the first temperature field as the input layer training samples of the heat conduction model, and use the first temperature field as the output layer training sample of the heat conduction model to train the heat conduction model to obtain the trained heat conduction model.

10. The method according to claim 6, characterized in that, Verify the trained heat conduction model using the second key features. When the verification passes, obtain the temperature prediction model, including: Use the key features in the first key features except the second temperature field as the input of the trained heat conduction model to obtain the predicted temperature field; Based on the predicted temperature field and the second temperature field, determine the accuracy of the predicted temperature field. If the accuracy reaches the preset threshold, the trained heat conduction model is the temperature prediction model; if the accuracy does not reach the preset threshold, re-collect the small-scale laboratory data and re-obtain the first key features based on the small-scale laboratory data, and use the re-obtained first key features to train the heat conduction model until the accuracy of the predicted temperature field reaches the preset threshold.

11. The method according to claim 1, wherein The wildfire data of the target area includes: The wildfire intensity image data of the target area, the wind speed data of the target area, the wind direction data of the target area, and the structural parameters of the transmission channel of the target area.

12. The method according to claim 11, wherein Based on the wildfire data of the target area, using the pre-established temperature prediction model to predict the temperature rise change of the transmission channel in the target area, including: Performing data processing on the wildfire data of the target area to obtain the wildfire data of the target area after data processing; Performing feature extraction on the wildfire data of the target area after data processing to obtain target key features; Using the target key features as the input of the temperature prediction model and outputting the temperature field corresponding to the transmission channel in the target area.

13. The method according to claim 12, wherein The performing data processing on the wildfire data of the target area to obtain the wildfire data of the target area after data processing includes: Performing data cleaning on the wildfire data of the target area; Performing normalization processing on the wildfire data of the target area after data cleaning to obtain the wildfire data of the target area after data processing.

14. The method according to claim 12, wherein The target key features include: The first flame height, the first fire source area, the first heat radiation flux density, the first wind speed, the first wind direction, and the structural parameters of the transmission channel in the target area.

15. The method according to claim 14, characterized in that, The performing feature extraction on the wildfire data of the target area after data processing to obtain target key features includes: Extracting the wind speed data, wind direction data, and structural parameters of the transmission channel from the wildfire data of the target area after data processing to obtain the first wind speed, the first wind direction, and the structural parameters of the transmission channel in the target area; Performing noise removal, image enhancement, and radiation correction on the wildfire intensity image data of the target area in the small-scale laboratory data after data processing to obtain the processed wildfire intensity image data of the target area; Using a target detection model to perform fire source identification on the processed wildfire intensity image data of the target area to obtain the first flame height and the first fire source area; Based on the wildfire intensity image data of the target area, determining the first heat radiation flux density corresponding to the wildfire intensity image data of the target area according to the radiation standard.

16. A temperature rise prediction device for transmission channels under wildfire action based on multi-scale experiments, characterized in that, Including: A collection unit for collecting wildfire data of the target area; A prediction unit for predicting the temperature field corresponding to the transmission channel in the target area based on the wildfire data of the target area by using the pre-established temperature prediction model; A determination unit for determining the temperature rise change of the transmission channel in the target area based on the temperature field corresponding to the transmission channel in the target area; The pre-established temperature prediction model is constructed with laboratory data as small-scale laboratory data and verified with experimental data as large-scale field experimental data.

17. A computer device, characterized in that, Including: One or more processors; The processor is used to store one or more programs; When the one or more programs are executed by the one or more processors, the method for predicting the temperature rise of a transmission channel under the action of a wildfire based on multi-scale experiments as described in any one of claims 1 to 15 is implemented.

18. A computer-readable storage medium, characterized in that, There is a computer program stored thereon, and when the computer program is executed, the method for predicting the temperature rise of a transmission channel under the action of a wildfire based on multi-scale experiments as described in any one of claims 1 to 15 is implemented.

Images