A lightning protection monitoring method and system

Abstract

The application provides a lightning protection monitoring method and system, the method comprises the following steps: obtaining past atmospheric weighted temperature data set, past thundercloud observation data set and past radar echo data set to train and construct an initial thundercloud prediction neural network, and then obtaining a final thundercloud prediction neural network; obtaining a plurality of predicted thundercloud maps based on the final thundercloud prediction neural network, converting the predicted thundercloud maps into thundercloud grid maps, and obtaining a plurality of thunderstorm grid areas in the thundercloud grid maps; obtaining a predicted thunderstorm moving path based on the thunderstorm grid areas in the thundercloud grid maps in adjacent time frames to perform lightning protection. The final thundercloud prediction neural network is used for preliminary thunderstorm prediction, the predicted thunderstorm moving path is obtained through the predicted thundercloud map, the accurate prediction result of the position and time of the thunderstorm is obtained, and then the lightning protection accuracy and the lightning protection effect are improved through the combination with passive lightning protection measures.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data prediction, in particular to a lightning protection monitoring method and system. BACKGROUND

[0002] Lightning is a discharge phenomenon accompanied by lightning and thunder, and its generation process often occurs inside cumulonimbus under strong convective weather conditions. Lightning is a natural phenomenon with great destructive power and suddenness, which brings great challenges and risks to the safe and stable operation of power systems.

[0003] For power systems, lightning strikes or induction into the power transmission network will produce transient overvoltage, which is likely to cause insulation breakdown, equipment damage, and even cause large-scale power outages.

[0004] Traditional lightning protection measures can protect electrical equipment and power transmission lines from lightning damage to some extent, but they are basically passive lightning protection measures, such as lightning rods, lightning arresters, and grounding systems. Although the passive protection method can absorb and disperse the energy of lightning, it cannot predict the specific occurrence position and time of lightning in advance, and it is difficult to make precise protection. SUMMARY

[0005] In view of the deficiencies of the prior art, the purpose of the present application is to provide a lightning protection monitoring method and system, which aims to solve the technical problems that the prior art uses passive protection measures such as lightning rods, lightning arresters, and grounding systems for lightning protection, which cannot predict the specific occurrence position and time of lightning in advance, and it is difficult to make precise protection.

[0006] In order to achieve the above purpose, in a first aspect, the present application provides a lightning protection monitoring method, comprising the following steps:

[0007] Obtain a past atmospheric weighted temperature data set, a past thundercloud observation data set, and a past radar echo data set corresponding to a prediction area;

[0008] Construct an initial thundercloud prediction neural network, and train the initial thundercloud prediction neural network into a final thundercloud prediction neural network based on the past atmospheric weighted temperature data set, the past thundercloud observation data set, and the past radar echo data set;

[0009] Obtain a plurality of predicted thundercloud maps under a continuous time frame corresponding to the prediction area based on the final thundercloud prediction neural network, convert the predicted thundercloud maps into thundercloud grid maps, and obtain a plurality of thunderstorm grid areas in the thundercloud grid maps;

[0010] Obtain a predicted thunderstorm movement path based on the thunderstorm grid areas in the thundercloud grid maps under adjacent time frames, and perform lightning protection based on the predicted thunderstorm movement path.

[0011] Compared with the prior art, the present application has the beneficial effects that: the final thundercloud prediction neural network is obtained through the past atmospheric weighted temperature data set, the past thundercloud observation data set and the past radar echo data set, and a plurality of prediction thundercloud maps are obtained based on the final thundercloud prediction neural network, thereby completing preliminary thunderstorm prediction of the prediction area, i.e., the specific occurrence position and time of lightning are predicted in advance, and the lightning protection accuracy is improved; the prediction thunderstorm moving path is obtained according to the prediction thundercloud map, thereby completing more detailed position and time prediction results of the thunderstorm, and the lightning protection accuracy and effect are further improved through the combination with passive lightning protection measures; the past atmospheric weighted temperature data set with high correlation with the generation of thunderstorms is introduced based on the past thundercloud observation data set and the past radar echo data set, thereby effectively improving the prediction accuracy of the final thundercloud prediction neural network and improving the acquisition accuracy of the prediction thundercloud map.

[0012] Further, the past atmospheric weighted temperature data set, the past thundercloud observation data set and the past radar echo data set each include past atmospheric weighted temperatures, past thundercloud observation maps and past radar echo maps in a plurality of continuous time frames, and the step of obtaining the past atmospheric weighted temperature data set corresponding to the prediction area includes:

[0013] obtaining the relative humidity and the saturated water vapor pressure of different atmospheric layers in a continuous time frame corresponding to the prediction area;

[0014] obtaining the average water vapor pressure of the corresponding atmospheric layer based on the relative humidity and the saturated water vapor pressure in the same time frame;

[0015] obtaining the past atmospheric weighted temperature through a plurality of average water vapor pressures, and combining a plurality of past atmospheric weighted temperatures in continuous time frames into a past atmospheric weighted temperature data set.

[0016] Further, the formula for obtaining the average water vapor pressure is:

[0017] ,

[0018] wherein, represents the average water vapor pressure of the i-th atmospheric layer, represents the relative humidity of the i-th atmospheric layer, represents the saturated water vapor pressure of the i-th atmospheric layer;

[0019] the formula for obtaining the past atmospheric weighted temperature is:

[0020] ,

[0021] wherein, represents the past atmospheric weighted temperature at the jth time frame, represents the average temperature of the ith atmospheric layer, represents the thickness of the ith atmospheric layer.

[0022] Further, the initial thundercloud prediction neural network comprises a thundercloud prediction module, a return prediction module and a temperature prediction module, and the step of training the initial thundercloud prediction neural network into a final thundercloud prediction neural network based on the past atmospheric weighted temperature dataset, the past thundercloud observation dataset and the past radar return dataset comprises:

[0023] obtaining a predicted radar return picture set through the past radar return dataset and the return prediction module;

[0024] obtaining a predicted atmospheric weighted temperature set through the past atmospheric weighted temperature dataset and the temperature prediction module;

[0025] obtaining a predicted thundercloud picture set through the past thundercloud observation dataset, the predicted radar return picture set, the predicted atmospheric weighted temperature set and the thundercloud prediction module;

[0026] constructing a loss function through the predicted thundercloud picture set, a real thundercloud observation picture set, the predicted atmospheric weighted temperature set, a real atmospheric weighted temperature set, the predicted radar return picture set and a real radar return picture set, and correcting the thundercloud prediction module, the return prediction module and the temperature prediction module based on the loss function to obtain a final thundercloud prediction neural network.

[0027] Further, the formula for obtaining the predicted radar return picture set is:

[0028] ,

[0029] wherein, represents the predicted radar return picture set from the 1st future frame to the ath future frame at time t, represents the past radar return picture set from the bth past frame to the 0th current frame at time t, represents the return prediction module;

[0030] the formula for obtaining the predicted atmospheric weighted temperature set is:

[0031] ,

[0032] wherein, represents the predicted atmospheric weighted temperature set from the 1st future frame to the ath future frame at time t, represents the past atmospheric weighted temperature set from the bth past frame to the 0th current frame at time t, represents the temperature prediction module;

[0033] The acquisition formula of the predicted thundercloud set is:

[0034]

[0035] wherein, represents the predicted thundercloud set from the future 1 frame to the future a frame at the time t, represents the set of past thundercloud observation maps from the past b frame to the current 0 frame at the time t, represents the thundercloud prediction module;

[0036] The formula of the loss function is:

[0037]

[0038] wherein, represents the real thundercloud observation map set from the future 1 frame to the future a frame at the time t, represents the real radar echo map set from the future 1 frame to the future a frame at the time t, represents the real atmospheric weighted temperature set from the future 1 frame to the future a frame at the time t, represents the loss function, both represent the weight coefficient, respectively represent the module parameters of the echo prediction module, the temperature prediction module and the thundercloud prediction module.

[0039] Further, the thundercloud grid map includes a plurality of grid points with the same area, and the step of acquiring a plurality of thunderstorm grid areas in the thundercloud grid map includes:

[0040] determining whether the radar echo intensity of each grid point is higher than the intensity threshold value, and selecting the grid point corresponding to the radar echo intensity higher than the intensity threshold value as a thunderstorm grid point;

[0041] determining whether the thunderstorm grid points are adjacent, and combining the adjacent thunderstorm grid points as a thunderstorm grid area.

[0042] Further, the step of acquiring a predicted thunderstorm moving path based on the thunderstorm grid area in the thundercloud grid map at the adjacent time frame includes:

[0043] acquiring the grid distance from each thunderstorm grid area in the thundercloud grid map at the previous time frame to each thunderstorm grid area in the thundercloud grid map at the next time frame;

[0044] ​​​​​The grid distance is compared with the distance threshold value based on a plurality of the grid distances to obtain a distance threshold value, and the grid distance less than the distance threshold value is selected as a moving sub-path;

[0045] A plurality of the moving sub-paths are concatenated as a predicted thunderstorm moving path.

[0046] Further, the calculation formula of the grid distance is:

[0047]

[0048] wherein, represents the grid distance between the mth thunderstorm grid area in the previous time frame and the nth thunderstorm grid area in the next time frame, both represent a weight function, represents the distance between the confidence ellipse of the mth thunderstorm grid area in the previous time frame and the center point of the nth thunderstorm grid area in the next time frame, represents the square root of the absolute value of the area difference between the confidence ellipse of the mth thunderstorm grid area in the previous time frame and the confidence ellipse of the nth thunderstorm grid area in the next time frame.

[0049] In a second aspect, the embodiments of the present application provide a lightning protection monitoring system, applied to the lightning protection monitoring method of the first aspect, and the system comprises:

[0050] An acquisition module is configured to acquire a past atmospheric weighted temperature data set, a past thundercloud observation data set and a past radar echo data set corresponding to a prediction area;

[0051] A construction module is configured to construct an initial thundercloud prediction neural network, and train the initial thundercloud prediction neural network into a final thundercloud prediction neural network based on the past atmospheric weighted temperature data set, the past thundercloud observation data set and the past radar echo data set;

[0052] A prediction module is configured to acquire a plurality of predicted thundercloud maps in consecutive time frames corresponding to the prediction area based on the final thundercloud prediction neural network, convert the predicted thundercloud maps into thundercloud grid maps, and acquire a plurality of thunderstorm grid areas in the thundercloud grid maps;

[0053] An analysis module is configured to acquire a predicted thunderstorm moving path based on the thunderstorm grid areas in the thundercloud grid maps in adjacent time frames, and perform lightning protection based on the predicted thunderstorm moving path.

[0054] ​​In a third aspect, an embodiment of the present application provides a computer, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and the processor implements the lightning protection monitoring method according to the first aspect when executing the computer program.

[0055] In a fourth aspect, an embodiment of the present application provides a storage medium having a computer program stored thereon, and the computer program is executed by a processor to implement the lightning protection monitoring method according to the first aspect. BRIEF DESCRIPTION OF DRAWINGS

[0056] Figure 1 a flow chart of the lightning protection monitoring method according to the first embodiment of the present application;

[0057] Figure 2 a structural block diagram of the lightning protection monitoring system according to the second embodiment of the present application;

[0058] The following detailed description will further describe the present application with reference to the above drawings. DETAILED DESCRIPTION

[0059] In order to facilitate the understanding of the present application, the present application will be described more fully below with reference to the accompanying drawings. The present application is shown in a number of embodiments in the drawings. However, the present application can be realized in many different forms and is not limited to the embodiments described herein. On the contrary, these embodiments are provided so that the disclosure of the present application is more thorough and complete.

[0060] It should be noted that when an element is referred to as being "fixedly attached" to another element, it can be directly on the other element or there can be intervening elements. When an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements can be present. As used herein the terms "vertical", "horizontal", "left", "right", and the like are merely used for the purpose of illustration.

[0061] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0062] Referring to Figure 1 The lightning protection monitoring method according to the first embodiment of the present application comprises the following steps:

[0063] S10: obtaining a past atmospheric weighted temperature data set, a past thundercloud observation data set, and a past radar echo data set corresponding to a prediction area;

[0064] The past atmospheric weighted temperature data set, the past thundercloud observation data set and the past radar echo data set respectively include past atmospheric weighted temperatures, past thundercloud observation maps and past radar echo maps in a plurality of continuous time frames. It should be noted that the time frames in the past atmospheric weighted temperature data set, the past thundercloud observation data set and the past radar echo data set are all the same time frames, and the past atmospheric weighted temperatures, the past thundercloud observation maps and the past radar echo maps in each same time frame correspond to each other.

[0065] The step S10 comprises:

[0066] S110: acquiring relative humidity and saturated water vapor pressure of different atmospheric layers in a continuous time frame corresponding to a prediction area;

[0067] In this embodiment, the relative humidity and the saturated water vapor pressure can be collected by a meteorological sensor. It can be understood that the relative humidity and the saturated water vapor pressure exist in each atmospheric layer.

[0068] S120: acquiring average water vapor pressure of a corresponding atmospheric layer based on the relative humidity and the saturated water vapor pressure in the same time frame;

[0069] The acquisition formula of the average water vapor pressure is:

[0070] ,

[0071] wherein, represents average water vapor pressure of the i-th atmospheric layer, represents relative humidity of the i-th atmospheric layer, represents saturated water vapor pressure of the i-th atmospheric layer.

[0072] S130: acquiring the past atmospheric weighted temperature through a plurality of average water vapor pressures, and combining a plurality of past atmospheric weighted temperatures in continuous time frames into a past atmospheric weighted temperature data set;

[0073] The acquisition formula of the past atmospheric weighted temperature is:

[0074] ,

[0075] wherein, represents past atmospheric weighted temperature in the j-th time frame, represents average temperature of the i-th atmospheric layer, represents thickness of the i-th atmospheric layer.

[0076] S20: constructing an initial thundercloud prediction neural network, and training the initial thundercloud prediction neural network into a final thundercloud prediction neural network based on the past atmospheric weighted temperature dataset, the past thundercloud observation dataset and the past radar echo dataset;

[0077] The initial thundercloud prediction neural network comprises a thundercloud prediction module, an echo prediction module and a temperature prediction module.

[0078] The step S20 comprises:

[0079] S210: obtaining a predicted radar echo image set through the past radar echo dataset and the echo prediction module;

[0080] The obtaining formula of the predicted radar echo image set is:

[0081] ,

[0082] Wherein, represents the predicted radar echo image set from the future 1 frame to the future a frame at the time t, represents the past radar echo image set from the past b frame to the current 0 frame at the time t, represents the echo prediction module.

[0083] In the embodiment, the past radar echo images in the past radar echo dataset can be cut in time sequence, the past radar echo images in the front of the time sequence are taken as the input values of the echo prediction module, and the past radar echo images in the rear of the time sequence are taken as the output values of the echo prediction module to train the echo prediction module, and then the predicted radar echo image set is obtained through the echo prediction module.

[0084] S220: obtaining a predicted atmospheric weighted temperature set through the past atmospheric weighted temperature dataset and the temperature prediction module;

[0085] The obtaining formula of the predicted atmospheric weighted temperature set is:

[0086] ,

[0087] Wherein, represents the predicted atmospheric weighted temperature set from the future 1 frame to the future a frame at the time t, represents the past atmospheric weighted temperature set from the past b frame to the current 0 frame at the time t, represents the temperature prediction module. The training mode of the temperature prediction module is consistent with that of the echo prediction module, which will not be described here.

[0088] S230: obtaining a predicted thundercloud image set through the past thundercloud observation data set, the predicted radar echo image set, the predicted atmospheric weighted temperature set and the thundercloud prediction module;

[0089] The formula for obtaining the predicted thundercloud image set is:

[0090] ,

[0091] Among them, represents the predicted thundercloud image set from 1 frame in the future to a frame in the future at time t, represents a set of past thundercloud observation images from b frames in the past to 0 frames in the present at time t, represents a thundercloud prediction module. It can be understood that when obtaining the predicted thundercloud image set, the predicted radar echo image set and the predicted atmospheric weighted temperature set are both used as input values of the thundercloud prediction module, as a reference basis for prediction by the thundercloud prediction module, to improve the accuracy of obtaining the predicted thundercloud image set.

[0092] S240: constructing a loss function through the predicted thundercloud image set, a real thundercloud observation image set, the predicted atmospheric weighted temperature set, a real atmospheric weighted temperature set, the predicted radar echo image set and a real radar echo image set, and correcting the thundercloud prediction module, the echo prediction module and the temperature prediction module based on the loss function to obtain a final thundercloud prediction neural network;

[0093] The formula for the loss function is:

[0094] ,

[0095] Among them, represents a real thundercloud observation image set from 1 frame in the future to a frame in the future at time t, represents a real radar echo image set from 1 frame in the future to a frame in the future at time t, represents a real atmospheric weighted temperature set from 1 frame in the future to a frame in the future at time t, represents a loss function, , Both represent weight coefficients, , , respectively represent the module parameters of the echo prediction module, the temperature prediction module and the thundercloud prediction module. It should be noted that in the process of training the initial thundercloud prediction neural network, the real thundercloud observation image set, the real atmospheric weighted temperature set and the real radar echo image set are respectively data sets formed by cutting the past atmospheric weighted temperature data set, the past thundercloud observation data set and the past radar echo data set based on time series.

[0096] S30: obtaining a plurality of predicted thundercloud maps in a continuous time frame corresponding to the predicted area based on the final thundercloud prediction neural network, converting the predicted thundercloud maps into thundercloud grid maps, and obtaining a plurality of thunderstorm grid areas in the thundercloud grid maps;

[0097] It can be understood that by taking the obtained real-time atmospheric weighted temperature, real-time radar echo map and real-time thundercloud observation map as input values of the final thundercloud prediction neural network, a plurality of predicted thundercloud maps can be output. The essence of converting the predicted thundercloud maps into thundercloud grid maps is to set a separation line in the predicted thundercloud maps with the same row spacing and column spacing, so as to form a plurality of grid points in the predicted thundercloud maps, thereby forming the thundercloud grid maps. That is, the thundercloud grid maps include a plurality of grid points with the same area.

[0098] The step S30 includes:

[0099] S310: determining whether the radar echo intensity of each grid point is higher than the intensity threshold value, and selecting the grid point corresponding to the radar echo intensity higher than the intensity threshold value as a thunderstorm grid point;

[0100] S320: determining whether the thunderstorm grid points are adjacent, and combining adjacent thunderstorm grid points into a thunderstorm grid area;

[0101] It can be understood that if two thunderstorm grid points are not adjacent, they are determined to be different thunderstorm grid areas.

[0102] S40: obtaining a predicted thunderstorm movement path based on the thunderstorm grid areas in the thundercloud grid maps in adjacent time frames, and preventing thunder and lightning based on the predicted thunderstorm movement path;

[0103] The step S40 includes:

[0104] S410: obtaining a grid distance from each thunderstorm grid area in the thundercloud grid map in a previous time frame to each thunderstorm grid area in the thundercloud grid map in a next time frame;

[0105] The calculation formula of the grid distance is:

[0106] ,

[0107] wherein, represents the grid distance between the mth thunderstorm grid area in the previous time frame and the nth thunderstorm grid area in the next time frame, , both represent a weight function, a square root of an absolute value of an area difference between a confidence ellipse of the mth thunderstorm grid region in the previous time frame and a confidence ellipse of the nth thunderstorm grid region in the next time frame. a square root of an absolute value of an area difference between a confidence ellipse of the mth thunderstorm grid region in the previous time frame and a confidence ellipse of the nth thunderstorm grid region in the next time frame.

[0108] S420: obtaining a distance threshold value based on a plurality of the grid distances, comparing the grid distances with the distance threshold value, and selecting the grid distance smaller than the distance threshold value as a moving sub-path;

[0109] Suppose that there are thunderstorm grid region a and thunderstorm grid region b in the thundercloud grid map in the previous time frame, and there are thunderstorm grid region c and thunderstorm grid region d in the thundercloud grid map in the next time frame, the grid distance between a and c is 10, the grid distance between a and d is 20, and the distance threshold value is 15, then the grid distance between a and c is selected as the moving sub-path.

[0110] It should be noted that if a plurality of thunderstorm grid regions in the thundercloud grid map in the previous time frame are all selected as the moving sub-path in a thunderstorm grid region in the thundercloud grid map in the next time frame, it is determined that a thunderstorm merging situation occurs, and if a thunderstorm grid region in the thundercloud grid map in the previous time frame is all selected as the moving sub-path in a plurality of thunderstorm grid regions in the thundercloud grid map in the next time frame, it is determined that a thunderstorm splitting situation occurs. Preferably, if there is a thunderstorm grid region in the thundercloud grid map in the next time frame which has no matched path, it is selected as a new thunderstorm.

[0111] S430: concatenating a plurality of the moving sub-paths as a predicted thunderstorm moving path;

[0112] It can be understood that by performing the above operation between a plurality of the thundercloud grid maps in consecutive time frames, the concatenation between the moving sub-paths can be completed.

[0113] The final thundercloud prediction neural network is acquired through the past atmospheric weighted temperature data set, the past thundercloud observation data set and the past radar echo data set, and a plurality of prediction thundercloud maps are acquired based on the final thundercloud prediction neural network, preliminary thunderstorm prediction of a prediction area is completed, that is, the specific occurrence position and time of lightning are predicted in advance, and the accuracy of lightning protection is improved; the prediction thunderstorm moving path is acquired according to the prediction thundercloud map, more detailed position and time prediction results of thunderstorms are completed, and the accuracy and effect of lightning protection are further improved through the combination of passive lightning protection measures; the past atmospheric weighted temperature data set with a relatively strong correlation with thunderstorm generation is introduced based on the past thundercloud observation data set and the past radar echo data set, the prediction accuracy of the final thundercloud prediction neural network is effectively improved, and the acquisition accuracy of the prediction thundercloud map is improved.

[0114] Please refer to Figure 2 The second embodiment of the present application provides a lightning protection monitoring system, which is applied to the lightning protection monitoring method in the above-mentioned embodiments and has been described above. As used below, the terms "module", "unit", "sub-unit" and the like can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, hardware or a combination of software and hardware can also be implemented and conceived.

[0115] The system comprises:

[0116] The acquisition module 10 is configured to acquire a past atmospheric weighted temperature data set, a past thundercloud observation data set and a past radar echo data set corresponding to a prediction area.

[0117] The acquisition module 10 comprises:

[0118] The first unit is configured to acquire the relative humidity and the saturated water vapor pressure of different atmospheric layers in a continuous time frame corresponding to the prediction area.

[0119] The second unit is configured to acquire the average water vapor pressure of the corresponding atmospheric layer based on the relative humidity and the saturated water vapor pressure in the same time frame.

[0120] The third unit is configured to acquire the past atmospheric weighted temperature through a plurality of average water vapor pressures, and combine a plurality of past atmospheric weighted temperatures in a continuous time frame into a past atmospheric weighted temperature data set.

[0121] The construction module 20 is configured to construct an initial thundercloud prediction neural network, and train the initial thundercloud prediction neural network into a final thundercloud prediction neural network based on the past atmospheric weighted temperature data set, the past thundercloud observation data set and the past radar echo data set.

[0122] The construction module 20 comprises:

[0123] The fourth unit is configured to obtain a predicted radar echo map set through the historical radar echo data set and the echo prediction module;

[0124] The fifth unit is configured to obtain a predicted atmospheric weighted temperature set through the historical atmospheric weighted temperature data set and the temperature prediction module;

[0125] The sixth unit is configured to obtain a predicted thundercloud map set through the historical thundercloud observation data set, the predicted radar echo map set, the predicted atmospheric weighted temperature set and the thundercloud prediction module;

[0126] The seventh unit is configured to construct a loss function through the predicted thundercloud map set, a real thundercloud observation map set, the predicted atmospheric weighted temperature set, a real atmospheric weighted temperature set, the predicted radar echo map set and a real radar echo map set, and correct the thundercloud prediction module, the echo prediction module and the temperature prediction module based on the loss function to obtain a final thundercloud prediction neural network;

[0127] The prediction module 30 is configured to obtain a plurality of predicted thundercloud maps in a continuous time frame corresponding to a prediction area based on the final thundercloud prediction neural network, convert the predicted thundercloud maps into a thundercloud grid map, and obtain a plurality of thunderstorm grid areas in the thundercloud grid map;

[0128] The prediction module 30 comprises:

[0129] The eighth unit is configured to determine whether the radar echo intensity of each grid point is higher than an intensity threshold value, and select the grid point corresponding to the radar echo intensity higher than the intensity threshold value as a thunderstorm grid point;

[0130] The ninth unit is configured to determine whether the thunderstorm grid points are adjacent, and combine the adjacent thunderstorm grid points into a thunderstorm grid area;

[0131] The analysis module 40 is configured to obtain a predicted thunderstorm moving path based on the thunderstorm grid areas in the thundercloud grid map in adjacent time frames, and perform lightning protection based on the predicted thunderstorm moving path;

[0132] The analysis module 40 comprises:

[0133] The tenth unit is configured to obtain a grid distance from each thunderstorm grid area in the thundercloud grid map in a previous time frame to each thunderstorm grid area in the thundercloud grid map in a next time frame;

[0134] Eleventh unit, for obtaining distance threshold based on several grid distances, comparing the grid distance with the distance threshold, selecting the grid distance less than the distance threshold as a moving sub-path;

[0135] Twelfth unit, for concatenating several moving sub-paths as a predicted thunderstorm moving path.

[0136] The application further provides a computer comprising a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor implements the lightning protection monitoring method as described in the above technical solution when executing the computer program.

[0137] The application further provides a storage medium having a computer program stored thereon, and the computer program is executable on a processor to implement the lightning protection monitoring method as described in the above technical solution.

[0138] In the description of the present application, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present application, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0139] The above embodiments only express several embodiments of the present application, and the description is more specific and detailed, but it cannot be understood as a limitation on the scope of the patent of the present application. It should be noted that for ordinary skilled in the art, without departing from the concept of the present application, several modifications and improvements can be made, which are all within the scope of protection of the present application. Therefore, the scope of protection of the patent of the present application should be subject to the appended claims.

Claims

1. A lightning protection monitoring method characterized by, The method comprises the following steps: obtaining a past atmospheric weighted temperature data set, a past thundercloud observation data set and a past radar echo data set corresponding to a prediction area, wherein the past atmospheric weighted temperature data set, the past thundercloud observation data set and the past radar echo data set respectively comprise past atmospheric weighted temperatures, past thundercloud observation maps and past radar echo maps in a plurality of continuous time frames; the step of obtaining the past atmospheric weighted temperature data set corresponding to the prediction area comprises: obtaining relative humidity and saturated water vapor pressure of different atmospheric layers in a continuous time frame corresponding to the prediction area; in the same time frame, obtaining the average water vapor pressure of the corresponding atmospheric layer based on the relative humidity and the saturated water vapor pressure; obtaining the past atmospheric weighted temperature through a plurality of average water vapor pressures, and combining a plurality of past atmospheric weighted temperatures in continuous time frames into a past atmospheric weighted temperature data set; constructing an initial thundercloud prediction neural network, wherein the initial thundercloud prediction neural network comprises a thundercloud prediction module, an echo prediction module and a temperature prediction module, and training the initial thundercloud prediction neural network into a final thundercloud prediction neural network based on the past atmospheric weighted temperature data set, the past thundercloud observation data set and the past radar echo data set; the step of training the initial thundercloud prediction neural network into a final thundercloud prediction neural network based on the past atmospheric weighted temperature data set, the past thundercloud observation data set and the past radar echo data set comprises: obtaining a prediction radar echo map set through the past radar echo data set and the echo prediction module; obtaining a prediction atmospheric weighted temperature set through the past atmospheric weighted temperature data set and the temperature prediction module; obtaining a prediction thundercloud map set through the past thundercloud observation data set, the prediction radar echo map set, the prediction atmospheric weighted temperature set and the thundercloud prediction module; constructing a loss function through the prediction thundercloud map set, a real thundercloud observation map set, the prediction atmospheric weighted temperature set, a real atmospheric weighted temperature set, the prediction radar echo map set and a real radar echo map set, and correcting the thundercloud prediction module, the echo prediction module and the temperature prediction module based on the loss function to obtain a final thundercloud prediction neural network; obtaining a plurality of prediction thundercloud maps in a continuous time frame corresponding to the prediction area based on the final thundercloud prediction neural network, converting the prediction thundercloud maps into a thundercloud grid map, and obtaining a plurality of thunderstorm grid areas in the thundercloud grid map; obtaining a prediction thunderstorm moving path based on the thunderstorm grid areas in the thundercloud grid map in adjacent time frames, and preventing thunder and lightning based on the prediction thunderstorm moving path; the step of obtaining a prediction thunderstorm moving path based on the thunderstorm grid areas in the thundercloud grid map in adjacent time frames comprises: obtaining a grid distance from each thunderstorm grid area in the thundercloud grid map in a previous time frame to each thunderstorm grid area in the thundercloud grid map in a next time frame; The grid distance is calculated based on the distance threshold value, and the grid distance less than the distance threshold value is selected as a moving sub-path; The moving sub-paths are connected to obtain a predicted thunderstorm moving path.

2. The lightning protection monitoring method according to claim 1, characterized in that, The average water vapor pressure is calculated based on the relative humidity and the saturated water vapor pressure. ， wherein, represents the average water vapor pressure of the i-th atmospheric layer, represents the relative humidity of the i-th atmospheric layer, represents the saturation water vapor pressure of the i-th atmospheric layer; The past atmospheric weighted temperature is calculated based on the average water vapor pressure. ， wherein, represents the past atmospheric weighted temperature under the jth time frame, represents the average temperature of the ith atmospheric layer, represents the thickness of the ith atmospheric layer.

3. The lightning protection monitoring method according to claim 1, characterized in that, The predicted radar echo set is calculated based on the past radar echo set and the echo prediction module. ， wherein, represents a set of predicted radar echo maps from future 1 frame to future a frame at time t, represents a set of past radar echo maps from past b frame to current 0 frame at time t, represents an echo prediction module; The predicted atmospheric weighted temperature set is calculated based on the past atmospheric weighted temperature set and the temperature prediction module. ， wherein, represents a set of atmospheric weighted temperatures from future 1 frame to future a frame at time t, represents a set of past atmospheric weighted temperatures from past b frame to current 0 frame at time t, represents a temperature prediction module; The predicted thundercloud set is calculated based on the past thundercloud set, the predicted radar echo set, the predicted atmospheric weighted temperature set, and the thundercloud prediction module. ， wherein, represents a set of predicted thundercloud maps from future 1 frame to future a frame at time t, represents a set of past thundercloud observation maps from past b frame to current 0 frame at time t, represents a thundercloud prediction module; The loss function is calculated based on the predicted thundercloud set and the past thundercloud set. ， wherein, represents a real thundercloud observation set from 1 frame in the future to a frame in the future at time t, represents a real radar echo set from 1 frame in the future to a frame in the future at time t, represents a real atmosphere weighted temperature set from 1 frame in the future to a frame in the future at time t, represents a loss function, , both represent a weight coefficient, , , respectively represent module parameters of the echo prediction module, the temperature prediction module and the thundercloud prediction module.

4. The lightning protection monitoring method according to claim 1, characterized in that, The thundercloud grid map includes a plurality of grid points with the same area, and the step of obtaining a plurality of thunderstorm grid regions in the thundercloud grid map includes: The radar echo intensity of each grid point is determined, and the grid point corresponding to the radar echo intensity higher than the intensity threshold value is selected as a thunderstorm grid point; The thunderstorm grid points are determined to be adjacent, and the adjacent thunderstorm grid points are combined as a thunderstorm grid region.

5. The lightning protection monitoring method according to claim 1, wherein The grid distance is calculated based on the distance threshold value, and the grid distance less than the distance threshold value is selected as a moving sub-path; ， wherein, denotes the grid distance between the mth thunderstorm grid region in the preceding time frame and the nth thunderstorm grid region in the following time frame, , both denote a weighting function, denotes the distance between the confidence ellipse of the mth thunderstorm grid region in the preceding time frame and the center point of the nth thunderstorm grid region in the following time frame, denotes the square root of the absolute value of the area difference between the confidence ellipse of the mth thunderstorm grid region in the preceding time frame and the confidence ellipse of the nth thunderstorm grid region in the following time frame.

6. A lightning protection monitoring system for use in the lightning protection monitoring method according to any one of claims 1 to 5, characterized by The system includes: An acquisition module is configured to acquire a past atmospheric weighted temperature data set, a past thundercloud observation data set, and a past radar echo data set corresponding to a prediction area, wherein the past atmospheric weighted temperature data set, the past thundercloud observation data set, and the past radar echo data set each include past atmospheric weighted temperatures, past thundercloud observation maps, and past radar echo maps in a plurality of continuous time frames. The acquisition module includes: A first unit is configured to acquire relative humidity and saturated water vapor pressure of different atmospheric layers in a continuous time frame corresponding to a prediction area; A second unit is configured to acquire average water vapor pressure of a corresponding atmospheric layer based on the relative humidity and the saturated water vapor pressure in the same time frame; A third unit is configured to acquire the past atmospheric weighted temperature through a plurality of average water vapor pressures, and combine a plurality of past atmospheric weighted temperatures in continuous time frames into a past atmospheric weighted temperature data set; A construction module is configured to construct an initial thundercloud prediction neural network, wherein the initial thundercloud prediction neural network includes a thundercloud prediction module, an echo prediction module, and a temperature prediction module, and train the initial thundercloud prediction neural network into a final thundercloud prediction neural network based on the past atmospheric weighted temperature data set, the past thundercloud observation data set, and the past radar echo data set. The construction module includes: A fourth unit is configured to acquire a predicted radar echo set through the past radar echo data set and the echo prediction module; A fifth unit is configured to acquire a predicted atmospheric weighted temperature set through the past atmospheric weighted temperature data set and the temperature prediction module; A sixth unit is configured to acquire a predicted thundercloud set through the past thundercloud observation data set, the predicted radar echo set, the predicted atmospheric weighted temperature set, and the thundercloud prediction module. a seventh unit configured to construct a loss function based on the predicted thundercloud set, the real thundercloud observation set, the predicted atmospheric weighted temperature set, the real atmospheric weighted temperature set, the predicted radar echo set, and the real radar echo set, and correct the thundercloud prediction module, the echo prediction module, and the temperature prediction module based on the loss function to obtain a final thundercloud prediction neural network; a prediction module configured to obtain a plurality of predicted thunderclouds corresponding to a continuous time frame in a prediction area based on the final thundercloud prediction neural network, convert the predicted thunderclouds into a thundercloud grid map, and obtain a plurality of thunderstorm grid areas in the thundercloud grid map; an analysis module configured to obtain a predicted thunderstorm moving path based on the thunderstorm grid areas in the thundercloud grid map in adjacent time frames, and perform lightning protection based on the predicted thunderstorm moving path; the analysis module includes: a tenth unit configured to obtain a grid distance from each of the thunderstorm grid areas in the thundercloud grid map in a previous time frame to each of the thunderstorm grid areas in the thundercloud grid map in a next time frame; an eleventh unit configured to obtain a distance threshold based on a plurality of the grid distances, compare the grid distances with the distance threshold, and select the grid distances smaller than the distance threshold as moving sub-paths; a twelfth unit configured to concatenate a plurality of the moving sub-paths into a predicted thunderstorm moving path.

7. A computer comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the lightning protection monitoring method of any one of claims 1-5.

Images