Lightning interceptor for forest lightning stroke area and lightning current amplitude prediction method

Abstract

The invention relates to the technical field of lightning protection, in particular to a lightning interceptor for a forest lightning stroke area and a lightning current amplitude prediction method. Collecting various historical time sequence data of each monitoring point in each lightning stroke event through a built-in sensor in the lightning interceptor; dynamically calculating the field strength weight of each monitoring point based on the fluctuation and difference characteristics of historical electric field time sequence data, and screening out prominent point locations which are obviously influenced by lightning stroke; predicted electric field time sequence data of the to-be-monitored point positions are generated by further combining historical electric fields and historical meteorological data, and the electric field similarity of the to-be-monitored point positions and the protruding point positions is obtained by analyzing the similarity between the predicted electric field time sequence data and the historical electric fields of the protruding point positions, the spatial positions and the field intensity weights. Finally, a network model is trained based on historical meteorology, electric field and lightning current data of the highlighted point locations, and the data contribution degree is adjusted by using the electric field similarity, so that the model adaptively learns the influence of different highlighted point locations, and the stability and precision of lightning current prediction are effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of lightning protection, in particular to a lightning interceptor for a forest lightning stroke area and a lightning current amplitude prediction method. BACKGROUND

[0002] With the climate change in recent years, the forests in the north and south are prone to strong convective weather or dry weather, which can easily cause thunderstorms, leading to lightning strikes on trees and causing forest fires. In order to avoid these forest fires, lightning interceptors such as lightning protection belts are often installed in areas with high incidence of thunderstorms. The lightning interceptors break through the limitation of traditional lightning protection facilities that can only "passively wait" for lightning strikes. By deploying a high-conductivity lightning rod array, the lightning interceptor uses the "upward leader" technology to actively release an ion flow opposite in polarity to the charge of the thundercloud, forming a discharge channel between the cloud and the ground, thereby guiding lightning to strike the interceptor and avoiding direct strikes on trees. The lightning current amplitude is a core parameter for measuring the damage of lightning, and accurate prediction of the lightning current amplitude is of great significance for forest lightning protection, disaster reduction, and ecological protection.

[0003] In the prior art, when predicting the lightning current amplitude, the lightning conditions of monitoring points with similar thunderstorm characteristics and lightning events in the forest lightning stroke area are usually used as references to train a network model for predicting the lightning current amplitude in the future period of the monitoring position. However, in training the network model, the lightning conditions of all the referenced monitoring points are usually assigned the same attention weight, and this static weight allocation method often fails to focus on key influencing points, resulting in inaccurate final prediction results. SUMMARY

[0004] In order to solve the technical problem that in training the network model, the lightning conditions of all the referenced monitoring points are usually assigned the same attention weight, and this static weight allocation method often fails to focus on key influencing points, resulting in inaccurate final prediction results, the purpose of the present application is to provide a lightning interceptor for a forest lightning stroke area and a lightning current amplitude prediction method, and the technical solution adopted is as follows: A lightning current amplitude prediction method for a forest lightning stroke area, comprising: In the forest lightning stroke area to be measured, historical meteorological time series data, historical lightning current time series data, and historical electric field time series data of each monitoring point in each lightning stroke event are obtained; In each lightning stroke event, the fluctuation characteristics and difference characteristics of the historical electric field time series data between the monitoring points are analyzed to determine the field strength weight of each monitoring point for screening out prominent points in each lightning stroke event; Optionally, one of the monitoring points is taken as a to-be-monitored point. Based on the historical electric field time series data and the historical meteorological time series data of the to-be-monitored point, predicted electric field time series data of the to-be-monitored point is obtained. The predicted electric field time series data of the to-be-monitored point is subjected to similarity analysis with the historical electric field time series data of the prominent point in each lightning stroke event, and is combined with the position distribution characteristics and the field intensity weight of the prominent point to determine the electric field similarity between the to-be-monitored point and each prominent point. Based on the electric field similarity between the to-be-monitored point and the prominent point, the meteorological time series data of the prominent point, the historical electric field time series data and the historical lightning current time series data, a network model is trained for lightning current prediction of the to-be-monitored point.

[0005] Further, the method for obtaining the field intensity weight comprises: In each lightning stroke event, the value obtained by negatively correlating the standard deviation of the historical electric field intensity value of each monitoring point is taken as the electric field intensity stability factor of each monitoring point. In each lightning stroke event, the difference characteristics of the historical electric field intensity values of all monitoring points at the same time are analyzed to determine the electric field intensity prominence factor of each monitoring point at each time. In each lightning stroke event, the product of the electric field intensity prominence factor and the electric field intensity stability factor of each monitoring point at all times is normalized to obtain the field intensity weight of each monitoring point in each lightning stroke event.

[0006] Further, the method for obtaining the electric field intensity prominence factor comprises: In each lightning stroke event, the mean value of the historical electric field intensity values of all monitoring points at the same time is taken as the electric field mean value characteristic value, and the value obtained by normalizing the difference between the historical electric field intensity value of each monitoring point at each time and the corresponding electric field mean value characteristic value at each time is taken as the electric field intensity prominence factor of each monitoring point at each time.

[0007] Further, the method for obtaining the prominent point comprises: In each lightning stroke event, the monitoring point with a field intensity weight greater than a preset field intensity prominence threshold is taken as the prominent point in each historical lightning stroke event.

[0008] Further, the method for obtaining the predicted electric field time series data comprises: In all lightning stroke events, the historical electric field time series data and the historical meteorological time series data of the to-be-monitored point are taken as the input of the SARIMA network model to determine the model parameters. Based on the historical electric field time series data of the to-be-monitored point in all lightning stroke events and the model parameters, a SARIMA network model is trained to obtain a SARIMA model for predicting lightning electric field. Obtain the current electric field time series data of the to-be-tested monitoring point, take the current electric field time series data as the input of the SARIMA model for predicting lightning strike electric field, and thus obtain the predicted electric field time series data at the to-be-tested monitoring point.

[0009] Further, the method for obtaining the electric field similarity comprises: Performing similarity analysis on the predicted electric field time series data of the to-be-tested monitoring point and the historical electric field time series data of the prominent point in each lightning strike event, to determine the electric field similarity parameter between the to-be-tested monitoring point and each prominent point in each lightning strike event; Analyzing the positional relationship between the to-be-tested monitoring point and each prominent point in each lightning strike event, to determine the positional similarity parameter between the to-be-tested monitoring point and each prominent point in each lightning strike event; Taking the normalized value of the product of the electric field similarity parameter and the positional similarity parameter between the to-be-tested monitoring point and each prominent point in each lightning strike event as the electric field similarity factor between the to-be-tested monitoring point and each prominent point in each lightning strike event; In each lightning strike event, taking the normalized value of the product of the field intensity weight of each prominent point and the electric field similarity factor between each prominent point and the to-be-tested monitoring point as the electric field similarity between the to-be-tested monitoring point and each prominent point in each lightning strike event.

[0010] Further, the method for obtaining the electric field similarity parameter comprises: Taking the negatively correlated and normalized value of the DTW value of the predicted electric field time series data at the to-be-tested monitoring point and the historical electric field time series data of each prominent point in each lightning strike event as the electric field similarity parameter between the to-be-tested monitoring point and each prominent point in each lightning strike event.

[0011] Further, the method for obtaining the positional similarity parameter comprises: Taking the negatively correlated value of the Euclidean distance between the to-be-tested monitoring point and each prominent point in each lightning strike event as the positional similarity parameter.

[0012] Further, the network model trained based on the electric field similarity between the to-be-tested monitoring point and the prominent point, the meteorological time series data of the prominent point, the historical electric field time series data and the historical lightning current time series data, for predicting lightning current of the to-be-tested monitoring point, comprises: The historical meteorological time series data, historical electric field time series data of the to-be-measured monitoring point corresponding to each prominent point in each lightning event are taken as inputs, the electric field similarity between the to-be-measured point and each prominent point corresponding to each lightning event is taken as an attention weight, and the historical lightning current time series data of the to-be-measured point corresponding to each prominent point in each lightning event is taken as an output, so that the ConvLSTM network model is trained, and a trained network model is obtained. The current meteorological time series data and current electric field time series data of the to-be-measured point in a current period are obtained and taken as inputs of the trained network model, so that the lightning current time series data of the to-be-measured point in a future period can be output.

[0013] A lightning interceptor for a forest lightning strike area, comprising a lightning interceptor body, a lightning current prediction module built in the lightning interceptor body, the lightning current prediction module is used to realize the steps in a lightning current amplitude prediction method for a forest lightning strike area.

[0014] The present application has the following beneficial effects: In the to-be-measured forest lightning strike area, the historical meteorological time series data, historical lightning current time series data and historical electric field time series data of each monitoring point in each lightning event are obtained, covering a multi-dimensional data set of the whole lightning chain, providing more comprehensive data support for subsequent model training. Since lightning is discharged through a leader channel, the electric field strength at the leader conduction place can better indicate the lightning intensity during discharge lightning than other monitoring points. Therefore, when calculating and analyzing the similarity between monitoring points, these leader conduction places should be more referential for subsequent lightning prediction. Therefore, in each lightning event, the field strength weight of each monitoring point is dynamically calculated based on the fluctuation and difference characteristics of the historical electric field time series data, and the prominent point significantly affected by the lightning event is selected, so that the model can focus on the key area with true thunderstorm prominent characteristics. Further, the predicted electric field time series data of the to-be-measured point is generated by combining the historical electric field and meteorological time series data, the change of the electric field before lightning is simulated in advance, then the similarity, spatial position distribution characteristics of the predicted electric field time series data and the historical electric field of the prominent point, and the field strength weight of the prominent point are analyzed, a time and space comprehensive similarity evaluation system is constructed, and the electric field similarity between the to-be-measured point and each prominent point is obtained. This index provides an adaptive contribution weight for different prominent points. Finally, the network model is trained based on the meteorological, electric field and lightning current data of the prominent point, and the data contribution is adjusted by using the electric field similarity between the to-be-measured point and the prominent point, so that the network model can adaptively learn the influence intensity of different prominent points on the to-be-measured point, and predict the lightning current of the to-be-measured point, effectively improving the stability and precision of the prediction result. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced. Obviously, the accompanying drawings in the following description only represent some embodiments of the present application, and for those skilled in the field, other drawings can be obtained based on these drawings without any creative effort.

[0016] Figure 1 A module structure diagram of a lightning current prediction module in a lightning current interceptor for a forest lightning stroke area according to an embodiment of the present application; Figure 2 A method flowchart of a lightning current amplitude prediction method for a forest lightning stroke area according to an embodiment of the present application; Figure 3 A method flowchart of a highlight point acquisition method according to an embodiment of the present application; Figure 4 A method flowchart of an electric field similarity acquisition method according to an embodiment of the present application. DETAILED DESCRIPTION

[0017] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined purposes, the specific embodiments, structures, features and effects of a lightning interceptor for a forest lightning stroke area and a lightning current amplitude prediction method according to the present application are described in detail as follows in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0018] 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 the present application belongs.

[0019] The specific scheme of a lightning interceptor for a forest lightning stroke area and a lightning current amplitude prediction method according to the present application is specifically described below in combination with the accompanying drawings.

[0020] With the intensification of global climate change and the increasing frequency of extreme weather events, forest ecosystems in both the north and south face an increasingly severe threat of lightning-induced fires. The frequent occurrence of severe convective weather (such as thunderstorm clouds) has led to a significant increase in lightning activity in southern forests, while northern forests, due to drought and low rainfall, have dry and flammable vegetation, making them more prone to large-scale fires during thunderstorms. To prevent these forest fires, lightning interceptors are often installed in high-risk thunderstorm areas. The core principle of lightning interceptors is to actively intervene in the lightning discharge process, creating a safe channel between the cloud and the ground, guiding the lightning current to a predetermined path and discharging it to the ground, thereby directing the lightning to strike the interceptor and preventing it from directly hitting trees.

[0021] Lightning interceptors deploy an array of highly conductive lightning rods (a combination of vertical and horizontal rods) to release an ion flow with the opposite polarity to the charge of the thundercloud, forming an "upward leader." When the intensity of the thundercloud reaches a threshold, the upward leader couples with the thundercloud leader, actively intercepting the lightning discharge channel and causing the lightning to strike the interceptor rather than the protected target. Therefore, during the operation of a lightning interceptor, the amplitude of the lightning current is the core parameter for measuring the destructive power of a lightning strike. Accurately predicting the amplitude of the lightning current is of great significance for forest lightning protection and disaster reduction, ecological protection, and other related purposes.

[0022] This invention provides a lightning interceptor for use in forest lightning strike areas, including a lightning interceptor body and a built-in lightning current prediction module. (See also...) Figure 1 This diagram illustrates the module structure of a lightning current prediction module provided in an embodiment of the present invention, including a processor 100, a memory 101, a bus 102, and a communication interface 103. The processor 100, the communication interface 103, and the memory 101 are connected via the bus 102. The memory 101 may include a high-speed random access memory, and the bus 102 may be an ISA bus, a PCI bus, or an EISA bus, etc. The processor 100 may be an integrated circuit chip with signal processing capabilities. The memory 101 stores at least one instruction, at least one program, a code set, or an instruction set. When the processor loads and executes the at least one instruction, at least one program, a code set, or an instruction set, it implements the steps in a lightning current amplitude prediction method for forest lightning strike areas.

[0023] Please see Figure 2 The diagram illustrates a method flowchart for predicting lightning current amplitude in forest lightning strike areas according to an embodiment of the present invention. The method includes the following steps: Step S1: Within the forest lightning strike area to be tested, acquire historical meteorological time-series data, historical lightning current time-series data, and historical electric field time-series data for each monitoring point in each lightning strike event.

[0024] First, in the area to be tested, the position of each lightning interceptor is taken as a monitoring point. In the past historical period, in the period of each lightning event, the historical meteorological time series data of each monitoring point is obtained by the various meteorological monitoring sensors built in the lightning interceptor (in the embodiment of the application, the types of meteorological time series data are set as basic meteorological data such as temperature, humidity, and wind speed), the historical lightning current time series data is obtained by the current meter built in the lightning interceptor, and the historical electric field time series data is obtained by the electric field meter built in the lightning interceptor. Among them, various time series data are collected synchronously and have the same collection frequency.

[0025] It should be noted that in this embodiment of the application, the historical period is set as the past year, and the collection frequency of various time series data is set as 10 times per second. The specific values can be adjusted according to the implementation scene, and are not limited herein.

[0026] Step S2: In each lightning event, the fluctuation characteristics and difference characteristics of the historical electric field time series data between the monitoring points are analyzed to determine the field strength weight of each monitoring point for screening out the prominent point in each lightning event.

[0027] When lightning occurs, a large amount of negative charge is accumulated on the side close to the ground of the thundercloud. Under the action of electromagnetic induction, a large amount of positive charge is generated on the side close to the thundercloud on the trees and lightning protection measures on the ground. Thus, an electric field is formed at the top of the trees and lightning protection measures under the thundercloud. Since the conductivity of the trees is poorer than that of the lightning protection measures, the thundercloud will preferentially strike the lightning protection measures. Meanwhile, since lightning is discharged through a leader channel, the electric field strength of the leading electrically-conductive place can better indicate the lightning intensity when discharging lightning, compared with other monitoring points. These leading electrically-conductive places should be more referential, because the leader channel is jointly formed by the charges of the thundercloud and the trees or lightning interceptor facilities on the ground, which leads to a stronger electric field compared with the electric field formed by the thundercloud and the ground in other regions, and the corresponding electric field gradually strengthens with the increase of the charges of the trees and the tip of the lightning interceptor.

[0028] Therefore, in this step, the fluctuation characteristics and difference characteristics of the historical electric field time series data between the monitoring points can be compared in each lightning event to determine the field strength weight of each monitoring point, and the prominent point in each lightning event is screened out based on the field strength weight. The prominent point is the monitoring point that has a greater response intensity to the lightning event and is directly affected by lightning in each lightning event.

[0029] Preferably, the method for obtaining the field prominent point in an embodiment of the application comprises: Please refer to Figure 3Fig. 1 shows a method flowchart of a method for obtaining a highlight point in an embodiment of the present application, which comprises the following steps: Step S201: In each lightning stroke event, analyze the fluctuation characteristics of the historical electric field time series data of each monitoring point, and determine the electric field intensity stability factor of each monitoring point.

[0030] In each lightning stroke event, calculate the standard deviation of the historical electric field intensity value of each monitoring point. The larger the standard deviation, the greater the fluctuation degree of the historical electric field intensity value of the monitoring point, and the smaller the stability. Therefore, the value after negatively correlating the standard deviation is taken as the electric field intensity stability factor of each monitoring point. The larger the electric field intensity stability factor, the higher the electric field stability at the monitoring point. The negatively correlating can be realized by the formula wherein, represents an exponential function with natural constant e as the base, and x represents the independent variable.

[0031] Step S202: In each lightning stroke event, analyze the difference characteristics of the historical electric field intensity values of all monitoring points at the same time, and determine the electric field intensity highlight factor of each monitoring point at each time.

[0032] In each lightning stroke event, take the mean value of the historical electric field intensity values of all monitoring points at the same time as the electric field mean characteristic value. The electric field mean characteristic value represents the average level of the electric field intensity of all monitoring points at the same time, which provides a reference benchmark.

[0033] Then, calculate the difference between the historical electric field intensity value of each monitoring point at each time and the corresponding electric field mean characteristic value at each time. The larger the positive difference value, the higher the historical electric field intensity of the monitoring point at the time, and the stronger the corresponding electric field, which is more likely to be the leading current place, and thus the reference is higher. Therefore, the difference is normalized to obtain the electric field intensity highlight factor of each monitoring point at each time. Since the difference value can be positive or negative, the normalization method adopts function.

[0034] Step S203: In each lightning stroke event, fuse the corresponding electric field intensity highlight factor and electric field intensity stability factor of each monitoring point to determine the field intensity weight of each monitoring point.

[0035] Based on the analysis in the preceding steps S201 and S202, the greater the electric field intensity stability factor of the monitoring point is, the higher the electric field stability at the monitoring point is, the greater the electric field intensity prominent factor is, the stronger the corresponding electric field is, and the more likely the electric field is the leading electric field, so the reference is higher, so the two factors are positively correlated with the field intensity weight of the monitoring point, and therefore, in each lightning event, the product of the electric field intensity prominent factor and the electric field intensity stability factor of each monitoring point at all times is normalized and used as the field intensity weight of each monitoring point in each lightning event, and the greater the field intensity weight is, the greater the field intensity prominence of the monitoring point in the lightning event is, the higher the response degree to the lightning event is, and the greater the reference value for the lightning current amplitude prediction of the subsequent process is. The normalization is a well-known technical means in the art, and the normalization function can be linear normalization or standard normalization, and the specific normalization method is not limited herein.

[0036] Step S204: In each lightning event, the prominent point is selected from all monitoring points according to the field intensity weight of the monitoring point.

[0037] In each lightning event, the monitoring point with a field intensity weight greater than a preset field intensity prominent threshold is selected as the prominent point in each historical lightning event, and the selected prominent point is a monitoring point significantly affected by the lightning event, that is, a key point with a thunderstorm prominent feature.

[0038] It should be noted that the preset field intensity prominent threshold in the embodiment of the application is 0.6, and the specific value can be adjusted according to the implementation scenario, which is not limited herein.

[0039] Step S3: Optionally, a monitoring point is selected as a to-be-monitored point, and predicted electric field time series data at the to-be-monitored point are obtained based on historical electric field time series data and historical meteorological time series data of the to-be-monitored point; similarity analysis is performed on the predicted electric field time series data of the to-be-monitored point and the historical electric field time series data of the prominent point in each lightning event, and the position distribution feature and the field intensity weight of the prominent point are combined to determine the electric field similarity between the to-be-monitored point and each prominent point.

[0040] When lightning strikes, a large amount of negative charge is gathered at the lower part of the thundercloud, and a large amount of positive charge is gathered at the top of the trees and lightning intercepters on the ground under the action of the electric field caused by the thundercloud. The positive charge at the top of the trees and lightning intercepters and the negative charge at the lower part of the thundercloud form an electric field, and when the intensity of the electric field reaches a certain level, a leader channel is formed, thereby generating lightning current when discharging lightning. Therefore, when the electric field intensity between two monitoring points is similar, the lightning current amplitude when discharging lightning is also basically similar, so in this step, the similarity of the electric field intensity between the monitoring points needs to be analyzed.

[0041] In this step, first, an optional monitoring point is selected as a to-be-monitored point, and the electric field intensity of the to-be-monitored point in a future period of time is predicted based on the historical electric field time series data and the historical meteorological time series data of each monitoring point, so as to obtain the predicted electric field time series data of the to-be-monitored point.

[0042] Preferably, the method for obtaining the predicted electric field time series data in an embodiment of the present application comprises: For thunderstorms, the speed of various conditions in thunderclouds to accumulate electric charges and form a leader channel is roughly the same under the influence of meteorological environment, so the electric field situation in the future period of time can be preliminarily predicted by a seasonal difference autoregressive moving average model SARIMA model according to the electric field situation between thunderclouds and the ground and the meteorological characteristics in a large number of lightning events in the past.

[0043] In all lightning events, the historical electric field time series data and the historical meteorological time series data of the to-be-monitored point are taken as the input of the SARIMA network model, so as to determine the model parameters, and then the SARIMA network model is trained based on the historical electric field time series data of the to-be-monitored point in all lightning events and the model parameters, so as to obtain the SARIMA model for predicting lightning electric field; finally, the current electric field time series data of the to-be-monitored point is obtained, and the current electric field time series data is taken as the input of the SARIMA model for predicting lightning electric field, so as to obtain the predicted electric field time series data of the to-be-monitored point.

[0044] It should be noted that the SARIMA network model is a known technology, and the specific process is not described here; in this embodiment of the present application, the length of the predicted electric field time series data is set to 1 hour, and the specific length can be adjusted according to the implementation scene, which is not limited here.

[0045] The predicted electric field time series data of the to-be-monitored point realizes the simulation of the change of the electric field before lightning, so after obtaining the predicted electric field time series data of the to-be-monitored point, the similarity between the predicted electric field time series data of the to-be-monitored point and the historical electric field time series data of the prominent point in each lightning event can be analyzed, and the position distribution characteristics between the monitoring points and the field intensity weight of the prominent point are combined, so as to obtain the electric field similarity between the to-be-monitored point and each prominent point. The electric field similarity represents the similarity between the electric field characteristics of the to-be-monitored point in a future period of time and the electric field characteristics of the monitoring point affected by lightning events, so as to provide an adaptive contribution weight for each prominent point in the subsequent process.

[0046] Preferably, in an embodiment of the present application, the method for obtaining the electric field similarity comprises: Please refer to Figure 4Fig. 1 shows a flow chart of a method for obtaining the electric field similarity in an embodiment of the present application, which comprises the following steps: Step S301: Perform similarity analysis on the predicted electric field time series data of the to-be-monitored point and the historical electric field time series data of the prominent point in each lightning stroke event, to determine the electric field similarity parameter between the to-be-monitored point and each prominent point in each lightning stroke event.

[0047] The DTW value can capture the shape matching degree of two time series data on the time axis, and can be used to reflect the similarity, so the DTW value of the predicted electric field time series data at the to-be-monitored point and the historical electric field time series data of each prominent point in each lightning stroke event is calculated, the smaller the DTW value, the higher the similarity between the two time series data, so the DTW value is negatively correlated and normalized to correct the logical relationship, thereby obtaining the electric field similarity parameter between the to-be-monitored point and each prominent point in each lightning stroke event, the greater the electric field similarity parameter here, the higher the electric field similarity between the to-be-monitored point and each prominent point in each lightning stroke event. The negative correlation and normalization processing here can use the formula wherein, represents the exponential function with the natural constant e as the base, and x represents the independent variable.

[0048] It should be noted that the method for obtaining the DTW value is a known technology, and the specific process is not described here.

[0049] Step S302: Analyze the positional relationship between the to-be-monitored point and the prominent point in each lightning stroke event, to determine the positional similarity parameter between the to-be-monitored point and each prominent point in each lightning stroke event.

[0050] In a lightning stroke event, the electric field change is affected by the local meteorological conditions, and the electric field pattern of the adjacent monitoring point may be more similar, so the Euclidean distance between the to-be-monitored point and each prominent point in each lightning stroke event is calculated, the smaller the Euclidean distance, the closer the distance between the two points, and the more likely they have similar electric field patterns, so the value of the Euclidean distance after negative correlation mapping is used as the positional similarity parameter, based on the aforementioned logic, the greater the positional similarity parameter, the closer the positions, and the more likely they have consistent electric field characteristics. Similarly, the negative correlation mapping method here can use the formula wherein, represents the exponential function with the natural constant e as the base, and x represents the independent variable.

[0051] Step S303: Determine the electric field similarity factor between the to-be-monitored point and each prominent point in each lightning stroke event based on the electric field similarity parameter and the positional similarity parameter between the to-be-monitored point and each prominent point in each lightning stroke event.

[0052] Based on the analysis in steps S301 and S302, the electric field similar parameters and the position similar parameters between the to-be-monitored point and each prominent point in each lightning stroke event are positively correlated with the electric field similarity, so in this embodiment of the present application, the product of the electric field similar parameters and the position similar parameters between the to-be-monitored point and each prominent point in each lightning stroke event is normalized, and the value after normalization is taken as the electric field similarity factor between the to-be-monitored point and each prominent point in each lightning stroke event. The greater the electric field similarity factor obtained by fusing the similar characteristics of the electric field intensity and the similar characteristics of the spatial position, the higher the electric field similarity between the two points. The normalization is a technical means familiar to those skilled in the art, and the selection of the normalization function can be linear normalization or standard normalization, and the specific normalization method is not limited herein.

[0053] Step S304: The electric field similarity factor between the to-be-monitored point and each prominent point in each lightning stroke event is fused with the field intensity weight of each prominent point, so as to obtain the electric field similarity between the to-be-monitored point and each prominent point in each lightning stroke event.

[0054] Based on the description in step S203, in a lightning stroke event, the greater the field intensity weight of a prominent point, the greater the field intensity prominence of the prominent point in the lightning stroke event, the higher the response degree of the prominent point to the lightning stroke event, and the greater the reference value of the lightning current amplitude prediction of the subsequent process, so in this step, the product of the field intensity weight of each prominent point and the electric field similarity factor between each prominent point and the to-be-monitored point in each lightning stroke event is normalized, and the value after normalization is taken as the electric field similarity between the to-be-monitored point and each prominent point in each lightning stroke event. The electric field similarity can provide an adaptive contribution weight for the prominent point in each lightning stroke event. The normalization is a technical means familiar to those skilled in the art, and the selection of the normalization function can be linear normalization or standard normalization, and the specific normalization method is not limited herein.

[0055] S4: Training a network model based on the electric field similarity between the to-be-monitored point and the prominent point, the meteorological time series data of the prominent point, the historical electric field time series data, and the historical lightning current time series data, for lightning current prediction of the to-be-monitored point.

[0056] Since the prominent point in each lightning event is the monitoring point significantly affected by the lightning event, that is, the key point with prominent characteristics of thunderstorm, in this step, the network model can be trained based on the meteorological time series data, historical electric field time series data and historical lightning current time series data of the prominent point. Meanwhile, in view of the electric field similarity between the to-be-monitored point and each prominent point in each lightning event obtained in the above step, which provides a contribution weight for each prominent point, the electric field similarity is involved in the training process of the network model, so as to obtain the trained network model for lightning current prediction of the to-be-monitored point.

[0057] Preferably, in an embodiment of the present application, the network model is trained based on the electric field similarity between the to-be-monitored point and the prominent point, the meteorological time series data, the historical electric field time series data and the historical lightning current time series data of the prominent point, for lightning current prediction of the to-be-monitored point, comprising: Setting data input channels: including meteorological parameter channels and electric field intensity channels, then inputting the historical meteorological time series data, the historical electric field time series data of the to-be-monitored point corresponding to each prominent point in each lightning event, taking the electric field similarity between the to-be-monitored point and each prominent point in each lightning event as the attention weight, and taking the historical lightning current time series data of the to-be-monitored point corresponding to each prominent point in each lightning event as the output, so as to guide the model to learn the mapping relationship from the input to the output flow, for training the ConvLSTM network model, to obtain the trained network model.

[0058] Finally, the current meteorological time series data and the current electric field time series data (obtained based on various sensors built-in the lightning interceptor at the to-be-monitored point) in the current period of the to-be-monitored point are obtained as the input of the trained network model, so as to output the lightning current time series data of the to-be-monitored point in the future period.

[0059] It should be noted that the ConvLSTM network model is a known technology, and the training process is also a known technology, so the specific process is not described here.

[0060] In summary, in the forest lightning stroke area to be tested, the historical meteorological time series data, the historical lightning current time series data and the historical electric field time series data of each monitoring point in each lightning stroke event are obtained, covering the multi-dimensional data set of the whole chain of lightning stroke, providing more comprehensive data support for subsequent model training. Since lightning stroke is discharged through a leader channel, the electric field intensity at the leader conduction site is more indicative of the lightning stroke intensity during discharge lightning stroke than other monitoring sites. Therefore, in the subsequent calculation and analysis of the similarity between monitoring sites, these leader conduction sites should be more referential for subsequent lightning prediction. Therefore, in each lightning stroke event, based on the fluctuation and difference characteristics of the historical electric field time series data, the field intensity weight of each monitoring site is dynamically calculated, and the prominent sites significantly affected by lightning stroke events are screened out, so that the model can focus on the key areas with true thunderstorm prominent features. Further, by combining the historical electric field and meteorological time series data to generate predicted electric field time series data of the monitoring site to be monitored, the change of the electric field before lightning stroke is simulated in advance, and then the similarity, spatial position distribution characteristics of the predicted electric field time series data and the historical electric field of the prominent sites, and the field intensity weight of the prominent sites are analyzed, a time and space comprehensive similarity evaluation system is constructed, and the electric field similarity between the monitoring site to be monitored and each prominent site is obtained. This index provides an adaptive contribution weight for different prominent sites. Finally, the network model is trained based on the meteorological, electric field and lightning current data of the prominent sites, and the electric field similarity between the monitoring site to be monitored and the prominent sites is used to adjust the data contribution, so that the network model can adaptively learn the influence intensity of different prominent sites on the monitoring site to be monitored, and predict the lightning current of the monitoring site to be monitored, effectively improving the stability and accuracy of the prediction result.

[0061] It should be noted that the above-mentioned sequence of embodiments is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0062] Each embodiment in the specification is described in a progressive manner, and the same or similar parts between each embodiment can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. A method for predicting the amplitude of lightning current in forest lightning strike areas, characterized in that, The method includes: Within the forest lightning strike area to be tested, acquire historical meteorological time-series data, historical lightning current time-series data, and historical electric field time-series data for each monitoring point in each lightning strike event; In each lightning strike event, the fluctuation characteristics and differences of historical electric field time series data between monitoring points are analyzed, and the field strength weight of each monitoring point is determined to screen out the prominent points in each lightning strike event. Select any monitoring point as the monitoring point, and obtain the predicted electric field time series data of the monitoring point based on the historical electric field time series data and historical meteorological time series data of the monitoring point. Perform similarity analysis between the predicted electric field time series data of the monitoring point and the historical electric field time series data of the prominent points in each lightning strike event, and combine it with the location distribution characteristics and the field strength weight of the prominent points to determine the electric field similarity between the monitoring point and each prominent point. A network model is trained based on the electric field similarity between the monitoring point and the prominent point, the meteorological time series data of the prominent point, the historical electric field time series data, and the historical lightning current time series data, and is used to predict the lightning current of the monitoring point.

2. The method for predicting lightning current amplitude in forest lightning strike areas according to claim 1, characterized in that, The method for obtaining the field strength weight includes: In each lightning strike event, the standard deviation of the historical electric field intensity values ​​at each monitoring point is negatively correlated and mapped to the value, which is used as the electric field intensity stability factor for each monitoring point. In each lightning strike event, the differences in historical electric field intensity values ​​at the same time for all monitoring points are analyzed to determine the prominent factor of electric field intensity at each monitoring point at each time. In each lightning strike event, the normalized value of the product of the electric field strength prominence factor and the electric field strength stability factor at all times for each monitoring point is used as the field strength weight of each monitoring point in each lightning strike event.

3. The method for predicting lightning current amplitude in forest lightning strike areas according to claim 2, characterized in that, The method for obtaining the electric field strength prominence factor includes: In each lightning strike event, the average of the historical electric field intensity values ​​of all monitoring points at the same time is taken as the electric field mean characteristic value. The normalized value of the difference between the historical electric field intensity value of each monitoring point at each time and the corresponding electric field mean characteristic value at each time is taken as the electric field intensity highlighting factor of each monitoring point at each time.

4. The method for predicting lightning current amplitude in forest lightning strike areas according to claim 1, characterized in that, The method for obtaining the protruding points includes: In each lightning strike event, the monitoring points with field strength weights greater than the preset field strength threshold are designated as the prominent points in each historical lightning strike event.

5. The method for predicting lightning current amplitude in forest lightning strike areas according to claim 1, characterized in that, The method for obtaining the predicted electric field time series data includes: In all lightning strike events, historical electric field time series data and historical meteorological time series data of the monitoring points are used as inputs to the SARIMA network model to determine the model parameters; Based on the historical electric field time series data of the monitoring points in all lightning strike events and the model parameters, a SARIMA network model is trained to obtain a SARIMA model for predicting the electric field of lightning strikes. The current electric field time series data of the monitoring point to be tested is obtained, and the current electric field time series data is used as the input of the SARIMA model for predicting the lightning electric field, thereby obtaining the predicted electric field time series data at the monitoring point to be tested.

6. The method for predicting lightning current amplitude in forest lightning strike areas according to claim 1, characterized in that, The method for obtaining the electric field similarity includes: The predicted electric field time series data of the monitoring points are compared with the historical electric field time series data of the prominent points in each lightning strike event to determine the electric field similarity parameters between the monitoring points and each prominent point in each lightning strike event. Analyze the positional relationship between the monitoring points and the prominent points in each lightning strike event, and determine the positional similarity parameters between the monitoring points and each prominent point in each lightning strike event; The normalized value of the product of the electric field similarity parameter and the position similarity parameter between the monitoring point and each prominent point in each lightning strike event is used as the electric field similarity factor between the monitoring point and each prominent point in each lightning strike event. In each lightning strike event, the normalized value of the product of the field strength weight of each protruding point and the electric field similarity factor between each protruding point and the point to be monitored is used as the electric field similarity between the point to be monitored and each protruding point in each lightning strike event.

7. A method for predicting lightning current amplitude in forest lightning strike areas according to claim 6, characterized in that, The method for obtaining the electric field similarity parameters includes: The predicted electric field time series data at the monitoring point to be measured is negatively correlated with the DTW value of the historical electric field time series data of each prominent point in each lightning strike event, and the normalized value is used as the electric field similarity parameter between the monitoring point to be measured and each prominent point in each lightning strike event.

8. A method for predicting lightning current amplitude in forest lightning strike areas according to claim 6, characterized in that, The method for obtaining the positional similarity parameter includes: The value obtained by negatively correlating the Euclidean distance between the monitored point and the location of each prominent point in each lightning strike event is used as the location similarity parameter.

9. A method for predicting lightning current amplitude in forest lightning strike areas according to claim 1, characterized in that, The network model trained based on the electric field similarity between the monitored point and the prominent point, meteorological time-series data of the prominent point, historical electric field time-series data, and historical lightning current time-series data is used to predict lightning current at the monitored point, including: The ConvLSTM network model is trained by taking the historical meteorological time series data and historical electric field time series data of each prominent point corresponding to the monitoring point in each lightning strike event as input, the electric field similarity between the monitoring point and each prominent point corresponding to each lightning strike event as attention weight, and the historical lightning current time series data of each prominent point corresponding to the monitoring point in each lightning strike event as output. The current meteorological time series data and current electric field time series data of the monitoring point in the current period are obtained and used as input to the trained network model, so that the lightning current time series data of the monitoring point in the future period can be output.

10. A lightning interceptor for use in forest lightning strike areas, comprising a lightning interceptor body, characterized in that, The lightning interceptor body has a built-in lightning current prediction module, which is used to implement the steps in the lightning current amplitude prediction method for forest lightning strike areas as described in any one of claims 1 to 9.

Images