Lightning stroke protection method, device, equipment, medium and product

Abstract

The invention discloses a lightning stroke protection method, device and equipment, a medium and a product. The method comprises the following steps: acquiring real-time thunder and lightning related data of a target facility; inputting the real-time lightning related data into a lightning stroke probability prediction model obtained through federal learning training to obtain a lightning stroke probability prediction result; determining a lightning stroke intensity prediction result according to the real-time lightning related data and a pre-trained lightning stroke intensity prediction model; according to the lightning stroke probability prediction result and the lightning stroke intensity prediction result, determining a lightning stroke risk level; and adjusting the lightning protection strategy in response to the change of the lightning risk level. According to the technical scheme of the embodiment of the invention, the prediction capability of the electric power facility on the lightning stroke degree and the lightning stroke protection flexibility are improved.

Description

Technical Field

[0001] This application relates to the technical field of lightning protection, and particularly to a lightning strike protection method, device, equipment, medium and product. Background Art

[0002] Lightning strike is one of the main natural disasters faced by substations, which may damage equipment, cause power outages, and even trigger safety accidents such as fires. Traditional lightning protection measures mainly rely on installing lightning rods and grounding systems, but these measures are difficult to cope with the complex challenges brought by multiple lightning strikes and have insufficient protection capabilities when the lightning strike intensity is high or the frequency is high. The existing lightning strike protection measures for substations are single and respond passively.

[0003] At present, traditional substations have poor prediction ability for lightning strike events, and the lightning protection measures of traditional substations mainly adopt fixed designs and cannot be adjusted according to different lightning strike events. Therefore, their adaptability and flexibility are poor. Summary of the Invention

[0004] This application provides a lightning strike protection method, device, equipment, medium and product to improve the prediction ability of lightning strike intensity and the flexibility of lightning strike protection.

[0005] According to one aspect of this application, a lightning strike protection method is provided, which is applied to a central server. The method includes:

[0006] Obtain real-time lightning-related data of a target facility;

[0007] Input the real-time lightning-related data into a lightning strike probability prediction model trained through federated learning to obtain a lightning strike probability prediction result;

[0008] Determine a lightning strike intensity prediction result according to the real-time lightning-related data and a pre-trained lightning strike intensity prediction model;

[0009] Determine a lightning risk level according to the lightning strike probability prediction result and the lightning strike intensity prediction result;

[0010] In response to a change in the lightning risk level, adjust the lightning strike protection strategy.

[0011] According to another aspect of this application, a lightning strike protection device is provided, which is applied to a central server and includes:

[0012] A data acquisition module, configured to obtain real-time lightning-related data of a target facility;

[0013] A probability prediction module, configured to input the real-time lightning-related data into a lightning strike probability prediction model trained through federated learning to obtain a lightning strike probability prediction result;

[0014] An intensity prediction module, configured to determine a lightning strike intensity prediction result according to real-time lightning-related data and a pre-trained lightning strike intensity prediction model;

[0015] A risk determination module, configured to determine a lightning risk level according to the lightning strike probability prediction result and the lightning strike intensity prediction result;

[0016] A lightning strike protection module, configured to adjust a lightning strike protection strategy in response to a change in the lightning risk level.

[0017] According to another aspect of the present application, an electronic device is provided, and the electronic device includes:

[0018] At least one processor; and

[0019] A memory communicatively connected to the at least one processor; wherein,

[0020] The memory stores a computer program executable by the at least one processor, and when the computer program is executed by the at least one processor, the at least one processor is enabled to execute the lightning strike protection method according to any embodiment of the present application.

[0021] According to another aspect of the present application, a computer-readable storage medium is provided, and the computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the lightning strike protection method according to any embodiment of the present application is implemented.

[0022] According to another aspect of the present application, a computer program product is provided, and the computer program product includes a computer program, and when the computer program is executed by a processor, the lightning strike protection method according to any embodiment of the present application is implemented.

[0023] In the technical solution of the embodiment of the present application, real-time lightning-related data is input into a lightning strike probability prediction model obtained through federated learning to obtain a lightning strike probability prediction result. Federated learning can avoid unifying different types of data of different organizations or institutions in different regions. Instead, local clients are set up in each region for local model training, and then the global model is determined through the federated learning system. This not only achieves the purpose of predicting the lightning strike probability but also greatly reduces the difficulty of model training. By applying federated learning, which was originally used for data confidentiality, to the training of the lightning strike probability prediction model, local training is carried out separately using different types of data related to lightning strikes, improving the efficiency of model training. The different types of data used for training ensure the accuracy of the lightning strike probability prediction, thereby ensuring the prediction ability of lightning strikes. According to the real-time lightning-related data and a pre-trained lightning strike intensity prediction model, a lightning strike intensity prediction result is determined. By using another prediction model to predict the possible lightning strike intensity, the prediction of the lightning strike intensity is carried out on the basis of the lightning strike probability prediction, which can provide an accurate basis for subsequent means and strategies to deal with lightning strikes. According to the lightning strike probability prediction result and the lightning strike intensity prediction result, the lightning risk level is determined. When the lightning risk level changes, the lightning protection strategy is adjusted, which can targetedly adjust the protection measures to cope with different degrees of lightning strike events and improve the flexibility of the target facility for lightning protection.

[0024] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0026] Figure 1 It is a flowchart of a lightning protection method provided in Embodiment 1 of the present application;

[0027] Figure 2 It is a schematic diagram of the federated learning training of a lightning strike probability prediction model applicable to Embodiment 2 of the present application;

[0028] Figure 3 It is a schematic structural diagram of a lightning protection device provided in Embodiment 3 of the present application;

[0029] Figure 4 It is a schematic structural diagram of an electronic device for implementing the lightning protection method of the embodiment of the present application. Detailed implementation manners

[0030] To enable those skilled in the art to better understand the solution of this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of this application.

[0031] It should be noted that the terms "first", "second", etc. in the description and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data used in appropriate cases can be interchanged so that the embodiments of this application described here can be implemented in an order different from those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0032] Embodiment 1

[0033] Figure 1 A flowchart of a lightning strike protection method is provided for Embodiment 1 of this application. This embodiment is applicable to the situation of dealing with lightning strike events and protecting power facilities. This method can be executed by a lightning strike protection device, which can be implemented in the form of hardware and / or software, and the lightning strike protection device can be configured in an electronic device. As Figure 1 shown, this method includes:

[0034] S110. Obtain real-time lightning-related data of the target facility.

[0035] Among them, the target facility can be any facility that needs to install lightning protection equipment in real life, which can be a building, or an electronic device or mechanical device that needs lightning protection, etc. For example, it can be a power facility, such as a substation, etc. The embodiments of this application do not limit the target facility that needs lightning protection. Of course, it should be noted that the facility may be a series of buildings on a large scale and is not limited to a single small unit.

[0036] The real-time lightning-related data can be any data related to lightning weather or lightning strike events. For example, it can include but is not limited to lightning activity data (such as lightning strike coordinates, lightning intensity, lightning type, lightning occurrence time, number of return strokes, etc.), meteorological data (such as atmospheric electric field, wind speed, humidity, etc.), and power equipment status data (such as voltage, temperature, load information of power equipment, etc.). It should be noted that due to the relatively stable geographical environment of the target facility, the geographical environment data (such as terrain, vegetation, soil type, etc.) has relatively stable influencing factors on the target facility being struck by lightning. Therefore, the geographical environment data can be discussed as real-time lightning-related data or not participate in the prediction as real-time lightning-related data, which is not limited here.

[0037] Of course, different types of real-time lightning-related data can be sampled in real time by different organizations and institutions according to specific circumstances, which is not limited in the embodiments of this application.

[0038] S120: Input the real-time lightning-related data into the lightning strike probability prediction model obtained by federated learning to obtain the lightning strike probability prediction result.

[0039] Among them, the lightning strike probability prediction model can be a model used to predict the lightning strike probability. In the embodiments of this application, the machine learning model is trained by federated learning to obtain this lightning strike probability prediction model. Correspondingly, the cumulative probability prediction result is the output result of this cumulative probability prediction model. It can be understood that this model inputs the real-time lightning-related data and outputs the lightning strike probability prediction result.

[0040] Of course, it should be noted that the lightning strike probability prediction model can be trained by means of federated learning. Federated learning is a distributed machine learning method that allows multiple participants (such as mobile devices, browsers, distributed servers, etc.) to jointly train a machine learning model without sharing the original data. Its core idea is to train the model on local devices and send the model updates (such as gradients or model parameters) to the central server for aggregation, thus forming a global model. The data types used to train the lightning strike probability prediction model are different, various, and large in quantity. If a common single model is used, the data transmission and coordination are complex, and the computational workload of local computing (or cloud computing) is huge, bringing a huge burden on the software and hardware for training the model. Therefore, local clients are set at the specific institutions or organizations where different types and various kinds of data are located. The local models are trained using the local clients and the local data of each institution or organization, and then the local parameters obtained from the training are fed back to the central server. The central server aggregates the local parameters uploaded by all local clients to obtain the global model parameters, thereby performing iterative training of the overall model and finally obtaining the cumulative probability prediction model. Exemplarily, for example, local clients can be set in the meteorological department to specifically train local models for meteorological data and lightning strike events; local clients can also be set in the power department to specifically train local models for the operating parameters of power equipment and lightning strike times, etc. The embodiments of the present application do not enumerate here exhaustively. Of course, all local models participating in federated learning can be any kind of machine learning model, for example, a neural network model.

[0041] S130. Determine the lightning strike intensity prediction result according to the real-time lightning-related data and the pre-trained lightning strike intensity prediction model.

[0042] Among them, the lightning strike intensity prediction model can be any kind of machine learning model. This model is used to predict the intensity of upcoming lightning strike events. This model inputs real-time lightning-related data and outputs the lightning strike intensity prediction result. Of course, it should be noted that the lightning strike intensity prediction model is not trained by means of federated learning. Since the types of various data required for the prediction of lightning strike probability are diverse, it is difficult to train in the same model. However, the lightning strike intensity prediction is carried out under the condition that the lightning strike probability is confirmed to be relatively high, and the types of reference data required for predicting the lightning strike intensity are less. Therefore, it can be trained in a single local or cloud model.

[0043] S140. Determine the lightning risk level according to the lightning strike probability prediction result and the lightning strike intensity prediction result.

[0044] Based on the lightning strike probability prediction result, further predict the lightning strike intensity, so as to determine the lightning risk of the target facility. Among them, the lightning risk level can be an index that quantifies the level of lightning risk. The predicted lightning strike probability can be a probability value. Similarly, the predicted lightning strike intensity can also be an intensity value. According to the high and low of the probability value and intensity value, and the corresponding relationship with the pre-defined lightning risk level, determine the risk level of the lightning strike event that the current target facility may encounter in the future.

[0045] S150. In response to the change of the lightning risk level, adjust the lightning strike protection strategy.

[0046] Among them, the lightning strike protection strategy can be a series of pre-set lightning strike defense measures and other plan contents according to the severity of the lightning strike event. When the lightning risk level changes, the plan corresponding to the lightning risk level can be activated. It can be understood that compared with the situation where the lightning strike risk level is relatively low, when the lightning strike risk level is relatively high, the corresponding lightning strike protection strategy needs to be more rigorous and complex.

[0047] The technical solution of the embodiment of the present application inputs real-time lightning-related data into the lightning strike probability prediction model trained by federated learning to obtain the lightning strike probability prediction result. Federated learning can avoid unifying different types of data of different organizations or institutions in different places, but set up local clients in different places for local model training, and then determine the global model through the federated learning system. This not only achieves the purpose of predicting the lightning strike probability, but also greatly reduces the difficulty of model training. Applying federated learning, which was originally used for data confidentiality, to the training of the lightning strike probability prediction model, and using different types of data related to lightning strikes for local training respectively, improves the efficiency of model training. The different types of data used for training ensure the accuracy of the lightning strike probability prediction, thus ensuring the prediction ability of lightning strikes; according to the real-time lightning-related data and the pre-trained lightning strike intensity prediction model, determine the lightning strike intensity prediction result, and use another prediction model to predict the possible lightning strike intensity. Predicting the lightning strike intensity on the basis of the lightning strike probability prediction can provide an accurate basis for subsequent means and strategies to deal with lightning strikes; according to the lightning strike probability prediction result and the lightning strike intensity prediction result, determine the lightning risk level, and adjust the lightning strike protection strategy when the lightning risk level changes, which can targetedly adjust the protection measures to deal with lightning strike events of different degrees, and improve the flexibility of the target facility for lightning strike protection.

[0048] In an alternative embodiment, the real-time lightning strike related data includes lightning strike frequency data, lightning strike intensity data, and lightning strike interval data. The lightning strike frequency data may be the frequency and number information of lightning strikes occurring on the target facility. The lightning strike intensity data may be the intensity information of lightning strikes occurring on the target facility. The lightning strike interval data may be the interval time information between consecutive lightning strikes on the target facility. The real-time lightning related data includes the above three aspects but is not limited to the above three aspects.

[0049] Determining the lightning strike intensity prediction result according to the real-time lightning related data and the pre-trained lightning strike intensity prediction model in S130 may include:

[0050] S131. According to the real-time lightning related data, respectively determine the temporal characteristics of the lightning strike frequency data, the lightning strike intensity data, and the lightning strike interval data.

[0051] Among them, the temporal characteristics, that is, the time series characteristics, may be the characteristic information of the real-time lightning related data changing with time. Analyze the lightning strike frequency data, the lightning strike intensity data, and the lightning strike interval data respectively to obtain the temporal characteristics of the three. Exemplarily, the dynamic time warping (DTW) technology or any one of the time domain analysis methods may be used to analyze the temporal characteristics of the real-time lightning related data, and the embodiments of the present application do not limit this.

[0052] S132. Input each temporal characteristic into the lightning strike intensity prediction model to determine the lightning strike intensity prediction result.

[0053] Input each temporal characteristic into the lightning strike intensity prediction model, and the model outputs the lightning strike intensity prediction result. It can be understood that the lightning strike intensity prediction model is trained for a specific area, such as the target facility. Record various information of the target facility being struck by lightning in a past historical period, analyze the temporal characteristics of these data, and use the temporal characteristics of these historical data to train the machine learning model so that the machine learning model has the ability to predict the upcoming lightning strike intensity according to the temporal characteristics of the lightning related data, that is, the trained lightning strike intensity prediction model. The embodiments of the present application do not limit the model basis and training process of the lightning strike intensity prediction model.

[0054] The lightning strike intensity prediction model and the lightning strike probability prediction model are two concepts. The lightning strike probability prediction model needs to consider the possible lightning strike situations in different geographical regions, different meteorological conditions, and different conditions. The lightning strike intensity prediction model is trained based on the historical data of a specific geographical area, that is, the target facility. For the target facility, the result of its intensity prediction is more accurate. On the basis of the lightning strike probability prediction, a special intensity prediction is carried out for the target facility, which further improves the accuracy of the lightning strike event prediction.

[0055] In another alternative embodiment, determining the lightning risk level according to the lightning strike probability prediction result and the lightning strike intensity prediction result in S140 may include:

[0056] S141. Calculate a lightning risk assessment value according to the lightning strike probability prediction result and a preset lightning strike probability weight, and the lightning strike intensity prediction result and a preset lightning strike intensity weight.

[0057] Among them, the lightning strike probability weight may be the weight used for calculating the lightning risk assessment value by the lightning strike probability prediction result; similarly, the lightning strike intensity weight may be the weight used for calculating the lightning risk assessment value by the lightning strike intensity prediction result; the lightning risk assessment value may be a quantitative index for evaluating the lightning strike risk. It can be understood that the lightning strike probability prediction result is a predicted probability value, and the lightning strike intensity prediction result is also a predicted intensity value. The two numerical values can be preprocessed by means such as normalization and standardization, then multiplied by their respective weights respectively, and calculated in the form of a weighted sum to obtain the lightning risk assessment value.

[0058] S142. Determine the lightning risk level according to the lightning risk assessment value in the corresponding relationship between the pre-stored lightning risk assessment value and the risk level.

[0059] Among them, the risk level can be divided into multiple different levels, corresponding to different severities of the lightning risk. Each risk level can respectively correspond to a numerical value interval of different risk assessment values. After calculating the lightning risk assessment value in the previous step, look up in this corresponding relationship to find the risk level corresponding to the numerical value interval as the final lightning risk level. It can be understood that the corresponding relationship between the lightning risk assessment value and the risk level can be set by relevant staff according to a large number of tests or manual experience, and this corresponding relationship can be stored in advance in the form of a table or a set, etc. The embodiments of the present application do not limit this.

[0060] In the above embodiment, by calculating the quantitative index of the lightning risk assessment value in the way of weighted sum, and then determining the lightning risk level, it provides a practical method for predicting and determining the severity of the lightning strike risk for the target facility, provides a reliable basis for adjusting the lightning strike protection strategy in the future, and helps to improve the flexibility of lightning strike protection.

[0061] In yet another alternative embodiment, adjusting the lightning strike protection strategy in response to a change in the lightning risk level in S150 may include:

[0062] S151. In response to the lightning risk level changing to a low level, activate the lightning rod and the preset grounding system of the target facility.

[0063] Among them, the lightning rod and the preset grounding system are basic lightning protection measures, which can fully cope with relatively mild lightning strike events. When the lightning risk level is converted to a low level, for example, when lightning strikes never occur and change to a low lightning strike risk level, or when the lightning strike risk level changes from medium to low, etc., at this time, when the lightning risk level is low, only the lightning rod and the grounding system need to be turned on to provide sufficient lightning protection ability for the target facility.

[0064] S152. In response to the change of the lightning risk level to medium, activate the transient overvoltage suppressor of the target facility.

[0065] Similarly, when the lightning strike risk level is converted to medium, for example, when the lightning strike risk level changes from low to medium, or when the lightning strike risk level changes from high to medium, etc., at this time, when the lightning risk level is medium, it is only necessary to further turn on the transient overvoltage suppressor of the target facility. The transient overvoltage suppressors on each key device in the target facility can effectively prevent lightning surges from damaging the devices.

[0066] S153. In response to the change of the lightning risk level to high, shut down the preset power area in the target facility.

[0067] Similarly, when the lightning risk level is converted to high, for example, when the lightning strike risk level is upgraded from low / medium to high, etc., at this time, when the lightning risk level is high, shut down some power areas in the target facility, that is, cut off some power lines, so as to protect the safety of the core devices.

[0068] In the above embodiments, in the face of the change of the lightning risk level, different coping strategies are invoked to protect the target facility, which further improves the flexibility of the target facility to cope with lightning strike events on the premise of ensuring the safety of the target facility.

[0069] Embodiment 2

[0070] Figure 2 The figure is a flowchart of training a lightning strike probability prediction model by federated learning provided in Embodiment 2 of this application. Embodiment 2 of this application introduces the training method of the lightning strike probability prediction model trained based on federated learning involved in the foregoing embodiments. As Figure 2 shown, it specifically includes:

[0071] S210. For each round of the federated learning process, send the global parameters obtained after the previous round of federated learning training to each local client, so that each local client trains the local model according to the global parameters and each local data, and determines the local parameters of this round of training; among them, the local data of different local clients are data related to different types of lightning strike events.

[0072] S220. Obtain the local parameters uploaded by each local client, and perform an aggregation operation on each local parameter in a preset manner to obtain new global parameters.

[0073] It should be noted that the initial models of the local models in different local clients are the same. Since the data in the training datasets used by different local clients are different, the model parameters determined during the training process are different.

[0074] When training for the first time, the central server distributes the initial global model parameters to each local client, which are used as the initial model parameters of each local model to participate in the training process. During the training process of each local model, different types of labeled data are used, such as temperature, humidity, wind speed, etc. in meteorological data, and the correlation probabilities of these data with past lightning strike events in historical data are used as labels.

[0075] During the training process, the model parameters of the local model are continuously iterated until the model loss converges. Then, the model parameters of this round of training are uploaded to the central server. The central server aggregates the local parameters of this round of training uploaded by each local client in a preset manner, such as directly calculating the average value, and the result is used as the global parameter for the next round of training.

[0076] In an alternative embodiment, the different types of lightning strike event-related data may include lightning activity data, meteorological data, geographical environment data, and power equipment status data.

[0077] It can be understood that different local clients can train the model based on different lightning strike event-related data according to specific situations. For example, the meteorological department can train the local model according to the meteorological data it obtains; the environmental department can train the local model according to the geographical environment data it obtains; the power department can set different local models for training according to the lightning activity data and power equipment status data. The embodiments of the present application do not list them all here.

[0078] In the technical solution of the embodiments of the present application, through the model training method of federated learning, distributed training is performed on different types of data from different sources, which can reduce the data transmission pressure of the overall training and the computing power pressure of model training, and provide a relatively efficient solution for lightning strike prediction.

[0079] Embodiment III

[0080] Figure 3 This is a schematic structural diagram of a lightning protection device provided in Embodiment III of the present application. As Figure 3 shown, the device 300 includes:

[0081] A data acquisition module 310, configured to acquire real-time lightning-related data of a target facility;

[0082] A probability prediction module 320, configured to input the real-time lightning-related data into a lightning strike probability prediction model obtained by federated learning to obtain a lightning strike probability prediction result;

[0083] An intensity prediction module 330, configured to determine a lightning strike intensity prediction result according to the real-time lightning-related data and a pre-trained lightning strike intensity prediction model;

[0084] A risk determination module 340, configured to determine a lightning risk level according to the lightning strike probability prediction result and the lightning strike intensity prediction result;

[0085] A lightning strike protection module 350, configured to adjust a lightning strike protection strategy in response to a change in the lightning risk level.

[0086] The technical solution of the embodiment of the present application inputs the real-time lightning-related data into a lightning strike probability prediction model obtained by federated learning to obtain a lightning strike probability prediction result. Federated learning can avoid unifying different types of data of different organizations or institutions in different regions, but instead set up local clients in each region for local model training, and then determine the global model through the federated learning system. This not only achieves the purpose of predicting the lightning strike probability, but also greatly reduces the difficulty of model training. Applying federated learning, which was originally used for data confidentiality, to the training of the lightning strike probability prediction model, and using different types of data related to lightning strikes for local training respectively, improves the efficiency of model training. The different types of data used for training ensure the accuracy of the lightning strike probability prediction, thus ensuring the prediction ability of lightning strikes; according to the real-time lightning-related data and a pre-trained lightning strike intensity prediction model, a lightning strike intensity prediction result is determined. Using another prediction model to predict the possible lightning strike intensity, and predicting the lightning strike intensity on the basis of the lightning strike probability prediction, can provide an accurate basis for subsequent means and strategies to deal with lightning strikes; according to the lightning strike probability prediction result and the lightning strike intensity prediction result, a lightning risk level is determined. When the lightning risk level changes, the lightning strike protection strategy is adjusted, which can specifically adjust the protection measures to cope with different degrees of lightning strike events, and improves the flexibility of the target facility for lightning strike protection.

[0087] In an optional implementation manner, the device 300 further includes a lightning strike probability prediction model training module, which may include:

[0088] A local training unit, for each round of the federated learning process, to send the global parameters obtained after the previous round of federated learning training to each local client, so that each local client trains the local model according to the global parameters and each local data, and determines the local parameters of this round of training; wherein, the local data of different local clients are data related to different types of lightning strike events;

[0089] A global update unit, for obtaining the local parameters uploaded by each local client, and performing an aggregation operation on each local parameter in a preset manner to obtain new global parameters.

[0090] In an alternative embodiment, the data related to different types of lightning strike events includes lightning activity data, meteorological data, geographical environment data, and power equipment status data.

[0091] In an alternative embodiment, the real-time lightning strike related data includes lightning strike frequency data, lightning strike intensity data, and lightning strike interval data;

[0092] The intensity prediction module 330 may include:

[0093] A timing feature determination unit, for respectively determining the timing features of the lightning strike frequency data, lightning strike intensity data, and lightning strike interval data according to the real-time lightning related data;

[0094] An intensity result prediction unit, for inputting each timing feature into the lightning strike intensity prediction model to determine the lightning strike intensity prediction result.

[0095] In an alternative embodiment, the risk determination module 340 may include:

[0096] An evaluation value determination unit, for calculating a lightning risk evaluation value according to the lightning strike probability prediction result and a preset lightning strike probability weight, as well as the lightning strike intensity prediction result and a preset lightning strike intensity weight;

[0097] A risk level determination unit, for determining the lightning risk level according to the lightning risk evaluation value in the pre-stored correspondence between the lightning risk evaluation value and the risk level.

[0098] In an alternative embodiment, the lightning protection module 350 may include:

[0099] A low-level response unit, for responding to the change of the lightning risk level to a low level, and starting the lightning rod and a preset grounding system of the target facility;

[0100] A medium-level response unit, for responding to the change of the lightning risk level to a medium level, and starting the transient overvoltage suppressor of the target facility;

[0101] A high-level response unit is used to cut off the power supply to a preset power area in a target facility in response to a high-level change in the lightning risk level.

[0102] The lightning protection device provided by the embodiments of the present application can execute the lightning protection methods provided by any embodiment of the present application, and has function modules and beneficial effects corresponding to executing each lightning protection method.

[0103] Embodiment 4

[0104] Figure 4 The structural schematic diagram of an electronic device 10 that can be used to implement the embodiments of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital processors, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or claimed herein.

[0105] As Figure 4 shown, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. Among them, the memory stores a computer program executable by the at least one processor. The processor 11 can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0106] A plurality of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0107] The processor 11 may be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the lightning protection method.

[0108] In some embodiments, the lightning protection method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the lightning protection method described above may be executed. Alternatively, in other embodiments, the processor 11 may be configured to execute the lightning protection method by any other suitable means (e.g., by means of firmware).

[0109] Various embodiments of the systems and techniques described above in this document may be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGA), application specific integrated circuits (ASIC), application specific standard products (ASSP), system-on-a-chip systems (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that may be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a special-purpose or general-purpose programmable processor that receives data and instructions from a storage system, at least one input device, and at least one output device, and transmits the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0110] The computer programs for implementing the methods of this application may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer programs are executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer programs may be executed entirely on the machine, partially on the machine, as a stand-alone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0111] In the context of this application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0112] To provide for interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can also be used to provide for interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic, speech, or tactile input).

[0113] The systems and techniques described herein can be implemented in a computing system that includes backend components (such as, for example, a data server), or a computing system that includes middleware components (such as, for example, an application server), or a computing system that includes frontend components (such as, for example, a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (such as, for example, a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0114] A computing system may include a client and a server. The client and the server are generally far from each other and usually interact via a communication network. The relationship between the client and the server is created by computer programs running on respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0115] The embodiments of the present application also disclose a computer program product, which includes a computer program that, when executed by a processor, implements the lightning protection method provided in any embodiment of the present application. This program product and the lightning protection methods disclosed in the embodiments of the present application belong to the same inventive concept, and thus will not be elaborated herein.

[0116] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in the present application can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present application can be achieved, and no limitation is imposed herein.

[0117] The above specific embodiments do not constitute a limitation to the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present application shall be included within the protection scope of the present application.

Claims

1. A lightning protection method, characterized in that: Applied to a central server, the method comprises: Obtain real-time lightning-related data of target facilities; Inputting the real-time lightning-related data into a lightning strike probability prediction model obtained through federated learning training to obtain a lightning strike probability prediction result; Determine a lightning strike intensity prediction result according to the real-time lightning related data and a pre-trained lightning strike intensity prediction model; Determining a lightning risk level according to the lightning strike probability prediction result and the lightning strike intensity prediction result; In response to a change in the lightning risk level, a lightning protection strategy is adjusted.

2. The method according to claim 1, characterized in that The lightning strike probability prediction model is trained in the following way: For each round of federated learning process, the global parameters obtained after the previous round of federated learning training are sent to each local client, so that each local client trains the local model according to the global parameters and each local data to determine the local parameters of this round of training; wherein the local data of different local clients are different types of lightning event related data; The local parameters uploaded by each of the local clients are obtained, and a preset aggregation operation is performed on each of the local parameters to obtain new global parameters.

3. The method according to claim 2, characterized in that The different types of lightning event related data include lightning activity data, meteorological data, geographical environment data and power equipment status data.

4. The method according to claim 1, characterized in that: The real-time lightning strike related data includes lightning strike frequency data, lightning strike intensity data and lightning strike interval data; Determining a lightning strike intensity prediction result according to the real-time lightning-related data and a pre-trained lightning strike intensity prediction model includes: According to the real-time lightning-related data, respectively determine the time series characteristics of the lightning strike frequency data, the lightning strike intensity data and the lightning strike interval data; Each of the time series features is input into the lightning strike intensity prediction model to determine the lightning strike intensity prediction result.

5. The method according to claim 1, characterized in that The determining of the lightning risk level according to the lightning strike probability prediction result and the lightning strike intensity prediction result includes: Calculating a lightning risk assessment value based on the lightning strike probability prediction result and the preset lightning strike probability weight, and the lightning strike intensity prediction result and the preset lightning strike intensity weight; According to the lightning risk assessment value, the lightning risk level is determined in a pre-stored correspondence between lightning risk assessment values ​​and risk levels.

6. The method according to claim 1, characterized in that The step of adjusting the lightning protection strategy in response to a change in the lightning risk level includes: In response to the lightning risk level changing to a low level, activating a lightning rod and a preset grounding system of the target facility; In response to the lightning risk level changing to a medium level, activating a transient overvoltage suppressor of the target facility; In response to the lightning risk level changing to a high level, shutting down a preset power area in the target facility.

7. A lightning protection device, characterized in that: Applied to the central server, including: A data acquisition module, used to obtain real-time lightning-related data of target facilities; A probability prediction module, used for inputting the real-time lightning-related data into a lightning strike probability prediction model obtained through federated learning training to obtain a lightning strike probability prediction result; An intensity prediction module, used to determine a lightning strike intensity prediction result based on the real-time lightning-related data and a pre-trained lightning strike intensity prediction model; A risk determination module, used to determine a lightning risk level according to the lightning strike probability prediction result and the lightning strike intensity prediction result; The lightning protection module is used to adjust the lightning protection strategy in response to changes in the lightning risk level.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the lightning protection method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the lightning protection method according to any one of claims 1 to 6 when executed.

10. A computer program product, characterized in that The computer program product comprises a computer program, which, when executed by a processor, implements the lightning protection method according to any one of claims 1 to 6.

Images