Electromagnetic safety restoring force digital twin training method and system

Abstract

The application provides an electromagnetic safety restoring force digital twin training method and system, constructs a test twin space, determines a test equipment group based on electromagnetic test data, and associates real interference data; determines interference dimensions based on equipment properties of each test equipment in the test equipment group, generates false interference data according to the interference dimensions; updates the state of the test equipment according to the real interference data, generates actual data, and directionally replaces the running data of the corresponding dimensions based on the false interference data to generate false data; collects calling information of the training end to the auxiliary plug-in, generates error area guide data according to the comparison information of the calling information, the actual data and the false data, and the auxiliary plug-in one-to-one corresponds to the running data of each dimension, so that the real interference data and the false interference data can be fused, the training complexity is improved, and the disposal efficiency of an operation and maintenance personnel for an electromagnetic safety event is improved.

Description

Technical Field

[0001] This invention relates to data processing technology, and more particularly to a digital twin training method and system for electromagnetic safety restoring force. Background Technology

[0002] In complex electromagnetic environments such as power systems and industrial control, equipment faces the risk of failure due to various electromagnetic interferences, and there is an urgent need for an efficient safety resilience training system. For example, when a transformer in a substation is subjected to electromagnetic pulse interference from lightning, it is necessary to quickly locate the faulty equipment and implement recovery strategies. Traditional electromagnetic safety training often uses fixed fault scenario simulations, such as assuming a certain line voltage is abnormal. After repeated training, trainees are prone to developing inertia thinking, which leads to diagnostic deviations when facing dynamic electromagnetic interference in actual combat.

[0003] Currently, traditional training models typically pre-set fixed fault types and locations, lack simulation of the dynamic characteristics of electromagnetic interference, and the fault scenarios are usually fixed types. Furthermore, they cannot dynamically guide the actual training progress of domestic and international trainees and lack personalized training guidance support.

[0004] Therefore, how to integrate real and spoof interference data to increase training complexity and thus improve the efficiency of operations and maintenance personnel in handling electromagnetic safety incidents has become an urgent problem to be solved. Summary of the Invention

[0005] This invention provides a digital twin training method and system for electromagnetic safety resilience, which can fuse real interference data and spoof interference data to increase training complexity and thereby improve the efficiency of maintenance personnel in handling electromagnetic safety incidents.

[0006] A first aspect of the present invention provides a digital twin training method for electromagnetic safety restoring force, comprising:

[0007] Construct a test twin space, determine the test equipment group based on electromagnetic test data, and correlate it with real interference data;

[0008] Based on the equipment attributes of each test device in the test equipment group, the interference dimension is determined, and false interference data is generated according to the interference dimension.

[0009] The test equipment is updated with the real interference data to generate actual data. The corresponding dimension of the running data is replaced with the false interference data to generate false data.

[0010] The system collects call information from the training end to the auxiliary plugins, and generates misleading guidance data based on the comparison information between the call information and actual and fake data. Each auxiliary plugin corresponds to one of the running data in each dimension.

[0011] Optionally, in one possible implementation of the first aspect, the construction of the test twin space, determining the test equipment group based on electromagnetic test data, and associating it with real interference data, includes:

[0012] A corresponding test twin space is constructed based on the target device, and the test twin space includes multiple twin devices;

[0013] The system receives electromagnetic test data input from the interference terminal, including the number of interferences, interference radius, electromagnetic interference type, and electromagnetic interference intensity.

[0014] Based on the number of interferences, multiple coordinate points are selected as interference locations, and the interference area is obtained according to the interference locations and interference radius.

[0015] The twin devices that generate electromagnetic effects within the interference area are used as test devices. The test devices located in the same interference area are counted to obtain a test device group.

[0016] The actual interference data of each test device is obtained based on the electromagnetic interference type and intensity, and the actual interference data is correlated with each test device in the test device group.

[0017] Optionally, in one possible implementation of the first aspect, obtaining the actual interference data of each of the test devices based on the electromagnetic interference type and electromagnetic interference intensity includes:

[0018] The test position of the test equipment is obtained, and the interference distance corresponding to each test equipment is obtained based on the test position and the interference position.

[0019] The interference coefficient is obtained by the ratio of the preset reference distance and the interference distance corresponding to the electromagnetic interference type. The electromagnetic interference data of each test device corresponding to the electromagnetic interference type is obtained by the product of the interference coefficient and the electromagnetic interference intensity.

[0020] Based on the electromagnetic interference data, obtain the actual interference data of the test equipment.

[0021] Optionally, in one possible implementation of the first aspect, determining the interference dimension based on the device attributes of each test device in the test device group, and generating false interference data according to the interference dimension, includes:

[0022] Based on the real interference data, the actual interference dimension corresponding to the electromagnetic interference type is obtained, and the actual interference dimension is used as the elimination dimension.

[0023] Remove the excluded dimensions from the obstacle interference dimension set to obtain multiple candidate obstacle dimensions. The interference dimension set includes all preset fault dimensions of the device.

[0024] Based on the test equipment, retrieve the corresponding equipment logs, and determine the anomaly coefficient of the candidate obstacle dimension of the corresponding test equipment in the historical period according to the equipment logs;

[0025] Based on the anomaly coefficients, the candidate obstacle dimensions are sorted in descending order to obtain the obstacle dimension sequence;

[0026] Based on the number of configurations, the candidate obstacle dimensions in the obstacle dimension sequence are selected as interference dimensions in sequence.

[0027] Anomaly analysis is performed on the corresponding dimension data in the device logs based on the interference dimension statistics, and the obtained abnormal data is regarded as false interference data.

[0028] Optionally, in one possible implementation of the first aspect, determining the anomaly coefficient of the candidate obstacle dimension of the corresponding test device within a historical period based on the device log includes:

[0029] Obtain the runtime of the components in the test equipment corresponding to the candidate obstacle dimension, and count the number of abnormal data in the equipment log based on the runtime;

[0030] The anomaly coefficient is obtained by the ratio of the number of anomalies to the reference number of anomalies for the corresponding candidate obstacle dimension.

[0031] Optionally, in one possible implementation of the first aspect, the step of updating the state of the test equipment based on the real interference data to generate actual data, and then selectively replacing the operating data of the corresponding dimension based on the false interference data to generate false data, includes:

[0032] The operating state of the test equipment after interference is determined based on the actual interference data to obtain the interference state. The interference state is then used to update the test equipment to obtain the actual data.

[0033] Based on the aforementioned false interference data, the device logs of the corresponding dimensions will be used as change logs;

[0034] Based on the false interference data, obtain the log data corresponding to the interference dimension in the change log, retrieve the false interference data to replace the log data, and generate false data.

[0035] Optionally, in one possible implementation of the first aspect, the collection of training terminal call information for auxiliary plugins, and the generation of misleading guidance data based on the comparison information between the call information and actual data and spurious data, include:

[0036] The duration of the training end's call to the auxiliary plugin is counted in real time, and the auxiliary plugin whose call duration is longer than a preset duration is marked as the judgment plugin;

[0037] When the judgment plugin corresponds to false data, the judgment plugin is determined to be a guidance plugin, and the guidance level is determined according to the training level of the training end;

[0038] Based on the aforementioned guidance level, actual and false data are processed to generate misleading guidance data.

[0039] Optionally, in one possible implementation of the first aspect, the processing of actual and false data based on the guidance level to generate misleading guidance data includes:

[0040] Based on the historical diagnostic success rate of the training end, a guidance level is determined, which includes at least a diagnostic logic level, a dimension correction level, and a fault location level.

[0041] Based on the diagnostic logic level, one-dimensional guidance data is generated to elicit the misunderstanding.

[0042] Based on the aforementioned dimensional correction level, two-dimensional guidance data for misconception extraction and dimensional introduction is generated;

[0043] Based on the fault location level, three-dimensional guiding data is generated to elicit misconceptions, introduce dimensions, and locate data.

[0044] Optionally, in one possible implementation of the first aspect, generating three-dimensional guiding data for misconception identification, dimension introduction, and data location based on the fault location level includes:

[0045] Based on the plugin name of the guide plugin, a negative prompt message is generated, and based on the negative prompt message, a misconception prompt message is generated;

[0046] Based on the plugin name of the auxiliary plugin corresponding to the actual interference dimension, generate correctness prompt information, and based on the correctness prompt information, generate dimension introduction information;

[0047] Receive the selection information of the dimension to be introduced by the training end, determine the dimension to be introduced, and obtain the specific abnormal entries in the introduced dimension caused by the real interference data.

[0048] The specific abnormal entries are marked for prominence to generate data location information;

[0049] Based on the combined information of misconception extraction, dimension introduction, and data positioning, three-dimensional guidance data is obtained.

[0050] A second aspect of the present invention provides an electromagnetic safety restoring force digital twin training system, comprising:

[0051] The association module is used to construct a test twin space, determine the test equipment group based on electromagnetic test data, and associate it with real interference data;

[0052] The determination module is used to determine the interference dimension based on the device attributes of each test device in the test device group, and generate false interference data according to the interference dimension.

[0053] The update module is used to update the status of the test equipment based on the real interference data, generate actual data, and replace the corresponding dimension of the running data based on the false interference data to generate false data.

[0054] The generation module is used to collect the call information of the auxiliary plugins from the training end, and generate misleading guidance data based on the comparison information of the call information with the actual data and fake data. The auxiliary plugins correspond one-to-one with the running data of each dimension.

[0055] A third aspect of the present invention provides an electronic device, comprising: a memory, a processor, and a computer program, wherein the computer program is stored in the memory, and the processor executes the computer program to perform the methods described in the first aspect of the present invention and various possible methods related to the first aspect.

[0056] A fourth aspect of the present invention provides a storage medium storing a computer program, which, when executed by a processor, is used to implement the first aspect of the present invention and various methods possibly involved in the first aspect.

[0057] The beneficial effects of this invention are as follows:

[0058] 1. This invention can fuse real and spoof interference data, increasing training complexity and thus improving the efficiency of maintenance personnel in handling electromagnetic safety incidents. Firstly, this invention constructs a test twin space and associates it with real interference data to achieve realistic simulation of electromagnetic safety training scenarios. Specifically, this invention constructs a digital twin model based on the target device, receives electromagnetic test data input from the interfering end, generates interference regions in the twin space, selects affected test device groups, calculates the interference distance based on the electromagnetic interference type and device location, and generates realistic interference data through interference coefficients, thus solving the problem of insufficient realism in traditional fixed-scenario training.

[0059] 2. This invention can generate spurious interference data that complements real interference through device attribute analysis and historical log mining, thereby increasing training complexity. First, actual interference dimensions are removed from the real interference data to obtain candidate obstacle dimensions. Anomaly coefficients for each dimension are calculated and sorted in descending order of anomaly coefficients to generate an obstacle dimension sequence. Dimensions with higher anomaly coefficients are selected based on the number of configurations, and corresponding anomaly data is extracted from the device logs as spurious interference data. This ensures that the spurious data complements the real interference dimensions, effectively simulating actual device failure modes, increasing training complexity, and facilitating subsequent improvements in the efficiency of maintenance personnel in handling electromagnetic safety incidents.

[0060] 3. This invention can generate multi-dimensional guidance information by collecting trainee behavior data, thereby achieving personalized training support. It tracks the real-time call duration of auxiliary plugins on the training end. When the call duration exceeds a preset duration and corresponds to spurious data, it generates three levels of guidance data based on the training level. This tiered guidance mechanism improves the diagnostic efficiency for trainees at different levels. Attached Figure Description

[0061] Figure 1 A flowchart of a digital twin training method for electromagnetic safety restoring force provided by the present invention;

[0062] Figure 2 A schematic diagram of the structure of an electromagnetic safety restoring force digital twin training system provided by the present invention;

[0063] Figure 3 This is a schematic diagram of the hardware structure of an electronic device provided by the present invention. Detailed Implementation

[0064] The technical solution of the present invention will be described in detail below with reference to specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0065] like Figure 1 As shown, this invention provides a flowchart of a digital twin training method for electromagnetic safety resilience. This method includes:

[0066] S1. Construct a test twin space, determine the test equipment group based on electromagnetic test data, and associate it with real interference data.

[0067] It should be noted that in traditional electromagnetic training models, the equipment faults set are usually fixed. As a result, when personnel enter the model for maintenance training multiple times, they will quickly identify the corresponding fault causes due to inertia, which will affect the training effect. However, this solution can configure real interference data and spoof interference data according to the actual equipment operation to improve the training effect.

[0068] It is understandable that a corresponding digital twin space is constructed by using actual target equipment and receiving electromagnetic test data set by configuration personnel. This allows for the determination of test equipment groups based on the electromagnetic test data, the association of real interference data with the equipment, and the setting of real fault data. This facilitates the subsequent configuration of false interference data, thereby increasing the difficulty of training.

[0069] Among them, the test twin space is a digital twin space for electromagnetic safety training, the electromagnetic test data is the configuration data for electromagnetic interference, the test equipment group is a collection of equipment for fault setting, and the real interference data is the interference data that actually affects equipment faults.

[0070] In some embodiments, the specific implementation of step S1 (constructing the test twin space, determining the test equipment group based on electromagnetic test data, and associating it with real interference data) includes:

[0071] S11, construct a corresponding test twin space based on the target device, wherein the test twin space includes multiple twin devices.

[0072] Understandably, the digital twin model of the target device needs to include multi-dimensional information such as its physical structure, electrical characteristics, and functional logic. The collaborative operation of multiple twin devices can simulate system interaction in complex electromagnetic environments, such as industrial scenarios where communication devices, sensors, and controllers coexist. The constructed test twin space has high simulation accuracy and can accurately reflect the electromagnetic response characteristics of the target device in the real environment, providing a reliable virtual platform for subsequent interference testing.

[0073] The target device refers to the equipment used for electromagnetic simulation training, and the twin device refers to the twin digital device corresponding to the target device.

[0074] S12, receive electromagnetic test data input from the interference end, the electromagnetic test data including the number of interferences, interference radius, electromagnetic interference type and electromagnetic interference intensity.

[0075] It is understandable that the interference end is the terminal that configures the interference information, the interference quantity is the actual number of devices that need to be interfered with, the interference radius is the radius of the range of electromagnetic interference generated by the interference information, the electromagnetic interference type is the type of dimension that can be interfered with by electromagnetic fields, such as magnetic fields, voltage, temperature sensors, etc., and the electromagnetic interference intensity is the electromagnetic intensity that is used to perform electromagnetic interference.

[0076] S13, select multiple coordinate points as interference locations based on the number of interferences, and obtain the interference area according to the interference location and interference radius.

[0077] It is understandable that the interference quantity input from the interference end is obtained by selecting interference coordinates in the test twin space to obtain the corresponding number of interference positions. The interference position and interference radius are used to obtain the interference area that the corresponding interference information at each interference position can produce interference effects, so as to subsequently determine the devices affected by interference within the corresponding interference area.

[0078] Among them, the interference location is the location where electromagnetic interference information is transmitted, and the interference area is the range within which electromagnetic interference information can produce interference effects.

[0079] S14, the twin devices that generate electromagnetic influence in the interference area are used as test devices, and the test devices located in the same interference area are counted to obtain a test device group.

[0080] It is understandable that the test equipment is a twin device that generates electromagnetic effects within the interference area, and the test equipment group consists of test equipment located within the same interference area, which facilitates subsequent analysis of the test results.

[0081] S15, obtain the actual interference data of each of the test devices according to the electromagnetic interference type and electromagnetic interference intensity, and associate the actual interference data with each test device in the test device group.

[0082] It is understandable that different types of electromagnetic interference are affected differently by statistical electromagnetic interference intensity, and therefore the interference data generated on the test equipment are also different. Therefore, the actual interference data after the corresponding test equipment is affected by interference can be determined according to the actual electromagnetic interference type and intensity, so as to establish data correlation with the test equipment and facilitate subsequent training simulations by personnel.

[0083] In some embodiments, a specific implementation of step S15 (obtaining the actual interference data of each test device based on the electromagnetic interference type and intensity) includes:

[0084] S151, obtain the test position of the test equipment, and obtain the interference distance corresponding to each test equipment based on the test position and the interference position.

[0085] It is understandable that the relative relationship between the test location and the interference location determines the length of the electromagnetic wave propagation path, i.e. the interference distance. By determining the interference distance through the test location and the interference location, the attenuation of the electromagnetic interference intensity can be calculated, thereby obtaining the actual intensity of electromagnetic interference affecting the test equipment.

[0086] The interference distance is the distance between the test equipment and the intensity of the emitted electromagnetic interference.

[0087] S152, the interference coefficient is obtained based on the ratio of the preset reference distance and the interference distance corresponding to the electromagnetic interference type. Based on the product of the interference coefficient and the electromagnetic interference intensity, the electromagnetic interference data of each test device corresponding to the electromagnetic interference type is obtained.

[0088] It is understandable that different types of electromagnetic interference are affected by battery interference to varying degrees. That is, the electromagnetic influence relationship generated at different distances for each type of electromagnetic interference can be retrieved to determine the corresponding interference coefficient, so as to obtain electromagnetic interference data and thus determine the true interference data of the test equipment.

[0089] Among them, the preset reference distance is the unit distance corresponding to the attenuation of electromagnetic interference intensity under standard conditions. For example, the interference impact level is reduced by 10% for every meter the test equipment is away from the interference source. The interference coefficient is the influence coefficient of electromagnetic interference intensity on the current test equipment. The electromagnetic interference data is the interference data that acts on the test equipment after propagation through the interference distance, that is, the product of the interference coefficient and the electromagnetic interference intensity.

[0090] S153, Based on the electromagnetic interference data, obtain the actual interference data of the test equipment.

[0091] Understandably, electromagnetic interference data, such as electric field strength and frequency, needs to be converted into actual effects that the equipment can perceive, such as voltage fluctuations. In this way, the values ​​of the test equipment after receiving interference can be determined so that they can be correlated with the test equipment later.

[0092] For example, when the testing device is a voltage sensor, the normal voltage reading is 12V. After receiving electromagnetic interference, the actual interference data can be obtained as 16V.

[0093] S2, determine the interference dimension based on the device attributes of each test device in the test device group, and generate false interference data according to the interference dimension.

[0094] Understandably, in order to improve the training effect, spurious interference data can be added to the real interference data to increase the training complexity. Therefore, when setting spurious interference data, it is necessary to first determine the interference dimension corresponding to the spurious interference data. That is, the interference dimension corresponding to the spurious interference data cannot be the same as the dimension corresponding to the real interference data. Therefore, the interference dimension corresponding to the spurious interference data can be determined by the device attributes of the testing equipment, so that the spurious data can be combined with the real data later to increase the training difficulty and improve the training effect.

[0095] Among them, the interference dimension is the information dimension corresponding to the false interference data. For example, it can be temperature. That is, when the real interference data does not contain temperature interference, the interference dimension corresponding to the false interference data can be the temperature dimension, so as to increase the complexity of the training simulation. False interference data is artificially set false data, that is, data that does not actually cause abnormal equipment operation.

[0096] In some embodiments, a specific implementation of step S2 (determining the interference dimension based on the device attributes of each test device in the test device group, and generating false interference data according to the interference dimension) includes:

[0097] S21, based on the real interference data, obtain the actual interference dimension corresponding to the electromagnetic interference type, and use the actual interference dimension as the elimination dimension.

[0098] It is understandable that the electromagnetic interference type corresponds to the information type of the actual interference data. For example, when the actual interference data is voltage data, the corresponding electromagnetic interference type is voltage, and thus the actual interference dimension can be obtained as the voltage dimension.

[0099] Among them, the actual interference dimension is the information dimension corresponding to the real interference data, such as voltage, and the elimination dimension is the information dimension that needs to be deleted, so as to form a complementary training data structure of "real-false" dimensions in the future, prevent the training end from forming a path dependency on a single dimension interference, and improve the cross-dimensional fault diagnosis capability.

[0100] By implementing the above methods, the actual interference dimension can be used as the elimination dimension, which can avoid the overlap between the dimensions of false data and real data.

[0101] S22, remove the eliminated dimensions from the obstacle interference dimension set to obtain multiple candidate obstacle dimensions. The interference dimension set includes all preset fault dimensions of the device.

[0102] Understandably, in order to identify the interference dimensions corresponding to the spurious interference data, the dimensions to be removed can be deleted from the set of interference dimensions, so as to obtain multiple candidate obstacle dimensions to choose from.

[0103] Among them, the interference dimension set is a pre-set dimension set containing multiple fault dimensions, and the candidate obstacle dimensions are obstacle information dimensions waiting to be filtered. When the obstacle interference dimension contains multiple preset fault dimensions such as voltage, current, temperature, and humidity, and the voltage dimension is removed, multiple candidate obstacle dimensions such as current, temperature, and humidity can be obtained, so as to determine the corresponding dimension for setting false interference data in the multiple candidate obstacle dimensions.

[0104] S23, retrieve the corresponding device logs based on the test device, and determine the anomaly coefficient of the candidate obstacle dimension of the corresponding test device in the historical period according to the device logs.

[0105] Understandably, in order to identify false interference data, false interference data can be set based on the corresponding device logs. Device logs record historical device data. By analyzing the frequency of anomalies in candidate dimensions over historical periods, such as the temperature dimension having 3 anomalies in 10 days, its "susceptibility" can be quantified. Dimensions with higher anomaly coefficients are more likely to malfunction in actual operation. Prioritizing them as false interference dimensions can improve the authenticity of training data.

[0106] Among them, the device log is the historical log of the test device, the historical period is a pre-set time period, and the anomaly coefficient is the evaluation coefficient of the corresponding anomaly in the candidate obstacle dimension of the test device.

[0107] In some embodiments, a specific implementation of step S23 (determining the anomaly coefficient of the candidate obstacle dimension of the corresponding test device within a historical period based on the device log) includes:

[0108] S231, obtain the runtime of the component in the test device corresponding to the candidate obstacle dimension, and count the number of abnormal data in the device log based on the runtime.

[0109] It is understandable that some anomalies are due to normal operation losses caused by long runtime. Therefore, the corresponding anomaly dimension can be used as a distracting dimension for false data, so as to treat the normal losses as a distracting factor and increase the complexity of the equipment anomaly.

[0110] Among them, runtime is the usage time of the corresponding component of the test equipment, such as 2 years; abnormal data is the abnormal data that appears in the equipment log, such as the normal dimension is 24° and the abnormal data is the temperature of 30°; and the number of abnormal data is the number of times abnormal data appears.

[0111] Through the above implementation methods, the present invention can obtain the number of anomalies of components in the test equipment, so as to subsequently filter out the interference dimension corresponding to false interference data based on the number of anomalies.

[0112] S232, the anomaly coefficient is obtained based on the ratio of the number of anomalies to the reference number of anomalies corresponding to the dimension of the candidate obstacle.

[0113] Understandably, the reference anomaly count is the expected failure frequency based on equipment design standards or historical big data. It is pre-set. By comparing the actual anomaly count with the reference value, the degree of failure deviation in different dimensions can be standardized. The generated anomaly coefficient has cross-dimensional comparability, which allows high-frequency failure dimensions and low-frequency dimensions to be uniformly ranked, providing a quantitative standard for subsequent priority selection of interference dimensions.

[0114] The anomaly coefficient is the evaluation coefficient for the dimension in which anomalies occur, which is the ratio of the number of anomalies to the reference number of anomalies for the corresponding candidate obstacle dimension.

[0115] S24. Arrange the candidate obstacle dimensions in descending order according to the anomaly coefficient to obtain the obstacle dimension sequence.

[0116] Understandably, the anomaly coefficient reflects the failure tendency of the candidate obstacle dimensions in historical operation. The descending order can give priority to high-frequency failure dimensions so that high-frequency candidate obstacle dimensions can be quickly identified in the future, ensuring that the generated false interference data is closer to the actual failure mode of the equipment.

[0117] Among them, the obstacle dimension sequence is the dimension sequence obtained by arranging the dimensions of the candidate obstacles in descending order.

[0118] S25, based on the configuration quantity, select the candidate obstacle dimensions from the obstacle dimension sequence as interference dimensions.

[0119] It is understandable that the configuration quantity is the number of fake interference data that the personnel pre-determine based on the set complexity. For example, it can be 3, 4, etc. That is, the higher the complexity, the more configurations are corresponding to, and the lower the complexity, the fewer configurations are corresponding to.

[0120] S26, perform anomaly analysis on the corresponding dimension data in the device log based on the interference dimension statistics, and use the obtained abnormal data as false interference data.

[0121] Understandably, once the interference dimension is determined, the corresponding dimension data in the device logs can be statistically analyzed to filter and analyze the numerous dimensions of data, obtain abnormal data, and then use this abnormal data as false interference data for subsequent association with the corresponding test equipment.

[0122] For example, when the interference dimension is temperature, if we collect temperature data from the past month, and then filter and analyze the temperature data from that month, the normal temperature is 24°C, and we determine that 30°C is an abnormal temperature, then we can treat 30°C as false interference data.

[0123] S3, update the status of the test equipment based on the real interference data to generate actual data, and replace the corresponding dimension of the running data based on the false interference data to generate false data.

[0124] Understandably, real interference data reflects the device's response in a real electromagnetic environment. Therefore, the real interference data is used to update the state of the test device, for example, changing the normal operating state of the device to a stopped state, to obtain the actual data. The identified false interference data is then used to replace the corresponding dimension of the operating data to obtain false data. The generated actual data and false data form a double data interference, increasing the complexity of the system simulation.

[0125] The actual data refers to the device data corresponding to the actual interference dimension in the test twin space, while the spoof data refers to the interference simulation training data set in the test twin space.

[0126] In some embodiments, the specific implementation of step S3 (updating the status of the test equipment based on the real interference data to generate actual data, and replacing the operating data of the corresponding dimension based on the false interference data to generate false data) includes:

[0127] S31, determine the operating state of the test equipment after interference based on the actual interference data, obtain the interference state, update the test equipment with the interference state, and obtain the actual data.

[0128] It is understandable that, since real interference data corresponds to different operating states of the test equipment, for example, when the difference between the real interference data and the normal operating state is small, the operating state of the test equipment may be an abnormal prompt, but it can still run. When the real interference data deviates significantly from the normal operating state of the equipment, a serious abnormality will occur, causing the equipment to stop operating. Therefore, the interference state of the test equipment after interference can be determined based on the real interference data, and the operating state of the test equipment in the test twin space can be updated to obtain the actual data, such as updating the test equipment to the shutdown state.

[0129] S32, based on the false interference data, the device logs of the corresponding dimension are used as change logs.

[0130] It is understandable that the device logs corresponding to the interference dimension are determined based on the false interference data and used as change logs so that the data in the change logs can be replaced in the future, thereby generating false data.

[0131] The change log is the log of the device that needs to have its data changed or replaced.

[0132] S33, Based on the false interference data, obtain the log data corresponding to the interference dimension in the change log, retrieve the false interference data to replace the log data, and generate false data.

[0133] It is understandable that the log data is data that changes the corresponding interference dimension of the log, such as temperature data. Therefore, the selected log data can be replaced with fake interference data to obtain fake data, so that the interference personnel can conduct simulation training and improve the training effect.

[0134] S4. Collect the call information of the auxiliary plugins from the training end, and generate misleading guidance data based on the comparison information of the call information with the actual data and the fake data. The auxiliary plugins correspond one-to-one with the running data of each dimension.

[0135] Understandably, the training end's behavior in calling auxiliary plugins reflects its fault diagnosis approach. By analyzing the call duration, cognitive biases of trainees can be identified, such as over-reliance on a certain plugin without being able to locate the fault. By comparing the call information with actual or spoofed data, it can be determined whether trainees are confusing the impact dimensions of real and spoofed interference. The purpose of generating misconception guidance data is to specifically correct diagnostic biases. For example, when trainees mistakenly take spoofed software faults as real electromagnetic interference, different levels of guidance prompts can be provided to enable personnel to conduct normal training simulations.

[0136] The training terminal is the information terminal for personnel conducting electromagnetic simulation training. The auxiliary plugin is a plugin that assists the training terminal in viewing data. It is also responsible for monitoring the decision path and time consumption of the training terminal when processing its corresponding dimension logs and feeding back this information for misconception identification. The misconception guidance data is information data that guides and prompts for diagnosing misconceptions.

[0137] In some embodiments, the specific implementation of step S4 (collecting the call information of the auxiliary plugin by the training end, and generating misleading guidance data based on the comparison information of the call information with actual data and fake data) includes:

[0138] S41, Real-time statistics of the call duration of the auxiliary plugin by the training end, and marking the auxiliary plugin whose call duration is longer than the preset duration as the judgment plugin.

[0139] It is understandable that when the training end calls and views data of a certain dimension for a long time, it indicates that the current dimension is diagnostic data for personnel to perform equipment maintenance. Therefore, in order to determine whether the information called by the training end for a long time is a real interference dimension, the call duration of the auxiliary plugin by the training end can be counted for subsequent data analysis.

[0140] The call duration is the time it takes for the training end to call the auxiliary plugin to view information, the preset duration is the pre-set basic viewing duration, and the plugin is determined to be an auxiliary plugin whose call duration is greater than the preset duration.

[0141] It should be noted that different dimensions of data have corresponding auxiliary plugins. For example, when viewing temperature data, you can call the temperature plugin to perform statistical analysis on temperature data from multiple days, and when viewing voltage data, you can call the voltage plugin.

[0142] S42, when the judgment plugin corresponds to false data, the judgment plugin is determined to be a guidance plugin, and the guidance level is determined according to the training level of the training end.

[0143] It is understandable that when false data is found in the judgment plugin, it means that the training end is caught in the diagnosis of false interference data. Therefore, the judgment plugin corresponding to the false data can be used as a guide plugin, and the corresponding guide level can be determined according to the training level of the training end, so as to generate corresponding misleading guide data in the future, so that the trainer can identify the correct real interference data in a timely manner.

[0144] Among them, the guidance plugin is a judgment plugin for generating guidance information, the training level is the level corresponding to the training end, that is, the higher the efficiency of the training in the historical period, the higher the corresponding level, indicating that the maintenance capability of the training end is stronger, and then only simple guidance information needs to be generated. The guidance level is the level of generating misconception guidance information.

[0145] The above implementation methods can achieve tiered guidance, adapt to different stages of cognitive ability, reduce restrictions on trainees' thinking, and improve their self-diagnosis ability.

[0146] S43, Based on the guidance level, process the actual data and false data to generate misleading guidance data.

[0147] Understandably, the guidance level determines the complexity and information content of the guidance data. Therefore, actual data and spurious data can be processed and updated according to the guidance level to generate misleading guidance data, so that the training end can perform timely anomaly repair and improve repair efficiency.

[0148] In some embodiments, a specific implementation of step S43 (processing actual data and spoof data based on the guidance level to generate misleading guidance data) includes:

[0149] S431, Based on the historical diagnostic success rate of the training end, determine the guidance level, which includes at least the diagnostic logic level, the dimension correction level, and the fault location level.

[0150] It is understandable that the higher the success rate of diagnosis and repair in the training end during the historical period, the stronger the diagnostic capability of the training end, and consequently, the higher the guidance level. Therefore, the diagnostic success rate of the training end can be retrieved to identify the corresponding guidance level.

[0151] The guidance levels include diagnostic logic level, dimension correction level, and fault location level. The diagnostic logic level is the level at which guidance prompts are needed for diagnostic logic. The dimension correction level is the level at which guidance prompts are needed for correcting the judgment dimensions. The fault location level is the level at which guidance prompts are needed to locate the actual interference fault.

[0152] It should be noted that there is a correlation between the diagnostic success rate and the guidance level. The range of guidance information corresponding to different levels is different, so as to provide different guidance information for training at different levels in order to improve training effectiveness.

[0153] S432, Based on the diagnostic logic level, generate one-dimensional guidance data to identify the misunderstanding.

[0154] Understandably, the diagnostic logic level targets fundamental misconceptions, such as confusing cause and effect, and the generated one-dimensional guiding data focuses on correcting deviations in the diagnostic path.

[0155] Among them, the one-dimensional guiding data is the one-dimensional guiding data that leads to misunderstandings.

[0156] For example, when a trainer continuously calls the temperature plugin corresponding to fake data, the system generates a "dimensional error" message to guide them out of the inherent calling dimension.

[0157] Through the above implementation methods, one-dimensional guidance data is generated, which enables trainers to reduce invalid plugin calls, shorten the diagnostic path, and facilitate the establishment of a correct fault diagnosis logic framework on the training side.

[0158] S433, Based on the aforementioned dimension correction level, generate two-dimensional guidance data for misconception extraction and dimension introduction.

[0159] Understandably, when the correction level for the corresponding dimension is determined on the training end, not only is misconception data generated, but also dimension introduction data is generated to prompt the personnel for the correct true interference dimension, thereby improving the training efficiency of the training end.

[0160] The two-dimensional guidance data includes data from two dimensions: misconception introduction and dimension introduction.

[0161] S434, Based on the fault location level, generate three-dimensional guidance data for misconception identification, dimension introduction, and data location.

[0162] Understandably, the fault location level adds specific data locations to the two-dimensional guidance, improving the accuracy of the guidance data and making it easier for the training end to gradually determine the real interference data for maintenance training, thereby improving training efficiency.

[0163] The three-dimensional guidance data includes guidance prompts in three dimensions: misconception identification, dimension introduction, and data positioning.

[0164] In some embodiments, the specific implementation of step S434 (generating three-dimensional guidance data for misconception identification, dimension introduction, and data positioning based on the fault location level) includes:

[0165] S4341, Generate negative prompt information based on the plugin name of the guide plugin, and generate misconception prompt information based on the negative prompt information.

[0166] It is understandable that the plugin name is the name of the guiding plugin, such as temperature plugin, voltage plugin, and the negative prompt message is the prompt message that negates the dimension of the plugin.

[0167] For example, when the plugin name of the bootloader is determined to be the temperature plugin, and the actual interference data corresponds to the voltage dimension, the negative prompt message that can be generated can be "not the temperature dimension", and the misleading prompt message can be "information call outside the temperature dimension".

[0168] S4342, Generate correctness prompt information based on the plugin name of the auxiliary plugin corresponding to the actual interference dimension, and generate dimension introduction information based on the correctness prompt information.

[0169] It is understandable that the actual interference dimension corresponds to a specific auxiliary plugin, such as the "voltage plugin" corresponding to the voltage fluctuation dimension. By generating correctness prompts, such as "It is recommended to check the voltage data", the voltage dimension is introduced, thereby guiding the trainee to view the information of the correct dimension and improving diagnostic efficiency.

[0170] Among them, the correctness prompt information indicates the dimension information where the real interference data is located, and the dimension introduction information is a prompt information to guide the training end to view the correct interference dimension.

[0171] S4343, Receive the selection information of the dimension to be introduced by the training end, determine the dimension to be introduced, and obtain the specific abnormal entries in the introduced dimension caused by the real interference data.

[0172] It is understandable that when the training end clicks on a dimension to import data, it obtains the specific abnormal entries in the real interference data corresponding to the imported dimension. That is, it can obtain the data location of the abnormal data caused by the real interference data, so as to make it prominently marked later, so that the training end can see the abnormal data in time.

[0173] The introduced dimension is the dimension that guides personnel to check for anomalies, such as the voltage dimension, and the specific anomaly item is the specific data location where the anomaly occurred.

[0174] S4344, Mark the specific abnormal entries with salience to generate data location information.

[0175] It is understandable that specific abnormal items should be clearly marked, for example, by retrieving preset pixel values ​​to update the corresponding data and obtain data location information, so that personnel can clearly see the abnormal data information.

[0176] Among them, the data location information is the information that locates and displays the actual interference data, such as highlighting the abnormal voltage data of the interference in red.

[0177] S4345, Based on the combined information of the misconception extraction, dimension introduction, and data positioning, three-dimensional guidance data is obtained.

[0178] Understandably, 3D guidance data combines information such as identifying misunderstandings, introducing dimensions, and locating data to form a complete diagnostic logic chain, thereby improving the trainee's accuracy in locating faults.

[0179] See Figure 2 This is a schematic diagram of the structure of an electromagnetic safety resilience digital twin training system provided in an embodiment of the present invention. The electromagnetic safety resilience digital twin training system includes:

[0180] The association module is used to construct a test twin space, determine the test equipment group based on electromagnetic test data, and associate it with real interference data.

[0181] The determination module is used to determine the interference dimension based on the device attributes of each test device in the test device group, and generate false interference data according to the interference dimension.

[0182] The update module is used to update the status of the test equipment based on the real interference data, generate actual data, and replace the corresponding dimension of the operating data based on the false interference data to generate false data.

[0183] The generation module is used to collect the call information of the auxiliary plugins from the training end, and generate misleading guidance data based on the comparison information of the call information with the actual data and fake data. The auxiliary plugins correspond one-to-one with the running data of each dimension.

[0184] See Figure 3 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present invention. The electronic device 30 includes: a processor 31, a memory 32, and a computer program; wherein...

[0185] The memory 32 is used to store the computer program, and the memory may also be flash memory. The computer program is, for example, an application program or functional module that implements the above method.

[0186] The processor 31 is configured to execute the computer program stored in the memory to implement the various steps performed by the device in the above method. For details, please refer to the relevant descriptions in the preceding method embodiments.

[0187] Alternatively, the memory 32 can be either standalone or integrated with the processor 31.

[0188] When the memory 32 is a device independent of the processor 31, the device may further include:

[0189] Bus 33 is used to connect the memory 32 and the processor 31.

[0190] The present invention also provides a readable storage medium storing a computer program, which, when executed by a processor, is used to implement the methods provided in the various embodiments described above.

[0191] The readable storage medium can be a computer storage medium or a communication medium. A communication medium includes any medium that facilitates the transfer of computer programs from one location to another. A computer storage medium can be any available medium accessible to a general-purpose or special-purpose computer. For example, a readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application-Specific Integrated Circuit (ASIC). Alternatively, the ASIC can be located in a user equipment. Of course, the processor and the readable storage medium can also exist as discrete components in a communication device. The readable storage medium can be a read-only memory (ROM), random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0192] The present invention also provides a program product including executable instructions stored in a readable storage medium. At least one processor of the device can read the executable instructions from the readable storage medium, and the at least one processor executes the executable instructions to cause the device to implement the methods provided in the various embodiments described above.

[0193] In the embodiments of the above-described device, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly manifested as execution by a hardware processor, or execution by a combination of hardware and software modules within the processor.

[0194] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A digital twin training method for electromagnetic safety restoring force, characterized in that, include: Construct a test twin space, determine the test equipment group based on electromagnetic test data, and correlate it with real interference data; Interference dimensions are determined based on the device attributes of each test device in the test equipment group, and false interference data is generated according to the interference dimensions, including: Based on the real interference data, the actual interference dimension corresponding to the electromagnetic interference type is obtained, and the actual interference dimension is used as the elimination dimension. Remove the excluded dimensions from the obstacle interference dimension set to obtain multiple candidate obstacle dimensions. The interference dimension set includes all preset fault dimensions of the device. Based on the test equipment, retrieve the corresponding equipment logs, and determine the anomaly coefficient of the candidate obstacle dimension of the corresponding test equipment in the historical period according to the equipment logs; Based on the anomaly coefficients, the candidate obstacle dimensions are sorted in descending order to obtain the obstacle dimension sequence; Based on the number of configurations, the candidate obstacle dimensions in the obstacle dimension sequence are selected as interference dimensions in sequence. Anomaly analysis is performed on the corresponding dimension data in the device log based on the interference dimension statistics, and the obtained abnormal data is regarded as false interference data. The test equipment is updated with the real interference data to generate actual data. The corresponding dimension of the running data is replaced with the false interference data to generate false data. The system collects call information from the training end to auxiliary plugins. Based on the comparison information between the call information and actual and spurious data, it generates misleading guidance data. Each auxiliary plugin corresponds to a specific dimension of the runtime data, including: The duration of the training end's call to the auxiliary plugin is counted in real time, and the auxiliary plugin whose call duration is longer than a preset duration is marked as the judgment plugin; When the judgment plugin corresponds to false data, the judgment plugin is determined to be a guidance plugin, and the guidance level is determined according to the training level of the training end; Based on the aforementioned guidance level, actual and false data are processed to generate misleading guidance data.

2. The method according to claim 1, characterized in that, The construction of the test twin space, which determines the test equipment group based on electromagnetic test data and correlates it with real interference data, includes: A corresponding test twin space is constructed based on the target device, and the test twin space includes multiple twin devices; The system receives electromagnetic test data input from the interference terminal, including the number of interferences, interference radius, electromagnetic interference type, and electromagnetic interference intensity. Based on the number of interferences, multiple coordinate points are selected as interference locations, and the interference area is obtained according to the interference locations and interference radius. The twin devices that generate electromagnetic effects within the interference area are used as test devices. The test devices located in the same interference area are counted to obtain a test device group. The actual interference data of each test device is obtained based on the electromagnetic interference type and intensity, and the actual interference data is correlated with each test device in the test device group.

3. The method according to claim 2, characterized in that, The process of obtaining the actual interference data for each of the test devices based on the electromagnetic interference type and intensity includes: The test position of the test equipment is obtained, and the interference distance corresponding to each test equipment is obtained based on the test position and the interference position. The interference coefficient is obtained by the ratio of the preset reference distance and the interference distance corresponding to the electromagnetic interference type. The electromagnetic interference data of each test device corresponding to the electromagnetic interference type is obtained by the product of the interference coefficient and the electromagnetic interference intensity. Based on the electromagnetic interference data, obtain the actual interference data of the test equipment.

4. The method according to claim 1, characterized in that, The step of determining the anomaly coefficient of the candidate obstacle dimension of the corresponding test device within the historical time period based on the device log includes: Obtain the runtime of the components in the test equipment corresponding to the candidate obstacle dimension, and count the number of abnormal data in the equipment log based on the runtime; The anomaly coefficient is obtained by the ratio of the number of anomalies to the reference number of anomalies for the corresponding candidate obstacle dimension.

5. The method according to claim 1, characterized in that, The step of updating the test equipment status based on the real interference data to generate actual data, and then replacing the corresponding dimension of the operating data with the false interference data to generate false data, includes: The operating state of the test equipment after interference is determined based on the actual interference data to obtain the interference state. The interference state is then used to update the test equipment to obtain the actual data. Based on the aforementioned false interference data, the device logs of the corresponding dimensions will be used as change logs; Based on the false interference data, obtain the log data corresponding to the interference dimension in the change log, retrieve the false interference data to replace the log data, and generate false data.

6. The method according to claim 1, characterized in that, The process of processing actual and false data based on the guidance level to generate misleading guidance data includes: Based on the historical diagnostic success rate of the training end, a guidance level is determined, which includes at least a diagnostic logic level, a dimension correction level, and a fault location level. Based on the diagnostic logic level, one-dimensional guidance data is generated to elicit the misunderstanding. Based on the aforementioned dimensional correction level, two-dimensional guidance data for misconception extraction and dimensional introduction is generated; Based on the fault location level, three-dimensional guiding data is generated to elicit misconceptions, introduce dimensions, and locate data.

7. The method according to claim 6, characterized in that, The generation of three-dimensional guiding data based on the fault location level, including misconception identification, dimension introduction, and data location, includes: Based on the plugin name of the guide plugin, a negative prompt message is generated, and based on the negative prompt message, a misconception prompt message is generated; Based on the plugin name of the auxiliary plugin corresponding to the actual interference dimension, generate correctness prompt information, and based on the correctness prompt information, generate dimension introduction information; Receive the selection information of the dimension to be introduced by the training end, determine the dimension to be introduced, and obtain the specific abnormal entries in the introduced dimension caused by the real interference data. The specific abnormal entries are marked for prominence to generate data location information; Based on the combined information of misconception extraction, dimension introduction, and data positioning, three-dimensional guidance data is obtained.

8. A digital twin training system for electromagnetic safety restoring force, characterized in that, include: The association module is used to construct a test twin space, determine the test equipment group based on electromagnetic test data, and associate it with real interference data; The determination module is used to determine the interference dimension based on the device attributes of each test device in the test equipment group, and to generate false interference data according to the interference dimension, including: Based on the real interference data, the actual interference dimension corresponding to the electromagnetic interference type is obtained, and the actual interference dimension is used as the elimination dimension. Remove the excluded dimensions from the obstacle interference dimension set to obtain multiple candidate obstacle dimensions. The interference dimension set includes all preset fault dimensions of the device. Based on the test equipment, retrieve the corresponding equipment logs, and determine the anomaly coefficient of the candidate obstacle dimension of the corresponding test equipment in the historical period according to the equipment logs; Based on the anomaly coefficients, the candidate obstacle dimensions are sorted in descending order to obtain the obstacle dimension sequence; Based on the number of configurations, the candidate obstacle dimensions in the obstacle dimension sequence are selected as interference dimensions in sequence. Anomaly analysis is performed on the corresponding dimension data in the device log based on the interference dimension statistics, and the obtained abnormal data is regarded as false interference data. The update module is used to update the status of the test equipment based on the real interference data, generate actual data, and replace the corresponding dimension of the running data based on the false interference data to generate false data. The generation module is used to collect call information from the training end regarding auxiliary plugins. Based on the comparison information between the call information and actual and spurious data, it generates misleading guidance data. Each auxiliary plugin corresponds to a specific dimension of the runtime data, including: The duration of the training end's call to the auxiliary plugin is counted in real time, and the auxiliary plugin whose call duration is longer than a preset duration is marked as the judgment plugin; When the judgment plugin corresponds to false data, the judgment plugin is determined to be a guidance plugin, and the guidance level is determined according to the training level of the training end; Based on the aforementioned guidance level, actual and false data are processed to generate misleading guidance data.

Images