Power equipment safety detection method and device and terminal equipment

Abstract

The invention relates to a power equipment safety detection method and apparatus, and a terminal device. The method comprises the steps of obtaining a current electrical characteristic quantity and a historical electrical characteristic quantity of a to-be-detected device; inputting the current electrical characteristic quantity into a trained power fingerprint identification model to obtain a current power fingerprint of the to-be-tested device output by the trained power fingerprint identification model; inputting the historical electrical characteristic quantity into a trained power fingerprint identification model to obtain a plurality of abnormal power fingerprints corresponding to the to-be-tested device and output by the trained power fingerprint identification model, each abnormal power fingerprint corresponding to one security hole; calculating a first similarity between the current power fingerprint and each abnormal power fingerprint; and when the first similarity between the current power fingerprint and the abnormal power fingerprint is greater than a first preset threshold, determining that the to-be-tested device has a security vulnerability corresponding to the abnormal power fingerprint. Through the method and the device, the problem of relatively low safety detection accuracy of the power equipment in related technologies is solved.

Description

Technical Field

[0001] The present application belongs to the technical field of power data processing, and in particular, relates to a method, device and terminal device for safety detection of power equipment. Background Art

[0002] With the development of power systems, the security of power systems has received more and more attention. Detecting security threats to power systems is a very important part of power systems. For example, power equipment is often used irrationally during use, which can cause power equipment overload, short circuit, and even cause certain security threats to the power system.

[0003] Therefore, it is necessary to monitor the operating status of power equipment in real time and perform safety detection on power equipment. In the prior art, safety detection of power equipment is often performed based on several fixed parameters (e.g., current, voltage or power). For example, when the power of the power equipment is greater than its rated power, it is determined that the power equipment is overloaded. However, safety detection of power equipment based solely on the above parameters cannot detect potential safety threats to the power equipment, and the detection accuracy is also low.

[0004] Currently, no effective solution has been proposed for the problem of low accuracy in safety detection of power equipment in related technologies. Summary of the invention

[0005] The embodiments of the present application provide a method, apparatus and terminal device for safety detection of electric power equipment, so as to at least solve the problem of low accuracy of safety detection of electric power equipment in the related art.

[0006] In a first aspect, an embodiment of the present application provides a method for safety detection of power equipment, comprising: obtaining current electrical characteristic quantities and historical electrical characteristic quantities of a device to be tested; inputting the current electrical characteristic quantities into a trained power fingerprint recognition model to obtain the current power fingerprint of the device to be tested output by the trained power fingerprint recognition model; inputting the historical electrical characteristic quantities into the trained power fingerprint recognition model to obtain a plurality of abnormal power fingerprints corresponding to the device to be tested output by the trained power fingerprint recognition model, wherein each of the abnormal power fingerprints corresponds to a security vulnerability; calculating a first similarity between the current power fingerprint and each of the abnormal power fingerprints; and determining that the device to be tested has the security vulnerability corresponding to the abnormal power fingerprint when the first similarity between the current power fingerprint and the abnormal power fingerprint is greater than a first preset threshold.

[0007] In some embodiments, before obtaining the current electrical characteristic quantities and historical electrical characteristic quantities of the device to be tested, the method also includes: obtaining the electrical characteristic quantities of multiple power devices, and constructing an operation database based on the electrical characteristic quantities of the multiple power devices; dividing the operation database into a training data set, a verification data set, and a test data set; inputting the training data set into the power fingerprint recognition model to be trained, and updating various parameters in the power fingerprint recognition model to be trained with the goal of minimizing a preset loss function; inputting the verification data set into the power fingerprint recognition model to be trained to determine whether the power fingerprint recognition model to be trained has converged; if the power fingerprint recognition model to be trained has converged, using the test data set to evaluate the recognition effect of the power fingerprint recognition model to be trained; if the recognition effect of the power fingerprint recognition model to be trained meets the preset indicators, determining that the power fingerprint recognition model to be trained has been trained to obtain the trained power fingerprint recognition model.

[0008] In some embodiments, obtaining electrical characteristic quantities of multiple electrical devices and constructing an operation database based on the electrical characteristic quantities of the multiple electrical devices includes: controlling sensors to collect the electrical characteristic quantities of the multiple electrical devices; standardizing the electrical characteristic quantities to obtain standardized data; performing outlier processing on the standardized data to obtain cleaned data; marking the cleaned data to obtain labels corresponding to each of the cleaned data; and constructing the operation database based on the cleaned data and the labels corresponding to each of the cleaned data.

[0009] In some embodiments, calculating the first similarity between the current power fingerprint and each of the abnormal power fingerprints includes: storing the multiple abnormal power fingerprints and the mapping relationship between each of the abnormal power fingerprints and the security vulnerability in a vulnerability database; querying the abnormal power fingerprint corresponding to the device under test from the vulnerability database; and calculating the first similarity between the current power fingerprint and each of the abnormal power fingerprints.

[0010] In some embodiments, after determining that the device under test has a security vulnerability corresponding to the abnormal power fingerprint, the method further includes: calculating a second similarity between the current power fingerprint and each threat feature in a preset threat event database, wherein the threat event database includes multiple threat events and the threat feature corresponding to each threat event; when the second similarity between the current power fingerprint and the threat feature is greater than a second preset threshold, determining that the device under test has the threat event corresponding to the threat feature.

[0011] In some embodiments, the vulnerability database also stores a first risk score corresponding to each of the security vulnerabilities; the threat event database also stores a second risk score corresponding to each of the threat events; after determining that the device under test has the threat event corresponding to the threat feature, the method further includes: searching the vulnerability database for the first risk score corresponding to each of the security vulnerabilities existing in the device under test; searching the threat event database for the second risk score corresponding to each of the threat events existing in the device under test; based on the first risk score corresponding to each of the security vulnerabilities existing in the device under test and the second risk score corresponding to each of the threat events existing in the device under test, determine the risk level of the device under test, and generate a security detection report corresponding to the device under test.

[0012] In some embodiments, the current power fingerprint is used to characterize the time domain characteristics and frequency domain characteristics of the current electrical characteristic quantity of the device under test.

[0013] In the second aspect, an embodiment of the present application provides an electric power equipment safety detection device, including: an acquisition module, used to acquire current electrical characteristic quantities and historical electrical characteristic quantities of the device under test; a first identification module, used to input the current electrical characteristic quantities into a trained electric power fingerprint recognition model, and obtain the current electric power fingerprint of the device under test output by the trained electric power fingerprint recognition model; a second identification module, used to input the historical electrical characteristic quantities into the trained electric power fingerprint recognition model, and obtain multiple abnormal electric power fingerprints corresponding to the device under test output by the trained electric power fingerprint recognition model, wherein each abnormal electric power fingerprint corresponds to a security vulnerability; a calculation module, used to calculate a first similarity between the current electric power fingerprint and each abnormal electric power fingerprint; a determination module, used to determine that the device under test has the security vulnerability corresponding to the abnormal electric power fingerprint when the first similarity between the current electric power fingerprint and the abnormal electric power fingerprint is greater than a first preset threshold.

[0014] In a third aspect, an embodiment of the present application provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the power equipment safety detection method of any one of the above-mentioned first aspects is implemented.

[0015] In a fourth aspect, an embodiment of the present application provides a computer program product, including a computer program. When the computer program is executed, the power equipment safety detection method described in any one of the above-mentioned first aspects is executed.

[0016] Compared with the related art, the power equipment safety detection method, device and terminal device provided in the embodiments of the present application obtain the current power fingerprint and abnormal power fingerprint corresponding to the device under test by inputting the current electrical characteristic quantity and the historical electrical characteristic quantity of the device under test into the trained power fingerprint recognition model; then, the current power fingerprint can be compared with each abnormal power fingerprint, and when the first similarity between the current power fingerprint and the abnormal power fingerprint is greater than the first preset threshold, it is determined that the device under test currently has a security vulnerability corresponding to the abnormal power fingerprint; in this way, not only the current security vulnerability of the device under test can be detected, but also multiple abnormal power fingerprints existing in the device under test during the historical operating period can be detected based on the historical electrical characteristic quantity of the device under test, and the security vulnerability corresponding to each abnormal power fingerprint, so as to discover the potential security threat of the device under test; in addition, by calculating the first similarity between the current power fingerprint and the abnormal power fingerprint of the device under test to determine whether the device under test has a security vulnerability, compared with determining the operating status of the device by only obtaining device parameters, the safety detection accuracy of the power equipment is higher, which can improve the safety and reliability of the power system. Through the present application, the problem of low safety detection accuracy of power equipment in the related technology is solved, and the technical effect of improving the safety detection accuracy of power equipment is achieved.

[0017] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 is a flow chart of a method for safety detection of electric power equipment according to an embodiment of the present application; Figure 2 is a flow chart of a power fingerprint recognition model training method according to an embodiment of the present application; Figure 3 is a structural schematic diagram of a power equipment safety detection device according to an embodiment of the present application; Figure 4 It is a structural diagram of a terminal device according to an embodiment of the present application. DETAILED DESCRIPTION

[0020] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0021] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0022] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0023] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0024] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0025] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0026] With the development of power systems, the security of power systems has received more and more attention. Detecting security threats to power systems is a very important part of power systems. For example, power equipment is often used irrationally during use, which can cause power equipment overload, short circuit, and even cause certain security threats to the power system.

[0027] Therefore, it is necessary to monitor the operating status of power equipment in real time and perform safety detection on power equipment. In the prior art, safety detection of power equipment is often performed based on several fixed parameters (e.g., current, voltage or power). For example, when the power of the power equipment is greater than its rated power, it is determined that the power equipment is overloaded. However, safety detection of power equipment based solely on the above parameters cannot detect potential safety threats to the power equipment, and the detection accuracy is also low.

[0028] Currently, no effective solution has been proposed for the problem of low accuracy in safety detection of power equipment in related technologies.

[0029] The power fingerprint technology collects electrical data from power equipment, uses artificial intelligence technology and big data technology to mine the "power fingerprint" features that can characterize the characteristics of the power equipment, and combines intrusive and non-intrusive identification methods to identify the type, characteristics, parameters and user behavior habits of the power equipment, thereby realizing monitoring, control, management and friendly interaction of the power equipment.

[0030] Not only that, power fingerprint technology can also enable users to use electricity safely. Electricity is still the primary cause of fires. One-third of larger fires are caused by electrical reasons, and most of them are electrical line failures, accounting for nearly 80% of the total number of electrical fires. Power fingerprint technology can accurately identify dangerous electrical equipment, dangerous electricity use behaviors, and dangerous electrical events under mixed operating conditions of multiple electrical appliances, and control dangerous factors, thereby achieving active defense against electrical fires. Through high-frequency collection of electrical signals from equipment running in electrical circuits, feature extraction and learning, artificial intelligence recognition, accurate event analysis, precise equipment perception, and online continuous evolution of algorithms, power fingerprint technology can accurately identify dangerous electrical equipment, dangerous electricity use behaviors, and dangerous electrical events under mixed operating conditions of multiple electrical appliances, and control dangerous factors.

[0031] In view of this, the embodiment of the present application provides a method for safety detection of electric equipment, by inputting the current electrical characteristic quantity and the historical electrical characteristic quantity of the device under test into the trained power fingerprint recognition model, the current power fingerprint and the abnormal power fingerprint corresponding to the device under test are obtained; then, the current power fingerprint can be compared with each abnormal power fingerprint, and when the first similarity between the current power fingerprint and the abnormal power fingerprint is greater than the first preset threshold, it is determined that the device under test currently has a security vulnerability corresponding to the abnormal power fingerprint; in this way, not only the current security vulnerability of the device under test can be detected, but also multiple abnormal power fingerprints existing in the device under test during the historical operation period can be detected based on the historical electrical characteristic quantity of the device under test, and the security vulnerability corresponding to each abnormal power fingerprint, so as to discover the potential security threat of the device under test; in addition, by calculating the first similarity between the current power fingerprint and the abnormal power fingerprint of the device under test to determine whether the device under test has a security vulnerability, compared with determining the operating status of the device only by obtaining device parameters, the safety detection accuracy of the power device is higher, which can improve the safety and reliability of the power system. Through this application, the problem of low safety detection accuracy of power equipment in the related technology is solved, and the technical effect of improving the safety detection accuracy of power equipment is achieved.

[0032] The following will be combined Figure 1 For an explanation of the power equipment safety detection method provided by an embodiment of the present application, please refer to Figure 1 , Figure 1 is a flow chart of a method for safety detection of electric power equipment according to an embodiment of the present application, such as Figure 1 As shown, the method includes: Step S101, obtaining current electrical characteristic quantities and historical electrical characteristic quantities of the device under test.

[0033] In this embodiment, the device to be tested may be a common electrical device in a household, such as a washing machine, a kettle, a fan, an air conditioner, etc. The electrical characteristic quantity may include the operating current value, the operating voltage value, the operating power, the operating frequency, and the operating temperature of the electrical device.

[0034] The above electrical characteristics can be collected in real time by various sensors installed on the power equipment to fully reflect the operating status of the power equipment under different working conditions. The current electrical characteristics of the device under test can be all electrical characteristics collected by the device under test in the current time period (for example, within 30 minutes, 1 hour), and the historical electrical characteristics of the device under test can be all electrical characteristics collected in the historical time period (for example, the past 7 days, the past 30 days, etc.).

[0035] After the current electrical characteristic quantities and the historical electrical characteristic quantities of the device under test are collected, data preprocessing may be performed on the current electrical characteristic quantities and the historical electrical characteristic quantities to improve the quality of data subsequently input into the trained power fingerprint recognition model.

[0036] Specifically, the above data preprocessing may include standardization processing and outlier processing.

[0037] Step S102: input the current electrical characteristic quantity into the trained power fingerprint recognition model to obtain the current power fingerprint of the device under test output by the trained power fingerprint recognition model.

[0038] Step S103, inputting the historical electrical characteristic quantity into the trained power fingerprint recognition model, obtaining a plurality of abnormal power fingerprints corresponding to the device under test output by the trained power fingerprint recognition model, wherein each abnormal power fingerprint corresponds to a security vulnerability.

[0039] In this embodiment, the current power fingerprint is used to characterize the time domain characteristics and frequency domain characteristics of the current electrical characteristic quantity of the device under test. The time domain characteristics may include the basic statistical values ​​such as the mean, standard deviation, maximum value, minimum value, etc. of the current, voltage, and power of the device under test; the frequency domain characteristics may include the maximum value and average value of the power of the device under test in the frequency domain (for example, using Fourier transform to perform spectrum analysis on the power of the device under test).

[0040] The trained power fingerprint recognition model can output a power fingerprint corresponding to the input electrical feature quantity based on the input electrical feature quantity. The power fingerprint recognition model can be constructed based on a convolutional neural network (or a recurrent neural network, or any neural network model based on deep learning).

[0041] In addition, after obtaining the power fingerprint, the power fingerprint can be stored in a secure database for subsequent use.

[0042] The following will be combined Figure 2 The exemplary process of the power fingerprint recognition model training method provided by an embodiment of the present application is described. Figure 2 , Figure 2 is a flow chart of a power fingerprint recognition model training method according to an embodiment of the present application. Figure 2 As shown, the power fingerprint recognition model training method includes the following steps: Step S201: acquiring electrical characteristic quantities of a plurality of electric devices, and constructing an operation database based on the electrical characteristic quantities of the plurality of electric devices.

[0043] In this embodiment, obtaining electrical characteristic quantities of multiple power devices and constructing an operation database based on the electrical characteristic quantities of the multiple power devices includes the following steps: Step 1: Control sensors to collect electrical characteristic quantities of multiple electrical devices.

[0044] In this embodiment, the operating current value of the electrical equipment can be collected by a current sensor installed on the electrical equipment, the operating voltage value of the electrical equipment can be collected by a voltage sensor installed on the electrical equipment, and the operating temperature of the electrical equipment can be collected by a temperature sensor installed on the electrical equipment.

[0045] Step 2: Standardize the electrical characteristic quantities to obtain standardized data.

[0046] In this embodiment, the standardization process can ensure that the electrical feature quantities are within the same dimensional range, so that the feature weights will not be unbalanced due to data scale differences during subsequent model training. In the example code implementation, the StandardScaler() function can be used to standardize the electrical feature quantities. The mathematical expression of the StandardScaler() function can be expressed as: X scaled = (X-μ) / σ.

[0047] Among them, X is the original data, X scaled is the data after standardization, μ is the mean of the original data, and σ is the standard deviation of the original data.

[0048] Step 3: Perform outlier processing on the standardized data to obtain cleaned data.

[0049] In this embodiment, in the example code implementation, the IsolationForest() function can be used to process outliers in the electrical feature quantities, and outliers in the electrical feature quantities can be identified by constructing an isolation forest. The quality of the data used for subsequent model training can be improved by removing these outliers.

[0050] In addition, the cleaned data can be saved as a CSV (Comma-Separated Values) file for use in subsequent model training.

[0051] Step 4: label the cleaned data to obtain labels corresponding to each cleaned data.

[0052] In this embodiment, after data cleaning is completed, all cleaned data can be marked to obtain labels corresponding to each cleaned data. The label can be the type of each power device, timestamp data, security vulnerabilities of the power device (if any), etc.

[0053] Step 5: construct a running database based on the cleaned data and the labels corresponding to each cleaned data.

[0054] In this embodiment, the cleaned data can be used to generate the operation data of the power equipment, wherein the operation data may include the current value, voltage value, temperature value, active power, reactive power, power factor, current harmonics, current mutation amount and power mutation amount when the working state is switched, etc. of the power equipment in a specific working mode. The above operation data and labels are used as a group of training samples respectively to construct an operation database of the power equipment.

[0055] Among them, the operation database of power equipment can store private data collected by itself, and can also store public data sets.

[0056] Step S202: divide the running database into a training data set, a verification data set and a test data set.

[0057] In this embodiment, corresponding operation data can be extracted from the operation database, and then the extracted operation data can be divided into a training data set, a verification data set, and a test data set by randomly extracting the data in a random manner ...

[0058] The training data set is used to update the parameters in the power fingerprint recognition model to minimize the loss function. The validation data set is used to tune the power fingerprint recognition model and select the best parameters. The test data set is used to evaluate the generalization ability and performance of the trained power fingerprint recognition model.

[0059] In step S203, the training data set is input into the power fingerprint recognition model to be trained, and various parameters in the power fingerprint recognition model to be trained are updated with the goal of minimizing a preset loss function.

[0060] In this embodiment, the loss function may be a cross entropy loss function.

[0061] Step S204: input the verification data set into the power fingerprint recognition model to be trained to determine whether the power fingerprint recognition model to be trained has converged.

[0062] In this embodiment, a verification data set can be used to determine whether the power fingerprint recognition model to be trained has converged. As an example, the verification data set can be input into the power fingerprint recognition model to be trained to obtain the current loss function value of the power fingerprint recognition model to be trained; then the loss function value of the power fingerprint recognition model to be trained at the last iterative update (the data input into the power fingerprint recognition model is still the verification data set) is obtained; by calculating the difference between the current loss function value and the loss function value of the last iterative update, and comparing the difference with the preset convergence threshold, it is determined whether the power fingerprint recognition model to be trained has converged.

[0063] For example, if after inputting the verification data set, the difference in the loss function value between two iterations of the power fingerprint recognition model to be trained is less than the preset convergence threshold, it can be determined that the power fingerprint recognition model to be trained has converged.

[0064] Step S205 , when the power fingerprint recognition model to be trained has converged, the test data set is used to evaluate the recognition effect of the power fingerprint recognition model to be trained.

[0065] In this embodiment, the test data set can be used to evaluate the recognition effect of the power fingerprint recognition model to be trained, and the recognition effect of the power fingerprint recognition model to be trained can be comprehensively measured by multiple indicators (such as accuracy, recall rate and F1 value). For example, when the accuracy rate is greater than 0.95, it can be determined that the power fingerprint recognition model to be trained has been trained.

[0066] Step S206, when the recognition effect of the power fingerprint recognition model to be trained meets the preset index, it is determined that the power fingerprint recognition model to be trained has been trained, and the trained power fingerprint recognition model is obtained.

[0067] In this embodiment, during the training process of the power fingerprint recognition model, data preprocessing technology can be used to uniformly convert data of different time resolutions into a standard format, and interpolation algorithms and smoothing filtering technologies can be applied to ensure data consistency. In the process of building the power fingerprint recognition model, a multi-layer neural network or an integrated learning algorithm can be used, combined with a variety of feature extraction technologies, to enhance the adaptability of the power fingerprint recognition model to diversified input data. At the same time, transfer learning can be used to accelerate the training process and improve the generalization ability of the model. In addition, during training, cross-validation can be implemented to evaluate the performance of the power fingerprint recognition model at multiple time resolutions, and data enhancement technology can be used to generate synthetic data to further enhance the adaptability. The evaluation mechanism measures the model performance through a variety of indicators (for example, accuracy, recall, and F1 value), and provides visualization tools to help analyze the performance differences of the model under various types of data.

[0068] It should be noted that the power fingerprint recognition model provided in the embodiment of the present application mainly includes two functions, one is to generate the current power fingerprint based on the input current electrical characteristic quantity; the other is to output the security vulnerabilities of the device under test in the historical time period based on the input historical electrical characteristic quantity, and output the abnormal power fingerprint corresponding to each security vulnerability. The above-mentioned power fingerprint generation can also be extracted based on mathematical features. As an example, PCA (Principal Components Analysis) technology can be used to extract the main device characteristics of the device under test from the input electrical characteristic quantity (for example, the input electrical characteristic quantity includes current value, voltage value, power, frequency and temperature value, and PCA technology is used to extract 3 main device characteristics therefrom), and the main device characteristics can be averaged or weighted averaged to generate the power fingerprint of the device under test.

[0069] The power fingerprint recognition model is trained through the above steps S201 to S206, so that the trained power fingerprint recognition model can not only output the current power fingerprint based on the current electrical characteristic quantity of the device under test, but also output the security vulnerabilities of the device under test in the historical time period based on the historical electrical characteristic quantity of the device under test, and output the abnormal power fingerprint corresponding to each security vulnerability, so as to mine the potential security threats of the device under test; in addition, by outputting the current power fingerprint and abnormal power fingerprint of the device under test through the above-mentioned trained power fingerprint recognition model, the abnormal power fingerprint can be used as the basis for security detection, which plays a key role in the subsequent vulnerability detection process. Compared with determining the operating status of the device only by obtaining device parameters, its safety detection accuracy of power equipment is higher, which can improve the safety and reliability of the power system.

[0070] Step S104: calculating a first similarity between the current power fingerprint and each abnormal power fingerprint.

[0071] In this embodiment, multiple abnormal power fingerprints and the mapping relationship between each abnormal power fingerprint and the security vulnerability can be stored in a vulnerability database; and the abnormal power fingerprint corresponding to the device under test is queried from the vulnerability database; finally, the first similarity between the current power fingerprint and each abnormal power fingerprint is calculated.

[0072] Step S105: when the first similarity between the current power fingerprint and the abnormal power fingerprint is greater than a first preset threshold, it is determined that the device under test has a security vulnerability corresponding to the abnormal power fingerprint.

[0073] In this embodiment, cosine similarity can be used to calculate the first similarity between the current power fingerprint and each abnormal power fingerprint. The value of cosine similarity is between 0 and 1. The closer the cosine similarity value is to 1, the more similar the features of the two are.

[0074] As an example, the first preset threshold can be set to 0.85. When the first similarity between the current power fingerprint and the abnormal power fingerprint is greater than 0.85, it can be determined that the device under test has a security vulnerability corresponding to the abnormal power fingerprint. It should be noted that the first preset threshold can be selected according to the accuracy expected by the user, and this application does not limit the setting of the first preset threshold.

[0075] The vulnerability database not only contains the mapping relationship between the abnormal power fingerprints and security vulnerabilities detected by the power equipment safety detection method provided by the embodiment of the present application, but also can obtain the mapping relationship between other abnormal power fingerprints and security vulnerabilities from other vulnerability databases. Among them, security vulnerabilities may include overload, overvoltage, undervoltage, etc. By traversing the mapping relationship between all abnormal power fingerprints and security vulnerabilities in the vulnerability database, calculating the first similarity between each abnormal power fingerprint and the current power fingerprint, the security vulnerabilities and potential risks of the equipment under test can be detected and reported in a timely manner.

[0076] In addition, the addition of the power fingerprint recognition model can capture subtle anomalies during the operation of the equipment under test, achieve higher-precision detection, and significantly reduce false alarms. At the same time, an alarm mechanism can be added to notify the operation and maintenance personnel to handle the security vulnerabilities found in the equipment under test, generate detailed vulnerability reports, and provide repair suggestions. A feedback mechanism can also be added to continuously enhance the security protection capabilities of the power system.

[0077] In addition to detecting security vulnerabilities of the device under test, it is also possible to detect whether there are threat events (for example, malicious power attacks, network attacks, equipment misoperation, etc.) on the device under test.

[0078] Specifically, after determining that the device under test has a security vulnerability corresponding to the abnormal power fingerprint, the power equipment security detection method provided in the embodiment of the present application further includes the following steps: Step 1: Calculate a second similarity between the current power fingerprint and each threat feature in a preset threat event database, wherein the threat event database includes multiple threat events and a threat feature corresponding to each threat event.

[0079] Step 2: When the second similarity between the current power fingerprint and the threat feature is greater than a second preset threshold, it is determined that a threat event corresponding to the threat feature exists in the device under test.

[0080] In this embodiment, since the current power fingerprint is used to characterize the time domain characteristics and frequency domain characteristics of the current electrical characteristic quantity of the device under test, it is possible to detect whether the device under test is currently in a known attacked state or threatened state by comparing the current power fingerprint with each threat characteristic in the preset threat event database.

[0081] The threat event database can collect security intelligence data from multiple sources, including various types of threat events (such as known attack methods, malware, and vulnerability exploits) and threat characteristics corresponding to each threat event (for example, the timing characteristics and frequency domain characteristics of the current value, voltage value, and power of the device when it is in a certain threat event).

[0082] In this embodiment, cosine similarity can be used to calculate the second similarity between the current power fingerprint and each threat feature. The value of cosine similarity is between 0 and 1. The closer the cosine similarity value is to 1, the more similar the features of the two are.

[0083] As an example, the second preset threshold can be set to 0.85. When the first similarity between the current power fingerprint and the threat feature is greater than 0.85, it can be determined that the device under test has a threat event corresponding to the threat feature. It should be noted that the second preset threshold can be selected according to the accuracy expected by the user, and this application does not limit the setting of the second preset threshold.

[0084] By using the power fingerprint recognition model to identify the current power fingerprint of the device under test, and comparing the identified current power fingerprint with each threat feature in the threat event database, the most relevant threat events can be automatically screened out and the risk level can be assessed by combining similarity analysis and multi-dimensional matching mechanisms. In this way, not only can known threats in the device under test be detected, but also potential complex attack patterns can be identified by capturing subtle changes in the power fingerprint of the device under test. In addition, the threat event database can be updated based on the latest security intelligence to ensure that the device under test can cope with the latest threat trends. At the same time, after completing the detection of threat events, a threat event report can also be generated, which contains the threat event type, attack path, risk level and protection recommendations, helping operation and maintenance personnel make more accurate repair decisions based on the actual behavior of the device under test, and reduce the security risks of the device under test and the power system.

[0085] In this embodiment, the vulnerability database further stores a first risk score corresponding to each security vulnerability; and the threat event database further stores a second risk score corresponding to each threat event.

[0086] Step 3: searching the vulnerability database for a first risk score corresponding to each security vulnerability in the device under test.

[0087] Step 4: Search the threat event database for a second risk score corresponding to each threat event existing in the device to be tested.

[0088] Step 5: determine the risk level of the device under test based on the first risk score corresponding to each security vulnerability in the device under test and the second risk score corresponding to each threat event in the device under test, and generate a security detection report corresponding to the device under test.

[0089] As an example, assuming that the vulnerability database stores security vulnerability 1-overload, its corresponding first risk score can be set to 8; assuming that the threat event database stores threat event 1-malicious power attack, its corresponding second risk score can be set to 9. If security vulnerability 1 and threat event 1 are detected in the device under test, the first risk score and the second risk score can be accumulated or weighted, and the risk level of the device under test can be determined based on the accumulated risk score. For example, if the accumulated risk score is higher than 10, a high risk level is output; if the accumulated risk score is less than 10 but greater than 5, a medium risk level is output; if the accumulated risk score is less than 5, a low risk level is output. Alternatively, the accumulated risk score can be directly output. In the example code implementation, the np.clip() function can be used to limit the accumulated risk score to the range of 0 to 100.

[0090] The above security detection report can list all security vulnerabilities and threat events detected from the device under test, including the type, name, severity and corresponding description of these security vulnerabilities and threat events.

[0091] In this embodiment, based on the power fingerprint recognition model, through multi-dimensional risk scoring and dynamic weight adjustment, accurate risk assessment can be performed on the security vulnerabilities and threat events existing on the power equipment. The power fingerprint recognition model provides unique fingerprint features of the power equipment, so that the risk assessment can be combined with the operating status, historical behavior data, and current threat features of the power equipment for more fine-grained analysis. Not only can the operating environment, importance, and threat possibility of the power equipment be considered, but also the abnormal power fingerprints identified by the power fingerprint recognition model can be relied on to generate a more accurate comprehensive risk score and provide a detailed impact analysis. Security vulnerabilities can be dynamically classified and more priority suggestions can be provided for repair and preventive measures. In addition, the abnormal power fingerprints output by the power fingerprint recognition model and the security vulnerabilities corresponding to the abnormal power fingerprints (security vulnerabilities that occurred in the equipment under test in the historical time period) can be used to help estimate the specific impact of potential threats, provide a visual risk report, and display risk scores, impact analysis, repair suggestions, etc. With the help of the continuous monitoring and feedback mechanism of the power fingerprint recognition model, the risk assessment results can also be dynamically updated to ensure the timeliness and accuracy of the power system's response to threats (including security vulnerabilities and threat events), and effectively improve the reliability and safety of the power system.

[0092] In one embodiment, specific repair strategies and preventive measures can also be generated in combination with security vulnerabilities and threat events detected on the device under test. The above-mentioned repair strategies and preventive measures cover areas such as vulnerability repair, patch management, configuration optimization, and support automated patch deployment and repair. By providing preventive security measures (such as system reinforcement, network isolation, and device monitoring), it can help prevent future security risks and reduce potential attack surfaces by optimizing existing security policies. After the repair is completed, a verification mechanism can be started to ensure the repair effect, and a report can be generated to track the repair process. In addition, the repair strategy and preventive measures can be adjusted dynamically to ensure that the latest threats are addressed, and operation and maintenance personnel can be allowed to customize repair plans according to needs to achieve highly flexible security management.

[0093] Specifically, according to the type of security vulnerability detected on the device under test and the corresponding first risk score, a corresponding repair strategy can be matched from a preset security database, wherein the security database contains a mapping relationship between multiple security vulnerabilities and repair strategies, for example, recommending patches or configuration changes for specific vulnerability types.

[0094] Then, specific repair suggestions can be generated based on the matched repair strategy, including specific operation steps, such as: first install the patch; second modify the firewall rules; and finally adjust the device configuration.

[0095] While generating repair suggestions, a series of preventive measures can also be recommended based on historical security vulnerabilities, historical threat events, and historical risk levels detected on the devices under test to ensure that the same or similar security vulnerabilities and threat events will not occur again. These preventive measures may include: increasing the monitoring frequency of the devices under test, implementing network isolation for the devices under test, and performing security audits regularly.

[0096] The above repair strategies and preventive measures can be sent directly to the operation and maintenance personnel and stored in the system log in the format of a CSV file for subsequent review and tracking of repair progress.

[0097] Through the above steps S101 to S105, by inputting the current electrical characteristic quantity and the historical electrical characteristic quantity of the device under test into the trained power fingerprint recognition model, the current power fingerprint and the abnormal power fingerprint corresponding to the device under test are obtained; then, the current power fingerprint can be compared with each abnormal power fingerprint, and when the first similarity between the current power fingerprint and the abnormal power fingerprint is greater than the first preset threshold, it is determined that the device under test currently has a security vulnerability corresponding to the abnormal power fingerprint; in this way, not only can the current security vulnerability of the device under test be detected, but also multiple abnormal power fingerprints existing in the device under test during the historical operating period can be detected based on the historical electrical characteristic quantity of the device under test, and the security vulnerability corresponding to each abnormal power fingerprint, so as to discover the potential security threat of the device under test; in addition, by calculating the first similarity between the current power fingerprint and the abnormal power fingerprint of the device under test to determine whether the device under test has a security vulnerability, compared with determining the operating status of the device by only obtaining device parameters, the safety detection accuracy of the power device is higher, which can improve the safety and reliability of the power system. Through this application, the problem of low safety detection accuracy of power equipment in the related art is solved, and the technical effect of improving the safety detection accuracy of power equipment is achieved.

[0098] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0099] Corresponding to the power equipment safety detection method described in the above embodiment, Figure 3 A schematic structural diagram of an electric power equipment safety detection device according to an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0100] See also Figure 3 The power equipment safety detection device 3 includes: an acquisition module 30, which is used to acquire the current electrical characteristic quantity and the historical electrical characteristic quantity of the device under test; a first identification module 31, which is used to input the current electrical characteristic quantity into the trained power fingerprint recognition model to obtain the current power fingerprint of the device under test output by the trained power fingerprint recognition model; a second identification module 32, which is used to input the historical electrical characteristic quantity into the trained power fingerprint recognition model to obtain multiple abnormal power fingerprints corresponding to the device under test output by the trained power fingerprint recognition model, wherein each abnormal power fingerprint corresponds to a security vulnerability; a calculation module 33, which is used to calculate the first similarity between the current power fingerprint and each abnormal power fingerprint; a determination module 34, which is used to determine that the device under test has a security vulnerability corresponding to the abnormal power fingerprint when the first similarity between the current power fingerprint and the abnormal power fingerprint is greater than a first preset threshold.

[0101] In one embodiment, the power equipment safety detection device 3 also includes a training module, which is used to obtain electrical characteristic quantities of multiple power equipment and construct an operation database based on the electrical characteristic quantities of multiple power equipment; divide the operation database into a training data set, a verification data set and a test data set; input the training data set into the power fingerprint recognition model to be trained, and update the various parameters in the power fingerprint recognition model to be trained with the goal of minimizing a preset loss function; input the verification data set into the power fingerprint recognition model to be trained to determine whether the power fingerprint recognition model to be trained has converged; when the power fingerprint recognition model to be trained has converged, use the test data set to evaluate the recognition effect of the power fingerprint recognition model to be trained; when the recognition effect of the power fingerprint recognition model to be trained meets the preset indicators, it is determined that the power fingerprint recognition model to be trained has been trained, and the trained power fingerprint recognition model is obtained.

[0102] In one embodiment, the training module is also used to control the sensor to collect electrical characteristic quantities of multiple electrical equipment; standardize the electrical characteristic quantities to obtain standardized data; perform outlier processing on the standardized data to obtain cleaned data; label the cleaned data to obtain labels corresponding to each cleaned data; and construct an operation database based on the cleaned data and the labels corresponding to each cleaned data.

[0103] In one embodiment, the calculation module 33 is also used to store multiple abnormal power fingerprints and the mapping relationship between each abnormal power fingerprint and the security vulnerability in the vulnerability database; query the abnormal power fingerprint corresponding to the device under test from the vulnerability database; and calculate the first similarity between the current power fingerprint and each abnormal power fingerprint.

[0104] In one embodiment, the determination module 34 is also used to calculate the second similarity between the current power fingerprint and each threat feature in a preset threat event database, wherein the threat event database includes multiple threat events and a threat feature corresponding to each threat event; when the second similarity between the current power fingerprint and the threat feature is greater than a second preset threshold, it is determined that there is a threat event corresponding to the threat feature in the device under test.

[0105] In one embodiment, the determination module 34 is also used to search the vulnerability database for a first risk score corresponding to each security vulnerability existing in the device under test; search the threat event database for a second risk score corresponding to each threat event existing in the device under test; determine the risk level of the device under test based on the first risk score corresponding to each security vulnerability existing in the device under test and the second risk score corresponding to each threat event existing in the device under test, and generate a security detection report corresponding to the device under test.

[0106] In one embodiment, the current power fingerprint is used to characterize the time domain characteristics and frequency domain characteristics of the current electrical characteristic quantity of the device under test.

[0107] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0108] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0109] Figure 4 is a schematic diagram of the structure of a terminal device according to an embodiment of the present application. Figure 4 As shown, the terminal device 4 includes: at least one processor 40 ( Figure 4 Only one is shown in the figure) a processor, a memory 41, and a computer program 42 stored in the memory 41 and executable on at least one processor 40, and when the processor 40 executes the computer program 42, the steps in any of the above-mentioned embodiments of the power equipment safety detection method are implemented.

[0110] The terminal device 4 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal device 4 may include but is not limited to a processor 40 and a memory 41. It is understood by those skilled in the art that Figure 4 It is only an example of the terminal device 4 and does not constitute a limitation on the terminal device 4. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, etc.

[0111] The processor 40 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0112] In some embodiments, the memory 41 may be an internal storage unit of the terminal device 4, such as a hard disk or memory of the terminal device 4. In other embodiments, the memory 41 may also be an external storage device of the terminal device 4, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal device 4. In other embodiments, the memory 41 may also include both an internal storage unit and an external storage device of the terminal device 4. The memory 41 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as program codes of a computer program 42. The memory 41 may also be used to temporarily store data that has been output or is to be output.

[0113] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps in the above-mentioned embodiments of the power equipment safety detection method can be implemented.

[0114] An embodiment of the present application provides a computer program product. When the computer program product runs on a mobile terminal, the mobile terminal can implement the steps in the above-mentioned embodiments of the power equipment safety detection method when executing the computer program product.

[0115] The present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the terminal device, a recording medium, a computer memory, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), an electric carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a disk or an optical disk.

[0116] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0117] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0118] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0119] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0120] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for safety detection of electric power equipment, characterized in that: include: Obtain current electrical characteristic quantities and historical electrical characteristic quantities of the device under test; Inputting the current electrical characteristic quantity into a trained power fingerprint recognition model to obtain a current power fingerprint of the device under test output by the trained power fingerprint recognition model; Inputting the historical electrical characteristic quantity into the trained power fingerprint recognition model to obtain a plurality of abnormal power fingerprints corresponding to the device under test output by the trained power fingerprint recognition model, wherein each abnormal power fingerprint corresponds to a security vulnerability; Calculating a first similarity between the current power fingerprint and each of the abnormal power fingerprints; When the first similarity between the current power fingerprint and the abnormal power fingerprint is greater than a first preset threshold, it is determined that the device under test has the security vulnerability corresponding to the abnormal power fingerprint.

2. The method according to claim 1, characterized in that Before obtaining the current electrical characteristic quantity and the historical electrical characteristic quantity of the device under test, the method further includes: Acquire electrical characteristic quantities of a plurality of electrical devices, and construct an operation database based on the electrical characteristic quantities of the plurality of electrical devices; Dividing the running database into a training data set, a validation data set and a test data set; Inputting the training data set into the power fingerprint recognition model to be trained, and updating various parameters in the power fingerprint recognition model to be trained with the goal of minimizing a preset loss function; Inputting the verification data set into the power fingerprint recognition model to be trained, and determining whether the power fingerprint recognition model to be trained has converged; When the power fingerprint recognition model to be trained has converged, using the test data set to evaluate the recognition effect of the power fingerprint recognition model to be trained; When the recognition effect of the power fingerprint recognition model to be trained meets the preset index, it is determined that the power fingerprint recognition model to be trained has been trained, and the trained power fingerprint recognition model is obtained.

3. The method according to claim 2, characterized in that Acquiring electrical characteristic quantities of a plurality of electrical devices and constructing an operation database based on the electrical characteristic quantities of the plurality of electrical devices includes: Controlling sensors to collect the electrical characteristic quantities of the plurality of electrical devices; Performing standardization processing on the electrical characteristic quantity to obtain standardized data; Performing outlier processing on the standardized data to obtain cleaned data; Marking the cleaned data to obtain labels corresponding to the cleaned data; The operation database is constructed based on the cleaned data and the labels corresponding to each of the cleaned data.

4. The method according to any one of claims 1 to 3, characterized in that Calculating the first similarity between the current power fingerprint and each of the abnormal power fingerprints includes: storing the plurality of abnormal power fingerprints and a mapping relationship between each of the abnormal power fingerprints and the security vulnerability in a vulnerability database; querying the abnormal power fingerprint corresponding to the device under test from the vulnerability database; A first similarity between the current power fingerprint and each of the abnormal power fingerprints is calculated.

5. The method according to claim 4, characterized in that After determining that the device under test has a security vulnerability corresponding to the abnormal power fingerprint, the method further includes: Calculating a second similarity between the current power fingerprint and each threat feature in a preset threat event database, wherein the threat event database includes a plurality of threat events and the threat feature corresponding to each of the threat events; When the second similarity between the current power fingerprint and the threat feature is greater than a second preset threshold, it is determined that the threat event corresponding to the threat feature exists in the device under test.

6. The method according to claim 5, characterized in that The vulnerability database further stores a first risk score corresponding to each of the security vulnerabilities; the threat event database further stores a second risk score corresponding to each of the threat events; After determining that the device under test has the threat event corresponding to the threat feature, the method further includes: Searching the vulnerability database for the first risk score corresponding to each of the security vulnerabilities existing in the device under test; Searching the threat event database for the second risk score corresponding to each of the threat events existing in the device under test; Based on the first risk score corresponding to each of the security vulnerabilities existing in the device under test and the second risk score corresponding to each of the threat events existing in the device under test, the risk level of the device under test is determined, and a security detection report corresponding to the device under test is generated.

7. The method according to any one of claims 1 to 3, characterized in that The current power fingerprint is used to characterize the time domain characteristics and frequency domain characteristics of the current electrical characteristic quantity of the device under test.

8. A power equipment safety detection device, characterized in that: include: An acquisition module is used to acquire current electrical characteristic quantities and historical electrical characteristic quantities of the device under test; A first recognition module, configured to input the current electrical characteristic quantity into a trained power fingerprint recognition model to obtain a current power fingerprint of the device under test output by the trained power fingerprint recognition model; A second identification module is used to input the historical electrical characteristic quantity into the trained power fingerprint identification model to obtain a plurality of abnormal power fingerprints corresponding to the device under test output by the trained power fingerprint identification model, wherein each abnormal power fingerprint corresponds to a security vulnerability; A calculation module, used for calculating a first similarity between the current power fingerprint and each of the abnormal power fingerprints; The determination module is used to determine that the device under test has the security vulnerability corresponding to the abnormal power fingerprint when the first similarity between the current power fingerprint and the abnormal power fingerprint is greater than a first preset threshold.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the power equipment safety detection method according to any one of claims 1 to 7 is implemented.

10. A computer program product, characterized in that It comprises a computer program, and when the computer program is executed, the power equipment safety detection method according to any one of claims 1 to 7 is executed.

Images