Electrical safety management method and system for fault identification with learning function

Abstract

The invention discloses a fault identification electrical safety management method and system with a learning function. The method comprises the following steps: acquiring an electrical fault classifier; obtaining a training data set; training the electrical fault classifier through the training data set to obtain a trained electrical fault classifier; acquiring historical equipment operation state information of the to-be-identified electrical equipment at the current time point and historical environment information in a first time period; inputting the historical equipment operation state information at the current time point and the historical environment information in the first time period into a trained electrical fault classifier so as to obtain a classification result; and judging whether to give an alarm according to a classification result. According to the method, the environment information and the equipment running state information are combined to train the classifier, so that the classifier can deeply excavate the incidence relation between the environment and the equipment running state, and the classifier has the advantages of being accurate in result and high in robustness.

Description

Technical Field

[0001] This application relates to the field of electrical safety technologies, and particularly to an electrical safety management method with a learning function for fault recognition and an electrical safety management system with a learning function for fault recognition. Background Art

[0002] The existing technologies for electrical faults usually target fault monitoring based on current / voltage waveform transformation, that is, electrical fault detection of electrical appliances is performed through the mathematical models of current / voltage.

[0003] However, the existing technologies have the problem of inaccurate detection. Summary of the Invention

[0004] The purpose of the present invention is to provide an electrical safety management method with a learning function for fault recognition to at least solve one of the above technical problems.

[0005] In one aspect of the present invention, there is provided an electrical safety management method with a learning function for fault recognition, and the electrical safety management method with a learning function for fault recognition includes: Obtain a database, where the database includes historical device operation status information of each electrical device at each time point in seconds, historical environment information corresponding to the historical device operation status information at each time point in seconds, accident time points, and accident causes; Segment the historical environment information corresponding to the historical device operation status information at each time point in seconds with every two adjacent accident time points as the starting point and the ending point, so as to obtain multiple segments of first objective historical environment information segments; Obtain the historical environment information of a preset time period before the ending point with each accident time point as the ending point as the second objective historical environment information segment; Obtain an electrical fault classifier; Form a training data set by combining each segment of objective historical environment information segment, the second objective historical environment information segment, each accident time point, the historical device operation status information of the electrical device corresponding to each accident time point, and the accident cause; Train the electrical fault classifier with the training data set, so as to obtain a trained electrical fault classifier; Obtain the historical device operation status information of the electrical device to be recognized at the current time point; Input the historical device operation status information at the current time point into the trained electrical fault classifier, so as to obtain a classification result; Judge whether to give an alarm according to the classification result.

[0006] Optionally, the electrical safety management method with a learning function for fault recognition further includes: Create a first environmental database, where the first environmental database includes each segment of the first objective historical environmental information segment; Create a second environmental database, where the second environmental database includes each segment of the second objective historical environmental information segment; Obtain the historical accident information of the electrical equipment to be identified; Select the first environmental database or the second environmental database as the comparison object according to the historical accident information of the electrical equipment to be identified; When the classification result is an alarm, obtain the alarm confidence level through the selected comparison object.

[0007] Optionally, the step of selecting the first environmental database or the second environmental database as the comparison object according to the historical accident information of the electrical equipment to be identified includes: Obtain the time point of a historical accident information before the current time point, and this time point is called the historical accident time point; Judge whether the time interval between the historical accident time point and the current time point exceeds a first time period. If not, select the first environmental database as the comparison object.

[0008] Optionally, judge whether the time interval between the historical accident time point and the current time point exceeds the first time period. If so, select the second environmental database as the comparison object.

[0009] Optionally, when the first environmental database is selected as the comparison object, the step of obtaining the alarm confidence level through the selected comparison object when the classification result is an alarm includes: Compare the historical equipment operation status information between the historical accident time point and the current time point with each segment of the first objective historical environmental information segment respectively, so as to obtain the one with the highest similarity value as the alarm confidence level value.

[0010] Optionally, when the second environmental database is selected as the comparison object, the step of obtaining the alarm confidence level through the selected comparison object when the classification result is an alarm includes: Compare the historical equipment operation status information between the historical accident time point and the current time point with each segment of the first objective historical environmental information segment respectively, so as to obtain the one with the highest similarity value as the alarm confidence level value.

[0011] Optionally, the electrical fault classifier includes a five-layer convolutional network, and a squeeze-and-excitation network module and a spatial attention module are added between each convolutional layer.

[0012] Optionally, the electrical fault classifier is trained by the following method: Step 1: Initialize the parameters of the electrical fault classifier and the training parameters; Step 2: Input the training set into the feature extractor to obtain electrical features; Step 3: Input the electrical features into the classifier to obtain the predicted classification result; Step 4: Obtain the classification loss function according to the classification result; Step 5: Repeat the above steps until the iteration is completed or the loss value tends to be stable, then the training is completed, and the model parameters at the end of training are obtained.

[0013] Optionally, the classification loss function includes: ; where L class represents the classification loss value, is the true label value, is the predicted classification result, n is the number of categories, the loss value is calculated through the loss function, and the network parameters are updated in the direction of reducing the loss value.

[0014] This application also provides an electrical safety management system with a learning function for fault identification. The electrical safety management system with a learning function for fault identification includes: A database acquisition module, which is used to acquire a database. The database includes the historical device operation status information of each electrical device at each time point in seconds, the historical environment information corresponding to the historical device operation status information at each time point in seconds, the accident time point, and the accident cause; A first objective historical environment information segment acquisition module, which is used to segment the historical environment information corresponding to the historical device operation status information at each time point in seconds with every two adjacent accident time points as the starting point and the ending point, so as to obtain multiple segments of first objective historical environment information segments; A second objective historical environment information segment acquisition module, which is used to obtain the historical environment information of a preset time period before the cut-off point with each accident time point as the cut-off point as the second objective historical environment information segment; An electrical fault classifier acquisition module, which is used to acquire an electrical fault classifier; A training data set acquisition module, which is used to form a training data set by each segment of objective historical environment information segment, the second objective historical environment information segment, each accident time point, the historical device operation status information of the electrical device corresponding to each accident time point, and the accident cause; An electrical fault classifier acquisition module, which is used to train the electrical fault classifier through the training data set to obtain a trained electrical fault classifier; A historical device operation status information acquisition module, which is used to acquire the historical device operation status information of the electrical device to be identified at the current time point; A classification result acquisition module, which is used to input the historical device operation status information at the current time point into a trained electrical fault classifier to obtain a classification result; A judgment module, which is used to judge whether to give an alarm according to the classification result.

[0015] Beneficial effects: The electrical safety management method for fault identification with a learning function in this application combines environmental information and device operation status information (such as information that can be obtained through sensors or other means during device operation, such as current and voltage) to train a classifier, so that the classifier can deeply explore the correlation between the environment and the device operation status, and thus the classifier in this application has the advantages of accurate results and strong robustness. Description of the drawings

[0016] Figure 1 is a schematic flowchart of an electrical safety management method for fault identification with a learning function according to an embodiment of this application.

[0017] Figure 2 is a schematic diagram of an electronic device for implementing the electrical safety management method for fault identification with a learning function according to an embodiment of this application. Detailed implementation manners

[0018] To make the purpose, technical solutions and advantages of the implementation of this application clearer, the technical solutions in the embodiments of this application will be described in more detail below with reference to the drawings in the embodiments of this application. In the drawings, the same or similar reference numerals represent the same or similar elements or elements with the same or similar functions from beginning to end. The described embodiments are some, but not all, of the embodiments of this application. The embodiments described below by referring to the drawings are exemplary and are intended to explain this application and should not be construed as limiting this application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of this application without creative efforts shall fall within the protection scope of this application. The embodiments of this application will be described in detail below with reference to the drawings.

[0019] As Figure 1 shown, the electrical safety management method for fault identification with a learning function includes: Step 1: Obtain a database, where the database includes the historical device operation status information of each electrical device at each time point in seconds, the historical environmental information corresponding to the historical device operation status information at each time point in seconds, the accident time point, and the accident cause; Step 2: Segment the historical environmental information corresponding to the historical equipment operation status information at each time point in seconds, with every two adjacent accident time points as the starting point and the ending point, so as to obtain multiple segments of first objective historical environmental information segments; Step 3: Take each accident time point as the ending point, and obtain the historical environmental information in the preset time period before the ending point as the second objective historical environmental information segment; Step 4: Obtain an electrical fault classifier; Step 5: Combine each segment of objective historical environmental information segment, the second objective historical environmental information segment, each accident time point, the historical equipment operation status information of the electrical equipment corresponding to each accident time point, and the accident cause to form a training data set; Step 6: Train the electrical fault classifier with the training data set to obtain a trained electrical fault classifier; Step 7: Obtain the historical equipment operation status information at the current time point of the electrical equipment to be identified and the historical environmental information within the first time period; Step 8: Input the historical equipment operation status information at the current time point and the historical environmental information within the first time period into the trained electrical fault classifier to obtain a classification result; Step 9: Determine whether to give an alarm according to the classification result.

[0020] The electrical safety management method for fault identification with a learning function in this application combines environmental information and equipment operation status information (such as information that can be obtained through sensors or other means during equipment operation, such as current and voltage) to train a classifier, so that the classifier can deeply explore the correlation between the environment and the equipment operation status, and thus the classifier in this application has the advantages of accurate results and strong robustness.

[0021] In this embodiment, the historical environmental information in this application may include information such as temperature, humidity, operation time, and dust concentration in the operation environment.

[0022] In this embodiment, the accident cause may include short circuit, motor failure, overload, etc.

[0023] In this embodiment, the electrical safety management method for fault identification with a learning function further includes: Establish a first environment library, and the first environment library includes each segment of first objective historical environmental information segment; Establish a second environment library, and the second environment library includes each segment of second objective historical environmental information segment; Obtain the historical accident information of the electrical equipment to be identified; Select the first environmental library or the second environmental library as the comparison object according to the historical accident information of the electrical equipment to be identified; When the classification result is an alarm, obtain the alarm confidence level through the selected comparison object.

[0024] In this embodiment, generally, the same faults will have a certain degree of environmental similarity. For example, being in a humid environment for a long time is likely to cause short circuits and other situations. Therefore, by comparing the similarities, the confidence level of the alarm can be further increased. When the similarity is high, it means that the alarm confidence level will also be high, thus making a further judgment on the result judged by the classifier and increasing the credibility.

[0025] In this embodiment, the selecting the first environmental library or the second environmental library as the comparison object according to the historical accident information of the electrical equipment to be identified includes: Obtain the time point of a historical accident information before the current time point, and this time point is called the historical accident time point; Judge whether the time interval between the historical accident time point and the current time point exceeds the first time period. If not, select the first environmental library as the comparison object.

[0026] In this embodiment, judge whether the time interval between the historical accident time point and the current time point exceeds the first time period. If so, select the second environmental library as the comparison object.

[0027] In this embodiment, when the first environmental library is selected as the comparison object, the obtaining the alarm confidence level through the selected comparison object when the classification result is an alarm includes: Compare the historical equipment operation state information between the historical accident time point and the current time point with each first objective historical environmental information segment respectively to obtain the one with the highest similarity value as the alarm confidence level value.

[0028] In this embodiment, when the second environmental library is selected as the comparison object, the obtaining the alarm confidence level through the selected comparison object when the classification result is an alarm includes: Compare the historical equipment operation state information between the historical accident time point and the current time point with each first objective historical environmental information segment respectively to obtain the one with the highest similarity value as the alarm confidence level value.

[0029] In this embodiment, the electrical fault classifier includes a five-layer convolutional network, and a squeeze-and-excitation network module and a spatial attention module are added between each convolutional layer.

[0030] In this embodiment, the electrical fault classifier is trained by the following method: Step 1: Initialize the parameters of the electrical fault classifier and the training parameters; Step 2: Input the training set into the feature extractor to obtain electrical features; Step 3: Input the electrical features into the classifier to obtain the predicted classification results; Step 4: Obtain the classification loss function according to the classification results; Step 5: Repeat the above steps until the iteration is completed or the loss value tends to be stable, then the training is completed, and the model parameters at the end of the training are obtained.

[0031] In this embodiment, the classification loss function includes: ; where Lclass represents the classification loss value, is the true label value, is the predicted classification result, n is the number of categories, the loss value is calculated through the loss function, and the network parameters are updated in the direction of decreasing the loss value.

[0032] Through the classification model of the present application, the semantic and implicit information of the features can be fully retained, so that the classification is more accurate.

[0033] The present application also provides an electrical safety management system with a learning function for fault identification. The electrical safety management system with a learning function for fault identification includes a database acquisition module, a first objective historical environment information segment acquisition module, a second objective historical environment information segment acquisition module, an electrical fault classifier acquisition module, a training data set acquisition module, an electrical fault classifier acquisition module, a historical device operation status information acquisition module, a classification result acquisition module, and a judgment module. Among them, The database acquisition module is used to acquire a database, and the database includes the historical device operation status information of each electrical device at each time point in seconds, the historical environment information corresponding to the historical device operation status information at each time point in seconds, the accident time point, and the accident cause; The first objective historical environment information segment acquisition module is used to segment the historical environment information corresponding to the historical device operation status information at each time point in seconds with every two adjacent accident time points as the starting point and the ending point, so as to obtain multiple segments of first objective historical environment information segments; The second objective historical environment information segment acquisition module is used to obtain the historical environment information of a preset time period before the cut-off point with each accident time point as the cut-off point as the second objective historical environment information segment; The electrical fault classifier acquisition module is used to acquire an electrical fault classifier; The training data set acquisition module is used to form a training data set by each segment of objective historical environment information, the second segment of objective historical environment information, each accident time point, the historical equipment operation status information of the electrical equipment corresponding to each accident time point, and the accident cause; The electrical fault classifier acquisition module is used to train the electrical fault classifier through the training data set, so as to obtain a trained electrical fault classifier; The historical equipment operation status information acquisition module is used to obtain the historical equipment operation status information of the electrical equipment to be identified at the current time point; The classification result acquisition module is used to input the historical equipment operation status information at the current time point into the trained electrical fault classifier, so as to obtain the classification result; The judgment module is used to judge whether to give an alarm according to the classification result.

[0034] It should be noted that the foregoing explanation of the method embodiments also applies to the system of this embodiment, and will not be repeated here.

[0035] This application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor. When the processor executes the computer program, it implements the electrical safety management method with learning function for fault identification as described above.

[0036] This application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, it can implement the electrical safety management method with learning function for fault identification as described above.

[0037] Figure 2 It is an exemplary structural diagram of an electronic device capable of implementing the electrical safety management method with learning function for fault identification provided by an embodiment of this application.

[0038] As Figure 2As shown, the electronic device includes an input device 501, an input interface 502, a central processing unit 503, a memory 504, an output interface 505, and an output device 506. Among them, the input interface 502, the central processing unit 503, the memory 504, and the output interface 505 are interconnected through a bus 507. The input device 501 and the output device 506 are respectively connected to the bus 507 through the input interface 502 and the output interface 505, and then connected to other components of the electronic device. Specifically, the input device 501 receives external input information and transmits the input information to the central processing unit 503 through the input interface 502. The central processing unit 503 processes the input information based on computer-executable instructions stored in the memory 504 to generate output information, stores the output information temporarily or permanently in the memory 504, and then transmits the output information to the output device 506 through the output interface 505. The output device 506 outputs the output information to the outside of the electronic device for user use.

[0039] That is to say, Figure 2 the electronic device shown can also be implemented to include: a memory storing computer-executable instructions; and one or more processors that, when executing the computer-executable instructions, can implement the electrical safety management method with fault recognition having a learning function in combination with Figure 1 the description.

[0040] In one embodiment, Figure 2 the electronic device shown can be implemented to include: a memory 504 configured to store executable program code; one or more processors configured to run the executable program code stored in the memory 504 to execute the electrical safety management method with fault recognition having a learning function in the above embodiment.

[0041] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0042] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM), and / or non-volatile memory in the form of, for example, read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0043] A computer-readable medium includes permanent and non-permanent, removable and non-removable media that can store information by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic disk storage or other magnetic storage devices, or any other non-transitory medium that can store information accessible by a computing device.

[0044] The flowcharts and block diagrams in the figures illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code that includes one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the figures. For example, two consecutive blocks marked may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or overall flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0045] In this embodiment, the so-called processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0046] The memory can be used to store computer programs and / or modules. By running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory, the processor can implement various functions of the system / terminal device. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store the operating system, application programs required for at least one function (such as the sound playback function, the image playback function, etc.); the data storage area can store the data created according to the use of the mobile phone (such as audio data, phone book, etc.). In addition, the memory can include high-speed random access memory, and can also include non-volatile memory, such as hard disks, memory, plug-in hard disks, smart media cards (SMC), secure digital (SD) cards, flash cards, at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage devices.

[0047] In this embodiment, if the modules / units integrated in the system / terminal device are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above embodiment methods of the present invention, it can also be completed by a computer program instructing relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, it can implement the steps of the above various method embodiments. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or system that can carry computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. Although this application is disclosed above with preferred embodiments, it is not actually used to limit this application. Any person skilled in the art can make possible changes and modifications without departing from the spirit and scope of this application. Therefore, the protection scope of this application should be determined by the scope defined by the claims of this application.

[0048] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system or a computer program product. Therefore, the present application can take the form of a completely hardware embodiment, a completely software embodiment or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0049] In addition, it is obvious that the word "including" does not exclude other units or steps. The multiple units, modules or systems stated in the system claims can also be implemented by one unit or the total system through software or hardware.

[0050] Although the present invention has been described in detail above with general descriptions and specific embodiments, on the basis of the present invention, some modifications or improvements can be made, which are obvious to those skilled in the art. Therefore, these modifications or improvements made without departing from the spirit of the present invention all fall within the scope of protection of the present invention.

Claims

1. An electrical safety management method for fault identification with learning function, characterized in that: The electrical safety management method for fault identification with learning function includes: Acquire a database, the database including historical equipment operation status information of each electrical equipment at each time point in seconds, historical environment information corresponding to the historical equipment operation status information at each time point in seconds, accident time point and accident cause; Taking every two adjacent accident time points as the starting point and the ending point, segmenting the historical environment information corresponding to the historical equipment operation status information at each time point in seconds, thereby obtaining a plurality of first objective historical environment information segments; Taking each accident time point as a cutoff point, obtaining historical environmental information of a preset time period before the cutoff point as a second objective historical environmental information segment; Get an electrical fault classifier; Each objective historical environmental information segment, the second objective historical environmental information segment, each accident time point, the historical equipment operation status information of the electrical equipment corresponding to each accident time point, and the cause of the accident form a training data set; Training the electrical fault classifier using the training data set to obtain a trained electrical fault classifier; Obtain historical equipment operation status information of the electrical equipment to be identified at the current time point and historical environment information within a first time period; Inputting historical equipment operation status information at the current time point and historical environment information within the first time period into a trained electrical fault classifier to obtain a classification result; Determine whether to issue an alarm based on the classification results.

2. The electrical safety management method for fault identification with learning function according to claim 1, characterized in that: The electrical safety management method for fault identification with learning function further comprises: Establishing a first environment library, wherein the first environment library includes each first objective historical environment information segment; Establishing a second environment library, wherein the second environment library includes each second objective historical environment information segment; Obtain historical accident information of the electrical equipment to be identified; Selecting the first environment library or the second environment library as a comparison object according to the historical accident information of the electrical equipment to be identified; When the classification result is an alarm, the alarm confidence is obtained through the selected comparison object.

3. The electrical safety management method for fault identification with learning function according to claim 2, characterized in that: The selecting the first environment library or the second environment library as a comparison object according to the historical accident information of the electrical equipment to be identified comprises: The time point of obtaining the historical accident information before the current time point is called the historical accident time point; It is determined whether the time interval between the historical accident time point and the current time point exceeds the first time period. If not, the first environment library is selected as the comparison object.

4. The electrical safety management method for fault identification with learning function according to claim 3, characterized in that: Determine whether the time interval between the historical accident time point and the current time point exceeds the first time period. If so, select the second environment library as the comparison object.

5. The electrical safety management method for fault identification with learning function according to claim 4, characterized in that: When the first environment library is selected as the comparison object, when the classification result is an alarm, obtaining the alarm confidence through the selected comparison object includes: The historical equipment operation status information between the historical accident time point and the current time point is respectively compared with each first objective historical environment information segment for similarity, so as to obtain the one with the highest similarity value as the alarm confidence value.

6. The electrical safety management method for fault identification with learning function according to claim 5, characterized in that: When the second environment library is selected as the comparison object, when the classification result is an alarm, obtaining the alarm confidence through the selected comparison object includes: The historical equipment operation status information between the historical accident time point and the current time point is respectively compared with each first objective historical environment information segment for similarity, so as to obtain the one with the highest similarity value as the alarm confidence value.

7. The electrical safety management method for fault identification with learning function according to claim 6, characterized in that: The electrical fault classifier includes a five-layer convolutional network, and a squeeze-excitation network module and a spatial attention module are added between each convolutional layer.

8. The electrical safety management method for fault identification with learning function according to claim 7, characterized in that: The electrical fault classifier is trained by the following method: Step 1: Initialize electrical fault classifier parameters and training parameters; Step 2: Inputting the training set into the feature extractor to obtain electrical features; Step 3: Inputting the electrical features into a classifier to obtain a predicted classification result; Step 4: Obtain the classification loss function based on the classification results; Step 5: Repeat the above steps until the iteration is completed or the loss value tends to be stable, then the training is completed, and the model parameters at the completion of the training are obtained.

9. The electrical safety management method for fault identification with learning function according to claim 8, characterized in that: The classification loss function includes: ； Among them, Lclass represents the classification loss value, is the true label value, is the predicted classification result, n is the number of categories, the loss value is calculated by the loss function, and the network parameters are updated in the direction of reducing the loss value.

10. An electrical safety management system for fault identification with learning function, characterized in that: The electrical safety management system for fault identification with learning function comprises: A database acquisition module, the database acquisition module is used to acquire a database, the database including historical equipment operation status information of each electrical equipment at each time point in seconds, historical environment information corresponding to the historical equipment operation status information at each time point in seconds, accident time point and accident cause; A first objective historical environment information segment acquisition module, the first objective historical environment information segment acquisition module is used to segment the historical environment information corresponding to the historical equipment operation status information at each time point in seconds by taking every two adjacent accident time points as the starting point and the ending point, thereby acquiring multiple first objective historical environment information segments; A second objective historical environmental information segment acquisition module, the second objective historical environmental information segment acquisition module is used to use each accident time point as a cutoff point to acquire historical environmental information of a preset time period before the cutoff point as a second objective historical environmental information segment; An electrical fault classifier acquisition module, wherein the electrical fault classifier acquisition module is used to acquire an electrical fault classifier; A training data set acquisition module, the training data set acquisition module is used to form a training data set by combining each objective historical environmental information segment, the second objective historical environmental information segment, each accident time point, the historical equipment operation status information of the electrical equipment corresponding to each accident time point, and the cause of the accident; An electrical fault classifier acquisition module, wherein the electrical fault classifier acquisition module is used to train the electrical fault classifier using a training data set, thereby acquiring a trained electrical fault classifier; A historical equipment operation status information acquisition module, the historical equipment operation status information acquisition module is used to acquire the historical equipment operation status information of the electrical equipment to be identified at the current time point; A classification result acquisition module, wherein the classification result acquisition module is used to input historical equipment operation status information at a current time point into a trained electrical fault classifier to obtain a classification result; A judgment module is used to judge whether to issue an alarm according to the classification result.

Images