Fusing equipment early warning device and method for power equipment prediction based on artificial intelligence

Abstract

The invention belongs to the technical field of intelligent power grids, and discloses a fusing equipment early warning device and method for power equipment prediction based on artificial intelligence. The method comprises the following steps: collecting a current value of a fusing device in unit use time before fusing; analyzing the current value of the fusing equipment in unit use time before fusing, and extracting an abnormal current value in the current value; the ratio of the abnormal current value to the standard current value is compared with a preset abnormal multiple interval threshold value for analysis, a power grid fault type or an aging analysis instruction is generated, and the power grid fault type comprises lightning protection equipment damage and abnormal use of electric equipment in a power grid; acquiring aging influence data from the time when the fusing equipment is put into use to the current moment, wherein the aging influence data comprises environment influence data, rated current triggering times, use time and fusing equipment production information; the cause of the fault can be analyzed timely and accurately, the troubleshooting time is shortened, and the maintenance efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of smart grid technology, and more specifically, to a fuse equipment early warning device and method for power equipment prediction based on artificial intelligence. Background Art

[0002] Due to the large current fluctuations of some power equipment in the power grid system, when the traditional fuse is triggered by the instantaneous high current, the performance of the fuse itself will gradually deteriorate, reducing the service life of the fuse itself, thereby reducing the economic benefits when the fuse is triggered;

[0003] The existing Chinese patent with authorization announcement number CN116660672B discloses a power grid equipment fault diagnosis method and system based on big data, including a server, a power grid equipment collection and marking module, an internal cause data diagnosis and analysis module, an auxiliary data diagnosis and analysis module, an external cause data diagnosis and analysis module and an operation warning and supervision module; by performing internal cause monitoring and analysis on the corresponding power grid equipment in the corresponding associated equipment set to generate an internal cause normal signal or an internal cause abnormal signal, performing auxiliary data processing and analysis on the corresponding power grid equipment after generating the internal cause normal signal to generate an auxiliary cause normal signal or an auxiliary cause abnormal signal, and analyzing the environmental conditions in the control area to which the corresponding power grid equipment belongs after generating the auxiliary cause normal signal to generate an external cause normal signal or an external cause abnormal signal, a step-by-step multi-factor analysis is realized, the accuracy of the fault diagnosis and analysis results is significantly improved, and effective supervision of the power grid equipment in the supervision area is carried out.

[0004] For example, when the fuse of an electric power device in a power grid blows, there is a lack of consideration for the aging factor of the electric power device itself. If the fault of the electric power device is analyzed only based on the electrical characteristics of the electric power device (such as current, voltage, resistance, etc.), the analysis result of the cause of the fault of the electric power device will be reduced. If the power grid maintenance personnel maintain the electric power equipment based on this analysis result, it is easy to increase the troubleshooting time and reduce the maintenance efficiency.

[0005] In view of this, the present invention proposes a fuse equipment early warning device and method for power equipment prediction based on artificial intelligence to solve the above problems. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solution: a fuse equipment early warning method based on artificial intelligence prediction of power equipment, comprising:

[0007] Collect the current value per unit use time before the fuse device blows;

[0008] Analyze the current value per unit time of use of the fuse device before it blows, and extract the abnormal current value;

[0009] The ratio of the abnormal current value to the standard current value is compared and analyzed with the preset abnormal multiple interval threshold value to generate a power grid fault type or aging analysis instruction. The power grid fault type includes damage to lightning protection equipment and abnormal use of electrical equipment in the power grid;

[0010] Collect aging impact data from the time when the fuse equipment is put into use to the present moment. The aging impact data includes environmental impact data, the number of times the rated current is triggered, the use time and the production information of the fuse equipment;

[0011] Preprocessing the environmental impact data according to the aging analysis instruction to obtain preprocessed environmental impact data;

[0012] Input the pre-processed environmental impact data, the number of triggering rated currents and the use time into the pre-built aging impact analysis model to obtain the analysis results of aging and current fusing, including yes or no;

[0013] If the analysis result of aging and current fusing is negative, a fuse device quality warning instruction is generated and sent to the user terminal, so that the user can maintain the fuse device based on the fuse device quality warning instruction.

[0014] Furthermore, the method for extracting the abnormal current value includes:

[0015] Step 1, arranging the current values ​​per unit usage time before the fuse device is blown according to the collection time;

[0016] Step 2, calculate the difference between the first n consecutive and adjacent current values, obtain n-1 differences, take the average value of the n-1 differences as the standard fluctuation amplitude, and take the average value of the n consecutive and adjacent current values ​​as the standard current value;

[0017] Step 3: The current value exceeding the standard fluctuation range is regarded as an abnormal current value.

[0018] Furthermore, the method of generating a power grid fault type or aging analysis instruction includes:

[0019] The preset abnormal multiple interval thresholds include a1 and a2, a2 ​​is greater than a1. If the ratio of the abnormal current value to the standard current value is greater than or equal to a1, and less than or equal to a2, the power grid fault type is abnormal use of electrical equipment in the power grid; if the ratio of the abnormal current value to the standard current value is greater than a2, the power grid fault type is damage to the lightning protection equipment; if the ratio of the abnormal current value to the standard current value is less than a1, an aging analysis instruction is generated.

[0020] Furthermore, the training method of the aging impact analysis model includes:

[0021] i groups of aging sample data are collected in advance, where i is an integer greater than 1, and the aging sample data include aging characteristic data and labels corresponding to the aging characteristic data, and the labels include yes and no; the aging characteristic data include fusing characteristic data and stage characteristic data, and the labels corresponding to the fusing characteristic data are yes, and the labels corresponding to the stage characteristic data are no; the fusing characteristic data include pre-treatment fusing environmental impact data, the number of times the fusing triggers rated current, the fusing use time and the production information of the fusing equipment; the stage characteristic data include pre-treatment stage environmental impact data, the number of times the stage triggers rated current, the stage use time and the production information of the fusing equipment;

[0022] The aging sample data is divided into a training set and a test set, a classifier is constructed, the aging feature data in the training set is used as the input of the aging impact analysis model, and the label in the training set is used as the output, the classifier is trained to obtain an initial classifier, the initial classifier is tested using the test set, and a classifier that meets a preset accuracy is output as the aging impact analysis model, and the aging impact analysis model is a naive Bayes model or a support vector machine model.

[0023] Furthermore, the method for collecting the fuse characteristic data includes:

[0024] Under the conditions of different environmental data and rated current triggering times of different fuse equipment production information, the time series data of different environmental data, the rated current triggering times, and the corresponding fusing time are collected from the beginning of use of the fuse equipment until the fuse equipment blows. The fusing time is the time recorded from the beginning of use of the fuse equipment until the fuse equipment blows, that is, the fusing use time; the time series data of different environmental data are preprocessed to obtain preprocessed fusing environmental impact data, and the preprocessed fusing environmental impact data include temperature average value, temperature standard deviation, humidity average value, humidity standard deviation, corrosion gas concentration average value and corrosion gas concentration standard deviation.

[0025] Furthermore, the method for collecting the stage characteristic data includes:

[0026] Under the conditions of different environmental data and rated current triggering times of different fuse equipment production information, the time series data of different environmental data, the time series data of rated current triggering times and the stage use time corresponding to any time are collected from the beginning of use of the fuse equipment to any moment before the fuse equipment melts. The stage use time is the interval time from the beginning of use of the fuse equipment before melting to any corresponding moment, that is, the stage use time; the time series data of different environmental data are preprocessed to obtain the environmental impact data of the preprocessing stage, and the environmental impact data of the preprocessing stage include the temperature average value, temperature standard deviation, humidity average value, humidity standard deviation, corrosion gas concentration average value and corrosion gas concentration standard deviation.

[0027] Furthermore, the environmental impact data include temperature, humidity, and corrosive gas concentration; the pretreatment aging impact data include temperature average value, temperature standard deviation, humidity average value, humidity standard deviation, corrosive gas concentration average value, and corrosive gas concentration standard deviation.

[0028] Furthermore, the number of times the rated current is triggered is the number of times the circuit exceeds the rated current of the fuse device but does not reach the fuse current.

[0029] A fuse device early warning device for power equipment prediction based on artificial intelligence, implementing the fuse device early warning method for power equipment prediction based on artificial intelligence, comprising:

[0030] The first acquisition module is used to acquire the current value per unit use time before the fuse device is blown;

[0031] The first processing module analyzes the current value per unit use time of the fuse device before it blows, and extracts the abnormal current value therein;

[0032] The second processing module is used to compare and analyze the ratio of the abnormal current value to the standard current value with the preset abnormal multiple interval threshold value, and generate a power grid fault type or aging analysis instruction. The power grid fault type includes damage to the lightning protection equipment and abnormal use of the power equipment in the power grid;

[0033] The second collection module is used to collect aging impact data of the fuse device from the time it is put into use to the present moment, and the aging impact data includes environmental impact data, the number of times the rated current is triggered, the use time and the production information of the fuse device;

[0034] A preprocessing module, used for preprocessing the environmental impact data according to the aging analysis instruction to obtain preprocessed environmental impact data;

[0035] An identification module is used to input the pre-processed environmental impact data, the number of triggering rated currents and the use time into a pre-built aging impact analysis model to obtain an analysis result of aging and current fusing, the analysis result including yes or no;

[0036] The instruction sending module generates a fuse device quality warning instruction if the analysis result of aging and current fusing is no, and sends the fuse device quality warning instruction to the user terminal, so that the user maintains the fuse device based on the fuse device quality warning instruction.

[0037] An electronic device comprises 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 method for early warning of fuse equipment based on artificial intelligence prediction of electric power equipment is implemented.

[0038] A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed, implements the artificial intelligence-based power equipment prediction fuse equipment early warning method.

[0039] The technical effects and advantages of the present invention are as follows:

[0040] By collecting the current value per unit use time before the fuse device blows, and analyzing it, the standard fluctuation amplitude and the standard current value are calculated, thereby extracting the abnormal current value, and determining the type of power grid fault according to the ratio of the abnormal current value to the standard current value. The principle is to distinguish the different characteristics of the abnormal current when the specific power grid fault type occurs, and obtain the specific power grid fault type; when there is no specific power grid fault type, generate an aging analysis instruction, process the aging impact data collected from the time the fuse device is put into use to the current moment, and input the aging impact analysis model trained in advance to obtain the analysis results of aging and this blowing. If yes, it is determined that the blowing is caused by the aging of the material itself. If not, based on the analysis results, it can be concluded that the cause of the blowing of the fuse device this time is caused by the quality of the fuse device of this model and production batch.

[0041] Through the implementation of this technical solution, when the fuse device blows, the cause of the fault can be analyzed in a timely and accurate manner, which is convenient for power grid maintenance personnel to quickly maintain the power grid, reduce fault detection time, and improve maintenance efficiency; at the same time, the quality of the fuse device in use can also be analyzed, and the power grid maintenance personnel can replace the fuse device of this model and production batch in advance, further ensuring the stable operation of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 This is a structural schematic diagram of a fuse equipment early warning device for power equipment prediction based on artificial intelligence according to the present invention;

[0043] Figure 2 This is a flow chart of a method for obtaining abnormal current value according to the present invention;

[0044] Figure 3 A flow chart of a method for generating a power grid fault type or aging analysis instruction according to the present invention;

[0045] Figure 4 The present invention is a flow chart of the fuse equipment early warning method for power equipment prediction based on artificial intelligence. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] Example 1

[0048] See also Figure 1 As shown, the fuse equipment early warning device for power equipment prediction based on artificial intelligence described in this embodiment includes a first acquisition module, a first processing module, a second processing module, a second acquisition module, a preprocessing module, an identification module and an instruction sending module, and each module is connected by wire and / or wirelessly.

[0049] The first acquisition module is used to acquire the current value per unit use time before the fuse device blows.

[0050] The first processing module analyzes the current value per unit use time of the fuse device before it blows, and extracts the abnormal current value therein;

[0051] See also Figure 2 As shown, the method for extracting the abnormal current value includes:

[0052] Step 1, arranging the current values ​​per unit usage time before the fuse device is blown according to the collection time;

[0053] Step 2, calculate the difference between the first n consecutive and adjacent current values, obtain n-1 differences, take the average value of the n-1 differences as the standard fluctuation amplitude, and take the average value of the n consecutive and adjacent current values ​​as the standard current value;

[0054] Step 3: The current value exceeding the standard fluctuation range is regarded as an abnormal current value; the abnormal current value is the main factor causing the fuse device to blow, and is usually several times different from the normal current value.

[0055] The second processing module is used to compare and analyze the ratio of the abnormal current value to the standard current value with the preset abnormal multiple interval threshold to generate a power grid fault type or aging analysis instruction. The power grid fault type includes damage to lightning protection equipment and abnormal use of electrical equipment in the power grid.

[0056] See also Figure 3 As shown, the method for generating a power grid fault type or aging analysis instruction includes:

[0057] The preset abnormal multiple interval thresholds include a1 and a2, a2 ​​is greater than a1, if the ratio of the abnormal current value to the standard current value is greater than or equal to a1, and less than or equal to a2, then the power grid fault type is abnormal use of electrical equipment in the power grid; the reason is: when electrical equipment in the power grid is improperly turned on or off, transient current and surge current will be generated, which are usually 5 to 7 times the standard current. The preset abnormal multiple interval threshold is set specifically according to the power consumption area served by the corresponding power grid.

[0058] In response to abnormal use of electrical equipment in the power grid, power grid maintenance personnel will strengthen standardized electricity use training for factories or commercial areas corresponding to the power grid, or notify the person in charge of the electrical equipment to inspect soft starters, inverters, surge protectors, sequential start controllers, and troubleshoot faulty equipment.

[0059] If the ratio of the abnormal current value to the standard current value is greater than a2, the type of power grid fault is damage to the lightning protection equipment. The reason is that when the lightning protection equipment is damaged, the abnormal current value instantly reaches hundreds of thousands of amperes, far exceeding 7 times. For this fault, the lightning protection equipment can be repaired or replaced.

[0060] If the ratio of the abnormal current value to the standard current value is less than a1, an aging analysis instruction is generated.

[0061] The second acquisition module is used to collect aging impact data of the fuse device from the time it was put into use to the present moment. The aging impact data includes environmental impact data, the number of times the rated current is triggered, the usage time and the production information of the fuse device; the production information of the fuse device includes the model of the fuse device and the production batch of the fuse device; the environmental impact data includes temperature, humidity, and corrosive gas concentration; the temperature, humidity, and corrosive gas concentration are respectively collected by relevant sensors installed in the accessories of the fuse device, among which the temperature, humidity, and corrosive gas concentration all affect the service life of the fuse device to varying degrees.

[0062] The number of times the rated current is triggered is the number of times the circuit exceeds the rated current of the fuse device but does not reach the fuse current. The more times this happens, the more fragile the fuse in the fuse device will become, affecting its service life; the usage time is the time interval from the time the fuse device is put into use to the current moment.

[0063] The preprocessing module is used to preprocess the environmental impact data according to the aging analysis instruction to obtain preprocessed environmental impact data. The preprocessed aging impact data includes the temperature average value, temperature standard deviation, humidity average value, humidity standard deviation, corrosion gas concentration average value, and corrosion gas concentration standard deviation.

[0064] When generating aging analysis instructions, preprocessing the environmental impact data can reduce the computing resources of the predicted fuse equipment early warning device.

[0065] The identification module is used to input the pre-processed environmental impact data, the number of times the rated current is triggered and the usage time into the pre-built aging impact analysis model to obtain the analysis results of aging and this fusing. The analysis results include yes or no. If it is yes, it is determined that this fusing is related to the aging of the fuse device; if it is no, it is determined that this fusing is not related to the aging of the fuse device.

[0066] If only the pre-processed environmental impact data is used as the input of the aging impact analysis model, the impact of time cannot be reflected, which will affect the judgment accuracy of the aging impact analysis model. Therefore, this embodiment uses time and pre-processed environmental impact data as the input of the aging impact analysis model, which helps to improve the judgment accuracy of the aging impact analysis model.

[0067] The training method of the aging impact analysis model includes:

[0068] i groups of aging sample data are collected in advance; the aging sample data include aging characteristic data and labels corresponding to the aging characteristic data, and the labels include yes and no; the aging characteristic data include fusing characteristic data and stage characteristic data, and the label corresponding to the fusing characteristic data is yes, and the label corresponding to the stage characteristic data is no; the fusing characteristic data include pre-treatment fusing environmental impact data, the number of times the fusing triggers the rated current, the fusing use time and the production information of the fusing equipment; the stage characteristic data include pre-treatment stage environmental impact data, the number of times the stage triggers the rated current, the stage use time and the production information of the fusing equipment;

[0069] The aging sample data is divided into a training set and a test set, and a classifier is constructed. The aging feature data in the training set is used as the input of the aging impact analysis model, and the label in the training set is used as the output. The classifier is trained to obtain an initial classifier, and the initial classifier is tested using the test set. The classifier that meets the preset accuracy is output as the aging impact analysis model, and the aging impact analysis model is a naive Bayes model or a support vector machine model.

[0070] The collection methods of fuse characteristic data include:

[0071] In an experimental environment, the production information of different fuse devices is simulated under different environmental data and the number of times the rated current is triggered. The time series data of different environmental data, the number of times the rated current is triggered, and the corresponding fusing time are collected from the beginning of use of the fuse device to the time when the fuse device is blown. The fusing time is the time recorded from the beginning of use of the fuse device to the time when the fuse device is blown, that is, the fusing use time; the time series data of different environmental data are preprocessed to obtain preprocessed fusing environmental impact data, and the preprocessed fusing environmental impact data include temperature average value, temperature standard deviation, humidity average value, humidity standard deviation, corrosion gas concentration average value, and corrosion gas concentration standard deviation.

[0072] Methods for collecting stage characteristic data include:

[0073] In an experimental environment, the production information of different fuse devices is simulated under different environmental data and rated current triggering times. The time series data of different environmental data, the time series data of rated current triggering times, and the stage use time corresponding to any time are collected from the beginning of use of the fuse device to any moment before the fuse device melts. The stage use time is the interval time from the beginning of use of the fuse device before melting to any corresponding moment, that is, the stage use time; the time series data of different environmental data are preprocessed to obtain the environmental impact data of the preprocessing stage. The environmental impact data of the preprocessing stage include the average temperature, the standard deviation of the temperature, the average humidity, the standard deviation of the humidity, the average corrosion gas concentration, and the standard deviation of the corrosion gas concentration.

[0074] The instruction sending module generates a fuse device quality warning instruction if the analysis result of aging and this fuse is no, and sends the fuse device quality warning instruction to the user terminal, so that the user can maintain the fuse device based on the fuse device quality warning instruction; indicating that the reason for the fuse device to blow this time is caused by the quality of the fuse device of this model and production batch.

[0075] This embodiment collects and analyzes the current value per unit use time of the fuse device before it blows, calculates the standard fluctuation amplitude and the standard current value, thereby extracting the abnormal current value, and determining the type of power grid fault according to the ratio of the abnormal current value to the standard current value. The principle is to distinguish the different characteristics of the abnormal current when the specific power grid fault type occurs, and obtain the specific power grid fault type; when there is no specific power grid fault type, generate an aging analysis instruction, process the aging impact data collected from the time the fuse device is put into use to the current moment in the database, and input the aging impact analysis model trained in advance to obtain the analysis results of aging and this blowing. If yes, it is determined that the blowing is caused by the aging of the material itself. If not, based on the analysis results, it can be concluded that the cause of the blowing of the fuse device this time is caused by the quality of the fuse device of this model and production batch.

[0076] Through the implementation of this technical solution, when the fuse device blows, the cause of the fault can be analyzed in time, which is convenient for power grid maintenance personnel to quickly maintain the power grid, reduce fault detection time, and improve maintenance efficiency; at the same time, the quality of the fuse device in use can also be analyzed, and the power grid maintenance personnel can replace the fuse device of this model and production batch in advance, so as to further ensure the stable operation of the power grid.

[0077] Example 2

[0078] See also Figure 4 As shown, this embodiment provides a fuse device early warning method for power equipment prediction based on artificial intelligence, including: collecting the current value per unit use time of the fuse device before it blows;

[0079] Analyze the current value per unit time of use of the fuse device before it blows, and extract the abnormal current value;

[0080] The ratio of the abnormal current value to the standard current value is compared and analyzed with the preset abnormal multiple interval threshold value to generate a power grid fault type or aging analysis instruction. The power grid fault type includes damage to lightning protection equipment and abnormal use of electrical equipment in the power grid;

[0081] Collect aging impact data from the time when the fuse equipment is put into use to the present moment. The aging impact data includes environmental impact data, the number of times the rated current is triggered, the use time and the production information of the fuse equipment;

[0082] Preprocessing the environmental impact data according to the aging analysis instruction to obtain preprocessed environmental impact data;

[0083] Input the pre-processed environmental impact data, the number of triggering rated currents and the use time into the pre-built aging impact analysis model to obtain the analysis results of aging and current fusing, including yes or no;

[0084] If the analysis result of aging and current fusing is negative, a fuse device quality warning instruction is generated and sent to the user terminal, so that the user can maintain the fuse device based on the fuse device quality warning instruction.

[0085] Example 3

[0086] According to another aspect of the present application, an electronic device is also provided. The electronic device may include one or more processors and one or more memories. The memories store computer-readable codes, and when the computer-readable codes are executed by one or more processors, the fuse device early warning method for power device prediction based on artificial intelligence as described above may be executed.

[0087] The electronic device may include a bus, one or more CPUs, ROM, RAM, a communication port connected to a network, input / output, a hard disk, etc. A storage device in the electronic device, such as a ROM or a hard disk, may store the fuse device early warning method for power device prediction based on artificial intelligence provided in the present application. Furthermore, the electronic device may also include a user interface.

[0088] Example 4

[0089] According to one embodiment of the present application, a computer-readable storage medium is provided. Computer-readable instructions are stored on the computer-readable storage medium. When the computer-readable instructions are executed by the processor, the fuse device early warning method based on artificial intelligence prediction of power equipment according to the embodiment of the present application described with reference to the above figures can be executed. The storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0090] In addition, according to the implementation of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the present application provides a non-transitory machine-readable storage medium, which stores machine-readable instructions, and the machine-readable instructions can be executed by a processor to execute instructions corresponding to the method steps provided in the present application, such as: a fuse device early warning method for power equipment prediction based on artificial intelligence. When the computer program is executed by a central processing unit (CPU), the above functions defined in the method of the present application are executed.

[0091] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0092] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A fuse equipment early warning method for power equipment prediction based on artificial intelligence, characterized in that: include: Collect the current value per unit use time before the fuse device blows; Analyze the current value per unit time of use of the fuse device before it blows, and extract the abnormal current value; The ratio of the abnormal current value to the standard current value is compared and analyzed with the preset abnormal multiple interval threshold value to generate a power grid fault type or aging analysis instruction. The power grid fault type includes damage to lightning protection equipment and abnormal use of electrical equipment in the power grid; Collect aging impact data from the time when the fuse equipment is put into use to the present moment. The aging impact data includes environmental impact data, the number of times the rated current is triggered, the use time and the production information of the fuse equipment; Preprocessing the environmental impact data according to the aging analysis instruction to obtain preprocessed environmental impact data; Input the pre-processed environmental impact data, the number of triggering rated currents and the use time into the pre-built aging impact analysis model to obtain the analysis results of aging and current fusing, including yes or no; If the analysis result of aging and current fusing is no, a fuse device quality warning instruction is generated and sent to the user terminal, so that the user can maintain the fuse device based on the fuse device quality warning instruction.

2. The method for early warning of fuse equipment based on artificial intelligence prediction of power equipment according to claim 1 is characterized in that: The method for extracting the abnormal current value comprises: Step 1, arranging the current values ​​per unit usage time before the fuse device is blown according to the collection time; Step 2, calculate the difference between the first n consecutive and adjacent current values, obtain n-1 differences, take the average value of the n-1 differences as the standard fluctuation amplitude, and take the average value of the n consecutive and adjacent current values ​​as the standard current value; Step 3: The current value exceeding the standard fluctuation range is regarded as an abnormal current value.

3. The method for early warning of fuse equipment based on artificial intelligence prediction of power equipment according to claim 1 is characterized in that: Methods for generating power grid fault type or aging analysis instructions include: The preset abnormal multiple interval thresholds include a1 and a2, a2 ​​is greater than a1. If the ratio of the abnormal current value to the standard current value is greater than or equal to a1, and less than or equal to a2, the power grid fault type is abnormal use of electrical equipment in the power grid; if the ratio of the abnormal current value to the standard current value is greater than a2, the power grid fault type is damage to the lightning protection equipment; if the ratio of the abnormal current value to the standard current value is less than a1, an aging analysis instruction is generated.

4. The method for early warning of fuse equipment based on artificial intelligence prediction of power equipment according to claim 1 is characterized in that: The training method of the aging impact analysis model includes: i groups of aging sample data are collected in advance, where i is an integer greater than 1, and the aging sample data include aging characteristic data and labels corresponding to the aging characteristic data, and the labels include yes and no; the aging characteristic data include fusing characteristic data and stage characteristic data, and the labels corresponding to the fusing characteristic data are yes, and the labels corresponding to the stage characteristic data are no; the fusing characteristic data include pre-treatment fusing environmental impact data, the number of times the fusing triggers rated current, the fusing use time and the production information of the fusing equipment; the stage characteristic data include pre-treatment stage environmental impact data, the number of times the stage triggers rated current, the stage use time and the production information of the fusing equipment; The aging sample data is divided into a training set and a test set, a classifier is constructed, the aging feature data in the training set is used as the input of the aging impact analysis model, and the label in the training set is used as the output, the classifier is trained to obtain an initial classifier, the initial classifier is tested using the test set, and a classifier that meets a preset accuracy is output as the aging impact analysis model, and the aging impact analysis model is a naive Bayes model or a support vector machine model.

5. The method for early warning of fuse equipment based on artificial intelligence prediction of power equipment according to claim 4 is characterized in that: The method for collecting the fuse characteristic data includes: Under the conditions of different environmental data and rated current triggering times of different fuse equipment production information, the time series data of different environmental data, the rated current triggering times, and the corresponding fusing time are collected from the beginning of use of the fuse equipment until the fuse equipment blows. The fusing time is the time recorded from the beginning of use of the fuse equipment until the fuse equipment blows, that is, the fusing use time; the time series data of different environmental data are preprocessed to obtain preprocessed fusing environmental impact data, and the preprocessed fusing environmental impact data include temperature average value, temperature standard deviation, humidity average value, humidity standard deviation, corrosion gas concentration average value and corrosion gas concentration standard deviation.

6. The method for early warning of fuse equipment based on artificial intelligence prediction of power equipment according to claim 4 is characterized in that: The method for collecting the stage characteristic data includes: Under the conditions of different environmental data and rated current triggering times of different fuse equipment production information, the time series data of different environmental data, the time series data of rated current triggering times and the stage use time corresponding to any time are collected from the beginning of use of the fuse equipment to any moment before the fuse equipment melts. The stage use time is the interval time from the beginning of use of the fuse equipment before melting to any corresponding moment, that is, the stage use time; the time series data of different environmental data are preprocessed to obtain the environmental impact data of the preprocessing stage, and the environmental impact data of the preprocessing stage include the temperature average value, temperature standard deviation, humidity average value, humidity standard deviation, corrosion gas concentration average value and corrosion gas concentration standard deviation.

7. The method for early warning of fuse equipment based on artificial intelligence prediction of electric power equipment according to claim 1 is characterized in that: The environmental impact data include temperature, humidity, and corrosive gas concentration; the pretreatment aging impact data include temperature average value, temperature standard deviation, humidity average value, humidity standard deviation, corrosive gas concentration average value, and corrosive gas concentration standard deviation.

8. The method for early warning of fuse equipment based on artificial intelligence prediction of electric power equipment according to claim 1 is characterized in that: The triggering rated current times are the times that the circuit exceeds the rated current of the fuse device but does not reach the fuse current.

9. A fuse device early warning device for power equipment prediction based on artificial intelligence, implementing the fuse device early warning method for power equipment prediction based on artificial intelligence as claimed in any one of claims 1 to 8, characterized in that: include: The first acquisition module is used to acquire the current value per unit use time before the fuse device is blown; The first processing module analyzes the current value per unit use time of the fuse device before it blows, and extracts the abnormal current value therein; The second processing module is used to compare and analyze the ratio of the abnormal current value to the standard current value with the preset abnormal multiple interval threshold value, and generate a power grid fault type or aging analysis instruction. The power grid fault type includes damage to the lightning protection equipment and abnormal use of the power equipment in the power grid; The second collection module is used to collect aging impact data of the fuse device from the time it is put into use to the present moment, and the aging impact data includes environmental impact data, the number of times the rated current is triggered, the use time and the production information of the fuse device; A preprocessing module, used for preprocessing the environmental impact data according to the aging analysis instruction to obtain preprocessed environmental impact data; An identification module is used to input the pre-processed environmental impact data, the number of triggering rated currents and the use time into a pre-built aging impact analysis model to obtain an analysis result of aging and current fusing, the analysis result including yes or no; The instruction sending module generates a fuse device quality warning instruction if the analysis result of aging and current fusing is no, and sends the fuse device quality warning instruction to the user terminal, so that the user maintains the fuse device based on the fuse device quality warning instruction.

Images