Fuse Device Early Warning Device and Method for Power Equipment Prediction Based on Artificial Intelligence

Abstract

The present invention belongs to the technical field of smart grids. The present invention discloses a fusing device warning device and method for power equipment prediction based on artificial intelligence. The method includes: collecting the current value per unit usage time before the fusing of the fusing device; analyzing the current value per unit usage time before the fusing of the fusing device to extract abnormal current values; comparing and analyzing the ratio of the abnormal current value to the standard current value with a preset abnormal multiple interval threshold to generate a power grid fault type or aging analysis instruction, and the power grid fault types include lightning protection equipment damage and abnormal usage of electrical equipment in the power grid; collecting aging influence data from the time when the fusing device is put into use to the current moment, and the aging influence data includes environmental influence data, the number of times of triggering the rated current, the usage time, and the production information of the fusing device. It can timely and accurately analyze the cause of this fault, reduce the fault troubleshooting time, and improve the maintenance efficiency.

Description

Technical Field

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

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

[0003] The existing Chinese patent with the authorization announcement number CN116660672B discloses a method and system for fault diagnosis of power grid equipment based on big data, including a server, a power grid equipment acquisition and marking module, an internal cause data diagnosis and analysis module, an accessory data diagnosis and analysis module, an external cause data diagnosis and analysis module, and an operation warning and supervision module; by monitoring and analyzing the internal causes of the corresponding power grid equipment in the corresponding associated equipment set to generate an internal cause normal signal or an internal cause abnormal signal, when generating an internal cause normal signal, processing and analyzing the accessory data of the corresponding power grid equipment to generate an accessory cause normal signal or an accessory cause abnormal signal, and when generating an accessory cause normal signal, analyzing the environmental conditions within the control area to which the corresponding power grid equipment belongs to generate an external cause normal signal or an external cause abnormal signal, realizing step-by-step multi-factor analysis, significantly improving the accuracy of the fault diagnosis and analysis results and effectively supervising the power grid equipment within the supervision area.

[0004] For example, when the fuse of a power equipment in the power grid melts, the consideration of the aging factor of the power equipment itself is lacking. If only the electrical characteristics (such as current, voltage, resistance, etc.) of the power equipment are used to analyze the fault of the power equipment, the analysis result of the fault cause of the power equipment is reduced. If the power grid maintenance personnel perform maintenance on the power equipment based on this analysis result, it is easy to increase the fault troubleshooting time and reduce the maintenance efficiency.

[0005] In view of this, the present invention proposes a fuse device 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 object, the present invention provides the following technical solution: A fuse device warning method for power equipment prediction based on artificial intelligence, including:

[0007] Collect the current value per unit usage time before the fuse device melts;

[0008] Analyze the current value per unit usage time before the fuse device melts, and extract the abnormal current values;

[0009] Compare the ratio of the abnormal current value to the standard current value with the preset abnormal multiple interval threshold, and generate an instruction for analyzing the power grid fault type or aging. The power grid fault types include damage to lightning protection equipment and abnormal use of electrical equipment in the power grid.

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

[0011] Preprocess the environmental impact data according to the aging analysis instruction to obtain the preprocessed environmental impact data.

[0012] Input the preprocessed environmental impact data, the number of times of triggering the rated current, and the usage time into the pre-constructed aging impact analysis model to obtain the analysis result of aging and this fuse, and the analysis result includes yes or no.

[0013] If the analysis result of aging and this fuse is no, then generate a quality warning instruction for the fuse equipment, and send the quality warning instruction for the fuse equipment to the user terminal, so that the user can maintain the fuse equipment based on the quality warning instruction for the fuse equipment.

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

[0015] Step 1: Arrange the current values per unit usage time before the fuse of the fuse equipment according to the collection time.

[0016] Step 2: Calculate the differences between the first n consecutive and adjacent current values to obtain n - 1 differences, take the average of the n - 1 differences as the standard fluctuation amplitude, and take the average of the n consecutive and adjacent current values as the standard current value.

[0017] Step 3: Take the current values exceeding the standard fluctuation amplitude as the abnormal current values.

[0018] Further, the method for generating an instruction for analyzing the power grid fault type or aging includes:

[0019] The preset abnormal multiple interval threshold includes 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; if the ratio of the abnormal current value to the standard current value is greater than a2, then the power grid fault type is damage to lightning protection equipment; if the ratio of the abnormal current value to the standard current value is less than a1, then generate an aging analysis instruction.

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

[0021] Pre-collect i sets of aging sample data, where i is an integer greater than 1. The aging sample data includes aging characteristic data and the corresponding labels of the aging characteristic data. The labels include yes or no. The aging characteristic data includes fuse characteristic data and stage characteristic data. The label corresponding to the fuse characteristic data is yes, and the label corresponding to the stage characteristic data is no. The fuse characteristic data includes preprocessing fuse environment impact data, fuse trigger rated current times, fuse usage time, and fuse device production information. The stage characteristic data includes preprocessing stage environment impact data, stage trigger rated current times, stage usage time, and fuse device production information.

[0022] Divide the aging sample data into a training set and a test set, construct a classifier, respectively use the aging characteristic data in the training set as the input of the aging impact analysis model, and use the labels in the training set as the output to train the classifier to obtain an initial classifier. Use the test set to test the initial classifier, and output the classifier that meets the preset accuracy as the aging impact analysis model. The aging impact analysis model is a Naive Bayes model or a Support Vector Machine model.

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

[0024] Under the conditions of different fuse device production information, different environmental data, and trigger rated current times, collect the time series data of different environmental data, the trigger rated current times, and the corresponding fuse time from the start of use of the fuse device until the fuse device fuses. The fuse time is the time recorded from the start of use of the fuse device until the fuse device fuses, that is, the fuse usage time. Preprocess the time series data of different environmental data to obtain preprocessing fuse environment impact data. The preprocessing fuse environment impact data includes temperature average value, temperature standard deviation, humidity average value, humidity standard deviation, corrosion gas concentration average value, and corrosion gas concentration standard deviation.

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

[0026] Under the conditions of different fuse device production information, different environmental data, and trigger rated current times, collect the time series data of different environmental data, the time series data of the trigger rated current times, and the corresponding stage usage time at any moment from the start of use of the fuse device until the fuse device melts. The stage usage time is the time interval from the start of use before the fuse device melts to the corresponding moment, that is, the stage usage time. Preprocess the time series data of different environmental data to obtain preprocessing stage environment impact data. The preprocessing stage environment impact data includes 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 includes temperature, humidity, and corrosive gas concentration; the preprocessing aging impact data includes the average temperature, standard deviation of temperature, average humidity, standard deviation of humidity, average corrosive gas concentration, and standard deviation of corrosive gas concentration.

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

[0029] A warning device for a fusing device for predicting power equipment based on artificial intelligence, implementing the warning method for a fusing device for predicting power equipment based on artificial intelligence, includes:

[0030] A first acquisition module, configured to acquire the current value per unit usage time before the fusing device fuses;

[0031] A first processing module, analyzes the current value per unit usage time before the fusing device fuses, and extracts the abnormal current values therein;

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

[0033] A second acquisition module, configured to acquire the aging impact data from the time when the fusing device is put into use to the current moment, where the aging impact data includes environmental impact data, the number of times of triggering the rated current, usage time, and fusing device production information;

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

[0035] An identification module, configured to input the preprocessed environmental impact data, the number of times of triggering the rated current, and the usage time into a pre-constructed aging impact analysis model to obtain an analysis result of aging and the current fusing, where the analysis result includes yes or no;

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

[0037] An electronic device includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, the warning method for a fusing device for predicting power equipment based on artificial intelligence as described above is implemented.

[0038] A computer-readable storage medium has a computer program stored thereon, and when the computer program is executed, the fuse device warning method for power equipment prediction based on artificial intelligence is implemented.

[0039] The technical effects and advantages of a fuse device warning device and method for power equipment prediction based on artificial intelligence according to the present invention:

[0040] By collecting the current value per unit usage time before the fuse device fuses, analyzing it, calculating the standard fluctuation amplitude and the standard current value, abnormal current values are extracted, and the power grid fault type is determined according to the ratio of the abnormal current value to the standard current value. The principle is to distinguish based on the different characteristics shown by the abnormal current when specific power grid fault types occur, so as to obtain the specific power grid fault type; when there is no specific power grid fault type, an aging analysis instruction is generated, the aging influence data of the fuse device collected in the database from the time of commissioning to the current time is processed, and input into the pre-trained aging influence analysis model to obtain the analysis result of aging and this fuse. If it is yes, it is determined that this fuse is caused by the aging of the material itself. If it is no, based on the analysis result, it can be concluded that the reason for the fuse of this fuse device this time is the quality of the fuse device of this model and production batch.

[0041] Through the technical solution of this embodiment, when the fuse device fuses, the cause of this 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 the fault troubleshooting time, and improve the maintenance efficiency; at the same time, the quality of the fuse device in use can also be analyzed, and power grid maintenance personnel can replace the fuse device of this model and production batch in advance to further ensure the stable operation of the power grid. Brief Description of the Drawings

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

[0043] Figure 2 It is a flowchart of the method for obtaining abnormal current values according to the present invention;

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

[0045] Figure 4 It is a flowchart of the fuse device warning method for power equipment prediction based on artificial intelligence according to the present invention. Detailed Embodiments

[0046] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0047] Embodiment 1

[0048] Please refer to Figure 1 As shown in the figure, a fuse device warning device for power equipment prediction based on artificial intelligence 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. Each module is connected by wire and / or wireless.

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

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

[0051] Please refer to Figure 2 As shown in the figure, the method for extracting the abnormal current value includes:

[0052] Step 1: Arrange the current values per unit usage time before the fuse device blows according to the acquisition time;

[0053] Step 2: Calculate the differences between the first n consecutive and adjacent current values to 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: Take the current values exceeding the standard fluctuation amplitude as abnormal current values; the abnormal current value is the main factor causing the fuse device to blow and usually differs from the normal current value by several times.

[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 types include lightning protection equipment damage and abnormal use of electrical equipment in the power grid.

[0056] Please refer to Figure 3 As shown in the figure, the method for generating a power grid fault type or aging analysis instruction includes:

[0057] The preset abnormal multiple interval threshold includes a1 and a2, where 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. The reason is that when electrical equipment in the power grid is turned on or off improperly, 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 specifically set according to the power consumption area corresponding to the power grid service.

[0058] For the abnormal use of electrical equipment in the power grid, grid maintenance personnel should strengthen the standardized electricity use training for factories or commercial areas in the corresponding power consumption area of the power grid, or notify the person in charge of the electrical equipment to inspect the soft starter, frequency converter, surge protector, and sequence start controller to check for faulty equipment.

[0059] 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 lightning protection equipment. The reason is that when the lightning protection equipment is damaged, the abnormal current value reaches hundreds of thousands of amperes instantly, 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 acquire the aging influence data from the time when the fuse equipment is put into use to the current moment. The aging influence data includes environmental influence data, the number of times of triggering the rated current, the service time, and the production information of the fuse equipment. The production information of the fuse equipment includes the fuse equipment model and the production batch of the fuse equipment. The environmental influence data includes temperature, humidity, and corrosive gas concentration. The temperature, humidity, and corrosive gas concentration are respectively acquired by relevant sensors installed on the accessories of the fuse equipment. Among them, the temperature, humidity, and corrosive gas concentration all affect the service life of the fuse equipment to varying degrees.

[0062] The number of times of triggering the rated current is the number of times when the circuit exceeds the rated current of the fuse equipment but does not reach the fusing current. The more times it occurs, the more fragile the fuse in the fuse equipment will become, affecting its service life. The service time is the time interval from when the fuse equipment is put into use to the current moment.

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

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

[0065] An identification module is configured to input the pre - processed environmental impact data, the number of times of triggering the rated current, and the usage time into a pre - constructed aging impact analysis model to obtain an analysis result of aging and the current fuse - blowing. The analysis result includes "yes" or "no". If it is "yes", it is determined that the current fuse - blowing is related to the aging of the fuse device; if it is "no", it is determined that the current fuse - blowing 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, in this embodiment, the usage time and the pre - processed environmental impact data are used as the input of the aging impact analysis model at the same time, 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] Pre - collect i groups of aging sample data; the aging sample data includes aging characteristic data and the corresponding labels of the aging characteristic data. The labels include "yes" and "no"; the aging characteristic data includes fuse - blowing characteristic data and stage characteristic data. The label corresponding to the fuse - blowing characteristic data is "yes", and the label corresponding to the stage characteristic data is "no"; the fuse - blowing characteristic data includes pre - processed fuse - blowing environmental impact data, the number of times of triggering the rated current during fuse - blowing, the usage time of fuse - blowing, and the production information of the fuse device; the stage characteristic data includes pre - processed stage environmental impact data, the number of times of triggering the rated current in the stage, the usage time in the stage, and the production information of the fuse device.

[0069] Divide the aging sample data into a training set and a test set, construct a classifier, respectively use the aging characteristic data in the training set as the input of the aging impact analysis model, use the labels in the training set as the output, train the classifier to obtain an initial classifier, and use the test set to test the initial classifier. Output a classifier that meets the preset accuracy as the aging impact analysis model. The aging impact analysis model is a Naive Bayes model or a Support Vector Machine model.

[0070] The collection method of the fuse - blowing characteristic data includes:

[0071] Under the experimental environment, simulate different production information of fuse devices under different environmental data and the number of times of triggering the rated current, collect the time - series data of different environmental data, the number of times of triggering the rated current, and the corresponding fuse - blowing time when the fuse device is used from the start until it blows. The fuse - blowing time is the time recorded when the fuse device is used from the start until it blows, that is, the usage time of fuse - blowing; pre - process the time - series data of different environmental data to obtain pre - processed fuse - blowing environmental impact data. The pre - processed fuse - blowing environmental impact data includes the average temperature, the standard deviation of temperature, the average humidity, the standard deviation of humidity, the average concentration of corrosive gas, and the standard deviation of the concentration of corrosive gas.

[0072] The method for collecting stage characteristic data includes:

[0073] Under the experimental environment, simulate the production information of different fusing devices under different environmental data and the number of times of triggering the rated current. Collect the time series data of different environmental data, the time series data of the number of times of triggering the rated current, and the stage usage time corresponding to any moment from the start of using the fusing device until any moment before the fusing device fuses. The stage usage time is the interval time from the start of using the fusing device before fusing to the corresponding moment, that is, the stage usage time; preprocess the time series data of different environmental data to obtain the environmental impact data in the preprocessing stage. The environmental impact data in the preprocessing stage includes the average temperature, temperature standard deviation, average humidity, humidity standard deviation, average concentration of corrosive gas, and standard deviation of corrosive gas concentration.

[0074] The instruction sending module, if the analysis result of aging and the current fusing is negative, generates a quality warning instruction for the fusing device and sends the quality warning instruction for the fusing device to the user terminal, so that the user can maintain the fusing device based on the quality warning instruction for the fusing device; it is explained that the reason for the fusing of the fusing device this time is caused by the quality of the fusing device of this model and production batch.

[0075] In this embodiment, by collecting the current value per unit usage time before the fusing device fuses, analyzing, calculating the standard fluctuation amplitude and the standard current value, the abnormal current value is extracted, and the power grid fault type is determined according to the ratio of the abnormal current value to the standard current value. The principle is to distinguish according to the different characteristics shown by 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, an aging analysis instruction is generated, the aging impact data of the fusing device collected in the database from the start of use to the current moment is processed, and input into the pre-trained aging impact analysis model to obtain the analysis result of aging and the current fusing. If it is positive, it is determined that the current fusing is caused by the aging of the material itself. If it is negative, based on the analysis result, it can be concluded that the reason for the fusing of the fusing device this time is caused by the quality of the fusing device of this model and production batch.

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

[0077] Embodiment 2

[0078] Please refer toFigure 4 As shown in Figure 4 , this embodiment provides a fuse device warning method for power equipment prediction based on artificial intelligence, including: collecting the current value per unit usage time before the fuse device fuses;

[0079] Analyzing the current value per unit usage time before the fuse device fuses, and extracting the abnormal current values therein;

[0080] Comparing and analyzing 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 types include lightning protection device damage and abnormal usage of electrical equipment in the power grid;

[0081] Collecting the aging influence data from the time when the fuse device is put into use to the current moment. The aging influence data includes environmental influence data, the number of times of triggering the rated current, the usage time, and the production information of the fuse device;

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

[0083] Inputting the preprocessed environmental influence data, the number of times of triggering the rated current, and the usage time into a pre-constructed aging influence analysis model to obtain the analysis result of aging and this fuse, and the analysis result includes yes or no;

[0084] If the analysis result of aging and this fuse is no, then generate a fuse device quality warning instruction and send 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.

[0085] Embodiment 3

[0086] According to another aspect of the present application, an electronic device is further provided. The electronic device may include one or more processors and one or more memories. Among them, computer-readable code is stored in the memory, and when the computer-readable code is run by one or more processors, it can execute the above-mentioned fuse device warning method for power equipment prediction based on artificial intelligence.

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

[0088] Embodiment 4

[0089] According to an 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 run by a processor, the fuse device warning method based on artificial intelligence power equipment prediction according to the embodiment of the present application described with reference to the above drawings 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, etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0090] In addition, according to an embodiment 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 storing machine-readable instructions that can be run by a processor to execute instructions corresponding to the method steps provided by the present application, such as: the fuse device warning method based on artificial intelligence power equipment prediction. 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] As described above, the above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

[0092] Finally: The above are only the preferred embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A fuse device warning method for power equipment prediction based on artificial intelligence, characterized in that, Including: Collecting the current value per unit usage time before the fuse device fuses; Analyzing the current value per unit usage time before the fuse device fuses and extracting the abnormal current values therein; Comparing and analyzing 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, where the power grid fault types include lightning protection device damage and abnormal usage of electrical equipment in the power grid; Collecting the aging influence data from the time the fuse device is put into use to the current moment, where the aging influence data includes environmental influence data, the number of times of triggering the rated current, the usage time, and the production information of the fuse device; Preprocessing the environmental influence data according to the aging analysis instruction to obtain the preprocessed environmental influence data; Inputting the preprocessed environmental influence data, the number of times of triggering the rated current, and the usage time into a pre-constructed aging influence analysis model to obtain the analysis result of aging and this fuse, where the analysis result includes yes or no; If the analysis result of aging and this fuse is no, then generating a quality warning instruction for the fuse device and sending the quality warning instruction for the fuse device to the user terminal so that the user can maintain the fuse device based on the quality warning instruction for the fuse device.

2. The fuse device warning method for power equipment prediction based on artificial intelligence according to claim 1, characterized in that The method for extracting the abnormal current value includes: Step 1: Arranging the current values per unit usage time before the fuse device fuses according to the collection time; Step 2: Calculating the differences between the first n consecutive and adjacent current values to obtain n - 1 differences, taking the average value of the n - 1 differences as the standard fluctuation amplitude, and taking the average value of the n consecutive and adjacent current values as the standard current value; Step 3: Taking the current values exceeding the standard fluctuation amplitude as the abnormal current values.

3. The fuse device warning method for power equipment prediction based on artificial intelligence according to claim 1, characterized in that, The method for generating a power grid fault type or aging analysis instruction includes: The preset abnormal multiple interval threshold includes a1 and a2, where 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 usage of electrical equipment in the power grid; if the ratio of the abnormal current value to the standard current value is greater than a2, then the power grid fault type is lightning protection device damage; if the ratio of the abnormal current value to the standard current value is less than a1, then an aging analysis instruction is generated.

4. The fuse device warning method for power equipment prediction based on artificial intelligence according to claim 1, characterized in that, The training method of the aging influence analysis model includes: Pre-collecting i groups of aging sample data, where i is an integer greater than 1. The aging sample data includes aging characteristic data and the labels corresponding to the aging characteristic data, and the labels include yes or no; the aging characteristic data includes fuse characteristic data and stage characteristic data, the label corresponding to the fuse characteristic data is yes, and the label corresponding to the stage characteristic data is no; the fuse characteristic data includes preprocessed fuse environmental influence data, the number of times of triggering the rated current during fuse, the usage time during fuse, and the production information of the fuse device; the stage characteristic data includes preprocessed stage environmental influence data, the number of times of triggering the rated current in the stage, the usage time in the stage, and the production information of the fuse device; Divide the aged sample data into a training set and a test set, construct a classifier, use the aged feature data in the training set as the input of the aging impact analysis model and the labels in the training set as the output respectively to train the classifier to obtain an initial classifier, and use the test set to test the initial classifier. Output the classifier that meets the preset accuracy as the aging impact analysis model. The aging impact analysis model is a Naive Bayes model or a Support Vector Machine model.

5. The fuse device warning method for power equipment prediction based on artificial intelligence according to claim 4, characterized in that, The method for collecting the fuse feature data includes: Under the conditions of different fuse device production information, different environmental data and the number of times of triggering the rated current, collect the time series data of different environmental data, the number of times of triggering the rated current, and the corresponding fuse time from the start of use of the fuse device until the fuse device fuses. The fuse time is the time recorded from the start of use of the fuse device until the fuse device fuses, that is, the fuse usage time; preprocess the time series data of different environmental data to obtain preprocessed fuse environmental impact data, and the preprocessed fuse environmental impact data includes average temperature, temperature standard deviation, average humidity, humidity standard deviation, average corrosion gas concentration and corrosion gas concentration standard deviation.

6. The fuse device warning method for power equipment prediction based on artificial intelligence according to claim 4, characterized in that, The method for collecting the stage feature data includes: Under the conditions of different fuse device production information, different environmental data and the number of times of triggering the rated current, collect the time series data of different environmental data, the time series data of the number of times of triggering the rated current, and the corresponding stage usage time at any moment from the start of use of the fuse device until before the fuse device fuses. The stage usage time is the interval time from the start of use before the fuse device fuses to the corresponding moment, that is, the stage usage time; preprocess the time series data of different environmental data to obtain preprocessed stage environmental impact data, and the preprocessed stage environmental impact data includes average temperature, temperature standard deviation, average humidity, humidity standard deviation, average corrosion gas concentration and corrosion gas concentration standard deviation.

7. The fuse device warning method for power equipment prediction based on artificial intelligence according to claim 1, characterized in that, The environmental impact data includes temperature, humidity, and corrosion gas concentration; the preprocessed aging impact data includes average temperature, temperature standard deviation, average humidity, humidity standard deviation, average corrosion gas concentration, and corrosion gas concentration standard deviation.

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

9. A fuse device warning device for power equipment prediction based on artificial intelligence, which implements the fuse device warning method for power equipment prediction based on artificial intelligence according to any one of claims 1-8, characterized in that, It includes: A first acquisition module for acquiring the current value per unit usage time before the fuse device fuses; A first processing module for analyzing the current value per unit usage time before the fuse device fuses and extracting the abnormal current value therein; A second processing module for comparing and analyzing 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 an aging analysis instruction. The power grid fault type includes lightning protection device damage and abnormal use of electrical equipment in the power grid; A second acquisition module for acquiring the aging impact data from the start of use of the fuse device to the current moment. The aging impact data includes environmental impact data, the number of times of triggering the rated current, usage time, and fuse device production information; A preprocessing module for preprocessing environmental impact data according to aging analysis instructions to obtain preprocessed environmental impact data; An identification module for inputting the preprocessed environmental impact data, the triggered rated current times, and the usage time into a pre-constructed aging impact analysis model to obtain an analysis result of aging and the current fuse blowing, where the analysis result includes yes or no; An instruction sending module. If the analysis result of aging and the current fuse blowing is no, it generates a quality warning instruction for the fuse device and sends the quality warning instruction for the fuse device to the user terminal so that the user can maintain the fuse device based on the quality warning instruction for the fuse device.

Images