CN116526415A - A kind of electric equipment protection device and its control method - Google Patents

Abstract

The application provides a power equipment protection device and a control method thereof, wherein the obtained historical overload data of power equipment are analyzed, a data abnormal interval is determined, abnormal data is determined through the data abnormal interval, and the abnormal data is removed to obtain stable overload data; the equipment overload rate of the power equipment is determined through stable overload data, the reliable warning probability of different sensors in the power equipment is determined through the correct warning times of the different sensors, and the unreliable warning probability of the different sensors in the power equipment is determined through the error warning times of the different sensors; in the same time window, obtaining comprehensive warning probability according to the overload rate, the reliable warning probability and the unreliable warning probability of the equipment; when the warning information of different time windows is received, the warning information is sequenced according to the comprehensive warning probability corresponding to the warning information and then presented to the overload manager, so that the overload warning accuracy of the power equipment protection device can be effectively improved.

Description

A kind of electric equipment protection device and its control method

technical field

The present application relates to the technical field of power equipment protection, and more specifically, the present application relates to a power equipment protection device and a control method thereof.

Background technique

The power equipment protection device is a device used to protect various equipment in the power system (such as transformers, generators, cables, lines, etc.) Current, voltage, frequency, etc., and take corresponding control measures to protect the safe operation of power equipment.

When the power system is overloaded, the power equipment protection device will detect abnormal overload data and send an overload warning signal. For example, the power equipment protection device can monitor the current value through the current sensor. When the current value in the power system exceeds the preset threshold , indicating that the equipment is in an overload state, and the current sensor will trigger an overload warning signal, but in the prior art, the overload control in the power equipment protection device is carried out through the overload data detected in real time, because the threshold value setting of the sensor for overload detection is inaccurate Or the accuracy and error of the sensor, there will be a large error in the overload warning only through the overload data detected in real time, resulting in a low accuracy rate of the overload warning of the power equipment protection device.

Contents of the invention

The present application provides a power equipment protection device and a control method thereof to solve the technical problem of low overload warning accuracy in the power equipment protection device.

In order to solve the above technical problems, the application adopts the following technical solutions:

In a first aspect, the present application provides a control method for a power equipment protection device, including:

Start the overload control of the power equipment protection device, and obtain the historical overload data of the power equipment;

Analyzing the historical overload data, determining a data abnormal interval, determining abnormal data through the data abnormal interval, removing the abnormal data, and obtaining stable overload data;

Through the stable overload data, the equipment overload rate of the electric equipment can be determined, the reliable warning probability of different sensors in the electric equipment can be determined through the correct warning times of different sensors, and the false alarm probability of different sensors in the power equipment can be determined through the wrong warning times of different sensors. Reliable warning probability;

In each time window, according to the equipment overload rate, the reliable warning probability and the unreliable warning probability, the comprehensive warning probability corresponding to the warning information of the time window is obtained;

When receiving warning information in different time windows, the warning information is sorted according to the comprehensive warning probability corresponding to the warning information in each time window, and the warning information sequence is obtained, and the warning information sequence is presented to the overload management personnel.

In some embodiments, analyzing the historical overload data, and determining the data abnormal interval may specifically include:

Statistically analyzing the historical overload data to obtain the standard deviation and mean of the historical overload data;

The data abnormal interval is determined according to the standard deviation and mean value of the historical overload data.

In some embodiments, determining the abnormal data through the data abnormal interval may specifically include: comparing the data abnormal interval with the historical overload data, and marking the historical overload data that is not in the data abnormal interval, as abnormal data.

In some embodiments, using the stable overload data, determining the equipment overload rate of the electric equipment may specifically include:

Determine the time window in the stable overload data through the preset number of overloads;

Determine the equipment overload rate of the electric equipment according to the time window and the number of overload times.

In some embodiments, determining the reliable warning probability of different sensors in the power equipment through the number of correct warnings of different sensors may specifically include:

Determine the correct number of warnings for different sensors by stabilizing the number of overloads of electrical equipment in the overload data;

Determine the reliable warning probability of different sensors according to the number of overload times and the correct warning times of the different sensors, and the reliable warning probability is determined according to the following formula:

in, Indicates the reliable warning probability of the sensor, /> Indicates the alert state of the sensor, /> Indicates the overload status of electrical equipment, /> Indicates the number of overloads of electrical equipment, /> Indicates the correct alarm times of the sensor when the electrical equipment is overloaded.

In some embodiments, determining the unreliable warning probability of different sensors in the power equipment through the number of false warnings of different sensors may specifically include:

Determine the number of false alarms of different sensors by stabilizing the overload times of electrical equipment in the overload data;

Determine the unreliable warning probability of different sensors according to the preset time window and the number of false warnings of the different sensors, wherein the unreliable warning probability is determined according to the following formula:

in, Indicates the unreliable warning probability of the sensor, /> Indicates the alert state of the sensor, /> Indicates the normal state of the electrical equipment, /> Indicates the number of error alarms of the sensor when the power equipment is normal, /> Indicates a preset time window.

In some embodiments, the warning information is sorted according to the comprehensive warning probability corresponding to the warning information in each time window, and the obtained warning information sequence may specifically include:

The warning information in different time windows is sorted according to the corresponding comprehensive warning probability, and the warning information with the same comprehensive warning probability is sorted according to the time distance, and finally the warning information sequence is obtained.

In a second aspect, the present application provides a protection device for electric equipment, which includes a warning control unit, and the warning control unit includes:

The stable overload data determination module is used to start the overload control of the power equipment protection device, and obtain the historical overload data of the power equipment; analyze the historical overload data, determine the data abnormal interval, determine the abnormal data through the data abnormal interval, and set The abnormal data is removed to obtain stable overload data;

The warning probability determination module is used to determine the equipment overload rate of the electric equipment through the stable overload data, determine the reliable warning probability of different sensors in the electric equipment through the correct warning times of different sensors, and determine the reliable warning probability of different sensors in the power equipment through the wrong warning times of different sensors Unreliable warning probability of different sensors in power equipment;

The comprehensive warning probability determination module is used to obtain the comprehensive warning probability corresponding to the warning information of the time window according to the equipment overload rate, the reliable warning probability and the unreliable warning probability in each time window;

The warning information presentation module is used to sort the warning information according to the comprehensive warning probability corresponding to the warning information of each time window when receiving the warning information of different time windows, obtain the warning information sequence, and present the warning information sequence to the overload manager.

In a third aspect, the present application provides a computer device, the computer device includes a memory and a processor; the memory stores codes, and the processor is configured to acquire the codes and execute the above-mentioned power equipment protection device Control Method.

In a fourth aspect, the present application provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the above-mentioned method for controlling a power equipment protection device is implemented.

The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects:

In a power equipment protection device and its control method provided by the present application, the overload control of the power equipment protection device is started, and the historical overload data of the power equipment is obtained; the historical overload data is analyzed to determine the data abnormal interval, and through the Determine the abnormal data in the data abnormal interval, remove the abnormal data, and obtain stable overload data; determine the equipment overload rate of the electric equipment through the stable overload data, and determine the correct warning times of different sensors in the electric equipment. Reliable warning probability, through the number of false warnings of different sensors, determine the unreliable warning probability of different sensors in the power equipment; in each time window, according to the equipment overload rate, the reliable warning probability and the unreliable warning probability Obtain the comprehensive warning probability corresponding to the warning information of this time window; when receiving the warning information of different time windows, sort the warning information according to the comprehensive warning probability corresponding to the warning information of each time window, obtain the warning information sequence, and put the A sequence of alert messages is presented to overload management personnel.

This application obtains stable overload data by removing abnormal data from the historical overload data of electric power equipment. The stable overload data is more accurate and reliable, and can improve the accuracy of subsequent warning probability calculations of different sensors. When calculating the comprehensive warning probability, equipment overload is taken into account. rate, reliable warning probability and unreliable warning probability, making the warning information more comprehensive and reliable, and finally sorting the comprehensive warning probability of multiple warning information to obtain the warning information sequence, which is convenient for overload management personnel to deal with, thus effectively improving the protection of electronic equipment. The overload warning accuracy of the device.

Description of drawings

Fig. 1 is an exemplary flow chart of a control method of a power equipment protection device according to some embodiments of the present application;

Fig. 2 is a schematic diagram of exemplary hardware and/or software of an alert control unit according to some embodiments of the present application;

Fig. 3 is a schematic structural diagram of a computer device applying a control method for a power device protection device according to some embodiments of the present application.

Detailed ways

The example of this application provides a power equipment protection device and its control method, the core of which is to start the overload control of the power equipment protection device, and obtain the historical overload data of the power equipment; analyze the historical overload data, determine the data abnormal interval, and pass The abnormal data is determined in the data abnormal interval, and the abnormal data is removed to obtain stable overload data; through the stable overload data, the equipment overload rate of the electric equipment is determined, and the correct warning times of different sensors are used to determine the different The reliable warning probability of the sensor, through the number of false warnings of different sensors, determines the unreliable warning probability of different sensors in the power equipment; in each time window, according to the equipment overload rate, the reliable warning probability and the unreliable The warning probability obtains the comprehensive warning probability corresponding to the warning information in the time window; when receiving the warning information in different time windows, sort the warning information according to the comprehensive warning probability corresponding to the warning information in each time window, and obtain the warning information sequence, and put The warning information sequence is presented to overload management personnel, thereby effectively improving the overload warning accuracy rate of the power equipment protection device.

In order to better understand the above-mentioned technical solution, the above-mentioned technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Referring to FIG. 1 , this figure is an exemplary flow chart of a control method of a power equipment protection device according to some embodiments of the present application. The control method 100 of the power equipment protection device mainly includes the following steps:

In step 101, start the overload control of the electric equipment protection device, obtain the historical overload data of the electric equipment, analyze the historical overload data, determine the data abnormal interval, determine the abnormal data through the data abnormal interval, and store the abnormal data Removed to get stable overload data.

The historical overload data is the data that records the overload situation of the electric equipment and the warning situation and specific data of different sensors. In some embodiments, the data source for obtaining the historical overload data of the electric equipment is obtained from the log file in this application , it can also be obtained from systems that record historical data such as equipment monitoring systems, fault alarm systems, and maintenance record systems during actual implementation. There is no limitation here. What needs to be explained is that determining the available data sources will help subsequent data acquisition And integration, according to the determined data source, appropriate methods can be adopted to obtain historical overload data. In this application, the method of file import is adopted. In actual implementation, methods such as API call and database query can also be used. There is no limitation here. The way to obtain historical overload data varies depending on the data source.

In some embodiments, the historical overload data is analyzed, and the abnormal interval of the data can be determined in the following manner, that is, the historical overload data is statistically analyzed to obtain the standard deviation and mean value of the historical overload data, and then according to the historical overload data The standard deviation and mean determine the outlier intervals in the data.

Preferably, in some embodiments, the abnormal data can be determined through the abnormal data interval in the following manner: compare the abnormal data interval with the historical overload data, and mark the historical overload data that is not in the abnormal data interval , as abnormal data, for example, assuming that the data (unit: Celsius) representing the temperature sensor in the historical overload data of electric equipment is: , if the temperature exceeds 40°C, it is considered an outlier. By calculating the mean and standard deviation of the temperature data, assuming that the mean is 28°C and the standard deviation is 10°C, here you can choose to use the mean plus or minus 3 times the standard deviation as range, the upper limit of the range is /> , the lower limit of the interval is , for each of the above-mentioned temperature data points in the historical overload data, it is judged whether it is within the interval. In this embodiment, the ninth data point 100°C exceeds the upper limit interval and is marked as abnormal data. In the application, flags are used to represent abnormal data points, and the flags can also use specific values or labels to represent abnormal data points, which are not limited here.

In some embodiments, for data points marked as abnormal data, the abnormal data needs to be removed to obtain stable overload data. According to the result of the marking, each data point in the historical overload data is traversed, and for The data points can be directly deleted from the historical overload data. In the specific implementation, it can be deleted from the historical overload data or a new data set can be recreated, and the historical overload data of non-abnormal data can be copied to the new data set. Finally, stable overload data is obtained. In this application, by calculating statistical indicators and setting abnormal intervals to detect and remove abnormal data in historical overload data, historical overload data can be made more accurate and reliable, so as to improve the accuracy of subsequent calculations of different sensor warning probabilities. Accuracy.

In step 102, the equipment overload rate of the electric equipment is determined through the stable overload data, the reliable warning probability of different sensors in the electric equipment is determined through the correct warning times of different sensors, and the error warning probability of different sensors in the power equipment is determined through the wrong warning times of different sensors. Unreliable alert probability for different sensors.

In some embodiments, the equipment overload rate of the electric equipment can be determined through the stable overload data in the following manner: determine the time window in the stable overload data through the preset overload times, according to the time window and the overload times Determine the equipment overload rate of electric equipment, and the equipment overload rate of electric equipment is determined according to the following formula: where, /> Indicates the reliable warning probability of the sensor, /> Indicates the alert state of the sensor, /> Indicates the overload status of electrical equipment, /> Indicates the number of overloads of electrical equipment, /> Indicates the correct alarm times of the sensor when the electric equipment is overloaded.

In some embodiments, the unreliable warning probability of different sensors in the power equipment can be determined through the number of false warnings of different sensors, specifically in the following manner: through the number of overloads of the power equipment, the number of false warnings of different sensors is determined, according to the preset The time window and the number of false alerts for different sensors determine the unreliable alert probability for different sensors, where the unreliable alert probability for each sensor is determined according to the following formula: in, Indicates the unreliable warning probability of the sensor, /> Indicates the alert state of the sensor, /> Indicates the normal state of the electrical equipment, /> Indicates the number of false alarms of the sensor when the power equipment is normal, /> Indicates a preset time window. In step 103, in each time window, the comprehensive warning probability corresponding to the warning information of the time window is obtained according to the equipment overload rate, the reliable warning probability and the unreliable warning probability.

Preferably, in some embodiments, in each time window, the stable overload data can be obtained through the warning information in the time window, and the warning information includes the overload times of the electric equipment and all the power equipment in each time window. The alarm situation of the sensor, etc., through the stable overload data to determine the equipment overload rate, reliable warning probability and unreliable warning probability to obtain the comprehensive warning probability. When a time window is determined, the equipment overload rate, Reliable warning probability and unreliable warning probability will not be repeated here, and the comprehensive warning probability is determined according to the following formula:

in, Indicates the comprehensive warning probability, /> Indicates the equipment overload rate, /> Indicates the overload status of the electrical equipment, Indicates the normal state of the electrical equipment, /> Indicates the sensor /> The alert status of the /> Represents the sensor set in the power equipment, /> Indicates the sensor /> The unreliable alert probability of , /> Indicates the normal rate of the equipment. It should be noted that the comprehensive warning probability can comprehensively consider the equipment overload rate and the performance of the warning system to provide more comprehensive and accurate warning information. It is very important to detect and deal with it in a timely manner. Through the comprehensive warning probability, it can help to identify the real overload of power equipment and reduce false alarms, improve the accuracy of overload diagnosis. The calculation of the comprehensive warning probability takes into account the equipment overload rate, reliable warning probability and The unreliable warning probability makes the warning information more comprehensive and reliable, which helps to improve the reliability and safety of the power equipment protection device, thereby effectively improving the overload warning accuracy of the power equipment protection device.

In step 104, when the warning information of different time windows is received, the warning information is sorted according to the comprehensive warning probability corresponding to the warning information of each time window, and the warning information sequence is obtained, and the warning information sequence is presented to the overload management personnel.

In some embodiments, the warning information at different times is sorted according to the comprehensive warning probability corresponding to the warning information at different times. The comprehensive warning probability is sorted, and then the warning information with the same comprehensive warning probability is sorted according to the time distance, and finally the warning information sequence is obtained.

It should be noted that different time windows contain a series of warning information, and each warning information corresponds to a specific time window and device status. For each warning information, its corresponding comprehensive warning probability can be calculated. The comprehensive warning probability is considered According to the equipment overload rate, reliable warning probability and unreliable warning probability, according to the calculated comprehensive warning probability, the warning information is sorted according to the probability from high to low. In this way, the first warning information in the warning information sequence will be the one with the highest The warning information of the comprehensive warning probability, and the last warning information will be the warning information with the lowest comprehensive warning probability. If the comprehensive warning probability is the same, it will be sorted according to the time distance. The priority is higher if it is closer to the current time. The warning information is sorted according to the above rules, and the sorted warning information sequence is presented to the overload management personnel. The overload management personnel can judge the priority of the fault according to the order of the warning information in the warning information sequence. Usually, the overload management personnel will first The alert message with the highest priority is processed because it represents the most serious and urgent failure condition.

This application uses the historical overload data of power equipment to remove abnormal data processing, so that the historical overload data is more accurate and reliable, thereby improving the accuracy of subsequent warning probability calculations for different sensors. When calculating the comprehensive warning probability, the equipment overload rate and reliability are taken into account The warning probability and unreliable warning probability make the warning information more comprehensive and reliable. Finally, the comprehensive warning probability of multiple warning information is sorted to obtain the warning information sequence, which is convenient for overload management personnel to deal with, thereby effectively improving the overload warning of power equipment protection devices. Accuracy.

In addition, another aspect of the present application, in some embodiments, the present application provides a power equipment protection device, the system includes a warning control unit, refer to Figure 2, which is a warning according to some embodiments of the present application A schematic diagram of exemplary hardware and/or software of the control unit. The warning control unit 200 includes: a stable overload data determination module 201, a warning probability determination module 202, a comprehensive warning probability determination module 203, and a warning information presentation module 204, which are respectively described as follows:

The stable overload data determination module 201, in this application, the stable overload data determination module 201 is mainly used to start the overload control of the power equipment protection device, obtain the historical overload data of the power equipment; analyze the historical overload data, determine the data abnormal interval, Determining abnormal data through the data abnormal interval, removing the abnormal data, and obtaining stable overload data;

The warning probability determination module 202, in this application, the warning probability determination module 202 is mainly used to determine the equipment overload rate of the electric equipment through the stable overload data, and determine the reliable warning probability of different sensors in the electric equipment through the correct warning times of different sensors , determine the unreliable warning probability of different sensors in power equipment through the number of false warnings of different sensors;

The comprehensive warning probability determination module 203, the comprehensive warning probability determination module 203 in this application is mainly used in each time window to obtain the time window according to the equipment overload rate, the reliable warning probability and the unreliable warning probability The comprehensive warning probability corresponding to the warning information;

The warning information presentation module 204, the warning information presentation module 204 in this application is mainly used to sort the warning information according to the comprehensive warning probability corresponding to the warning information in each time window when receiving warning information in different time windows, and obtain the warning information sequence , presenting the warning information sequence to the overload manager.

In some embodiments, the present application also provides a computer device, the computer device includes a memory and a processor, the memory stores codes, and the processor is configured to obtain the codes and execute the above-mentioned power device The control method of the protective device.

In some embodiments, refer to FIG. 3 , which is a schematic structural diagram of a computer device according to a method for controlling a power equipment protection device provided in an embodiment of the present application. The control method of the above-mentioned power equipment protection device in the above-mentioned embodiment can be realized by the computer equipment shown in FIG.

The processor 301 may be a general-purpose central processing unit (central processing unit, CPU), a specific application integrated circuit (application specific integrated circuit, ASIC), or one or more control methods for controlling the power equipment protection device in this application implement. Communication bus 302 may include a path for communicating information between the components described above.

The memory 303 may be a read-only memory (read only memory, ROM) or other types of static storage devices capable of storing static information and instructions, a random access memory (random access memory, RAM) or other types of memory devices capable of storing information and instructions Dynamic storage devices can also be electrically erasable programmable read only memory (electrically erasable programmable read only memory, EEPROM), read-only disc (compact disc readonly memory, CDROM) or other optical disc storage, optical disc storage (including compact disc, laser disc , compact disc, digital versatile disc, blu-ray disc, etc.), magnetic disk or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited to this. The memory 303 may exist independently, and is connected to the processor 301 through the communication bus 302 . The memory 303 can also be integrated with the processor 301 .

Wherein, the memory 303 is used to store program codes for executing the solutions of the present application, and the execution is controlled by the processor 301 . The processor 301 is used to execute program codes stored in the memory 303 . One or more software modules may be included in the program code. The control method of the power equipment protection device in the above embodiments may be implemented by one or more software modules in the program codes in the processor 301 and the memory 303 .

The communication interface 304 uses any device such as a transceiver to communicate with other devices or communication networks, such as Ethernet, radio access network (radio access network, RAN), wireless local area network (wireless local area networks, WLAN) and so on.

In a specific implementation, as an embodiment, the computer device may include multiple processors, and each of these processors may be a single-core (single CPU) processor or a multi-core (multi-CPU) processor . A processor herein may refer to one or more devices, circuits, and/or processing cores for processing data (eg, computer program instructions).

The above computer equipment may be a general computer equipment or a special computer equipment. In a specific implementation, the computer device may be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. The embodiment of the present application does not limit the type of computer equipment.

Those skilled in the art should understand that the embodiments of the present invention may be provided as methods, systems, or computer program products. Accordingly, the present invention can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

For example, in some embodiments, the present 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 a processor, the control of the above-mentioned power equipment protection device is realized. method.

The present invention is described according to the flowcharts and/or block diagrams of the methods, devices (systems), and computer program products of the embodiments of the present invention. It should be understood that each procedure and/or block in the flowchart and/or block diagram, and combinations of procedures and/or blocks in the flowchart and/or block diagram can be realized by computer program instructions. These computer program instructions may be provided to a general purpose computer, special purpose computer, embedded processor, or processor of other programmable data processing equipment to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing equipment produce a Means for realizing the functions specified in one or more steps of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to operate in a specific manner, such that the instructions stored in the computer-readable memory produce an article of manufacture comprising instruction means, the instructions The device realizes the function specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions can also be loaded onto a computer or other programmable data processing device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby The instructions provide steps for implementing the functions specified in the flow chart flow or flows and/or block diagram block or blocks.

While preferred embodiments of the invention have been described, additional changes and modifications to these embodiments can be made by those skilled in the art once the basic inventive concept is appreciated. Therefore, it is intended that the appended claims be construed to cover the preferred embodiment as well as all changes and modifications which fall within the scope of the invention.

Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the present invention

The spirit and scope of the invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention also intends to include these modifications and variations.

Claims (10)

1. A control method for a power equipment protection device, comprising the steps of: Start the overload control of the power equipment protection device, and obtain the historical overload data of the power equipment; Analyzing the historical overload data, determining a data abnormal interval, determining abnormal data through the data abnormal interval, removing the abnormal data, and obtaining stable overload data; Through the stable overload data, the equipment overload rate of the electric equipment can be determined, the reliable warning probability of different sensors in the electric equipment can be determined through the correct warning times of different sensors, and the false alarm probability of different sensors in the power equipment can be determined through the wrong warning times of different sensors. Reliable warning probability; In each time window, according to the equipment overload rate, the reliable warning probability and the unreliable warning probability, the comprehensive warning probability corresponding to the warning information of the time window is obtained; When receiving warning information in different time windows, the warning information is sorted according to the comprehensive warning probability corresponding to the warning information in each time window, and the warning information sequence is obtained, and the warning information sequence is presented to the overload management personnel. 2. The method according to claim 1, wherein analyzing the historical overload data and determining the data abnormal interval specifically includes: Statistically analyzing the historical overload data to obtain the standard deviation and mean of the historical overload data; The data abnormal interval is determined according to the standard deviation and mean value of the historical overload data. 3. The method according to claim 1, wherein determining the abnormal data through the data abnormal interval specifically comprises: comparing the data abnormal interval with the historical overload data, and determining the abnormal data that is not in the data abnormal interval Mark the historical overload data as abnormal data. 4. The method according to claim 1, wherein determining the equipment overload rate of the electric equipment through the stable overload data specifically comprises: Determine the time window in the stable overload data through the preset number of overloads; Determine the equipment overload rate of the electric equipment according to the time window and the number of overload times. 5. The method according to claim 1, characterized in that, determining the reliable warning probability of different sensors in the power equipment through the correct warning times of different sensors specifically comprises: Determine the correct number of warnings for different sensors by stabilizing the number of overloads of electrical equipment in the overload data; Determine the reliable warning probability of different sensors according to the number of overload times and the correct warning times of the different sensors, and the reliable warning probability is determined according to the following formula: where, /> Indicates the reliable warning probability of the sensor, /> Indicates the alert state of the sensor, /> Indicates the overload status of electrical equipment, /> Indicates the number of overloads of electrical equipment, /> Indicates the correct alarm times of the sensor when the electric equipment is overloaded. 6. The method according to claim 1, characterized in that, determining the unreliable warning probability of different sensors in the power equipment through the number of false warnings of different sensors specifically comprises: Determine the number of false alarms of different sensors by stabilizing the overload times of electrical equipment in the overload data; Determine the unreliable warning probability of different sensors according to the preset time window and the number of false warnings of the different sensors, wherein the unreliable warning probability is determined according to the following formula: where, /> Indicates the unreliable warning probability of the sensor, /> Indicates the alert state of the sensor, /> Indicates the normal state of the electrical equipment, /> Indicates the number of error alarms of the sensor when the power equipment is normal, /> Indicates a preset time window. 7. The method according to claim 1, wherein the warning information is sorted according to the comprehensive warning probability corresponding to the warning information in each time window, and the obtained warning information sequence specifically includes: The warning information in different time windows is sorted according to the corresponding comprehensive warning probability, and the warning information with the same comprehensive warning probability is sorted according to the time distance, and finally the warning information sequence is obtained. 8. A protection device for electric power equipment, characterized in that it includes a warning control unit, and the warning control unit includes: The stable overload data determination module is used to start the overload control of the power equipment protection device, and obtain the historical overload data of the power equipment; analyze the historical overload data, determine the data abnormal interval, determine the abnormal data through the data abnormal interval, and set The abnormal data is removed to obtain stable overload data; The warning probability determination module is used to determine the equipment overload rate of the electric equipment through the stable overload data, determine the reliable warning probability of different sensors in the electric equipment through the correct warning times of different sensors, and determine the reliable warning probability of different sensors in the power equipment through the wrong warning times of different sensors Unreliable warning probability of different sensors in power equipment; The comprehensive warning probability determination module is used to obtain the comprehensive warning probability corresponding to the warning information of the time window according to the equipment overload rate, the reliable warning probability and the unreliable warning probability in each time window; The warning information presentation module is used to sort the warning information according to the comprehensive warning probability corresponding to the warning information of each time window when receiving the warning information of different time windows, obtain the warning information sequence, and present the warning information sequence to the overload manager. 9. A computer device, characterized in that the computer device comprises a memory and a processor, the memory stores codes, the processor is configured to obtain the codes, and execute any one of claims 1 to 7. The control method of the power equipment protection device described in the item. 10. A computer-readable storage medium, the computer-readable storage medium stores a computer program, characterized in that, when the computer program is executed by a processor, the electric device according to any one of claims 1 to 7 is realized The control method of the protective device.