Power equipment early warning monitoring system and method

Abstract

The invention provides a power equipment early warning monitoring system and method, and relates to the field of power equipment detection, and the system comprises a monitoring equipment subsystem, a monitoring gateway subsystem and an early warning server subsystem. The monitoring equipment subsystem comprises a plurality of power monitoring terminals, and each terminal is connected with at least one power equipment. The monitoring gateway subsystem is in communication connection with each terminal and is used for initializing identification code matching, establishing an equipment characteristic data set, receiving a monitoring instruction set and obtaining historical and real-time operation characteristic parameters according to instruction execution. And the early warning server subsystem communicates with the monitoring gateway subsystem, stores the equipment health degree double-baseline model and the dynamic early warning rule base, issues the initial early warning rule base after the monitoring gateway is initialized, generates an equipment health degree evaluation sequence and an early warning result according to the real-time monitoring sequence, and updates the dynamic early warning rule base. According to the invention, monitoring in the dynamic operation process of power equipment operation and instruction receiving is realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of power equipment monitoring, and particularly relates to a power equipment early warning monitoring system and method. Background Art

[0002] With the continuous development and increasing scale of the power system, the stable operation of power equipment is crucial for ensuring the reliability and safety of power supply. During the long-term operation of power equipment, due to various factors such as electrical stress, thermal stress, mechanical stress, and environmental factors, the performance of the equipment may gradually deteriorate or even fail, which may further lead to power outages and cause huge losses to the social economy.

[0003] Traditional power equipment monitoring methods mainly rely on regular inspections and preventive tests. Regular inspections often have a certain lag and it is difficult to detect potential problems in the operation of equipment in a timely manner; while preventive tests usually require power outages, which not only affect the continuity of power supply, but also the test results may be interfered by various factors and cannot accurately reflect the real-time health status of the equipment.

[0004] In addition, there are a wide variety of power equipment and complex operating environments, and the fault modes and characteristics of different equipment are also different, which makes it face many challenges to establish a comprehensive and accurate equipment fault early warning model. Therefore, there is an urgent need for a system and method that can monitor the operation status of power equipment in real time and accurately, and early warn of potential faults, so as to improve the reliability and stability of the power system and reduce the operation and maintenance costs. Summary of the Invention

[0005] Therefore, the present invention provides a power equipment early warning monitoring system and method to realize the monitoring and early warning of various parameters during the operation of power equipment.

[0006] In the first aspect of the present invention, a power equipment early warning monitoring system is provided, including:

[0007] A monitoring equipment subsystem, including a plurality of power monitoring terminals, each of the power monitoring terminals is configured with an equipment identification code and a verification identification code, and at least one power equipment is accessed by one of the power monitoring terminals;

[0008] A monitoring gateway subsystem, communicatively connected to each of the power monitoring terminals,

[0009] and is configured to initialize the matching of the equipment identification code and the verification identification code, and establish an equipment feature data set;

[0010] and is configured to receive a monitoring instruction set, the monitoring instruction set including an equipment selection instruction and a monitoring mode instruction;

[0011] And when configured to receive a monitoring instruction set, execute the following steps:

[0012] Generate a device feature call request according to the device selection instruction,

[0013] Match the historical operation feature parameters within the corresponding first time window from the device feature dataset;

[0014] Suspend the monitoring mode instruction, obtain the operation feature parameters from the power monitoring terminal within the first time window, and obtain a reference monitoring sequence;

[0015] Execute the monitoring mode instruction after the second time window and generate a sequence of real-time monitoring data;

[0016] An early warning server subsystem, communicatively connected to the monitoring gateway subsystem,

[0017] And it stores a device health double baseline model and a dynamic early warning rule library constructed based on a neural network model,

[0018] And is configured to issue an initial early warning rule library after the initialization of the monitoring gateway;

[0019] Is configured to generate a device health evaluation sequence and an early warning result after receiving the real-time monitoring sequence, and update the dynamic early warning rule library according to the evaluation sequence.

[0020] As a further preferred method, the power monitoring terminal includes at least one of a temperature sensor, a current transformer, and a partial discharge detector.

[0021] As a further preferred method, the power monitoring terminal further includes a cable joint monitoring unit, which includes a distributed cable temperature sensing unit, a joint deformation monitoring unit, and an ambient humidity monitoring unit;

[0022] If it is simultaneously detected that the temperature rise rate is higher than a preset value, the deformation rate exceeds the preset value, and the humidity is lower than the preset value, trigger a joint aging warning.

[0023] As a further preferred method, when the early warning server subsystem responds to an access request from the monitoring gateway:

[0024] Verify the digital certificate of the gateway and the device certificate chain of the power monitoring terminal;

[0025] After the certificate chain verification passes, distribute a dynamic encryption key to the monitoring gateway, and the key is used to decrypt the encrypted monitoring data uploaded by the power monitoring terminal.

[0026] The second aspect of the present invention provides a power equipment monitoring and early warning method, including the following steps:

[0027] S1. Construct a device feature training set, including time series data and feature marking data.

[0028] The time series data is historical operation parameters stored based on time series as the benchmark unit.

[0029] The feature marking data is historical operation parameters stored based on device failure events as the benchmark unit and stored before and after the specified time window before and after the occurrence of the device failure events.

[0030] S2. Extract the time domain features of the time series data and the feature marking data respectively.

[0031] S3. Generate a device health double baseline model according to the time domain features and parameter fluctuation thresholds at the time of device failure, and the time domain skewness threshold and time domain kurtosis threshold within the specified time window before and after device failure.

[0032] S4. Under the preset workload and within the preset time window;

[0033] Obtain the first baseline regarding the skewness change and parameter fluctuation threshold before device failure.

[0034] Obtain the second baseline regarding the kurtosis change trend and kurtosis change type at the time of device failure.

[0035] S5. Obtain the real-time monitoring data of the monitored power device corresponding to the device feature training set.

[0036] When the real-time monitoring data deviates from the first baseline, generate the first warning data.

[0037] Calculate the time delay for the time domain features of the real-time monitoring data to reach the first baseline under the current data deviation degree, and generate the second warning data.

[0038] If the skewness change has the same data as that within the specified time window before the feature marking data corresponding to the second baseline in the first baseline, generate the second warning data.

[0039] If the real-time monitoring data reaches the first baseline after the second warning data is issued and its kurtosis change trend and kurtosis change threshold match the second baseline, generate the third warning data.

[0040] As a further preferred method, in S5, when obtaining the real-time monitoring data of the monitored power device corresponding to the device feature training set, the following steps are further included:

[0041] Generate a device feature call request according to the device selection instruction.

[0042] Match the historical operation feature parameters within the corresponding first time window from the device feature dataset.

[0043] Suspend the monitoring mode instruction, obtain the operating characteristic parameters monitored by the power monitoring terminal within the first time window, and obtain a reference monitoring sequence;

[0044] Execute the monitoring mode instruction after the second time window and generate a sequence of real-time monitoring data;

[0045] Compare the reference monitoring sequence with the real-time monitoring data obtained within the second time window, obtain the characteristic difference between the time domain characteristics of the two, and use the characteristic difference as the extended interval of the first baseline.

[0046] In a third aspect of the present invention, there is provided an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it is adapted to implement the method of the second aspect of the present invention.

[0047] In a fourth aspect of the present invention, there is provided a storage medium, on which a computer program is stored. The computer program is characterized in that when it is executed by a processor, it is adapted to the method of the second aspect of the present invention.

[0048] The above technical solutions of the present invention have the following advantages compared with the prior art:

[0049] Real-time and accurate monitoring: By setting multiple power monitoring terminals configured with device identification codes and verification identification codes, real-time data collection of power equipment can be carried out. The monitoring gateway subsystem can flexibly obtain the operating characteristic parameters within different time windows according to the monitoring instruction set, generate a reference monitoring sequence and a real-time monitoring data sequence, providing a rich data basis for accurately evaluating the device status. At the same time, the early warning server subsystem can accurately analyze the real-time monitoring sequence by using the device health double baseline model and the dynamic early warning rule library based on the neural network model, generate a device health evaluation sequence and an early warning result, and timely discover potential problems of the device.

[0050] Multi-dimensional monitoring: The power monitoring terminal includes various monitoring devices such as temperature sensors, current transformers, and partial discharge detectors, and can obtain the operating parameters of power equipment from multiple dimensions, comprehensively reflecting the operating status of the equipment. In addition, the cable joint monitoring unit integrates a distributed cable temperature sensing unit, a joint deformation monitoring unit, and an environmental humidity monitoring unit. Through multi-parameter joint judgment, it can more accurately trigger the joint aging warning and effectively prevent cable joint failures.

[0051] High security: When the early warning server subsystem responds to the access request of the monitoring gateway, it will verify the digital certificate of the gateway and the device certificate chain of the power monitoring terminal to ensure the legality and security of the access device. By distributing dynamic encryption keys to the monitoring gateway to decrypt the encrypted monitoring data uploaded by the power monitoring terminal, the security during data transmission is further guaranteed, preventing data leakage or tampering.

[0052] Adaptive early warning: The early warning server subsystem can update the dynamic early warning rule library according to the device health evaluation sequence, enabling it to continuously optimize the early warning rules with the change of the device operation state and the accumulation of new data, improving the accuracy and adaptability of early warning. At the same time, the power equipment monitoring and early warning method generates a double baseline model of device health by constructing a device feature training set and combining time-domain feature analysis, and generates various early warning data according to the deviation of real-time monitoring data from the double baseline, realizing multi-stage and refined early warning of device faults, providing more sufficient time for maintenance personnel to take corresponding measures and reducing the possibility of faults.

[0053] Effectively guide maintenance: The early warning results provided by the system and method can help maintenance personnel understand the health status of the equipment in advance, arrange the maintenance plan targeted, change passive maintenance to active maintenance, avoid unnecessary power outages for maintenance, improve the availability of power equipment, reduce maintenance costs, and ensure the reliable operation of the power system. Brief description of the drawings

[0054] Figure 1 It is the structural block diagram of the system provided by Embodiment 1 of the present invention.

[0055] Figure 2 It is the structural block diagram of the electronic device provided by Embodiment 2 of the present invention. Detailed implementation manners

[0056] In order to be able to understand the features and technical content of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure will be elaborated in detail below with reference to the accompanying drawings. The accompanying drawings are only for reference and explanation, and are not used to limit the embodiments of the present disclosure. In the following technical description, for the sake of explanation, multiple details are provided to provide a full understanding of the disclosed embodiments. However, one or more embodiments can still be implemented without these details. In other cases, well-known structures and devices can be shown in a simplified manner.

[0057] Embodiment 1

[0058] The first aspect of the embodiments of the present disclosure provides a power equipment early warning and monitoring system, as Figure 1 shown, including a monitoring device subsystem, a monitoring gateway subsystem, and a monitoring server subsystem.

[0059] The monitoring device subsystem includes multiple power monitoring terminals. Each of the power monitoring terminals is configured with a device identification code and a verification identification code. One of the power monitoring terminals is connected to at least one power device.

[0060] As a further preferred embodiment of the present disclosure, the power monitoring terminal includes at least one of a temperature sensor, a current transformer, and a partial discharge monitor.

[0061] As a further preferred embodiment of the present disclosure, the power monitoring terminal further includes a cable joint monitoring unit, which includes a distributed cable temperature sensing unit, a joint deformation monitoring unit, and an ambient temperature monitoring unit. In the embodiment of the present disclosure, the cable joint monitoring unit is arranged at the connection between the power device and the cable. If, within a specified time window during the real-time monitoring process, it is simultaneously detected that the temperature rise rate in the set area is higher than the preset value, the deformation rate exceeds the preset value, and the humidity is lower than the preset value, a joint aging warning is triggered. It should be noted that the preset values mentioned in the cable joint monitoring unit are all empirical setting thresholds when the monitored cable of this type ages.

[0062] In the embodiment of the present disclosure, the monitoring gateway subsystem is communicatively connected to each of the power monitoring terminals.

[0063] And is configured to initialize the matching of the device identification code and the verification identification code, and establish a device feature data set.

[0064] And is configured to receive a monitoring instruction set, and the monitoring instruction set includes a device selection instruction and a monitoring mode instruction.

[0065] And when receiving the monitoring instruction set, it is configured to perform the following steps:

[0066] Generate a device feature call request according to the device selection instruction.

[0067] Match the corresponding historical operation feature parameters within the first time window from the device feature data set.

[0068] Suspend the monitoring mode instruction, and obtain the operation feature parameters from the power monitoring terminal within the first time window to obtain a reference monitoring sequence.

[0069] Execute the monitoring mode instruction after the second time window and generate a sequence of real-time monitoring data.

[0070] The warning server subsystem is communicatively connected to the monitoring gateway subsystem.

[0071] And it stores a device health double baseline model and a dynamic warning rule library constructed based on a neural network model.

[0072] and is configured to issue an initial warning rule library after the monitoring gateway is initialized;

[0073] is configured to generate a device health evaluation sequence and a warning result after receiving a real-time monitoring sequence, and update the dynamic warning rule library according to the evaluation sequence.

[0074] As a preferred security guarantee method in an embodiment of the present disclosure, when the warning server subsystem responds to an access request from a monitoring gateway:

[0075] Read the device identification code and verification identification code of the power monitoring terminal, verify the digital certificate of the gateway and the device certificate chain of the power monitoring terminal. At the same time, the device identification code is also used for information verification and storage with the power equipment to which it is connected;

[0076] After the certificate chain verification passes, distribute a dynamic encryption key to the monitoring gateway, and the key is used to decrypt the encrypted monitoring data uploaded by the power monitoring terminal.

[0077] In a second aspect of the embodiments of the present disclosure, a power equipment monitoring and warning method is provided, including the following steps:

[0078] S1. Construct a device feature training set, including time series data and feature marker data,

[0079] The time series data is historical operation parameters stored based on a time series as a reference unit,

[0080] The feature marker data is historical operation parameters stored based on a device failure event as a reference unit and stored before and after a specified time window before and after the occurrence of the device failure event;

[0081] S2. Extract the time domain features of the time series data and the feature marker data respectively;

[0082] S3. Generate a device health double baseline model according to the time domain features and parameter fluctuation thresholds during device failure and the time domain skewness threshold and time domain kurtosis threshold within a specified time window before and after device failure;

[0083] S4. Under a preset workload and within a preset time window;

[0084] Obtain a first baseline regarding the skewness change and parameter fluctuation threshold before device failure;

[0085] Obtain a second baseline regarding the kurtosis change trend and kurtosis change type during device failure;

[0086] S5. Obtain the real-time monitoring data of the monitored power equipment corresponding to the device feature training set;

[0087] When the skewness change of the real-time monitoring data and the parameter fluctuation threshold reach a predetermined ratio of the first baseline, generate first warning data.

[0088] Calculate the time delay for the time-domain characteristics of the real-time monitoring data to reach the first baseline under the current skewness change and parameter fluctuation threshold, and generate second warning data.

[0089] If the skewness change is the same as the data within a specified time window before the characteristic marker data corresponding to the second baseline exists in the first baseline, generate third warning data.

[0090] If the real-time monitoring data reaches the first baseline after the second warning data or the third warning data is issued and its kurtosis change trend and kurtosis change threshold match the second baseline, generate fourth warning data.

[0091] As a preferred method, when obtaining the real-time monitoring data of the monitored power equipment in the device feature training set, the following steps are further included:

[0092] Generate a device feature call request according to the device selection instruction.

[0093] Match the historical operation characteristic parameters within the corresponding first time window from the device feature dataset.

[0094] Suspend the monitoring mode instruction, and obtain the operation characteristic parameters monitored by the power monitoring terminal within the first time window to obtain a reference monitoring sequence.

[0095] Execute the monitoring mode instruction after the second time window and generate a sequence of real-time monitoring data.

[0096] Compare the reference monitoring sequence with the real-time monitoring data obtained within the second time window to obtain the characteristic difference between the time-domain characteristics of the two, and use the characteristic difference as the extended interval of the first baseline. In the embodiments of the present disclosure, the setting of the extended interval is to reduce the interference of signals and sampling data caused by sudden changes in the monitoring mode after accessing the power monitoring terminal. Therefore, before executing the monitoring mode instruction, suspend the instruction and normally execute the operation order within the specified first time window to make the power equipment perform steady-state operation and use the monitoring data in the steady state as the reference monitoring sequence.

[0097] The embodiments of the present disclosure will further elaborate on the method configured and executed by the warning server subsystem. In the embodiments of the present disclosure, the initial warning rule library is that when the skewness change of the real-time monitoring data and the parameter fluctuation threshold reach a predetermined ratio of the first baseline, generate first warning data.

[0098] Calculate the time delay for the time-domain characteristics of the real-time monitoring data to reach the first baseline under the current skewness change and parameter fluctuation threshold, and generate second warning data.

[0099] If the skewness change is the same as the data within a specified time window before the characteristic marker data corresponding to the second baseline exists in the first baseline, generate third warning data; when generating the second warning data or the third warning data, initiate a maintenance request and write the delay to the first baseline and the delay to the second baseline into the maintenance request;

[0100] If the real-time monitoring data reaches the first baseline after the second warning data or the third warning data is sent, and its kurtosis change trend and kurtosis change threshold match the second baseline, generate fourth warning data. When generating the fourth warning data, determine that a fault has occurred and disconnect the power equipment.

[0101] After being configured to receive the real-time monitoring sequence, generate an equipment health evaluation sequence and a warning result. The equipment health evaluation sequence is set as multiple groups of reference baselines set according to the first baseline and the second baseline. When the real-time monitoring data deviates from the first baseline and reaches any reference baseline within the specified time window in the real-time monitoring sequence formed by the real-time monitoring data, generate the state at this time. It should be noted that each reference baseline is set as a data fitting baseline formed by the first baseline under the skewness change and parameter fluctuation threshold of a specified ratio, so as to obtain the health evaluation sequence in the continuous working state.

[0102] Update the dynamic warning rule library according to the evaluation sequence. Specifically, in S5 of the embodiment of the present disclosure, the warning rule library is that when the skewness change and parameter fluctuation threshold of the real-time monitoring data reach a predetermined ratio of the first baseline, generate the first warning data, and calculate the delay of the time domain characteristics of the real-time monitoring data reaching the first baseline under the current skewness change and parameter fluctuation threshold, and generate the second warning data. The generation of the second warning data is judged according to the delay of the current time domain characteristics reaching the first baseline within the current sampling time window, match the real-time monitoring data of the current time window in the equipment characteristic training set, obtain the most probable event of the health change in the next time window, and gradually match to reach the first delay. At this time, generate the second probability warning data and send it together with the second warning data. It should be noted that obtaining the most probable event of the health change in the next time window is the sample set with the highest probability of occurrence among multiple samples in the already matched real-time monitoring data. The sample set is set with a health threshold range obtained according to the reference baseline to avoid accidental events.

[0103] The embodiments of the present disclosure further achieve real-time and accurate monitoring: By setting multiple power monitoring terminals configured with device identification codes and verification identification codes, real-time data collection of power equipment can be carried out. The monitoring gateway subsystem can flexibly obtain the operation characteristic parameters within different time windows according to the monitoring instruction set, generate a reference monitoring sequence and a real-time monitoring data sequence, providing a rich data basis for accurately evaluating the device status. At the same time, the early warning server subsystem can accurately analyze the real-time monitoring sequence by using the device health double baseline model and the dynamic early warning rule library constructed based on the neural network model, generate a device health evaluation sequence and an early warning result, and timely discover potential problems of the device.

[0104] Multi-dimensional monitoring: The power monitoring terminal includes various monitoring devices such as temperature sensors, current transformers, and partial discharge detectors, and can obtain the operation parameters of power equipment from multiple dimensions, comprehensively reflecting the operation status of the equipment. In addition, the cable joint monitoring unit integrates a distributed cable temperature sensing unit, a joint deformation monitoring unit, and an environmental humidity monitoring unit. Through joint judgment of multiple parameters, it can more accurately trigger the joint aging warning and effectively prevent cable joint failures.

[0105] High security: When the early warning server subsystem responds to the access request of the monitoring gateway, it will verify the digital certificate of the gateway and the device certificate chain of the power monitoring terminal to ensure the legality and security of the access device. By distributing dynamic encryption keys to the monitoring gateway to decrypt the encrypted monitoring data uploaded by the power monitoring terminal, the security during data transmission is further guaranteed, preventing data leakage or tampering.

[0106] Adaptive early warning: The early warning server subsystem can update the dynamic early warning rule library according to the device health evaluation sequence, enabling it to continuously optimize the early warning rules with the change of the device operation status and the accumulation of new data, improving the accuracy and adaptability of the early warning. At the same time, the power equipment monitoring and early warning method generates a device health double baseline model by constructing a device feature training set and combining time-domain feature analysis, and generates various early warning data according to the deviation of the real-time monitoring data from the double baseline, realizing multi-stage and refined early warning of device failures, providing more sufficient time for maintenance personnel to take corresponding measures and reducing the possibility of failures.

[0107] Effectively guide operation and maintenance: The early warning results provided by the system and method can help maintenance personnel understand the health status of the equipment in advance, arrange the operation and maintenance plan targeted, change passive maintenance to active maintenance, avoid unnecessary power outages for maintenance, improve the availability of power equipment, reduce operation and maintenance costs, and ensure the reliable operation of the power system.

[0108] Embodiment 2

[0109] Combined with Figure 2As shown, an embodiment of the present disclosure provides an electronic device, including a processor 30 and a memory 31.

[0110] Optionally, the device may further include a communication interface 32 and a bus 33. Among them, the processor 30, the communication interface 32, and the memory 31 can complete mutual communication through the bus 33. The communication interface 32 can be used for information transmission. The processor 30 can call the logical instructions in the memory 31 to execute the patent value analysis system based on big data technology in the above embodiment.

[0111] An embodiment of the present disclosure provides a storage medium storing computer-executable instructions, and the computer-executable instructions are set to execute the method in the first embodiment of the present disclosure.

[0112] The above storage medium may be a transient computer-readable storage medium or a non-transient computer-readable storage medium. The non-transient storage medium includes: various media that can store program codes such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs, and may also be a transient storage medium.

[0113] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure so that those skilled in the art can practice them. Other embodiments may include structural, logical, electrical, process, and other changes. The embodiments merely represent possible variations. Unless explicitly required, the individual components and functions are optional, and the order of operations may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the terms used in this application are only for describing the embodiments and are not used to limit the claims. As used in the description of the embodiments and the claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to also include the plural forms. Similarly, as used in this application, the term "and / or" refers to any and all possible combinations including one or more of the associated listed items. Additionally, when used in this application, the term "comprise" and its variants "comprises" and / or "comprising" etc. mean the presence of the stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or groups thereof. Without further limitation, an element defined by the statement "comprising one..." does not exclude the presence of additional identical elements in the process, method, or apparatus comprising the element. In this document, each embodiment may focus on the differences from other embodiments, and the same or similar parts among the embodiments may be referred to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method parts disclosed in the embodiments, the relevant parts may refer to the description of the method parts.

Claims

1. The power equipment early warning monitoring system is characterized by: include: The monitoring device subsystem includes a plurality of power monitoring terminals, each of which is configured with a device identification code and a verification identification code, and one of the power monitoring terminals is connected to at least one power device; A monitoring gateway subsystem is communicatively connected to each of the power monitoring terminals. and is configured to initialize the matching of the device identification code and the verification identification code to establish a device feature data set; and is configured to receive a monitoring instruction set, the monitoring instruction set including a device selection instruction and a monitoring mode instruction; And when it is configured to receive a monitoring instruction set, it executes the following steps: Generate a device feature call request based on the device selection instruction, Matching the historical operation characteristic parameters within the corresponding first time window from the equipment characteristic data set; Suspend the monitoring mode instruction, obtain the operation characteristic parameters from the power monitoring terminal within the first time window, and obtain the reference monitoring sequence; executing the monitoring mode instructions after the second time window and generating a sequence of real-time monitoring data; The early warning server subsystem is communicatively connected to the monitoring gateway subsystem. It also stores a dual baseline model of equipment health based on a neural network model and a dynamic warning rule library. and is configured to issue an initial warning rule base after the monitoring gateway is initialized; It is configured to generate an equipment health evaluation sequence and early warning results after receiving a real-time monitoring sequence, and update a dynamic early warning rule base according to the evaluation sequence.

2. The electric power equipment early warning monitoring system according to claim 1 is characterized in that: The power monitoring terminal includes at least one of a temperature sensor, a current transformer, and a partial discharge detector.

3. The electric power equipment early warning monitoring system according to claim 2 is characterized in that: The power monitoring terminal also includes a cable joint monitoring unit, which includes a distributed cable temperature sensing unit, a joint deformation monitoring unit and an environmental humidity monitoring unit; If it is detected at the same time that the temperature rise rate is higher than the preset value, the deformation rate exceeds the preset value and the humidity is lower than the preset value, the joint aging warning is triggered.

4. The electric power equipment early warning monitoring system according to claim 1, characterized in that: When the early warning server subsystem responds to the access request of the monitoring gateway: Verify the digital certificate of the gateway and the device certificate chain of the power monitoring terminal; When the certificate chain is verified, a dynamic encryption key is distributed to the monitoring gateway, and the key is used to decrypt the encrypted monitoring data uploaded by the power monitoring terminal.

5. The electric power equipment early warning monitoring method is characterized in that: The steps include: S1. Build a device feature training set, including time series data and feature labeling data. The time series data is the historical operating parameters stored with the time series as the reference unit. The characteristic marking data is stored with the equipment failure event as the reference unit, and is a historical operating parameter stored around a specified time window before and after the occurrence of the equipment failure event; S2, respectively extracting the time domain features of the time series data and the feature mark data; S3, generating a dual baseline model of equipment health according to the time domain characteristics and parameter fluctuation threshold of the equipment failure, and the time domain skewness threshold and time domain kurtosis threshold in a specified time window before and after the equipment failure; S4, under a preset workload and within a preset time window; Obtaining a first baseline of skewness changes and parameter fluctuation thresholds before equipment failure; Obtaining a second baseline regarding the kurtosis change trend and kurtosis change type when the equipment fails; S5, obtaining real-time monitoring data of the monitored power equipment corresponding to the equipment feature training set; When the skewness change and parameter fluctuation threshold of the real-time monitoring data reach a predetermined ratio of the first baseline, first warning data is generated. Calculate the time delay for the time domain characteristics of the real-time monitoring data to reach the first baseline under the current skewness change and parameter fluctuation threshold, and generate second warning data, If the skewness change has data in the first baseline that is the same as data in a specified time window before the feature marker data corresponding to the second baseline, generating third warning data; If the real-time monitoring data reaches the first baseline after the second warning data or the third warning data is issued and its kurtosis change trend and kurtosis change threshold match the second baseline, the fourth warning data is generated.

6. The electric power equipment early warning monitoring method according to claim 5 is characterized in that: In S5, when acquiring the real-time monitoring data of the monitored power equipment corresponding to the equipment feature training set, the following steps are also included: Generate a device feature call request based on the device selection instruction, Matching the historical operation characteristic parameters within the corresponding first time window from the equipment characteristic data set; Suspend the monitoring mode instruction, obtain the operating characteristic parameters monitored by the power monitoring terminal within the first time window, and obtain the reference monitoring sequence; executing the monitoring mode instructions after the second time window and generating a sequence of real-time monitoring data; The benchmark monitoring sequence is compared with the real-time monitoring data acquired in the second time window to obtain a feature difference between the time domain features of the two, and the feature difference is used as an expansion interval of the first baseline.

7. An electronic device, characterized in that: It includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it is suitable for implementing the electric power equipment early warning monitoring method as described in any one of claims 5-6.

8. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it is suitable for implementing the electric power equipment early warning monitoring method as described in any one of claims 5-6.

Images