CN115877198A - Primary and secondary fusion switch fault diagnosis early warning system based on edge calculation - Google Patents
Primary and secondary fusion switch fault diagnosis early warning system based on edge calculation Download PDFInfo
- Publication number
- CN115877198A CN115877198A CN202211665689.0A CN202211665689A CN115877198A CN 115877198 A CN115877198 A CN 115877198A CN 202211665689 A CN202211665689 A CN 202211665689A CN 115877198 A CN115877198 A CN 115877198A
- Authority
- CN
- China
- Prior art keywords
- data
- early warning
- real
- primary
- fault diagnosis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000004927 fusion Effects 0.000 title claims abstract description 149
- 238000003745 diagnosis Methods 0.000 title claims abstract description 127
- 238000004364 calculation method Methods 0.000 title claims abstract description 27
- 238000004891 communication Methods 0.000 claims abstract description 7
- 210000002569 neuron Anatomy 0.000 claims description 40
- 238000000034 method Methods 0.000 claims description 30
- 230000007613 environmental effect Effects 0.000 claims description 24
- 230000008859 change Effects 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 4
- 238000012935 Averaging Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 claims 1
- 238000012545 processing Methods 0.000 abstract description 6
- 230000005540 biological transmission Effects 0.000 abstract description 5
- 238000009826 distribution Methods 0.000 abstract description 3
- 238000013500 data storage Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000013461 design Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000011065 in-situ storage Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Landscapes
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention provides a primary and secondary fusion switch fault diagnosis and early warning system based on edge computing, which relates to the technical field of power distribution networks and comprises a cloud server, a plurality of edge computing terminal devices and a plurality of data collectors, wherein the data collectors are in network communication connection with the cloud server through the edge computing terminal devices, a fault diagnosis and early warning model runs on the cloud server, and the edge computing terminal devices acquire the fault diagnosis and early warning model from the cloud server. According to the invention, a large amount of data storage and calculation processing can be migrated to the edge calculation terminal device, unnecessary real-time operation information transmission is reduced, the calculation processing load and the communication bandwidth requirement of the cloud server are greatly reduced, only the fault diagnosis early warning information after calculation processing is sent to the cloud server, and the cloud server pushes the early warning signal through the monitoring center, so that a supervisor can timely receive the fault early warning information and take corresponding measures, and the operation reliability of the primary and secondary fusion switch is improved.
Description
Technical Field
The invention relates to the technical field of power distribution networks, in particular to a primary and secondary fusion switch fault diagnosis and early warning system based on edge calculation.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The primary and secondary integration means that the primary and secondary equipment adopts an integrated design concept, namely, the primary equipment is standardized, the terminal product is miniaturized and standardized in design and is plug and play, and the interface of the primary and secondary equipment is standardized, so that the high integration of the primary and secondary equipment is realized, and the requirements of sectional line loss management, in-situ feeder automation, single-phase earth fault detection and automatic detection are met. The primary and secondary fusion switch is an important component of a power distribution network system, and when the switch equipment breaks down, the overhaul of the switch equipment brings great troubles to production and life, so that the effective and accurate monitoring and diagnosis of the switch equipment are realized, and the method is an effective way for improving the reliability of power supply equipment and the intelligent level of power grid operation. The power system urgently needs a fault monitoring and diagnosing technology aiming at the switch equipment, can predict potential risks, reduces the possibility of power failure, and further improves the quality of power supply. However, in the prior art, an early warning and monitoring method based on a primary and secondary switch fault is lacking, one reason is that the data volume is large, valuable information is extracted from multiple data, and the other reason is that more data are transmitted, and the network burden and the calculation burden are large, so that a primary and secondary fusion switch fault diagnosis and early warning system based on edge calculation needs to be developed and designed.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the method overcomes the defects in the prior art, and provides a primary and secondary fusion switch fault diagnosis and early warning system based on edge calculation.
In order to solve the problems, the invention adopts the technical scheme that:
a primary and secondary fusion switch fault diagnosis early warning system based on edge computing comprises a cloud server, a plurality of edge computing terminal devices and a plurality of data collectors, wherein the data collectors are in network communication connection with the cloud server through the edge computing terminal devices, a fault diagnosis early warning model runs on the cloud server, the edge computing terminal devices acquire the fault diagnosis early warning model from the cloud server, the edge computing terminal devices compare and judge the fault diagnosis early warning model with acquired node operation data to acquire early warning information, the early warning information is uploaded to the cloud server, the edge computing terminal devices generate operation data of a primary and secondary fusion switch according to the acquired data of the data collectors, the operation data are clustered to acquire the node operation data, and the node operation data are uploaded to the cloud server to be used for training a new fault diagnosis early warning model.
According to a further preferred embodiment of the above technical solution, the edge computing terminal device has functions of data acquisition, data computation, failure early warning analysis, and feature recognition, the data acquisition device includes a voltage acquisition device, a current acquisition device, a zero sequence voltage acquisition device, a zero sequence current acquisition device, a temperature and humidity acquisition device, a switch state acquisition device, and a mechanical characteristic sensor, and the voltage acquisition device is configured to acquire voltage information of the primary and secondary fusion switches, record the voltage information as real-time voltage data, and send the voltage information to the edge computing terminal device for comparison and judgment; the current collector obtains current information of the first and second fusion switches, records the current information as real-time current data, and sends the real-time current data to the edge computing terminal device for comparison and judgment; the zero sequence voltage collector acquires zero sequence voltage information of the first and second fusion switches, records the zero sequence voltage information as real-time zero sequence voltage data, and sends the real-time zero sequence voltage data to the edge computing terminal for comparison and judgment; the zero sequence current obtains zero sequence current information of a primary and secondary fusion switch, records the zero sequence current information as real-time zero sequence current data, and sends the real-time zero sequence current data to an edge computing terminal device for comparison and judgment; the temperature and humidity collector obtains environmental temperature and humidity data of the primary and secondary fusion switch, records the environmental temperature and humidity data as real-time environmental temperature and humidity data, and sends the environmental temperature and humidity data to the edge computing terminal device for comparison and judgment, the on-off state collector is used for obtaining on-off state data of the primary and secondary fusion switch, records the on-off state data as real-time on-off state data, and sends the real-time on-off state data to the edge computing terminal device for comparison and judgment, and the mechanical characteristic sensor obtains mechanical characteristic data of the primary and secondary fusion switch, records the mechanical characteristic data as real-time mechanical characteristic data, and sends the mechanical characteristic data to the edge computing terminal device for comparison and judgment.
A primary and secondary fusion switch fault diagnosis and early warning method based on edge calculation comprises the following steps:
step s1, the edge computing terminal device obtains the operation data of the primary and secondary fusion switches through a plurality of data collectors to generate the real-time operation data of the primary and secondary fusion switches;
step s2, the edge computing terminal device obtains a primary and secondary fusion switch fault diagnosis early warning model from the cloud service;
step s3, the edge computing terminal device inputs the real-time operation data of the primary and secondary fusion switches into a fault diagnosis early warning model for comparison, judges whether the real-time operation data of the primary and secondary fusion switches are normal or not, if the real-time operation data of the primary and secondary fusion switches are abnormal, the fault diagnosis early warning information is obtained and uploaded to a cloud server, and if the real-time operation data of the primary and secondary fusion switches are normal, whether the real-time operation data of the primary and secondary fusion switches need to be uploaded to the cloud server or not is judged according to the real-time operation data;
step s4, the edge computing terminal device sends the fault diagnosis early warning information and the real-time operation information of the primary and secondary fusion switch to a cloud server;
step s5, in the step 3, if the real-time operation data of the primary and secondary fusion switches are judged to be uploaded to the cloud server, the cloud server trains a new fault diagnosis early warning model; and the new fault diagnosis early warning model is sent to the edge computing terminal device.
Further, in step s1, the data collector includes a voltage collector, a current collector, a zero-sequence voltage collector, a zero-sequence current collector, a temperature and humidity collector, a switch state collector and a mechanical characteristic sensor, and the voltage collector is configured to obtain voltage information of the primary and secondary fusion switches, record the voltage information as real-time voltage data, and send the voltage data to the edge computing terminal device for comparison and judgment; the current collector acquires current information of the first fusion switch and the second fusion switch, records the current information as real-time current data, and sends the real-time current data to the edge computing terminal device for comparison and judgment; the zero sequence voltage collector acquires zero sequence voltage information of the first and second fusion switches, records the zero sequence voltage information as real-time zero sequence voltage data, and sends the real-time zero sequence voltage data to the edge computing terminal for comparison and judgment; the zero sequence current acquires zero sequence current information of a primary fusion switch and a secondary fusion switch, records the information as real-time zero sequence current data, and sends the data to an edge computing terminal device for comparison and judgment; the temperature and humidity collector obtains environmental temperature and humidity data of the primary and secondary fusion switch, records the environmental temperature and humidity data as real-time environmental temperature and humidity data, and sends the environmental temperature and humidity data to the edge computing terminal device for comparison and judgment, the on-off state collector is used for obtaining on-off state data of the primary and secondary fusion switch, records the on-off state data as real-time on-off state data, and sends the real-time on-off state data to the edge computing terminal device for comparison and judgment, and the mechanical characteristic sensor obtains mechanical characteristic data of the primary and secondary fusion switch, records the mechanical characteristic data as real-time mechanical characteristic data, and sends the mechanical characteristic data to the edge computing terminal device for comparison and judgment.
Further, in step s2, the fault diagnosis and early warning model is obtained to include a plurality of neuron models ω ki Model of each neuron ω ki Corresponding data sample X i A plurality of data samples X i Respectively inputting corresponding neuron models omega ki A plurality of neuronsModel omega k Sum of calculated results b k Obtaining a fault diagnosis early warning result y k The input and output corresponding relation of the fault diagnosis early warning model is as follows:
in the formula, X 1 ～X 7 Respectively corresponding to the real-time running data, omega, of the voltage, the current, the zero-sequence voltage, the zero-sequence current, the temperature and the humidity, the switching state and the mechanical characteristics collected by the primary and secondary fusion switch collectors k1 ～ω k7 The method comprises the following steps of respectively corresponding to a voltage neuron model, a current neuron model, a zero sequence voltage neuron model, a zero sequence current neuron model, a temperature and humidity neuron model, an on-off state neuron model and a mechanical characteristic neuron model.
Further, in step s2, the edge computing terminal device obtains the primary and secondary fusion switch fault diagnosis and early warning model from the cloud service, where the early warning model includes early warning model identifiers, and the early warning model identifiers correspond to the plurality of edge computing terminal devices and are used by the cloud service to send different early warning models to the edge computing terminal device nodes respectively.
Further, the step s3 includes the steps of:
step s301, the edge computing terminal device compares the acquired real-time operation data of the primary and secondary fusion switches with the acquired fault diagnosis early warning model, and judges whether the real-time operation data of the primary and secondary fusion switches meet a threshold range set by the fault diagnosis early warning model; if the set threshold range is met, judging that the primary and secondary fusion switches operate normally, and if the set threshold range is not met, judging that the primary and secondary fusion switches are abnormal, acquiring fault diagnosis early warning information and sending the fault diagnosis early warning information;
step s302, according to that the real-time operation data of the primary and secondary fusion switches in step s301 meets a threshold range set by the fault diagnosis early warning model, whether the real-time operation data changes in the threshold range is judged, if no change trend exists, the edge computing terminal device does not upload the real-time operation data to the cloud server, if a change trend exists, whether the change trend of the real-time operation data is consistent with that of the real-time operation data at the previous moment is judged, if the change trend is consistent, the edge computing terminal device judges that the primary and secondary fusion switches corresponding to the real-time operation data possibly have operation abnormity, the edge computing terminal device obtains fault diagnosis early warning information and sends the fault diagnosis early warning information to the cloud server, meanwhile, the real-time operation data of the primary and secondary fusion switches are uploaded to the cloud server, and if the change trend of the real-time operation data at the previous moment is inconsistent, the edge computing terminal device does not upload the real-time operation data to the cloud server.
Further, in step s4, the fault diagnosis and early warning information and the real-time operation information of the primary and secondary fusion switches sent by the edge computing terminal devices include node identifiers, and the node identifiers identify the plurality of edge computing terminal devices, and are used for sending the real-time operation data of the primary and secondary fusion switches and the fault diagnosis and early warning information to the cloud server.
Further, in step s5, training a new fault diagnosis and early warning model includes the following steps:
acquiring real-time operation data of a primary and secondary fusion switch uploaded to a cloud server, and storing the real-time operation data as sample data in a time sequence according to the acquired real-time operation data;
respectively extracting sample data to generate characteristic data according to the type of the fault diagnosis early warning model;
and summing and averaging the generated characteristic data to obtain a characteristic value of the early warning model, and obtaining a new early warning diagnosis model according to the characteristic value of the early warning model.
The application provides an edge computing terminal device, including: at least one memory for storing a program; at least one processor for executing programs stored by the memory; wherein, when the program stored in the memory is executed, the processor is used for executing the steps of the primary and secondary fusion switch fault diagnosis and early warning method based on edge calculation.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides a primary and secondary fusion switch fault diagnosis early warning system and an early warning method based on edge computing, which can transfer a large amount of data storage and computing processing to an edge computing terminal device, reduce unnecessary real-time operation information transmission, greatly reduce the computing processing load and communication bandwidth requirements of a cloud server, only send the computed fault diagnosis early warning information to the cloud server, and the cloud server pushes early warning signals through a monitoring center, so that a supervisor can timely receive the fault early warning information and take corresponding measures, and the operation reliability of a primary and secondary fusion switch is improved.
Drawings
FIG. 1 is a schematic diagram of the system of the present invention;
FIG. 2 is a flow chart illustrating the steps of the method of the present invention;
FIG. 3 is a schematic diagnostic flow diagram according to the present invention;
FIG. 4 is a schematic diagram of a neuron mathematical model for diagnosing and warning faults according to the present invention;
FIG. 5 is a schematic structural diagram of an edge computing terminal device according to the present invention.
In the figure: 1. cloud server, 2, edge computing terminal device, 3, data collection station.
Detailed Description
The present invention is further described in detail with reference to the accompanying drawings, and the following embodiments are only used for more clearly illustrating the technical solutions of the present invention, and modifications made by those skilled in the art on the basis of the embodiments of the present invention are all within the scope of the present invention.
As shown in fig. 1 to 5, the invention provides a primary and secondary fusion switch fault diagnosis early warning system based on edge computing, which includes a cloud server 1, a plurality of edge computing terminal devices 2, and a plurality of data collectors 3, where the data collectors 3 are in network communication connection with the cloud server 1 through the edge computing terminal devices 2, a fault diagnosis early warning model operates on the cloud server 1, the edge computing terminal devices 2 acquire the fault diagnosis early warning model from the cloud server 1, the edge computing terminal devices 2 compare and judge the fault diagnosis early warning model with the acquired node operation data to acquire early warning information, and upload the early warning information to the cloud server 1, and the edge computing terminal devices 2 generate operation data of a primary and secondary fusion switch from the acquired data collectors 3, cluster the operation data to acquire node operation data, and upload the node operation data to the cloud server 1 for training a new fault diagnosis early warning model. In the embodiment of the invention, a fault diagnosis early warning model runs on a cloud server 1, the fault diagnosis early warning model can be generated according to experience values of primary and secondary fusion switch running data and is used as a classic fault diagnosis early warning model of a primary and secondary fusion switch fault diagnosis early warning system and is sent to an edge computing terminal device 2, the edge computing terminal device 2 compares the acquired classic fault diagnosis early warning model with acquired primary and secondary fusion switch real-time running data and judges whether the real-time running data of a primary and secondary fusion switch exceeds a set threshold range of the fault diagnosis early warning model, fault diagnosis early warning information is acquired according to a judgment result and is sent to the cloud server 1, the cloud server 1 sends the fault diagnosis early warning information to related personnel, and corresponding measures are taken according to the fault diagnosis early warning information to improve the running reliability of the primary and secondary fusion switches.
Illustratively, the edge computing terminal device 2 has functions of data acquisition, data calculation, fault early warning analysis and feature recognition, the data acquisition device 3 includes a voltage acquisition device, a current acquisition device, a zero sequence voltage acquisition device, a zero sequence current acquisition device, a temperature and humidity acquisition device, a switch state acquisition device and a mechanical characteristic sensor, the voltage acquisition device is used for acquiring voltage information of a primary and secondary fusion switch, recording the voltage information as real-time voltage data and sending the real-time voltage data to the edge computing terminal device 2 for comparison and judgment; the current collector obtains current information of the first and second fusion switches, records the current information as real-time current data, and sends the real-time current data to the edge computing terminal device 2 for comparison and judgment; the zero sequence voltage collector acquires zero sequence voltage information of the first and second fusion switches, records the zero sequence voltage information as real-time zero sequence voltage data, and sends the real-time zero sequence voltage data to the edge computing terminal for comparison and judgment; the zero sequence current acquires zero sequence current information of the primary and secondary fusion switches, records the information as real-time zero sequence current data, and sends the data to the edge computing terminal device 2 for comparison and judgment; the temperature and humidity collector obtains environmental temperature and humidity data of the primary and secondary fusion switch, records the environmental temperature and humidity data as real-time environmental temperature and humidity data, and sends the environmental temperature and humidity data to the edge computing terminal device 2 for comparison and judgment, the switch state collector is used for obtaining switch state data of the primary and secondary fusion switch, records the switch state data as real-time switch state data, and sends the switch state data to the edge computing terminal device 2 for comparison and judgment, and the mechanical characteristic sensor obtains mechanical characteristic data of the primary and secondary fusion switch, records the mechanical characteristic data as real-time mechanical characteristic data, and sends the mechanical characteristic data to the edge computing terminal device 2 for comparison and judgment. In the system of the embodiment of the invention, the edge computing terminal device 2 pre-processes the acquired data of the data acquisition unit, but uploads the data in real time, and after the data are input into the fault diagnosis early warning model for comparison, the real-time data of the operation of the primary and secondary fusion switches are uploaded as required. The method has the advantages that the data volume of data transmission is reduced, network congestion is prevented, the calculation amount of server background data is reduced, meanwhile, real-time monitoring and fault diagnosis and early warning of the primary and secondary fusion switch can be met, and guarantee is provided for safe, stable and reliable operation of the primary and secondary fusion switch.
As shown in fig. 2 and fig. 3, the present invention provides an embodiment of a primary and secondary fusion switch fault diagnosis and early warning method based on edge calculation, where the fault diagnosis and early warning method includes the following steps:
step s1, the edge computing terminal device 2 acquires the operation data of the primary and secondary fusion switch through a plurality of data collectors 3 to generate the real-time operation data of the primary and secondary fusion switch;
step s2, the edge computing terminal device 2 obtains a primary and secondary fusion switch fault diagnosis early warning model from the cloud service 1;
step s3, the edge computing terminal device 2 inputs the real-time operation data of the primary and secondary fusion switches into the fault diagnosis early warning model for comparison, judges whether the real-time operation data of the primary and secondary fusion switches are normal or not, if the real-time operation data of the primary and secondary fusion switches are abnormal, obtains fault diagnosis early warning information and uploads the fault diagnosis early warning information to the cloud server 1, and if the real-time operation data of the primary and secondary fusion switches are normal, judges whether the real-time operation data needs to be uploaded to the cloud server 1 or not according to the real-time operation data;
step s4, the edge computing terminal device 2 sends the fault diagnosis early warning information and the real-time operation information of the primary and secondary fusion switches to the cloud server 1;
step s5, in step 3, if the real-time operation data of the primary and secondary fusion switches are judged to be uploaded to the cloud server 1, the cloud server 1 trains a new fault diagnosis early warning model; and issues the new fault diagnosis and early warning model to the edge computing terminal device 2. In the prior art, the real-time operation data volume of the primary and secondary fusion switches is large, the cloud server extracts valuable information from various data and diagnoses the operation condition of the primary and secondary fusion switches, the process is complicated, and the other reason is that more data are transmitted, so that the network burden and the calculation burden are large. Therefore, real-time monitoring and fault early warning are not facilitated for the operation condition of the primary and secondary fusion switches. In the embodiment of the invention, most of the computing functions borne by the cloud server need to be downloaded to the plurality of distributed edge computing terminal devices, the edge computing terminal devices 2 compare the acquired operation data of the primary and secondary fusion switches with the fault diagnosis and early warning model to acquire fault diagnosis and early warning information, and the fault diagnosis and early warning information is sent to the cloud server 1. The embodiment of the invention not only reduces the data calculation burden of the cloud server 1, but also reduces the bandwidth requirement of the communication transmission between the edge terminal and the server, and increases the reliability of data transmission.
In the step s1, the data collector 3 includes a voltage collector, a current collector, a zero sequence voltage collector, a zero sequence current collector, a temperature and humidity collector, a switch state collector and a mechanical characteristic sensor, and the voltage collector is used for acquiring voltage information of the primary and secondary fusion switch, recording the voltage information as real-time voltage data, and sending the real-time voltage data to the edge computing terminal device 2 for comparison and judgment; the current collector obtains current information of the first and second fusion switches, records the current information as real-time current data, and sends the real-time current data to the edge computing terminal device 2 for comparison and judgment; the zero sequence voltage collector acquires zero sequence voltage information of a first and a second fusion switches, records the zero sequence voltage information as real-time zero sequence voltage data, and sends the real-time zero sequence voltage data to the edge computing terminal for comparison and judgment; the zero sequence current obtains zero sequence current information of the primary and secondary fusion switches, records the zero sequence current information as real-time zero sequence current data, and sends the real-time zero sequence current data to the edge computing terminal device 2 for comparison and judgment; the temperature and humidity collector obtains environmental temperature and humidity data of the primary and secondary fusion switch, records the environmental temperature and humidity data as real-time environmental temperature and humidity data, and sends the environmental temperature and humidity data to the edge computing terminal device 2 for comparison and judgment, the switch state collector is used for obtaining switch state data of the primary and secondary fusion switch, records the switch state data as real-time switch state data, and sends the switch state data to the edge computing terminal device 2 for comparison and judgment, and the mechanical characteristic sensor obtains mechanical characteristic data of the primary and secondary fusion switch, records the mechanical characteristic data as real-time mechanical characteristic data, and sends the mechanical characteristic data to the edge computing terminal device 2 for comparison and judgment.
In step s4, the fault diagnosis early warning information and the real-time operation information of the primary and secondary fusion switches sent by the edge computing terminal devices 2 include node identifiers, and the node identifiers identify the plurality of edge computing terminal devices 2 and are used for sending the real-time operation data and the fault diagnosis early warning information of the primary and secondary fusion switches to the cloud server 1.
In the step s2, the fault diagnosis early warning model includes a plurality of neuron models omega ki Model of each neuron ω ki Corresponding data sample X i A plurality of data samples X i Respectively inputting corresponding neuron models omega ki Modeling a plurality of neurons as ω k Sum of calculated results b k To obtain a fault diagnosis early warning result y k The input and output corresponding relation of the fault diagnosis early warning model is as follows:
in the formula, X 1 ～X 7 Respectively corresponding to the real-time running data of voltage, current, zero-sequence voltage, zero-sequence current, temperature and humidity, switch state and mechanical characteristics collected by the primary and secondary fusion switch collector 3 k1 ～ω k7 Respectively corresponding to a voltage neuron model, a current neuron model, a zero-sequence voltage neuron model, a zero-sequence current neuron model, a temperature and humidity neuron model, an on-off state neuron model and a mechanical characteristic neuronAnd (4) modeling. As shown in fig. 4, which is a schematic diagram of a neural network mathematical model, the early warning and diagnosis process according to the embodiment of the present invention is to set different voltage neuron models, current neuron models, zero-sequence voltage neuron models, zero-sequence current neuron models, temperature and humidity neuron models, on-off state neuron models, and mechanical characteristic neuron models by using real-time data obtained by the edge computing terminal 2 according to each data collector 3 as data samples X according to different data types, and input the sample data X into different neuron models respectively, simulate a data processing process in which input data is weighted by a certain weight, and simulate the obtained fault diagnosis early warning information as a summation process with bias.
In step s2, the edge computing terminal devices 2 acquire the primary and secondary fusion switch fault diagnosis and early warning models from the cloud service 1, where the early warning model identifiers include early warning model identifiers, correspond to the plurality of edge computing terminal devices 2, and are used by the cloud service 1 to send different early warning models to the edge computing terminal device 2 nodes respectively.
The step s3 includes the steps of:
step s301, the edge computing terminal device 2 compares the acquired real-time operation data of the primary and secondary fusion switches with the acquired fault diagnosis and early warning model, and judges whether the real-time operation data of the primary and secondary fusion switches meet the threshold range set by the fault diagnosis and early warning model; if the set threshold range is met, judging that the primary and secondary fusion switches operate normally, and if the set threshold range is not met, judging that the primary and secondary fusion switches are abnormal, acquiring fault diagnosis early warning information and sending the fault diagnosis early warning information;
step s302, according to that the real-time operation data of the primary and secondary fusion switches in step s301 meets the threshold range set by the fault diagnosis early warning model, whether the real-time operation data changes in the threshold range is judged, if no change trend exists, the edge computing terminal device 2 does not upload the real-time operation data to the cloud server 1, if a change trend exists, whether the change trend of the real-time operation data is consistent with that of the real-time operation data at the previous moment is judged, if the change trend is consistent, the edge computing terminal device 2 judges that the primary and secondary fusion switches corresponding to the real-time operation data possibly have operation abnormity, the edge computing terminal device 2 obtains fault diagnosis early warning information and sends the fault diagnosis early warning information to the cloud server 1, meanwhile, the real-time operation data of the primary and secondary fusion switches is uploaded to the cloud server 1, and if the change trend of the real-time operation data is inconsistent with that of the real-time operation data at the previous moment is judged, the edge computing terminal device 2 does not upload the real-time operation data to the cloud server 1.
In step s5, training a new fault diagnosis early warning model includes the following steps:
acquiring real-time operation data of a primary and secondary fusion switch uploaded to the cloud server 1, and storing the real-time operation data as sample data in a time sequence according to the acquired real-time operation data;
respectively extracting sample data to generate characteristic data according to the type of the fault diagnosis early warning model;
and summing and averaging the generated characteristic data to obtain an early warning model characteristic value, and obtaining a new early warning diagnosis model according to the early warning model characteristic value.
An edge computing terminal device, comprising: at least one memory for storing a program;
at least one processor for executing programs stored by the memory; wherein when the program stored in the memory is executed, the processor is used for executing the method in any one of the primary and secondary fusion switch fault diagnosis and early warning methods based on edge calculation.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts by those skilled in the art based on the technical solution of the present invention.
Claims (10)
1. Primary and secondary fusion switch fault diagnosis early warning system based on edge calculation, its characterized in that:
the intelligent fault diagnosis and early warning system comprises a cloud server (1), a plurality of edge computing terminal devices (2) and a plurality of data collectors (3), wherein the data collectors (3) are in network communication connection with the cloud server (1) through the edge computing terminal devices (2), a fault diagnosis and early warning model runs on the cloud server (1), the edge computing terminal devices (2) obtain the fault diagnosis and early warning model from the cloud server (1), the edge computing terminal devices (2) compare and judge the fault diagnosis and early warning model and the obtained node running data to obtain early warning information, the early warning information is uploaded to the cloud server (1), the edge computing terminal devices (2) generate the running data of a secondary fusion switch according to the obtained data of the data collectors (3), cluster the running data to obtain the node running data, and upload the node running data to the cloud server (1) for training of a new fault diagnosis and early warning model.
2. The primary and secondary fusion switch fault diagnosis and early warning system based on edge calculation as claimed in claim 1, wherein:
the edge computing terminal device (2) has the functions of data acquisition, data computation, fault early warning analysis and feature recognition, the data acquisition device (3) comprises a voltage acquisition device, a current acquisition device, a zero sequence voltage acquisition device, a zero sequence current acquisition device, a temperature and humidity acquisition device, a switch state acquisition device and a mechanical characteristic sensor, and the voltage acquisition device is used for acquiring voltage information of a primary fusion switch and a secondary fusion switch, recording the voltage information as real-time voltage data and sending the real-time voltage data to the edge computing terminal device (2) for comparison and judgment; the current collector obtains current information of the first and second fusion switches, records the current information as real-time current data, and sends the real-time current data to the edge computing terminal device (2) for comparison and judgment; the zero sequence voltage collector acquires zero sequence voltage information of the first and second fusion switches, records the zero sequence voltage information as real-time zero sequence voltage data, and sends the real-time zero sequence voltage data to the edge computing terminal for comparison and judgment; the zero sequence current obtains zero sequence current information of a primary and secondary fusion switch, records the zero sequence current information as real-time zero sequence current data, and sends the real-time zero sequence current data to the edge computing terminal device (2) for comparison and judgment; the temperature and humidity collector acquires environmental temperature and humidity data of the primary and secondary fusion switch, records the environmental temperature and humidity data as real-time environmental temperature and humidity data, sends the environmental temperature and humidity data to the edge computing terminal device (2) for comparison and judgment, the on-off state collector is used for acquiring on-off state data of the primary and secondary fusion switch, records the on-off state data as real-time on-off state data, sends the real-time on-off state data to the edge computing terminal device (2) for comparison and judgment, and the mechanical characteristic sensor acquires mechanical characteristic data of the primary and secondary fusion switch, records the mechanical characteristic data as real-time mechanical characteristic data, and sends the mechanical characteristic data to the edge computing terminal device (2) for comparison and judgment.
3. The primary and secondary fusion switch fault diagnosis early warning method based on edge calculation is characterized by comprising the following steps:
the fault diagnosis early warning method comprises the following steps:
step s1, the edge computing terminal device (2) acquires the operation data of the primary and secondary fusion switches through a plurality of data collectors (3) to generate the real-time operation data of the primary and secondary fusion switches;
step s2, the edge computing terminal device (2) acquires a primary and secondary fusion switch fault diagnosis early warning model from the cloud service (1);
step s3, the edge computing terminal device (2) inputs the real-time operation data of the primary and secondary fusion switches into a fault diagnosis early warning model for comparison, judges whether the real-time operation data of the primary and secondary fusion switches are normal or not, if the real-time operation data of the primary and secondary fusion switches are abnormal, obtains fault diagnosis early warning information and uploads the fault diagnosis early warning information to the cloud server (1), and if the real-time operation data of the primary and secondary fusion switches are normal, judges whether the fault diagnosis early warning information needs to be uploaded to the cloud server (1) according to the real-time operation data;
step s4, the edge computing terminal device (2) sends the fault diagnosis early warning information and the real-time operation information of the primary and secondary fusion switches to the cloud server (1);
step s5, in the step s3, if the abnormality is judged, uploading the real-time operation data of the primary and secondary fusion switches to the cloud server (1), and training a new fault diagnosis early warning model by the cloud server (1); and the new fault diagnosis early warning model is sent to the edge computing terminal device (2).
4. The primary and secondary fusion switch fault diagnosis and early warning method based on edge calculation as claimed in claim 3, wherein:
in the step s1, the data collector (3) comprises a voltage collector, a current collector, a zero-sequence voltage collector, a zero-sequence current collector, a temperature and humidity collector, a switch state collector and a mechanical characteristic sensor, wherein the voltage collector is used for obtaining voltage information of the primary and secondary fusion switch, recording the voltage information as real-time voltage data and sending the real-time voltage data to the edge computing terminal device (2) for comparison and judgment; the current collector obtains current information of the first and second fusion switches, records the current information as real-time current data, and sends the real-time current data to the edge computing terminal device (2) for comparison and judgment; the zero sequence voltage collector acquires zero sequence voltage information of a first and a second fusion switches, records the zero sequence voltage information as real-time zero sequence voltage data, and sends the real-time zero sequence voltage data to the edge computing terminal for comparison and judgment; the zero sequence current obtains zero sequence current information of a primary and secondary fusion switch, records the zero sequence current information as real-time zero sequence current data, and sends the real-time zero sequence current data to the edge computing terminal device (2) for comparison and judgment; the temperature and humidity collector acquires environmental temperature and humidity data of the primary and secondary fusion switch, records the environmental temperature and humidity data as real-time environmental temperature and humidity data, sends the environmental temperature and humidity data to the edge computing terminal device (2) for comparison and judgment, the on-off state collector is used for acquiring on-off state data of the primary and secondary fusion switch, records the on-off state data as real-time on-off state data, sends the real-time on-off state data to the edge computing terminal device (2) for comparison and judgment, and the mechanical characteristic sensor acquires mechanical characteristic data of the primary and secondary fusion switch, records the mechanical characteristic data as real-time mechanical characteristic data, and sends the mechanical characteristic data to the edge computing terminal device (2) for comparison and judgment.
5. The primary and secondary fusion switch fault diagnosis and early warning method based on edge calculation as claimed in claim 3, wherein:
in the step s2, the fault diagnosis early warning model includes a plurality of neuron models omega ki Model of each neuron ω ki Corresponding data sample X i A plurality of data samples X i Respectively inputting corresponding neuron models omega ki Modeling a plurality of neurons ω k Sum of calculated results b k To obtain a fault diagnosis early warning result y k The input and output corresponding relation of the fault diagnosis early warning model is as follows:
in the formula, X 1 ～X 7 Respectively corresponding to the voltage, current, zero sequence voltage, zero sequence current, temperature and humidity, switch state and mechanical characteristic operation real-time data, omega, collected by the primary and secondary fusion switch collector (3) k1 ～ω k7 The method comprises the following steps of respectively corresponding to a voltage neuron model, a current neuron model, a zero sequence voltage neuron model, a zero sequence current neuron model, a temperature and humidity neuron model, an on-off state neuron model and a mechanical characteristic neuron model.
6. The primary and secondary fusion switch fault diagnosis and early warning method based on edge calculation as claimed in claim 3, wherein:
in the step s2, the edge computing terminal devices (2) obtain the primary and secondary fusion switch fault diagnosis and early warning model from the cloud service (1), wherein the early warning model comprises early warning model identifications, the early warning model identifications correspond to the edge computing terminal devices (2), and the early warning model identifications are used for the cloud service (1) to respectively send different early warning models to the edge computing terminal device (2) nodes.
7. The primary and secondary fusion switch fault diagnosis and early warning method based on edge calculation as claimed in claim 3, wherein:
the step s3 includes the steps of:
step s301, the edge computing terminal device (2) compares the acquired real-time operation data of the primary and secondary fusion switches with the acquired fault diagnosis and early warning model, and judges whether the real-time operation data of the primary and secondary fusion switches meet a threshold range set by the fault diagnosis and early warning model; if the set threshold range is met, judging that the primary and secondary fusion switches operate normally, and if the set threshold range is not met, judging that the primary and secondary fusion switches are abnormal, acquiring fault diagnosis early warning information and sending the fault diagnosis early warning information;
step s302, according to the fact that the real-time operation data of the primary and secondary fusion switches in step s301 meet a threshold range set by the fault diagnosis early warning model, whether the real-time operation data change in the threshold range is judged, if no change trend exists, the edge computing terminal device (2) does not upload the real-time operation data to the cloud server (1), if a change trend exists, whether the change trend of the real-time operation data is consistent with that of the real-time operation data at the previous moment is judged, if the change trend is consistent, the edge computing terminal device (2) judges that an operation anomaly may exist in the primary and secondary fusion switches corresponding to the real-time operation data, the edge computing terminal device (2) obtains fault diagnosis early warning information and sends the fault diagnosis early warning information to the cloud server (1), meanwhile, the real-time operation data of the primary and secondary fusion switches are uploaded to the cloud server (1), and if the change trend of the real-time operation data is inconsistent with that of the real-time operation data at the previous moment is judged, the edge computing terminal device (2) does not upload the real-time operation data to the cloud server (1).
8. The primary and secondary fusion switch fault diagnosis and early warning method based on edge calculation as claimed in claim 3, wherein:
in the step s4, the fault diagnosis early warning information and the primary and secondary fusion switch real-time operation information sent by the edge computing terminal devices (2) include node identifiers, and the node identifiers identify the plurality of edge computing terminal devices (2) corresponding to the node identifiers and are used for sending the primary and secondary fusion switch real-time operation data and the fault diagnosis early warning information to the cloud server (1).
9. The primary and secondary fusion switch fault diagnosis and early warning method based on edge calculation as claimed in claim 3, wherein:
in step s5, training a new fault diagnosis early warning model includes the following steps:
the method comprises the steps of obtaining real-time operation data of a primary and secondary fusion switch uploaded to a cloud server (1), and storing the real-time operation data as sample data according to the obtained real-time operation data in a time sequence;
respectively extracting sample data to generate characteristic data according to the type of the fault diagnosis early warning model;
and summing and averaging the generated characteristic data to obtain an early warning model characteristic value, and obtaining a new early warning diagnosis model according to the early warning model characteristic value.
10. An edge computing terminal device, characterized by:
the method comprises the following steps: at least one memory for storing a program;
at least one processor for executing programs stored by the memory;
wherein the processor is configured to perform the method of any one of claims 3 to 9 when the program stored in the memory is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211665689.0A CN115877198A (en) | 2022-12-23 | 2022-12-23 | Primary and secondary fusion switch fault diagnosis early warning system based on edge calculation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211665689.0A CN115877198A (en) | 2022-12-23 | 2022-12-23 | Primary and secondary fusion switch fault diagnosis early warning system based on edge calculation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115877198A true CN115877198A (en) | 2023-03-31 |
Family
ID=85754458
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211665689.0A Pending CN115877198A (en) | 2022-12-23 | 2022-12-23 | Primary and secondary fusion switch fault diagnosis early warning system based on edge calculation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115877198A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116488169A (en) * | 2023-06-25 | 2023-07-25 | 北京智芯微电子科技有限公司 | Fault processing method, device, system and medium based on intelligent switch |
| CN117454234A (en) * | 2023-12-26 | 2024-01-26 | 国网天津市电力公司宁河供电分公司 | County power grid fault identification method and county power grid fault identification device based on cloud edge cooperation |
| CN117914001A (en) * | 2024-03-18 | 2024-04-19 | 北京智芯微电子科技有限公司 | Power system, fault studying and judging method, device, equipment and medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108828409A (en) * | 2018-08-03 | 2018-11-16 | 南方电网科学研究院有限责任公司 | Fault detection system based on edge calculation |
| CN111507489A (en) * | 2020-04-20 | 2020-08-07 | 电子科技大学中山学院 | Cloud-edge-coordinated amusement equipment fault prediction and health management system and method |
| CN111563612A (en) * | 2020-04-13 | 2020-08-21 | 深圳达实智能股份有限公司 | Predictive operation and maintenance management method and system for air conditioner of subway station |
| CN111579923A (en) * | 2020-05-19 | 2020-08-25 | 广东电网有限责任公司 | Power distribution network fault diagnosis system and method |
| CN111830408A (en) * | 2020-06-23 | 2020-10-27 | 朗斯顿科技(北京)有限公司 | Motor fault diagnosis system and method based on edge calculation and deep learning |
| CN112751421A (en) * | 2021-02-05 | 2021-05-04 | 广东港博新能源科技有限公司 | Digital computing enhanced high-reliability low-voltage power distribution safety monitoring system |
| CN114298175A (en) * | 2021-12-14 | 2022-04-08 | 国网河北能源技术服务有限公司 | Power equipment state monitoring and fault early warning method and system based on edge calculation |
| CN115186883A (en) * | 2022-06-29 | 2022-10-14 | 成都航天科工大数据研究院有限公司 | Industrial equipment health state monitoring system and method based on Bian Yun collaborative computing |
| CN115361664A (en) * | 2022-08-16 | 2022-11-18 | 四川翰亭志科技有限公司 | Integrated intelligent monitoring and early warning security system |
-
2022
- 2022-12-23 CN CN202211665689.0A patent/CN115877198A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108828409A (en) * | 2018-08-03 | 2018-11-16 | 南方电网科学研究院有限责任公司 | Fault detection system based on edge calculation |
| CN111563612A (en) * | 2020-04-13 | 2020-08-21 | 深圳达实智能股份有限公司 | Predictive operation and maintenance management method and system for air conditioner of subway station |
| CN111507489A (en) * | 2020-04-20 | 2020-08-07 | 电子科技大学中山学院 | Cloud-edge-coordinated amusement equipment fault prediction and health management system and method |
| CN111579923A (en) * | 2020-05-19 | 2020-08-25 | 广东电网有限责任公司 | Power distribution network fault diagnosis system and method |
| CN111830408A (en) * | 2020-06-23 | 2020-10-27 | 朗斯顿科技(北京)有限公司 | Motor fault diagnosis system and method based on edge calculation and deep learning |
| CN112751421A (en) * | 2021-02-05 | 2021-05-04 | 广东港博新能源科技有限公司 | Digital computing enhanced high-reliability low-voltage power distribution safety monitoring system |
| CN114298175A (en) * | 2021-12-14 | 2022-04-08 | 国网河北能源技术服务有限公司 | Power equipment state monitoring and fault early warning method and system based on edge calculation |
| CN115186883A (en) * | 2022-06-29 | 2022-10-14 | 成都航天科工大数据研究院有限公司 | Industrial equipment health state monitoring system and method based on Bian Yun collaborative computing |
| CN115361664A (en) * | 2022-08-16 | 2022-11-18 | 四川翰亭志科技有限公司 | Integrated intelligent monitoring and early warning security system |
Non-Patent Citations (2)
| Title |
|---|
| 李正茂: "《云网融合：算力时代的数字信息基础设施》", 30 April 2020, 中信出版社, pages: 110 - 115 * |
| 毕昊林等: "基于边缘计算的柱上开关状态监测研究", 《中国新技术新产品》, 30 June 2020 (2020-06-30), pages 13 - 14 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116488169A (en) * | 2023-06-25 | 2023-07-25 | 北京智芯微电子科技有限公司 | Fault processing method, device, system and medium based on intelligent switch |
| CN117454234A (en) * | 2023-12-26 | 2024-01-26 | 国网天津市电力公司宁河供电分公司 | County power grid fault identification method and county power grid fault identification device based on cloud edge cooperation |
| CN117914001A (en) * | 2024-03-18 | 2024-04-19 | 北京智芯微电子科技有限公司 | Power system, fault studying and judging method, device, equipment and medium |
| CN117914001B (en) * | 2024-03-18 | 2024-05-17 | 北京智芯微电子科技有限公司 | Power system, fault studying and judging method, device, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109146093B (en) | Power equipment field investigation method based on learning | |
| CN115877198A (en) | Primary and secondary fusion switch fault diagnosis early warning system based on edge calculation | |
| CN110717665A (en) | System and method for fault identification and trend analysis based on scheduling control system | |
| CN112817280A (en) | Implementation method for intelligent monitoring alarm system of thermal power plant | |
| CN113708493B (en) | Cloud edge cooperation-based power distribution terminal operation and maintenance method and device and computer equipment | |
| CN110095661B (en) | Distribution transformer high-voltage side open-phase fault first-aid repair method | |
| CN111444169A (en) | Transformer substation electrical equipment state monitoring and diagnosis system and method | |
| CN109670584A (en) | A kind of fault diagnosis method and system based on big data | |
| CN116614177B (en) | Optical fiber state multidimensional parameter monitoring system | |
| CN113327741A (en) | Front end structure for monitoring oil-filled transformer in real time | |
| CN117289085A (en) | Multi-line fault analysis and diagnosis method and system | |
| CN112904148A (en) | Intelligent cable operation monitoring system, method and device | |
| CN116418117A (en) | Equipment detection system for intelligent power grid | |
| CN116125204A (en) | Fault prediction system based on power grid digitization | |
| CN112415330A (en) | Power grid fault intelligent identification method and system based on wide area information | |
| CN117612345A (en) | Power equipment state monitoring and alarming system and method | |
| CN114996843A (en) | Design method of electric aircraft power system fault diagnosis and health management system | |
| CN114743089A (en) | Image recognition GIS fault diagnosis device and method based on SSA-SVM | |
| CN117560300A (en) | Intelligent internet of things flow prediction and optimization system | |
| CN112803587A (en) | Intelligent inspection method for state of automatic equipment based on diagnosis decision library | |
| CN115146727A (en) | Intelligent power utilization system fault detection method and system | |
| CN111857015B (en) | Power transmission and transformation cloud intelligent controller | |
| CN114442543A (en) | Computer monitoring method suitable for early warning of hydropower station fault | |
| CN109507468B (en) | Header box branch current detection method and system based on correlation characteristics | |
| CN113129160A (en) | Electric power communication network inspection method based on equipment state perception and intellectualization |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |