CN116488343B - Intelligent power equipment safety monitoring system and method based on Internet of things - Google Patents
Intelligent power equipment safety monitoring system and method based on Internet of things Download PDFInfo
- Publication number
- CN116488343B CN116488343B CN202310462642.2A CN202310462642A CN116488343B CN 116488343 B CN116488343 B CN 116488343B CN 202310462642 A CN202310462642 A CN 202310462642A CN 116488343 B CN116488343 B CN 116488343B
- Authority
- CN
- China
- Prior art keywords
- equipment
- power
- power equipment
- frequency sensor
- sensor
- 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.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000003384 imaging method Methods 0.000 claims abstract description 27
- 238000013528 artificial neural network Methods 0.000 claims abstract description 13
- 238000012549 training Methods 0.000 claims abstract description 10
- 230000008859 change Effects 0.000 claims description 5
- 238000003062 neural network model Methods 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 3
- 238000004020 luminiscence type Methods 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 abstract description 4
- 238000001514 detection method Methods 0.000 description 12
- 239000003990 capacitor Substances 0.000 description 5
- 230000008878 coupling Effects 0.000 description 5
- 238000010168 coupling process Methods 0.000 description 5
- 238000005859 coupling reaction Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 238000007493 shaping process Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 2
- 238000009413 insulation Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005684 electric field Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000004393 prognosis Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/0096—Radiation pyrometry, e.g. infrared or optical thermometry for measuring wires, electrical contacts or electronic systems
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
- G01R31/1218—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing using optical methods; using charged particle, e.g. electron, beams or X-rays
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
- G01R31/1227—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00001—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by the display of information or by user interaction, e.g. supervisory control and data acquisition systems [SCADA] or graphical user interfaces [GUI]
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00032—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
Abstract
The invention discloses an intelligent monitoring system and method for safety of power equipment based on the Internet of things, which are characterized in that different power equipment share the same partial discharge sensing device, different partial discharge sensing devices are additionally arranged, the partial discharge sensing devices are used as bands to divide the power equipment into different equipment sets, and the power equipment sets interact with edge computing equipment corresponding to the power equipment sets respectively. Therefore, the control cost can be controlled under the condition of timely and accurately mastering the field condition, the data transmission burden is reduced, and the reliability of the overall operation of the system is improved. In addition, through controlling the binocular imaging equipment to detect different objects under different conditions, on one hand, the state of the sensing device is evaluated, and on the other hand, input data for training the neural network is enriched, so that the judgment of the partial discharge phenomenon is more accurate and predictive.
Description
Technical Field
The invention belongs to the application of the internet of things and edge computing technology in a smart grid, and particularly relates to a system and a method for intelligently monitoring the safety of power equipment in the grid.
Background
Currently, with the general increase of electricity demand, the increase of the number of electric power equipment, the increase of the workload and the increase of the capacity of the equipment have become a necessary trend, and the electric power equipment is exposed to the environment to continuously operate, and the insulation degradation is caused by the thermal effect caused by the temperature increase, the electric effect caused by the electric field concentration, the mechanical effect caused by the mechanical stress and the environmental effect caused by the time lapse, so that the partial discharge phenomenon occurs, and finally the electric power equipment malfunction or accident occurs.
Therefore, it is very important and necessary to detect abnormality of the power equipment, monitor the degree of insulation deterioration, and predict the maintenance period. Through measurement and monitoring of partial discharge, early warning and maintenance can be effectively carried out. For this purpose, partial discharge detection devices are provided in various kinds of power equipment in a power equipment system such as a high-voltage cable, a transformer, a GIS, a switch, a power receiving device, a high-voltage board, a low-voltage board, a motor control board, and a power distribution board, and the purpose is to cope with various emergency situations.
However, the existing safety monitoring system and method for electrical equipment have the following problems in terms of partial discharge detection: firstly, the existing partial discharge detection means is single, and the site condition can not be mastered timely and accurately; secondly, the existing technical scheme for detecting partial discharge by adopting various means is fixed in configuration and high in cost; thirdly, various sensing devices generate a large amount of data at any time, so that a large burden is brought to data transmission, and even phenomena of monitoring and untimely coping caused by data blocking occur; fourth, existing solutions often fail to evaluate the status of the various sensing devices themselves; fifth, the field-collected monitoring data has limited training effect on the neural network.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides an intelligent monitoring system and an intelligent monitoring method for safety of power equipment based on the Internet of things.
The invention provides an intelligent monitoring system for safety of electric equipment based on the Internet of things, which comprises first electric equipment, second electric equipment, a frequency sensor, edge computing equipment and a cloud server, wherein the first electric equipment is connected with the second electric equipment; at least one of the first power devices and at least one of the second power devices share one of the frequency sensors;
the frequency sensor is used for detecting the first power equipment in a matching way, and the frequency sensor is used for detecting the second power equipment in a matching way, wherein the first sensing device is different from the second sensing device.
Preferably, the first sensing device is binocular imaging equipment, and the second sensing device is a current sensor; wherein the current sensor is mounted on a ground line of the second electrical device.
Preferably, the binocular imaging device includes a visible light receiving module and an infrared light receiving module, and the binocular imaging device is capable of rotating to detect a plurality of the first power devices.
Preferably, the plurality of first power devices that can be detected by the same binocular imaging apparatus and the plurality of second power devices that respectively share the frequency sensor with the plurality of first power devices together form a device set.
Preferably, the data collected by the frequency sensor, the binocular image device and the current sensor corresponding to the plurality of first power devices and the plurality of second power devices in one device set are all transmitted to the same edge computing device.
Meanwhile, the invention also provides a monitoring method applied to the intelligent monitoring system for the safety of the electric equipment based on the Internet of things, which comprises the following steps:
s1: detecting high-frequency electromagnetic waves emitted by local discharge at a first power device and a second power device which are nearby and correspond to the frequency sensor through the frequency sensor;
s2: detecting a discharge current of the second power equipment in a pulse form due to partial discharge by a current sensor mounted on the second power equipment ground line;
s3: the edge computing equipment collects the positions and discharge signals of the frequency sensor and the current sensor, and extracts characteristic quantities from the signals;
s4: and the edge computing equipment performs pattern matching according to the characteristic quantity extracted in the step S3 and a corresponding training result set in the neural network model, starts remote alarm if the consistency of the characteristic patterns exceeds a set threshold value, and synchronously sends related data to a cloud server.
Preferably, after the step S4, the method further includes the steps of:
s5: when the edge computing equipment only collects the high-frequency electromagnetic wave discharge signal of the frequency sensor and does not collect the discharge current discharge signal of the current sensor, starting the binocular image equipment to rotate to the position aligned with the first power equipment corresponding to the frequency sensor;
s6: and the visible light receiving module and the infrared light receiving module of the binocular imaging equipment are used for simultaneously collecting the visible light signal and the infrared light signal at the first power equipment so as to respectively judge the luminescence and the temperature change caused by partial discharge.
Preferably, after the step S6, the method further includes the steps of:
s7: when the edge computing equipment only collects the discharge current discharge signal of the current sensor and does not collect the high-frequency electromagnetic wave discharge signal of the frequency sensor, starting binocular image equipment to rotate to the position, corresponding to the frequency sensor, of the first power equipment;
s8: and collecting visible light signals at the first power equipment through a visible light receiving module of the binocular imaging equipment so as to check the working state of the frequency sensor.
Preferably, in the step S8, a duration of the visible light receiving module of the binocular imaging apparatus for collecting the visible light signals at the first power apparatus is proportional to the number of the second power apparatuses corresponding to the frequency sensor.
Preferably, the data collected in the step S3 and the step S6 are used as an input layer of the neural network, so as to train the neural network.
Compared with the prior art, the intelligent monitoring scheme of the power equipment is improved, the same partial discharge sensing device is shared for different power equipment, different partial discharge sensing devices are additionally arranged, the power equipment is divided into different equipment sets by taking the partial discharge sensing devices as ties, and the power equipment sets interact with the corresponding edge computing equipment respectively. Therefore, the control cost can be controlled under the condition of timely and accurately mastering the field condition, the data transmission burden is reduced, and the reliability of the overall operation of the system is improved. In addition, through controlling the binocular imaging equipment to detect different objects under different conditions, on one hand, the state of the sensing device is evaluated, and on the other hand, input data for training the neural network is enriched, so that the judgment of the partial discharge phenomenon is more accurate and predictive.
Drawings
FIG. 1 is a diagram of an intelligent monitoring system architecture for electrical equipment security according to the present invention;
FIG. 2 is a signal processing circuit of the visible light receiving module of the present invention;
fig. 3 is a schematic flow chart of the intelligent monitoring method for safety of electric power equipment.
Reference numerals illustrate: the light-sensitive light-receiving device comprises a photosensitive light-receiving element 1, a series resistor 2, a direct current amplifier 3, a first parallel resistor 4, a coupling capacitor 5, a second parallel resistor 6, a notch filter 7, a low-pass filter 8, a pulse shaping circuit 9 and a buffer circuit 10.
Detailed Description
The techniques described below are susceptible to various modifications and alternative embodiments, and are described in detail herein with reference to the accompanying drawings. However, this is not meant to limit the techniques described below to particular embodiments. It should be understood that the invention includes all similar modifications, equivalents and alternatives falling within the spirit and scope of the techniques described below.
1-3, the invention provides an intelligent power equipment safety monitoring system based on the Internet of things, which comprises a first power equipment, a second power equipment, a frequency sensor, edge computing equipment and a cloud server; at least one of the first power devices and at least one of the second power devices share one of the frequency sensors;
the frequency sensor is used for detecting the first power equipment in a matching way, and the frequency sensor is used for detecting the second power equipment in a matching way, wherein the first sensing device is different from the second sensing device.
The detection of whether nearby power equipment releases high-frequency wireless electromagnetic waves due to the occurrence of partial discharge by a frequency sensor is a means conventionally used at present. However, this noncontact method requires a sufficiently close judgment object, otherwise it is difficult to ensure accuracy. Too close a distance, however, also presents safety concerns.
On the basis of sharing one frequency sensor for a plurality of electric devices, namely not excessively increasing the number of the frequency sensors, the invention further configures different first sensing devices and second sensing devices for different electric devices, and further increases the accuracy of detection and judgment. Furthermore, in consideration of high integration level of some power equipment and the fact that the peripheral casing (such as GIS) is exposed, the plurality of power equipment can be detected respectively in different time periods by using the same sensing device through the optical detection means, so that the first sensing device is different from the second sensing device.
The first sensing device is binocular imaging equipment, and the second sensing device is a current sensor; still further, the current sensor is mounted on a ground line of the second electrical device.
The object which cannot be detected or is inconvenient to detect by the optical detection means can be directly connected with the current sensor on the grounding wire, and the contact detection method has high precision and quick response; the optical detection means such as binocular imaging equipment has the advantages of no limitation of distance, no need of modifying the power equipment, flexible detection means, one-to-many implementation and the like.
The binocular imaging equipment comprises a visible light receiving module and an infrared light receiving module, and the binocular imaging equipment can rotate to detect a plurality of first power equipment.
The visible light receiving module can receive the light signal generated during discharge under the condition of ensuring a sufficient safety distance, and is easy to acquire the required signal intensity.
As shown in fig. 2, the signal processing circuit of the visible light receiving module includes a photosensitive light receiving element 1, a series resistor 2, a dc amplifier 3, a first parallel resistor 4, a coupling capacitor 5, a second parallel resistor 6, a notch filter 7, a low-pass filter 8, a pulse shaping circuit 9, and a buffer circuit 10. The photosensitive light receiving element 1 is connected in series with the series resistor 2, one end of the series resistor 2 is grounded, the other end of the series resistor is connected with the input end of the direct current amplifier 3, the output end of the direct current amplifier 3 is connected with one end of the first parallel resistor 4 and one end of the coupling capacitor 5, the other end of the first parallel resistor 4 is grounded, the other end of the coupling capacitor 5 is connected with one end of the second parallel resistor 6, and the other end of the second parallel resistor 6 is grounded. One end of the coupling capacitor 5, which is connected with the second parallel resistor, is used as an output signal end, and is sequentially connected with the notch filter 7, the low-pass filter 8, the pulse shaping circuit 9 and the buffer circuit 10.
After the infrared light signals collected by the infrared light receiving module are amplified, filtered and analog-to-digital converted, a temperature change trend curve is generated by combining the charge quantity and the frequency of the discharge signals collected by the visible light receiving module, so that the temperature change trend curve is used as one of the bases for judging partial discharge.
The first power devices and the second power devices respectively sharing the frequency sensor with the first power devices can be detected by the same binocular imaging device to form a device set.
The frequency sensor, the binocular image equipment and the data acquired by the current sensor, which are corresponding to the first power equipment and the second power equipment, are all transmitted to the same edge computing equipment.
That is, through the one-to-many detection function of the binocular imaging device, the association between a plurality of first power devices is established, and the association between each first power device and the corresponding second power device is established through the frequency sensor, so that a device set is formed, and the collection and preprocessing of the related data of the power devices are completed through the same edge computing device. The architecture can greatly relieve the data transmission burden of the whole system, and can realize the regulation and control of each frequency sensor, binocular image equipment and current sensor in a local range more flexibly and timely.
Meanwhile, the invention also provides a monitoring method applied to the intelligent monitoring system for the safety of the electric equipment based on the Internet of things, which comprises the following steps:
s1: detecting high-frequency electromagnetic waves emitted by local discharge at a first power device and a second power device which are nearby and correspond to the frequency sensor through the frequency sensor;
s2: detecting a discharge current of the second power equipment in a pulse form due to partial discharge by a current sensor mounted on the second power equipment ground line;
s3: the edge computing equipment collects the positions and discharge signals of the frequency sensor and the current sensor, and extracts characteristic quantities from the signals;
s4: and the edge computing equipment performs pattern matching according to the characteristic quantity extracted in the step S3 and a corresponding training result set in the neural network model, starts remote alarm if the consistency of the characteristic patterns exceeds a set threshold value, and synchronously sends related data to a cloud server.
In general, when the frequency sensor and the current sensor both collect abnormal signals, it can be determined that the corresponding second power device is partially discharged. The local discharge of the power equipment is characterized differently in consideration of the environmental differences of the power equipment which is positioned in different areas and belongs to different equipment sets and the differences of the types and the working strengths of the power equipment, so that the neural network models of the preferred different edge computing equipment are different.
Wherein, after the step S4, the method further comprises the following steps:
s5: when the edge computing equipment only collects the high-frequency electromagnetic wave discharge signal of the frequency sensor and does not collect the discharge current discharge signal of the current sensor, starting the binocular image equipment to rotate to the position aligned with the first power equipment corresponding to the frequency sensor;
s6: and the visible light receiving module and the infrared light receiving module of the binocular imaging equipment are used for simultaneously collecting the visible light signal and the infrared light signal at the first power equipment so as to respectively judge the luminescence and the temperature change caused by partial discharge.
The frequency sensor serves as both a partial discharge detection means and a judgment means. That is, if only the frequency sensor collects the discharge signal and the current sensor does not collect the discharge signal, it is basically estimated that the first power device has partial discharge. In this case, the binocular imaging apparatus is mobilized to monitor the corresponding first power apparatus without the binocular imaging apparatus working at the moment.
Wherein, after the step S6, the method further comprises the following steps:
s7: when the edge computing equipment only collects the discharge current discharge signal of the current sensor and does not collect the high-frequency electromagnetic wave discharge signal of the frequency sensor, starting binocular image equipment to rotate to the position, corresponding to the frequency sensor, of the first power equipment;
s8: and collecting visible light signals at the first power equipment through a visible light receiving module of the binocular imaging equipment so as to check the working state of the frequency sensor.
For the case where the current sensor collects the discharge signal and the frequency sensor does not respond, it is highly likely that the frequency sensor has failed. In this case, the binocular imaging apparatus may be directly invoked to continuously collect the visible light signal at the first power apparatus corresponding to the frequency sensor. The first power device and the second power device sharing the same frequency sensor are closer in physical distance, and in general, when the current sensor detects that the second power device is partially discharged, there is a greater possibility that partial discharge occurs at least in the vicinity of the first power device and is captured by the visible light receiving module of the binocular imaging device. Therefore, by continuously collecting the visible light signal at the first power device, after the visible light signal with the partial discharge characteristic is collected, if the frequency sensor is continuously unresponsive, it can be basically determined that the frequency sensor at the location has indeed failed.
In the step S8, a duration of the visible light receiving module of the binocular imaging device for collecting the visible light signals at the first power device is proportional to the number of the second power devices corresponding to the frequency sensor.
The frequency sensor can only monitor in a short distance, so that the more second power equipment corresponding to the same frequency sensor, the more power equipment in the area belongs to the core node, and the greater the probability and the severity of the consequences of partial discharge. It is therefore also particularly necessary to enhance the continuous monitoring of the status of the frequency sensor itself.
The data collected in the step S3 and the step S6 are used as an input layer of the neural network, so as to train the neural network.
The training of the neural network by using the data collected in the step S3 and the step S6 as the input layer of the neural network specifically includes:
sa: extracting kurtosis of the discharge signal acquired by the frequency sensor as a first characteristic quantity;
sb: extracting a mean value of the spectrum amplitude of the discharge signal acquired by the frequency sensor as a second characteristic quantity;
sc: extracting kurtosis of the discharge signal acquired by the current sensor as a third feature quantity;
sd: extracting a mean value of the spectrum amplitude of the discharge signal acquired by the current sensor as a fourth feature quantity;
on the basis, the first power equipment and the second power equipment sharing the same frequency sensor are considered to be relatively close in physical distance, the working environment is basically consistent, namely the first power equipment and the second power equipment sharing the same frequency sensor have certain correlation, so that the relation between the visible light signals and infrared signals acquired by the binocular image equipment and the actual running condition of the first power equipment can be further analyzed, the relation is used as priori data and is input into the neural network in the form of additional parameters, training data of the neural network is enriched, the training effect is improved, and the accuracy of diagnosis and prognosis of the second power equipment is improved.
While the invention has been described in detail in connection with the general description and the specific embodiments thereof, modifications and improvements may be made thereto. The above description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the invention, but other variations and modifications can be made by those skilled in the art without departing from the spirit and scope of the invention.
Claims (6)
1. A monitoring method of an intelligent monitoring system for safety of electric equipment based on the Internet of things is characterized in that,
the monitoring system includes:
the cloud server comprises first power equipment, second power equipment, a frequency sensor, edge computing equipment and a cloud server; at least one of the first power devices and at least one of the second power devices share one of the frequency sensors;
the device also comprises a first sensing device for detecting the first power equipment in cooperation with the frequency sensor and a second sensing device for detecting the second power equipment in cooperation with the frequency sensor, wherein the first sensing device is binocular image equipment, and the second sensing device is a current sensor;
wherein the current sensor is mounted on a ground line of the second electrical device;
the binocular image equipment comprises a visible light receiving module and an infrared light receiving module, and can rotate to detect a plurality of first power equipment;
the monitoring method comprises the following steps:
s1: detecting high-frequency electromagnetic waves emitted by local discharge at a first power device and a second power device which are nearby and correspond to the frequency sensor through the frequency sensor;
s2: detecting a discharge current of the second power equipment in a pulse form due to partial discharge by a current sensor mounted on the second power equipment ground line;
s3: the edge computing equipment collects the positions and discharge signals of the frequency sensor and the current sensor, and extracts characteristic quantities from the signals;
s4: the edge computing equipment performs pattern matching according to the feature quantity extracted in the step S3 and a corresponding training result set in the neural network model, if the feature pattern consistency exceeds a set threshold value, remote alarm is started, and related data are synchronously sent to a cloud server;
s5: when the edge computing equipment only collects the high-frequency electromagnetic wave discharge signal of the frequency sensor and does not collect the discharge current discharge signal of the current sensor, starting the binocular image equipment to rotate to the position aligned with the first power equipment corresponding to the frequency sensor;
s6: and the visible light receiving module and the infrared light receiving module of the binocular imaging equipment are used for simultaneously collecting the visible light signal and the infrared light signal at the first power equipment so as to respectively judge the luminescence and the temperature change caused by partial discharge.
2. The monitoring method according to claim 1, further comprising the step of, after said step S6:
s7: when the edge computing equipment only collects the discharge current discharge signal of the current sensor and does not collect the high-frequency electromagnetic wave discharge signal of the frequency sensor, starting binocular image equipment to rotate to the position, corresponding to the frequency sensor, of the first power equipment;
s8: and collecting visible light signals at the first power equipment through a visible light receiving module of the binocular imaging equipment so as to check the working state of the frequency sensor.
3. The method according to claim 2, wherein in the step S8, the duration of the acquisition of the visible light signal by the visible light receiving module of the binocular imaging apparatus is proportional to the number of the second power apparatuses corresponding to the frequency sensor.
4. A monitoring method according to claim 3, wherein the data collected in step S3 and step S6 are used as input layers of the neural network for training the neural network.
5. The monitoring method according to claim 1, wherein the plurality of first power devices that can be detected by the same binocular imaging apparatus and the plurality of second power devices that respectively share the frequency sensor with the plurality of first power devices together constitute a device set.
6. The method of claim 5, wherein the data collected by the frequency sensor, the binocular imaging device, and the current sensor corresponding to the plurality of first power devices and the plurality of second power devices are transmitted to a same edge computing device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310462642.2A CN116488343B (en) | 2023-04-26 | 2023-04-26 | Intelligent power equipment safety monitoring system and method based on Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310462642.2A CN116488343B (en) | 2023-04-26 | 2023-04-26 | Intelligent power equipment safety monitoring system and method based on Internet of things |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116488343A CN116488343A (en) | 2023-07-25 |
| CN116488343B true CN116488343B (en) | 2023-10-27 |
Family
ID=87226552
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310462642.2A Active CN116488343B (en) | 2023-04-26 | 2023-04-26 | Intelligent power equipment safety monitoring system and method based on Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116488343B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104407277A (en) * | 2014-11-08 | 2015-03-11 | 莆田学院 | Dual-band ultraviolet video multi-information fusion-based partial discharge monitoring device and detection method |
| CN108459244A (en) * | 2018-01-31 | 2018-08-28 | 天津大学 | Based on UHF and the united power cable partial discharge detecting systems of HFCT |
| CN112684293A (en) * | 2020-12-25 | 2021-04-20 | 国网青海省电力公司 | Power distribution system insulation fault diagnosis device |
-
2023
- 2023-04-26 CN CN202310462642.2A patent/CN116488343B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104407277A (en) * | 2014-11-08 | 2015-03-11 | 莆田学院 | Dual-band ultraviolet video multi-information fusion-based partial discharge monitoring device and detection method |
| CN108459244A (en) * | 2018-01-31 | 2018-08-28 | 天津大学 | Based on UHF and the united power cable partial discharge detecting systems of HFCT |
| CN112684293A (en) * | 2020-12-25 | 2021-04-20 | 国网青海省电力公司 | Power distribution system insulation fault diagnosis device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116488343A (en) | 2023-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104990629B (en) | A kind of electrical equipment fault automatic early-warning system of infrared imaging temperature measuring | |
| CN109142904B (en) | Image recognition-based fault monitoring method and device for direct-current transmission converter valve | |
| CN104977087B (en) | A kind of method of the electrical equipment fault automatic early-warning based on infrared imaging temperature measuring | |
| CN111190065A (en) | Non-contact on-line monitoring system for power equipment | |
| CN110690763A (en) | Intelligent monitoring device and monitoring method for electric power system | |
| CN103674286A (en) | In-station communication device fault diagnosis method based on infrared image | |
| CN113467433A (en) | Method and device for detecting faults of mechanical equipment | |
| CN102545152B (en) | A kind of Intelligent surge protector monitoring system | |
| CN106872070A (en) | A kind of optical fiber composite cable expert diagnostic system based on many reference amounts | |
| CN210629196U (en) | Intelligent monitoring device for electric power system | |
| CN111899211A (en) | Transformer oil leakage fault detection system and method based on images and smell | |
| CN108986420A (en) | A kind of power distribution cabinet monitoring alarm system | |
| CN201490710U (en) | Intelligent monitoring type surge protector | |
| CN116488343B (en) | Intelligent power equipment safety monitoring system and method based on Internet of things | |
| CN116723211B (en) | Remote inspection device for large-space environment power equipment | |
| CN102185385A (en) | System and method thereof for detecting physical on/off state of power protection circuit | |
| CN104485991A (en) | Optical module fault automatic alarm method and system | |
| CN203855261U (en) | Real-time monitoring system for elevator running | |
| CN203337286U (en) | Optical-fiber on-line temperature measuring system dedicated for electric power contacts | |
| CN109856495A (en) | A kind of portable cable inspection earthing state assisted detection system and method | |
| CN206470340U (en) | Power quality monitoring system | |
| CN115524569A (en) | Fault diagnosis method, device and system | |
| CN115061012A (en) | Intelligent monitoring and diagnosing system and method based on edge computing power supply grid | |
| CN110702973A (en) | Online measuring device for induced voltage of cable sheath | |
| CN103869772A (en) | Monitoring system for environment of internet of things of transformer substation |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |