CN117110812A - Method for collecting ultrahigh frequency partial discharge signals in switch cabinet room - Google Patents
Method for collecting ultrahigh frequency partial discharge signals in switch cabinet room Download PDFInfo
- Publication number
- CN117110812A CN117110812A CN202311092009.5A CN202311092009A CN117110812A CN 117110812 A CN117110812 A CN 117110812A CN 202311092009 A CN202311092009 A CN 202311092009A CN 117110812 A CN117110812 A CN 117110812A
- Authority
- CN
- China
- Prior art keywords
- sound
- partial discharge
- switch cabinet
- collecting
- ultrahigh frequency
- 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
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000012423 maintenance Methods 0.000 claims abstract description 33
- 230000005236 sound signal Effects 0.000 claims abstract description 31
- 238000013135 deep learning Methods 0.000 claims abstract description 28
- 230000002159 abnormal effect Effects 0.000 claims abstract description 25
- 238000012545 processing Methods 0.000 claims abstract description 22
- 238000005516 engineering process Methods 0.000 claims abstract description 3
- 238000013527 convolutional neural network Methods 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 125000004122 cyclic group Chemical group 0.000 claims description 6
- 230000035945 sensitivity Effects 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000013500 data storage Methods 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 claims description 3
- 238000013136 deep learning model Methods 0.000 claims description 2
- 238000000605 extraction Methods 0.000 claims description 2
- 238000001228 spectrum Methods 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 abstract description 10
- 238000007689 inspection Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 3
- 238000009413 insulation Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 230000032683 aging Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- 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
- G01R31/1209—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 acoustic measurements
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Testing Relating To Insulation (AREA)
Abstract
The invention relates to the technical field of partial discharge signal acquisition, and discloses a method for acquiring an ultrahigh frequency partial discharge signal in a switch cabinet room, wherein the method for acquiring the ultrahigh frequency partial discharge signal in the switch cabinet room comprises the following steps of: s1, arranging a sound sensor inside a switch cabinet; s2, continuously collecting sound signals received from the sound sensor; s3, running a deep learning voice recognition model in the embedded processing unit; s4, analyzing and classifying the sound signals by using a deep learning sound recognition model; and S5, matching the collected sound with a sound mode in a sound fingerprint library by adopting a data matching technology. The invention can detect abnormal sound modes in time through the deep learning sound recognition model, reduces the manual operation and maintenance cost, improves the monitoring efficiency, provides high accuracy and expandability, reduces the false alarm rate and is suitable for different types of equipment and environments.
Description
Technical Field
The invention relates to the technical field of partial discharge signal acquisition, in particular to a method for acquiring an ultrahigh frequency partial discharge signal in a switch cabinet.
Background
At present, in a power system, equipment such as a switch cabinet and the like can generate partial discharge phenomena with different degrees due to aging of insulation in a long-time operation process, and partial discharge PD is discharge generated on an insulated partial area between two conductive electrodes, and a gap is not completely closed;
this may be due to discontinuities or defects in the insulation system, the intensity of these discharges is often very small, but they can accelerate insulation aging and eventually lead to serious short-circuit faults;
therefore, the existing monitoring device for partial discharge is often installed in the switch cabinet to monitor and collect related signals, so that the position of the partial discharge can be perceived at the first time, and related maintenance can be timely carried out.
However, the existing method for collecting the ultrahigh frequency partial discharge signal in the switch cabinet room has at least the following defects:
1. the prior art generally relies on periodic inspection and periodic inspection to monitor the status of the equipment, or requires contact installation inspection with high voltage components, which can lead to problems being ignored or discovered when developing into a severe phase, and also increases the risk of equipment damage and maintenance;
2. the traditional monitoring method requires manual intervention and data analysis, and maintenance personnel are required to periodically patrol equipment. The method is time-consuming and labor-consuming, and is easy to cause human errors;
3. some existing monitoring techniques are prone to false positives because they are difficult to distinguish between real problems and noise interference, which can result in unnecessary downtime and maintenance, wasting resources.
Therefore, we propose a method for collecting the ultra-high frequency partial discharge signal in the switch cabinet.
Disclosure of Invention
The invention aims to provide a method for collecting ultrahigh frequency partial discharge signals in a switch cabinet room, which can immediately detect an abnormal sound mode through a deep learning sound identification model, avoid neglecting and severity of problems, reduce manual operation and maintenance cost by automatic and remote access, improve monitoring efficiency, enable maintenance personnel to remotely access equipment states, reduce inspection work, and most importantly, provide high accuracy and expandability, reduce false alarm rate, be suitable for different types of equipment and environments, help to improve equipment reliability, reduce maintenance cost, reduce potential risks and losses and solve the problems in the background art.
In order to achieve the above purpose, the present invention provides the following technical solutions: the method for collecting the ultrahigh frequency partial discharge signals in the switch cabinet room comprises the following steps of:
s1, arranging a sound sensor in a switch cabinet, wherein the sound sensor has high sensitivity and is calibrated regularly to capture sound signals emitted from the switch cabinet;
s2, continuously collecting sound signals received from the sound sensor and converting the sound signals into digital sound data;
s3, running a deep learning voice recognition model in the embedded processing unit, wherein the deep learning voice recognition model is based on a convolutional neural network and a cyclic neural network and is used for processing and analyzing voice signals in real time;
s4, analyzing and classifying the sound signals by using a deep learning sound recognition model to distinguish partial discharge sound modes from environmental noise;
s5, matching the collected sound with sound modes in a sound fingerprint library by adopting a data matching technology so as to detect any abnormal sound which is not matched with the known partial discharge sound mode;
s6, when an abnormal sound mode is detected, triggering an alarm, wherein the alarm information comprises time and frequency characteristics of the abnormal sound and the position in the switch cabinet;
s7, uploading the collected sound data, the identification result and the alarm information to a cloud server for remote access and data storage;
and S8, automatically generating a maintenance report based on the identification result and the alarm information, wherein the maintenance report comprises the nature, the position, the possible reasons and the suggested maintenance steps of the abnormal sound.
As a preferred embodiment of the present invention, the acoustic sensor employs an acoustic sensor module that is calibrated by zero to eliminate deviation, thereby ensuring high sensitivity and reliability.
As a preferred embodiment of the present invention, the deep learning voice recognition model employs a convolutional neural network for spectral feature extraction, and a cyclic neural network for modeling timing information of a voice signal.
As a preferred embodiment of the present invention, the acoustic fingerprint library stores known acoustic patterns of various devices, which are periodically updated and maintained to maintain accuracy.
As a preferred embodiment of the invention, the embedded processing unit is provided with hardware accelerator support, including a graphics processing unit to improve the performance and speed of the deep learning model.
As a preferred embodiment of the invention, the maintenance report comprises a severity level of the abnormal sound, wherein the level comprises low, medium, high, and recommended maintenance operations.
As a preferred embodiment of the present invention, the collected sound data is compressed and encrypted to ensure the security of data transmission.
As a preferred embodiment of the present invention, the deep learning voice recognition model can automatically adapt to a new voice pattern without requiring manual retraining.
As a preferred implementation mode of the invention, the collected sound data and alarm information are pushed to the user in real time through the mobile phone application program, so that the user can respond to abnormal conditions in time.
Compared with the prior art, the invention has the following beneficial effects:
1. according to the method for collecting the ultrahigh frequency partial discharge signal in the switch cabinet, the sound sensor can monitor the sound signal in the switch cabinet in real time, including partial discharge sound, and the abnormal sound mode can be timely detected through the deep learning sound recognition model, so that the problem can be found and processed in early stage, potential faults or accidents can be avoided, the reliability and safety of equipment are improved, and the contactless installation and use can be realized.
2. According to the method for collecting the ultrahigh frequency partial discharge signal in the switch cabinet room, the embedded processing unit and cloud connection are utilized, so that automatic collection, analysis and uploading of data are realized, maintenance personnel can monitor the state of equipment by remotely accessing the cloud server without having to visit the site, the efficiency of equipment monitoring is improved, timely measures are allowed to be taken, and the maintenance cost and the downtime are reduced.
3. According to the method for collecting the ultrahigh frequency partial discharge signal in the switch cabinet room, the voice signal mode including partial discharge voice can be identified with high accuracy through deep learning of the voice identification model, the accuracy enables the system to be hardly misreported, the monitoring reliability is improved, in addition, the technical scheme can be expanded to different types of equipment and environments, the method is suitable for multiple industries and application fields, and wide applicability and customization are achieved.
Drawings
For a more clear description of the technical solutions of the embodiments of the present invention, reference will now be made to the following detailed description of non-limiting embodiments, with reference to the accompanying drawings, in which it is apparent that the drawings used in the following description are only some embodiments of the present invention, and from which other drawings can be obtained without inventive effort to a person skilled in the art.
Fig. 1 is a schematic flow structure diagram of a method for collecting ultrahigh frequency partial discharge signals in a switch cabinet room.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the present invention provides a technical solution: a method for collecting ultrahigh frequency partial discharge signals in a switch cabinet room comprises the following steps:
deployment of sound sensor: a highly sensitive sound sensor is deployed in the switchgear cabinet, which may take the form of a microphone or a sound sensor module, the sensor being arranged inside the switchgear cabinet, with particular attention being paid to the point of occurrence of the potential partial discharge.
In this embodiment, the acoustic sensor is used as a sensor for converting acoustic pressure fluctuations into electrical signals, and includes an acoustic sensitive element, such as a microphone or a piezoelectric sensor, which generates a corresponding electrical signal reflecting the amplitude and frequency of the sound when the acoustic fluctuations enter the switch cabinet and hit the sensor.
Collecting real-time sound signals: the sound sensor continuously collects ambient sound and partial discharge sound and converts the sound signal into a digital signal.
In this embodiment, the sound signal captured by the sensor is an analog signal, and needs to be converted into a digital signal by an analog-to-digital converter (ADC), and the sampling rate determines the number of samples collected per second, usually in units of hertz (Hz), so that the resolution of the sound signal can be improved with a higher sampling rate.
An embedded processing unit: the embedded processing unit is a small computing device and is provided with a deep learning voice recognition algorithm. The sound signal is transmitted to the embedded processing unit through the sensor interface.
In this embodiment, the embedded processing unit includes one or more processors and memory for running a deep learning algorithm.
The deep learning voice recognition algorithm is a neural network model that analyzes a voice signal through a Convolutional Neural Network (CNN) and a cyclic neural network (RNN) or the like. These network layers may extract features in the sound signal, such as spectrum, time domain information, etc.
Deep learning voice recognition: the deep learning voice recognition model is trained to recognize partial discharge voice patterns and ambient noise.
In this embodiment, the deep learning voice recognition model is trained based on the labeled voice data set.
During training, the model learning identifies patterns of partial discharge sounds, including their spectral features and timing information. Once trained, the model may classify the sound signals in a real-time environment.
Abnormality detection and alarm triggering: algorithms are implemented within the embedded processing unit to compare the sound collected in real-time to the sound patterns in the sound fingerprint library.
In this embodiment, the abnormal sound is detected by comparing the sound signal collected in real time with the sound pattern in the sound fingerprint library using a pattern matching technique (such as correlation analysis or feature matching). If a sound is detected that does not match the known partial discharge sound pattern, an alarm is triggered.
Data upload and remote access: the collected sound data can be uploaded to a cloud server or a local server through internet connection.
In this embodiment, the voice data is transmitted using a security protocol, such as HTTPS, to ensure confidentiality of the data transmission. The data is stored on the server and can be accessed anytime and anywhere through a Web interface or a mobile phone application.
Automatically generating a maintenance report: when an abnormal sound is identified, the system automatically generates a maintenance report including information on the location, severity, etc. of the problem.
In the present embodiment, the maintenance report is generated based on the identification result and the alarm information. The method can comprise the characteristics of sound signals, the frequency distribution and intensity of sound and detailed information related to partial discharge, and can automatically classify from light to heavy according to the severity of abnormal sound, wherein the classes comprise low, medium and high, so that fault points with higher classes can be processed in time, and related recommended maintenance operations can be automatically generated to help maintenance personnel to know the nature of the problem.
Example 1
Abnormality monitoring of a piezoelectric power device
The sound signal is monitored in real time by deploying a sound sensor, including a microphone and a sound sensor module, within a high voltage power device, such as a transformer or a switch cabinet.
In this embodiment, the sound signal within the device is first continuously acquired by the sound sensor, digitized and transmitted to the embedded processing unit.
The deep learning voice recognition model analyzes voice in real time and detects partial discharge voice patterns.
If an abnormal sound is detected, the system triggers an alarm while recording the location and severity of the problem.
And uploading the data to a cloud server, and automatically generating a maintenance report.
Example two
Device health monitoring in manufacturing
In a manufacturing environment, acoustic sensors may be placed alongside various machines and equipment on a production line to monitor their operating status in real time.
In this embodiment, the sound signals generated by the machine and the device are first captured by the sound sensor, digitized and transmitted to the embedded processing unit.
The deep learning voice recognition model may recognize voice patterns in various operating states.
If an abnormal sound occurs, the system will trigger an alarm and generate a maintenance report to provide maintenance guidance.
Example III
Remote monitoring of an electric power distribution network
In an electrical power distribution network, sound sensors may be deployed in a distributed manner, monitoring the sound signals of substations, switchgears and cabling.
In this embodiment, the sound signals of each site are collected through the sensor network, and the data are transmitted to the central server for processing.
The deep learning voice recognition model analyzes the voice signal and detects partial discharge or other abnormal sounds.
If a problem is detected, the system will alert while providing information on the location and severity of the problem for the operation and maintenance personnel to take timely action.
Working principle: firstly, sound sensors, which may be microphones or sound sensor modules, are arranged in the switch cabinet to be monitored, which are distributed at key locations in the switch cabinet to capture sound signals from different areas, the sound sensors continuously collect sound signals from the switch cabinet and convert the signals into digitized data, which sound signals include sound from equipment operation, partial discharge or other potential problems, the collected sound data are transmitted to an embedded processing unit, which is a small computing device, usually equipped with a deep learning sound recognition algorithm, the embedded processing unit is responsible for analyzing the sound signals in real time, then a deep learning sound recognition model is run in the embedded processing unit, which model is based on a convolutional neural network and a cyclic neural network for processing and analyzing the sound signals, the model can identify partial discharge sound patterns and environmental noise by learning training data of known sound patterns, while the deep-learning sound identification model analyzes and classifies sound signals collected in real time, if the model detects abnormal sounds which do not match the known partial discharge sound patterns, the system will trigger alarms including time, frequency characteristics of the abnormal sounds and positions occurring in the switch cabinet, the collected sound data, identification results and alarm information are uploaded to a cloud server for remote access and data storage, which allows maintenance personnel to monitor the status of the equipment at any time and any place without going to the spot, when the abnormal sounds occur, the system automatically generates maintenance reports including the nature, position, possible causes and suggested maintenance steps of the abnormal sounds, allowing its maintenance personnel to respond to the problem faster and take appropriate action.
The invention relates to a method for collecting ultrahigh frequency partial discharge signals in a switch cabinet room, which comprises the following steps of adopting a general standard component or a component known by a person skilled in the art, and adopting a structure and a principle known by the person skilled in the art through a technical manual or a routine experimental method.
Claims (9)
1. The method for collecting the ultrahigh frequency partial discharge signal in the switch cabinet room is characterized by comprising the following steps of:
s1, arranging a sound sensor in a switch cabinet, wherein the sound sensor has high sensitivity and is calibrated regularly to capture sound signals emitted from the switch cabinet;
s2, continuously collecting sound signals received from the sound sensor and converting the sound signals into digital sound data;
s3, running a deep learning voice recognition model in the embedded processing unit, wherein the deep learning voice recognition model is based on a convolutional neural network and a cyclic neural network and is used for processing and analyzing voice signals in real time;
s4, analyzing and classifying the sound signals by using a deep learning sound recognition model to distinguish partial discharge sound modes from environmental noise;
s5, matching the collected sound with sound modes in a sound fingerprint library by adopting a data matching technology so as to detect any abnormal sound which is not matched with the known partial discharge sound mode;
s6, when an abnormal sound mode is detected, triggering an alarm, wherein the alarm information comprises time and frequency characteristics of the abnormal sound and the position in the switch cabinet;
s7, uploading the collected sound data, the identification result and the alarm information to a cloud server for remote access and data storage;
and S8, automatically generating a maintenance report based on the identification result and the alarm information, wherein the maintenance report comprises the nature, the position, the possible reasons and the suggested maintenance steps of the abnormal sound.
2. The method for collecting the ultrahigh frequency partial discharge signal in the switch cabinet room according to claim 1, wherein the method comprises the following steps: the sound sensor adopts a sound sensor module which eliminates deviation through zero point calibration, thereby ensuring high sensitivity and reliability.
3. The method for collecting the ultrahigh frequency partial discharge signal in the switch cabinet room according to claim 1, wherein the method comprises the following steps: the deep learning voice recognition model adopts a convolutional neural network for spectrum feature extraction, and simultaneously adopts a cyclic neural network for modeling time sequence information of a voice signal.
4. The method for collecting the ultrahigh frequency partial discharge signal in the switch cabinet room according to claim 1, wherein the method comprises the following steps: the acoustic fingerprint library stores known acoustic patterns for a variety of devices, which are periodically updated and maintained to maintain accuracy.
5. The method for collecting the ultrahigh frequency partial discharge signal in the switch cabinet room according to claim 1, wherein the method comprises the following steps: the embedded processing unit is provided with hardware accelerator support, including a graphics processing unit to improve the performance and speed of the deep learning model.
6. The method for collecting the ultrahigh frequency partial discharge signal in the switch cabinet room according to claim 1, wherein the method comprises the following steps: the maintenance report includes severity levels of abnormal sounds, wherein the levels include low, medium, high, and recommended maintenance operations.
7. The method for collecting the ultrahigh frequency partial discharge signal in the switch cabinet room according to claim 1, wherein the method comprises the following steps: the collected sound data is compressed and encrypted to ensure the safety of data transmission.
8. The method for collecting the ultrahigh frequency partial discharge signal in the switch cabinet room according to claim 1, wherein the method comprises the following steps: the deep learning voice recognition model can automatically adapt to a new voice mode without manual retraining.
9. The method for collecting the ultrahigh frequency partial discharge signal in the switch cabinet room according to claim 1, wherein the method comprises the following steps: the collected sound data and alarm information are pushed to a user in real time through a mobile phone application program, so that the user can respond to abnormal conditions in time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311092009.5A CN117110812A (en) | 2023-08-29 | 2023-08-29 | Method for collecting ultrahigh frequency partial discharge signals in switch cabinet room |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311092009.5A CN117110812A (en) | 2023-08-29 | 2023-08-29 | Method for collecting ultrahigh frequency partial discharge signals in switch cabinet room |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117110812A true CN117110812A (en) | 2023-11-24 |
Family
ID=88801720
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311092009.5A Pending CN117110812A (en) | 2023-08-29 | 2023-08-29 | Method for collecting ultrahigh frequency partial discharge signals in switch cabinet room |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117110812A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118566659A (en) * | 2024-05-21 | 2024-08-30 | 南京苏逸实业有限公司 | A monitoring device for switch cabinet discharge information, a fault determination method and a storage medium |
| CN119375642A (en) * | 2024-12-25 | 2025-01-28 | 昂顿科技（上海）有限公司 | A method and system for online monitoring of partial discharge of high-voltage switch cabinet |
-
2023
- 2023-08-29 CN CN202311092009.5A patent/CN117110812A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118566659A (en) * | 2024-05-21 | 2024-08-30 | 南京苏逸实业有限公司 | A monitoring device for switch cabinet discharge information, a fault determination method and a storage medium |
| CN119375642A (en) * | 2024-12-25 | 2025-01-28 | 昂顿科技（上海）有限公司 | A method and system for online monitoring of partial discharge of high-voltage switch cabinet |
| CN119375642B (en) * | 2024-12-25 | 2025-04-15 | 昂顿科技（上海）有限公司 | A method and system for online monitoring of partial discharge of high-voltage switch cabinet |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102604708B1 (en) | Switchboard diagnosis system based on artificial intelligence and switchboard diagnosis method based on artificial intelligence | |
| CN114167315A (en) | A kind of transformer intelligent online monitoring system and method | |
| CN117110812A (en) | Method for collecting ultrahigh frequency partial discharge signals in switch cabinet room | |
| CN110208022A (en) | Power equipment multiple features audio-frequency fingerprint fault diagnosis method and system based on machine learning | |
| CN117767570A (en) | Lightning protection screen and intelligent monitoring system and method thereof | |
| CN118114019A (en) | A method and system for automatic identification of distribution network topology based on data analysis | |
| CN119619703B (en) | A circuit short circuit fault monitoring system and method based on the Internet of Things | |
| CN118380013A (en) | A switch cabinet monitoring and fault diagnosis method based on voiceprint recognition technology | |
| CN103197206A (en) | Electrical level scanning type ultrahigh frequency partial discharge on-line monitoring system and monitoring method | |
| KR20210050274A (en) | Equipment failure prediction system and method | |
| CN110347717A (en) | A kind of big data storage method based on urban electric power equipment monitoring | |
| US12516976B2 (en) | Outdoor application of distributed fiber optic sensing / acoustic sensing | |
| KR20210077496A (en) | Equipment failure prediction system having multi-channel sensors for receiving acoustic signals in the ultrasonic band | |
| CN119202987A (en) | A bearing fault diagnosis method and device | |
| JP2002090412A (en) | Partial-discharge measuring apparatus | |
| CN111653291A (en) | Intelligent health monitoring method for power equipment based on voiceprint | |
| CN115077605A (en) | Intelligent substation management system | |
| CN120870947B (en) | Intelligent operation and maintenance fault early warning method for rail transit variable-frequency power supply | |
| CN120009720B (en) | GIS combined electrical apparatus abnormal sound voiceprint monitoring system | |
| CN119619769B (en) | A method and system for monitoring and early warning of partial discharge of high voltage circuit breaker | |
| CN120801847A (en) | Fault monitoring system for electromechanical installation engineering | |
| CN120577654A (en) | Warning location method based on partial discharge warning system of high-voltage switchgear | |
| CN117857601A (en) | Safety monitoring and preventing system | |
| KR102922586B1 (en) | System and method for diagnosing fault of switchboard based on multi ai | |
| KR20210060049A (en) | Equipment failure prediction system and method using sound signal of ultrasonic band |
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 |