CN117148076A - Multi-feature fusion type high-voltage switch cabinet partial discharge identification method and system - Google Patents
Multi-feature fusion type high-voltage switch cabinet partial discharge identification method and system Download PDFInfo
- Publication number
- CN117148076A CN117148076A CN202311422063.1A CN202311422063A CN117148076A CN 117148076 A CN117148076 A CN 117148076A CN 202311422063 A CN202311422063 A CN 202311422063A CN 117148076 A CN117148076 A CN 117148076A
- Authority
- CN
- China
- Prior art keywords
- monitoring
- partial discharge
- cabinet
- identification
- voltage switch
- 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.)
- Granted
Links
- 230000004927 fusion Effects 0.000 title claims abstract description 93
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000012544 monitoring process Methods 0.000 claims abstract description 378
- 238000004458 analytical method Methods 0.000 claims abstract description 46
- 238000001514 detection method Methods 0.000 claims abstract description 18
- 230000035945 sensitivity Effects 0.000 claims description 24
- 238000005065 mining Methods 0.000 claims description 18
- 230000006698 induction Effects 0.000 claims description 15
- 230000007613 environmental effect Effects 0.000 claims description 14
- 238000004422 calculation algorithm Methods 0.000 claims description 11
- 238000010206 sensitivity analysis Methods 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 8
- 238000012512 characterization method Methods 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 abstract description 7
- 230000006870 function Effects 0.000 description 15
- 238000012545 processing Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000000354 decomposition reaction Methods 0.000 description 2
- 230000005684 electric field Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000001052 transient effect Effects 0.000 description 2
- 101000856246 Arabidopsis thaliana Cleavage stimulation factor subunit 77 Proteins 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013524 data verification Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 230000037361 pathway Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- LSJNBGSOIVSBBR-UHFFFAOYSA-N thionyl fluoride Chemical compound FS(F)=O LSJNBGSOIVSBBR-UHFFFAOYSA-N 0.000 description 1
- 238000011426 transformation method Methods 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
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Acoustics & Sound (AREA)
- Testing Relating To Insulation (AREA)
Abstract
The application discloses a multi-feature fusion high-voltage switch cabinet partial discharge identification method and a system, which relate to the technical field of power equipment detection, wherein the method comprises the following steps: obtaining a target voltage switch cabinet; obtaining a preset discharge monitoring ternary configuration; performing monitoring feature analysis on a target high-voltage switch cabinet, and constructing a cabinet body partial discharge monitoring sub-module comprising a plurality of partial discharge monitoring units; real-time monitoring is carried out on the target high-voltage switch cabinet based on the plurality of partial discharge monitoring units, and a plurality of real-time signal monitoring results are obtained; performing monitoring environment interference compensation fusion to obtain a plurality of characteristic fusion monitoring results; constructing a cabinet partial discharge recognition channel based on the partial discharge recognition sensitive analysis function; and based on the multiple feature fusion monitoring results, executing partial discharge identification of the target voltage switch cabinet according to the cabinet partial discharge identification channel to obtain a cabinet partial discharge identification report. The application has the technical effects of high recognition efficiency and good recognition accuracy and confidence.
Description
Technical Field
The application relates to the technical field of power equipment detection, in particular to a multi-feature fusion high-voltage switch cabinet partial discharge identification method and system.
Technical Field
The switch cabinet is widely applied to a power system and a power network and is used for controlling, distributing and protecting electric energy in the power system, and partial discharge is a common fault of the switch cabinet, which can cause damage to equipment and even cause dangerous situations such as fire or explosion. The degree of influence on the reliability of the switch cabinet is different due to different discharge amounts. The detection method of the partial discharge of the switch cabinet mainly comprises ultrasonic detection, ground wave detection and ultrahigh frequency detection. The existing partial discharge identification based on a single detection method or multiple monitoring methods has the technical problems of low identification efficiency and poor identification accuracy confidence.
Disclosure of Invention
The application aims to provide a multi-feature fusion high-voltage switch cabinet partial discharge identification method and system. The method is used for solving the technical problems of low recognition efficiency and poor recognition accuracy confidence in the prior art.
In view of the technical problems, the application provides a multi-feature fusion high-voltage switch cabinet partial discharge identification method and a multi-feature fusion high-voltage switch cabinet partial discharge identification system.
In a first aspect, the application provides a multi-feature fusion high-voltage switch cabinet partial discharge identification method, wherein the method comprises the following steps:
Obtaining a target voltage switch cabinet; obtaining a preset discharge monitoring ternary configuration, wherein the preset discharge monitoring ternary configuration comprises a plurality of cabinet discharge monitoring hardware, and the plurality of cabinet discharge monitoring hardware comprises ultrasonic monitoring hardware, pulse current monitoring hardware and gas monitoring hardware; based on a cabinet monitoring feature mining algorithm, monitoring feature analysis is carried out on the target high-voltage switch cabinet according to the preset discharge monitoring ternary configuration, and a cabinet partial discharge monitoring sub-module is built, wherein the cabinet partial discharge monitoring sub-module comprises a plurality of partial discharge monitoring units; real-time monitoring is carried out on the target high-voltage switch cabinet based on the plurality of partial discharge monitoring units, so that a plurality of real-time signal monitoring results are obtained, wherein each real-time signal monitoring result comprises an ultrasonic monitoring signal set, a pulse current monitoring signal set and a gas monitoring characteristic set; traversing the plurality of real-time signal monitoring results to carry out monitoring environment interference compensation fusion to obtain a plurality of characteristic fusion monitoring results; constructing a cabinet partial discharge recognition channel based on the partial discharge recognition sensitive analysis function; and executing partial discharge identification of the target high-voltage switch cabinet according to the cabinet partial discharge identification channel based on the characteristic fusion monitoring results to obtain a cabinet partial discharge identification report.
In a second aspect, the present application further provides a multi-feature fusion high-voltage switchgear partial discharge recognition system, where the system includes:
the target acquisition module is used for acquiring a target voltage switch cabinet; the system comprises a configuration acquisition module, a configuration detection module and a control module, wherein the configuration acquisition module is used for acquiring a preset discharge monitoring ternary configuration, the preset discharge monitoring ternary configuration comprises a plurality of cabinet discharge monitoring hardware, and the plurality of cabinet discharge monitoring hardware comprises ultrasonic monitoring hardware, pulse current monitoring hardware and gas monitoring hardware; the partial discharge monitoring configuration module is used for carrying out monitoring feature analysis on the target high-voltage switch cabinet according to the preset discharge monitoring ternary configuration based on a cabinet monitoring feature mining algorithm, and constructing a cabinet partial discharge monitoring sub-module, wherein the cabinet partial discharge monitoring sub-module comprises a plurality of partial discharge monitoring units; the real-time monitoring module is used for carrying out real-time monitoring on the target high-voltage switch cabinet based on the plurality of partial discharge monitoring units to obtain a plurality of real-time signal monitoring results, wherein each real-time signal monitoring result comprises an ultrasonic monitoring signal set, a pulse current monitoring signal set and a gas monitoring characteristic set; the feature fusion module is used for traversing the plurality of real-time signal monitoring results to carry out monitoring environment interference compensation fusion and obtain a plurality of feature fusion monitoring results; the identification construction module is used for constructing a cabinet partial discharge identification channel based on the partial discharge identification sensitive analysis function; and the partial discharge identification module is used for carrying out partial discharge identification of the target high-voltage switch cabinet according to the cabinet partial discharge identification channel based on the characteristic fusion monitoring results to obtain a cabinet partial discharge identification report.
One or more technical solutions provided in the embodiments of the present application at least have the following technical effects or advantages:
the target voltage switch cabinet is obtained; obtaining a preset discharge monitoring ternary configuration; based on a cabinet monitoring feature mining algorithm, monitoring feature analysis is carried out on a target high-voltage switch cabinet, and a cabinet partial discharge monitoring sub-module is built, wherein the cabinet partial discharge monitoring sub-module comprises a plurality of partial discharge monitoring units; real-time monitoring is carried out on the target high-voltage switch cabinet based on the plurality of partial discharge monitoring units, and a plurality of real-time signal monitoring results are obtained; traversing a plurality of real-time signal monitoring results to carry out monitoring environment interference compensation fusion to obtain a plurality of characteristic fusion monitoring results; constructing a cabinet partial discharge recognition channel based on the partial discharge recognition sensitive analysis function; and based on the multiple feature fusion monitoring results, executing partial discharge identification of the target voltage switch cabinet according to the cabinet partial discharge identification channel to obtain a cabinet partial discharge identification report. Thereby achieving the technical effects of high recognition efficiency and good recognition accuracy and confidence.
The foregoing description is only an overview of the present application, and is intended to more clearly illustrate the technical means of the present application, be implemented according to the content of the specification, and be more apparent in view of the above and other objects, features and advantages of the present application, as follows.
Drawings
Embodiments of the application and the following brief description are described with reference to the drawings, in which:
FIG. 1 is a schematic flow chart of a multi-feature fusion high-voltage switch cabinet partial discharge identification method of the application;
FIG. 2 is a schematic flow chart of a partial discharge recognition channel of a cabinet body constructed based on a partial discharge recognition sensitive analysis function in the multi-feature fusion high-voltage switch cabinet partial discharge recognition method of the application;
fig. 3 is a schematic structural diagram of a multi-feature fused high-voltage switchgear partial discharge recognition system of the present application.
Reference numerals illustrate: the system comprises a target acquisition module 11, a configuration acquisition module 12, a partial discharge monitoring configuration module 13, a real-time monitoring module 14, a feature fusion module 15, an identification construction module 16 and a partial discharge identification module 17.
Detailed Description
The application solves the technical problems of low recognition efficiency and poor recognition accuracy confidence in the prior art by providing the multi-feature fusion high-voltage switch cabinet partial discharge recognition method and system.
In order to solve the above problems, the technical embodiment adopts the following overall concept:
firstly, acquiring a target voltage switch cabinet; then, acquiring a preset discharge monitoring ternary configuration; then, monitoring characteristic analysis is carried out on the target high-voltage switch cabinet through a cabinet monitoring characteristic mining algorithm, and a cabinet partial discharge monitoring sub-module is established, wherein the sub-module comprises a plurality of partial discharge monitoring units; further, a plurality of partial discharge monitoring units are utilized to monitor the target high-voltage switch cabinet in real time, and a plurality of real-time signal monitoring results are obtained; then, carrying out environment interference compensation fusion on a plurality of real-time signal monitoring results to obtain a plurality of characteristic fusion monitoring results; in addition, a cabinet body partial discharge identification channel is established, and the channel is established for the target voltage switch cabinet based on a partial discharge identification sensitive analysis function; and finally, combining the monitoring results with the partial discharge identification channels of the cabinet body by using the feature fusion, executing the partial discharge identification of the target high-voltage switch cabinet, and generating a cabinet body partial discharge identification report. Thereby achieving the technical effects of high recognition efficiency and good recognition accuracy and confidence.
In order to better understand the above technical solutions, the following detailed description will be given with reference to the accompanying drawings and specific embodiments, and it should be noted that the described embodiments are only some embodiments of the present application, and not all embodiments of the present application, and it should be understood that the present application is not limited by the exemplary embodiments described herein. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to fall within the scope of the application. It should be further noted that, for convenience of description, only some, but not all of the drawings related to the present application are shown.
Example 1
As shown in fig. 1, the application provides a multi-feature fusion high-voltage switch cabinet partial discharge identification method, which comprises the following steps:
s100: obtaining a target voltage switch cabinet;
wherein a switchgear is a power grid device for controlling, distributing and protecting electrical energy in a power system. The target high-voltage switch cabinet is obtained, and the high-voltage switch cabinet object for partial discharge identification is firstly definitely used as an operation object of the subsequent step. The method comprises the steps of obtaining the target high-voltage switch cabinet, and determining information such as the position, the model, the parameters and the like of the high-voltage switch cabinet to be monitored so that subsequent monitoring and identification work can be performed in a targeted manner.
Optionally, the target high-voltage switch cabinet comprises an independent high-voltage switch cabinet unit, a plurality of high-voltage switch cabinet clusters of the same type in a power network, or a cluster network formed by a plurality of high-voltage switch cabinets.
S200: obtaining a preset discharge monitoring ternary configuration, wherein the preset discharge monitoring ternary configuration comprises a plurality of cabinet discharge monitoring hardware, and the plurality of cabinet discharge monitoring hardware comprises ultrasonic monitoring hardware, pulse current monitoring hardware and gas monitoring hardware;
optionally, the partial discharge monitoring is performed on the switch cabinet, and the partial discharge monitoring method includes: pulse current method (apparent discharge method), ultra High Frequency (UHF) detection method, transient ground voltage (TEV) detection method, ultrasonic detection method (AE), SF6 gas composition test method.
The ultrasonic monitoring hardware monitors based on an ultrasonic detection method (AE), including a plurality of ultrasonic detectors. The electric breakdown occurs in the air gap, and the discharge can be completed instantaneously, at this time, the electric energy is converted into heat energy instantaneously, the gas in the discharge center is expanded under the action of the heat energy, and the gas propagates outwards through the sound wave. Because the area of partial discharge is relatively small, the partial discharge sound source is a point sound source. The partial discharge detection of the switch cabinet can be realized by monitoring ultrasonic waves, and the accurate positioning of the discharge source can be realized. In addition, the ultrasonic monitoring has the technical characteristics of no electrical interference, no interference to the detection result caused by attenuation and refraction and reflection of the ultrasonic waves, and the method is complemented by other monitoring hardware in the preset discharge monitoring ternary configuration.
The pulse current monitoring hardware monitors based on a pulse current method (apparent discharge method) and comprises a plurality of pulse current monitors. When partial discharge occurs, a very brief pulsed current is generated, typically on the order of nanoseconds in width. These current pulses induce transient electromagnetic wave radiation and are transmitted through the cable. When the high-voltage switch cabinet is in a stable state, the total current of the three-phase cable is zero after the current of the three-phase cable is overlapped at the joint; and when no partial discharge event occurs, only a uniform noise current signal is monitored at the junction. If abnormal pulse current signals are detected at the joint, the signals accord with the characteristic of partial discharge, and the occurrence of partial discharge events together in the high-voltage switch cabinet can be determined. The pulse current monitor detects the occurrence of partial discharge by measuring the pulse current. In addition, the pulse current monitoring has the technical characteristics of high sensitivity, good real-time performance, measurable discharge capacity, discharge repetition rate, average current, easy noise interference and even low annihilation signal-to-noise ratio. And further complemented by other monitoring hardware in the preset discharge monitoring ternary configuration.
The gas monitoring hardware monitors based on SF6 gas composition testing methods, including a plurality of SF6 gas composition testers. In the high-voltage switch cabinet, SF6 gas fills the inner cavity to serve as an insulating medium, after the high-voltage switch cabinet is subjected to partial discharge, the SF6 gas can be partially decomposed under the action of high-voltage electric arcs, and abnormal decomposition products can occur in the air chamber of the high-voltage switch cabinet. The main electrical decomposition products of SF6 are: HF. SO2, SOF2, cuF2, WO3, etc. The detection and positioning of partial discharge can be realized by detecting the SF6 component of the relevant air chamber.
S300: based on a cabinet monitoring feature mining algorithm, monitoring feature analysis is carried out on the target high-voltage switch cabinet according to the preset discharge monitoring ternary configuration, and a cabinet partial discharge monitoring sub-module is built, wherein the cabinet partial discharge monitoring sub-module comprises a plurality of partial discharge monitoring units;
optionally, the partial discharge monitoring unit comprises an ultrasonic detector, a pulse current monitor and an SF6 gas monitor. And the plurality of partial discharge monitoring units correspond to a plurality of partial discharge monitoring points of the monitoring characteristic analysis result of the target voltage switch cabinet to form a cabinet partial discharge monitoring sub-module. And carrying out monitoring characteristic analysis on the target voltage switch cabinet according to a preset discharge monitoring ternary configuration, wherein the monitoring characteristic analysis is used for acquiring the layout position of the partial discharge monitoring unit based on the composition of materials, structures and the like of the target voltage switch cabinet.
Further, based on a cabinet monitoring feature mining algorithm, monitoring feature analysis is performed on the target high-voltage switch cabinet according to the preset discharge monitoring ternary configuration, and a cabinet partial discharge monitoring sub-module is built, wherein step S300 includes:
obtaining basic attribute characteristics of a cabinet body of the target high-voltage switch cabinet;
acquiring real-time cabinet body environment characteristics of the target high-voltage switch cabinet, and carrying out partial discharge induction analysis based on the real-time cabinet body environment characteristics to acquire a cabinet body environment partial discharge induction coefficient;
Carrying out partial discharge airspace feature mining on the target high-voltage switch cabinet to obtain cabinet discharge airspace feature distribution;
and based on the preset discharge monitoring ternary configuration, carrying out monitoring sensor layout on the target high-voltage switch cabinet according to the basic attribute characteristics of the cabinet body, the local discharge induction coefficient of the environment of the cabinet body and the distribution of the discharge airspace characteristics of the cabinet body, so as to obtain the local discharge monitoring sub-module of the cabinet body.
Optionally, the cabinet base attribute characteristics of the target high voltage switchgear include size and shape, material construction, voltage class, insulation class, safety characteristics, access mode, load capacity, and the like. The basic attribute characteristics of the cabinet body reflect the basic characteristics of the target high-voltage switch cabinet, and standardized description of the target high-voltage switch cabinet is provided.
The real-time cabinet body environment characteristic of the target voltage switch cabinet refers to the environment characteristic of the interior of the target switch cabinet and is used for reflecting the real-time environment state of the interior of the target switch cabinet, and optionally, the real-time cabinet body environment characteristic comprises an environment temperature characteristic, an environment humidity characteristic, an electric field intensity characteristic and the like. And carrying out partial discharge induction analysis based on the real-time cabinet environmental characteristics, and identifying factors possibly causing partial discharge. The cabinet environment partial discharge induction coefficient is used for quantifying an index of the influence degree of the cabinet environment on partial discharge.
Optionally, the real-time environmental state is acquired based on a plurality of real-time environmental state sensors in the target voltage switchgear. Including ambient temperature sensors, ambient humidity sensors, ambient electric field sensors, etc.
Alternatively, the partial discharge induction analysis is performed by a partial discharge induction analysis pathway. The method includes the steps of obtaining historical partial discharge monitoring records, taking partial discharge intensity and partial discharge frequency as characteristic matching response characteristics, taking real-time cabinet environment characteristics as characteristic matching constraint characteristics, constructing a response relation between the real-time cabinet environment characteristics and partial discharge events, and obtaining a partial discharge induction analysis path.
In addition, a discharge monitoring sensor is arranged and connected into the monitoring system. The sensor can be connected with the monitoring system in a wired or wireless mode, and the detected discharge signal is transmitted to the monitoring system for analysis and processing.
Further, the step of performing partial discharge airspace feature mining on the target high-voltage switch cabinet to obtain cabinet discharge airspace feature distribution further comprises the following steps:
obtaining a partial discharge position record library of the target high-voltage switch cabinet;
carrying out partial discharge position clustering on the partial discharge position record library to obtain a plurality of partial discharge position clustering results;
Calculating the partial discharge trigger degree based on the clustering results of the partial discharge positions to obtain a plurality of partial discharge position trigger degrees;
screening the plurality of partial discharge position trigger degrees based on a preset position trigger degree to obtain a plurality of identification partial discharge position trigger degrees larger than the preset position trigger degree;
based on the target high-voltage switch cabinet, carrying out partial discharge influence analysis on a plurality of positions to obtain a plurality of partial discharge position influence values;
screening the plurality of partial discharge position influence values based on preset position influence values to obtain a plurality of identification partial discharge position influence values larger than the preset position influence values;
and executing the union position identification of the target high-voltage switch cabinet based on the triggering degrees of the plurality of identification partial discharge positions and the influence degree of the plurality of identification partial discharge positions to obtain the cabinet discharge airspace characteristic distribution.
Optionally, the partial discharge position record library is constructed based on a partial discharge event log, and the partial discharge position records of multiple partial discharge events in the partial discharge event log are extracted by calling the partial discharge event log and based on the data mining technology principle, and the multiple partial discharge position records are added to the partial discharge position record library.
The partial discharge position clustering is used for carrying out clustering analysis based on discharge positions on the partial discharge position records, and obtaining a plurality of partial discharge position clustering results. The clustering results of the partial discharge positions reflect the positions of the partial discharge event of the target high-voltage switch cabinet.
Optionally, the acquiring partial discharge trigger level is calculated based on the monitored data and the characteristics of the partial discharge event. The monitoring data and features include: amplitude characteristics of the partial discharge signal, discharge frequency, partial discharge type, partial discharge duration, etc. The trigger degree of the partial discharge position is used for reflecting the trigger probability of the partial discharge event of the partial discharge position. The partial discharge positions corresponding to the triggering degrees of the plurality of identification partial discharge positions, which are larger than the triggering degrees of the preset positions, have higher possibility of triggering the partial discharge event.
The identification partial discharge position influence degree is used for quantifying the influence degree of a plurality of partial discharge position clusters, which occur partial discharge events, on the target high-voltage switch cabinet. Optionally, the analysis of the influence of the partial discharge is realized according to the corresponding relation between the partial discharge position and the functional partition of the internal structure of the target high-voltage switch cabinet. For example, if the local discharge position neighborhood circuit is concentrated and the distance from the functional partition with high importance is short, the local discharge has a large influence and the local discharge position has a high influence.
And carrying out union position identification of the target voltage switch cabinet by integrating the triggering degree of the plurality of identification partial discharge positions and the influence degree of the plurality of identification partial discharge positions, and obtaining the discharge airspace characteristic distribution of the cabinet body. The method realizes the mark recognition of the high-risk key discharge airspace of the target high-voltage switch cabinet, and is convenient for the follow-up targeted monitoring according to the cabinet body discharge airspace characteristic distribution.
S400: real-time monitoring is carried out on the target high-voltage switch cabinet based on the plurality of partial discharge monitoring units, so that a plurality of real-time signal monitoring results are obtained, wherein each real-time signal monitoring result comprises an ultrasonic monitoring signal set, a pulse current monitoring signal set and a gas monitoring characteristic set;
optionally, the real-time monitoring is continuous on-line monitoring, the plurality of partial discharge monitoring units monitor the target high-voltage switch cabinet in real time, and a plurality of real-time signal monitoring results after data encoding are transmitted to the multi-feature fusion high-voltage switch cabinet partial discharge recognition system through the data connection channel. The data coding realizes the compression of a plurality of real-time signal monitoring results by a specific coding method and a specific coding format, thereby being convenient for data transmission.
Optionally, after a plurality of real-time signal monitoring results are obtained, data verification is performed on the plurality of real-time signal monitoring results, so that the integrity and accuracy of the received detection result data are ensured, and the accuracy of partial discharge identification is improved.
S500: traversing the plurality of real-time signal monitoring results to carry out monitoring environment interference compensation fusion to obtain a plurality of characteristic fusion monitoring results;
further, the step S500 further includes:
traversing the plurality of real-time signal monitoring results to obtain a first real-time signal monitoring result, wherein the first real-time signal monitoring result comprises a first ultrasonic monitoring signal set, a first pulse current monitoring signal set and a first gas monitoring characteristic set;
performing monitoring environment interference compensation fusion based on the first ultrasonic monitoring signal set to obtain a first compensation ultrasonic monitoring signal set;
performing monitoring environment interference compensation fusion based on the first pulse current monitoring signal set to obtain a first compensation pulse current monitoring signal set;
performing monitoring environment interference compensation fusion based on the first gas monitoring feature set to obtain a first compensation gas monitoring feature set;
integrating the first compensation ultrasonic monitoring signal set, the first compensation pulse current monitoring signal set and the first compensation gas monitoring feature set, generating a first feature fusion monitoring result corresponding to the first real-time signal monitoring result, and adding the first feature fusion monitoring result to the plurality of feature fusion monitoring results.
In partial discharge monitoring, environmental interference may affect the accuracy of the ultrasonic monitoring signal, and thus compensation and fusion are required to improve the reliability of monitoring. The monitoring environment interference compensation fusion is used for reducing the influence of environment noise on ultrasonic monitoring.
Optionally, the monitoring environment interference compensation fusion method includes: noise filtering, removing signal components from ambient noise by employing filters or signal processing techniques. For an ultrasonic monitoring signal, a wavelet transformation method is introduced, and the signal to noise ratio is improved while the signal evaluability is not changed; signal enhancement, which is to amplify the monitored ultrasonic signal to highlight the characteristic or mode; the multiple sensors are fused, the monitoring and the acquisition are carried out through the multiple sensors, and the monitoring results of the multiple sensors are fused together, so that the detection performance of partial discharge is improved. The fusion can adopt methods such as weighted average, feature fusion and the like.
The first feature fusion monitoring result is a feature set obtained after feature fusion association storage is performed on a first compensation ultrasonic monitoring signal set, a first compensation pulse current monitoring signal set and a first compensation gas monitoring feature set obtained through environmental compensation processing.
In addition, it should be understood that, based on the same method principle as that of obtaining the first compensated ultrasonic monitoring signal set, the monitoring environment interference compensation fusion is performed on the first pulse current monitoring signal set to obtain the first compensated pulse current monitoring signal set; performing monitoring environment interference compensation fusion on the first gas monitoring feature set to obtain a first compensation gas monitoring feature set; further developments are not described here for the sake of brevity.
Further, based on the first ultrasonic monitoring signal set, monitoring environment interference compensation fusion is performed, and a first compensated ultrasonic monitoring signal set is obtained, and the steps further include:
acquiring real-time hardware sensing environment information of the first ultrasonic monitoring signal set to obtain a plurality of real-time sensing environment indexes;
performing environmental impact analysis based on the plurality of real-time sensing environmental indexes to obtain a plurality of sensing environmental impact values;
if any one of the sensing environment influence values is greater than or equal to a preset environment influence value, generating a first ultrasonic sensing compensation instruction, and performing monitoring environment interference compensation on the first ultrasonic monitoring signal set according to the first ultrasonic sensing compensation instruction to obtain the first compensation ultrasonic monitoring signal set;
And if the sensing environment influence degrees are smaller than the preset environment influence degree, generating a first ultrasonic sensing fusion instruction, and outputting the first ultrasonic monitoring signal set into the first compensating ultrasonic monitoring signal set according to the first ultrasonic sensing fusion instruction.
The real-time sensing environment index is a real-time environment noise value, and represents an original value of a real-time environment characteristic. Optionally, the environmental impact analysis is performed by calculating the degree of influence of noise on the signal-to-noise ratio of the ultrasonic monitoring signal. The signal-to-noise ratio calculation formula is as follows:
；
where Signal Power represents the Power of the Signal and Noise Power represents the Power of the Noise. And analyzing the quality of the signal according to the calculated signal-to-noise ratio value. The higher the signal-to-noise ratio, the better the signal quality, the less the environmental noise affects the ultrasonic monitoring signal, and vice versa.
Optionally, if the sensing environment influence is greater than/equal to the preset environment influence, that is, the real-time signal-to-noise ratio is not higher than the preset monitoring signal-to-noise ratio requirement, it is indicated that the environment has a larger influence on the partial discharge monitoring system, and the monitoring environment interference compensation of the first ultrasonic monitoring signal set is performed based on the first ultrasonic sensing compensation instruction. If the influence of the sensing environment is smaller than the influence of the preset environment, namely the real-time signal-to-noise ratio is higher than the signal-to-noise ratio requirement of the preset monitoring signal, the influence of the environment on the partial discharge monitoring system is slight, and the monitoring environment interference compensation is not needed.
S600: constructing a cabinet partial discharge recognition channel based on the partial discharge recognition sensitive analysis function;
further, as shown in fig. 2, based on the partial discharge recognition sensitivity analysis function, a cabinet partial discharge recognition channel is constructed, and step S600 further includes:
based on the target high-voltage switch cabinets, obtaining a plurality of same-family high-voltage switch cabinets, and collecting partial discharge identification records of the plurality of same-family high-voltage switch cabinets to obtain a same-family partial discharge identification record library;
acquiring partial discharge identification records based on the target high-voltage switch cabinet to obtain a main body partial discharge identification record library;
training a partial discharge recognition network based on the peer partial discharge recognition record library;
testing the partial discharge identification network based on the main body partial discharge identification record library to obtain partial discharge identification accuracy and partial discharge identification loss rate;
inputting the partial discharge identification accuracy rate and the partial discharge identification loss rate into the partial discharge identification sensitivity analysis function to obtain a partial discharge identification sensitivity index;
judging whether the partial discharge identification sensitivity index is smaller than a preset sensitivity index;
if the partial discharge identification sensitivity index is larger than or equal to a preset sensitivity index, a network mapping instruction is obtained, and the partial discharge identification network is added to the cabinet partial discharge identification channel according to the network mapping instruction.
The same-family high-voltage switch cabinets refer to high-voltage switch cabinets which are the same type or the same series as the target high-voltage switch cabinets, and have similar cabinet body basic attribute characteristics. And acquiring partial discharge identification records of a plurality of same-family high-voltage switch cabinets to obtain a same-family partial discharge identification record library. And the same family partial discharge recognition record library is used as a training data set to train the partial discharge recognition network, so that the sample quantity of the training set is enriched while the adaptation degree of the sample and the target high-voltage switch cabinet is ensured, and the training effect of the partial discharge recognition network is further ensured.
Optionally, the partial discharge identification network is constructed based on a deep learning network, including a Convolutional Neural Network (CNN) or a Recurrent Neural Network (RNN), for extracting features from the partial discharge data and classifying. The partial discharge identification network takes the characteristic fusion monitoring result as an input characteristic and takes the partial discharge identification result as a corresponding characteristic.
Alternatively, the partial discharge recognition accuracy is used to indicate the proportion of the partial discharge correctly recognized. By comparing the output of the network with the actual tag of the test data. The partial discharge recognition loss rate indicates an error generated when recognizing the partial discharge. Based on the loss function acquisition, the method is used for quantifying the difference between the predicted result of the measurement network and the actual label.
If the partial discharge identification sensitivity index is greater than/equal to the preset sensitivity index, the partial discharge identification network performance meets the preset partial discharge identification requirement of the high-voltage switch cabinet.
Further, the method further comprises:
the partial discharge recognition sensitivity analysis function is as follows:
；
wherein P is sen Characterization of partial discharge identification sensitivity index, X 1 Characterization partial discharge identification accuracy, X 2 Characterization ofPartial discharge identifies loss rate.
S700: and executing partial discharge identification of the target high-voltage switch cabinet according to the cabinet partial discharge identification channel based on the characteristic fusion monitoring results to obtain a cabinet partial discharge identification report.
Optionally, the cabinet partial discharge identification report includes a partial discharge identification result, and is used for quantifying occurrence of tactical partial discharge events. The cabinet partial discharge identification report contains information about the partial discharge event, including the location of the partial discharge event, the partial discharge intensity, the duration, etc. And further provides data support for operation and maintenance personnel to know the state of the high-voltage switch cabinet and further analyze and process.
In summary, the multi-feature fusion high-voltage switch cabinet partial discharge identification method provided by the invention has the following technical effects:
The target voltage switch cabinet is obtained; obtaining a preset discharge monitoring ternary configuration; based on a cabinet monitoring feature mining algorithm, monitoring feature analysis is carried out on a target high-voltage switch cabinet, and a cabinet partial discharge monitoring sub-module is built, wherein the cabinet partial discharge monitoring sub-module comprises a plurality of partial discharge monitoring units; real-time monitoring is carried out on the target high-voltage switch cabinet based on the plurality of partial discharge monitoring units, and a plurality of real-time signal monitoring results are obtained; traversing a plurality of real-time signal monitoring results to carry out monitoring environment interference compensation fusion to obtain a plurality of characteristic fusion monitoring results; constructing a cabinet partial discharge recognition channel based on the partial discharge recognition sensitive analysis function; and based on the multiple feature fusion monitoring results, executing partial discharge identification of the target voltage switch cabinet according to the cabinet partial discharge identification channel to obtain a cabinet partial discharge identification report. Thereby achieving the technical effects of high recognition efficiency and good recognition accuracy and confidence.
Example two
Based on the same conception as the multi-feature fusion high-voltage switch cabinet partial discharge identification method in the embodiment, as shown in fig. 3, the application also provides a multi-feature fusion high-voltage switch cabinet partial discharge identification system, which comprises:
The target acquisition module 11 is used for acquiring a target voltage switch cabinet;
a configuration obtaining module 12, configured to obtain a preset discharge monitoring ternary configuration, where the preset discharge monitoring ternary configuration includes a plurality of cabinet discharge monitoring hardware, and the plurality of cabinet discharge monitoring hardware includes an ultrasonic monitoring hardware, a pulse current monitoring hardware, and a gas monitoring hardware;
the partial discharge monitoring configuration module 13 is configured to perform monitoring feature analysis on the target high-voltage switch cabinet according to the preset discharge monitoring ternary configuration based on a cabinet monitoring feature mining algorithm, and build a cabinet partial discharge monitoring sub-module, wherein the cabinet partial discharge monitoring sub-module comprises a plurality of partial discharge monitoring units;
the real-time monitoring module 14 is configured to monitor the target high-voltage switch cabinet in real time based on the plurality of partial discharge monitoring units, and obtain a plurality of real-time signal monitoring results, where each real-time signal monitoring result includes an ultrasonic monitoring signal set, a pulse current monitoring signal set, and a gas monitoring feature set;
the feature fusion module 15 is configured to traverse the plurality of real-time signal monitoring results to perform monitoring environment interference compensation fusion, and obtain a plurality of feature fusion monitoring results;
The identification construction module 16 is used for constructing a cabinet partial discharge identification channel based on the partial discharge identification sensitive analysis function;
and the partial discharge identification module 17 is used for executing the partial discharge identification of the target high-voltage switch cabinet according to the cabinet partial discharge identification channel based on the characteristic fusion monitoring results to obtain a cabinet partial discharge identification report.
Further, the partial discharge monitoring configuration module 13 further includes:
the same-family record acquisition unit is used for acquiring a plurality of same-family high-voltage switch cabinets based on the target high-voltage switch cabinets, and carrying out partial discharge identification record acquisition on the plurality of same-family high-voltage switch cabinets to acquire a same-family partial discharge identification record library;
the main body record acquisition unit is used for carrying out partial discharge identification record acquisition based on the target high-voltage switch cabinet to obtain a main body partial discharge identification record library;
the identification network training unit is used for training the partial discharge identification network based on the same family partial discharge identification record library;
the identification network test unit is used for testing the partial discharge identification network based on the main body partial discharge identification record library to obtain the partial discharge identification accuracy and the partial discharge identification loss rate;
The sensitivity index unit is used for inputting the partial discharge identification accuracy rate and the partial discharge identification loss rate into the partial discharge identification sensitivity analysis function to obtain a partial discharge identification sensitivity index;
the sensitivity index judging unit is used for judging whether the partial discharge identification sensitivity index is smaller than a preset sensitivity index;
and the network mapping unit is used for obtaining a network mapping instruction if the partial discharge identification sensitivity index is greater than/equal to a preset sensitivity index, and adding the partial discharge identification network to the cabinet partial discharge identification channel according to the network mapping instruction.
Further, the sensitivity index unit further includes a sensitivity analysis function unit:
the partial discharge recognition sensitivity analysis function is as follows:
；
wherein P is sen Characterization of partial discharge identification sensitivity index, X 1 Characterization partial discharge identification accuracy, X 2 And characterizing the partial discharge recognition loss rate.
Further, the feature fusion module 15 further includes:
the monitoring result extraction unit is used for traversing the plurality of real-time signal monitoring results to obtain a first real-time signal monitoring result, wherein the first real-time signal monitoring result comprises a first ultrasonic monitoring signal set, a first pulse current monitoring signal set and a first gas monitoring feature set;
The compensation ultrasonic unit is used for carrying out monitoring environment interference compensation fusion based on the first ultrasonic monitoring signal set to obtain a first compensation ultrasonic monitoring signal set;
the compensation pulse current unit is used for carrying out monitoring environment interference compensation fusion based on the first pulse current monitoring signal set to obtain a first compensation pulse current monitoring signal set;
the compensation gas unit is used for carrying out monitoring environment interference compensation fusion based on the first gas monitoring feature set to obtain a first compensation gas monitoring feature set;
the monitoring feature fusion unit is used for integrating the first compensation ultrasonic monitoring signal set, the first compensation pulse current monitoring signal set and the first compensation gas monitoring feature set, generating a first feature fusion monitoring result corresponding to the first real-time signal monitoring result, and adding the first feature fusion monitoring result to the plurality of feature fusion monitoring results.
Further, the compensating ultrasonic monitoring unit further includes:
the environment information unit is used for collecting real-time hardware sensing environment information of the first ultrasonic monitoring signal set and obtaining a plurality of real-time sensing environment indexes;
the environment influence degree analysis unit is used for carrying out environment influence degree analysis based on the plurality of real-time sensing environment indexes to obtain a plurality of sensing environment influence degrees;
The interference compensation unit is used for generating a first ultrasonic sensing compensation instruction if any one of the sensing environment influence values is larger than/equal to a preset environment influence value, and carrying out monitoring environment interference compensation on the first ultrasonic monitoring signal set according to the first ultrasonic sensing compensation instruction to obtain the first compensation ultrasonic monitoring signal set;
and the sensing fusion unit is used for generating a first ultrasonic sensing fusion instruction if the sensing environment influence degrees are smaller than the preset environment influence degree, and outputting the first ultrasonic monitoring signal set as the first compensation ultrasonic monitoring signal set according to the first ultrasonic sensing fusion instruction.
Further, the identification construction module 16 further includes:
the attribute acquisition unit is used for acquiring basic attribute characteristics of the cabinet body of the target high-voltage switch cabinet;
the discharge induction analysis unit is used for obtaining real-time cabinet body environment characteristics of the target high-voltage switch cabinet, and carrying out partial discharge induction analysis based on the real-time cabinet body environment characteristics to obtain a cabinet body environment partial discharge induction coefficient;
the feature mining unit is used for mining the partial discharge airspace features of the target high-voltage switch cabinet to obtain cabinet discharge airspace feature distribution;
And the sensor layout unit is used for carrying out monitoring sensor layout on the target high-voltage switch cabinet according to the basic attribute characteristics of the cabinet body, the local discharge induction coefficient of the environment of the cabinet body and the distribution of the discharge airspace characteristics of the cabinet body based on the preset discharge monitoring ternary configuration, so as to obtain the local discharge monitoring sub-module of the cabinet body.
Further, the feature mining unit further includes:
the position record acquisition unit is used for acquiring a partial discharge position record library of the target high-voltage switch cabinet;
the position clustering unit is used for carrying out partial discharge position clustering on the partial discharge position record library to obtain a plurality of partial discharge position clustering results;
the trigger degree calculating unit is used for calculating the trigger degrees of partial discharge based on the clustering results of the partial discharge positions to obtain the trigger degrees of the partial discharge positions;
the triggering degree screening unit is used for screening the plurality of partial discharge position triggering degrees based on a preset position triggering degree to obtain a plurality of identification partial discharge position triggering degrees larger than the preset position triggering degree;
the discharge influence analysis unit is used for carrying out partial discharge influence analysis on a plurality of positions based on the target high-voltage switch cabinet to obtain a plurality of partial discharge position influence values;
The influence screening unit is used for screening the plurality of partial discharge position influence values based on preset position influence values to obtain a plurality of identification partial discharge position influence values larger than the preset position influence values;
and the union position identification unit is used for executing the union position identification of the target high-voltage switch cabinet based on the triggering degrees of the plurality of identification partial discharge positions and the influence degree of the plurality of identification partial discharge positions, and obtaining the discharge airspace characteristic distribution of the cabinet body.
It should be understood that the embodiments mentioned in this specification focus on the differences from other embodiments, and the specific embodiment in the first embodiment is equally applicable to a multi-feature fusion high-voltage switchgear partial discharge recognition system described in the second embodiment, which is not further developed herein for brevity of description.
It is to be understood that both the foregoing description and the embodiments of the present application enable one skilled in the art to utilize the present application. While the application is not limited to the embodiments described above, obvious modifications and variations of the embodiments described herein are possible and are within the principles of the application.
Claims (8)
1. The multi-feature fusion high-voltage switch cabinet partial discharge identification method is characterized by comprising the following steps of:
obtaining a target voltage switch cabinet;
obtaining a preset discharge monitoring ternary configuration, wherein the preset discharge monitoring ternary configuration comprises a plurality of cabinet discharge monitoring hardware, and the plurality of cabinet discharge monitoring hardware comprises ultrasonic monitoring hardware, pulse current monitoring hardware and gas monitoring hardware;
based on a cabinet monitoring feature mining algorithm, monitoring feature analysis is carried out on the target high-voltage switch cabinet according to the preset discharge monitoring ternary configuration, and a cabinet partial discharge monitoring sub-module is built, wherein the cabinet partial discharge monitoring sub-module comprises a plurality of partial discharge monitoring units;
real-time monitoring is carried out on the target high-voltage switch cabinet based on the plurality of partial discharge monitoring units, so that a plurality of real-time signal monitoring results are obtained, wherein each real-time signal monitoring result comprises an ultrasonic monitoring signal set, a pulse current monitoring signal set and a gas monitoring characteristic set;
traversing the plurality of real-time signal monitoring results to carry out monitoring environment interference compensation fusion to obtain a plurality of characteristic fusion monitoring results;
constructing a cabinet partial discharge recognition channel based on the partial discharge recognition sensitive analysis function;
And executing partial discharge identification of the target high-voltage switch cabinet according to the cabinet partial discharge identification channel based on the characteristic fusion monitoring results to obtain a cabinet partial discharge identification report.
2. The method of claim 1, wherein constructing a cabinet partial discharge identification channel based on the partial discharge identification sensitivity analysis function comprises:
based on the target high-voltage switch cabinets, obtaining a plurality of same-family high-voltage switch cabinets, and collecting partial discharge identification records of the plurality of same-family high-voltage switch cabinets to obtain a same-family partial discharge identification record library;
acquiring partial discharge identification records based on the target high-voltage switch cabinet to obtain a main body partial discharge identification record library;
training a partial discharge recognition network based on the peer partial discharge recognition record library;
testing the partial discharge identification network based on the main body partial discharge identification record library to obtain partial discharge identification accuracy and partial discharge identification loss rate;
inputting the partial discharge identification accuracy rate and the partial discharge identification loss rate into the partial discharge identification sensitivity analysis function to obtain a partial discharge identification sensitivity index;
judging whether the partial discharge identification sensitivity index is smaller than a preset sensitivity index;
If the partial discharge identification sensitivity index is larger than or equal to a preset sensitivity index, a network mapping instruction is obtained, and the partial discharge identification network is added to the cabinet partial discharge identification channel according to the network mapping instruction.
3. The method according to claim 2, wherein the method comprises:
the partial discharge recognition sensitivity analysis function is as follows:
；
wherein P is sen Characterization of partial discharge identification sensitivity index, X 1 Characterization partial discharge identification accuracy, X 2 And characterizing the partial discharge recognition loss rate.
4. The method of claim 1, wherein traversing the plurality of real-time signal monitoring results for monitoring ambient interference compensation fusion to obtain a plurality of feature fusion monitoring results comprises:
traversing the plurality of real-time signal monitoring results to obtain a first real-time signal monitoring result, wherein the first real-time signal monitoring result comprises a first ultrasonic monitoring signal set, a first pulse current monitoring signal set and a first gas monitoring characteristic set;
performing monitoring environment interference compensation fusion based on the first ultrasonic monitoring signal set to obtain a first compensation ultrasonic monitoring signal set;
performing monitoring environment interference compensation fusion based on the first pulse current monitoring signal set to obtain a first compensation pulse current monitoring signal set;
Performing monitoring environment interference compensation fusion based on the first gas monitoring feature set to obtain a first compensation gas monitoring feature set;
integrating the first compensation ultrasonic monitoring signal set, the first compensation pulse current monitoring signal set and the first compensation gas monitoring feature set, generating a first feature fusion monitoring result corresponding to the first real-time signal monitoring result, and adding the first feature fusion monitoring result to the plurality of feature fusion monitoring results.
5. The method of claim 4, wherein performing a monitoring environmental disturbance compensation fusion based on the first set of ultrasonic monitoring signals to obtain the first set of compensated ultrasonic monitoring signals comprises:
acquiring real-time hardware sensing environment information of the first ultrasonic monitoring signal set to obtain a plurality of real-time sensing environment indexes;
performing environmental impact analysis based on the plurality of real-time sensing environmental indexes to obtain a plurality of sensing environmental impact values;
if any one of the sensing environment influence values is greater than or equal to a preset environment influence value, generating a first ultrasonic sensing compensation instruction, and performing monitoring environment interference compensation on the first ultrasonic monitoring signal set according to the first ultrasonic sensing compensation instruction to obtain the first compensation ultrasonic monitoring signal set;
And if the sensing environment influence degrees are smaller than the preset environment influence degree, generating a first ultrasonic sensing fusion instruction, and outputting the first ultrasonic monitoring signal set into the first compensating ultrasonic monitoring signal set according to the first ultrasonic sensing fusion instruction.
6. The method of claim 1, wherein based on a cabinet monitoring feature mining algorithm, monitoring feature analysis is performed on the target high-voltage switch cabinet according to the preset discharge monitoring ternary configuration, and a cabinet partial discharge monitoring sub-module is built, comprising:
obtaining basic attribute characteristics of a cabinet body of the target high-voltage switch cabinet;
acquiring real-time cabinet body environment characteristics of the target high-voltage switch cabinet, and carrying out partial discharge induction analysis based on the real-time cabinet body environment characteristics to acquire a cabinet body environment partial discharge induction coefficient;
carrying out partial discharge airspace feature mining on the target high-voltage switch cabinet to obtain cabinet discharge airspace feature distribution;
and based on the preset discharge monitoring ternary configuration, carrying out monitoring sensor layout on the target high-voltage switch cabinet according to the basic attribute characteristics of the cabinet body, the local discharge induction coefficient of the environment of the cabinet body and the distribution of the discharge airspace characteristics of the cabinet body, so as to obtain the local discharge monitoring sub-module of the cabinet body.
7. The method of claim 6, wherein the performing partial discharge spatial feature mining on the target high voltage switchgear to obtain a switchgear body discharge spatial feature distribution comprises:
obtaining a partial discharge position record library of the target high-voltage switch cabinet;
carrying out partial discharge position clustering on the partial discharge position record library to obtain a plurality of partial discharge position clustering results;
calculating the partial discharge trigger degree based on the clustering results of the partial discharge positions to obtain a plurality of partial discharge position trigger degrees;
screening the plurality of partial discharge position trigger degrees based on a preset position trigger degree to obtain a plurality of identification partial discharge position trigger degrees larger than the preset position trigger degree;
based on the target high-voltage switch cabinet, carrying out partial discharge influence analysis on a plurality of positions to obtain a plurality of partial discharge position influence values;
screening the plurality of partial discharge position influence values based on preset position influence values to obtain a plurality of identification partial discharge position influence values larger than the preset position influence values;
and executing the union position identification of the target high-voltage switch cabinet based on the triggering degrees of the plurality of identification partial discharge positions and the influence degree of the plurality of identification partial discharge positions to obtain the cabinet discharge airspace characteristic distribution.
8. A multi-feature fused high voltage switchgear partial discharge identification system, the system comprising:
the target acquisition module is used for acquiring a target voltage switch cabinet;
the system comprises a configuration acquisition module, a configuration detection module and a control module, wherein the configuration acquisition module is used for acquiring a preset discharge monitoring ternary configuration, the preset discharge monitoring ternary configuration comprises a plurality of cabinet discharge monitoring hardware, and the plurality of cabinet discharge monitoring hardware comprises ultrasonic monitoring hardware, pulse current monitoring hardware and gas monitoring hardware;
the partial discharge monitoring configuration module is used for carrying out monitoring feature analysis on the target high-voltage switch cabinet according to the preset discharge monitoring ternary configuration based on a cabinet monitoring feature mining algorithm, and constructing a cabinet partial discharge monitoring sub-module, wherein the cabinet partial discharge monitoring sub-module comprises a plurality of partial discharge monitoring units;
the real-time monitoring module is used for carrying out real-time monitoring on the target high-voltage switch cabinet based on the plurality of partial discharge monitoring units to obtain a plurality of real-time signal monitoring results, wherein each real-time signal monitoring result comprises an ultrasonic monitoring signal set, a pulse current monitoring signal set and a gas monitoring characteristic set;
The feature fusion module is used for traversing the plurality of real-time signal monitoring results to carry out monitoring environment interference compensation fusion and obtain a plurality of feature fusion monitoring results;
the identification construction module is used for constructing a cabinet partial discharge identification channel based on the partial discharge identification sensitive analysis function;
and the partial discharge identification module is used for carrying out partial discharge identification of the target high-voltage switch cabinet according to the cabinet partial discharge identification channel based on the characteristic fusion monitoring results to obtain a cabinet partial discharge identification report.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311422063.1A CN117148076B (en) | 2023-10-31 | 2023-10-31 | Multi-feature fusion type high-voltage switch cabinet partial discharge identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311422063.1A CN117148076B (en) | 2023-10-31 | 2023-10-31 | Multi-feature fusion type high-voltage switch cabinet partial discharge identification method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117148076A true CN117148076A (en) | 2023-12-01 |
| CN117148076B CN117148076B (en) | 2024-01-26 |
Family
ID=88899139
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311422063.1A Active CN117148076B (en) | 2023-10-31 | 2023-10-31 | Multi-feature fusion type high-voltage switch cabinet partial discharge identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117148076B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117538710A (en) * | 2023-12-14 | 2024-02-09 | 四川大唐国际甘孜水电开发有限公司 | Intelligent early warning method and system for local dynamic discharge monitoring |
| CN118091344A (en) * | 2024-04-25 | 2024-05-28 | 北京迪赛奇正科技有限公司 | Power converter detection method and system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009047663A (en) * | 2007-08-23 | 2009-03-05 | Chubu Electric Power Co Inc | Partial discharge detecting technique for electric equipment and device thereof |
| CN102435922A (en) * | 2011-10-26 | 2012-05-02 | 上海交通大学 | Acoustic-electric combined detection system and positioning method for GIS (Gas Insulated Switchgear) local discharge |
| CN208445119U (en) * | 2018-05-25 | 2019-01-29 | 南通豪强电器设备有限公司 | A kind of protection type switchgear |
| CN112085084A (en) * | 2020-08-24 | 2020-12-15 | 宁波大学 | Transformer fault diagnosis method based on multi-feature fusion common vector |
| CN112748317A (en) * | 2021-03-23 | 2021-05-04 | 国网河南省电力公司电力科学研究院 | Switch cabinet partial discharge fault detection method and system based on multiple monitoring data |
| CN115598476A (en) * | 2022-10-18 | 2023-01-13 | 广东电网有限责任公司广州供电局（Cn） | Method, device and medium for monitoring multi-parameter fusion insulation state of annular net cage |
| CN116338399A (en) * | 2023-05-04 | 2023-06-27 | 华北电力大学 | GIS partial discharge detection system based on multi-parameter combination |
| CN116452542A (en) * | 2023-04-19 | 2023-07-18 | 华北电力大学（保定） | GIS partial discharge defect diagnosis method based on nerve supervision decision tree |
-
2023
- 2023-10-31 CN CN202311422063.1A patent/CN117148076B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009047663A (en) * | 2007-08-23 | 2009-03-05 | Chubu Electric Power Co Inc | Partial discharge detecting technique for electric equipment and device thereof |
| CN102435922A (en) * | 2011-10-26 | 2012-05-02 | 上海交通大学 | Acoustic-electric combined detection system and positioning method for GIS (Gas Insulated Switchgear) local discharge |
| CN208445119U (en) * | 2018-05-25 | 2019-01-29 | 南通豪强电器设备有限公司 | A kind of protection type switchgear |
| CN112085084A (en) * | 2020-08-24 | 2020-12-15 | 宁波大学 | Transformer fault diagnosis method based on multi-feature fusion common vector |
| CN112748317A (en) * | 2021-03-23 | 2021-05-04 | 国网河南省电力公司电力科学研究院 | Switch cabinet partial discharge fault detection method and system based on multiple monitoring data |
| CN115598476A (en) * | 2022-10-18 | 2023-01-13 | 广东电网有限责任公司广州供电局（Cn） | Method, device and medium for monitoring multi-parameter fusion insulation state of annular net cage |
| CN116452542A (en) * | 2023-04-19 | 2023-07-18 | 华北电力大学（保定） | GIS partial discharge defect diagnosis method based on nerve supervision decision tree |
| CN116338399A (en) * | 2023-05-04 | 2023-06-27 | 华北电力大学 | GIS partial discharge detection system based on multi-parameter combination |
Non-Patent Citations (3)
| Title |
|---|
| XUEYOU HUANG 等: "Partial Discharge Identification of Distribution Cable Based on Multi-Feature Machine Learning", 《2022 7TH INTERNATIONAL CONFERENCE ON COMMUNICATION, IMAGE AND SIGNAL PROCESSING (CCISP)》, pages 1 - 5 * |
| YUN WANG 等: "Acoustic Detection and Decision Fusion Recognition of PD in Power Cable", 《2021 IEEE 2ND CHINA INTERNATIONAL YOUTH CONFERENCE ON ELECTRICAL ENGINEERING (CIYCEE)》, pages 1 - 6 * |
| 李先锋 等: "基于多特征融合的GIS隔离开关接触状态评估方法", 《热力发电》, pages 1 - 7 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117538710A (en) * | 2023-12-14 | 2024-02-09 | 四川大唐国际甘孜水电开发有限公司 | Intelligent early warning method and system for local dynamic discharge monitoring |
| CN117538710B (en) * | 2023-12-14 | 2024-07-23 | 四川大唐国际甘孜水电开发有限公司 | Intelligent early warning method and system for local dynamic discharge monitoring |
| CN118091344A (en) * | 2024-04-25 | 2024-05-28 | 北京迪赛奇正科技有限公司 | Power converter detection method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117148076B (en) | 2024-01-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117148076B (en) | Multi-feature fusion type high-voltage switch cabinet partial discharge identification method and system | |
| CN105676085B (en) | Based on extra-high voltage GIS detection method for local discharge combined of multi-sensor information | |
| CN109444682A (en) | The construction method of partial discharge of switchgear diagnostic system based on multi-information fusion | |
| CN107942206B (en) | GIS partial discharge positioning method | |
| CN109001997B (en) | Anti-interference environment information acquisition system | |
| CN103267932A (en) | GIS partial discharging detection system and method | |
| CN114576566B (en) | Gas pipeline early warning method, device, equipment and storage medium | |
| CN112147444B (en) | Power transformer working state monitoring method and system | |
| KR20140120331A (en) | System for analyzing and locating partial discharges | |
| CN110673075B (en) | Method for evaluating electromagnetic interference resistance of ultrahigh frequency partial discharge detector | |
| JP2015078882A (en) | Insulation diagnostic device | |
| CN114252749B (en) | Transformer partial discharge detection method and device based on multiple sensors | |
| CN117538710B (en) | Intelligent early warning method and system for local dynamic discharge monitoring | |
| CN109507556A (en) | MDS type switchgear fault detection alarm device | |
| CN115993511A (en) | Partial discharge type high-precision detection and identification device, method and equipment | |
| CN205581259U (en) | GIS local discharge on -line monitoring system with little meteorological monitoring | |
| CN118091234A (en) | Current transformer for fault diagnosis processing | |
| CN116660703B (en) | Distribution network system insulation fault on-line monitoring system based on data analysis | |
| CN113625133A (en) | Online monitoring feedback system and method for partial discharge of power distribution equipment | |
| CN107991593A (en) | A kind of noise and shelf depreciation positioning GIS state of insulation on-line monitoring systems | |
| Judd et al. | Investigation of radiometric partial discharge detection for use in switched HVDC testing | |
| CN110261741A (en) | Discharge position localization method, device and the terminal device of high-tension switch gear | |
| CN112487714B (en) | Method for generating cable shaft fire state identification decision tree model | |
| CN209356622U (en) | MDS type switchgear fault detection alarm device | |
| CN106093728A (en) | A kind of partial discharge location instrument |
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 |