CN117538710B - Intelligent early warning method and system for local dynamic discharge monitoring - Google Patents
Intelligent early warning method and system for local dynamic discharge monitoring Download PDFInfo
- Publication number
- CN117538710B CN117538710B CN202311725284.6A CN202311725284A CN117538710B CN 117538710 B CN117538710 B CN 117538710B CN 202311725284 A CN202311725284 A CN 202311725284A CN 117538710 B CN117538710 B CN 117538710B
- Authority
- CN
- China
- Prior art keywords
- ultrasonic
- result
- signal
- feedback data
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 87
- 238000000034 method Methods 0.000 title claims abstract description 49
- 230000002159 abnormal effect Effects 0.000 claims abstract description 73
- 238000013507 mapping Methods 0.000 claims abstract description 34
- 238000011156 evaluation Methods 0.000 claims abstract description 25
- 230000009467 reduction Effects 0.000 claims abstract description 25
- 239000013307 optical fiber Substances 0.000 claims abstract description 17
- 238000010276 construction Methods 0.000 claims abstract description 11
- 238000004891 communication Methods 0.000 claims abstract description 9
- 230000003993 interaction Effects 0.000 claims abstract description 9
- 238000012795 verification Methods 0.000 claims description 38
- 238000012216 screening Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 13
- 230000005856 abnormality Effects 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 238000010606 normalization Methods 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 5
- 230000000694 effects Effects 0.000 abstract description 14
- 239000000463 material Substances 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 238000012423 maintenance Methods 0.000 description 5
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000012937 correction Methods 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001514 detection method 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
- 238000010892 electric spark Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 239000012212 insulator Substances 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000000452 restraining effect Effects 0.000 description 1
- 238000002604 ultrasonography Methods 0.000 description 1
- 230000000007 visual 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K11/00—Measuring temperature based upon physical or chemical changes not covered by groups G01K3/00, G01K5/00, G01K7/00 or G01K9/00
- G01K11/32—Measuring temperature based upon physical or chemical changes not covered by groups G01K3/00, G01K5/00, G01K7/00 or G01K9/00 using changes in transmittance, scattering or luminescence in optical fibres
-
- 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
- G01R31/08—Locating faults in cables, transmission lines, or networks
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/185—Electrical failure alarms
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Testing Relating To Insulation (AREA)
Abstract
The invention discloses an intelligent early warning method and system for monitoring partial dynamic discharge, which relate to the technical field of electric power and comprise the following steps: acquiring a target feature set of a monitoring target, wherein the target feature set is constructed by extracting structural features and equipment features of interaction data after communication connection with the monitoring target is established; carrying out probability evaluation of partial discharge, and establishing probability identification of partial discharge in spatial distribution; performing focus analysis of a monitored target, an array ultrasonic sensor and an optical fiber temperature sensor, and recording sensor coordinates; performing influence mapping construction of ultrasonic signals; monitoring in real time, and receiving ultrasonic feedback data and temperature feedback data; analyzing the signal intensity, performing ultrasonic positioning compensation and determining an abnormal position; and carrying out signal reduction to generate a partial dynamic discharge early warning result. The invention solves the technical problem that the abnormal position of partial discharge can not be accurately determined in the prior art, and achieves the technical effect of accurately determining the abnormal position.
Description
Technical Field
The invention relates to the technical field of electric power, in particular to an intelligent early warning method and system for monitoring partial dynamic discharge.
Background
In an electrical power system, partial discharge is one of the main causes of equipment failure, and thus monitoring and positioning of partial discharge plays a vital role in maintenance and operation safety of electrical power equipment. At present, ultrasonic sensors and temperature sensors are widely applied to partial discharge monitoring of electric power equipment, however, the prior art generally only performs simple signal processing and analysis, and cannot accurately judge abnormal positions and health states of the equipment. The prior art has the technical problem that the abnormal position of partial discharge cannot be accurately determined.
Disclosure of Invention
The intelligent early warning method and the system for monitoring the partial dynamic discharge effectively solve the technical problem that the abnormal position of the partial discharge cannot be accurately determined in the prior art, and achieve the technical effect of accurately determining the abnormal position.
The application provides an intelligent early warning method and system for monitoring partial dynamic discharge, and the technical scheme is as follows:
in a first aspect, an embodiment of the present application provides an intelligent early warning method for monitoring partial dynamic discharge, where the method includes:
acquiring a target feature set of a monitoring target, wherein the target feature set is constructed by extracting structural features and equipment features of interaction data after communication connection with the monitoring target is established;
carrying out probability evaluation of partial discharge on the monitoring target, and establishing a probability identifier of partial discharge of spatial distribution;
performing attention analysis of the monitoring target by the probability identification and the equipment characteristic, and recording sensor coordinates based on an attention analysis result array ultrasonic sensor and an optical fiber temperature sensor;
Performing influence mapping construction of ultrasonic signals according to the structural features and the sensor coordinates;
real-time monitoring of a monitoring target is carried out through an ultrasonic sensor and an optical fiber temperature sensor of the array, and ultrasonic feedback data and temperature feedback data are received;
performing signal intensity analysis on the ultrasonic feedback data, performing ultrasonic positioning compensation according to a signal intensity analysis result, the influence mapping and the temperature feedback data, and determining an abnormal position;
And carrying out signal reduction through the abnormal position and the influence mapping, and generating an early warning result of partial dynamic discharge based on the signal reduction result and the abnormal position.
In a second aspect, an embodiment of the present application provides an intelligent early warning system for monitoring partial dynamic discharge, the system including:
The device comprises a target feature set acquisition module, a monitoring target processing module and a monitoring target processing module, wherein the target feature set acquisition module is used for acquiring a target feature set of a monitoring target, wherein the target feature set is constructed by extracting structural features and equipment features of interaction data after communication connection with the monitoring target is established;
the partial discharge probability evaluation module is used for carrying out partial discharge probability evaluation on the monitoring target and establishing a spatial distribution partial discharge probability identifier;
the attention analysis module is used for carrying out attention analysis of the monitoring target by the probability identification and the equipment characteristic, and recording sensor coordinates based on an attention analysis result array ultrasonic sensor and an optical fiber temperature sensor;
The influence map construction module is used for carrying out influence map construction of ultrasonic signals according to the structural features and the sensor coordinates;
the feedback data receiving module is used for monitoring a monitoring target in real time through an ultrasonic sensor and an optical fiber temperature sensor of the array and receiving ultrasonic feedback data and temperature feedback data;
the ultrasonic positioning compensation module is used for carrying out signal intensity analysis on the ultrasonic feedback data, carrying out ultrasonic positioning compensation according to a signal intensity analysis result, the influence mapping and the temperature feedback data, and determining an abnormal position;
And the early warning result generation module is used for carrying out signal reduction through the abnormal position and the influence mapping and generating an early warning result of partial dynamic discharge based on the signal reduction result and the abnormal position.
One or more technical solutions provided in the embodiments of the present application at least have the following technical effects or advantages:
The method comprises the steps of firstly obtaining a target feature set of a monitoring target, after communication connection with the monitoring target is established, carrying out partial discharge probability evaluation on the monitoring target through extracting structural features and equipment features of interaction data, then establishing a spatial distribution probability mark, further carrying out attention analysis on the monitoring target through the probability mark and the equipment features, carrying out influence mapping construction of ultrasonic signals according to structural features and sensor coordinates, carrying out real-time monitoring on the monitoring target through the ultrasonic sensors and the optical fiber temperature sensors of the array, receiving ultrasonic feedback data and temperature feedback data, carrying out signal intensity analysis on the ultrasonic feedback data, carrying out ultrasonic positioning compensation according to signal intensity analysis results, influence mapping and temperature feedback data, determining abnormal positions, finally carrying out signal reduction through the abnormal positions and the influence mapping, and generating early warning results of partial dynamic discharge based on the signal reduction results and the abnormal positions. The technical problem that the abnormal position of partial discharge cannot be accurately determined in the prior art is effectively solved, and the technical effect of accurately determining the abnormal position is achieved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of an intelligent early warning method for monitoring partial dynamic discharge according to an embodiment of the present application;
FIG. 2 is a schematic flow chart of a method for analyzing interest of a monitored target according to an embodiment of the present application;
FIG. 3 is a schematic flow chart of a method for performing ultrasonic positioning compensation according to an embodiment of the present application;
FIG. 4 is a flowchart of a method for updating strength loss reduction results according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an intelligent early warning system for monitoring partial dynamic discharge according to an embodiment of the present application.
Reference numerals illustrate: the system comprises a target feature set acquisition module 1, a partial discharge probability evaluation module 2, a focus analysis module 3, an influence mapping construction module 4, a feedback data receiving module 5, an ultrasonic positioning compensation module 6 and an early warning result generation module 7.
Detailed Description
The application provides an intelligent early warning method and system for monitoring partial dynamic discharge, which are used for solving the technical problem that the abnormal position of partial discharge cannot be accurately determined in the prior art.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. 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 be within the scope of the application.
It should be noted that the terms "comprises" and "comprising," along with any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or modules not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
As shown in fig. 1, the present invention provides an intelligent early warning method for monitoring partial dynamic discharge, which is used for accurately determining a position where a partial discharge abnormality occurs, and the method includes:
A monitoring target is determined, where the monitoring target refers to a specific device or system part to be monitored, including a transformer, a breaker, an insulator, and other key parts in a power system, or other devices related to high-voltage power, and partial discharge may occur in the device or system part during operation. After the monitoring target is determined, communication connection is established with the monitoring target, interaction data are acquired through the communication connection, a series of characteristics of the monitoring target are extracted from the interaction data, the characteristics describe the characteristics of the monitoring target, a target characteristic set of the monitoring target is constructed through the characteristics, the target characteristic set comprises structural characteristics and equipment characteristics of the monitoring target, wherein the structural characteristics refer to characteristics related to the physical structure or the electrical structure of the monitoring target, and the structural characteristics comprise the size, the shape, the material composition and the like of the equipment; the device characteristics refer to characteristics related to the type, manufacturer, model, operation parameters, etc. of the device of the monitoring target, for example, for a transformer, the device characteristics include capacity, voltage level, cooling mode, etc.
And carrying out probability evaluation of partial discharge on the monitoring target, wherein the partial discharge refers to tiny electric sparks or current pulses generated by some reason inside the equipment, the probability evaluation is carried out on the probability of the partial discharge, specifically, a probability model of the partial discharge is established based on historical data of the monitoring target and equipment checking results, the historical data comprise operation parameters, environmental conditions, historical maintenance records and the like of the equipment, the equipment checking comprises appearance, structure, connection and the like, the probability model of the partial discharge can comprehensively consider factors such as equipment aging, environmental conditions, operation modes and the like according to input data, the probability of the partial discharge generated by the monitoring target in a future period is predicted, and the discharge probability evaluation results are output. Based on the discharge probability evaluation result, a probability identifier of partial discharge of a space distribution is established, the probability identifier is established and is used for describing the distribution condition of the partial discharge probability in space, firstly, the space of a monitoring target is divided to form a series of discrete space units or grids, each space unit represents a specific position, position information in the discharge probability evaluation result output by a probability model is matched with coordinates of the space unit, the association of the discharge probability and the space unit is established, the probability value is mapped to the corresponding space unit, and a visual probability distribution map or identifier is formed, namely, the probability identifier of the partial discharge of the space distribution is generated.
And carrying out attention analysis of the monitoring target by using the probability identification and the equipment characteristics, wherein the attention analysis refers to evaluating the importance of the monitoring target by using the probability identification and the equipment characteristics of partial discharge, and determining the area or the part needing to be closely attended according to the attention analysis, specifically, evaluating the probability of partial discharge of different space positions according to the probability identification of partial discharge of spatial distribution, wherein a high probability area is regarded as the area needing special attention, and meanwhile, taking the equipment characteristics into the analysis, for example, certain equipment is easier to cause partial discharge due to the type, age, material or other factors, then the specific part of the equipment or the equipment is given a higher attention degree, and finally, the partial discharge probability and the equipment characteristics are comprehensively considered, and each space position or the equipment part is allocated an attention grade, wherein the attention grade can be a numerical value, a color code or other identification and is used for representing the attention degree of the position or the part. And determining which positions are required to be provided with the ultrasonic sensor and the optical fiber temperature sensor for more intimate monitoring based on the attention analysis result, wherein the positions or positions with high attention level are subjected to optimization and other modes to achieve sufficient monitoring precision of relevant positions, the positions of the sensors are determined and are arrayed, and then the space coordinates of each sensor are recorded.
The structural characteristics of the monitoring target influence the propagation path, intensity and distribution of the ultrasonic signals, for example, factors such as materials, sizes, shapes and the like in the equipment structure influence the propagation speed and attenuation degree of ultrasonic waves, and the influence of different structural characteristics on the ultrasonic signals is different, depending on the frequency, wavelength and specific parameters of the structural characteristics of the signals, so that the relation between the structural characteristics and the ultrasonic signals needs to be mapped, and the influence mapping relation of the structural characteristics on the ultrasonic signals is constructed. Each sensor has its specific coordinates representing its position in the device or system, and the different sensor coordinates correspond to different device structural features, e.g. the position of one sensor may be closer to a specific part of the device or to a critical structure, different structural features (e.g. hardness, permittivity, size, etc. of the material) may have an effect on the propagation of the ultrasonic signal, e.g. a hard material may attenuate the ultrasonic signal faster, whereas a material with a high permittivity may affect the propagation speed of the ultrasonic wave, and the specific device structural features represented by each coordinate are different due to the different coordinates of the sensor, and therefore for each sensor coordinate it is necessary to evaluate its corresponding critical structural feature, by collecting data about the structural feature, correlating each sensor coordinate with its corresponding critical structural feature, establishing a mapping relation for analyzing the propagation of the ultrasonic signal at each sensor position, by using these mappings to adjust or correct the interpretation of the signal.
The monitoring target is continuously observed and measured in real time through the ultrasonic sensors and the optical fiber temperature sensors of the array, and ultrasonic feedback data and temperature feedback data are received, wherein the feedback data are data reflecting the monitoring result.
The signal intensity analysis is performed on the ultrasonic feedback data, and as the signal intensity provides the propagation information of the ultrasonic signal in the monitoring target, such as attenuation, scattering and the like of the signal, the analysis on the signal intensity is helpful to understand the intensity and the range of partial discharge, and the signal intensity analysis result is obtained through the analysis, wherein the signal intensity analysis result is a quantized index, such as the amplitude, the energy or the power of the signal, and reflects the intensity and the propagation characteristics of the ultrasonic signal. The method comprises the steps of determining the position and intensity information of partial discharge through a signal intensity analysis result, wherein the structural characteristics of a monitoring target cause scattering, refraction or attenuation of an ultrasonic signal to influence the positioning accuracy, the influence mapping relation describes the specific propagation influence of the structural characteristics on the ultrasonic signal, so that the preliminary positioning result is corrected through the influence mapping, the propagation speed of the ultrasonic wave is influenced by the temperature due to the fact that the partial discharge is accompanied with the temperature rise, and the positioning accuracy is further influenced, the ultrasonic positioning result is corrected through temperature feedback data, ultrasonic positioning compensation is carried out through three factors including the comprehensive signal intensity analysis result, the influence mapping and the temperature feedback data, and finally the abnormal position where the partial discharge occurs is determined.
For each abnormal position, inquiring the structural characteristics related to the abnormal position, determining the influence relation of the ultrasonic signals matched with the abnormal position through the influence mapping relation (the influence mapping) between the related structure and the ultrasonic signals, further restoring the ultrasonic signals by using the corresponding influence mapping for each abnormal position, analyzing the restored ultrasonic signals after restoring, extracting key characteristics such as frequency, amplitude, phase and the like, and finally generating early warning results of partial dynamic discharge based on the signal restoring results and the abnormal positions, wherein the early warning results comprise warning level, discharge type, discharge trend and the like, for example, if the restored ultrasonic signals show high amplitude and specific frequency, the partial discharge of a certain specific type exists, and the discharge is dynamic or has development trend. According to the embodiment of the application, through extracting the target feature set, carrying out partial discharge probability evaluation, focusing analysis, constructing influence mapping, monitoring ultrasonic feedback data and temperature feedback data in real time, and carrying out signal intensity analysis and ultrasonic positioning compensation, the technical effect of accurately determining the abnormal position of partial discharge is finally achieved.
In a preferred implementation manner provided by the embodiment of the present application, as shown in fig. 2, the method further includes:
The conversion ratio of the partial discharge probability to the device key value is established, the device key value reflects the value and the importance of the device, the higher the device key value is, the more critical and important the device is, because the probability identification data and the key value data of the device are inconsistent in dimension, format and the like, data conversion is needed, the difference between the data is eliminated by establishing the conversion relation between the partial discharge probability and the device key value, so that the data can be compared and calculated, for example, an electric device is assumed, the device key value of the electric device is higher because the electric device is a key component, and an appropriate conversion ratio can be set, so that the device with high key value obtains higher weight on the partial discharge probability.
The key value of the equipment is related to the characteristics of the equipment, the key value calculation of the equipment can be performed through the equipment characteristics, and the equipment key value calculation result is generated through calculation according to factors such as the type, age, material, history maintenance record and the like of the equipment.
Combining the calculated device key value with the probability identifier, and performing normalization calculation according to the established conversion ratio, for example, assuming that the reference of the device key value is 10, that is, when a certain device key value is 10, the attention analysis result is equal to the partial discharge probability of the device in value, and the set conversion ratio is: for every 10 increases in the key value, the partial discharge probability increases by 0.1, and assuming that the partial discharge probability of the device a is 0.2 and the device key value is 10, the attention analysis result of the device a is: 0.2+0=0.2; assuming that the partial discharge probability of the device B is 0.2 and the device key value is 30, the analysis result of interest of the device B is: Through the normalization calculation, the attention analysis of the monitoring target is realized, and the sensor can be further arranged according to the attention analysis result. According to the preferred embodiment, dimension and format differences among different data are eliminated through normalization processing, so that key values and partial discharge probabilities of different devices can be compared and calculated, attention degrees among different devices can be analyzed and compared more easily by converting the data to the same dimension, and further, according to attention analysis result array sensors, reasonable arrangement of the sensors is achieved, and therefore the technical effects of improving monitoring effects and accuracy are achieved.
In another preferred implementation manner provided by the embodiment of the present application, as shown in fig. 3, the method further includes:
And checking and analyzing the collected ultrasonic feedback data, identifying whether abnormal data exist by comparing the relation between the current data and historical data, a threshold value or other standards, and recording the time node of an abnormal signal, namely the occurrence time of data abnormality, if the abnormal data are found.
After determining the time node of the abnormal signal, backtracking and expanding the ultrasonic signal data near the time node, including expanding a time window, so as to acquire more context information. Based on the backtracking of the augmented data, a verification location window is determined that contains the anomaly signal and sufficient data to verify and locate the anomaly.
And acquiring temperature feedback data related to the ultrasonic feedback data from the optical fiber temperature sensor in the verification positioning window, wherein the temperature feedback data comprises a temperature value, a temperature change rate, temperature distribution and the like, and further determining the spatial distribution of the temperature data according to the coordinates of the optical fiber temperature sensor. And then, carrying out abnormality judgment on the temperature data according to parameters (such as measuring range, precision, response time and the like) of the optical fiber temperature sensor, for example, if the temperature value of a certain area is out of a normal range or the temperature change rate is abnormal, considering that the area is abnormal. And determining the position and the range of the abnormality through abnormality positioning analysis, and generating positioning auxiliary results comprising information such as the position, the range, the severity and the like of the abnormal region.
And finally, compensating the ultrasonic positioning according to the positioning auxiliary result, including correction of an ultrasonic propagation model, adjustment of partial discharge prediction or optimization of other positioning algorithms, and the like, and improving the accuracy and reliability of the ultrasonic positioning through ultrasonic positioning compensation to finally determine the abnormal position. According to the preferred embodiment, more context information is obtained by backtracking and expanding ultrasonic signal data near the abnormal signal time node, and by determining the verification positioning window, the sufficient and reliable verification and positioning of abnormal data is ensured, so that the technical effects of improving the accuracy and reliability of abnormal positioning are achieved.
In another preferred implementation manner provided by the embodiment of the present application, the method further includes:
And clustering the ultrasonic feedback data by using a clustering algorithm (such as K-means, hierarchical clustering and the like), classifying the data with similar signal intensity together by clustering, dividing the data into different clusters, and generating a signal intensity clustering result after the clustering is completed, wherein each cluster represents a group of data with similar signal intensity.
In the signal strength clustering result, the largest cluster is found, and the largest cluster contains data points with the largest signal strength, which represent abnormality or need further attention, and the largest cluster is used as verification feature for checking whether other areas have data points similar to the feature. And screening a positioning auxiliary result by using the established influence mapping and the maximum cluster as a verification feature, screening out areas more similar to abnormal or to-be-focused data points, and determining one or more screening areas which are abnormal or to-be-focused places according to the screening result.
And calculating average difference values of ultrasonic feedback data and the largest cluster in the screening area, wherein the average difference values are used for evaluating the similarity between the screening area and the largest cluster, determining which areas have higher abnormal degrees by comparing the average difference values of different areas, compensating ultrasonic positioning according to the difference values by using a compensation model based on the average difference values, thereby more accurately determining abnormal positions, correcting and optimizing the ultrasonic positioning according to the compensation result, and adjusting parameters of an ultrasonic propagation model, adjusting a partial discharge prediction algorithm and the like. According to the preferred embodiment, the influence of noise and abnormal data is reduced through signal intensity clustering, the robustness of an algorithm is enhanced, the abnormal region is more accurately identified through screening and compensation by combining influence mapping, the possibility of false alarm is reduced, and therefore the technical effects of improving the accuracy and the robustness of ultrasonic positioning are achieved.
In another preferred implementation manner provided by the embodiment of the present application, the method further includes:
Selecting a maximum cluster from the signal strength clustering results, identifying signals with signal strength exceeding the maximum cluster, and marking the signals exceeding the maximum cluster in the maximum cluster and the signal strength clustering results as time verification signals.
For each time verification signal, the corresponding sensor coordinates are obtained, and by taking the sensor coordinates and the signal time sequence of the time verification signal as inputs, in combination with the time sequence information (such as the change of the signal strength along with the time), an objective function is constructed, wherein the objective function is used for describing the relationship between the abnormal position and the sensor coordinates and the signal time sequence, and a plurality of factors such as the signal strength, the signal duration, the sensor position and the like are considered for determining the abnormal position.
And (3) optimizing and restraining the objective function by using a compensation result, wherein the compensation result is a result obtained by correcting or adjusting the ultrasonic signal, provides information about signal quality and accuracy, further optimizes the objective function by taking the compensation result as a constraint condition, and finds an optimal solution meeting the objective function, namely an abnormal position, by carrying out an optimization algorithm, such as gradient descent, genetic algorithm and the like, on the objective function. In the preferred embodiment, various factors (including the spatial position of the sensor, the time sequence information of the signal and the compensation result) are considered in the optimizing process, and the abnormal position is more accurately determined, so that the technical effect of improving the accuracy and efficiency of abnormal detection is achieved.
In another preferred implementation manner provided by the embodiment of the present application, the method further includes:
According to the determined abnormal position, relevant ultrasonic feedback data are screened out, data integrity evaluation indexes (such as data continuity, deletion rate and the like) are used for evaluating the data for accurate characteristic analysis and propagation condition analysis, and according to the evaluation result, a part of ultrasonic signals with higher data integrity evaluation (which ensure that the analyzed ultrasonic signals are of high quality) are selected as the objects of subsequent analysis, namely the positioning selected ultrasonic signals.
For each selected ultrasonic signal, searching the corresponding influence mapping, calculating the intensity loss (such as attenuation and scattering) of the signal in the propagation process by using the influence mapping relations, carrying out reduction processing on the signal according to the calculated intensity loss, and accurately analyzing the characteristics and propagation condition of the ultrasonic signal by reducing the intensity loss of the signal.
Combining the reduction result of the strength loss and the information of the abnormal position, determining an early warning value by superposing the result of the strength loss on the abnormal position and the like, wherein the early warning value is used as an index for indicating the severity of the abnormal condition, and further outputting the early warning value as an early warning result to provide references for subsequent fault diagnosis, maintenance and the like. According to the preferred embodiment, the ultrasonic feedback data is evaluated by using the data integrity evaluation index, so that the analyzed ultrasonic signal is ensured to be of high quality, the technical effects of improving the accuracy and the reliability of analysis are achieved, and the early warning value is output as an early warning result, so that a quantifiable reference is provided for subsequent fault diagnosis, maintenance and the like, and the technical effect of providing powerful support for decision making is achieved.
In another preferred implementation manner provided by the embodiment of the present application, as shown in fig. 4, the method further includes:
the selected ultrasound signals are subjected to data structure analysis to determine whether they are independent data, which refers to data that is not directly related or dependent on other data.
If a selected ultrasonic signal is independent data, which indicates that the ultrasonic signal is not influenced and interfered by other signals, a corresponding verification instruction is generated according to the characteristics of the selected ultrasonic signal and verification requirements, wherein the verification instruction is used for verifying whether the selected ultrasonic signal accords with expectations or standards, and is an instruction used for guiding how to perform verification.
According to the verification instructions, the selected ultrasonic signals are subjected to verification processing, namely, the selected ultrasonic signals are compared with known normal or standard signals, specifically, verification data related to the signals are collected and processed, verification data are used for verifying the authenticity and accuracy of the signals, and if the similarity between the selected ultrasonic signals and the verification data is high, the signals are considered to be credible or effective.
Updating the intensity loss reduction result according to the authentication result, namely if the selected ultrasonic signal passes the authentication, indicating that the signal is high-quality data, and the intensity loss reduction result carried out on the signal before is not affected; if the selected ultrasonic signal is not authenticated, indicating that the ultrasonic signal is not high-quality and accurate, further processing or correction is needed to ensure the accuracy of the ultrasonic signal, and the intensity loss reduction result is correspondingly adjusted and updated according to the correction result. According to the preferred embodiment, the high-quality ultrasonic signals are screened out through data structure analysis and verification instruction generation, and signals possibly affected by interference or abnormality are removed, so that the technical effect of improving the data quality is achieved.
Example two
Based on the same inventive concept as the intelligent early warning method for partial dynamic discharge monitoring in the foregoing embodiments, as shown in fig. 5, the present application provides an intelligent early warning system for partial dynamic discharge monitoring, the system comprising:
The target feature set acquisition module 1 is used for acquiring a target feature set of a monitoring target, wherein the target feature set is constructed by extracting structural features and equipment features of interaction data after communication connection with the monitoring target is established;
the partial discharge probability evaluation module 2 is used for evaluating the probability of partial discharge of the monitoring target and establishing a spatial distribution probability identifier of the partial discharge;
A focus analysis module 3, wherein the focus analysis module 3 is used for performing focus analysis of the monitoring target with the probability identification and the equipment characteristic, and based on focus analysis result, an ultrasonic sensor and an optical fiber temperature sensor are arranged, and sensor coordinates are recorded;
The influence map construction module 4 is used for carrying out influence map construction of ultrasonic signals according to the structural features and the sensor coordinates;
The feedback data receiving module 5 is used for monitoring a monitoring target in real time through the ultrasonic sensor and the optical fiber temperature sensor of the array, and receiving ultrasonic feedback data and temperature feedback data;
The ultrasonic positioning compensation module 6 is used for carrying out signal intensity analysis on the ultrasonic feedback data, carrying out ultrasonic positioning compensation according to a signal intensity analysis result, the influence mapping and the temperature feedback data, and determining an abnormal position;
The early warning result generation module 7 is used for carrying out signal reduction through the abnormal position and the influence mapping, and generating an early warning result of partial dynamic discharge based on the signal reduction result and the abnormal position.
Further, the attention analysis module 3 is configured to perform the following method:
establishing a conversion ratio of partial discharge probability to a key value of the equipment;
Calculating the key value of the equipment through the equipment characteristics to generate an equipment key value calculation result;
carrying out normalization calculation based on the equipment key value calculation result, the probability identification and the conversion proportion;
And (5) completing the attention analysis by normalizing the calculation result.
Further, the ultrasonic positioning compensation module 6 is configured to perform the following method:
Performing data abnormality evaluation on the ultrasonic feedback data, and determining a time node of an abnormal signal;
performing backtracking expansion of signals on the time node to determine a verification positioning window;
acquiring temperature feedback data in a verification positioning window, and performing abnormal positioning of the temperature feedback data according to sensor coordinates and sensor parameters to generate a positioning auxiliary result;
and completing ultrasonic positioning compensation according to the positioning auxiliary result.
Further, the ultrasonic positioning compensation module 6 is configured to perform the following method:
Performing signal intensity clustering based on the ultrasonic feedback data to generate a signal intensity clustering result;
acquiring a maximum cluster in a signal strength clustering result, taking the maximum cluster as a verification feature, and carrying out region screening of a positioning auxiliary result based on influence mapping to determine a screening region;
and carrying out screening area compensation through the average difference value between other data in the ultrasonic feedback data and the maximum cluster, and completing ultrasonic positioning compensation according to a compensation result.
Further, the ultrasonic positioning compensation module 6 is configured to perform the following method:
taking the signal exceeding the maximum cluster in the maximum cluster and signal strength clustering result as a time verification signal;
Constructing an objective function based on the sensor coordinates and signal timing of the time verification signal;
And carrying out optimization constraint on the objective function through the compensation result, and determining the abnormal position.
Further, the early warning result generating module 7 is configured to execute the following method:
performing data integrity evaluation of ultrasonic feedback data based on the abnormal position, and positioning the selected ultrasonic signals;
Extracting an influence map corresponding to the selected ultrasonic signal, and executing strength loss reduction of the signal;
And determining an early warning value according to the strength loss reduction result and the abnormal position, and outputting the early warning value as an early warning result.
Further, the early warning result generating module 7 is configured to execute the following method:
judging whether the selected ultrasonic signal is independent data or not;
If the selected ultrasonic signal is independent data, generating a verification instruction;
Authenticating the selected ultrasonic signals based on verification data through the verification instruction;
and updating the strength loss reduction result according to the authentication result.
It should be noted that the sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. Other embodiments are within the scope of the application. In some cases, the acts or steps recited in the present application may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The foregoing description of the preferred embodiments of the application is not intended to limit the application to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the application are intended to be included within the scope of the application.
The specification and figures are merely exemplary illustrations of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents that fall within the scope of the application. It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the scope of the application. Thus, the present application is intended to include such modifications and alterations insofar as they come within the scope of the application or the equivalents thereof.
Claims (6)
1. The intelligent early warning method for monitoring the partial dynamic discharge is characterized by comprising the following steps of:
acquiring a target feature set of a monitoring target, wherein the target feature set is constructed by extracting structural features and equipment features of interaction data after communication connection with the monitoring target is established;
carrying out probability evaluation of partial discharge on the monitoring target, and establishing a probability identifier of partial discharge of spatial distribution;
performing attention analysis of the monitoring target by the probability identification and the equipment characteristic, and recording sensor coordinates based on an attention analysis result array ultrasonic sensor and an optical fiber temperature sensor;
Performing influence mapping construction of ultrasonic signals according to the structural features and the sensor coordinates;
real-time monitoring of a monitoring target is carried out through an ultrasonic sensor and an optical fiber temperature sensor of the array, and ultrasonic feedback data and temperature feedback data are received;
performing signal intensity analysis on the ultrasonic feedback data, performing ultrasonic positioning compensation according to a signal intensity analysis result, the influence mapping and the temperature feedback data, and determining an abnormal position;
performing signal reduction through the abnormal position and the influence mapping, and generating an early warning result of partial dynamic discharge based on a signal reduction result and the abnormal position;
Performing data abnormality evaluation on the ultrasonic feedback data, and determining a time node of an abnormal signal;
performing backtracking expansion of signals on the time node to determine a verification positioning window;
acquiring temperature feedback data in a verification positioning window, and performing abnormal positioning of the temperature feedback data according to sensor coordinates and sensor parameters to generate a positioning auxiliary result;
Completing ultrasonic positioning compensation according to the positioning auxiliary result;
Performing signal intensity clustering based on the ultrasonic feedback data to generate a signal intensity clustering result;
acquiring a maximum cluster in a signal strength clustering result, taking the maximum cluster as a verification feature, and carrying out region screening of a positioning auxiliary result based on influence mapping to determine a screening region;
and carrying out screening area compensation through the average difference value between other data in the ultrasonic feedback data and the maximum cluster, and completing ultrasonic positioning compensation according to a compensation result.
2. The method of claim 1, wherein the method further comprises:
establishing a conversion ratio of partial discharge probability to a key value of the equipment;
Calculating the key value of the equipment through the equipment characteristics to generate an equipment key value calculation result;
carrying out normalization calculation based on the equipment key value calculation result, the probability identification and the conversion proportion;
And (5) completing the attention analysis by normalizing the calculation result.
3. The method of claim 1, wherein the method further comprises:
taking the signal exceeding the maximum cluster in the maximum cluster and signal strength clustering result as a time verification signal;
Constructing an objective function based on the sensor coordinates and signal timing of the time verification signal;
And carrying out optimization constraint on the objective function through the compensation result, and determining the abnormal position.
4. The method of claim 1, wherein the method further comprises:
performing data integrity evaluation of ultrasonic feedback data based on the abnormal position, and positioning the selected ultrasonic signals;
Extracting an influence map corresponding to the selected ultrasonic signal, and executing strength loss reduction of the signal;
And determining an early warning value according to the strength loss reduction result and the abnormal position, and outputting the early warning value as an early warning result.
5. The method of claim 4, wherein the method further comprises:
judging whether the selected ultrasonic signal is independent data or not;
If the selected ultrasonic signal is independent data, generating a verification instruction;
Authenticating the selected ultrasonic signals based on verification data through the verification instruction;
and updating the strength loss reduction result according to the authentication result.
6. An intelligent early warning system for local dynamic discharge monitoring, the system comprising:
The device comprises a target feature set acquisition module, a monitoring target processing module and a monitoring target processing module, wherein the target feature set acquisition module is used for acquiring a target feature set of a monitoring target, wherein the target feature set is constructed by extracting structural features and equipment features of interaction data after communication connection with the monitoring target is established;
the partial discharge probability evaluation module is used for carrying out partial discharge probability evaluation on the monitoring target and establishing a spatial distribution partial discharge probability identifier;
the attention analysis module is used for carrying out attention analysis of the monitoring target by the probability identification and the equipment characteristic, and recording sensor coordinates based on an attention analysis result array ultrasonic sensor and an optical fiber temperature sensor;
The influence map construction module is used for carrying out influence map construction of ultrasonic signals according to the structural features and the sensor coordinates;
the feedback data receiving module is used for monitoring a monitoring target in real time through an ultrasonic sensor and an optical fiber temperature sensor of the array and receiving ultrasonic feedback data and temperature feedback data;
the ultrasonic positioning compensation module is used for carrying out signal intensity analysis on the ultrasonic feedback data, carrying out ultrasonic positioning compensation according to a signal intensity analysis result, the influence mapping and the temperature feedback data, and determining an abnormal position;
The early warning result generation module is used for carrying out signal reduction through the abnormal position and the influence mapping and generating an early warning result of partial dynamic discharge based on the signal reduction result and the abnormal position;
the ultrasonic positioning compensation module is used for executing the following method:
Performing data abnormality evaluation on the ultrasonic feedback data, and determining a time node of an abnormal signal;
performing backtracking expansion of signals on the time node to determine a verification positioning window;
acquiring temperature feedback data in a verification positioning window, and performing abnormal positioning of the temperature feedback data according to sensor coordinates and sensor parameters to generate a positioning auxiliary result;
Completing ultrasonic positioning compensation according to the positioning auxiliary result;
Performing signal intensity clustering based on the ultrasonic feedback data to generate a signal intensity clustering result;
acquiring a maximum cluster in a signal strength clustering result, taking the maximum cluster as a verification feature, and carrying out region screening of a positioning auxiliary result based on influence mapping to determine a screening region;
and carrying out screening area compensation through the average difference value between other data in the ultrasonic feedback data and the maximum cluster, and completing ultrasonic positioning compensation according to a compensation result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311725284.6A CN117538710B (en) | 2023-12-14 | 2023-12-14 | Intelligent early warning method and system for local dynamic discharge monitoring |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311725284.6A CN117538710B (en) | 2023-12-14 | 2023-12-14 | Intelligent early warning method and system for local dynamic discharge monitoring |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117538710A CN117538710A (en) | 2024-02-09 |
| CN117538710B true CN117538710B (en) | 2024-07-23 |
Family
ID=89784254
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311725284.6A Active CN117538710B (en) | 2023-12-14 | 2023-12-14 | Intelligent early warning method and system for local dynamic discharge monitoring |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117538710B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117970061B (en) * | 2024-04-02 | 2024-06-11 | 山东泰开电力电子有限公司 | High-voltage power capacitor fault early warning method and system |
| CN118395365B (en) * | 2024-07-01 | 2024-09-06 | 广东佰林电气设备厂有限公司 | Power box with function of monitoring abnormal metering data and monitoring method |
| CN118483510A (en) * | 2024-07-16 | 2024-08-13 | 扬州乐军电子科技有限公司 | Power utilization safety monitoring method and early warning device for distribution box |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2006119764A1 (en) * | 2005-05-13 | 2006-11-16 | Brüel & Kjær Sound & Vibration Measurement A/S | Determination of the position of an object |
| CN112213585A (en) * | 2020-10-10 | 2021-01-12 | 国网山东省电力公司枣庄供电公司 | High-voltage switch cabinet partial discharge positioning method and system considering temperature field change |
| CN117148076A (en) * | 2023-10-31 | 2023-12-01 | 南通豪强电器设备有限公司 | Multi-feature fusion type high-voltage switch cabinet partial discharge identification method and system |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050124883A1 (en) * | 2003-11-20 | 2005-06-09 | Hunt Thomas J. | Adaptive parallel artifact mitigation |
| JP5922508B2 (en) * | 2012-06-20 | 2016-05-24 | 株式会社フジクラ | Partial discharge measurement method |
| US20160369777A1 (en) * | 2015-06-03 | 2016-12-22 | Bigwood Technology, Inc. | System and method for detecting anomaly conditions of sensor attached devices |
| KR101729112B1 (en) * | 2015-12-31 | 2017-04-21 | 주식회사 효성 | Method and device for diagnosing Partial Discharge of Gas Insulated Switchgear |
| CN110031729B (en) * | 2018-12-08 | 2021-02-09 | 全球能源互联网欧洲研究院 | Detection method and system of partial discharge signal source and data fusion analysis unit |
| CN114910758B (en) * | 2022-05-17 | 2023-05-12 | 国网黑龙江省电力有限公司佳木斯供电公司 | Switch equipment partial discharge detection method based on intelligent sound-electricity combined sensing |
| CN115494356A (en) * | 2022-09-20 | 2022-12-20 | 江苏方天电力技术有限公司 | Intelligent online monitoring system and method for partial discharge of power equipment |
| CN116008753A (en) * | 2023-01-10 | 2023-04-25 | 聚为(天津)信息技术有限公司 | Intelligent monitoring method and system for cable |
| CN116679177A (en) * | 2023-07-13 | 2023-09-01 | 广东电网有限责任公司 | Cable joint partial discharge on-line monitoring device and method and power system |
-
2023
- 2023-12-14 CN CN202311725284.6A patent/CN117538710B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2006119764A1 (en) * | 2005-05-13 | 2006-11-16 | Brüel & Kjær Sound & Vibration Measurement A/S | Determination of the position of an object |
| CN112213585A (en) * | 2020-10-10 | 2021-01-12 | 国网山东省电力公司枣庄供电公司 | High-voltage switch cabinet partial discharge positioning method and system considering temperature field change |
| CN117148076A (en) * | 2023-10-31 | 2023-12-01 | 南通豪强电器设备有限公司 | Multi-feature fusion type high-voltage switch cabinet partial discharge identification method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117538710A (en) | 2024-02-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117538710B (en) | Intelligent early warning method and system for local dynamic discharge monitoring | |
| KR101554216B1 (en) | Method and apparatus thereof for verifying bad patterns in sensor-measured time series data | |
| JP2000512766A (en) | Statistical pattern analysis method for partial discharge measurement in high voltage insulation | |
| CN116559598B (en) | Smart distribution network fault positioning method and system | |
| KR102301201B1 (en) | Apparatus and method for precise state diagnosis of rotating machinery based on IoT sensor | |
| CN112734977B (en) | Equipment risk early warning system and algorithm based on Internet of things | |
| CN117370847B (en) | Deep learning-based disconnecting switch detection method and device | |
| CN116304909A (en) | Abnormality detection model training method, fault scene positioning method and device | |
| CN117111544B (en) | Automatic-adaptation building internet of things monitoring method and system | |
| CN117368651B (en) | Comprehensive analysis system and method for faults of power distribution network | |
| CN118091234B (en) | Current transformer for fault diagnosis processing | |
| CN117076955A (en) | Fault detection method and system for high-voltage frequency converter | |
| CN117200394A (en) | BMS battery management method and system based on BIM model | |
| CN117889945B (en) | Highway bridge construction vibration testing method | |
| CN116704733A (en) | Aging early warning method and system for aluminum alloy cable | |
| CN116520068B (en) | Diagnostic method, device, equipment and storage medium for electric power data | |
| CN117672255B (en) | Abnormal equipment identification method and system based on artificial intelligence and equipment operation sound | |
| CN110275896B (en) | Optical cable intrusion construction event identification method, device, equipment and readable storage medium | |
| CN116434368A (en) | Multifunctional handheld inspection instrument and inspection method | |
| CN115169385A (en) | Method and system for fitting target sensor for vehicle, and storage medium | |
| CN118100447B (en) | Intelligent monitoring method and system for high-voltage distribution line based on Internet of things | |
| CN118310612B (en) | Vehicle weighing method and device based on non-contact vibration detection and computer equipment | |
| CN117572158B (en) | Wave recording positioning fault indication method, system and indicator | |
| CN117668518B (en) | Discrete intelligent manufacturing method and system | |
| CN114547971A (en) | Fatigue damage state identification method and system for railway frog |
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 |