CN114113911A - Fault waveform-based fault type discrimination method and discrimination system - Google Patents
Fault waveform-based fault type discrimination method and discrimination system Download PDFInfo
- Publication number
- CN114113911A CN114113911A CN202111475878.7A CN202111475878A CN114113911A CN 114113911 A CN114113911 A CN 114113911A CN 202111475878 A CN202111475878 A CN 202111475878A CN 114113911 A CN114113911 A CN 114113911A
- Authority
- CN
- China
- Prior art keywords
- fault
- waveform
- fault type
- oscillogram
- time
- 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
- 238000012850 discrimination method Methods 0.000 title claims abstract description 19
- 238000000034 method Methods 0.000 claims abstract description 31
- 238000004422 calculation algorithm Methods 0.000 claims description 25
- 238000010586 diagram Methods 0.000 claims description 22
- 230000009191 jumping Effects 0.000 claims description 21
- 230000007704 transition Effects 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 11
- 238000013527 convolutional neural network Methods 0.000 claims description 8
- 238000013135 deep learning Methods 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 8
- 238000005070 sampling Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 5
- 150000001875 compounds Chemical class 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 abstract description 5
- 238000012545 processing Methods 0.000 abstract description 5
- 230000008569 process Effects 0.000 description 6
- 238000012549 training Methods 0.000 description 4
- 208000025274 Lightning injury Diseases 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000003709 image segmentation 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
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000036632 reaction speed Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 238000013526 transfer learning Methods 0.000 description 1
Images
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
- G01R31/08—Locating faults in cables, transmission lines, or networks
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Testing Of Short-Circuits, Discontinuities, Leakage, Or Incorrect Line Connections (AREA)
Abstract
The invention relates to the technical field of fault discrimination, and discloses a fault type discrimination method based on fault waveforms. A fault type discrimination method based on fault waveforms comprises the following steps: acquiring a fault oscillogram according to the fault recording data; and judging the fault type of the line according to the fault oscillogram. The fault type judging method based on the fault waveform reduces the difficulty of manual calculation, shortens the time of fault processing and improves the efficiency of fault processing. The embodiment of the invention also discloses a fault type discrimination system based on the fault waveform.
Description
Technical Field
The invention relates to the technical field of fault type judgment, in particular to a fault type judgment method and a fault type judgment system based on fault waveforms.
Background
The overhead transmission line is an important component of the power system, the safety state of the overhead transmission line is very important in the safe and stable operation of the line, and the fact that the fault type can be quickly judged when the overhead transmission line breaks down has important significance in efficient, stable and safe operation of the power system. At present, when a fault occurs, the type of the fault is judged by manual inspection, the consumed time is long, the reaction speed is low, and the efficiency is low.
Therefore, how to provide a method capable of improving the efficiency of determining the fault type is an urgent problem to be solved at present.
Disclosure of Invention
The embodiment of the invention provides a fault type judging method and a fault type judging system based on fault waveforms, and aims to solve the problems that the type of a fault is judged by manual inspection and the efficiency is low in the prior art. The following presents a simplified summary in order to provide a basic understanding of some aspects of the disclosed embodiments. This summary is not an extensive overview and is intended to neither identify key/critical elements nor delineate the scope of such embodiments. Its sole purpose is to present some concepts in a simplified form as a prelude to the more detailed description that is presented later.
According to a first aspect of the embodiments of the present invention, a fault type discrimination method based on a fault waveform is provided.
In one embodiment, the fault type discrimination method based on the fault waveform includes the following steps:
acquiring a fault oscillogram according to the fault recording data;
and judging the fault type of the line according to the fault oscillogram.
Optionally, the step of obtaining the fault oscillogram according to the fault recording data includes:
step (A), according to the fault recording data, obtaining the starting time and the ending time of the fault;
and (B) acquiring a fault oscillogram according to the fault starting time and the fault ending time.
Optionally, in the step (a), the step of obtaining the fault starting time according to the fault recording data includes:
when the sudden change of current starting meets the starting criterion, the starting criterion is judged to be the fault starting moment, and the criterion formula is as follows:
|Δi(n)|=|i(n)-i(n-N)|>ΔIs.set(formula 1)
In the formula,. DELTA.Is.setSetting value, Δ I, representing a sudden variable start judgments.set>0;
N represents the sampling times of each cycle;
n represents a time node, i (n) represents a current value of the time node;
in the formula, kdRepresenting a set value coefficient of a break variable starting criterion;
IA0representing the steady-state amplitude of the A-phase current;
IB0representing the steady-state amplitude of the B-phase current;
IC0representing the steady state magnitude of the C-phase current.
Optionally, in the step (a), the step of obtaining the fault termination time according to the fault recording data includes:
if in a period, all sampling points of the period simultaneously meet the condition that the absolute values of fault components in the period are all smaller than half of the load current amplitude, the current amplitudes of fault phases in the period are all smaller than the load current amplitude, and the starting time of the period is pushed forward by a period, namely the fault termination time.
Optionally, in the step (B), obtaining a fault waveform diagram according to the starting time and the ending time of the fault, including:
and obtaining the ABC three-phase voltage and a waveform diagram within the fault occurrence time according to the fault starting time and the fault ending time.
Optionally, the determining the fault type of the line according to the fault oscillogram includes:
and calculating the times of the jumping period To of the ABC three-phase voltage and the waveform within fixed time according To the ABC three-phase voltage and the waveform diagram within the fault occurrence time, and judging the fault type according To the times of the jumping period To.
Optionally, in the step (B), obtaining a fault waveform diagram according to the starting time and the ending time of the fault, including:
calculating the fault distance by using a lumped parameter method:
in the formula, DmFIs the distance to failure; f is a fault point; m and n are bus positions at two ends respectively; j is a sequence network number, is determined by the fault type, and is 1 for the three-phase short circuit J; for two-phase short circuit, J is 1, 2; short to ground, J ═ 1,2, 0; zJRepresenting an impedance; dLRepresents the total length of the line; dnFRepresents the distance from n to F;the sequence voltages representing the fault point F;represents the voltage measured by the terminal M;represents the voltage measured at the N terminal;represents the current measured by the M terminal;represents the current measured by the N terminal;
obtaining DmFThen, the sequence voltage U of the fault point F obtained by the formula (2) is combinedFJCalculating each sequence component of the short-circuit current at the fault point according to the following formula;
obtaining the transition resistance RFThe following formula:
in the formula (I), the compound is shown in the specification,in order to be the fault point current,is the fault point voltage;
according to transition resistance RFAnd drawing a fault waveform chart of the fault occurrence time.
Optionally, the determining the fault type of the line according to the fault oscillogram includes:
using an image recognition algorithm, will depend on the transition resistance RFAnd matching the drawn fault waveform image with a defined fault waveform image in a fault history library, and judging the fault type of the line.
Optionally, the image recognition algorithm comprises:
dividing the fault oscillogram into small areas;
generating a prior frame through a target detection algorithm;
screening the prior frames meeting the conditions, and outputting confidence frame;
and inputting the confidence picture frame into a convolutional neural network for deep learning to obtain a fault type judgment result.
Optionally, the method further includes a step of verifying the fault type determination result, specifically:
calculating the frequency of the jumping period of the ABC three-phase voltage and the waveform within fixed time according to the ABC three-phase voltage and the waveform diagram within the fault occurrence time, and judging the fault type according to the frequency of the jumping period;
if the results are the same, returning the judged fault type;
if the results are different, calling a dynamic thematic map of the longitude and latitude position of the fault point, and returning the fault type consistent with the judgment result of the dynamic thematic map based on the judgment result of the dynamic thematic map; if the dynamic thematic map is not changed, returning the judgment result of the original fault type.
According to a second aspect of the embodiments of the present invention, there is provided a fault type discrimination system based on a fault waveform.
In one embodiment, the fault type discrimination system based on fault waveform includes:
the oscillogram drawing module is used for obtaining a fault oscillogram according to the fault recording data;
and the fault type judging module is used for judging the fault type of the line according to the fault oscillogram.
Optionally, the waveform drawing module is specifically configured to:
acquiring the starting time and the ending time of the fault according to the fault recording data;
and obtaining a fault oscillogram according to the starting time and the ending time of the fault.
Optionally, the fault type determining module is specifically configured to:
and matching the fault waveform image with a defined fault waveform image in a fault history library by using an image recognition algorithm, and judging the fault type of the line.
Optionally, the image recognition algorithm comprises:
dividing the fault oscillogram into small areas;
generating a prior frame through a target detection algorithm;
screening the prior frames meeting the conditions, and outputting confidence frame;
and inputting the confidence picture frame into a convolutional neural network for deep learning to obtain a fault type judgment result.
Optionally, the system further includes a verification module, configured to verify the fault type determination result output by the fault type determination module, where the verification module includes:
calculating the frequency of the jumping period of the ABC three-phase voltage and the waveform within fixed time according to the ABC three-phase voltage and the waveform diagram within the fault occurrence time, and judging the fault type according to the frequency of the jumping period;
if the results are the same, returning the judged fault type;
if the results are different, calling a dynamic thematic map of the longitude and latitude position of the fault point, and returning the fault type consistent with the judgment result of the dynamic thematic map based on the judgment result of the dynamic thematic map; if the dynamic thematic map is not changed, returning the judgment result of the original fault type.
According to a third aspect of embodiments of the present invention, there is provided a computer apparatus.
In some embodiments, the computer device comprises a memory storing a computer program and a processor implementing the steps of the above method when executing the computer program.
The technical scheme provided by the embodiment of the invention has the following beneficial effects:
the data in the fault recorder is processed and analyzed, and a fault oscillogram is established by analyzing the fault recorder data, so that the fault type of the line is judged, the manual calculation difficulty is reduced, the fault processing time is shortened, and the fault processing efficiency is improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
FIG. 1 is a flow diagram illustrating a fault waveform based fault type discrimination method according to an exemplary embodiment;
FIG. 2 is a schematic diagram illustrating a fault waveform based fault type discrimination system in accordance with an exemplary embodiment;
FIG. 3 is a schematic diagram illustrating the structure of a computer device according to an example embodiment.
Detailed Description
The following description and the drawings sufficiently illustrate specific embodiments herein to enable those skilled in the art to practice them. Portions and features of some embodiments may be included in or substituted for those of others. The scope of the embodiments herein includes the full ambit of the claims, as well as all available equivalents of the claims. The terms "first," "second," and the like, herein are used solely to distinguish one element from another without requiring or implying any actual such relationship or order between such elements. In practice, a first element can also be referred to as a second element, and vice versa. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a structure, apparatus, or device that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such structure, apparatus, or device. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a structure, device or apparatus that comprises the element. The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
The terms "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like herein, as used herein, are defined as orientations or positional relationships based on the orientation or positional relationship shown in the drawings, and are used for convenience in describing and simplifying the description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus should not be construed as limiting the present invention. In the description herein, unless otherwise specified and limited, the terms "mounted," "connected," and "connected" are to be construed broadly, and may include, for example, mechanical or electrical connections, communications between two elements, direct connections, and indirect connections via intermediary media, where the specific meaning of the terms is understood by those skilled in the art as appropriate.
Herein, the term "plurality" means two or more, unless otherwise specified.
Herein, the character "/" indicates that the preceding and following objects are in an "or" relationship. For example, A/B represents: a or B.
Herein, the term "and/or" is an associative relationship describing objects, meaning that three relationships may exist. For example, a and/or B, represents: a or B, or A and B.
Fig. 1 shows an embodiment of a fault type discrimination method based on fault waveforms of the present invention.
In this optional embodiment, the fault type determination method based on the fault waveform includes the following steps:
step S1, obtaining a fault oscillogram according to the fault recording data;
and step S2, judging the fault type of the line according to the fault oscillogram.
The fault type judging method based on the fault waveform of the embodiment of the invention processes and analyzes the fault recording data in the fault recorder, thereby judging the fault type of the line.
The fault recording data comprises fault types, fault occurrence time, current and voltage change processes, relay protection and action conditions of automatic devices. When the system is abnormal or has faults, the fault recorder automatically records the fault type, the fault occurrence time, the current and voltage change process and the action conditions of the relay protection and the automatic device, and for three-phase electricity, fault recording data comprises the phase position of the fault. The fault recording data type is mainly in a comtrade format, and an effective means is provided for judging and analyzing the nature of the complex fault by analyzing the fault recording data.
In one embodiment, the step of obtaining the fault waveform map according to the fault recording data includes:
step (A), according to the fault recording data, obtaining the starting time and the ending time of the fault;
and (B) acquiring a fault oscillogram according to the fault starting time and the fault ending time.
Optionally, in the step (a), the step of obtaining the fault starting time according to the fault recording data includes:
when the sudden change of current starting meets the starting criterion, the starting criterion is judged to be the fault starting moment, and the criterion formula is as follows:
|Δi(n)|=|i(n)-i(n-N)|>ΔIs.set(formula 1)
In the formula,. DELTA.Is.setSetting value, Δ I, representing a sudden variable start judgments.set>0;
N represents the sampling times of each cycle;
n represents a time node, i (n) represents a current value of the time node;
in the formula, kdRepresenting a set value coefficient of a break variable starting criterion;
IA0representing the steady-state amplitude of the A-phase current;
IB0representing the steady-state amplitude of the B-phase current;
IC0representing the steady state magnitude of the C-phase current.
After obtaining the fault recording data of the fault recorder, judging the starting time of the fault, and aiming at: on one hand, the analysis time interval of the distance measurement and the transition resistance can be determined only by determining the starting moment of the fault; on the other hand, in calculating the fault distance and the transition resistance, the time synchronization of both ends is to be maintained. In normal conditions, the fault moments at two ends of the line are the same (traveling wave time difference can be ignored in power frequency analysis), but fault recording at two ends of the line possibly fails to time, so that the fault starting moments at two ends are calculated respectively, when the fault starting moments at two ends are different, the time difference caused by failure of the fault recorder due to time synchronization is considered, and the fault starting moments at two ends are aligned to the same moment for analysis.
Optionally, in the step (a), the step of obtaining the fault termination time according to the fault recording data includes:
if in a period, all sampling points of the period simultaneously meet the condition that the absolute values of fault components in the period are all smaller than half of the load current amplitude, the current amplitudes of fault phases in the period are all smaller than the load current amplitude, and the starting time of the period is pushed forward by a period, namely the fault termination time.
A section of complete fault oscillogram can be obtained by calibrating the starting time and the ending time of fault recording, and the diagnosis of line fault reasons can be carried out by analyzing the fault oscillogram.
In one embodiment, the step (B), obtaining a fault waveform diagram according to the fault starting time and the fault ending time, includes:
and obtaining the ABC three-phase voltage sum (UO) waveform diagram within the fault occurrence time according to the fault starting time and the fault ending time.
Next, the Uo waveform is analyzed, the fault starting time and the fault ending time are obtained, so that the fault occurrence time is clear, the number of times of the jumping period To of the Uo waveform within a fixed time (for example, 15ms) is calculated according To the Uo waveform diagram within the fault occurrence time, and the fault type is judged according To the number of times of the jumping period To. And the voltage value is regarded as a jumping period To when rising and falling, different fault types are realized, the times of the jumping period To in the UO waveform period are different, and the fault type can be judged according To the times of the jumping period To in the UO waveform period.
And (3) according To the actually occurring fault reasons, carrying out set division on various UO waveforms such as bird damage, windage yaw, icing, lightning stroke, external force damage and the like, and calculating the To number within 15ms of the starting time of each set fault. Through calculation, the number of the faults To of bird damage and windage yaw is obviously higher than that of other fault types such as icing, lightning stroke, external force damage and the like. Taking bird damage and windage yaw as examples, the fault period of bird damage and windage yaw can be recovered To normal within 60ms, the number of the To faults of bird damage is greater than that of windage yaw faults, wherein the To value interval of birds is [9,20], and the To value interval of windage yaw is [4,8], so that the fault type can be judged To be windage yaw fault if the To value of the fault oscillogram is greater than 9, and the fault type can be judged To be windage yaw fault if the To value of the fault oscillogram is within the To value interval of windage yaw fault.
In another embodiment, the step (B), obtaining the fault waveform map according to the fault starting time and the fault ending time, includes:
calculating the fault distance by using a lumped parameter method:
in the formula, DmFIs the distance to failure; f is a fault point; m and n are bus positions at two ends respectively; j is a sequence network number, is determined by the fault type, and is 1 for the three-phase short circuit J; for two-phase short circuit, J is 1, 2; short to ground, J ═ 1,2, 0; zJRepresenting an impedance; dLRepresents the total length of the line; dnFRepresents the distance from n to F;the sequence voltages representing the fault point F;represents the voltage measured by the terminal M;represents the voltage measured at the N terminal;represents the current measured by the M terminal;represents the current measured by the N terminal;
obtaining DmFThen, the sequence voltage U of the fault point F obtained by the formula (2) is combinedFJCalculating each sequence component of the short-circuit current at the fault point according to the following formula;
obtaining the transition resistance RFThe following formula:
in the formula (I), the compound is shown in the specification,in order to be the fault point current,is the fault point voltage;
according to transition resistance RFAnd drawing a fault waveform chart between the starting time and the ending time of the fault (namely the fault occurrence time).
Next, using an image recognition algorithm, the transition resistance R will be basedFThe drawn fault waveform image is matched with a defined fault waveform image in a fault history library,and judging the fault type of the line. For example, through the above calculation process, R of the fault such as bird damage, windage yaw, icing, lightning stroke, external force damage, etc. is obtainedFAnd data are stored, a fault waveform diagram of the fault is drawn, the drawn fault waveform diagram is matched with a defined fault waveform image in a fault history library by using an image recognition algorithm, and a most similar history picture is found according to image characteristics, so that the fault type is judged.
The image recognition algorithm comprises:
step S101, dividing the fault waveform map into small areas.
First, a plurality of small areas are generated on the fault waveform image by using an image segmentation algorithm, and the areas are the most basic sub-areas. And carrying out region combination according to the similarity between the regions, determining a standard for measuring the similarity, continuously overlapping small regions until all the small regions are combined together, and then making a circumscribed rectangle for each region to obtain a region box which can be an object.
And S102, generating a prior frame through a target detection algorithm.
The method comprises the steps of adopting a target detection algorithm, such as yolov5 algorithm, using a Mosaic enhancement method at an input end, splicing a plurality of pictures, such as 4 pictures according to a random scaling, random cutting and random arrangement mode, then carrying out self-adaptive anchor frame calculation, wherein a model generates a plurality of prior frames during each training.
Step S103, screening the prior frames meeting the conditions, and outputting confidence frames.
The output quantity of the prior boxes is controlled by calculating the IOU to screen the boxes meeting the condition, and then the output quantity of the prior boxes is controlled by non-maximum suppression, the boxes with the confidence degree higher than a preset confidence threshold value are output, for example, a confidence threshold value a is set, for example, a is equal to 0.7, and the boxes with the confidence degree higher than a are output. The IOU is the intersection ratio of two frames, namely the area ratio of the frame generated by the model to the real frame, and the larger the IOU value is, the better the prediction effect of the generated frame is.
And step S104, inputting the confidence picture frame into a convolutional neural network for deep learning to obtain a fault type judgment result.
Adding the least black edges into the zoomed picture through self-adaption through a frame output by the confidence threshold, and putting the picture into a convolutional neural network for deep learning; through multilayer processing, after initial low-level feature representation is gradually converted into high-level feature representation, a complex transition resistance image frame can be completed through a model, and the recognition accuracy is improved through carrying out convolutional neural network training by using the frame for many times.
The model pre-trained on the coco data set by yolov5x is used for transfer learning, so that the model can identify high-level features, the features are universal, and classification of the training model can be realized only by training a full connection layer, so that the detection of the fault waveform type is completed.
Of course, according to the teaching of the embodiment of the application, other deep learning algorithms, computer vision, instance segmentation models, frames and the like can be adopted to analyze and judge the line fault type, so that the stable operation of the line is effectively ensured.
In one embodiment, the step of determining the fault type of the line according to the fault oscillogram includes:
step S201, using image recognition algorithm, according to transition resistance RFMatching the drawn fault waveform image with a defined fault waveform image in a fault history library, and judging the fault type of the line; image recognition algorithm and method based on transition resistance RFThe step of drawing the fault waveform diagram has been explained in the above embodiments, and is not described herein again;
step S202, a step of verifying the fault type determination result, specifically:
according To a UO waveform diagram in the fault time, calculating the frequency of a jumping period To of the UO waveform, and judging the fault type according To the frequency of the jumping period To;
if the results are the same, returning the judged fault type;
if the results are different, calling a dynamic thematic map of the longitude and latitude position of the fault point, and returning the fault type consistent with the judgment result of the dynamic thematic map based on the judgment result of the dynamic thematic map; if the dynamic thematic map is not changed, returning the judgment result of the original fault type.
For example, if the fault is caused by bird damage or windage yaw, the checking method in step S202 is adopted to check the judgment result of the fault type, and if the results are the same, the judged fault type is returned; if the results are different, calling a bird and wind dynamic thematic map (the thematic map is the existing data and only needs to be inquired), inquiring the bird and wind dynamic thematic map at the longitude and latitude position of the fault point, and returning the fault type consistent with the thematic map judgment result based on the judgment result of the dynamic thematic map; if the dynamic thematic map is not changed, returning the judgment result of the original fault type.
By analyzing and judging the method, the type judgment and verification of the fault oscillogram are realized, and the accuracy of fault judgment is ensured.
In another embodiment, as shown in fig. 2, there is provided a fault type discrimination system based on a fault waveform, including:
the oscillogram drawing module 301 is configured to obtain a fault oscillogram according to the fault recording data;
and a fault type determining module 302, configured to determine a fault type of the line according to the fault oscillogram.
The waveform drawing module 301 is specifically configured to:
acquiring the starting time and the ending time of the fault according to the fault recording data;
and obtaining a fault oscillogram according to the starting time and the ending time of the fault.
The fault type determining module 302 is specifically configured to:
and matching the fault waveform image with a defined fault waveform image in a fault history library by using an image recognition algorithm, and judging the fault type of the line.
The image recognition algorithm comprises:
dividing the fault oscillogram into small areas;
generating a prior frame through a target detection algorithm;
screening the prior frames meeting the conditions, and outputting confidence frame;
and inputting the confidence picture frame into a convolutional neural network for deep learning to obtain a fault type judgment result.
The system also comprises a checking module for checking the fault type judgment result output by the fault type judgment module, and the checking module comprises:
according To a UO waveform diagram in the fault time, calculating the frequency of a jumping period To of the UO waveform, and judging the fault type according To the frequency of the jumping period To;
if the results are the same, returning the judged fault type;
if the results are different, calling a dynamic thematic map of the longitude and latitude position of the fault point, and returning the fault type consistent with the judgment result of the dynamic thematic map based on the judgment result of the dynamic thematic map; if the dynamic thematic map is not changed, returning the judgment result of the original fault type.
The working principle of the fault type discrimination system based on the fault waveform in the embodiment of the present application is the same as that of the fault type discrimination method based on the fault waveform in each of the embodiments described above, and details are not repeated here.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 3. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing static information and dynamic information data. The network interface of the computer device is used for communicating with an external terminal through a network connection. Which computer program is executed by a processor to carry out the steps in the above-described method embodiments.
Those skilled in the art will appreciate that the configuration shown in fig. 3 is a block diagram of only a portion of the configuration associated with aspects of the present invention and is not intended to limit the computing devices to which aspects of the present invention may be applied, and that a particular computing device may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In an embodiment, there is also provided a computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the above method embodiments when executing the computer program.
In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
The present invention is not limited to the structures that have been described above and shown in the drawings, and various modifications and changes can be made without departing from the scope thereof. The scope of the invention is limited only by the appended claims.
Claims (16)
1. A fault type discrimination method based on fault waveforms is characterized by comprising the following steps:
acquiring a fault oscillogram according to the fault recording data;
and judging the fault type of the line according to the fault oscillogram.
2. The fault type discrimination method based on the fault waveform according to claim 1,
the step of obtaining the fault oscillogram according to the fault recording data comprises the following steps:
step (A), according to the fault recording data, obtaining the starting time and the ending time of the fault;
and (B) acquiring a fault oscillogram according to the fault starting time and the fault ending time.
3. The fault type discrimination method based on the fault waveform according to claim 2,
in the step (a), the step of obtaining the fault starting time according to the fault recording data includes:
when the sudden change of current starting meets the starting criterion, the starting criterion is judged to be the fault starting moment, and the criterion formula is as follows:
|Δi(n)|=|i(n)-i(n-N)|>ΔIs.set(formula 1)
In the formula,. DELTA.Is.setSetting value, Δ I, representing a sudden variable start judgments.set>0;
N represents the sampling times of each cycle;
n represents a time node, i (n) represents a current value of the time node;
in the formula, kdRepresenting a set value coefficient of a break variable starting criterion;
IA0representing the steady-state amplitude of the A-phase current;
IB0representing the steady-state amplitude of the B-phase current;
IC0representing the steady state magnitude of the C-phase current.
4. The fault type discrimination method based on the fault waveform according to claim 2,
in the step (a), the step of obtaining the fault termination time according to the fault recording data includes:
if in a period, all sampling points of the period simultaneously meet the condition that the absolute values of fault components in the period are all smaller than half of the load current amplitude, the current amplitudes of fault phases in the period are all smaller than the load current amplitude, and the starting time of the period is pushed forward by a period, namely the fault termination time.
5. The fault type discrimination method based on the fault waveform according to claim 2,
the step (B) of obtaining a fault oscillogram according to the fault starting time and the fault ending time includes:
and obtaining the ABC three-phase voltage and a waveform diagram within the fault occurrence time according to the fault starting time and the fault ending time.
6. The fault type discrimination method based on the fault waveform according to claim 5,
the judging the fault type of the line according to the fault oscillogram comprises the following steps:
and calculating the frequency of the jumping period of the ABC three-phase voltage and the waveform within fixed time according to the ABC three-phase voltage and the waveform diagram within the fault occurrence time, and judging the fault type according to the frequency of the jumping period.
7. The fault type discrimination method based on the fault waveform according to claim 2,
the step (B) of obtaining a fault oscillogram according to the fault starting time and the fault ending time includes:
calculating the fault distance by using a lumped parameter method:
in the formula, DmFIs the distance to failure; f is a fault point; m and n are bus positions at two ends respectively; j is a sequence network number, is determined by the fault type, and is 1 for the three-phase short circuit J; for two-phase short circuit, J is 1, 2; short to ground, J ═ 1,2, 0; zJRepresenting an impedance; dLRepresents the total length of the line; dnFRepresents the distance from n to F;the sequence voltages representing the fault point F;represents the voltage measured by the terminal M;represents the voltage measured at the N terminal;represents the current measured by the M terminal;represents the current measured by the N terminal;
obtaining DmFThen, the sequence voltage U of the fault point F obtained by the formula (2) is combinedFJCalculating each sequence component of the short-circuit current at the fault point according to the following formula;
obtaining the transition resistance RFThe following formula:
in the formula (I), the compound is shown in the specification,in order to be the fault point current,is the fault point voltage;
according to transition resistance RFAnd drawing a fault waveform chart of the fault occurrence time.
8. The fault type discrimination method based on the fault waveform according to claim 7,
the judging the fault type of the line according to the fault oscillogram comprises the following steps:
using an image recognition algorithm, will depend on the transition resistance RFAnd matching the drawn fault waveform image with a defined fault waveform image in a fault history library, and judging the fault type of the line.
9. The fault type discrimination method based on the fault waveform according to claim 8,
the image recognition algorithm comprises:
dividing the fault oscillogram into small areas;
generating a prior frame through a target detection algorithm;
screening the prior frames meeting the conditions, and outputting confidence frame;
and inputting the confidence picture frame into a convolutional neural network for deep learning to obtain a fault type judgment result.
10. The method according to claim 8 or 9, wherein the method further comprises a step of verifying a fault type determination result, specifically:
calculating the frequency of the jumping period of the ABC three-phase voltage and the waveform within fixed time according to the ABC three-phase voltage and the waveform diagram within the fault occurrence time, and judging the fault type according to the frequency of the jumping period;
if the results are the same, returning the judged fault type;
if the results are different, calling a dynamic thematic map of the longitude and latitude position of the fault point, and returning the fault type consistent with the judgment result of the dynamic thematic map based on the judgment result of the dynamic thematic map; if the dynamic thematic map is not changed, returning the judgment result of the original fault type.
11. A fault type discrimination system based on a fault waveform, comprising:
the oscillogram drawing module is used for obtaining a fault oscillogram according to the fault recording data;
and the fault type judging module is used for judging the fault type of the line according to the fault oscillogram.
12. The fault waveform based fault type discrimination system of claim 11,
the oscillogram drawing module is specifically configured to:
acquiring the starting time and the ending time of the fault according to the fault recording data;
and obtaining a fault oscillogram according to the starting time and the ending time of the fault.
13. The fault type discrimination method based on the fault waveform according to claim 11,
the fault type judgment module is specifically configured to:
and matching the fault waveform image with a defined fault waveform image in a fault history library by using an image recognition algorithm, and judging the fault type of the line.
14. The fault waveform based fault type discrimination system of claim 13,
the image recognition algorithm comprises:
dividing the fault oscillogram into small areas;
generating a prior frame through a target detection algorithm;
screening the prior frames meeting the conditions, and outputting confidence frame;
and inputting the confidence picture frame into a convolutional neural network for deep learning to obtain a fault type judgment result.
15. The method according to claim 14, wherein the system further includes a checking module for checking the fault type determination result output by the fault type determination module, and the checking module includes:
calculating the frequency of the jumping period of the ABC three-phase voltage and the waveform within fixed time according to the ABC three-phase voltage and the waveform diagram within the fault occurrence time, and judging the fault type according to the frequency of the jumping period;
if the results are the same, returning the judged fault type;
if the results are different, calling a dynamic thematic map of the longitude and latitude position of the fault point, and returning the fault type consistent with the judgment result of the dynamic thematic map based on the judgment result of the dynamic thematic map; if the dynamic thematic map is not changed, returning the judgment result of the original fault type.
16. A computer arrangement, characterized in that the computer arrangement comprises a memory, in which a computer program is stored, and a processor, which when executing the computer program realizes the steps of the method according to any of claims 1 to 10.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111475878.7A CN114113911B (en) | 2021-12-06 | Fault type discriminating method and discriminating system based on fault waveform |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111475878.7A CN114113911B (en) | 2021-12-06 | Fault type discriminating method and discriminating system based on fault waveform |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114113911A true CN114113911A (en) | 2022-03-01 |
CN114113911B CN114113911B (en) | 2024-07-26 |
Family
ID=
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115311542A (en) * | 2022-08-25 | 2022-11-08 | 杭州恒胜电子科技有限公司 | Target detection method, device, equipment and medium |
CN117216485A (en) * | 2023-11-09 | 2023-12-12 | 国网山东省电力公司电力科学研究院 | Objective weighting-based power transmission wave-recording bird damage fault judging method and system |
CN117554809A (en) * | 2024-01-10 | 2024-02-13 | 北京博华鑫诺科技有限公司 | Motor winding balance detection method and device, electronic equipment and storage medium |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100102824A1 (en) * | 2007-04-18 | 2010-04-29 | Mario Tremblay | Electrical network fault location by distributed voltage measurements |
CN103746350A (en) * | 2014-01-23 | 2014-04-23 | 国家电网公司 | High-sensitivity busbar differential protection method |
CN104316844A (en) * | 2014-11-14 | 2015-01-28 | 广东电网有限责任公司佛山供电局 | Power distribution network fault type recognition method and device |
CN106841907A (en) * | 2016-12-12 | 2017-06-13 | 国网北京市电力公司 | The fault type judges method of overhead transmission line |
CN107091970A (en) * | 2017-05-19 | 2017-08-25 | 国网天津市电力公司 | The Fault Phase Selection method of isolated neutral system |
CN107505539A (en) * | 2017-10-23 | 2017-12-22 | 云南电网有限责任公司电力科学研究院 | A kind of distribution arc grounding fault identification method |
CN110474306A (en) * | 2019-08-23 | 2019-11-19 | 华中科技大学 | A kind of guard method and system of the dead-zone fault in DC grid |
CN111751665A (en) * | 2020-06-29 | 2020-10-09 | 深圳供电局有限公司 | Method and system for judging phase-to-phase fault based on power grid fault recording graph |
CN112147462A (en) * | 2020-09-16 | 2020-12-29 | 国网江西省电力有限公司电力科学研究院 | Power transmission line fault identification method based on deep learning |
CN113298767A (en) * | 2021-05-19 | 2021-08-24 | 南京大学 | Reliable go map recognition method capable of overcoming light reflection phenomenon |
US20210293873A1 (en) * | 2020-03-18 | 2021-09-23 | Mitsubishi Electric Research Laboratories, Inc. | Transient based Fault Location Method for Ungrounded Power Distribution Systems |
CN113466633A (en) * | 2021-07-30 | 2021-10-01 | 武汉三相电力科技有限公司 | Distributed fault monitoring integrated method and device for power transmission line |
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100102824A1 (en) * | 2007-04-18 | 2010-04-29 | Mario Tremblay | Electrical network fault location by distributed voltage measurements |
CN103746350A (en) * | 2014-01-23 | 2014-04-23 | 国家电网公司 | High-sensitivity busbar differential protection method |
CN104316844A (en) * | 2014-11-14 | 2015-01-28 | 广东电网有限责任公司佛山供电局 | Power distribution network fault type recognition method and device |
CN106841907A (en) * | 2016-12-12 | 2017-06-13 | 国网北京市电力公司 | The fault type judges method of overhead transmission line |
CN107091970A (en) * | 2017-05-19 | 2017-08-25 | 国网天津市电力公司 | The Fault Phase Selection method of isolated neutral system |
CN107505539A (en) * | 2017-10-23 | 2017-12-22 | 云南电网有限责任公司电力科学研究院 | A kind of distribution arc grounding fault identification method |
CN110474306A (en) * | 2019-08-23 | 2019-11-19 | 华中科技大学 | A kind of guard method and system of the dead-zone fault in DC grid |
US20210293873A1 (en) * | 2020-03-18 | 2021-09-23 | Mitsubishi Electric Research Laboratories, Inc. | Transient based Fault Location Method for Ungrounded Power Distribution Systems |
CN111751665A (en) * | 2020-06-29 | 2020-10-09 | 深圳供电局有限公司 | Method and system for judging phase-to-phase fault based on power grid fault recording graph |
CN112147462A (en) * | 2020-09-16 | 2020-12-29 | 国网江西省电力有限公司电力科学研究院 | Power transmission line fault identification method based on deep learning |
CN113298767A (en) * | 2021-05-19 | 2021-08-24 | 南京大学 | Reliable go map recognition method capable of overcoming light reflection phenomenon |
CN113466633A (en) * | 2021-07-30 | 2021-10-01 | 武汉三相电力科技有限公司 | Distributed fault monitoring integrated method and device for power transmission line |
Non-Patent Citations (2)
Title |
---|
何俊涛: "基于录波数据的电力系统故障元件智能诊断方法研究", 中国优秀硕士学位论文全文数据库 (工程科技Ⅱ辑) * |
王立建等: "一种图文融合的电网故障综合研判方法分析", 农村电气化, no. 407, 30 April 2021 (2021-04-30) * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115311542A (en) * | 2022-08-25 | 2022-11-08 | 杭州恒胜电子科技有限公司 | Target detection method, device, equipment and medium |
CN117216485A (en) * | 2023-11-09 | 2023-12-12 | 国网山东省电力公司电力科学研究院 | Objective weighting-based power transmission wave-recording bird damage fault judging method and system |
CN117216485B (en) * | 2023-11-09 | 2024-01-30 | 国网山东省电力公司电力科学研究院 | Objective weighting-based power transmission wave-recording bird damage fault judging method and system |
CN117554809A (en) * | 2024-01-10 | 2024-02-13 | 北京博华鑫诺科技有限公司 | Motor winding balance detection method and device, electronic equipment and storage medium |
CN117554809B (en) * | 2024-01-10 | 2024-03-22 | 北京博华鑫诺科技有限公司 | Motor winding balance detection method and device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP3314273B1 (en) | A method for correcting effect of saturation in current transformer and an intelligent electronic device therefor | |
CN110837683A (en) | Training and predicting method and device for prediction model of transient stability of power system | |
CN113688957A (en) | Target detection method, device, equipment and medium based on multi-model fusion | |
CN111179262A (en) | Electric power inspection image hardware fitting detection method combined with shape attribute | |
CN114821852B (en) | Power grid defect depth identification inspection robot control system based on feature pyramid | |
CN116503318A (en) | Aerial insulator multi-defect detection method, system and equipment integrating CAT-BiFPN and attention mechanism | |
CN113850330A (en) | Power distribution network fault cause detection method based on short-time Fourier transform and convolutional neural network | |
CN112816881A (en) | Battery differential pressure abnormality detection method, battery differential pressure abnormality detection device and computer storage medium | |
CN117668751B (en) | High-low voltage power system fault diagnosis method and device | |
CN114113911A (en) | Fault waveform-based fault type discrimination method and discrimination system | |
CN114113911B (en) | Fault type discriminating method and discriminating system based on fault waveform | |
CN116166642A (en) | Spatio-temporal data filling method, system, equipment and medium based on guide information | |
CN113569704B (en) | Segmentation point judging method, system, storage medium and electronic equipment | |
CN115589255A (en) | Optical cable general inspection instrument and test method | |
CN114861321A (en) | Problem scene extraction method, device, equipment and medium for traffic flow simulation | |
CN111639141B (en) | Data testing method and device and computer terminal | |
CN114049764A (en) | Traffic simulation method and system based on convolution long-time and short-time memory neural network | |
CN113447572A (en) | Steel rail flaw detection method, electronic device, steel rail flaw detection vehicle and readable storage medium | |
CN117466153B (en) | Fault detection method, device, computer equipment and readable storage medium | |
CN110942179A (en) | Automatic driving route planning method and device and vehicle | |
CN118196654A (en) | Video frame optimization method and device for unmanned aerial vehicle power line inspection | |
CN115425759A (en) | New energy power grid cascading failure prediction method and system capable of achieving autonomous learning and application | |
US20220413050A1 (en) | Complicated system fault diagnosis method and system based on multi-stage model | |
CN116243679A (en) | Intelligent fault monitoring and refined diagnosis method, device and storage medium | |
CN117214701A (en) | Motor demagnetizing fault diagnosis method and device |
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 |