CN117214780B - Transformer fault detection method and device - Google Patents
Transformer fault detection method and device Download PDFInfo
- Publication number
- CN117214780B CN117214780B CN202311474119.8A CN202311474119A CN117214780B CN 117214780 B CN117214780 B CN 117214780B CN 202311474119 A CN202311474119 A CN 202311474119A CN 117214780 B CN117214780 B CN 117214780B
- Authority
- CN
- China
- Prior art keywords
- transformer
- fault
- voiceprint
- current waveform
- detection result
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 164
- 230000002159 abnormal effect Effects 0.000 claims abstract description 72
- 238000000034 method Methods 0.000 claims abstract description 35
- 238000010586 diagram Methods 0.000 claims abstract description 33
- 230000005856 abnormality Effects 0.000 claims abstract description 26
- 230000009467 reduction Effects 0.000 claims description 31
- 238000004590 computer program Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 10
- 230000000630 rising effect Effects 0.000 claims description 9
- 230000007547 defect Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000001228 spectrum Methods 0.000 claims description 6
- 238000012706 support-vector machine Methods 0.000 claims description 4
- 238000009432 framing Methods 0.000 claims description 3
- 238000005315 distribution function Methods 0.000 claims 2
- 230000008569 process Effects 0.000 description 9
- 238000009413 insulation Methods 0.000 description 7
- 238000012544 monitoring process Methods 0.000 description 6
- 230000015556 catabolic process Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000032683 aging Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000004804 winding Methods 0.000 description 2
- 238000002679 ablation Methods 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000011248 coating agent Substances 0.000 description 1
- 238000000576 coating method Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 210000003298 dental enamel Anatomy 0.000 description 1
- 230000005684 electric field Effects 0.000 description 1
- 230000005674 electromagnetic induction Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000004907 flux Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 230000002427 irreversible effect Effects 0.000 description 1
- 230000003211 malignant effect Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 230000005477 standard model Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Landscapes
- Testing Relating To Insulation (AREA)
Abstract
The embodiment of the invention relates to the technical field of transformer detection, and discloses a transformer fault detection method and device, wherein the method comprises the following steps: acquiring real-time pulse current data of a transformer to be detected through a preset pulse current detection module; generating a current waveform video according to the real-time pulse current data, wherein the current waveform video comprises a plurality of frames of current waveform diagrams; extracting a current waveform chart in the current waveform video, and inputting the current waveform chart into a pre-constructed abnormal waveform recognition model to perform abnormal detection of current fluctuation so as to obtain a corresponding first abnormal detection result; and if the first abnormality detection result is matched with the set condition, carrying out transformer fault reminding. According to the transformer fault detection method, the current waveform video is obtained, the corresponding current waveform diagram is extracted, whether sudden pulse occurs or not is determined through waveform abnormality detection of the current waveform diagram, and then early warning detection of the transformer is achieved.
Description
Technical Field
The invention relates to the technical field of transformer detection, in particular to a transformer fault detection method and device.
Background
Currently, transformers are used as a common electrical device, which uses the principle of electromagnetic induction to transfer alternating current power between two or more windings, so that the voltages at the input end and the output end meet different requirements. The transformer plays a vital role in the circuit, and when the transformer fails, the whole circuit can not work normally, and even serious safety accidents can be caused. Therefore, the running state of the transformer is monitored in real time, the fault of the transformer is timely and accurately detected, and the occurrence of malignant accidents is avoided, so that the method has very important significance. Therefore, designing a solution capable of monitoring and early warning a transformer is a technical problem to be solved by those skilled in the art.
Disclosure of Invention
Aiming at the defects, the embodiment of the invention discloses a transformer fault detection method which can realize accurate fault early warning of a transformer.
The first aspect of the embodiment of the invention discloses a transformer fault detection method, which comprises the following steps:
acquiring real-time pulse current data of a transformer to be detected through a preset pulse current detection module; a current noise reduction circuit is arranged in the pulse current detection circuit, and the current noise reduction circuit carries out noise reduction treatment on the acquired real-time pulse current data;
Generating a current waveform video according to the real-time pulse current data, wherein the current waveform video comprises a multi-frame current waveform diagram; wherein each frame current waveform map is generated based on the detected real-time pulse current data;
extracting a current waveform chart in the current waveform video, and inputting the current waveform chart into a pre-constructed abnormal waveform recognition model to perform abnormal detection of current fluctuation so as to obtain a corresponding first abnormal detection result;
and if the first abnormal detection result is matched with the set condition, reminding the fault of the transformer.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, after the if the first anomaly detection result matches with a set condition, the method further includes:
acquiring two frames of waveform images adjacent to the front and rear of the current waveform image, and inputting the two frames of waveform images adjacent to the front and rear into an abnormal waveform identification model to acquire a second abnormal detection result;
and if the second abnormal detection result is also matched with the set condition, prompting the fault of the transformer.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, the extracting a current waveform chart in the current waveform video includes:
Image extraction is carried out on the current waveform video every second so as to obtain a current waveform diagram in a corresponding time period;
after the current waveform diagram is input into the pre-built abnormal waveform recognition model to perform abnormal detection of current fluctuation so as to obtain a corresponding first abnormal detection result, the method further comprises the following steps:
acquiring first time information associated with the first abnormality detection result, and carrying out data association on the first time information, the first abnormality detection result and corresponding transformer information;
when the times of detecting the first abnormal detection result of the corresponding transformer exceeds the set times, executing the next step;
acquiring a first time information set associated with the first abnormal detection result, and determining trend information of the abnormal detection result according to the first time information set, wherein the trend information is used for representing frequency information of sporadic pulse occurrence or fault time information of partial discharge occurrence;
and carrying out information reminding according to the fault time information.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, after the if the first anomaly detection result matches with a set condition, the method further includes:
Acquiring a transformer voiceprint signal at a transformer through a sound sensor arranged at the transformer;
performing feature recognition on the transformer voiceprint signals to obtain rising edge signals and falling edge signals in the transformer voiceprint signals, and performing amplitude lifting on the rising edge signals and the falling edge signals in the transformer voiceprint signals according to set amplitude so as to obtain the voiceprint signals to be noise reduced;
determining noise state information of the transformer according to the position information of the transformer, determining a corresponding voiceprint noise reduction model according to the noise state information, and performing noise reduction processing on the voiceprint signal to be noise reduced based on the voiceprint noise reduction model to obtain noise reduction information;
dividing continuous unstable noise-reducing voiceprint information into a plurality of sections of short-time voiceprint signals through framing and windowing operations; the preprocessed multi-section short-time voiceprint signals are converted into linear frequency spectrum signals by adopting fast Fourier transform;
carrying out feature extraction on the linear spectrum signal by adopting a Mel frequency cepstrum coefficient to obtain a voiceprint feature signal;
and identifying the voiceprint features through an anomaly detection algorithm to obtain corresponding voiceprint detection results.
In a first aspect of the embodiment of the present invention, the identifying the voiceprint feature by the anomaly detection algorithm to obtain a corresponding voiceprint detection result includes:
further feature extraction is carried out on the voiceprint features by adopting a deep confidence network to obtain deep voiceprint features, wherein the deep confidence network is composed of three layers of restricted Boltzmann machines; optimizing two super parameters of batch size and learning rate in the deep confidence network;
and inputting the deep voiceprint features into a support vector machine algorithm to perform defect identification so as to determine corresponding voiceprint detection results.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, the fault detection method further includes:
different kinds of parameter values of each acquisition time of the transformer to be detected are obtained, wherein the parameter values at least comprise an electric signal value and a gas signal value; the gas signal values are a first gas value, a second gas value, a third gas value, a fourth gas value and a fifth gas value;
constructing a first fault parameter, a second fault parameter and a third fault parameter according to the first gas value, the second gas value, the third gas value, the fourth gas value and the fifth gas value; the first fault parameter is the ratio of a third gas parameter to a fourth gas parameter, the second fault parameter is the ratio of the second gas parameter to the first gas parameter, and the third fault parameter is the ratio of the fourth gas parameter to the fifth gas parameter;
Determining corresponding fault probability data according to the first fault parameter, the second fault parameter, the third fault parameter, the electric signal value, the transformer fault table and the fault matching model; the fault matching model comprises:
，
wherein,for the first, second, third or electrical signal value, +.>For +.>Is a value range of>Is->To section->Distance of->For a range of historical intervals at the corresponding fault,is->To section->Distance of->Representing the fault probability of the transformer;
and determining the fault type and the fault probability curve of the transformer to be detected according to the fault probability data.
In an optional implementation manner, in a first aspect of the embodiment of the present invention, if the first anomaly detection result matches with a set condition, performing a transformer fault alert includes:
if the first abnormal detection result is a first discharge characteristic which is densely clustered, determining that the first discharge characteristic is matched with a first preset condition, and performing
And if the first abnormal detection result is a second discharge characteristic with a tailing effect, determining that the second discharge characteristic is matched with a second preset condition.
A second aspect of an embodiment of the present invention discloses a transformer fault detection device, including:
the acquisition module is used for: the real-time pulse current data of the transformer to be detected are obtained through a preset pulse current detection module; a current noise reduction circuit is arranged in the pulse current detection circuit, and the current noise reduction circuit carries out noise reduction treatment on the acquired real-time pulse current data;
and a video generation module: the current waveform video generating device is used for generating a current waveform video according to the real-time pulse current data, wherein the current waveform video comprises a plurality of frames of current waveform diagrams; wherein each frame current waveform map is generated based on the detected real-time pulse current data;
the waveform detection module: the current waveform image is used for extracting a current waveform image in the current waveform video, and the current waveform image is input into a pre-built abnormal waveform identification model to perform abnormal detection of current fluctuation so as to obtain a corresponding first abnormal detection result;
and the fault early warning module is used for: and the transformer fault reminding module is used for carrying out transformer fault reminding if the first abnormal detection result is matched with the set condition.
A third aspect of an embodiment of the present invention discloses an electronic device, including: a memory storing executable program code; a processor coupled to the memory; the processor invokes the executable program code stored in the memory to perform the transformer fault detection method disclosed in the first aspect of the embodiment of the present invention.
A fourth aspect of the embodiment of the present invention discloses a computer-readable storage medium storing a computer program, wherein the computer program causes a computer to execute the transformer fault detection method disclosed in the first aspect of the embodiment of the present invention.
Compared with the prior art, the embodiment of the invention has the following beneficial effects:
according to the transformer fault detection method, the current waveform video is obtained, the corresponding current waveform diagram is extracted, whether sudden pulses occur or not is determined by detecting waveform abnormality of the current waveform diagram, and then early warning detection of the transformer is achieved, the possibility of faults of the transformer is greatly reduced, and the use safety of the transformer is guaranteed.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, and it is obvious 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 a transformer fault detection method disclosed in an embodiment of the present invention;
FIG. 2 is a schematic diagram of a flow chart for detecting waveform anomalies according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a flow chart for voiceprint detection according to an embodiment of the present invention;
FIG. 4 is a schematic flow chart of auxiliary fault detection according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a transformer fault detection device according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that the terms "first," "second," "third," "fourth," and the like in the description and in the claims of the present invention are used for distinguishing between different objects and not necessarily for describing a particular sequential or chronological order. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus 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.
Currently, common methods include: infrared scanning technology, ultrasonic detection technology, electromagnetic sensing technology, etc. The application of the techniques can rapidly and accurately identify the partial discharge defects, and timely take maintenance measures to ensure the operation reliability and safety of equipment. There are various causes of partial discharge of the transformer, including breakage of materials, loosening of joints, inclusion of impurities in air, aging of insulating coating, and the like. Therefore, how to effectively detect and diagnose partial discharge of a transformer has been a subject of great attention by power system engineers. Based on the above, the embodiment of the invention discloses a transformer fault detection method, a device, electronic equipment and a storage medium, which are used for determining whether sudden pulse occurs or not by acquiring a current waveform video and extracting a corresponding current waveform diagram and detecting waveform abnormality of the current waveform diagram, so as to realize early warning detection of a transformer, greatly reduce the possibility of the transformer fault and ensure the use safety of the transformer.
Example 1
Referring to fig. 1, fig. 1 is a flow chart of a transformer fault detection method according to an embodiment of the invention. The execution main body of the method described in the embodiment of the invention is an execution main body composed of software or/and hardware, and the execution main body can receive related information in a wired or/and wireless mode and can send a certain instruction. Of course, it may also have certain processing and storage functions. The execution body may control a plurality of devices, such as a remote physical server or cloud server and related software, or may be a local host or server and related software that performs related operations on a device that is located somewhere, etc. In some scenarios, multiple storage devices may also be controlled, which may be located in the same location or in different locations than the devices. As shown in fig. 1, the transformer fault detection method comprises the following steps:
S101: acquiring real-time pulse current data of a transformer to be detected through a preset pulse current detection module; a current noise reduction circuit is arranged in the pulse current detection circuit, and the current noise reduction circuit carries out noise reduction treatment on the acquired real-time pulse current data;
s102: generating a current waveform video according to the real-time pulse current data, wherein the current waveform video comprises a multi-frame current waveform diagram; wherein each frame current waveform map is generated based on the detected real-time pulse current data;
s103: extracting a current waveform chart in the current waveform video, and inputting the current waveform chart into a pre-constructed abnormal waveform recognition model to perform abnormal detection of current fluctuation so as to obtain a corresponding first abnormal detection result;
s104: and if the first abnormal detection result is matched with the set condition, reminding the fault of the transformer.
In general, when a discharge situation has occurred, it is already in a relatively dangerous situation for the transformer to supply power; so at the time of monitoring, how to select an appropriate index to detect the state in which discharge is about to occur. In the actual monitoring process, abnormal burst pulses are found to occur before discharge breakdown occurs, and the burst pulse is difficult to observe by naked eyes in the actual process because the abnormal burst pulse has lower discharge quantity and shorter burst pulse duration, so in the embodiment of the invention, obvious differences corresponding to specific waveforms can be expected to occur because the burst pulse exists, and the burst pulse waveform is monitored. The sudden discharge pulse refers to that obvious discharge occurs in the insulating part of the device, and the sudden discharge pulse is displayed, so that the insulation defect is probably further increased after the sudden discharge pulse occurs, and further more serious subsequent results, such as breakdown, occur.
And when partial discharge occurs, even more serious consequences can occur if not intervening in time. Partial discharge refers to a localized electrical breakdown phenomenon that exists in an insulating medium. When a high voltage is applied to the insulation of the transformer windings, a concentrated electric field may occur, resulting in partial discharge of the insulation medium. If not handled in time, partial discharge can lead to insulation aging and material ablation, and finally can lead to insulation breakdown, thereby causing equipment failure and even explosion and having great influence on the normal operation of a power system.
In the embodiment of the invention, the whole detection efficiency can be greatly improved by directly detecting the current waveform graph, because the current waveform is in a more regular state under the conventional condition; only when abnormal, some fluctuation occurs; therefore, when the method is implemented, the method can be used for monitoring in two ways, one is to perform model construction on a normal waveform, and only when the normal waveform is met, no alarm is given, and the other is to detect an abnormal waveform, and the method can be used for monitoring when the abnormality occurs. In the embodiment of the invention, the normal waveform is more preferably detected, and because the comparison and aggregation of the relative characteristics of the normal waveform can better obtain a more standard model, more accurate prediction can be realized.
More preferably, after the first abnormality detection result matches the set condition, the method further includes:
acquiring two frames of waveform images adjacent to the front and rear of the current waveform image, and inputting the two frames of waveform images adjacent to the front and rear into an abnormal waveform identification model to acquire a second abnormal detection result;
and if the second abnormal detection result is also matched with the set condition, prompting the fault of the transformer.
In the actual implementation process, in order to perform more accurate prediction, the two frames of graphs before and after the current waveform graph can be further identified, and although the time of occurrence of waveform abnormality is short, the video of 20 frames per second is relatively long, so that when the method is implemented, the two frames of waveform graphs adjacent before and after can be further detected to further realize auxiliary judgment.
More preferably, the extracting the current waveform diagram in the current waveform video includes:
image extraction is carried out on the current waveform video every second so as to obtain a current waveform diagram in a corresponding time period;
because the abnormal waveform appears in a short time, the video images are generally extracted and identified at intervals of one second when the method is implemented, so that the abnormal waveform can be detected to the greatest extent, and the possibility of missed detection is avoided.
Fig. 2 is a schematic flow chart of waveform abnormality detection according to an embodiment of the present invention, as shown in fig. 2, after the current waveform diagram is input into an abnormality waveform recognition model that is built in advance to perform abnormality detection of current fluctuation, so as to obtain a corresponding first abnormality detection result, the method further includes:
s1031: acquiring first time information associated with the first abnormality detection result, and carrying out data association on the first time information, the first abnormality detection result and corresponding transformer information;
s1032: when the times of detecting the first abnormal detection result of the corresponding transformer exceeds the set times, executing the next step;
s1033: acquiring a first time information set associated with the first abnormal detection result, and determining trend information of the abnormal detection result according to the first time information set, wherein the trend information is used for representing frequency information of sporadic pulse occurrence or fault time information of partial discharge occurrence;
s1034: and carrying out information reminding according to the fault time information.
Sometimes, if the worker detects that an abnormal waveform occurs for the first time, the worker may also use a maintenance worker for maximum chemical combination; therefore, when the method is implemented, the abnormal condition is detected within a period of time, and the insulating layer is generally irreversible due to the fact that the insulating layer is worn out, so that the abnormal condition is represented on a detection result, namely the abnormal condition occurs more and more times; when the setting is carried out, if the rising trend is detected to be obvious, early warning is carried out as soon as possible.
More preferably, fig. 3 is a schematic flow chart of voiceprint detection according to an embodiment of the present invention, and as shown in fig. 3, after the first anomaly detection result matches a set condition, the method further includes:
s1051: acquiring a transformer voiceprint signal at a transformer through a sound sensor arranged at the transformer;
s1052: performing feature recognition on the transformer voiceprint signals to obtain rising edge signals and falling edge signals in the transformer voiceprint signals, and performing amplitude lifting on the rising edge signals and the falling edge signals in the transformer voiceprint signals according to set amplitude so as to obtain the voiceprint signals to be noise reduced;
s1053: determining noise state information of the transformer according to the position information of the transformer, determining a corresponding voiceprint noise reduction model according to the noise state information, and performing noise reduction processing on the voiceprint signal to be noise reduced based on the voiceprint noise reduction model to obtain noise reduction information;
s1054: dividing continuous unstable noise-reducing voiceprint information into a plurality of sections of short-time voiceprint signals through framing and windowing operations; the preprocessed multi-section short-time voiceprint signals are converted into linear frequency spectrum signals by adopting fast Fourier transform;
S1055: carrying out feature extraction on the linear spectrum signal by adopting a Mel frequency cepstrum coefficient to obtain a voiceprint feature signal;
s1056: and identifying the voiceprint features through an anomaly detection algorithm to obtain corresponding voiceprint detection results.
While the transformer is operating, it will be appreciated by those skilled in the art that the buzzing is caused by the vibration of the core caused by the alternating magnetic flux, and generally the magnitude of the sound is proportional to the voltage and current applied to the transformer. Under normal conditions, the sound is continuous and uniform, and the situation is that the transformer normally operates, the operation of the transformer is not affected, and the problem of the transformer is not represented.
Another aspect of generating abnormal noise comes from external factors. 1. An overvoltage condition occurs in the power grid. In general, overvoltage is caused when the power grid is in single-phase grounding or electromagnetic resonance, and the generated sound is sharper than usual. 2. The power grid has an overcurrent condition, which is generally caused by overload, high power load, traversing short circuit and the like. The occurrence of the two conditions is generally abnormal with the indication colleagues of the indication meters (voltmeters or ammeter), and the two conditions are easy to distinguish. 3. The transformer is operated in overload. The load change is big, and because of the harmonic effect, can send out the abnormal sound of "high pitch, big volume" in the transformer again, the instrument pointer can take place the swing. 4. The transformer is partially discharged. When the drop-out fuse or the tap switch of the transformer is in poor contact, abnormal sounds can be caused by local heating; when the transformer bushing of the transformer is stained, the enamel of the surface change falls off or cracks exist, and abnormal sound like fizzing can be heard. 5. Weather reasons. In special weather such as heavy fog weather, snowy weather, etc., the phenomenon of corona discharge and glow discharge can appear at the sleeve, blue small sparks can be seen at night, and abnormal sound can be caused in the situation.
Therefore, when the method is implemented, not only the image can be used, but also the corresponding detection can be carried out by combining the sound together, and when the method is implemented, the final abnormal detection result can be higher in accuracy by combining the sound result with the image detection result.
The step is mainly to process the voiceprint signal, and the high-frequency component attenuation of the signal is large and the low-frequency component attenuation is small in the transmission process because the signal transmission line shows low-pass filtering characteristics. The high frequency component of the signal is enhanced at the beginning of the transmission line to compensate for excessive attenuation of the high frequency component during transmission. The high frequency component of the signal mainly appears at the rising edge and the falling edge of the signal, and the mode of the embodiment of the invention is to enhance the amplitude at the rising edge and the falling edge of the signal to achieve the purpose of certain noise reduction. And finally, the accuracy of the sound detection result is higher.
More preferably, the identifying the voiceprint feature by the anomaly detection algorithm to obtain a corresponding voiceprint detection result includes:
Further feature extraction is carried out on the voiceprint features by adopting a deep confidence network to obtain deep voiceprint features, wherein the deep confidence network is composed of three layers of restricted Boltzmann machines; optimizing two super parameters of batch size and learning rate in the deep confidence network;
and inputting the deep voiceprint features into a support vector machine algorithm to perform defect identification so as to determine corresponding voiceprint detection results.
In the embodiment of the invention, the deep confidence network is arranged to further extract the voiceprint features, so that compared with the existing BPN model, the network level is deeper, deep voiceprint features can be fully mined, and finally the whole detection result is more accurate.
More preferably, fig. 4 is a schematic flow chart of auxiliary fault detection according to an embodiment of the present invention, and as shown in fig. 4, the fault detection method further includes:
s1061: different kinds of parameter values of each acquisition time of the transformer to be detected are obtained, wherein the parameter values at least comprise an electric signal value and a gas signal value; the gas signal values are a first gas value, a second gas value, a third gas value, a fourth gas value and a fifth gas value;
S1062: constructing a first fault parameter, a second fault parameter and a third fault parameter according to the first gas value, the second gas value, the third gas value, the fourth gas value and the fifth gas value; the first fault parameter is the ratio of a third gas parameter to a fourth gas parameter, the second fault parameter is the ratio of the second gas parameter to the first gas parameter, and the third fault parameter is the ratio of the fourth gas parameter to the fifth gas parameter;
s1063: determining corresponding fault probability data according to the first fault parameter, the second fault parameter, the third fault parameter, the electric signal value, the transformer fault table and the fault matching model; the fault matching model comprises:
，
wherein,for the first, second, third or electrical signal value, +.>For +.>Is a value range of>Is->To section->Distance of->For a range of historical intervals at the corresponding fault,is->To section->Distance of->Representing the fault probability of the transformer;
s1064: and determining the fault type and the fault probability curve of the transformer to be detected according to the fault probability data.
Through the mode, more accurate equipment fault type detection can be realized, and the obtained detection result is matched with the graph detection result and the voiceprint detection result, so that more various information can be provided, and the follow-up deeper equipment operation monitoring can be conveniently carried out. The fault type detection has higher accuracy than the detection result of a general support vector machine and a convolutional neural network.
More preferably, if the first abnormality detection result matches a set condition, performing a transformer fault alert, including:
if the first abnormal detection result is a first discharge characteristic which is densely clustered, determining that the first discharge characteristic is matched with a first preset condition, and performing
And if the first abnormal detection result is a second discharge characteristic with a tailing effect, determining that the second discharge characteristic is matched with a second preset condition.
In the embodiment of the invention, the discharge pulse has specific shape characteristics, faults corresponding to different shapes are also different, the pulse shape is in a cluster dense characteristic or an oscillation tail, which may be a more complex or serious discharge characteristic related to paper insulation, and a pulse signal which is not generally existed in external interference pulse and is once "clustered" or overlapped needs to be more careful, because the pulse signal is likely to be that the insulation part has started to generate creeping discharge.
In an embodiment of the present invention, the fault detection method further includes:
acquiring current detection information, temperature detection information and vibration information of each acquisition time of a transformer to be detected;
according to the distribution difference of the current detection information of each acquisition time, determining the acquisition time to be determined in each acquisition time, grouping the acquisition time to be determined, and obtaining at least two acquisition time groups to be determined;
Determining an abnormal confidence index corresponding to the acquisition time group to be determined according to the distribution difference of the same parameter value corresponding to each acquisition time in the acquisition time group to be determined;
determining a target to-be-determined acquisition time group in the to-be-determined acquisition time group according to the abnormal confidence index, and determining a correlation index value between any two different parameter values corresponding to the target to-be-determined acquisition time group according to the parameter values of each acquisition time in the target to-be-determined acquisition time group;
determining an influence factor of the target to-be-determined acquisition time group corresponding to each parameter value according to the related index value between any two different parameter values corresponding to the target to-be-determined acquisition time group;
constructing sample points corresponding to each acquisition time according to different kinds of parameter values of each acquisition time, and determining measurement distances between any two different sample points according to influence factors of each parameter value corresponding to a target to-be-determined acquisition time group and different kinds of parameter values of the acquisition time corresponding to the sample points;
and detecting outlier sample points according to the measured distance, so as to determine whether the transformer fails.
The fault judgment of the transformer is assisted by acquiring more parameter values, so that the final result is more accurate, when specific characteristic construction is carried out, the electric signal value, the temperature value and the vibration information are comprehensively judged to determine whether the transformer has faults, and more preferably, when specific implementation is carried out, the waveform diagram detection result, the sound detection result and the like can be comprehensively information to jointly construct a detection signal group of the transformer.
According to the transformer fault detection method, the current waveform video is obtained, the corresponding current waveform diagram is extracted, whether sudden pulses occur or not is determined by detecting waveform abnormality of the current waveform diagram, and then early warning detection of the transformer is achieved, the possibility of faults of the transformer is greatly reduced, and the use safety of the transformer is guaranteed.
Example two
Referring to fig. 5, fig. 5 is a schematic structural diagram of a transformer fault detection device according to an embodiment of the invention. As shown in fig. 5, the transformer fault detection apparatus may include:
the acquisition module 21: the real-time pulse current data of the transformer to be detected are obtained through a preset pulse current detection module; a current noise reduction circuit is arranged in the pulse current detection circuit, and the current noise reduction circuit carries out noise reduction treatment on the acquired real-time pulse current data;
video generation module 22: the current waveform video generating device is used for generating a current waveform video according to the real-time pulse current data, wherein the current waveform video comprises a plurality of frames of current waveform diagrams; wherein each frame current waveform map is generated based on the detected real-time pulse current data;
The waveform detection module 23: the current waveform image is used for extracting a current waveform image in the current waveform video, and the current waveform image is input into a pre-built abnormal waveform identification model to perform abnormal detection of current fluctuation so as to obtain a corresponding first abnormal detection result;
fault early warning module 24: and the transformer fault reminding module is used for carrying out transformer fault reminding if the first abnormal detection result is matched with the set condition.
According to the transformer fault detection method, the current waveform video is obtained, the corresponding current waveform diagram is extracted, whether sudden pulses occur or not is determined by detecting waveform abnormality of the current waveform diagram, and then early warning detection of the transformer is achieved, the possibility of faults of the transformer is greatly reduced, and the use safety of the transformer is guaranteed.
Example III
Referring to fig. 6, fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the invention. The electronic device may be a computer, a server, or the like, and of course, may also be an intelligent device such as a mobile phone, a tablet computer, a monitor terminal, or the like, and an image acquisition device having a processing function. As shown in fig. 6, the electronic device may include:
A memory 510 storing executable program code;
a processor 520 coupled to the memory 510;
wherein the processor 520 invokes executable program code stored in the memory 510 to perform some or all of the steps in the transformer fault detection method of embodiment one.
An embodiment of the present invention discloses a computer-readable storage medium storing a computer program, wherein the computer program causes a computer to execute some or all of the steps in the transformer fault detection method in the first embodiment.
The embodiment of the invention also discloses a computer program product, wherein when the computer program product runs on a computer, the computer is caused to execute part or all of the steps in the transformer fault detection method in the first embodiment.
The embodiment of the invention also discloses an application release platform, wherein the application release platform is used for releasing the computer program product, and the computer is caused to execute part or all of the steps in the transformer fault detection method in the first embodiment when the computer program product runs on the computer.
In various embodiments of the present invention, it should be understood that the size of the sequence numbers of the processes does not mean that the execution sequence of the processes is necessarily sequential, and the execution sequence of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer-accessible memory. Based on this understanding, the technical solution of the present invention, or a part contributing to the prior art or all or part of the technical solution, may be embodied in the form of a software product stored in a memory, comprising several requests for a computer device (which may be a personal computer, a server or a network device, etc., in particular may be a processor in a computer device) to execute some or all of the steps of the method according to the embodiments of the present invention.
In the embodiments provided herein, it should be understood that "B corresponding to a" means that B is associated with a, from which B can be determined. It should also be understood that determining B from a does not mean determining B from a alone, but may also determine B from a and/or other information.
Those of ordinary skill in the art will appreciate that some or all of the steps of the various methods of the described embodiments may be implemented by hardware associated with a program that may be stored in a computer-readable storage medium, including Read-Only Memory (ROM), random-access Memory (Random Access Memory, RAM), programmable Read-Only Memory (Programmable Read-Only Memory, PROM), erasable programmable Read-Only Memory (Erasable Programmable Read-Only Memory, EPROM), one-time programmable Read-Only Memory (OTPROM), electrically erasable programmable Read-Only Memory (EEPROM), compact disc Read-Only Memory (Compact Disc Read-Only Memory, CD-ROM), or other optical disk Memory, magnetic disk Memory, tape Memory, or any other medium capable of being used to carry or store data that is readable by a computer.
The transformer fault detection method, device, electronic equipment and storage medium disclosed in the embodiments of the present invention are described in detail, and specific examples are applied to illustrate the principles and implementation of the present invention, and the description of the above embodiments is only used to help understand the method and core idea of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Claims (8)
1. A method for detecting a transformer fault, comprising:
acquiring real-time pulse current data of a transformer to be detected through a preset pulse current detection module; a current noise reduction circuit is arranged in the pulse current detection module, and the current noise reduction circuit carries out noise reduction treatment on the acquired real-time pulse current data;
generating a current waveform video according to the real-time pulse current data, wherein the current waveform video comprises a multi-frame current waveform diagram; wherein each frame current waveform map is generated based on the detected real-time pulse current data;
Image extraction is carried out on the current waveform video every second to obtain a current waveform diagram in a corresponding time period, and the current waveform diagram is input into an abnormal waveform identification model which is built in advance to carry out abnormal detection of current fluctuation so as to obtain a corresponding first abnormal detection result;
acquiring first time information associated with the first abnormality detection result, and carrying out data association on the first time information, the first abnormality detection result and corresponding transformer information;
when the times of detecting the first abnormal detection result of the corresponding transformer exceeds the set times, executing the next step;
acquiring a first time information set associated with the first abnormal detection result, and determining trend information of the abnormal detection result according to the first time information set, wherein the trend information is used for representing frequency information of sporadic pulse occurrence or fault time information of partial discharge occurrence;
carrying out information reminding according to the fault time information;
and if the first abnormal detection result is matched with the set condition, reminding the fault of the transformer.
2. The transformer fault detection method according to claim 1, further comprising, after the first abnormality detection result matches a set condition:
Acquiring two frames of waveform images adjacent to the front and rear of the current waveform image, and inputting the two frames of waveform images adjacent to the front and rear into an abnormal waveform identification model to acquire a second abnormal detection result;
and if the second abnormal detection result is also matched with the set condition, prompting the fault of the transformer.
3. The transformer fault detection method according to claim 1, further comprising, after the first abnormality detection result matches a set condition:
acquiring a transformer voiceprint signal at a transformer through a sound sensor arranged at the transformer;
performing feature recognition on the transformer voiceprint signals to obtain rising edge signals and falling edge signals in the transformer voiceprint signals, and performing amplitude lifting on the rising edge signals and the falling edge signals in the transformer voiceprint signals according to set amplitude so as to obtain the voiceprint signals to be noise reduced;
determining noise state information of the transformer according to the position information of the transformer, determining a corresponding voiceprint noise reduction model according to the noise state information, and performing noise reduction processing on the voiceprint signal to be noise reduced based on the voiceprint noise reduction model to obtain noise reduction information;
Dividing continuous unstable noise-reducing voiceprint information into a plurality of sections of short-time voiceprint signals through framing and windowing operations; the preprocessed multi-section short-time voiceprint signals are converted into linear frequency spectrum signals by adopting fast Fourier transform;
carrying out feature extraction on the linear spectrum signal by adopting a Mel frequency cepstrum coefficient to obtain a voiceprint feature signal;
and identifying the voiceprint features through an anomaly detection algorithm to obtain corresponding voiceprint detection results.
4. The transformer fault detection method of claim 3, wherein the identifying the voiceprint features by an anomaly detection algorithm to obtain corresponding voiceprint detection results comprises:
further feature extraction is carried out on the voiceprint features by adopting a deep confidence network to obtain deep voiceprint features, wherein the deep confidence network is composed of three layers of restricted Boltzmann machines; optimizing two super parameters of batch size and learning rate in the deep confidence network;
and inputting the deep voiceprint features into a support vector machine algorithm to perform defect identification so as to determine corresponding voiceprint detection results.
5. The transformer fault detection method of claim 1, wherein the fault detection method further comprises:
Different kinds of parameter values of each acquisition time of the transformer to be detected are obtained, wherein the parameter values at least comprise an electric signal value and a gas signal value; the gas signal values are a first gas value, a second gas value, a third gas value, a fourth gas value and a fifth gas value;
constructing a first fault parameter, a second fault parameter and a third fault parameter according to the first gas value, the second gas value, the third gas value, the fourth gas value and the fifth gas value; the first fault parameter is the ratio of a third gas parameter to a fourth gas parameter, the second fault parameter is the ratio of the second gas parameter to the first gas parameter, and the third fault parameter is the ratio of the fourth gas parameter to the fifth gas parameter;
determining a corresponding probability distribution function according to the first fault parameter, the second fault parameter, the third fault parameter, the electric signal value, the transformer fault table and the logic membership model; the logical membership model includes:
，
wherein C is j Is the first fault parameter, the second fault parameter, the third fault parameter or the electrical signal value, T ij For C under corresponding fault j Is a value of l (C) j ,T ij ) Is C j To T ij Distance of interval T j For the history interval range under the corresponding fault, l (C j ,T ij ) Is C j To T j Distance of interval k ij (C j ) Representing the fault probability of the transformer;
and determining the fault type and fault probability curve of the transformer to be detected according to the probability distribution function.
6. A transformer fault detection device, comprising:
the acquisition module is used for: the real-time pulse current data of the transformer to be detected are obtained through a preset pulse current detection module; a current noise reduction circuit is arranged in the pulse current detection module, and the current noise reduction circuit carries out noise reduction treatment on the acquired real-time pulse current data;
and a video generation module: the current waveform video generating device is used for generating a current waveform video according to the real-time pulse current data, wherein the current waveform video comprises a plurality of frames of current waveform diagrams; wherein each frame current waveform map is generated based on the detected real-time pulse current data;
the waveform detection module: the method comprises the steps of performing image extraction on a current waveform video every second to obtain a current waveform diagram in a corresponding time period, and inputting the current waveform diagram into a pre-built abnormal waveform recognition model to perform abnormality detection on current fluctuation so as to obtain a corresponding first abnormality detection result;
Acquiring first time information associated with the first abnormality detection result, and carrying out data association on the first time information, the first abnormality detection result and corresponding transformer information;
when the times of detecting the first abnormal detection result of the corresponding transformer exceeds the set times, executing the next step;
acquiring a first time information set associated with the first abnormal detection result, and determining trend information of the abnormal detection result according to the first time information set, wherein the trend information is used for representing frequency information of sporadic pulse occurrence or fault time information of partial discharge occurrence;
carrying out information reminding according to the fault time information;
and the fault early warning module is used for: and the transformer fault reminding module is used for carrying out transformer fault reminding if the first abnormal detection result is matched with the set condition.
7. An electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor invokes the executable program code stored in the memory for performing the transformer fault detection method of any one of claims 1 to 5.
8. A computer-readable storage medium storing a computer program, wherein the computer program causes a computer to execute the transformer fault detection method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311474119.8A CN117214780B (en) | 2023-11-08 | 2023-11-08 | Transformer fault detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311474119.8A CN117214780B (en) | 2023-11-08 | 2023-11-08 | Transformer fault detection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117214780A CN117214780A (en) | 2023-12-12 |
| CN117214780B true CN117214780B (en) | 2024-02-02 |
Family
ID=89051469
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311474119.8A Active CN117214780B (en) | 2023-11-08 | 2023-11-08 | Transformer fault detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117214780B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117909911B (en) * | 2024-03-19 | 2024-06-14 | 江苏征途电气科技有限公司 | Electrical equipment partial discharge abnormality detection method based on artificial intelligence |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| NL7117870A (en) * | 1970-12-28 | 1972-06-30 | ||
| JP2002330306A (en) * | 2001-05-01 | 2002-11-15 | Mitsubishi Electric Corp | Flyback transformer abnormality detection circuit |
| CN102854445A (en) * | 2012-10-18 | 2013-01-02 | 上海市电力公司 | Method for extracting waveform feature of local discharge pulse current |
| KR20130017611A (en) * | 2011-08-11 | 2013-02-20 | (주) 예스텔레콤 | Apparatus for detecting arc fault using arc pulse timing |
| JP2014062775A (en) * | 2012-09-20 | 2014-04-10 | Rion Co Ltd | Vibration monitoring system, and environment monitoring system |
| CN104020398A (en) * | 2014-06-03 | 2014-09-03 | 华北电力大学 | Method for extracting partial discharge waveform features of converter transformer |
| CN106267560A (en) * | 2016-09-30 | 2017-01-04 | 深圳硅基仿生科技有限公司 | Pulse current for nerve stimulation produces circuit and retinal prosthesis system |
| US10132875B1 (en) * | 2013-04-25 | 2018-11-20 | Power Control Systems, Inc. | Device and method for open phase detection |
| CN110346685A (en) * | 2019-07-16 | 2019-10-18 | 杭州核诺瓦科技有限公司 | The device and method of large-size machine stator winding turn-to-turn state-detection |
| CN111830438A (en) * | 2019-04-19 | 2020-10-27 | 宁波奥克斯高科技有限公司 | Transformer fault detection method and transformer |
| CN112206415A (en) * | 2020-09-04 | 2021-01-12 | 未来穿戴技术有限公司 | Pulse signal processing circuit and method and medium-high frequency electrical stimulation device |
| KR20210044561A (en) * | 2019-10-15 | 2021-04-23 | 한국전력공사 | Apparatus and Method for converting power intelligently |
| CN113655318A (en) * | 2021-08-18 | 2021-11-16 | 中车青岛四方车辆研究所有限公司 | Detection device and method for LLC resonance abnormity |
| KR102329199B1 (en) * | 2021-09-08 | 2021-11-18 | 양전관 | Current transformer measuring line safety error detection system |
| CN114166852A (en) * | 2021-12-06 | 2022-03-11 | 国网宁夏电力有限公司超高压公司 | Smoothing reactor on-line monitoring method and system based on multispectral detection |
| CN216411535U (en) * | 2021-09-23 | 2022-04-29 | 国网浙江新昌县供电有限公司 | Distributed deployed portable current transformer polarity detection equipment |
| CN116027161A (en) * | 2023-03-16 | 2023-04-28 | 武汉纺织大学 | Method, device, equipment and medium for monitoring partial discharge pulse signals of power equipment |
| CN116593811A (en) * | 2023-07-17 | 2023-08-15 | 南京欧陆电气股份有限公司 | Integrated frequency converter running state monitoring system and monitoring method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7028899B2 (en) * | 1999-06-07 | 2006-04-18 | Metrologic Instruments, Inc. | Method of speckle-noise pattern reduction and apparatus therefore based on reducing the temporal-coherence of the planar laser illumination beam before it illuminates the target object by applying temporal phase modulation techniques during the transmission of the plib towards the target |
-
2023
- 2023-11-08 CN CN202311474119.8A patent/CN117214780B/en active Active
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| NL7117870A (en) * | 1970-12-28 | 1972-06-30 | ||
| JP2002330306A (en) * | 2001-05-01 | 2002-11-15 | Mitsubishi Electric Corp | Flyback transformer abnormality detection circuit |
| KR20130017611A (en) * | 2011-08-11 | 2013-02-20 | (주) 예스텔레콤 | Apparatus for detecting arc fault using arc pulse timing |
| JP2014062775A (en) * | 2012-09-20 | 2014-04-10 | Rion Co Ltd | Vibration monitoring system, and environment monitoring system |
| CN102854445A (en) * | 2012-10-18 | 2013-01-02 | 上海市电力公司 | Method for extracting waveform feature of local discharge pulse current |
| US10132875B1 (en) * | 2013-04-25 | 2018-11-20 | Power Control Systems, Inc. | Device and method for open phase detection |
| CN104020398A (en) * | 2014-06-03 | 2014-09-03 | 华北电力大学 | Method for extracting partial discharge waveform features of converter transformer |
| CN106267560A (en) * | 2016-09-30 | 2017-01-04 | 深圳硅基仿生科技有限公司 | Pulse current for nerve stimulation produces circuit and retinal prosthesis system |
| CN111830438A (en) * | 2019-04-19 | 2020-10-27 | 宁波奥克斯高科技有限公司 | Transformer fault detection method and transformer |
| CN110346685A (en) * | 2019-07-16 | 2019-10-18 | 杭州核诺瓦科技有限公司 | The device and method of large-size machine stator winding turn-to-turn state-detection |
| KR20210044561A (en) * | 2019-10-15 | 2021-04-23 | 한국전력공사 | Apparatus and Method for converting power intelligently |
| CN112206415A (en) * | 2020-09-04 | 2021-01-12 | 未来穿戴技术有限公司 | Pulse signal processing circuit and method and medium-high frequency electrical stimulation device |
| CN113655318A (en) * | 2021-08-18 | 2021-11-16 | 中车青岛四方车辆研究所有限公司 | Detection device and method for LLC resonance abnormity |
| KR102329199B1 (en) * | 2021-09-08 | 2021-11-18 | 양전관 | Current transformer measuring line safety error detection system |
| CN216411535U (en) * | 2021-09-23 | 2022-04-29 | 国网浙江新昌县供电有限公司 | Distributed deployed portable current transformer polarity detection equipment |
| CN114166852A (en) * | 2021-12-06 | 2022-03-11 | 国网宁夏电力有限公司超高压公司 | Smoothing reactor on-line monitoring method and system based on multispectral detection |
| CN116027161A (en) * | 2023-03-16 | 2023-04-28 | 武汉纺织大学 | Method, device, equipment and medium for monitoring partial discharge pulse signals of power equipment |
| CN116593811A (en) * | 2023-07-17 | 2023-08-15 | 南京欧陆电气股份有限公司 | Integrated frequency converter running state monitoring system and monitoring method |
Non-Patent Citations (2)
| Title |
|---|
| Remote fault diagnosis system for power transformer insulation based on RIA model;Mingjun Liu等;《2016 IEEE International Conference on High Voltage Engineering and Application (ICHVE)》;全文 * |
| 电力变压器局部放电带电检测及定位技术综述;刘嘉林等;《绝缘材料》;第48卷(第8期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117214780A (en) | 2023-12-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117214780B (en) | Transformer fault detection method and device | |
| CN103915818B (en) | Series connection fault electric arc detecting method and special device thereof | |
| CN104061851A (en) | Method for online monitoring deformation of transformer winding based on over-voltage response | |
| JP7378914B2 (en) | Evaluation of phase-resolved partial discharge | |
| CN110221137B (en) | Distribution transformer abnormal state detection method based on vibration-sound correlation | |
| US10191114B2 (en) | System for analysis of partial discharge defects of gas insulated switchgear | |
| JP2008514943A (en) | Method and apparatus for detecting an arc phenomenon on at least one electrical cable | |
| CN114252749B (en) | Transformer partial discharge detection method and device based on multiple sensors | |
| CN113671325B (en) | Terminal partial discharge monitoring method and system based on high-frequency electric field change | |
| CN102353881A (en) | Online capacitor monitoring system based on partial discharge monitoring | |
| JP2018112452A (en) | Device and method for partial discharge monitoring | |
| CN113447770A (en) | High-voltage circuit breaker partial discharge monitoring and early warning method | |
| JP2008185463A (en) | Insulation abnormality diagnosis system of electrical facility | |
| CN115856709A (en) | Data processing method for sensor of power equipment | |
| CN103400308A (en) | Online detection method and online detection system for running state of GIS (gas insulated switchgear) equipment | |
| EP2174149A1 (en) | A method and an apparatus for monitoring an activity of partial electrical discharges in an electrical apparatus powered with direct voltage | |
| CN114485379A (en) | Transformer winding on-line monitoring method | |
| CN102288881B (en) | Method for diagnosing severity of discharging shortcoming of oil paper insulation thorn of transformer | |
| CN111160383A (en) | Self-adaptive fire disaster model early warning detection method for oil-immersed transformer | |
| CN215416884U (en) | Power transformer state identification and safety prevention and control system | |
| KR102239343B1 (en) | Method and apparatus for determining the risk of deterioration of electrical equipment based on partial discharge | |
| CN112601967B (en) | Method and system for condition monitoring of electrical equipment | |
| CN113721116A (en) | Fault identification method and system based on partial discharge and oil pressure detection | |
| CN111624445A (en) | Partial discharge detection method and system based on infrared temperature measurement sensor | |
| CN117633611B (en) | Dangerous electrical appliance and electricity behavior identification method and system |
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 | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40104389 Country of ref document: HK |