CN117991061A - Insulator pollution flashover position identification method based on voiceprint and infrared thermal imaging - Google Patents
Insulator pollution flashover position identification method based on voiceprint and infrared thermal imaging Download PDFInfo
- Publication number
- CN117991061A CN117991061A CN202410386512.XA CN202410386512A CN117991061A CN 117991061 A CN117991061 A CN 117991061A CN 202410386512 A CN202410386512 A CN 202410386512A CN 117991061 A CN117991061 A CN 117991061A
- Authority
- CN
- China
- Prior art keywords
- insulator
- pollution flashover
- voiceprint
- area
- duration
- 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
- 239000012212 insulator Substances 0.000 title claims abstract description 315
- 238000001931 thermography Methods 0.000 title claims abstract description 34
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000012549 training Methods 0.000 claims description 13
- 239000003513 alkali Substances 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 9
- 239000013535 sea water Substances 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000011109 contamination Methods 0.000 claims 1
- 238000004590 computer program Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 239000000428 dust Substances 0.000 description 7
- 230000006870 function Effects 0.000 description 5
- 230000015556 catabolic process Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000001228 spectrum Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 239000011521 glass Substances 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 235000002639 sodium chloride Nutrition 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- FAPWRFPIFSIZLT-UHFFFAOYSA-M Sodium chloride Chemical compound [Na+].[Cl-] FAPWRFPIFSIZLT-UHFFFAOYSA-M 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 239000004020 conductor Substances 0.000 description 2
- 210000003608 fece Anatomy 0.000 description 2
- 239000003337 fertilizer Substances 0.000 description 2
- 239000007789 gas Substances 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 239000011810 insulating material Substances 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 239000011780 sodium chloride Substances 0.000 description 2
- 239000002689 soil Substances 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 239000000919 ceramic Substances 0.000 description 1
- 238000004939 coking Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 239000000356 contaminant Substances 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 125000001475 halogen functional group Chemical group 0.000 description 1
- 238000003331 infrared imaging Methods 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 229910052573 porcelain Inorganic materials 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
- 238000009736 wetting Methods 0.000 description 1
Landscapes
- Insulators (AREA)
Abstract
The invention discloses an insulator pollution flashover position identification method based on voiceprint and infrared thermal imaging, which comprises the following steps: acquiring the insulator audio frequency in the region to be identified, and extracting voiceprint characteristics of the insulator audio frequency to obtain the insulator voiceprint characteristics to be identified; calculating cosine similarity of the voice print characteristics of the insulator to be identified and the insulator pollution flashover comparison voice print characteristics, determining that the insulator audio is the insulator pollution flashover audio when the cosine similarity is larger than a similarity threshold, and judging that the insulator pollution flashover exists in the area; acquiring infrared thermal imaging of an insulator in the area to obtain the temperature of the insulator and the temperatures of the two ends of the insulator, marking the insulator with the temperature exceeding the temperatures of the two ends of the insulator as a pollution flashover area to be determined, and recording the duration of the high temperature of the pollution flashover area to be determined; calculating a duration difference value between the duration of the insulator pollution flashover audio frequency and the duration of the high temperature of the area to be determined of the pollution flashover, and if the duration difference value is smaller than a duration error threshold value, judging that the area to be determined of the pollution flashover is the occurrence position of the insulator pollution flashover.
Description
Technical Field
The invention belongs to the technical field of insulator pollution flashover detection, and particularly relates to an insulator pollution flashover position identification method based on voiceprint and infrared thermal imaging.
Background
The insulator is a special disc-shaped stacked insulating control, is usually made of glass or ceramic, and is arranged on the tower head of a high-voltage electric tower of the overhead transmission line for increasing the creepage distance. The insulator pollution flashover refers to the phenomenon that the surface of the insulator is creeped or flashover; the creepage of an insulator refers to a charging area where insulating materials around conductors on an overhead transmission line are electrically polarized, and the insulating materials are charged, wherein the creepage is caused by pollution substances with conductive performance, such as dust, greasy dirt and the like, accumulated on the surface of the insulator of the line, and after the surface of the insulator is wetted in humid weather, a discharging phenomenon is formed on the surface of the insulator, and electric leakage is generally caused. When the leakage current increases to a certain value, a surface breakdown discharge is caused, which is called flashover.
The insulator creepage is a phenomenon that frequently happens, if only intermittent slight creepage occurs, special treatment is not needed, but if continuous centralized creepage occurs, the creepage exceeds a certain time, and even when flashover occurs, the operation safety and reliability of a power system can be seriously affected. Firstly, the creepage phenomenon can lead to breakdown of components such as a telegraph pole, a bracket and the like, and accidents are caused. Secondly, the creepage of the high-voltage power equipment can lead to partial discharge of the equipment, so that the insulation capacity is reduced, and the ageing and damage of the equipment are accelerated. And thirdly, tripping power failure can be directly caused under the serious condition of creepage, so that the whole line is stopped and the power is cut off in a large-area. Therefore, the method is particularly important for insulator pollution flashover detection by technical means.
At present, the insulator is detected through personnel inspection, unmanned aerial vehicle inspection, telescope observation, camera shooting and the like, and the detection is usually inaccurate and timely, and a large amount of manpower and material resources are required to be consumed, so that the insulator is in a breakdown scrapped state when being detected. In the prior art, the insulator pollution flashover detection is realized by carrying out voiceprint recognition on the insulator, however, the voiceprint recognition can only judge that the insulator pollution flashover exists in a large range, the specific pollution flashover position can not be accurately positioned, and the early warning is only needed when the continuous concentrated pollution flashover phenomenon occurs, the continuous concentrated pollution flashover phenomenon can not be accurately judged by simple voiceprint recognition, and the early warning error probability is high.
Aiming at the problems existing in the prior art, the invention designs an insulator pollution flashover position identification method based on voiceprint and infrared thermal imaging.
Disclosure of Invention
Accordingly, the present invention is directed to a method for identifying a dirty flashover position of an insulator based on voiceprint and infrared thermal imaging, which can solve the above-mentioned problems.
The invention provides an insulator pollution flashover position identification method based on voiceprint and infrared thermal imaging, which comprises the following steps:
And judging the pollution flashover range:
Acquiring the insulator audio frequency in the region to be identified, and extracting voiceprint characteristics of the insulator audio frequency to obtain the insulator voiceprint characteristics to be identified;
calculating cosine similarity of the voice print characteristics of the insulator to be identified and the insulator pollution flashover comparison voice print characteristics, determining that the insulator audio is the insulator pollution flashover audio when the cosine similarity is larger than a similarity threshold, and judging that the insulator pollution flashover exists in the area;
Judging the pollution flashover position of the insulator:
acquiring an insulator infrared thermal image in the area, carrying out temperature identification on the insulator infrared thermal image to obtain the temperature of the insulator and the temperatures at the two ends of the insulator, marking the insulator with the temperature exceeding the temperatures at the two ends of the insulator as a pollution flashover area to be determined, and recording the high-temperature duration of the pollution flashover area to be determined;
Calculating a duration difference value between the duration of the insulator pollution flashover audio frequency and the duration of the high temperature of the area to be determined of the pollution flashover, and if the duration difference value is smaller than a duration error threshold value, judging that the area to be determined of the pollution flashover is the occurrence position of the insulator pollution flashover.
Further, the extracting the voiceprint feature of the insulator audio to obtain the insulator voiceprint feature to be identified includes:
preprocessing the insulator audio to obtain FBANK acoustic features of the insulator audio;
inputting FBANK acoustic features of the insulator audio frequency into a pre-trained voiceprint recognition model for processing to obtain the insulator voiceprint features to be recognized.
Further, the voiceprint recognition model is obtained through the following pre-training steps:
Constructing a basic voiceprint recognition model by using ECAPA-TDNN model;
Collecting insulator audios of different region types, extracting FBANK acoustic features of the insulator audios of the different region types, and constructing voiceprint training sets of the different region types;
And training the basic voiceprint recognition model by using voiceprint training sets of different region types to obtain the voiceprint recognition models of different region types.
Further, the different region types include: mountain forest areas, industrial areas, saline-alkali areas, seawater areas, and road farmland areas.
Further, the insulator pollution flashover comparison voiceprint characteristics are obtained through the following steps:
And collecting insulator pollution flashover audios of the same region type, and extracting voiceprint features of the insulator pollution flashover audios to obtain the insulator pollution flashover comparison voiceprint features.
Further, the temperature identification for the insulator infrared thermal imaging to obtain the insulator temperature and the temperatures at two ends thereof comprises the following steps:
Carrying out insulator contour recognition on the insulator infrared thermal imaging to obtain an insulator contour;
And selecting the temperature in the contour of the insulator as the temperature of the insulator, and selecting the temperatures at two ends of the contour of the insulator as the temperatures at two ends.
Further, after the determining that the area to be determined is the insulator pollution flashover occurrence position, performing:
Judging whether the duration of the insulator pollution flashover audio frequency and the duration of the high temperature of the area to be determined of the pollution flashover exceeds the early warning duration, if so, sending a pollution flashover early warning signal.
Further, after the sending of the pollution flashover early warning signal, the steps are performed:
and acquiring an insulator night image in the area, and carrying out image recognition on the insulator night image to obtain the pollution flashover degree and the number of the insulators.
Further, acquiring the night image of the insulator in the area, performing image recognition on the night image of the insulator, and obtaining the pollution flashover degree and the number of the insulator comprises the following steps:
acquiring night images of the side surfaces of the insulators in the area, and identifying and marking the luminous areas of the insulators through image outlines;
determining the pollution flashover severity of the insulator light-emitting area according to the light-emitting intensity of the insulator light-emitting area;
And calculating the length of the luminous area of the insulator, and calculating the number of the pollution flashover sheets of the insulator according to the length of the insulator.
Further, calculating a duration difference value between the duration of the insulator pollution flashover audio frequency and the duration of the high temperature of the area to be determined of the pollution flashover, if the duration difference value is smaller than a duration error threshold value, determining that the area to be determined of the pollution flashover is the occurrence position of the insulator pollution flashover comprises:
and if the time length difference value is larger than the time length error threshold value, judging that other anomalies of the insulator exist in the area to be determined by the pollution flashover.
The invention has the beneficial effects that:
Firstly, extracting voiceprint features of an insulator in an area to be identified by acquiring the insulator audio in the area to be identified, so as to obtain the voiceprint features of the insulator to be identified; and collecting the insulator audio frequency of the region, carrying out acoustic feature processing and voiceprint recognition on the insulator audio frequency of the region, reducing the interference of other audio frequencies and noise in the insulator audio frequency, and ensuring the accuracy of the comparison of the insulator voiceprint to be recognized and the pollution flashover insulator voiceprint.
Secondly, through calculating the cosine similarity of the voiceprint characteristics of the insulator to be identified and the insulator pollution flashover comparison voiceprint characteristics, when the cosine similarity is larger than a similarity threshold, the insulator audio frequency is determined to be the insulator pollution flashover audio frequency, the insulator pollution flashover exists in the area is judged, and whether the insulator pollution flashover exists in the insulator audio frequency area can be accurately and rapidly judged.
Thirdly, carrying out temperature identification on the insulator infrared thermal imaging by collecting the insulator infrared thermal imaging in the region, marking the region with the temperature exceeding the high temperature threshold as a pollution flashover region to be determined, and recording the high temperature duration of the pollution flashover region to be determined; because insulator audio voiceprint recognition can only judge that insulator pollution flashover exists in the area, namely the high-voltage electric tower range, the insulator pollution flashover can not be specifically positioned to the string of insulators, further judgment is carried out through insulator infrared thermal imaging, and the possible occurrence position of the insulator pollution flashover is determined through the high-temperature area.
And fourthly, calculating a duration difference value between the duration of the insulator pollution flashover audio frequency and the duration of the high temperature of the area to be determined of the pollution flashover, and if the duration difference value is smaller than a duration error threshold value, judging that the area to be determined of the pollution flashover is the occurrence position of the insulator pollution flashover. By adding the high-temperature time length of the insulator and the audio time length of the insulator as judging conditions and comparing the two time lengths, the pollution flashover occurrence position of the insulator can be accurately identified, and the replacement and maintenance of the pollution flashover insulator by subsequent staff are facilitated.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a method flow diagram of an embodiment of the present invention.
Detailed Description
For the convenience of understanding of those skilled in the art, the structure of the present invention will be described in further detail with reference to the accompanying drawings, and it should be understood that, unless the order of the steps mentioned in the present embodiment is specifically described, the order of the steps may be adjusted according to actual needs, and may even be performed simultaneously or partially simultaneously.
As shown in fig. 1, an embodiment of the present invention provides a method for identifying a dirty flash position of an insulator based on voiceprint and infrared thermal imaging, including:
and judging the pollution flashover range: s1 and S2;
S1, acquiring an insulator audio in a region to be identified, and extracting voiceprint features of the insulator audio to obtain the voiceprint features of the insulator to be identified;
s101, preprocessing the insulator audio to obtain FBANK acoustic features of the insulator audio;
S1011, emphasizing a high-frequency part of the insulator audio to obtain the emphasized insulator audio;
s1012, dividing the weighted insulator audio into a plurality of short-time frames, and substituting each short-time frame into a Hamming window function to obtain continuous short-time frames;
S1013, performing discrete Fourier transform on each short-time frame to obtain a frequency spectrum of each short-time frame, and performing modular squaring on the frequency spectrum of each short-time frame to obtain a power spectrum of the insulator audio;
s1014, filtering the power spectrum of the insulator audio through a Mel filter bank to obtain FBANK acoustic features.
In this step, can install insulator audio acquisition device in the middle of overhead transmission line's high-voltage electric tower, an insulator audio acquisition device can gather the insulator audio in radius 15 meters within range, therefore the region of a high-voltage electric tower can acquire the insulator audio through an insulator audio acquisition device, sets up insulator audio acquisition device in the middle part of high-voltage electric tower, can ensure that the signal intensity of the insulator audio who acquires is basically the same.
FBANK (FilterBank) is an audio front-end processing algorithm that processes audio in a manner similar to the human ear to improve speech recognition performance. Because FBANK acoustic features have higher correlation, the acoustic features are adopted as the features of the voiceprint to be identified, and the identification accuracy of the insulator audio can be effectively improved.
S102, inputting FBANK acoustic features of the insulator audio frequency into a pre-trained voiceprint recognition model for processing, and obtaining the insulator voiceprint features to be recognized.
S1021, constructing a basic voiceprint recognition model by using ECAPA-TDNN model;
s1022 is used for collecting insulator audios of different region types, extracting FBANK acoustic features of the insulator audios of the different region types, and constructing voiceprint training sets of the different region types;
S1023, training basic voiceprint recognition models by using voiceprint training sets of different region types to obtain the voiceprint recognition models of different region types.
In this step, the different region types include: mountain forest areas, industrial areas, saline-alkali areas, seawater areas, and road farmland areas. The cause of insulator pollution flashover due to different environmental factors in different areas is also different, for example, in mountain forest areas, which are areas with more birds, and often occur in seasons in which birds gather. Birds stay on the cross arms, and bird droppings fall on the insulator strings to form bird droppings pollution. And bird song sounds are also interfering factors that affect insulator audio discrimination. In industrial areas, such as industrial and mining enterprises like thermal power plants, chemical fertilizer plants, cement plants, coking plants, glass plants, metallurgical plants, etc., smoke dust and gas float in the air and form industrial pollution when falling on insulator strings. These contaminants may be liquids, gases or solids. In the saline-alkali area, dust containing salt particles is blown up by wind and accumulated on an insulator for a line in the saline-alkali area to form saline-alkali pollution. The damage of saline-alkali pollution to the line is more serious, and particularly in saline-alkali areas of sandy soil or semi-sandy soil, dust storm is often encountered, so that serious saline-alkali pollution is caused. In seawater areas, when a line approaches the coast, the ocean waves strike the coast, causing the seawater to splash or ocean particulates. Wind blows them far off shore. Once dropped onto the insulator, under dry weather conditions, the water evaporates and sea salt particles deposit on the insulator, forming a sea water foul. In the road farmland area, dust in the air flies upward due to wind or transportation vehicles, agricultural machinery and the like, and gradually falls on the surface of the insulator, so that pollution is formed. The dust does not contain a large amount of conductive materials, and the threat to the circuit is not great. If a large amount of fertilizers are applied in farmlands, conductive substances in dust are increased, and pollution flashover faults of insulator strings are easily caused.
Therefore, the insulator audios generated in different areas are different, for example, in mountain forest areas, bird sounds are main interference audios of the insulator audios, and therefore, the voiceprint recognition model of the area needs to remove the bird sounds more accurately; in the saline-alkali area and the seawater area, pollution flashover on the insulator is more severe and obvious due to pollution formed by saline alkali or seawater salinity, so that the pollution flashover frequency of the insulator in the area is higher; the insulator pollution flashover electrical conductivity is not very different in industrial areas and road areas, the pollution flashover audio frequency is not very different, but different types of noise exist, so that the insulator pollution flashover electrical conductivity needs to be distinguished. In order to ensure the accuracy of subsequent voiceprint recognition of insulator audios in different areas, the voiceprint recognition models in different areas are trained by adopting collected voiceprint samples in the areas, and the trained voiceprint recognition models in different areas are deployed in the corresponding areas without using a unified training model, so that the accuracy of voiceprint recognition in the local areas can be ensured.
The ECAPA-TDNN model structure and the specific training method are related art, and the description of this embodiment is omitted.
S2, calculating cosine similarity of the voiceprint features of the insulator to be identified and the insulator pollution flashover comparison voiceprint features, determining that the insulator audio is the insulator pollution flashover audio when the cosine similarity is larger than a similarity threshold, and judging that the insulator pollution flashover exists in the area;
S201, collecting insulator pollution flashover audio of the same region type, and extracting voiceprint features of the insulator pollution flashover audio to obtain insulator pollution flashover comparison voiceprint features.
In the step, the insulator pollution flashover comparison voiceprint characteristics are obtained by using the same identification method and the same voiceprint identification model as in the step S1, so that the accuracy of the insulator pollution flashover comparison voiceprint characteristics is ensured.
The insulator to be identified voice frequency is extracted by the voice print identification model, the insulator pollution flashover is compared with the voice print characteristic y, calculating the corresponding cosine similarity of x and y, wherein the similarity= (|x|y|) v (|x|y|), where|is L2 norm, and 0 is less than or equal to similarity is less than or equal to 1; the similarity threshold of the invention may be set to 0.8; if similarity >0.8, then the insulator audio is considered to be insulator pollution flashover audio.
Judging the pollution flashover position of the insulator: s3 and S4;
S3, acquiring infrared thermal imaging of the insulator in the region, carrying out temperature identification on the infrared thermal imaging of the insulator to obtain the temperature of the insulator and the temperatures of the two ends of the insulator, marking the insulator with the temperature exceeding the temperatures of the two ends of the insulator as a pollution flashover region to be determined, and recording the duration of the high temperature of the pollution flashover region to be determined;
S301, carrying out insulator contour recognition on the infrared thermal imaging of the insulator to obtain an insulator contour;
s302, selecting the temperature in the outline of the insulator as the temperature of the insulator, and selecting the temperatures at two ends of the outline of the insulator as the temperatures at two ends.
Further, if the temperature of the insulator includes a plurality of temperature values, comparing each temperature value with the temperatures of the two ends of the insulator, and marking a temperature value area where each temperature value exceeds the temperatures of the two ends of the insulator as a pollution flashover area to be determined.
In this step, since the insulator audio voiceprint recognition can only judge that the insulator pollution flashover exists in the region, namely the high-voltage point electric tower region, the insulator pollution flashover cannot be specifically positioned to the string of insulators, and further judgment needs to be performed through infrared thermal imaging. Different insulators (porcelain insulator, glass insulator and composite insulator) are slightly warmed up (slightly higher than the ambient temperature) under the normal working state, the whole temperature of the insulators is the same, two ends of each insulator are connected with leads, so that the two ends of each insulator are at a higher temperature than the insulators, when pollution flashover occurs on the insulators, leakage current on the surfaces of the insulators is increased, high temperature can be generated in a current increasing area, the temperature of the insulators is higher than that of the two ends of each insulator, the temperature of an insulator sheet area with serious pollution flashover is higher, the specific generation position of the pollution flashover of the insulators can be determined by utilizing the infrared thermal imaging of the insulators, the acquisition device of the infrared thermal imaging of the insulators can be placed on the upper part of a high-voltage electric tower, through overlooking shooting, the infrared thermal imaging of all insulators of the high-voltage electric tower can be ensured to be acquired, and when the pollution flashover of the insulators exists in the area, the pollution flashover of the insulators is determined to be a frequent phenomenon, if only the pollution flashover of the insulators occurs for a short duration time is generated, the insulator is not required to be cleaned and replaced by the insulators, and the continuous high temperature is required to be collected for subsequent judgment.
S4, calculating a duration difference value between the insulator pollution flashover audio duration and the high-temperature duration of the pollution flashover area to be determined, and if the duration difference value is smaller than a duration error threshold value, judging that the pollution flashover area to be determined is the insulator pollution flashover occurrence position.
Further, judging whether the duration of the insulator pollution flashover audio frequency and the duration of the high temperature of the area to be determined of the pollution flashover exceeds the early warning duration, if so, sending a pollution flashover early warning signal.
In this step, by adding the high temperature judgment condition of the insulator, and further comparing the occurrence time periods of the two, the exact occurrence position of the insulator pollution flashover can be obtained, and the insulator is a rapid and short process from the start of pollution flashover discharge to the high temperature, so that the difference between the audio time period and the high temperature time period is not large, and in this embodiment, the error threshold value can be 3 minutes.
Because insulator pollution flashover is a frequent phenomenon, if only a slight pollution flashover with a short duration appears, cleaning and replacement of the insulator are not needed, but if a continuous concentrated pollution flashover phenomenon appears, and the pollution flashover duration exceeds a certain time (in the embodiment, the early warning duration is 6 minutes), workers are required to be reminded of paying attention, the pollution flashover duration exceeds a certain time, high-voltage line short circuit is easy to cause, large-area power failure is caused, even line spark is caused, and therefore pollution flashover early warning is needed to inform the workers of cleaning and replacement of the insulator in the area.
Further, the night images of the insulators in the area are acquired, and the night images of the insulators are subjected to image recognition to obtain the pollution flashover degree and the number of the insulators. The method comprises the following specific steps:
acquiring night images of the side surfaces of the insulators in the area, and identifying and marking the luminous areas of the insulators through image outlines;
determining the pollution flashover severity of the insulator light-emitting area according to the light-emitting intensity of the insulator light-emitting area;
And calculating the length of the luminous area of the insulator, and calculating the number of the pollution flashover sheets of the insulator according to the length of the insulator.
In the step, the specific string of insulators in the area is known through the steps of voiceprint and infrared imaging identification, but the pollution flashover degree and the corresponding number of the insulators cannot be determined, so that night insulator images of the area can be shot by using an imaging device mounted on an inspection unmanned aerial vehicle or an imaging device arranged in the middle of a high-voltage tower, the pollution flashover degree and the pollution flashover number of the insulators are judged, the current halo can be clearly seen in the night images due to long-time creepage current on the surfaces of the pollution flashover insulators, the severity of the pollution flashover can be determined according to the luminous intensity, the more creepage current is, the more luminous intensity is the more serious the pollution flashover is, the insulator luminous area can be obtained by utilizing an image identification technology, and the length dimension and the number of the insulators are fixed dimensions, so that the pollution flashover degree of the insulators and the number of the insulators can be calculated by utilizing the lengths of the insulators, the pollution flashover degree and the number of the insulators can be synchronously maintained for personnel, and the maintenance personnel can be carried out in a corresponding position, and the maintenance work efficiency is improved.
In addition, if the time length difference value is larger than a time length error threshold value, judging that other anomalies of the insulator exist in the area to be determined by the pollution flashover.
In this step, there may be a problem that the high-temperature duration and the audio duration are not matched, which is generally that a shorter audio duration (may be short pollution flashover or misidentification of other audio) is collected, but the high-temperature duration is longer (there is a high temperature in the infrared thermal imaging, and the duration is longer), so that the difference between the two durations is larger, and at this time, other abnormal problems of the insulator, such as insulator degradation, internal core rod wetting, etc., may be caused, and through this step, the phenomenon may be identified and the end of the insulator is abnormal for early warning.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
In the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," "secured," and the like are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communicated with the inside of two elements or the interaction relationship of the two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms should not be understood as necessarily being directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Claims (10)
1. The insulator pollution flashover position identification method based on voiceprint and infrared thermal imaging is characterized by comprising the following steps of:
And judging the pollution flashover range:
Acquiring the insulator audio frequency in the region to be identified, and extracting voiceprint characteristics of the insulator audio frequency to obtain the insulator voiceprint characteristics to be identified;
calculating cosine similarity of the voice print characteristics of the insulator to be identified and the insulator pollution flashover comparison voice print characteristics, determining that the insulator audio is the insulator pollution flashover audio when the cosine similarity is larger than a similarity threshold, and judging that the insulator pollution flashover exists in the area;
Judging the pollution flashover position of the insulator:
acquiring an insulator infrared thermal image in the area, carrying out temperature identification on the insulator infrared thermal image to obtain the temperature of the insulator and the temperatures at the two ends of the insulator, marking the insulator with the temperature exceeding the temperatures at the two ends of the insulator as a pollution flashover area to be determined, and recording the high-temperature duration of the pollution flashover area to be determined;
Calculating a duration difference value between the duration of the insulator pollution flashover audio frequency and the duration of the high temperature of the area to be determined of the pollution flashover, and if the duration difference value is smaller than a duration error threshold value, judging that the area to be determined of the pollution flashover is the occurrence position of the insulator pollution flashover.
2. The method for identifying the insulator pollution flashover position based on voiceprint and infrared thermal imaging according to claim 1, wherein the extracting the voiceprint characteristics of the insulator audio frequency to obtain the insulator voiceprint characteristics to be identified comprises the following steps:
preprocessing the insulator audio to obtain FBANK acoustic features of the insulator audio;
inputting FBANK acoustic features of the insulator audio frequency into a pre-trained voiceprint recognition model for processing to obtain the insulator voiceprint features to be recognized.
3. The method for identifying the insulator pollution flashover position based on voiceprint and infrared thermal imaging according to claim 2, wherein the voiceprint identification model is obtained through the following pre-training steps:
Constructing a basic voiceprint recognition model by using ECAPA-TDNN model;
Collecting insulator audios of different region types, extracting FBANK acoustic features of the insulator audios of the different region types, and constructing voiceprint training sets of the different region types;
And training the basic voiceprint recognition model by using voiceprint training sets of different region types to obtain the voiceprint recognition models of different region types.
4. A method of identifying insulator contamination flashover locations based on voiceprint and infrared thermal imaging according to claim 3, wherein the different region types comprise: mountain forest areas, industrial areas, saline-alkali areas, seawater areas, and road farmland areas.
5. The method for identifying the insulator pollution flashover position based on voiceprint and infrared thermal imaging according to claim 1, wherein the insulator pollution flashover comparison voiceprint characteristics are obtained through the following steps:
And collecting insulator pollution flashover audios of the same region type, and extracting voiceprint features of the insulator pollution flashover audios to obtain the insulator pollution flashover comparison voiceprint features.
6. The method for identifying the pollution flashover position of the insulator based on voiceprint and infrared thermal imaging according to claim 1, wherein the step of identifying the temperature of the insulator by infrared thermal imaging to obtain the temperature of the insulator and the temperatures of the two ends of the insulator comprises the following steps:
Carrying out insulator contour recognition on the insulator infrared thermal imaging to obtain an insulator contour;
And selecting the temperature in the contour of the insulator as the temperature of the insulator, and selecting the temperatures at two ends of the contour of the insulator as the temperatures at two ends.
7. The method for identifying an insulator pollution flashover position based on voiceprint and infrared thermal imaging according to claim 1, wherein the determining that the area to be determined is the insulator pollution flashover occurrence position is performed after:
Judging whether the duration of the insulator pollution flashover audio frequency and the duration of the high temperature of the area to be determined of the pollution flashover exceeds the early warning duration, if so, sending a pollution flashover early warning signal.
8. The method for identifying a pollution flashover position of an insulator based on voiceprint and infrared thermal imaging according to claim 7, wherein the steps of sending a pollution flashover early warning signal are performed after:
and acquiring an insulator night image in the area, and carrying out image recognition on the insulator night image to obtain the pollution flashover degree and the number of the insulators.
9. The method for identifying the pollution flashover position of the insulator based on voiceprint and infrared thermal imaging according to claim 8, wherein the steps of collecting the night image of the insulator in the area, and identifying the night image of the insulator to obtain the pollution flashover degree and the number of the insulators comprise the following steps:
acquiring night images of the side surfaces of the insulators in the area, and identifying and marking the luminous areas of the insulators through image outlines;
determining the pollution flashover severity of the insulator light-emitting area according to the light-emitting intensity of the insulator light-emitting area;
And calculating the length of the luminous area of the insulator, and calculating the number of the pollution flashover sheets of the insulator according to the length of the insulator.
10. The method for identifying the insulator pollution flashover position based on voiceprint and infrared thermal imaging according to claim 1, wherein the calculating the duration difference between the insulator pollution flashover audio duration and the high-temperature duration of the area to be determined by pollution flashover comprises:
and if the time length difference value is larger than the time length error threshold value, judging that other anomalies of the insulator exist in the area to be determined by the pollution flashover.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410386512.XA CN117991061B (en) | 2024-04-01 | Insulator pollution flashover position identification method based on voiceprint and infrared thermal imaging |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410386512.XA CN117991061B (en) | 2024-04-01 | Insulator pollution flashover position identification method based on voiceprint and infrared thermal imaging |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117991061A true CN117991061A (en) | 2024-05-07 |
CN117991061B CN117991061B (en) | 2024-06-07 |
Family
ID=
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102928757A (en) * | 2012-11-22 | 2013-02-13 | 重庆理工大学 | Insulator arc-over fault positioning device and positioning method based on discharging light detection |
CN102937693A (en) * | 2012-11-26 | 2013-02-20 | 广州供电局有限公司 | External insulation strength discriminating method and system of contaminated insulators based on acoustic emission signals |
CN106129889A (en) * | 2016-06-08 | 2016-11-16 | 徐洪军 | A kind of insulator contamination on-Line Monitor Device and insulator decontamination apparatus |
CN109799442A (en) * | 2019-03-29 | 2019-05-24 | 云南电网有限责任公司电力科学研究院 | Insulator contamination prediction technique and system based on airborne hyperspectral |
CN114167119A (en) * | 2021-12-07 | 2022-03-11 | 厦门声百思信息科技有限公司 | System and method for monitoring phenomena of creepage, pollution flashover and flashover of insulator |
CN115753809A (en) * | 2022-11-30 | 2023-03-07 | 贵州电网有限责任公司 | Insulator contamination detection method, device, equipment and storage medium |
CN115862634A (en) * | 2022-12-23 | 2023-03-28 | 东莞理工学院 | Voiceprint recognition method and embedded device |
WO2024027009A1 (en) * | 2022-08-03 | 2024-02-08 | 重庆大学 | Infrared thermal imaging defect inspection method and apparatus for substation insulator |
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102928757A (en) * | 2012-11-22 | 2013-02-13 | 重庆理工大学 | Insulator arc-over fault positioning device and positioning method based on discharging light detection |
CN102937693A (en) * | 2012-11-26 | 2013-02-20 | 广州供电局有限公司 | External insulation strength discriminating method and system of contaminated insulators based on acoustic emission signals |
CN106129889A (en) * | 2016-06-08 | 2016-11-16 | 徐洪军 | A kind of insulator contamination on-Line Monitor Device and insulator decontamination apparatus |
CN109799442A (en) * | 2019-03-29 | 2019-05-24 | 云南电网有限责任公司电力科学研究院 | Insulator contamination prediction technique and system based on airborne hyperspectral |
CN114167119A (en) * | 2021-12-07 | 2022-03-11 | 厦门声百思信息科技有限公司 | System and method for monitoring phenomena of creepage, pollution flashover and flashover of insulator |
WO2024027009A1 (en) * | 2022-08-03 | 2024-02-08 | 重庆大学 | Infrared thermal imaging defect inspection method and apparatus for substation insulator |
CN115753809A (en) * | 2022-11-30 | 2023-03-07 | 贵州电网有限责任公司 | Insulator contamination detection method, device, equipment and storage medium |
CN115862634A (en) * | 2022-12-23 | 2023-03-28 | 东莞理工学院 | Voiceprint recognition method and embedded device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105116273A (en) | Insulator on-line monitoring system | |
CN112727710B (en) | Wind field thunderbolt density statistical method and system based on audio signals | |
CN111695506B (en) | Early warning method and system for wind-induced foreign matter short-circuit fault of transmission line | |
CN110907755A (en) | Power transmission line online monitoring fault recognition method | |
CN111274880A (en) | Video intelligent analysis auxiliary inspection and abnormity warning method | |
CN113623144A (en) | Blade state monitoring system based on acoustic algorithm and monitoring method thereof | |
CN106228140A (en) | The transmission line forest fire smog of a kind of combination weather environment sentences knowledge method | |
CN117991061B (en) | Insulator pollution flashover position identification method based on voiceprint and infrared thermal imaging | |
CN115467787A (en) | Motor state detection system and method based on audio analysis | |
CN117991061A (en) | Insulator pollution flashover position identification method based on voiceprint and infrared thermal imaging | |
CN112727703A (en) | Fan blade protective film damage monitoring method and system based on audio signal | |
CN115510265A (en) | Method and system for judging animal hazard distribution of pole tower in power transmission line | |
CN112683916A (en) | Method and device for identifying missing or mounting error of small hardware fittings of current collecting line tower | |
CN117009731A (en) | Power failure early warning method based on meteorological factors | |
CN115902541A (en) | Method and system for diagnosing discharge and defects of insulator of power transmission line | |
TWM646347U (en) | Computing device for predicting lightning strike | |
CN102937694A (en) | Device for monitoring external insulation strength of dirty insulator | |
CN113359211B (en) | Bird damage monitoring method for whole-line power transmission line | |
CN115187880A (en) | Communication optical cable defect detection method and system based on image recognition and storage medium | |
CN114442658A (en) | Automatic inspection system for unmanned aerial vehicle of power transmission and distribution line and operation method thereof | |
CN113640624A (en) | Pre-discharge risk early warning system and method for insulation defect of power transmission line | |
JP6053866B2 (en) | Wind power generation system and bird flight prediction device | |
CN110703080B (en) | GIS spike discharge diagnosis method, discharge degree identification method and device | |
CN114439702A (en) | Blade state monitoring method and device of wind driven generator | |
CN114167119A (en) | System and method for monitoring phenomena of creepage, pollution flashover and flashover of insulator |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant |