CN116310274A - State evaluation method for power transmission and transformation equipment - Google Patents
State evaluation method for power transmission and transformation equipment Download PDFInfo
- Publication number
- CN116310274A CN116310274A CN202310216335.6A CN202310216335A CN116310274A CN 116310274 A CN116310274 A CN 116310274A CN 202310216335 A CN202310216335 A CN 202310216335A CN 116310274 A CN116310274 A CN 116310274A
- Authority
- CN
- China
- Prior art keywords
- power transmission
- target
- equipment
- image
- transformation
- 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.)
- Pending
Links
- 230000005540 biological transmission Effects 0.000 title claims abstract description 103
- 230000009466 transformation Effects 0.000 title claims abstract description 99
- 238000011156 evaluation Methods 0.000 title claims abstract description 27
- 238000003745 diagnosis Methods 0.000 claims abstract description 23
- 238000003384 imaging method Methods 0.000 claims abstract description 18
- 238000001514 detection method Methods 0.000 claims abstract description 15
- 238000010438 heat treatment Methods 0.000 claims description 37
- 238000000034 method Methods 0.000 claims description 24
- 238000001228 spectrum Methods 0.000 claims description 15
- 230000007547 defect Effects 0.000 claims description 14
- 238000007689 inspection Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 9
- 230000003595 spectral effect Effects 0.000 claims description 6
- 230000036541 health Effects 0.000 claims description 5
- 239000012212 insulator Substances 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000013434 data augmentation Methods 0.000 claims description 4
- 238000003708 edge detection Methods 0.000 claims description 4
- 238000003331 infrared imaging Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000005856 abnormality Effects 0.000 claims description 3
- 239000003086 colorant Substances 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- 230000004927 fusion Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000010485 coping Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000011109 contamination Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000001931 thermography Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/255—Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
- G06V10/806—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/70—Labelling scene content, e.g. deriving syntactic or semantic representations
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Radiation Pyrometers (AREA)
Abstract
The invention provides a state evaluation method of power transmission and transformation equipment, which comprises the steps of collecting imaging information of the power transmission and transformation equipment in an area to be detected; respectively carrying out target identification on the visible light image and the infrared image through a pre-trained target identification model, and carrying out type identification on the identified power transmission and transformation equipment to frame a corresponding target equipment area; respectively carrying out fault detection and diagnosis on power transmission and transformation equipment in the visible light image and infrared image target identification area; and combining the visible light image with the fault diagnosis result of the infrared image target equipment area, and judging the working state of the power transmission and transformation equipment according to the severity of different types of faults. The invention combines data driving and model driving by considering the advantages and disadvantages of the multispectral image for different types of fault diagnosis, and meets the comprehensive and efficient state evaluation requirements of various power transmission and transformation devices.
Description
Technical Field
The invention relates to the technical field of state evaluation of power transmission and transformation equipment, in particular to a state evaluation method of power transmission and transformation equipment.
Background
Along with the application of intelligent inspection equipment such as unmanned aerial vehicle inspection lines, transformer substation inspection robots and the like and the massive use of the detection devices of the spectrum sensors such as infrared light, visible light and the like, massive image and video data are accumulated through the unmanned aerial vehicle equipment and the imaging sensors thereof. The collected image video data such as a large amount of infrared thermal imaging, visible light imaging, partial discharge atlas and the like are stored and processed in an unstructured mode, and the method is greatly helpful for finding out main defects of the appearance, environment, partial overheat, partial discharge and the like of the power equipment, can be used for evaluating the health degree of the working state of the power transmission and transformation equipment, but is lack of effective utilization means at present. Therefore, how to utilize these unstructured multispectral data for fault detection and status assessment of power transmission and transformation equipment is a significant challenge.
The traditional power equipment state evaluation is still highly finished by the person with abundant experience, a large amount of detection data cannot be comprehensively utilized, the state evaluation is still mainly based on single data, the efficiency is low, and the data island phenomenon is serious. In consideration of environmental, collection state device, space and other condition limitations, fault diagnosis and state evaluation of some power transmission and transformation equipment cannot rely on single spectrum image data only, and multispectral data fusion is also required. For example, the infrared inspection technology can be used for rapidly positioning the thermal defect of the equipment and regularly measuring the temperature field, but the infrared detection image lacks the power grid equipment outline and texture detail information of the visible light image, and the surface contamination, the part loss, the joint connection condition and the like cannot be accurately judged, so that the equipment identification and the state evaluation are required to be carried out through multi-spectrum data fusion by combining the visible light image.
In the face of a large amount of multispectral image data, the traditional method based on mathematical statistical analysis is difficult to adapt to the large-scale, unstructured and high-dimensional data processing requirements, a large amount of data in different running states of power transmission and transformation equipment is processed based on a data-driven deep learning method by utilizing the processing technology of large data analysis and artificial intelligence, the inherent correlation of the data is mined, the fault mode of the data is analyzed, and the power transmission and transformation equipment such as a power transmission line, a transformer, an insulator and a GIS is subjected to fault detection and state assessment by combining a model driving method based on physical mechanism analysis through multispectral data fusion.
Disclosure of Invention
The invention aims to provide a state evaluation method of power transmission and transformation equipment, which aims to solve the technical problem that how to combine data driving and model driving to meet the comprehensive and efficient state evaluation requirements of various power transmission and transformation equipment by considering the advantages and disadvantages of multispectral images for different types of fault diagnosis.
In one aspect, a method for evaluating a state of a power transmission and transformation device is provided, including:
acquiring imaging information of power transmission and transformation equipment in a region to be detected, wherein the imaging information is at least visible light images and infrared images of the power transmission and transformation equipment respectively shot at the same angle in the same region;
respectively carrying out target identification on the visible light image and the infrared image through a pre-trained target identification model, and carrying out type identification on the identified power transmission and transformation equipment to frame a corresponding target equipment area;
respectively carrying out fault detection and diagnosis on power transmission and transformation equipment in the visible light image and infrared image target identification area; determining temperature intervals represented by different red brightness in the infrared image, and comparing the temperature interval range of the heating fault with a preset temperature threshold value of the heating defect to determine the fault position in a target area; determining the frontal gradient structural characteristics and the edge texture characteristics in a target equipment area of the visible light image, judging whether the target equipment is faulty or not according to the contrast difference of the texture structures, and determining a fault area in the target area;
and combining the visible light image with the fault diagnosis result of the infrared image target equipment area, and judging the working state of the power transmission and transformation equipment according to the severity of different types of faults.
Preferably, after the imaging information is acquired, the shot multispectral image should be subjected to a film inspection of a preset program, whether the input image has obvious shooting abnormality is judged, and if the imaging effect meets the state evaluation requirement of a preset power transmission and transformation device, the imaging information is output.
Preferably, the target identification of the power transmission and transformation equipment at least comprises identification of the power transmission and transformation equipment of a power transmission line, a transformer, an insulator, a GIS and a circuit breaker.
Preferably, the target recognition model is used for target recognition of power transmission and transformation equipment, and data preprocessing of data augmentation is performed on different spectrum images through rotation scaling operation; inputting the processed spectrum image into a trained target recognition model to obtain typical characteristics of different power transmission and transformation devices; and identifying different types of power transmission and transformation equipment by extracting and classifying the characteristics of the input spectral image, wherein the output results of the identified target equipment are presented in the image in rectangular frames with different colors, and the different frames represent different types of power transmission and transformation equipment areas and are marked with the confidence values of identification.
Preferably, the fault detection and diagnosis of the power transmission and transformation equipment in the visible light image and infrared image target identification area comprises:
for the infrared images, temperature intervals of heating faults of different power transmission and transformation equipment are determined, the color interval of the infrared images corresponding to the heating faults is definitely obtained by combining an infrared imaging principle, the temperature interval range of the heating faults is obtained, and the characteristic threshold value for judging the heating faults is obtained by combining a preset color brightness interval.
Preferably, the method further comprises:
performing color gamut conversion on an infrared image area of the identification equipment, and converting a RGB color space into a YUV color space;
gray processing is carried out in a YUV color gamut, brightness information Y of a target area is extracted, and binarization threshold processing is carried out on the brightness information by combining with a characteristic threshold T of a heating defect;
judging whether the target area has a heating fault or not according to the binarization result, and marking a fault position in the target area if the heating fault occurs.
Preferably, the RGB color space is converted to YUV color space according to the following formula:
wherein ,
respectively represent YUV color space,>
respectively represent the color space of RGB.
Preferably, performing the binarization thresholding on the luminance information according to the following formula includes:
wherein y is brightness information, P is a binarization result, namely a quantized value by a binarization threshold method, and T is a characteristic threshold of the heating defect.
Preferably, the method further comprises:
for the visible light image, extracting gradient structural features of a target area by utilizing a gradient operator, and extracting edge texture features of the target area by utilizing an edge detection operator;
obtaining the obvious structural characteristics of the external contour of the target equipment by fusing the gradient and the edge characteristics of the target equipment;
according to the normal working state of the target power transmission and transformation equipment, determining the appearance outline and the connection state of the power transmission and transformation equipment under no fault, and taking the appearance outline and the connection state as template basis for judging whether the equipment is faulty or not;
and judging whether the target equipment has surface faults or not according to comparison between the obvious structural characteristics and the templates, and if so, identifying and marking the faults in the visible light image.
Preferably, the method further comprises:
and correspondingly combining the visible light image and the infrared image into a multispectral image, combining the visible light image and a fault diagnosis result of a target equipment area in the infrared image, determining the fault type and the fault degree of the target power transmission and transformation equipment, and judging the working state of the power transmission and transformation equipment according to the severity degree of different types of faults, wherein the working state of the power transmission and transformation equipment at least comprises health, good, attention and severity.
In summary, the embodiment of the invention has the following beneficial effects:
the state evaluation method of the power transmission and transformation equipment fully considers the advantages and disadvantages of the multispectral image for different types of fault diagnosis, combines the data driving and the model driving, can cope with the current research situation of big data, multidimensional and nonlinearity in the intelligent inspection of the current power grid, and can meet the comprehensive and efficient state evaluation requirements of various power transmission and transformation equipment. The advantages of various spectrum images in the process of coping with different types of fault detection are fully utilized, the fault types of the different spectrum images are identified and marked through the combination of data-driven target identification and model-driven fault diagnosis, and the comprehensive state evaluation of the power transmission and transformation equipment is carried out through multispectral fusion.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are required in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that it is within the scope of the invention to one skilled in the art to obtain other drawings from these drawings without inventive faculty.
Fig. 1 is a schematic flow chart of a state evaluation method of a power transmission and transformation device according to an embodiment of the present invention.
Fig. 2 is a logic schematic diagram of power transmission and transformation equipment identification in an embodiment of the invention.
Fig. 3 is a logic schematic diagram of an infrared image fault identification label in an embodiment of the invention.
Fig. 4 is a logic diagram of visible light image fault recognition in an embodiment of the present invention.
Fig. 5 is a logic schematic diagram of comprehensive state evaluation of a multi-spectrum fusion power transmission and transformation device in an embodiment of the invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings, for the purpose of making the objects, technical solutions and advantages of the present invention more apparent.
Fig. 1 is a schematic diagram of an embodiment of a state evaluation method of a power transmission and transformation device according to the present invention. In this embodiment, the method comprises the steps of:
step S1, acquiring imaging information of power transmission and transformation equipment in a region to be detected, wherein the imaging information is at least visible light images and infrared images of the power transmission and transformation equipment respectively shot at the same angle in the same region; that is, through intelligent inspection equipment such as unmanned aerial vehicle or unmanned car, shoot the equipment on the power transmission and transformation circuit, intelligent inspection equipment wears infrared imaging sensor and visible light's camera, can be used to catch the power transmission and transformation equipment under the same scene in the region of waiting to detect, and the output is the multispectral image data that is used for equipment state evaluation.
In a specific embodiment, after the imaging information is acquired, the shot multispectral image should pass through a film inspection of a preset program, whether the input image has obvious shooting abnormality is judged, and if the imaging effect meets the state evaluation requirement of a preset power transmission and transformation device, the imaging information is output.
Step S2, respectively carrying out target recognition on the visible light image and the infrared image through a pre-trained target recognition model, and carrying out type identification on the recognized power transmission and transformation equipment to frame out a corresponding target equipment area; that is, the data-driven deep learning algorithm YOLOV5 is used for target recognition of power transmission and transformation equipment, and firstly, data preprocessing is carried out on different spectrum images, and data augmentation is mainly carried out through rotating scaling operations of scale, angle and the like. The processed spectral images were then input into a trained YOLOV5 model, which contains Input, backbone, neck and Prediction four modules. By training and learning on the power grid equipment data, the typical characteristics of different power transmission and transformation equipment can be obtained, and by extracting and classifying the characteristics of the input spectral images, different types of power transmission and transformation equipment such as power transmission and transformation lines, transformers, insulators, GIS (gas insulated switchgear), circuit breakers and the like can be identified.
In a specific embodiment, the target identification of the power transmission and transformation equipment at least comprises identification of the power transmission and transformation equipment of a power transmission line, a transformer, an insulator, a GIS and a circuit breaker. As shown in fig. 2, the target recognition model is used for target recognition of power transmission and transformation equipment, and performs data preprocessing of data augmentation on different spectrum images through rotation scaling operation; inputting the processed spectrum image into a trained target recognition model to obtain typical characteristics of different power transmission and transformation devices; and identifying different types of power transmission and transformation equipment by extracting and classifying the characteristics of the input spectral image, wherein the output results of the identified target equipment are presented in the image in rectangular frames with different colors, and the different frames represent different types of power transmission and transformation equipment areas and are marked with the confidence values of identification.
Step S3, fault detection and diagnosis are respectively carried out on the power transmission and transformation equipment in the visible light image and infrared image target identification area; determining temperature intervals represented by different red brightness in the infrared image, and comparing the temperature interval range of the heating fault with a preset temperature threshold value of the heating defect to determine the fault position in a target area; determining gradient structure characteristics and edge texture characteristics in a target device area of the visible light image, judging whether the target device is faulty or not according to the contrast difference of texture structures, and determining a fault area in the target area; namely, fault detection and diagnosis are respectively carried out on power transmission and transformation equipment in the visible light image and infrared image target identification areas. And for the infrared image, according to analysis of a heating fault mechanism of the power transmission and transformation equipment, determining temperature intervals represented by different red brightness in the infrared image, and determining a temperature interval range in which the heating fault occurs. And then performing color gamut conversion and gray scale processing on the target equipment area, extracting brightness information of the equipment area, performing binarization feature extraction, judging whether the target area has a heating fault or not by combining a temperature threshold value of the heating defect, and marking the fault position of the target area under the condition of the heating fault. The fault detection and diagnosis of the whole infrared image is to detect and diagnose the heating fault by adopting a model driving mode on the basis of the data driving target identification. For visible light images, surface defects of power transmission and transformation equipment can be caused due to reasons such as appearance offset, missing and self-explosion, and the working state of the power transmission and transformation equipment is further affected. Therefore, according to the appearance and the normal working state of the target power transmission and transformation equipment, the appearance outline and the connection state of the power transmission and transformation equipment under no fault can be determined and used as template basis for judging whether the equipment is faulty or not. And then, respectively extracting gradient structure features and edge texture features in the target equipment region, judging whether the target equipment fails according to the contrast difference of the texture structures through feature fusion and template matching, if so, identifying the failure type in the visible light image, and marking the failure region.
In a specific embodiment, as shown in fig. 3, for an infrared image, temperature intervals of heating faults of different power transmission and transformation equipment are determined, a color interval of the infrared image corresponding to the heating faults is definitely obtained by combining an infrared imaging principle, a temperature interval range of the heating faults is obtained, and a characteristic threshold for judging the heating faults is obtained by combining a preset color brightness interval. Performing color gamut conversion on an infrared image area of the identification equipment, and converting a RGB color space into a YUV color space; gray processing is carried out in a YUV color gamut, brightness information Y of a target area is extracted, and binarization threshold processing is carried out on the brightness information by combining with a characteristic threshold T of a heating defect; judging whether the target area has a heating fault or not according to the binarization result, and marking a fault position in the target area if the heating fault occurs. Wherein the RGB color space is converted to YUV color space according to the following formula:
wherein ,
respectively represent YUV color space,>
respectively represent the color space of RGB.
The binarization thresholding of the luminance information according to the following formula comprises:
wherein y is brightness information, P is a binarization result, namely a quantized value by a binarization threshold method, and T is a characteristic threshold of the heating defect.
In this embodiment, as shown in fig. 4, for the visible light image, gradient structural features of the target region are extracted by using a gradient operator, and edge texture features of the target region are extracted by using an edge detection operator; obtaining the obvious structural characteristics of the external contour of the target equipment by fusing the gradient and the edge characteristics of the target equipment; according to the normal working state of the target power transmission and transformation equipment, determining the appearance outline and the connection state of the power transmission and transformation equipment under no fault, and taking the appearance outline and the connection state as template basis for judging whether the equipment is faulty or not; and judging whether the target equipment has surface faults or not according to comparison between the obvious structural characteristics and the templates, and identifying and marking the faults in the visible light image. For visible light images, gradient structural features of the target region are extracted by using the following Prewitt gradient operator,
and extracting edge texture features of the target area by using a Canny edge detection operator. By fusing the gradient and edge characteristics of the target device, the external contour and other obvious structural characteristics of the target device are obtained.
And S4, combining the visible light image with the fault diagnosis result of the infrared image target equipment area, and judging the working state of the power transmission and transformation equipment according to the severity of different types of faults. The fault identification method is characterized in that the fault of the infrared image and the light image is identified, and the defect type and the fault degree of the target power transmission and transformation equipment are comprehensively analyzed by utilizing the judging advantages of the multispectral image on different fault types. Then, according to the severity of different types of faults such as heating faults, surface faults and the like, the state of the power transmission and transformation equipment such as health, good, attention, severity and the like is comprehensively estimated through multi-spectrum weighted fusion.
In a specific embodiment, as shown in fig. 5, the visible light image and the infrared image are correspondingly combined into a multispectral image, the visible light image is combined with a fault diagnosis result of a target equipment area in the infrared image, diagnosis advantages of the multispectral image on different fault types are utilized, the fault type and the fault degree of the target power transmission and transformation equipment are comprehensively analyzed, a power grid maintainer is assisted in carrying out fault reason analysis, and the working state of the power transmission and transformation equipment such as health, good, attention, serious and the like is judged according to the severity degree of different types of faults. In a word, the invention realizes the effective state evaluation of different types of power transmission and transformation equipment based on a digital-analog dual-drive and multispectral fusion mode.
In summary, the embodiment of the invention has the following beneficial effects:
the state evaluation method of the power transmission and transformation equipment fully considers the advantages and disadvantages of the multispectral image for different types of fault diagnosis, combines the data driving and the model driving, can cope with the current research situation of big data, multidimensional and nonlinearity in the intelligent inspection of the current power grid, and can meet the comprehensive and efficient state evaluation requirements of various power transmission and transformation equipment. The advantages of various spectrum images in the process of coping with different types of fault detection are fully utilized, the fault types of the different spectrum images are identified and marked through the combination of data-driven target identification and model-driven fault diagnosis, and the comprehensive state evaluation of the power transmission and transformation equipment is carried out through multispectral fusion.
The foregoing disclosure is illustrative of the present invention and is not to be construed as limiting the scope of the invention, which is defined by the appended claims.
Claims (10)
1. A state evaluation method of a power transmission and transformation device, characterized by comprising:
acquiring imaging information of power transmission and transformation equipment in a region to be detected, wherein the imaging information is at least visible light images and infrared images of the power transmission and transformation equipment respectively shot at the same angle in the same region;
respectively carrying out target identification on the visible light image and the infrared image through a pre-trained target identification model, and carrying out type identification on the identified power transmission and transformation equipment to frame a corresponding target equipment area;
respectively carrying out fault detection and diagnosis on power transmission and transformation equipment in the visible light image and infrared image target identification area; determining temperature intervals represented by different red brightness in the infrared image, and comparing the temperature interval range of the heating fault with a preset temperature threshold value of the heating defect to determine the fault position in a target area; determining gradient structure characteristics and edge texture characteristics in a target device area of the visible light image, judging whether the target device is faulty or not according to the contrast difference of texture structures, and determining a fault area in the target area;
and combining the visible light image with the fault diagnosis result of the infrared image target equipment area, and judging the working state of the power transmission and transformation equipment according to the severity of different types of faults.
2. The method of claim 1, wherein after the imaging information is acquired, the shot multispectral image is subjected to a film inspection of a preset program, whether the input image has obvious shooting abnormality is judged, and if the imaging effect meets the state evaluation requirement of a preset power transmission and transformation device, the imaging information is output.
3. The method of claim 2, wherein the target identification of the power transmission and transformation device comprises at least identifying a power transmission and transformation device of a power transmission line, a transformer, an insulator, a GIS, a circuit breaker.
4. A method according to claim 3, wherein the object recognition model is used for object recognition of power transmission and transformation equipment, and data preprocessing for data augmentation is performed on different spectral images by performing a rotation scaling operation; inputting the processed spectrum image into a trained target recognition model to obtain typical characteristics of different power transmission and transformation devices; and identifying different types of power transmission and transformation equipment by extracting and classifying the characteristics of the input spectral image, wherein the output results of the identified target equipment are presented in the image in rectangular frames with different colors, and the different frames represent different types of power transmission and transformation equipment areas and are marked with the confidence values of identification.
5. The method of claim 4, wherein fault detection and diagnosis of power transmission and transformation equipment in the visible light image and infrared image target identification area comprises:
for the infrared images, temperature intervals of heating faults of different power transmission and transformation equipment are determined, the color interval of the infrared images corresponding to the heating faults is definitely obtained by combining an infrared imaging principle, the temperature interval range of the heating faults is obtained, and the characteristic threshold value for judging the heating faults is obtained by combining a preset color brightness interval.
6. The method as recited in claim 5, further comprising:
performing color gamut conversion on an infrared image area of the identification equipment, and converting a RGB color space into a YUV color space;
gray processing is carried out in a YUV color gamut, brightness information Y of a target area is extracted, and binarization threshold processing is carried out on the brightness information by combining with a characteristic threshold T of a heating defect;
judging whether the target area has a heating fault or not according to the binarization result, and marking a fault position in the target area if the heating fault occurs.
7. The method of claim 6, wherein the RGB color space is converted to a YUV color space according to the following formula:
wherein ,
respectively represent YUV color space,>
respectively represent the color space of RGB.
8. The method of claim 7, wherein binarizing thresholding the brightness information according to the following formula comprises:
wherein y is brightness information, P is a binarization result, namely a quantized value by a binarization threshold method, and T is a characteristic threshold of the heating defect.
9. The method as recited in claim 8, further comprising:
for the visible light image, extracting gradient structural features of a target area by utilizing a gradient operator, and extracting edge texture features of the target area by utilizing an edge detection operator;
obtaining the obvious structural characteristics of the external contour of the target equipment by fusing the gradient and the edge characteristics of the target equipment;
according to the normal working state of the target power transmission and transformation equipment, determining the appearance outline and the connection state of the power transmission and transformation equipment under no fault, and taking the appearance outline and the connection state as template basis for judging whether the equipment is faulty or not;
and judging whether the target equipment has surface faults or not according to comparison between the obvious structural characteristics and the templates, and identifying and marking the faults in the visible light image.
10. The method as recited in claim 9, further comprising:
and correspondingly combining the visible light image and the infrared image into a multispectral image, combining the visible light image and a fault diagnosis result of a target equipment area in the infrared image, determining the fault type and the fault degree of the target power transmission and transformation equipment, and judging the working state of the power transmission and transformation equipment according to the severity degree of different types of faults, wherein the working state of the power transmission and transformation equipment at least comprises health, good, attention and severity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310216335.6A CN116310274A (en) | 2023-02-27 | 2023-02-27 | State evaluation method for power transmission and transformation equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310216335.6A CN116310274A (en) | 2023-02-27 | 2023-02-27 | State evaluation method for power transmission and transformation equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116310274A true CN116310274A (en) | 2023-06-23 |
Family
ID=86793674
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310216335.6A Pending CN116310274A (en) | 2023-02-27 | 2023-02-27 | State evaluation method for power transmission and transformation equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116310274A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117538658A (en) * | 2023-11-16 | 2024-02-09 | 深圳市美信检测技术股份有限公司 | Artificial intelligence fault positioning method and device based on infrared spectrum and thermal imaging |
| CN117783793A (en) * | 2024-02-23 | 2024-03-29 | 泸州老窖股份有限公司 | Fault monitoring method and system for switch cabinet |
| CN118365973A (en) * | 2024-06-20 | 2024-07-19 | 国网湖北省电力有限公司武汉供电公司 | Multi-feature information fusion-based hybrid line state evaluation method and system |
-
2023
- 2023-02-27 CN CN202310216335.6A patent/CN116310274A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117538658A (en) * | 2023-11-16 | 2024-02-09 | 深圳市美信检测技术股份有限公司 | Artificial intelligence fault positioning method and device based on infrared spectrum and thermal imaging |
| CN117783793A (en) * | 2024-02-23 | 2024-03-29 | 泸州老窖股份有限公司 | Fault monitoring method and system for switch cabinet |
| CN117783793B (en) * | 2024-02-23 | 2024-05-07 | 泸州老窖股份有限公司 | Fault monitoring method and system for switch cabinet |
| CN118365973A (en) * | 2024-06-20 | 2024-07-19 | 国网湖北省电力有限公司武汉供电公司 | Multi-feature information fusion-based hybrid line state evaluation method and system |
| CN118365973B (en) * | 2024-06-20 | 2024-08-23 | 国网湖北省电力有限公司武汉供电公司 | Multi-feature information fusion-based hybrid line state evaluation method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112734692B (en) | Defect identification method and device for power transformation equipment | |
| CN110598736B (en) | Power equipment infrared image fault positioning, identifying and predicting method | |
| CN116310274A (en) | State evaluation method for power transmission and transformation equipment | |
| CN111784633B (en) | Insulator defect automatic detection algorithm for electric power inspection video | |
| CN110033431B (en) | Non-contact detection device and detection method for detecting corrosion area on surface of steel bridge | |
| CN107679495B (en) | Detection method for movable engineering vehicles around power transmission line | |
| WO2024000372A1 (en) | Defect detection method and apparatus | |
| CN114494185B (en) | Electrical equipment fault detection method based on RGB-T multi-scale feature fusion | |
| CN112465797A (en) | Intelligent diagnosis method and system for thermal state of cable terminal | |
| CN112508019A (en) | GIS isolation/grounding switch state detection method and system based on image recognition | |
| CN113205039A (en) | Power equipment fault image identification and disaster investigation system and method based on multiple DCNNs | |
| CN115147591A (en) | Transformer equipment infrared image voltage heating type defect diagnosis method and system | |
| CN117423018A (en) | Power equipment detection system and method based on unmanned aerial vehicle acquisition multi-mode source fusion | |
| CN116485802B (en) | Insulator flashover defect detection method, device, equipment and storage medium | |
| CN112241707A (en) | Wind-powered electricity generation field intelligence video identification device | |
| CN114792328A (en) | Infrared thermal imaging image processing and analyzing method | |
| CN103984956A (en) | Method for diagnosing surface pitting fault of blade of wind turbine generator of electric power system based on machine vision image | |
| CN108470141B (en) | Statistical feature and machine learning-based insulator identification method in distribution line | |
| CN115410154A (en) | Method for identifying thermal fault of electrical equipment of wind power engine room | |
| CN113689399B (en) | Remote sensing image processing method and system for power grid identification | |
| Huang et al. | Mango surface defect detection based on HALCON | |
| CN116051539A (en) | Diagnosis method for heating fault of power transformation equipment | |
| CN113284103B (en) | Substation equipment defect online detection method based on space transformation fast R-CNN model | |
| WANG et al. | Visual Tracking Inspection Method of Transmission Line based on Infrared Thermal Imaging. | |
| CN113034465B (en) | Power equipment thermal fault monitoring method, device and medium based on infrared image |
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 |