CN114548446B - Power equipment detection system and method based on artificial intelligence - Google Patents
Power equipment detection system and method based on artificial intelligence Download PDFInfo
- Publication number
- CN114548446B CN114548446B CN202210436257.6A CN202210436257A CN114548446B CN 114548446 B CN114548446 B CN 114548446B CN 202210436257 A CN202210436257 A CN 202210436257A CN 114548446 B CN114548446 B CN 114548446B
- Authority
- CN
- China
- Prior art keywords
- image
- data
- fusion
- visible light
- infrared
- 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.)
- Expired - Fee Related
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 19
- 230000004927 fusion Effects 0.000 claims abstract description 100
- 238000001228 spectrum Methods 0.000 claims abstract description 22
- 238000012544 monitoring process Methods 0.000 claims abstract description 13
- 238000006243 chemical reaction Methods 0.000 claims description 42
- 239000011159 matrix material Substances 0.000 claims description 27
- 230000009466 transformation Effects 0.000 claims description 22
- 238000012545 processing Methods 0.000 claims description 7
- 238000012423 maintenance Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 230000003595 spectral effect Effects 0.000 claims description 3
- 238000003331 infrared imaging Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 4
- 230000001131 transforming effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000006903 response to temperature Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000001931 thermography Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/251—Fusion techniques of input or preprocessed data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Evolutionary Biology (AREA)
- Tourism & Hospitality (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Strategic Management (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Image Analysis (AREA)
Abstract
The application discloses an electric power equipment detection system and method based on artificial intelligence, mainly relates to the technical field of equipment detection, and is used for solving the technical problem that the existing infrared image detection operation obstacle has large errors. The method comprises the following steps: the infrared early warning module is used for obtaining spectrum data corresponding to the infrared image; determining whether the power equipment corresponding to the infrared image has operation faults or not; the image matching module is used for importing the visible light image and the infrared image into an SIFT algorithm to complete matching of the power equipment, the visible light image and the infrared image; the image fusion module is used for determining the dominant frequency weight assignment so as to obtain fusion dominant frequency data of the fusion image; and acquiring fusion secondary frequency data of the fusion image to acquire the fusion image, and sending the fusion image to a personnel monitoring end. According to the method, whether the equipment accident occurs or not is rapidly detected, and the technical problem that the fault point is inaccurately positioned due to excessive dependence on infrared imaging is solved.
Description
Technical Field
The application relates to the technical field of equipment detection, in particular to an electric power equipment detection system and method based on artificial intelligence.
Background
The power system mainly comprises two categories of power generation equipment and power supply equipment, wherein the power generation equipment mainly comprises a power station boiler, a steam turbine, a gas turbine, a water turbine, a generator, a transformer and the like, and the power supply equipment mainly comprises power transmission lines, transformers, contactors and the like with various voltage grades.
The existing method for detecting whether the power equipment normally operates mainly comprises the following steps: whether the equipment operation fault occurs to the power equipment is judged by detecting a heat temperature distribution characteristic diagram of the power equipment during operation. For example, the infrared detection device is used to generate an infrared thermal imaging map to analyze the state of the device and the location of the fault.
However, the single method of detecting the fault point by the infrared detection device does not provide a very accurate fault point location, which is only a special response to temperature, and the detection mode of detecting the fault point by the temperature is too simple to ignore additional interference caused by external factors such as environment.
Disclosure of Invention
In view of the above-mentioned deficiencies of the prior art, the present invention provides a power equipment detection system and method based on artificial intelligence, so as to solve the above-mentioned technical problems.
In a first aspect, the application provides an electrical device detection system based on artificial intelligence. The system comprises: the infrared early warning module is used for acquiring an infrared image uploaded by the infrared acquisition equipment and carrying out transform domain processing on the infrared image so as to obtain frequency spectrum data corresponding to the infrared image; determining whether the power equipment corresponding to the infrared image has an operation fault or not based on the fluctuation peak value of the frequency spectrum data so as to generate a fault instruction to be sent to a maintenance terminal or generate a picture fusion instruction; the image matching module is used for acquiring a visible light image uploaded by the image acquisition equipment based on the image fusion instruction; importing the visible light image and the infrared image into an SIFT algorithm, and extracting the regional image features; matching of the power equipment, the visible light image and the infrared image is completed through regional image feature matching; the image fusion module is used for performing two-dimensional DCT conversion on the visible light image and the infrared image corresponding to the visible light image, determining the dominant frequency weight assignment corresponding to the visible light image and the infrared image based on the DCT conversion matrix after conversion, and further acquiring fusion dominant frequency data of the fusion image; and obtaining fusion secondary frequency data of the fusion image by taking the maximum absolute value, further carrying out inverse DCT (discrete cosine transformation) conversion on the fusion primary frequency data and the fusion secondary frequency data to obtain a fusion image, and sending the fusion image to a personnel monitoring end.
Further, the infrared early warning module comprises a frequency domain transformation unit and a frequency domain comparison unit; the frequency domain transformation unit is used for carrying out Fourier transformation on the infrared image so as to obtain corresponding frequency spectrum data; the frequency domain comparison unit is used for generating a data curve based on continuous signal values in the frequency spectrum data; fitting the data curve with a data curve generated at the last time point, and determining that the corresponding power equipment has an operation fault when the fitting degree is lower than a preset threshold value; otherwise, determining that the corresponding power equipment operates normally.
Further, the image fusion module comprises a dominant frequency fusion unit; the main frequency fusion unit is used for performing two-dimensional DCT conversion on the visible light image and the infrared image corresponding to the visible light image to obtain a first DCT conversion matrix and a second DCT conversion matrix; further obtaining secondary frequency data and main frequency data; calculating visible light secondary frequency energy and infrared secondary frequency energy based on respective main frequency data of the visible light image and the infrared image; and determining the corresponding dominant frequency weight assignment of the visible light image and the infrared image based on the ratio of the first secondary frequency energy to the second secondary frequency energy, and further acquiring fusion dominant frequency data of the fusion image.
Further, the system also comprises a matching checking module; the matching checking module is used for acquiring a first preset keying image corresponding to the visible light image and acquiring a second preset keying image corresponding to the infrared image; further acquiring first frequency domain data and second frequency domain data, determining whether the first frequency domain data and first standard data prestored in the power equipment accord with each other, and determining whether the second frequency domain data and second standard data prestored in the power equipment accord with each other; when the two are consistent, the verification is determined to be successful; and when any one of the data is inconsistent, generating matching error reporting information and sending the matching error reporting information to the personnel monitoring end.
In a second aspect, the present application provides an artificial intelligence-based power device detection method, including: acquiring an infrared image uploaded by infrared acquisition equipment, and performing transform domain processing on the infrared image to acquire frequency spectrum data corresponding to the infrared image; determining whether the power equipment corresponding to the infrared image has an operation fault or not based on the fluctuation peak value of the frequency spectrum data so as to generate a fault instruction to be sent to a maintenance terminal or generate a picture fusion instruction; acquiring a visible light image uploaded by image acquisition equipment based on the image fusion instruction; importing the visible light image and the infrared image into an SIFT algorithm, and extracting the regional image features; matching of the power equipment, the visible light image and the infrared image is completed through regional image feature matching; performing two-dimensional DCT conversion on the visible light image and the infrared image corresponding to the visible light image, determining the dominant frequency weight assignment corresponding to the visible light image and the infrared image based on the DCT conversion matrix after conversion, and further acquiring fusion dominant frequency data of the fusion image; and obtaining fusion secondary frequency data of the fusion image by taking the maximum absolute value, further carrying out inverse DCT (discrete cosine transformation) conversion on the fusion primary frequency data and the fusion secondary frequency data to obtain a fusion image, and sending the fusion image to a personnel monitoring end.
Further, determining whether the power equipment corresponding to the infrared image has an operation fault based on the fluctuation peak of the spectrum data specifically includes: generating a data curve based on the continuous signal values in the spectral data; fitting the data curve with a data curve generated at the last time point, and determining that the corresponding power equipment has an operation fault when the fitting degree is lower than a preset threshold value; otherwise, determining that the corresponding power equipment operates normally.
Further, the method is used for performing two-dimensional DCT transformation on the visible light image and the infrared image corresponding thereto, determining a dominant frequency weight assignment corresponding to the visible light image and the infrared image based on the DCT transformation matrix after the transformation, and further acquiring fusion dominant frequency data of the fusion image, and specifically includes: performing two-dimensional DCT conversion on the visible light image and the infrared image corresponding to the visible light image to obtain a first DCT conversion matrix and a second DCT conversion matrix; further obtaining secondary frequency data and main frequency data; calculating visible light secondary frequency energy and infrared secondary frequency energy based on respective main frequency data of the visible light image and the infrared image; and determining the corresponding dominant frequency weight assignment of the visible light image and the infrared image based on the ratio of the first secondary frequency energy to the second secondary frequency energy, and further acquiring fusion dominant frequency data of the fusion image.
Further, after the matching of the power device, the visible light image and the infrared image is completed through the region image feature matching, the method further includes: acquiring a first preset keying image corresponding to the visible light image and acquiring a second preset keying image corresponding to the infrared image; further acquiring first frequency domain data and second frequency domain data, determining whether the first frequency domain data and first standard data prestored in the power equipment accord with each other, and determining whether the second frequency domain data and second standard data prestored in the power equipment accord with each other; when the two are consistent, the verification is determined to be successful; and when any one of the parameters is not in accordance with the preset parameter, generating matching error reporting information and sending the matching error reporting information to the personnel monitoring terminal.
As can be appreciated by those skilled in the art, the present invention has at least the following beneficial effects: through infrared early warning module, turn into the frequency domain data of being convenient for handle with space scale data (infrared image), because power equipment is in normal operating process, the infrared image in short-term can not appear great change, consequently can be through detecting power equipment in the change of frequency domain data in short-term, realize whether the equipment accident appears in the short-term. Compared with the prior technical scheme of detecting whether equipment accidents occur or not through picture comparison, the method and the device greatly reduce the detection time. The image matching module is used for realizing the matching of the infrared image and the visible light image; through the image fusion module, the fusion of temperature detection and environment detection is realized, and the technical problem of inaccurate fault point positioning caused by excessive dependence on infrared imaging is avoided.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a schematic diagram of an internal structure of an electrical equipment detection system based on artificial intelligence according to an embodiment of the present application.
Fig. 2 is a flowchart of an electrical device detection method based on artificial intelligence according to an embodiment of the present disclosure.
Detailed Description
It should be understood by those skilled in the art that the embodiments described below are only preferred embodiments of the present disclosure, and do not mean that the present disclosure can be implemented only by the preferred embodiments, which are merely intended to explain the technical principles of the present disclosure and not to limit the scope of the present disclosure. All other embodiments that can be derived by one of ordinary skill in the art from the preferred embodiments provided by the disclosure without undue experimentation will still fall within the scope of the disclosure.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
The technical solutions proposed in the embodiments of the present application are described in detail below with reference to the accompanying drawings.
Fig. 1 is a power equipment detection system based on artificial intelligence according to an embodiment of the present application. As shown in fig. 1, the detection system provided in the embodiment of the present application mainly includes: the system comprises an infrared early warning module 110, an image matching module 120 and an image fusion module 130.
The infrared early warning module 110 is any feasible device or apparatus capable of acquiring an infrared image and performing transform domain conversion, and is mainly used for acquiring an infrared image uploaded by an infrared acquisition device and performing transform domain processing on the infrared image to acquire frequency spectrum data corresponding to the infrared image; and determining whether the power equipment corresponding to the infrared image has an operation fault or not based on the fluctuation peak value of the frequency spectrum data so as to generate a fault instruction and send the fault instruction to the maintenance terminal or generate a picture fusion instruction.
The transform domain processing is a processing method for converting the infrared image into a frequency domain value, and for example, the conversion from the spatial domain to the frequency domain may be realized by fourier transform or wavelet transform.
Illustratively, the infrared early warning module 110 includes a frequency domain transforming unit 111 and a frequency domain comparing unit 112; it should be noted that the frequency domain transforming unit 111 is any feasible device or apparatus capable of transforming the spatial domain into the frequency domain, and is mainly used for performing fourier transform on the infrared image to obtain corresponding spectrum data. The frequency domain comparison unit 112 is any feasible device or apparatus capable of comparing values and fitting curves, and is mainly used for generating a data curve based on continuous signal values in the spectrum data; fitting the data curve with a data curve generated at the last time point, and determining that the corresponding power equipment has an operation fault when the fitting degree is lower than a preset threshold value; otherwise, determining that the corresponding power equipment operates normally.
It should be noted that the preset threshold may be any feasible value, and those skilled in the art may determine the specific value of the preset threshold according to actual requirements.
The image matching module 120 is any feasible device or apparatus capable of performing image matching, and is mainly used for acquiring a visible light image uploaded by an image acquisition device based on an image fusion instruction; importing the visible light image and the infrared image into an SIFT algorithm, and extracting the regional image features; the sift (scale Invariant Feature transform) algorithm is a scale Invariant Feature transform matching algorithm. And matching the power equipment, the visible light image and the infrared image through the regional image feature matching.
The image fusion module 130 is any feasible device or apparatus capable of fusing an infrared image and a visible light image, and is configured to perform two-dimensional DCT transformation on the visible light image and the infrared image corresponding to the visible light image, where DCT (discrete Cosine transform) refers to discrete Cosine transform. Determining the corresponding dominant frequency weight assignment of the visible light image and the infrared image based on the converted DCT matrix, and further acquiring fusion dominant frequency data of the fusion image; and obtaining fusion secondary frequency data of the fusion image by taking the maximum absolute value, further carrying out inverse DCT (discrete cosine transformation) conversion on the fusion primary frequency data and the fusion secondary frequency data to obtain a fusion image, and sending the fusion image to a personnel monitoring end.
It should be noted that, based on the characteristic of DCT transformation, data aggregation occurs in data with the same frequency, and therefore, the main frequency data in this application is the data on the upper left side of the diagonal line of the DCT transformation matrix; the sub-frequency data is the data on the lower right side of the diagonal of the DCT transform matrix.
It should be further noted that the DCT transformation and the inverse DCT transformation can be implemented by the existing methods or techniques, which are not limited in this application.
Illustratively, the image fusion module 130 includes a dominant frequency fusion unit 131; the dominant frequency fusion unit 131 is configured to perform two-dimensional DCT transformation on the visible light image and the infrared image corresponding to the visible light image to obtain a first DCT transformation matrix and a second DCT transformation matrix; further obtaining secondary frequency data and main frequency data; calculating visible light secondary frequency energy and infrared secondary frequency energy based on respective main frequency data of the visible light image and the infrared image; and determining the corresponding dominant frequency weight assignment of the visible light image and the infrared image based on the ratio of the first secondary frequency energy to the second secondary frequency energy, and further acquiring fusion dominant frequency data of the fusion image.
It should be noted that the formula for calculating the visible light sub-frequency energy and the infrared sub-frequency energy is as follows:
wherein n is the preset image segmentation quantity, and D is the dominant frequencyAnd (4) data. n may be any feasible data. In addition, the present application also has a ratio-weight assignment database in which a direct correspondence between the ratio and the weight assignment is stored, and the ratio-weight assignment database can be obtained by a person skilled in the art through many experiments.
In addition, the present application may also verify whether there is a matching error in the image matching module 120.
Illustratively, the system further includes a match check module 140; the matching check module 140 is any optional module capable of performing matting and data, and is configured to obtain a first preset matting image corresponding to a visible light image and obtain a second preset matting image corresponding to an infrared image; further acquiring first frequency domain data and second frequency domain data, determining whether the first frequency domain data and first standard data prestored in the power equipment accord with each other, and determining whether the second frequency domain data and second standard data prestored in the power equipment accord with each other; when the two are consistent, the verification is determined to be successful; and when any one of the parameters is not in accordance with the preset parameter, generating matching error reporting information and sending the matching error reporting information to the personnel monitoring terminal.
In addition, an embodiment of the present application further provides a power device detection method based on artificial intelligence, and as shown in fig. 2, the detection method provided in the embodiment of the present application mainly includes the following steps:
Wherein, based on the fluctuation peak value of the spectrum data, it is determined whether the power equipment corresponding to the infrared image has an operation fault, which may specifically be: generating a data curve based on the continuous signal values in the spectral data; fitting the data curve with a data curve generated at the last time point, and determining that the corresponding power equipment has an operation fault when the fitting degree is lower than a preset threshold value; otherwise, determining that the corresponding power equipment runs normally.
The system comprises a visible light image and an infrared image corresponding to the visible light image, wherein the visible light image and the infrared image corresponding to the visible light image are subjected to two-dimensional DCT conversion, and the dominant frequency weight assignment corresponding to the visible light image and the infrared image is determined based on the DCT conversion matrix after conversion, so that fusion dominant frequency data of the fusion image are obtained, and the method can specifically comprise the following steps: performing two-dimensional DCT conversion on the visible light image and the infrared image corresponding to the visible light image to obtain a first DCT conversion matrix and a second DCT conversion matrix; further obtaining secondary frequency data and main frequency data; calculating visible light secondary frequency energy and infrared secondary frequency energy based on respective main frequency data of the visible light image and the infrared image; and determining the corresponding dominant frequency weight assignment of the visible light image and the infrared image based on the ratio of the first secondary frequency energy to the second secondary frequency energy, and further acquiring fusion dominant frequency data of the fusion image.
This application is through regional image feature matching, after accomplishing the matching of power equipment, visible light image and infrared image, can also: acquiring a first preset keying image corresponding to the visible light image and acquiring a second preset keying image corresponding to the infrared image; further acquiring first frequency domain data and second frequency domain data, determining whether the first frequency domain data and first standard data prestored in the power equipment accord with each other, and determining whether the second frequency domain data and second standard data prestored in the power equipment accord with each other; when the two are consistent, the verification is determined to be successful; and when any one of the parameters is not in accordance with the preset parameter, generating matching error reporting information and sending the matching error reporting information to the personnel monitoring terminal.
So far, the technical solutions of the present disclosure have been described in connection with the foregoing embodiments, but it is easily understood by those skilled in the art that the scope of the present disclosure is not limited to only these specific embodiments. The technical solutions in the above embodiments can be split and combined, and equivalent changes or substitutions can be made on related technical features by those skilled in the art without departing from the technical principles of the present disclosure, and any changes, equivalents, improvements, etc. made within the technical concept and/or technical principles of the present disclosure will fall within the protection scope of the present disclosure.
Claims (8)
1. An artificial intelligence based power equipment detection system, the system comprising:
the infrared early warning module is used for acquiring an infrared image uploaded by infrared acquisition equipment and carrying out transform domain processing on the infrared image so as to obtain frequency spectrum data corresponding to the infrared image; determining whether the power equipment corresponding to the infrared image has an operation fault or not based on the fluctuation peak value of the frequency spectrum data so as to generate a fault instruction to be sent to a maintenance terminal or generate a picture fusion instruction;
the image matching module is used for acquiring a visible light image uploaded by the image acquisition equipment based on the image fusion instruction; importing the visible light image and the infrared image into an SIFT algorithm, and extracting the image characteristics of the region; matching of the power equipment, the visible light image and the infrared image is completed through regional image feature matching;
the image fusion module is used for performing two-dimensional DCT conversion on the visible light image and the infrared image corresponding to the visible light image, determining the dominant frequency weight assignment corresponding to the visible light image and the infrared image based on the DCT conversion matrix after conversion, and further acquiring fusion dominant frequency data of the fusion image; acquiring first secondary frequency data in a DCT (discrete cosine transform) matrix corresponding to the visible light image and second secondary frequency data in a DCT matrix corresponding to the infrared image; determining the data with the maximum absolute value in the first secondary frequency data and the second secondary frequency data as the fusion secondary frequency data of the fusion image, further performing inverse DCT conversion on the fusion primary frequency data and the fusion secondary frequency data to obtain a fusion image, and sending the fusion image to a personnel monitoring end.
2. The artificial intelligence based power equipment detection system according to claim 1, wherein the infrared early warning module comprises a frequency domain transformation unit and a frequency domain comparison unit;
the frequency domain transformation unit is used for carrying out Fourier transformation on the infrared image so as to obtain corresponding frequency spectrum data;
the frequency domain comparison unit is used for generating a data curve based on continuous signal values in the frequency spectrum data; fitting the data curve with a data curve generated at the last time point, and determining that the corresponding power equipment has an operation fault when the fitting degree is lower than a preset threshold value; otherwise, determining that the corresponding power equipment operates normally.
3. The artificial intelligence based power device detection system of claim 1, wherein the image fusion module includes a dominant frequency fusion unit;
the main frequency fusion unit is used for performing two-dimensional DCT conversion on the visible light image and the infrared image corresponding to the visible light image to obtain a first DCT conversion matrix and a second DCT conversion matrix; further obtaining secondary frequency data and main frequency data; calculating visible light secondary frequency energy and infrared secondary frequency energy based on respective main frequency data of the visible light image and the infrared image; and determining the corresponding dominant frequency weight assignment of the visible light image and the infrared image based on the ratio of the first secondary frequency energy to the second secondary frequency energy, and further acquiring fusion dominant frequency data of the fusion image.
4. The artificial intelligence based power device detection system of claim 1, wherein the system further comprises a match check module;
the matching checking module is used for acquiring a first preset keying image corresponding to the visible light image and acquiring a second preset keying image corresponding to the infrared image; further acquiring first frequency domain data and second frequency domain data, determining whether the first frequency domain data and first standard data prestored in the power equipment accord with each other, and determining whether the second frequency domain data and second standard data prestored in the power equipment accord with each other; when the two are consistent, the verification is determined to be successful; and when any one of the parameters is not in accordance with the preset parameter, generating matching error reporting information and sending the matching error reporting information to the personnel monitoring terminal.
5. An artificial intelligence based power equipment detection method, characterized in that the method comprises:
acquiring an infrared image uploaded by infrared acquisition equipment, and performing transform domain processing on the infrared image to acquire frequency spectrum data corresponding to the infrared image; determining whether the power equipment corresponding to the infrared image has an operation fault or not based on the fluctuation peak value of the frequency spectrum data so as to generate a fault instruction and send the fault instruction to a maintenance terminal or generate a picture fusion instruction;
acquiring a visible light image uploaded by image acquisition equipment based on the image fusion instruction; importing the visible light image and the infrared image into an SIFT algorithm, and extracting the regional image features; matching of the power equipment, the visible light image and the infrared image is completed through regional image feature matching;
performing two-dimensional DCT conversion on the visible light image and the infrared image corresponding to the visible light image, determining the dominant frequency weight assignment corresponding to the visible light image and the infrared image based on the DCT conversion matrix after conversion, and further acquiring fusion dominant frequency data of the fusion image; acquiring first secondary frequency data in a DCT (discrete cosine transform) matrix corresponding to the visible light image and second secondary frequency data in a DCT matrix corresponding to the infrared image; determining the data with the maximum absolute value in the first secondary frequency data and the second secondary frequency data as the fusion secondary frequency data of the fusion image, performing inverse DCT conversion on the fusion primary frequency data and the fusion secondary frequency data to obtain a fusion image, and sending the fusion image to a personnel monitoring end.
6. The artificial intelligence-based power equipment detection method according to claim 5, wherein determining whether an operation fault occurs in power equipment corresponding to an infrared image based on a fluctuation peak of the spectrum data specifically includes:
generating a data curve based on the continuous signal values in the spectral data; fitting the data curve with a data curve generated at the last time point, and determining that the corresponding power equipment has an operation fault when the fitting degree is lower than a preset threshold value; otherwise, determining that the corresponding power equipment operates normally.
7. The artificial intelligence-based power equipment detection method according to claim 5, wherein the method is used for performing two-dimensional DCT conversion on the visible light image and the infrared image corresponding to the visible light image, determining a dominant frequency weight assignment corresponding to the visible light image and the infrared image based on the DCT transformation matrix after the conversion, and further acquiring fusion dominant frequency data of the fusion image, and specifically comprises the steps of:
performing two-dimensional DCT conversion on the visible light image and the infrared image corresponding to the visible light image to obtain a first DCT conversion matrix and a second DCT conversion matrix; further obtaining secondary frequency data and main frequency data; calculating visible light secondary frequency energy and infrared secondary frequency energy based on respective main frequency data of the visible light image and the infrared image; and determining the corresponding dominant frequency weight assignment of the visible light image and the infrared image based on the ratio of the first secondary frequency energy to the second secondary frequency energy, and further acquiring fusion dominant frequency data of the fusion image.
8. The artificial intelligence based power device detection method of claim 5, wherein after completing matching of power devices, visible light images and infrared images by region image feature matching, the method further comprises:
acquiring a first preset keying image corresponding to the visible light image and acquiring a second preset keying image corresponding to the infrared image; further acquiring first frequency domain data and second frequency domain data, determining whether the first frequency domain data and first standard data prestored in the power equipment accord with each other, and determining whether the second frequency domain data and second standard data prestored in the power equipment accord with each other; when the two are consistent, the verification is determined to be successful; and when any one of the parameters is not in accordance with the preset parameter, generating matching error reporting information and sending the matching error reporting information to the personnel monitoring terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210436257.6A CN114548446B (en) | 2022-04-25 | 2022-04-25 | Power equipment detection system and method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210436257.6A CN114548446B (en) | 2022-04-25 | 2022-04-25 | Power equipment detection system and method based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114548446A CN114548446A (en) | 2022-05-27 |
| CN114548446B true CN114548446B (en) | 2022-08-02 |
Family
ID=81667192
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210436257.6A Expired - Fee Related CN114548446B (en) | 2022-04-25 | 2022-04-25 | Power equipment detection system and method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114548446B (en) |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103413139B (en) * | 2013-06-28 | 2015-05-20 | 广东电网公司电力科学研究院 | Electric equipment abnormal heating detection method based on infrared inspection video data of power line inspection |
| WO2018014326A1 (en) * | 2016-07-22 | 2018-01-25 | 绿仕科技控股有限公司 | Security system and method |
| CN109345788A (en) * | 2018-09-26 | 2019-02-15 | 国网安徽省电力有限公司铜陵市义安区供电公司 | A kind of monitoring early-warning system of view-based access control model feature |
| CN110660065B (en) * | 2019-09-29 | 2023-10-20 | 云南电网有限责任公司电力科学研究院 | Infrared fault detection and identification algorithm |
| CN111429391B (en) * | 2020-03-23 | 2023-04-07 | 西安科技大学 | Infrared and visible light image fusion method, fusion system and application |
| CN111612736A (en) * | 2020-04-08 | 2020-09-01 | 广东电网有限责任公司 | Power equipment fault detection method, computer and computer program |
-
2022
- 2022-04-25 CN CN202210436257.6A patent/CN114548446B/en not_active Expired - Fee Related
Non-Patent Citations (1)
| Title |
|---|
| 基于离散平稳小波变换的图像融合方法;任重等;《传感器与微系统》;20200723(第08期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114548446A (en) | 2022-05-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105425123B (en) | A kind of ultraviolet imagery and the method and system of infrared imaging cooperation detection electrical equipment fault | |
| CN110567964B (en) | Method and device for detecting defects of power transformation equipment and storage medium | |
| CN114241730B (en) | Substation equipment monitoring and early warning system based on data acquisition | |
| CN101339212A (en) | Non-contact type high voltage phasing tester | |
| CN115563873A (en) | Digital twin simulation system and method of power network | |
| CN111459061A (en) | Electric power safety monitoring system based on 5G network | |
| CN109357766A (en) | Defect of transformer equipment detection method and defect detecting system based on infrared measurement of temperature | |
| Jiang et al. | Research on infrared image recognition method of power equipment based on deep learning | |
| CN112613339A (en) | Automatic identification and examination method and device for electrical drawings | |
| CN114548446B (en) | Power equipment detection system and method based on artificial intelligence | |
| CN114782423B (en) | Forming quality detection system and method for low-voltage coil of dry-type transformer | |
| CN117110798A (en) | Fault detection method and system for intelligent power distribution network | |
| CN113532753B (en) | Wind farm gear box oil leakage detection method based on machine vision | |
| CN113746132B (en) | Photovoltaic power station based on cloud edge cooperation and control method thereof | |
| CN111735545B (en) | Transformer substation infrared thermal imaging online monitoring method and system | |
| WO2024119983A1 (en) | Anomality detection method and apparatus for cable terminal of rail vehicle | |
| CN112444758B (en) | Intelligent power distribution network line fault diagnosis and classification evaluation method | |
| CN117498262A (en) | High-voltage direct-current electronic load switch protection circuit | |
| CN107453912A (en) | A kind of power remote monitoring system device | |
| Wang et al. | Application of infrared thermography and extension recognize method to intelligent fault diagnosis of distribution panels | |
| CN111583594B (en) | Distribution box early warning system and early warning method | |
| Tang et al. | Fault diagnosis of the external insulation infrared images based on Mask Region convolutional neural network and perceptual hash joint algorithm | |
| CN114421465A (en) | Power grid parameter identification and verification method and device based on element topology and storage medium | |
| CN114283330A (en) | Online inspection identification method and system based on multi-source data | |
| Li et al. | Research on Voltage Inductive Heated Defect Detection Technology Based on Temperature Width Intelligent Adjustment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20220802 |