Fault diagnosis method and device for power transformation equipment and storage medium

Abstract

The invention discloses a fault diagnosis method and device for power transformation equipment and a storage medium, and the method comprises the steps: recognizing a basic contour image of the power transformation equipment, determining the type of the equipment, and determining a corresponding collection region and the type of the collection region. Performing image acquisition on the acquisition area by using first acquisition equipment to generate a first analysis image; and according to the type of the collection area, determining a second collection device required outside the first collection device, carrying out image collection, and generating a second analysis image. And carrying out image fusion on the first analysis image and the second analysis image to obtain a fused image. And determining the fault type of the acquisition area of the power transformation equipment by analyzing the fused image. According to the invention, the cost and complexity of image acquisition can be reduced, the one-sidedness of analysis is avoided, and accurate fault diagnosis is realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of fault diagnosis of substation equipment, and in particular relates to a fault diagnosis method, device and storage medium for substation equipment. Background Art

[0002] Fault diagnosis of substation equipment is part of substation inspection. When diagnosing substation equipment faults, the substation equipment is generally powered on. In order to avoid manual participation in fault diagnosis of substation equipment, current fault diagnosis adopts the method of fusing infrared images and visible light images to intelligently identify fused images, thereby meeting the needs of fault diagnosis of substation equipment. However, not all substation equipment failures are accompanied by temperature changes. In many cases, the acquisition of infrared images is not a necessary step, which increases the cost and complexity of image acquisition. In addition, only by fusing infrared images and visible light images to diagnose substation equipment failures, faults that do not cause temperature changes are ignored, and the analysis angle is one-sided, which limits the comprehensiveness and accuracy of the diagnosis results. Summary of the invention

[0003] The embodiments of the present invention provide a fault diagnosis method, device and storage medium for substation equipment, which reduce the image acquisition cost, avoid the one-sidedness of the analysis angle, and improve the accuracy and comprehensiveness of fault diagnosis, thereby effectively ensuring the safety and stability of the substation equipment.

[0004] An embodiment of the present invention provides a fault diagnosis method for a substation, including: identifying a basic contour image of the substation to obtain the type of the substation.

[0005] According to the type of substation equipment, determine the collection area of ​​the substation equipment and the type of the collection area.

[0006] The first acquisition device is used to acquire images of the acquisition area to obtain a first analysis image, wherein the first acquisition device is a visible light camera.

[0007] According to the type of the acquisition area, a second acquisition device required for the acquisition area in addition to the visible light camera is determined, wherein the second acquisition device includes any one of the following or a combination thereof: an infrared imager, a medium-wave infrared instrument, and an ultraviolet instrument.

[0008] The image of the acquisition area is acquired based on the second acquisition device to obtain a second analysis image.

[0009] The first analysis image and the second analysis image are fused to obtain a fused image.

[0010] The fault type of the substation equipment acquisition area is determined according to the fused image.

[0011] Furthermore, if it is determined based on the type of the acquisition area that no other acquisition equipment is required except the visible light camera, the fault type of the substation equipment is determined based on the first analysis image.

[0012] Furthermore, the step of determining the collection area and the type of the collection area of ​​the substation equipment according to the type of the substation equipment includes:

[0013] According to the type of substation equipment, the model surface area of ​​the three-dimensional model of the substation equipment of this type and the monitoring area of ​​the monitoring equipment are obtained from the database.

[0014] The monitored area is compared with the model surface area to calculate the area monitored by each monitoring device.

[0015] According to the area monitored by each monitoring device, the surface of the substation equipment is divided into multiple areas to obtain various collection areas of the substation equipment.

[0016] For each collection area, a preset fault manifestation corresponding to the collection area is extracted from the database.

[0017] If the preset fault of the collection area is manifested as abnormal temperature information and normal gas information, the type of the collection area is determined to be a temperature information collection area.

[0018] If the preset fault of the collection area is manifested as abnormal gas information, the type of the collection area is determined to be a gas information collection area.

[0019] If the preset fault of the collection area is manifested as abnormal discharge information, the type of the collection area is determined to be a discharge information collection area.

[0020] If the preset fault of the collection area is manifested as abnormal apparent information, the type of the collection area is determined to be an apparent information collection area.

[0021] Further, according to the type of the acquisition area, determining a second acquisition device required for the acquisition area in addition to the visible light camera includes:

[0022] If the type of the collection area is a temperature information collection area, the second collection device is an infrared thermal imager.

[0023] If the type of the collection area is a gas information collection area, the second collection device is a medium-wave infrared instrument.

[0024] If the type of the collection area is a discharge information collection area, the second collection device is an ultraviolet instrument.

[0025] Further, fusing the first analysis image and the second analysis image to obtain a fused image includes:

[0026] The first analysis image and the second analysis image are fused using the Gram-Schmidt method to obtain a fused image.

[0027] Wherein, when the second acquisition device is an infrared thermal imager, the second analysis image is an infrared image, and the fused image is a temperature fused image.

[0028] When the second acquisition device is a medium-wave infrared instrument, the second analysis image is a medium-wave infrared image, and the fused image is a gas fusion image.

[0029] When the second acquisition device is an ultraviolet instrument, the second analysis image is an ultraviolet image, and the fused image is a discharge fusion image.

[0030] Further, determining the fault type of the substation equipment according to the fused image includes:

[0031] When the fused image is a temperature fusion image, obtain the total number of first pixels and the grayscale value of each first pixel of the temperature fusion image of the substation. Traverse each first pixel, and if its grayscale value is not within the standard temperature grayscale range, mark it as a temperature abnormality pixel. According to the number of temperature abnormality pixels and the total number of first pixels, calculate the temperature abnormality pixel rate. If the temperature abnormality pixel rate is greater than or equal to the standard temperature pixel rate, it is determined that there is a temperature abnormality in the acquisition area of ​​the substation.

[0032] When the fused image is a gas fusion image, the total number of second pixels of the gas fusion image of the substation and the grayscale value of each second pixel are obtained. Each second pixel is traversed, and if its grayscale value is not within the standard gas grayscale interval, it is marked as a gas abnormality pixel. Adjacent gas abnormality pixels are classified to obtain a number of abnormal pixel blocks. The number of pixels of each abnormal pixel block is matched with the gas model in the database to obtain a first matching degree. If the similarity of the first matching degree is greater than or equal to the standard matching degree, the abnormal pixel block is marked as a gas abnormality pixel block, and it is determined that there is a gas abnormality in the acquisition area of ​​the substation. If the similarity of the first matching degree is lower than the standard matching degree, the abnormal pixel block is marked as a non-gas abnormality pixel block, and it is checked whether the second pixel in the non-gas abnormality pixel block is a temperature abnormality pixel. The temperature abnormality pixel rate is calculated, and if it is greater than or equal to the standard temperature pixel rate, it is determined that there is a temperature abnormality in the acquisition area of ​​the substation.

[0033] When the fused image is a discharge fusion image, the total number of third pixels and the grayscale value of each third pixel of the discharge fusion image of the substation equipment are obtained. Each third pixel is traversed, and if its grayscale value is not within the standard discharge grayscale interval, it is marked as a discharge abnormality pixel. Adjacent discharge abnormality pixels are classified to obtain a number of abnormal pixel blocks, and the number of pixels of each abnormal pixel block is matched with the arc model in the database to obtain a second matching degree. If the similarity of the second matching degree is greater than or equal to the standard matching degree, the abnormal pixel block is marked as a discharge abnormality pixel block, and it is determined that there is a discharge abnormality in the acquisition area of ​​the substation equipment.

[0034] Further, determining the fault type of the substation equipment collection area according to the first analysis image includes:

[0035] The feature information of the first analysis image of the substation equipment is obtained, and similarity calculation is performed with the damaged appearance image in the database.

[0036] If the similarity between the first analysis image and the damaged apparent image is greater than or equal to the standard similarity, it is determined that there is an apparent abnormality in the collection area of ​​the substation equipment.

[0037] Further, after determining the fault type of the substation equipment acquisition area according to the fused image, the method further includes:

[0038] If the fault type in the substation equipment collection area is an apparent abnormal fault, the collection area is marked as a potential hazard area.

[0039] If the fault type in the substation equipment collection area is one of temperature abnormality, gas abnormality or discharge abnormality, check whether the collection area also has an apparent abnormal fault. If so, mark the collection area as a direct fault area. If not, mark the collection area as an internal fault area.

[0040] Based on the above method embodiment, the present invention provides a corresponding device embodiment.

[0041] An embodiment of the present invention provides a fault diagnosis device for substation equipment, including: a substation equipment classification module, a collection area determination module, a collection equipment setting module, an image collection and fusion module and a fault type determination module.

[0042] The substation equipment classification module is used to identify the basic outline image of the substation equipment and obtain the type of the substation equipment.

[0043] The collection area determination module is used to determine the collection area of ​​the substation equipment and the type of the collection area according to the type of the substation equipment.

[0044] The acquisition device setting module is used to determine the second acquisition device required for the acquisition area in addition to the visible light camera according to the type of the acquisition area. The second acquisition device includes any one or a combination of the following: infrared imager, medium-wave infrared instrument and ultraviolet instrument.

[0045] The image acquisition and fusion module is used to acquire an image of the acquisition area through a first acquisition device to obtain a first analysis image. The first acquisition device is a visible light camera. The image of the acquisition area is acquired based on a second acquisition device to obtain a second analysis image. The first analysis image and the second analysis image are image-fused to obtain a fused image.

[0046] The fault type determination module is used to determine the fault type of the substation equipment acquisition area according to the fused image.

[0047] Based on the above method item embodiments, the present invention provides a corresponding storage medium item embodiment.

[0048] An embodiment of the present invention provides a storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for diagnosing faults of a substation equipment described in any one of the above method embodiments can be implemented.

[0049] Compared with the prior art, the present invention has the following beneficial effects:

[0050] The embodiment of the present invention provides a fault diagnosis method, device and storage medium for substation equipment, which determines the type of equipment by identifying the basic contour image of the substation equipment, and then determines the acquisition area and its type. A visible light camera is used to obtain a first analysis image, and a second acquisition device is selected according to the area type to obtain a second analysis image. The two analysis images are fused, and the fault type of the acquisition area of ​​the substation equipment is determined according to the fused image. Compared with the method of diagnosing substation equipment faults by fusing infrared and visible light images in the prior art, the present invention not only considers faults caused by temperature changes, but also can identify fault types that are not accompanied by temperature changes. Through the flexible selection of multiple acquisition devices and image fusion, the accuracy of substation equipment fault diagnosis is improved, the cost and complexity of image acquisition are reduced, the one-sidedness of the analysis angle is avoided, and the comprehensiveness and reliability of the diagnosis results are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 The present invention is a flowchart of a fault diagnosis method for a substation provided by an embodiment of the present invention.

[0052] Figure 2 It is a structural schematic diagram of a fault diagnosis device for substation equipment provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] like Figure 1 As shown, an embodiment of the present invention provides a fault diagnosis method for a power substation, which at least includes the following steps:

[0055] Step S1: Identify the basic outline image of the substation equipment to obtain the type of the substation equipment.

[0056] Preferably, in the present invention, the basic contour image of the substation equipment is identified, and the specific identification process is as follows: using a drone to collect the basic contour image of the substation equipment, extracting key features from the collected basic contour image, and matching the extracted features with the contour image in the database. According to the matching results, the contour image in the database with the highest matching degree is obtained. By identifying the contour image with the highest matching degree, the type of the substation equipment is determined.

[0057] It is understandable that by collecting the basic contour images of substation equipment through drones and extracting key features to match them with the contour images in the database, the type of substation equipment can be accurately and quickly identified. Compared with the traditional manual inspection method, the use of drones for image collection not only improves the recognition efficiency, but also reduces the possibility of manual misjudgment, further improving the accuracy and reliability of recognition.

[0058] Step S2: Determine the collection area and type of the collection area of ​​the substation equipment according to the type of the substation equipment.

[0059] Specifically, in a preferred embodiment, determining the collection area and the type of the collection area of ​​the substation equipment according to the type of the substation equipment includes:

[0060] According to the type of substation equipment, the model surface area of ​​the three-dimensional model of the substation equipment of this type and the monitoring area of ​​the monitoring equipment are obtained from the database.

[0061] The monitored area is compared with the model surface area to calculate the area monitored by each monitoring device.

[0062] According to the area monitored by each monitoring device, the surface of the substation equipment is divided into multiple areas to obtain various collection areas of the substation equipment.

[0063] For each collection area, a preset fault manifestation corresponding to the collection area is extracted from the database.

[0064] If the preset fault of the collection area is manifested as abnormal temperature information and normal gas information, the type of the collection area is determined to be a temperature information collection area.

[0065] If the preset fault of the collection area is manifested as abnormal gas information, the type of the collection area is determined to be a gas information collection area.

[0066] If the preset fault of the collection area is manifested as abnormal discharge information, the type of the collection area is determined to be a discharge information collection area.

[0067] If the preset fault of the collection area is manifested as abnormal apparent information, the type of the collection area is determined to be an apparent information collection area.

[0068] It is understandable that by comparing the monitoring area with the model surface area, the area monitored by each monitoring device can be accurately calculated, thereby realizing a fine division of the surface of the substation equipment. This fine division can determine the various collection areas of the substation equipment, improving the monitoring coverage and accuracy of the substation equipment. At the same time, according to the preset fault manifestations corresponding to each collection area, such as abnormal temperature information, abnormal gas information, abnormal discharge information, etc., the type of collection area can be accurately determined, thereby effectively improving the efficiency and accuracy of fault diagnosis, and providing strong support for the operation and maintenance of substation equipment.

[0069] Step S3: Capture images of the acquisition area by a first acquisition device to obtain a first analysis image, wherein the first acquisition device is a visible light camera.

[0070] In actual operation, when the drone moves or surveys to the designated collection area, its visible light camera will be used to take pictures. The images taken will be used as the first analysis image and the basis for subsequent data analysis and processing.

[0071] Step S4: Determine, according to the type of the acquisition area, a second acquisition device required for the acquisition area in addition to the visible light camera, wherein the second acquisition device includes any one of the following or a combination thereof: an infrared imager, a medium-wave infrared instrument, and an ultraviolet instrument.

[0072] Specifically, in a preferred embodiment, determining, according to the type of the acquisition area, a second acquisition device required for the acquisition area in addition to the visible light camera includes:

[0073] If the type of the collection area is a temperature information collection area, the second collection device is an infrared thermal imager.

[0074] If the type of the collection area is a gas information collection area, the second collection device is a medium-wave infrared instrument.

[0075] If the type of the collection area is a discharge information collection area, the second collection device is an ultraviolet instrument.

[0076] It is understandable that by combining the visible light camera and the second acquisition device to process temperature, gas, discharge and other information respectively, it can effectively cover a variety of possible fault types, especially those that do not cause temperature changes. This multi-device combination acquisition method improves the diversity and accuracy of substation equipment fault detection, reduces dependence on a single device, and reduces the cost and complexity of the acquisition process.

[0077] Step S5: performing image acquisition on the acquisition area based on the second acquisition device to obtain a second analysis image.

[0078] Specifically, in a preferred embodiment, if the type of the acquisition area is a temperature information acquisition area, the second acquisition device is an infrared thermal imager.

[0079] If the type of the collection area is a gas information collection area, the second collection device is a medium-wave infrared instrument.

[0080] If the type of the collection area is a discharge information collection area, the second collection device is an ultraviolet instrument.

[0081] For example, in actual operation, according to the type of the acquisition area, a drone carrying a second acquisition device is used to acquire images. The second acquisition device is started, and the drone takes a picture of the acquisition area to generate a second analysis image for subsequent data analysis and processing.

[0082] Step S6: fusing the first analysis image and the second analysis image to obtain a fused image.

[0083] Specifically, in a preferred embodiment, fusing the first analysis image and the second analysis image to obtain a fused image includes:

[0084] The first analysis image and the second analysis image are fused using the Gram-Schmidt method to obtain a fused image.

[0085] Wherein, when the second acquisition device is an infrared thermal imager, the second analysis image is an infrared image, and the fused image is a temperature fused image.

[0086] When the second acquisition device is a medium-wave infrared instrument, the second analysis image is a medium-wave infrared image, and the fused image is a gas fusion image.

[0087] When the second acquisition device is an ultraviolet instrument, the second analysis image is an ultraviolet image, and the fused image is a discharge fusion image.

[0088] It can be understood that by fusing the first analysis image with the second analysis image, the comprehensiveness and accuracy of fault diagnosis are significantly improved. The Gram-Schmidt method is used to fuse images, which can effectively integrate different types of image information. The generated fused image has more depth and details, and provides richer fault information. When the second acquisition device is an infrared thermal imager, the generated temperature fusion image can accurately display temperature anomalies and help detect temperature-related faults. When the second acquisition device is a medium-wave infrared instrument, the obtained gas fusion image can effectively identify potential risks such as gas leaks. When the second acquisition device is a medium-wave infrared instrument, the generated discharge fusion image can clearly present the electrical discharge situation.

[0089] Step S7: determining the fault type of the substation equipment acquisition area according to the fused image.

[0090] Specifically, in a preferred embodiment, determining the fault type of the substation equipment according to the fused image includes:

[0091] When the fused image is a temperature fusion image, obtain the total number of first pixels and the grayscale value of each first pixel of the temperature fusion image of the substation. Traverse each first pixel, and if its grayscale value is not within the standard temperature grayscale range, mark it as a temperature abnormality pixel. According to the number of temperature abnormality pixels and the total number of first pixels, calculate the temperature abnormality pixel rate. If the temperature abnormality pixel rate is greater than or equal to the standard temperature pixel rate, it is determined that there is a temperature abnormality in the acquisition area of ​​the substation.

[0092] When the fused image is a gas fusion image, the total number of second pixels of the gas fusion image of the substation and the grayscale value of each second pixel are obtained. Each second pixel is traversed, and if its grayscale value is not within the standard gas grayscale interval, it is marked as a gas abnormality pixel. Adjacent gas abnormality pixels are classified to obtain a number of abnormal pixel blocks. The number of pixels of each abnormal pixel block is matched with the gas model in the database to obtain a first matching degree. If the similarity of the first matching degree is greater than or equal to the standard matching degree, the abnormal pixel block is marked as a gas abnormality pixel block, and it is determined that there is a gas abnormality in the acquisition area of ​​the substation. If the similarity of the first matching degree is lower than the standard matching degree, the abnormal pixel block is marked as a non-gas abnormality pixel block, and it is checked whether the second pixel in the non-gas abnormality pixel block is a temperature abnormality pixel. The temperature abnormality pixel rate is calculated, and if it is greater than or equal to the standard temperature pixel rate, it is determined that there is a temperature abnormality in the acquisition area of ​​the substation.

[0093] When the fused image is a discharge fusion image, the total number of third pixels and the grayscale value of each third pixel of the discharge fusion image of the substation equipment are obtained. Each third pixel is traversed, and if its grayscale value is not within the standard discharge grayscale interval, it is marked as a discharge abnormality pixel. Adjacent discharge abnormality pixels are classified to obtain a number of abnormal pixel blocks, and the number of pixels of each abnormal pixel block is matched with the arc model in the database to obtain a second matching degree. If the similarity of the second matching degree is greater than or equal to the standard matching degree, the abnormal pixel block is marked as a discharge abnormality pixel block, and it is determined that there is a discharge abnormality in the acquisition area of ​​the substation equipment.

[0094] It should be noted that the standard temperature grayscale interval is obtained by summarizing the grayscales of the first pixel when the temperature of the substation is normal in the database. The standard gas grayscale interval is obtained by summarizing the grayscales of the second pixel when the gas of the substation is normal in the database. The standard discharge grayscale interval is obtained by summarizing the grayscales of the third pixel when the substation discharge is normal in the database. The standard temperature abnormal pixel rate is the maximum value of the abnormal pixel rate when the temperature of the substation is normal in the database. The temperature abnormal pixel rate in the temperature fusion image is the number of temperature abnormal pixels divided by the total number of first pixels. The temperature abnormal pixel rate in the gas fusion image is the number of temperature abnormal pixels in the non-gas abnormal pixel block divided by the total number of second pixels in the non-gas abnormal pixel block. The adjacent refers to the pixels being closely connected horizontally or vertically, and there are no other pixels separating them.

[0095] Specifically, in a preferred embodiment, if it is determined based on the type of the acquisition area that no other acquisition equipment is required except the visible light camera, the fault type of the substation equipment is determined based on the first analysis image.

[0096] Preferably, determining the fault type of the substation equipment collection area according to the first analysis image includes:

[0097] The feature information of the first analysis image of the substation equipment is obtained, and similarity calculation is performed with the damaged appearance image in the database.

[0098] If the similarity between the first analysis image and the damaged apparent image is greater than or equal to the standard similarity, it is determined that there is an apparent abnormality in the collection area of ​​the substation equipment.

[0099] In an optional embodiment, after determining the fault type of the substation equipment acquisition area according to the fused image, the method further includes:

[0100] If the fault type in the substation equipment collection area is an apparent abnormal fault, the collection area is marked as a potential hazard area.

[0101] If the fault type in the substation equipment collection area is one of temperature abnormality, gas abnormality or discharge abnormality, check whether the collection area also has an apparent abnormal fault. If so, mark the collection area as a direct fault area. If not, mark the collection area as an internal fault area.

[0102] It is understandable that further classification and marking of fault types in the substation equipment collection area can help staff better prioritize different types of faults, prompting staff to repair direct fault areas, inspect internal fault areas, and maintain potential danger areas, thereby reducing the possibility of missed faults and improving the operational reliability and safety of substation equipment.

[0103] Based on the above method embodiment, the present invention provides a corresponding device embodiment.

[0104] like Figure 2 As shown, an embodiment of the present invention provides a fault diagnosis device for substation equipment, including: a substation equipment classification module 101, a collection area determination module 102, a collection equipment setting module 103, an image collection and fusion module 104 and a fault type determination module 105.

[0105] The substation equipment classification module 101 is used to identify the basic outline image of the substation equipment and obtain the type of the substation equipment.

[0106] The collection area determination module 102 is used to determine the collection area and the type of the collection area of ​​the substation equipment according to the type of the substation equipment.

[0107] The acquisition device setting module 103 is used to determine the second acquisition device required for the acquisition area in addition to the visible light camera according to the type of the acquisition area. The second acquisition device includes any one or a combination of the following: infrared imager, medium-wave infrared instrument and ultraviolet instrument.

[0108] The image acquisition and fusion module 104 is used to acquire an image of the acquisition area through a first acquisition device to obtain a first analysis image. The first acquisition device is a visible light camera. The image of the acquisition area is acquired based on a second acquisition device to obtain a second analysis image. The first analysis image and the second analysis image are image-fused to obtain a fused image.

[0109] The fault type determination module 105 is used to determine the fault type of the substation equipment acquisition area according to the fused image.

[0110] It should be noted that the embodiments of the device described above correspond to the above embodiments of the present invention, and can implement any of the methods described above in the present invention. In addition, the embodiments of the above-mentioned device are merely schematic, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which can be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art can understand and implement it without paying any creative work.

[0111] Based on the above method embodiment, the present invention provides a storage medium embodiment;

[0112] Another embodiment of the present invention provides a storage medium, which includes a stored computer program, wherein when the computer program is executed, the device where the storage medium is located is controlled to execute any one of the above-mentioned methods for diagnosing faults of substation equipment of the present invention.

[0113] The storage medium is a computer-readable storage medium, and the computer program includes computer program code, which may be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0114] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0115] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A fault diagnosis method for a substation, characterized in that: include: Identify the basic outline image of the substation equipment and obtain the type of the substation equipment; Determine the collection area and type of the collection area of ​​the substation equipment according to the type of substation equipment; Capturing an image of the acquisition area through a first acquisition device to obtain a first analysis image; wherein the first acquisition device is a visible light camera; Determine, according to the type of the acquisition area, a second acquisition device required for the acquisition area in addition to the visible light camera; wherein the second acquisition device includes any one of the following or a combination thereof: an infrared imager, a medium-wave infrared instrument, and an ultraviolet instrument; Capturing an image of the acquisition area based on a second acquisition device to obtain a second analysis image; Performing image fusion on the first analysis image and the second analysis image to obtain a fused image; The fault type of the substation equipment acquisition area is determined according to the fused image.

2. The fault diagnosis method for power conversion equipment according to claim 1, characterized in that: If it is determined based on the type of the acquisition area that no other acquisition equipment is required except the visible light camera, the fault type of the substation equipment is determined based on the first analysis image.

3. A fault diagnosis method for power substation equipment according to claim 1, characterized in that: Determining the collection area and the type of the collection area of ​​the substation equipment according to the type of the substation equipment includes: According to the type of substation equipment, a model surface area of ​​a three-dimensional model of the substation equipment of the type and a monitoring area of ​​a monitoring device are obtained from a database; Compare the monitored area with the model surface area and calculate the area monitored by each monitoring device; According to the area monitored by each monitoring device, the surface of the substation equipment is divided into multiple areas to obtain various collection areas of the substation equipment; For each collection area, extract the preset fault manifestation corresponding to the collection area from the database; If the preset fault of the collection area is manifested as abnormal temperature information and normal gas information, the type of the collection area is determined to be a temperature information collection area; If the preset fault of the collection area is manifested as abnormal gas information, the type of the collection area is determined to be a gas information collection area; If the preset fault of the collection area is manifested as abnormal discharge information, the type of the collection area is determined to be a discharge information collection area; If the preset fault of the collection area is manifested as abnormal apparent information, the type of the collection area is determined to be an apparent information collection area.

4. A fault diagnosis method for power transformation equipment according to claim 1, characterized in that: According to the type of the acquisition area, determining a second acquisition device required for the acquisition area in addition to the visible light camera includes: If the type of the acquisition area is a temperature information acquisition area, the second acquisition device is an infrared thermal imager; If the type of the collection area is a gas information collection area, the second collection device is a medium-wave infrared instrument; If the type of the collection area is a discharge information collection area, the second collection device is an ultraviolet instrument.

5. A fault diagnosis method for power transformation equipment according to claim 1, characterized in that: The step of fusing the first analysis image with the second analysis image to obtain a fused image includes: Using the Gram-Schmidt method to fuse the first analysis image and the second analysis image to obtain a fused image; Wherein, when the second acquisition device is an infrared thermal imager, the second analysis image is an infrared image, and the fused image is a temperature fused image; When the second acquisition device is a medium-wave infrared instrument, the second analysis image is a medium-wave infrared image, and the fused image is a gas fusion image; When the second acquisition device is an ultraviolet instrument, the second analysis image is an ultraviolet image, and the fused image is a discharge fusion image.

6. A fault diagnosis method for power substation equipment according to claim 1, characterized in that: Determining the fault type of the substation equipment according to the fused image includes: When the fused image is a temperature fusion image, the total number of first pixels and the grayscale value of each first pixel of the temperature fusion image of the substation equipment are obtained; each first pixel is traversed, and if its grayscale value is not within the standard temperature grayscale range, it is marked as a temperature abnormality pixel; according to the number of temperature abnormality pixels and the total number of first pixels, the temperature abnormality pixel rate is calculated; if the temperature abnormality pixel rate is greater than or equal to the standard temperature pixel rate, it is determined that there is a temperature abnormality in the acquisition area of ​​the substation equipment; When the fused image is a gas fusion image, the total number of second pixel points of the gas fusion image of the substation equipment and the grayscale value of each second pixel point are obtained; each second pixel point is traversed, and if its grayscale value is not within the standard gas grayscale interval, it is marked as a gas abnormality pixel point; adjacent gas abnormality pixel points are classified to obtain a number of abnormal pixel blocks; the number of pixels of each abnormal pixel block is matched with the gas model in the database to obtain a first matching degree; if the similarity of the first matching degree is greater than or equal to the standard matching degree, the abnormal pixel block is marked as a gas abnormality pixel block, and it is determined that there is a gas abnormality in the collection area of ​​the substation equipment; if the similarity of the first matching degree is lower than the standard matching degree, the abnormal pixel block is marked as a non-gas abnormality pixel block, and it is checked whether the second pixel point in the non-gas abnormality pixel block is a temperature abnormality pixel point; the temperature abnormality pixel point rate is calculated, and if it is greater than or equal to the standard temperature pixel point rate, it is determined that there is a temperature abnormality in the collection area of ​​the substation equipment; When the fused image is a discharge fusion image, the total number of third pixel points of the discharge fusion image of the substation equipment and the grayscale value of each third pixel point are obtained; each third pixel point is traversed, and if its grayscale value is not within the standard discharge grayscale interval, it is marked as a discharge abnormality pixel point; adjacent discharge abnormality pixel points are classified to obtain a number of abnormal pixel blocks, and the number of pixels of each abnormal pixel block is matched with the arc model in the database to obtain a second matching degree; if the similarity of the second matching degree is greater than or equal to the standard matching degree, the abnormal pixel block is marked as a discharge abnormality pixel block, and it is determined that there is a discharge abnormality in the collection area of ​​the substation equipment.

7. A fault diagnosis method for power transformation equipment according to claim 2, characterized in that: Determining the fault type of the substation equipment collection area according to the first analysis image includes: Acquire feature information of the first analysis image of the substation equipment, and perform similarity calculation with the damaged appearance image in the database; If the similarity between the first analysis image and the damaged apparent image is greater than or equal to the standard similarity, it is determined that there is an apparent abnormality in the collection area of ​​the substation equipment.

8. A fault diagnosis method for power substation equipment according to claim 1, characterized in that: After determining the fault type of the substation equipment acquisition area according to the fused image, the method further includes: If the fault type in the substation equipment collection area is an apparent abnormal fault, the collection area is marked as a potential danger area; If the fault type in the substation equipment collection area is one of temperature abnormality, gas abnormality or discharge abnormality, check whether the collection area also has an apparent abnormal fault. If so, mark the collection area as a direct fault area. If not, mark the collection area as an internal fault area.

9. A fault diagnosis device for a power substation, characterized in that: include: Substation equipment classification module, acquisition area determination module, acquisition equipment setting module, image acquisition and fusion module and fault type determination module; The substation equipment classification module is used to identify the basic outline image of the substation equipment and obtain the type of the substation equipment; The collection area determination module is used to determine the collection area of ​​the substation equipment and the type of the collection area according to the type of the substation equipment; The acquisition device setting module is used to determine, according to the type of the acquisition area, a second acquisition device required for the acquisition area in addition to the visible light camera; wherein the second acquisition device includes any one of the following or a combination thereof: an infrared imager, a medium-wave infrared instrument, and an ultraviolet instrument; The image acquisition and fusion module is used to acquire an image of the acquisition area through a first acquisition device to obtain a first analysis image; wherein the first acquisition device is a visible light camera; acquire an image of the acquisition area based on a second acquisition device to obtain a second analysis image; and fuse the first analysis image and the second analysis image to obtain a fused image; The fault type determination module is used to determine the fault type of the substation equipment acquisition area according to the fused image.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it can implement the fault diagnosis method for substation equipment described in any one of claims 1 to 8.

Images