Inspection method, device and inspection equipment for distribution network equipment based on infrared images

Abstract

This invention provides a method, apparatus, and inspection equipment for inspecting distribution network equipment based on infrared images, belonging to the field of distribution network inspection. Each distribution network device is equipped with an electronic tag. The inspection method includes: acquiring scanning information of the electronic tags on the distribution network device to be inspected; wherein, the scanning information includes the location, category, first feature, first infrared image, and first environmental parameters of the distribution network device to be inspected, the first infrared image being an infrared image of the distribution network device under normal operation, and the first feature being determined based on the appearance image of the distribution network device to be inspected; acquiring a visible light image and an infrared image of the distribution network device to be inspected at the inspection time; and generating inspection data for the distribution network device to be inspected based on the visible light image, the infrared image, and the scanning information. This invention can improve the inspection efficiency of distribution network equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network inspection, and in particular to an inspection method, device and inspection equipment for distribution network equipment based on infrared images. Background Art

[0002] As the foundation of the power grid, distribution network equipment is affected by various factors such as quality problems, aging, weather, and human operation after it is put into operation, which will cause the performance of distribution network equipment to decline, resulting in failure of distribution network equipment to operate. When distribution network equipment fails to operate due to failure, it will bring great harm to the safe and reliable operation of the power grid. Therefore, full inspection of distribution network equipment and timely maintenance of equipment have become an indispensable task in the daily production management of the power grid.

[0003] Inspection of distribution network equipment is a basic work to effectively ensure the safe operation of the power grid. Through inspection, we can understand the operating status of the equipment and changes in the surrounding environment, discover equipment defects and hidden dangers that endanger equipment safety, carry out corresponding maintenance according to the hidden dangers, eliminate defects in time, prevent accidents, limit faults to the smallest scope, and ensure the safety of the power grid and the stability of the power system.

[0004] At present, the data collection of each operation link in the distribution network equipment inspection process mainly relies on manual methods. However, distribution network equipment is of various types, large number, large number and wide distribution, and has high reliability requirements. Therefore, the traditional manual method has high requirements on the professional quality of the inspection personnel. In addition, the traditional manual method has high labor intensity and low efficiency, which cannot meet the requirements of the power grid. Summary of the invention

[0005] The embodiments of the present invention provide an inspection method, device and inspection equipment for distribution network equipment based on infrared images, so as to solve the problem of low inspection efficiency of the current inspection method.

[0006] In a first aspect, an embodiment of the present invention provides a method for inspecting a distribution network device of an Internet of Things, wherein each distribution network device is provided with an electronic tag, and the inspection method comprises:

[0007] Obtaining scanning information of the electronic tag on the distribution network device to be inspected; wherein the scanning information includes the location, category, first feature, first infrared image, preset alarm temperature and first environmental parameter of the distribution network device to be inspected, the first infrared image is an infrared image of the distribution network device to be inspected when it is working normally, and the first feature is determined based on the appearance image of the distribution network device to be inspected;

[0008] Obtaining the inspection visible light image and inspection infrared image of the distribution network equipment to be inspected at the time of inspection;

[0009] Based on the inspection visible light image, inspection infrared image and scanning information of the electronic tag, the inspection data of the distribution network equipment to be inspected is generated; the inspection data at least includes whether the distribution network equipment to be inspected exceeds the warning temperature or whether there is a regional abnormality alarm.

[0010] In a possible implementation, based on the inspection visible light image, the inspection infrared image and the scanning information of the electronic tag, the inspection data of the distribution network device to be inspected is generated, including:

[0011] Input the inspection visible light image, inspection infrared image and scanning information into the pre-trained distribution equipment inspection model to generate inspection data of the distribution network equipment to be inspected;

[0012] Among them, the distribution equipment inspection model includes a feature extraction module, a temperature recognition module, a correction module and a comparison module. The inspection data includes the location, category, whether the warning temperature is exceeded, whether the appearance is abnormal, and whether there is an abnormal area alarm of the distribution network equipment to be inspected.

[0013] In a possible implementation, the feature extraction module is used to extract features from the inspection visible light image based on a scale-invariant feature conversion algorithm to obtain a second feature of the inspection visible light image; the first feature is obtained by extracting features from a complete appearance image of the inspection distribution network device based on a scale-invariant feature conversion algorithm;

[0014] The temperature recognition module is used to determine the real-time temperature of the distribution network equipment to be inspected based on the inspection infrared image;

[0015] The correction module is used to correct the real-time temperature based on the first environmental parameter and the second environmental parameter to obtain the corrected temperature; wherein the first environmental parameter is the first temperature, the first humidity and the first brightness when the first infrared image is taken, and the second environmental parameter is the second temperature, the second humidity and the second brightness when the inspection infrared image is taken;

[0016] The comparison module is used to generate inspection data of the distribution network equipment to be inspected based on the first feature, the second feature, the corrected temperature, the first infrared image and the inspection infrared image.

[0017] In a possible implementation, the correction module is provided with a temperature deviation adjustment module, a humidity deviation adjustment module, a brightness deviation adjustment module and a comprehensive adjustment module;

[0018] The temperature deviation adjustment module is used to obtain the temperature deviation based on the temperature infrared adjustment curve, the first temperature and the second temperature;

[0019] The humidity deviation adjustment module is used to obtain the humidity deviation based on the humidity infrared adjustment curve, the first humidity and the second humidity;

[0020] The brightness deviation adjustment module is used to obtain the brightness deviation based on the brightness infrared adjustment curve, the first brightness and the second brightness;

[0021] The comprehensive adjustment module is used to determine the corrected temperature based on the temperature deviation, humidity deviation, brightness deviation, real-time temperature and infrared image comprehensive model.

[0022] In a possible implementation, the comparison module includes an appearance comparison unit, an overtemperature comparison unit, and a local temperature comparison unit;

[0023] The appearance comparison unit is used to determine whether the appearance of the distribution network device to be inspected is abnormal based on the first feature and the second feature;

[0024] The over-temperature comparison unit is used to determine whether the distribution network equipment to be inspected exceeds the warning temperature based on the corrected temperature and the preset alarm temperature;

[0025] The local temperature comparison unit is used to determine whether there is a regional abnormality alarm in the distribution network equipment to be inspected based on the first infrared image and the inspection infrared image.

[0026] In a possible implementation, the local temperature comparison unit is used to determine whether there is a regional abnormality alarm based on the first infrared image, the inspection infrared image and a preset temperature difference threshold.

[0027] In a possible implementation, the inspection method further includes issuing an early warning and submitting an inspection application if it is determined that the distribution network equipment to be inspected has at least one of an abnormal appearance, exceeds a warning temperature, or has an abnormal area alarm.

[0028] In a possible implementation, the inspection infrared image and the first infrared image have the same scanning speed, scanning times, and light flux when they are captured.

[0029] In a second aspect, an embodiment of the present invention provides a patrol device for distribution network equipment based on infrared images, each distribution network equipment is provided with an electronic tag, and the patrol device includes:

[0030] A first acquisition module is used to acquire scanning information of the electronic tag on the distribution network device to be inspected; wherein the scanning information includes a first feature of the distribution network device to be inspected, a first infrared image, a preset alarm temperature and a first environmental parameter, the first infrared image is an infrared image of the distribution network device to be inspected when it is working normally, and the first feature is determined based on the appearance image of the distribution network device to be inspected;

[0031] The second acquisition module is used to acquire the inspection visible light image and the inspection infrared image of the distribution network equipment to be inspected at the inspection time;

[0032] The data generation module is used to generate inspection data of the distribution network equipment to be inspected based on the inspection visible light image, inspection infrared image and scanning information of the electronic tag; the inspection data at least includes whether the distribution network equipment to be inspected exceeds the warning temperature or whether there is an area abnormality alarm.

[0033] In a third aspect, an embodiment of the present invention provides an inspection device, which is a wearable device and includes a memory and a processor. The memory is used to store computer programs, and the processor is used to call and run the computer programs stored in the memory to execute any method of the first aspect.

[0034] The embodiment of the present invention provides an inspection method for distribution network equipment based on infrared images. First, the scanning information of the electronic tag on the distribution network equipment to be inspected is obtained, and the scanning information includes the location, category, first feature, first infrared image, preset alarm temperature and first environmental parameter of the distribution network equipment to be inspected. In order to determine the real-time status of the distribution network equipment to be inspected, it is also necessary to obtain the inspection visible light image and inspection infrared image of the distribution network equipment to be inspected at the inspection time. Finally, based on the inspection visible light image, the inspection infrared image and the scanning information of the electronic tag, the inspection data of the distribution network equipment to be inspected is generated, and the inspection data can at least show whether the distribution network equipment to be inspected exceeds the warning temperature or whether there is a regional abnormal alarm. Therefore, not only the appearance of the distribution network equipment to be inspected can be abnormally identified, but also the working status of the distribution network equipment to be inspected can be identified, so that the inspection personnel can timely repair the distribution network equipment to be inspected when the warning temperature is exceeded or the regional abnormal alarm is alarmed. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 It is a flow chart of the implementation of the inspection method of distribution network equipment based on infrared images provided by an embodiment of the present invention;

[0037] Figure 2 It is a structural schematic diagram of a power distribution equipment inspection model provided by an embodiment of the present invention;

[0038] Figure 3 It is a structural schematic diagram of an inspection device for distribution network equipment based on infrared images provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0039] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0040] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0041] Figure 1 The implementation flow chart of the inspection method of the distribution network equipment based on infrared images provided by the embodiment of the present invention is described in detail as follows:

[0042] S110: Obtain scanning information of the electronic tag on the distribution network device to be inspected.

[0043] In order to facilitate inspection of distribution network equipment, an electronic tag is set on each distribution network equipment. The electronic tag can be an NFC tag or an RFID tag.

[0044] The inspection equipment is integrated with an NFC reader, which can be used to read the NFC tag on the network distribution equipment to be inspected to obtain the device information of the device. NFC near-field communication technology is an integration of contactless radio frequency identification and interconnection technology. It combines the functions of inductive card readers, inductive cards and point-to-point on a single chip, and can identify and exchange data with compatible devices within a short distance. Near Field Communication (NFC) is a short-range, high-frequency radio technology that operates at a frequency of 13.56MHz within a distance of 10 cm. Obtaining the device information of the device through the NFC reader can quickly obtain the inspection device information and avoid obtaining the information of non-inspection devices.

[0045] RFID readers can also be integrated into the inspection equipment. Electromagnetic waves can be emitted through the RFID readers to form an electromagnetic field in the surrounding space. When the RFID tag enters the electromagnetic field, it obtains energy from it, thereby activating the microchip circuit in the RFID tag to convert electromagnetic waves to read the information of the power distribution equipment stored in the chip.

[0046] The scanning information includes the location, category, first feature, first infrared image, preset alarm temperature and first environmental parameter of the distribution network device to be inspected. The first infrared image is an infrared image of the distribution network device to be inspected when it is working normally, and the first feature is determined based on the appearance image of the distribution network device to be inspected.

[0047] In addition, based on inspection requirements, the scanning information may also include the model and name of the power distribution equipment, information on accessories included in the power distribution equipment, and historical inspection records.

[0048] S120: Obtain an inspection visible light image and an inspection infrared image of the distribution network equipment to be inspected at the time of inspection.

[0049] After obtaining the scanning information of the electronic tag of the distribution network device to be inspected, the inspection visible light image and inspection infrared image at the inspection time can be obtained based on the visible optical imaging device, infrared detector or infrared camera integrated on the inspection device.

[0050] An infrared image is an image obtained by acquiring the intensity of infrared light from an object. Based on the infrared image, it is possible to monitor whether the distribution network equipment to be inspected is working within the normal temperature range.

[0051] The inspection visible light image is a visible light image, and whether the appearance of the distribution network equipment to be inspected is intact can be determined based on the visible light image.

[0052] In addition, in order to improve the accuracy of detection, the scanning speed, scanning times and light flux of the inspection infrared image and the first infrared image are the same when they are taken.

[0053] S130: Generate inspection data of the distribution network device to be inspected based on the inspection visible light image, the inspection infrared image and the scanning information of the electronic tag.

[0054] The inspection data at least includes whether the distribution network equipment to be inspected exceeds the warning temperature or whether there is any regional abnormal alarm.

[0055] The current inspection is mainly based on the appearance of the equipment, and it is impossible to determine whether the distribution network equipment to be inspected is working normally or the operating temperature is too high, so it is impossible to make timely judgments on the operating status of the distribution network equipment to be inspected, so that the inspection personnel can grasp the status of the distribution network equipment to be inspected in time.

[0056] In some embodiments, the inspection visible light image, the inspection infrared image and the scanning information may be input into a pre-trained distribution equipment inspection model to generate inspection data of the distribution network equipment to be inspected.

[0057] In this embodiment, the inspection model of power distribution equipment includes a feature extraction module, a temperature identification module, a correction module and a comparison module.

[0058] The inspection data includes the location and category of the distribution network equipment to be inspected, whether it exceeds the warning temperature, whether the appearance is abnormal, and whether there is any regional abnormality alarm.

[0059] In this embodiment, the feature extraction module is used to extract features from the inspection visible light image based on the scale-invariant feature conversion algorithm to obtain the second feature of the visible light image to be inspected. The first feature is also obtained by extracting features from the complete appearance image of the distribution network device to be inspected based on the scale-invariant feature conversion algorithm.

[0060] The scale-invariant feature conversion algorithm is a commonly used image processing and computer vision algorithm. It can find key points in images at different scales and rotations, and extract local feature descriptors of these key points, thereby achieving image matching and recognition. By using the scale-invariant feature conversion algorithm, the key points of the device to be detected can be accurately identified, so that the appearance of the distribution network device to be inspected can be accurately identified based on the first feature and the second feature.

[0061] In this embodiment, the temperature recognition module is used to determine the real-time temperature of the network distribution equipment to be inspected based on the inspection infrared image. The real-time temperature of the network distribution equipment to be inspected can be determined based on the temperature values ​​of all pixels in the network distribution equipment area to be inspected in the inspection infrared image.

[0062] In addition, since the infrared image may be affected by the external environment, the obtained real-time temperature needs to be corrected. In this embodiment, the correction module is used to correct the real-time temperature based on the first environmental parameter and the second environmental parameter to obtain the corrected temperature.

[0063] The first environmental parameter is the first temperature, the first humidity and the first brightness when the first infrared image is taken, and the second environmental parameter is the second temperature, the second humidity and the second brightness when the inspection infrared image is taken.

[0064] Specifically, the correction module is provided with a temperature deviation adjustment module, a humidity deviation adjustment module, a brightness deviation adjustment module and a comprehensive adjustment module.

[0065] The temperature of the power distribution equipment to be inspected collected in the infrared image will be affected by the shooting environment temperature, so it is necessary to consider the impact of the ambient temperature on the temperature of the infrared image. The temperature deviation adjustment module is used to make adjustments based on the temperature infrared adjustment curve, the first temperature and the second temperature to obtain the temperature deviation. The temperature infrared adjustment curve is constructed based on the historical shooting temperature of the area where the power distribution equipment to be inspected is located and the infrared temperature of the power distribution equipment to be inspected obtained at this temperature, which can reflect the influence of the infrared temperature on the external temperature. The temperature infrared adjustment curve is a curve of the real-time ambient temperature and the infrared temperature of the power distribution equipment to be inspected. Therefore, the first temperature and the second temperature can respectively determine the corresponding first infrared temperature and second infrared temperature based on the temperature infrared adjustment curve, and the temperature deviation can be determined based on the difference between the second infrared temperature and the first infrared temperature.

[0066] The temperature of the power distribution equipment to be inspected collected in the infrared image will be affected by the humidity in the shooting environment, so it is necessary to consider the impact of the ambient humidity on the temperature of the infrared image. The humidity deviation adjustment module is used to obtain the humidity deviation based on the humidity infrared adjustment curve, the first humidity and the second humidity. The humidity infrared adjustment curve is constructed based on the historical shooting humidity of the area where the power distribution equipment to be inspected is located and the infrared temperature of the power distribution equipment to be inspected obtained under the humidity, which can reflect the influence of the infrared temperature on the external humidity. The humidity infrared adjustment curve is a curve of the real-time ambient humidity and the infrared temperature of the power distribution equipment to be inspected. Therefore, the first humidity and the second humidity can respectively determine the corresponding third infrared temperature and fourth infrared temperature based on the humidity infrared adjustment curve, and the humidity deviation can be determined based on the difference between the fourth infrared temperature and the third infrared temperature.

[0067] The temperature of the power distribution equipment to be inspected collected in the infrared image will be affected by the brightness in the shooting environment, so it is necessary to consider the impact of the ambient brightness on the temperature of the infrared image. The brightness deviation adjustment module is used to obtain the brightness deviation based on the brightness infrared adjustment curve, the first brightness and the second brightness. The brightness infrared adjustment curve is constructed based on the historical shooting brightness of the area where the power distribution equipment to be inspected is located and the infrared temperature of the power distribution equipment to be inspected obtained at the temperature, which can reflect the influence of the infrared temperature on the external brightness. The brightness infrared adjustment curve is a curve of the real-time ambient brightness and the infrared temperature of the power distribution equipment to be inspected. Therefore, the first brightness and the second brightness can respectively determine the corresponding fifth infrared temperature and sixth infrared temperature based on the brightness infrared adjustment curve, and the brightness deviation can be determined based on the difference between the sixth infrared temperature and the fifth infrared temperature.

[0068] The comprehensive adjustment module is used to determine the correction temperature based on the temperature deviation, humidity deviation, brightness deviation, real-time temperature and infrared image comprehensive model. The infrared image comprehensive model is trained based on the historical temperature deviation, humidity deviation and brightness deviation and the corresponding environmental impact deviation. Therefore, by inputting the temperature deviation, humidity deviation and brightness deviation into the infrared image comprehensive model, the environmental deviation can be output, and then the correction temperature can be determined based on the sum of the environmental deviation and the real-time temperature.

[0069] In some embodiments, in order to accurately calibrate the temperature of the patrol infrared image, a calibration piece is also provided on the patrol device. The calibration piece is provided within the shooting range of the visible light image and the infrared image device. The calibration piece is a black body, which refers to a standard object whose temperature is not affected by the external environment. This ensures that the temperature of the calibration piece remains constant and does not change with changes in the environment. The patrol visible light image and the patrol infrared image both include images of the calibration piece. In order to ensure the accuracy of the temperature obtained by the patrol infrared image, the calibration piece is required to calibrate the temperature in real time. The infrared temperature value of each pixel in the patrol infrared image is corrected by the temperature of the calibration piece tested in the patrol infrared image. The corrected temperature of the distribution network equipment to be inspected is determined by averaging the temperatures of all the corrected pixels.

[0070] In some embodiments, the comparison module is used to generate inspection data of the distribution network device to be inspected based on the first feature, the second feature, the corrected temperature, the first infrared image and the inspection infrared image.

[0071] In this embodiment, the comparison module includes an appearance comparison unit, an over-temperature comparison unit and a local temperature comparison unit.

[0072] The appearance comparison unit is used to determine whether the appearance of the distribution network device to be inspected is abnormal based on the first feature and the second feature. Since the first feature and the second feature include the key points of the appearance of the distribution network device to be inspected, by comparing the first feature and the second feature, it can be determined whether the appearance of the distribution network device to be inspected is abnormal.

[0073] The over-temperature comparison unit is used to determine whether the distribution network equipment to be inspected exceeds the warning temperature based on the corrected temperature and the preset warning temperature. When the corrected temperature is greater than the preset warning temperature, it means that the distribution network equipment to be inspected is working at a high temperature, and the working temperature is too high to exceed the warning temperature, and the distribution network equipment to be inspected is working abnormally. In addition, when the corrected temperature is less than the preset normal working temperature, it means that the distribution network equipment to be inspected is also in an abnormal working state.

[0074] The local temperature comparison unit is used to determine whether there is a regional abnormality alarm for the distribution network equipment to be inspected based on the first infrared image and the inspection infrared image. Specifically, a preset temperature difference threshold is set for the temperature difference value of each area of ​​the infrared image. Therefore, it can be determined whether there is a regional abnormality alarm based on the first infrared image, the inspection infrared image and the preset temperature difference threshold.

[0075] In addition, when it is determined that the distribution network equipment to be inspected has at least one of an abnormal appearance, exceeds the warning temperature, or has an abnormal regional alarm, an early warning is issued and a maintenance application is submitted.

[0076] The inspection method provided by the present invention first obtains the scanning information of the electronic tag on the distribution network device to be inspected, and the scanning information includes the location, category, first feature, first infrared image, preset alarm temperature and first environmental parameter of the distribution network device to be inspected. In order to determine the real-time status of the distribution network device to be inspected, it is also necessary to obtain the inspection visible light image and inspection infrared image of the distribution network device to be inspected at the time of inspection. Finally, based on the inspection visible light image, the inspection infrared image, the first feature, the first infrared image and the first environmental parameter, the inspection data of the distribution network device to be inspected is generated, and the inspection data can at least show whether the distribution network device to be inspected exceeds the warning temperature or whether there is a regional abnormal alarm. Therefore, not only the appearance of the distribution network device to be inspected can be abnormally identified, but also the working status of the distribution network device to be inspected can be identified, so that the inspection personnel can promptly repair the distribution network device to be inspected when the warning temperature is exceeded or the regional abnormal alarm is alarmed.

[0077] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0078] The following is an embodiment of the device of the present invention. For details not described in detail, reference may be made to the corresponding method embodiments described above.

[0079] Figure 3 The following is a schematic diagram showing the structure of an inspection device for distribution network equipment based on infrared images provided by an embodiment of the present invention. For ease of explanation, only the parts related to the embodiment of the present invention are shown, which are described in detail as follows:

[0080] like Figure 3 As shown, the inspection device 300 of the distribution network equipment based on infrared images, each distribution network equipment is provided with an electronic tag, and the inspection device includes:

[0081] The first acquisition module 310 is used to acquire scanning information of the electronic tag on the distribution network device to be inspected; wherein the scanning information includes a first feature of the distribution network device to be inspected, a first infrared image, a preset alarm temperature and a first environmental parameter, the first infrared image is an infrared image of the distribution network device to be inspected when it is working normally, and the first feature is determined based on the appearance image of the distribution network device to be inspected;

[0082] The second acquisition module 320 is used to acquire the inspection visible light image and the inspection infrared image of the distribution network equipment to be inspected at the inspection time;

[0083] The data generation module 330 is used to generate inspection data of the distribution network equipment to be inspected based on the inspection visible light image, inspection infrared image and scanning information of the electronic tag; the inspection data at least includes whether the distribution network equipment to be inspected exceeds the warning temperature or whether there is an area abnormality alarm.

[0084] In a possible implementation, the data generation module 330 is used to input the inspection visible light image, the inspection infrared image and the scanning information into the pre-trained distribution equipment inspection model to generate the inspection data of the distribution network equipment to be inspected;

[0085] Among them, the distribution equipment inspection model includes a feature extraction module, a temperature recognition module, a correction module and a comparison module. The inspection data includes the location, category, whether the warning temperature is exceeded, whether the appearance is abnormal, and whether there is an abnormal area alarm of the distribution network equipment to be inspected.

[0086] In a possible implementation, the feature extraction module is used to extract features from the inspection visible light image based on a scale-invariant feature conversion algorithm to obtain a second feature of the inspection visible light image; the first feature is obtained by extracting features from a complete appearance image of the inspection distribution network device based on a scale-invariant feature conversion algorithm;

[0087] The temperature recognition module is used to determine the real-time temperature of the distribution network equipment to be inspected based on the inspection infrared image;

[0088] The correction module is used to correct the real-time temperature based on the first environmental parameter and the second environmental parameter to obtain the corrected temperature; wherein the first environmental parameter is the first temperature, the first humidity and the first brightness when the first infrared image is taken, and the second environmental parameter is the second temperature, the second humidity and the second brightness when the inspection infrared image is taken;

[0089] The comparison module is used to generate inspection data of the distribution network equipment to be inspected based on the first feature, the second feature, the corrected temperature, the first infrared image and the inspection infrared image.

[0090] In a possible implementation, the correction module is provided with a temperature deviation adjustment module, a humidity deviation adjustment module, a brightness deviation adjustment module and a comprehensive adjustment module;

[0091] The temperature deviation adjustment module is used to obtain the temperature deviation based on the temperature infrared adjustment curve, the first temperature and the second temperature;

[0092] The humidity deviation adjustment module is used to obtain the humidity deviation based on the humidity infrared adjustment curve, the first humidity and the second humidity;

[0093] The brightness deviation adjustment module is used to obtain the brightness deviation based on the brightness infrared adjustment curve, the first brightness and the second brightness;

[0094] The comprehensive adjustment module is used to determine the corrected temperature based on the temperature deviation, humidity deviation, brightness deviation, real-time temperature and infrared image comprehensive model.

[0095] In a possible implementation, the comparison module includes an appearance comparison unit, an overtemperature comparison unit, and a local temperature comparison unit;

[0096] The appearance comparison unit is used to determine whether the appearance of the distribution network device to be inspected is abnormal based on the first feature and the second feature;

[0097] The over-temperature comparison unit is used to determine whether the distribution network equipment to be inspected exceeds the warning temperature based on the corrected temperature and the preset alarm temperature;

[0098] The local temperature comparison unit is used to determine whether there is a regional abnormality alarm in the distribution network equipment to be inspected based on the first infrared image and the inspection infrared image.

[0099] In a possible implementation, the local temperature comparison unit is used to determine whether there is a regional abnormality alarm based on the first infrared image, the inspection infrared image and a preset temperature difference threshold.

[0100] In a possible implementation, the inspection method further includes issuing an early warning and submitting an inspection application if it is determined that the distribution network equipment to be inspected has at least one of an abnormal appearance, exceeds a warning temperature, or has an abnormal area alarm.

[0101] In a possible implementation, the inspection infrared image and the first infrared image have the same scanning speed, scanning times, and light flux when they are captured.

[0102] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0103] In a third aspect, the present invention further provides an inspection device, which is a wearable device and includes a memory and a processor. The memory is used to store computer programs, and the processor is used to call and run the computer programs stored in the memory to execute any method as in the first aspect.

[0104] Those of ordinary skill in the art will appreciate that the templates, units, and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0105] If the module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, it can implement the steps of the above-mentioned various inspection methods for distribution network equipment based on infrared images. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory, random access memory, electric carrier signal, telecommunication signal and software distribution medium.

[0106] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for inspecting distribution network equipment based on infrared images, characterized in that: Each distribution network device is equipped with an electronic tag, and the inspection method includes: Obtaining scanning information of the electronic tag on the distribution network device to be inspected; wherein the scanning information includes a first feature of the distribution network device to be inspected, a first infrared image, a preset alarm temperature and a first environmental parameter, the first infrared image is an infrared image of the distribution network device to be inspected when it is working normally, and the first feature is determined based on the appearance image of the distribution network device to be inspected; Obtaining an inspection visible light image and an inspection infrared image of the distribution network equipment to be inspected at the time of inspection; Based on the inspection visible light image, the inspection infrared image and the scanning information of the electronic tag, the inspection data of the distribution network device to be inspected is generated; the inspection data at least includes whether the distribution network device to be inspected exceeds the warning temperature or whether there is an area abnormality alarm.

2. The inspection method for distribution network equipment based on infrared images according to claim 1 is characterized in that: The generating of the inspection data of the distribution network device to be inspected based on the inspection visible light image, the inspection infrared image and the scanning information of the electronic tag comprises: Inputting the inspection visible light image, the inspection infrared image and the scanning information of the electronic tag into a pre-trained distribution equipment inspection model to generate inspection data of the distribution network equipment to be inspected; Among them, the distribution equipment inspection model includes a feature extraction module, a temperature recognition module, a correction module and a comparison module, and the inspection data includes the location, category, whether it exceeds the warning temperature, whether the appearance is abnormal, and whether there is a regional abnormality alarm of the distribution network equipment to be inspected.

3. The inspection method for distribution network equipment based on infrared images according to claim 2 is characterized in that: The feature extraction module is used to extract features from the inspection visible light image based on a scale-invariant feature conversion algorithm to obtain a second feature of the visible light image to be inspected; the first feature is obtained by extracting features from the complete appearance image of the distribution network device to be inspected based on a scale-invariant feature conversion algorithm; The temperature recognition module is used to determine the real-time temperature of the distribution network equipment to be inspected based on the inspection infrared image; The correction module is used to correct the real-time temperature based on the first environmental parameter and the second environmental parameter to obtain a corrected temperature; wherein the first environmental parameter is the first temperature, the first humidity and the first brightness when the first infrared image is taken, and the second environmental parameter is the second temperature, the second humidity and the second brightness when the inspection infrared image is taken; The comparison module is used to generate inspection data of the distribution network device to be inspected based on the first feature, the second feature, the corrected temperature, the first infrared image and the inspection infrared image.

4. The inspection method for distribution network equipment based on infrared images according to claim 3 is characterized in that: The correction module is provided with a temperature deviation adjustment module, a humidity deviation adjustment module, a brightness deviation adjustment module and a comprehensive adjustment module; The temperature deviation adjustment module is used to obtain the temperature deviation based on the temperature infrared adjustment curve, the first temperature and the second temperature; The humidity deviation adjustment module is used to obtain a humidity deviation based on the humidity infrared adjustment curve, the first humidity and the second humidity; The brightness deviation adjustment module is used to obtain the brightness deviation based on the brightness infrared adjustment curve, the first brightness and the second brightness; The comprehensive adjustment module is used to determine the corrected temperature based on the temperature deviation, the humidity deviation, the brightness deviation, the real-time temperature and the infrared image comprehensive model.

5. The inspection method for distribution network equipment based on infrared images according to claim 3 is characterized in that: The comparison module includes an appearance comparison unit, an over-temperature comparison unit and a local temperature comparison unit; The appearance comparison unit is used to determine whether the appearance of the distribution network device to be inspected is abnormal based on the first feature and the second feature; The over-temperature comparison unit is used to determine whether the distribution network equipment to be inspected exceeds the warning temperature based on the corrected temperature and the preset alarm temperature; The local temperature comparison unit is used to determine whether there is a regional abnormality alarm for the distribution network equipment to be inspected based on the first infrared image and the inspection infrared image.

6. The inspection method for distribution network equipment based on infrared images according to claim 5 is characterized in that: The local temperature comparison unit is used to determine whether there is a regional abnormality alarm based on the first infrared image, the inspection infrared image and a preset temperature difference threshold.

7. The inspection method for distribution network equipment based on infrared images according to any one of claims 1 to 6, characterized in that: The inspection method also includes issuing an early warning and submitting an inspection application if it is determined that the distribution network equipment to be inspected has at least one of an abnormal appearance, exceeds a warning temperature, or has an abnormal area alarm.

8. The inspection method for distribution network equipment based on infrared images according to any one of claims 1 to 6, characterized in that: The scanning speed, scanning times and light flux of the inspection infrared image and the first infrared image when shooting are the same.

9. A distribution network equipment inspection device based on infrared images, characterized in that: Each distribution network device is equipped with an electronic tag, and the inspection device includes: A first acquisition module is used to acquire scanning information of the electronic tag on the distribution network device to be inspected; wherein the scanning information includes a first feature of the distribution network device to be inspected, a first infrared image, a preset alarm temperature and a first environmental parameter, the first infrared image is an infrared image of the distribution network device to be inspected when it is working normally, and the first feature is determined based on the appearance image of the distribution network device to be inspected; The second acquisition module is used to acquire the inspection visible light image and the inspection infrared image of the distribution network equipment to be inspected at the inspection time; A data generation module is used to generate inspection data of the distribution network equipment to be inspected based on the inspection visible light image, the inspection infrared image and the scanning information of the electronic tag; the inspection data at least includes whether the distribution network equipment to be inspected exceeds the warning temperature or whether there is an area abnormality alarm.

10. A patrol inspection device, characterized in that: The inspection device is a wearable device, including a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the method according to any one of claims 1 to 8.

Images