CN115359275A - Fault identification method and device, electronic equipment and storage medium - Google Patents

Abstract

The application discloses a fault identification method and device, electronic equipment and a storage medium. The method specifically comprises the following steps: acquiring a reference set of a template image with annotation information and an image to be identified; the marking information comprises reference shooting position parameters and at least one piece of fault judgment information; determining a reference template image matched with the image to be identified in a reference set according to the reference shooting position parameter; and carrying out fault identification on the image to be identified according to each fault judgment information in the reference template image. According to the technical scheme, the reference template image is determined according to the parameters of the shooting position in the reference set, and then the faults of the power equipment in the image to be recognized are recognized, so that the effect of recognizing multiple fault problems at one time can be achieved, the problem that the prior art can only recognize single areas and single fault problems is solved, and the precision and the efficiency of fault recognition are greatly improved.

Description

Fault identification method and device, electronic equipment and storage medium

Technical Field

The present application relates to the field of image processing technologies, and in particular, to a method and an apparatus for identifying a fault, an electronic device, and a storage medium.

Background

Electric energy has been widely used throughout the world after years of development, electric power is an energy source taking electric energy as power, and a large-scale electric power system appearing in the 20 th century is one of the most important achievements in the history of human engineering science. The power system generates, transmits, transforms and distributes power through a series of power equipment, and supplies power to users, so that maintenance of the power equipment is very important to guarantee distribution of power.

Currently, for a possible fault of an electric power device, an image of the electric power device may be analyzed through an image processing technology to diagnose the fault occurrence. For the occurrence of single fault, the method can accurately judge. However, for different faults occurring at the same time in the same power equipment, the method is easy to ignore the faults, so that the diagnosis is wrong, the fault identification precision is reduced, and the operation and maintenance efficiency of the power equipment is reduced.

Disclosure of Invention

The application provides a fault identification method and device, electronic equipment and a storage medium, so that the fault identification precision of the power equipment is improved, and the operation and maintenance efficiency of the power equipment is improved.

According to an aspect of the present application, there is provided a fault identification method, the method including:

acquiring a reference set of a template image with annotation information and an image to be identified; the annotation information comprises reference shooting position parameters and at least one piece of fault judgment information;

determining a reference template image matched with the image to be identified in a reference set according to the reference shooting position parameter;

and carrying out fault identification on the image to be identified according to each fault judgment information in the reference template image.

According to another aspect of the present application, there is provided a fault recognition apparatus including:

the image acquisition module is used for acquiring a reference set of the template image with the labeling information and the image to be identified; the marking information comprises reference shooting position parameters and at least one piece of fault judgment information;

the image matching module is used for determining a reference template image matched with the image to be identified in the reference set according to the reference shooting position parameter;

and the fault identification module is used for identifying faults of the image to be identified according to the fault judgment information in the reference template image.

According to another aspect of the present application, there is provided an electronic apparatus including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein, the first and the second end of the pipe are connected with each other,

the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the fault identification method of any of the embodiments of the present application.

According to another aspect of the present application, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement a fault identification method according to any one of the embodiments of the present application when the computer instructions are executed.

According to the technical scheme, the reference template image is determined according to the parameters of the shooting position in the reference set, and then the faults of the power equipment in the image to be recognized are recognized, so that the effect of recognizing multiple fault problems at one time can be achieved, the problem that the existing technology can only recognize single fault problems in a single area is solved, and the precision and the efficiency of fault recognition are greatly improved.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present application, nor do they limit the scope of the present application. Other features of the present application will become apparent from the following description.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a flowchart of a fault identification method according to an embodiment of the present application;

fig. 2 is a flowchart of a fault identification method according to a second embodiment of the present application;

FIG. 3 is a flowchart of a thermal defect identification method according to a third embodiment of the present application;

fig. 4 is a schematic structural diagram of a fault identification device according to a fourth embodiment of the present application;

fig. 5 is a schematic structural diagram of an electronic device implementing the fault identification method according to the embodiment of the present application.

Detailed Description

In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the accompanying drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Example one

Fig. 1 is a flowchart of a fault identification method provided in an embodiment of the present application, where the embodiment is applicable to a situation where fault identification is performed on an electrical device, and the method may be performed by a fault identification device, where the fault identification device may be implemented in a form of hardware and/or software, and the fault identification device may be configured in an electronic device to be tested. As shown in fig. 1, the method includes:

s110, acquiring a reference set of a template image with annotation information and an image to be identified; wherein the annotation information includes reference shooting position parameters and at least one piece of failure determination information.

The annotation information may be information for marking a fault in the template image, such as a location in the image of the fault of the electrical device in the template image, a type of the fault, a resolution policy of the fault, and the like. The reference shooting position parameter included in the annotation information may be angle-of-view position information of the template image shooting, that is, the position of the camera when shooting the template image is represented; the failure determination information may be a failure problem that may exist in the template image. It is to be understood that, since a plurality of pieces of failure determination information may exist in the power equipment captured in one template image at the same time, at least one piece of failure determination information may be included in the annotation information. The template image may be an image for comparison with an image to be recognized to assist in fault recognition. Preferably, the template image may take an infrared image. The reference set may be a set of images of all template images. The image to be recognized may be an (infrared) image of the electric power equipment that needs to be fault-recognized.

In an optional implementation manner, before the acquiring the reference set of template images with annotation information and the image to be identified, the method may further include: and labeling each template image in the reference set according to the incidence relation between the fault area information and the fault identification strategy.

The failure region information may be used to characterize an image region (pixel region) having a failure problem in the template image, where the failure problem may include, but is not limited to, a temperature anomaly, a physical damage, and the like. The fault identification strategy may be a scheme for determining different faults of the power device. Taking an example of a thermal defect identification strategy, a thermal defect is a fault problem that the temperature of the electrical equipment is too high, and the identification strategy for the problem is to identify the temperature of the relevant component of the electrical equipment in the infrared image and the preset temperature threshold value, and if the temperature is higher than the preset temperature threshold value, determine that the thermal defect occurs in the electrical equipment. By establishing an association relationship between the position (image area) where the fault occurs and the policy adopted for identifying the fault, it can be understood that the fault which is likely to occur in the power equipment can be known in advance, and the association relationship is labeled on the template image.

Specifically, before the template image is marked, the template image can be collected firstly, in the inspection of the power equipment, the unmanned aerial vehicle or the robot and other automatic inspection equipment are adopted to carry out complete inspection on the site of the power system, and infrared images of all the power equipment are shot from a plurality of different angles to serve as the template image. And according to actual experience, carrying out region labeling on the power equipment shot in each template image and labeling identification strategies corresponding to faults which easily occur. Certainly, the labeling may be in a manual labeling manner, or in a manual labeling manner and a machine learning auxiliary labeling manner, and the labeling process is not limited in the embodiment of the present application.

And S120, determining a reference template image matched with the image to be identified in the reference set according to the reference shooting position parameter.

The reference set includes a plurality of template images, where there may be images similar to the image to be recognized, for example, the images may be similar to the power device being photographed, or the angles being photographed are similar, etc. And finding out a template image similar to the image to be identified from the reference set as a reference template image, and providing a basis for subsequent fault identification.

In an alternative embodiment, the determining, according to the reference shooting position parameter, a reference template image matching the image to be recognized in the reference set may include: determining a shooting position deviation value according to the reference shooting position parameter and the actual shooting position parameter of the image to be recognized; and determining a reference template image according to the preset deviation threshold value and the shooting position deviation value.

The reference shooting position parameter corresponds to the shooting position of the reference template image, the actual shooting position parameter corresponds to the shooting position of the image to be recognized, the difference value between the shooting positions is calculated according to the parameters of the two shooting positions, and the shooting position deviation value can include, but is not limited to, a longitude difference value, a latitude difference value, an altitude difference value, a yaw difference value, a pitch angle difference value and the like. And the preset deviation threshold is used for judging which template image is close to the shooting position of the image to be identified. Of course, the preset deviation threshold may be determined by a person skilled in the relevant art through a large number of experiments or empirical values, which is not limited in the embodiment of the present application. It is understood that if the deviation value of the shooting position of a certain template image meets the preset deviation threshold, the template image can be determined as the reference template image.

According to the embodiment, the reference template images are screened by determining the deviation value of the shooting position, so that an efficient method for selecting the reference template images is provided, the screening precision is high, the speed is high, and the fault identification efficiency is further improved.

And S130, carrying out fault identification on the image to be identified according to each fault judgment information in the reference template image.

According to the method, the corresponding fault problem is determined according to the label of the fault judgment information in the reference template image and the fault judgment basis contained in the fault judgment information, and the power equipment shot in the image to be identified and the fault diagnosis.

According to the technical scheme, the reference template image is determined according to the parameters of the shooting position in the reference set, and then the faults of the power equipment in the image to be recognized are recognized, so that the effect of recognizing multiple fault problems at one time can be achieved, the problem that the prior art can only recognize single areas and single fault problems is solved, and the precision and the efficiency of fault recognition are greatly improved.

Example two

Fig. 2 is a flowchart of a fault identification method provided in the second embodiment of the present application, and the present embodiment is to further refine fault identification based on the foregoing embodiments. As shown in fig. 2, the failure determination information includes area information and a failure identification policy, and the method includes:

s210, acquiring a reference set of a template image with annotation information and an image to be identified; wherein the annotation information includes reference shooting position parameters and at least one piece of failure determination information.

And S220, determining a reference template image matched with the image to be identified in the reference set according to the reference shooting position parameter.

And S230, determining at least one associated area coordinate in the image to be identified according to the information of each fault area.

The associated area coordinates may correspond to the fault area information, and the pixel area of the fault area on the reference template image corresponds to the area coordinates in the image to be identified, which may be in a pixel unit. And correspondingly finding at least one image area or pixel area corresponding to the fault area information in the image to be identified according to each fault area information in the reference template image obtained in the previous step.

In an alternative embodiment, the fault area information is associated with at least one fault detection strategy.

It can be understood that one fault area information may be associated with a plurality of fault identification strategies, that is, one fault area may have a plurality of and/or a plurality of different fault problems in the image range defined in the reference template image, and different fault problems correspond to different fault identification strategies.

And S240, carrying out fault identification on the image to be identified according to the coordinates of each associated area.

And judging the fault problem of the image to be recognized in the image range defined by the associated area coordinates determined in the previous step.

In an optional implementation manner, the performing fault identification on the image to be identified according to the coordinates of each associated region may include: determining a target identification strategy in at least one fault identification strategy according to the coordinates of each associated area; and determining at least one fault in the image to be identified according to the target identification strategy.

Since the associated area coordinates correspond to the fault area information, the fault identification strategy associated in the fault area information can also be applied to the image area defined by the associated area coordinates. And selecting a fault identification strategy in fault area information corresponding to the associated area coordinates from all fault identification strategies marked in the whole reference template image as a target identification strategy. And identifying the fault problem of the power equipment in the image to be identified by taking the target identification strategy as a standard. Of course, there may be multiple faults in the image to be identified.

In an alternative embodiment, the fault comprises a thermal defect fault of the electrical equipment; correspondingly, the fault identification strategy comprises at least one of a single-point absolute temperature strategy, a single-point temperature rise strategy, a multi-point absolute temperature difference strategy and a multi-point relative temperature difference strategy.

It should be noted that the acquired image to be recognized is an infrared image, and the infrared image includes temperature information of each area in the image.

The single-point absolute temperature strategy is suitable for identifying current heating type thermal defects, such as heating caused by poor contact of cable head connecting parts of outgoing cables. And setting an absolute temperature threshold value for a single-point absolute temperature strategy, and if the temperature information in the image to be identified is higher than the absolute temperature threshold value, judging that the electric power equipment has current heating type thermal defects.

The single-point temperature rise strategy is suitable for identification of comprehensive heating type thermal defects, such as heating phenomena caused by internal defects of a capacitor body. And setting a temperature rise threshold value for the single-point temperature rise strategy, and if the temperature value of the temperature information in the image to be identified is higher than the temperature rise threshold value, judging that the comprehensive heating type thermal defect occurs in the power equipment.

The multipoint absolute temperature difference strategy is suitable for identification of comprehensive heating type thermal defects, for example, the absolute temperature difference of a three-phase GIS (Gas Insulated Switchgear) air chamber caused by abnormal heating of the air chamber of a certain phase GIS is too large. The multipoint absolute temperature rise strategy can select at least two associated area coordinates, the difference value of temperature values in an image range defined by the at least two associated area coordinates is calculated and compared with a preset absolute temperature difference threshold, and if the difference value of the temperature values is larger than the absolute temperature difference threshold, the power equipment is judged to generate comprehensive heating type thermal defects.

The multi-point relative temperature difference strategy is suitable for identifying voltage heating type thermal defects, for example, the relative temperature difference of three-phase voltage transformer porcelain bottles caused by abnormal heating of a certain transformer porcelain bottle is overlarge. Similarly, the multipoint relative temperature difference strategy may select at least two associated region coordinates, count the highest temperature value and the lowest temperature value in the image range defined by the at least two associated region coordinates, calculate the temperature difference value in different image ranges in advance, compare the temperature difference values of the at least two associated regions (for example, by means of difference or quotient), compare the comparison value of the temperature difference value with the set relative temperature difference threshold, and if the comparison of the temperature difference value is greater than the relative temperature difference threshold, determine that the power device has voltage-induced thermal defects.

According to the technical scheme, the associated area coordinates corresponding to the fault area information in the reference template image are found in the image to be identified, the thermal defect fault is identified in the image range defined by the coordinates, the identification efficiency is effectively improved, the coordinates of the fault position corresponding to the fault area information and the fault identification strategy are simultaneously obtained from the reference template image, the fault identification accuracy can be greatly improved, and the fault identification is faster.

EXAMPLE III

The embodiment of the present application is a preferred embodiment provided on the basis of the foregoing embodiments, and identifies a thermal defect of an electrical device, as shown in fig. 3, the specific method includes the following steps:

1. and taking all images needing multi-type thermal defect identification as images to be identified, setting the total number of the images to be identified to be N, taking each image to be identified and longitude, latitude, height, yaw angle and pitch angle information of a camera when the image is shot as a combination, and forming a set J by all N combinations.

2. Let n be equal to 1,n as the index of the image to be recognized.

3. For the nth image to be identified in the set J, identifying the multiple types of thermal defects according to the following method:

and 3.1, making the recognition result set R (n) as an empty set, wherein the set R (n) is used for storing the thermal defect recognition result of the nth image to be recognized.

3.2, let m equal to 1,m as the index of the stencil image.

3.3, calculating shooting position parameter difference values of the nth image to be identified in the set J and the mth Zhang Moban image in the set I, including a longitude difference value C _jing (n, m), latitude difference C _wei (n, m), height difference C _gao (n, m) and a yaw angle difference C _pian (n, m) and a difference value C of pitch angle _fu (n, m), the specific calculation method is as follows:

C _jing (n,m)＝|P _jing (J,n)-P _jing (I,m)|；

C _wei (n,m)＝|P _wei (J,n)-P _wei (I,m)|；

C _gao (n,m)＝|P _gao (J,n)-P _gao (I,m)|；

C _pian (n,m)＝|P _pian (J,n)-P _pian (I,m)|；

C _fu (n,m)＝|P _fu (J,n)-P _fu (I,m)|；

wherein, P _jing (J, n) denotes the shooting longitude of the nth image to be recognized in the set J, P _jing (I, m) represents the shooting longitude of the m Zhang Moban image in set I; p _wei (J, n) represents the shooting latitude of the nth image to be identified in the set J, P _wei (I, m) represents the shooting latitude of the m Zhang Moban image in the set I; p _gao (J, n) represents the shooting height of the nth image to be identified in the set J, P _gao (I, m) represents the shooting height of the m Zhang Moban image in the set I; p _pian (J, n) represents the shooting yaw angle of the nth image to be recognized in the set J, P _pian (I, m) represents the shooting yaw angle of the m Zhang Moban image in the set I; p _fu (J, n) represents the shooting pitch angle of the nth image to be identified in the set J, P _fu (I, m) represents the imaging pitch angle of the m Zhang Moban image in the set I.

3.4, if the shooting position parameter difference between the nth image to be identified in the set J and the m Zhang Moban image in the set I simultaneously satisfies the following conditions:

C _jing (n,m)＜(2×10 ^-7 )°；

C _wei (n,m)＜(2×10 ^-7 )°；

C _gao (n,m)＜0.02m；

C _pian (n,m)＜3°；

C _fu (n,m)＜3°；

then the n-th image to be identified in the set J is judged to be matched with the m Zhang Moban image in the set I.

3.5, if M is equal to M, indicating that all the template images have been traversed, and continuing to execute the step 3.6; otherwise, let m add 1 by itself, and then re-execute step 3.3.

3.6, if the nth image to be identified of the set J is matched with 2 or more template images in the set I or the nth image to be identified of the set J is not matched with any template image in the set I, indicating that the nth image to be identified of the set J cannot be correctly and uniquely matched with the template image set I, and directly executing the step 3.12; otherwise, the template image uniquely matched with the nth image to be identified in the set J is marked as a template image m0, and the step 3.7 is continuously executed.

3.7, the number of recognition strategies contained in the recognition strategy set S (m 0) of the template image m0 is T. Let t equal to 1,t be the index that identifies the policy in policy set S (m 0).

3.8, judging whether the identification strategy t is a single-point absolute temperature strategy or not, and if not, continuing to perform the step 3.9; and if so, reading the hot spot temperature of each key part area in the image n to be recognized according to all key part area coordinates of the recognition strategy t, and judging whether the thermal defect exists in the image n to be recognized according to a judging method of a single-point absolute temperature strategy. If the single-point absolute temperature overhigh heat defect exists, forming a set R1 (n) by all key part areas with the single-point absolute temperature overhigh heat defect in the image n to be identified, and adding the set R1 (n) into the R (n); otherwise, the set R1 (n) is made an empty set, and the set R1 (n) is added to R (n).

3.9, judging whether the identification strategy t is a single-point temperature rise strategy or not, and if not, continuing to perform the step 3.10; and if so, reading the hot spot temperature of each key part area in the image n to be recognized according to the coordinates of all key part areas of the recognition strategy t, and judging whether the thermal defect exists in the image n to be recognized according to a judging method of a single-point temperature rise strategy. If the single-point temperature rise over-high heat defect exists, forming a set R2 (n) in all key part areas with the single-point temperature rise over-high heat defect in the image n to be identified, and adding the set R2 (n) into the R (n); otherwise, let set R2 (n) be an empty set, and add set R2 (n) to R (n).

3.10, judging whether the identification strategy t is a multipoint absolute temperature difference strategy or not, and if not, continuing to perform the step 3.11; if so, reading the hot spot temperature of each key part area in the image n to be recognized according to the coordinates of all key part areas of the recognition strategy t, and judging whether the thermal defect exists in the image n to be recognized according to a judgment method of a multi-point absolute temperature difference strategy. If the multipoint thermal defect with the excessive absolute temperature difference exists, forming 1 combination of the excessive absolute temperature difference areas for every 1 pair of key part areas with the multipoint thermal defect with the excessive absolute temperature difference in the image n to be recognized, combining all the excessive absolute temperature difference areas to form a set R3 (n), and adding the set R3 (n) into the R (n); otherwise, let set R3 (n) be an empty set, and add set R3 (n) to R (n).

3.11, judging whether the identification strategy t is a multipoint relative temperature difference strategy or not, and if not, continuing to perform the step 3.12; if so, reading the hot spot temperature of each key part area in the image n to be recognized according to the coordinates of all key part areas of the recognition strategy t, and judging whether the thermal defect exists in the image n to be recognized according to a judgment method of a multi-point relative temperature difference strategy. If the multipoint thermal defect with the overlarge relative temperature difference exists, forming 1 combination of the areas with the overlarge relative temperature difference in each 1 pair of key parts with the multipoint thermal defect with the overlarge relative temperature difference in the image n to be recognized, combining all the areas with the overlarge relative temperature difference to form a set R4 (n), and adding the set R4 (n) into the R (n); otherwise, let set R4 (n) be an empty set, and add set R4 (n) to R (n).

3.12, if the set R (n) is an empty set, namely R1 (n), R2 (n), R3 (n) and R4 (n) are not included, outputting the identification result of the image n to be identified as 'template image matching failure'; if the set R (n) is not an empty set, but R1 (n), R2 (n), R3 (n) and R4 (n) are all empty sets, outputting the identification result of the image n to be identified as 'no thermal defect'; if the set R (n) is not an empty set and at least 1 of the sets R1 (n), R2 (n), R3 (n) and R4 (n) is not an empty set, outputting key part areas or key part area combinations of the non-empty sets in the sets R1 (n), R2 (n), R3 (n) and R4 (n) and corresponding identification strategies as the thermal defect identification result of the image n to be identified.

4. If N is equal to N, the thermal defect identification of all the images to be identified is completed, and corresponding results are output; otherwise, let n add 1 by itself, and then re-execute step 3.

Example four

Fig. 4 is a schematic structural diagram of a fault identification device according to a third embodiment of the present application. As shown in fig. 4, the apparatus 400 includes:

the image acquisition module 410 is used for acquiring a reference set of the template image with the annotation information and an image to be identified; the marking information comprises reference shooting position parameters and at least one piece of fault judgment information;

the image matching module 420 is used for determining a reference template image matched with the image to be identified in the reference set according to the reference shooting position parameter;

and the fault identification module 430 is configured to perform fault identification on the image to be identified according to each fault determination information in the reference template image.

According to the technical scheme, the reference template image is determined according to the parameters of the shooting position in the reference set, and then the faults of the power equipment in the image to be recognized are recognized, so that the effect of recognizing multiple fault problems at one time can be achieved, the problem that the prior art can only recognize single areas and single fault problems is solved, and the precision and the efficiency of fault recognition are greatly improved.

In an optional embodiment, the failure determination information includes failure region information and a failure identification policy; accordingly, the fault identification module 430 may include:

the relevant area determining unit is used for determining at least one relevant area coordinate in the image to be identified according to the information of each fault area;

and the image fault identification unit is used for identifying faults of the image to be identified according to the coordinates of the associated areas.

In an alternative embodiment, the fault area information is associated with at least one fault detection strategy.

In an alternative embodiment, the image failure recognition unit may include:

the target strategy determining subunit is used for determining a target identification strategy in at least one fault identification strategy according to the coordinates of each associated area;

and the fault determining subunit is used for determining at least one fault in the image to be identified according to the target identification strategy.

In an alternative embodiment, the fault comprises a thermal defect fault of the electrical equipment; correspondingly, the fault identification strategy comprises at least one of a single-point absolute temperature strategy, a single-point temperature rise strategy, a multi-point absolute temperature difference strategy and a multi-point relative temperature difference strategy.

In an alternative embodiment, the image matching module 420 may include:

the position deviation determining unit is used for determining a shooting position deviation value according to the reference shooting position parameter and the actual shooting position parameter of the image to be recognized;

and the template image determining unit is used for determining a reference template image according to a preset deviation threshold value and the shooting position deviation value.

In an alternative embodiment, the apparatus 400 may further include:

and the image labeling module is used for labeling each template image in the reference set according to the incidence relation between the fault area information and the fault identification strategy.

The fault identification device provided by the embodiment of the application can execute the fault identification method provided by any embodiment of the application, and has the corresponding functional modules and beneficial effects of executing each fault identification method.

EXAMPLE five

FIG. 5 illustrates a schematic structural diagram of an electronic device 10 that may be used to implement embodiments of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application that are described and/or claimed herein.

As shown in fig. 5, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 11 can perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from a storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data necessary for the operation of the electronic apparatus 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to the bus 14.

A number of components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, or the like; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.

Processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, or the like. The processor 11 performs the various methods and processes described above, such as the fault identification method.

In some embodiments, the fault identification method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the fault identification method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the fault identification method by any other suitable means (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for implementing the methods of the present application may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on a machine, as a stand-alone software package partly on a machine and partly on a remote machine or entirely on a remote machine or server.

In the context of this application, a computer readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the Internet.

The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present application may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solution of the present application can be achieved, and the present invention is not limited thereto.

The above-described embodiments are not intended to limit the scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims (10)

1. A method of fault identification, the method comprising:

acquiring a reference set of a template image with annotation information and an image to be identified; the marking information comprises reference shooting position parameters and at least one piece of fault judgment information;

determining a reference template image matched with the image to be identified in the reference set according to the reference shooting position parameter;

and performing fault identification on the image to be identified according to each fault judgment information in the reference template image.

2. The method according to claim 1, wherein the failure determination information includes failure region information and a failure identification policy; correspondingly, the performing fault identification on the image to be identified according to each fault judgment information in the reference template image includes:

determining at least one associated area coordinate in the image to be identified according to the information of each fault area;

and carrying out fault identification on the image to be identified according to the coordinates of the associated areas.

3. The method according to claim 2, characterized in that the fault area information is associated with at least one fault identification policy.

4. The method according to claim 3, wherein the fault identifying the image to be identified according to each of the associated region coordinates comprises:

determining a target identification strategy in the at least one fault identification strategy according to the coordinates of each associated area;

and determining at least one fault in the image to be identified according to the target identification strategy.

5. The method of claim 4, wherein the fault comprises a thermal defect fault of the electrical equipment; correspondingly, the fault identification strategy comprises at least one of a single-point absolute temperature strategy, a single-point temperature rise strategy, a multi-point absolute temperature difference strategy and a multi-point relative temperature difference strategy.

6. The method according to any one of claims 1 to 5, wherein the determining a reference template image matching the image to be recognized in the reference set according to the reference shooting position parameter comprises:

determining a shooting position deviation value according to the reference shooting position parameter and the actual shooting position parameter of the image to be recognized;

and determining the reference template image according to a preset deviation threshold value and the shooting position deviation value.

7. The method according to any one of claims 1 to 5, wherein before the obtaining the reference set of template images with labeling information and the image to be identified, the method further comprises:

and labeling each template image in the reference set according to the incidence relation between the fault area information and the fault identification strategy.

8. A fault identification device, comprising:

the image acquisition module is used for acquiring a reference set of the template image with the labeling information and the image to be identified; the marking information comprises reference shooting position parameters and at least one piece of fault judgment information;

the image matching module is used for determining a reference template image matched with the image to be identified in the reference set according to the reference shooting position parameter;

and the fault identification module is used for identifying the fault of the image to be identified according to each fault judgment information in the reference template image.

9. An electronic device, characterized in that the electronic device comprises:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the fault identification method of any one of claims 1-7.

10. A computer-readable storage medium storing computer instructions for causing a processor to perform the fault identification method of any one of claims 1-7 when executed.

Images