CN115393566A

CN115393566A - Fault identification and early warning method and device for power equipment, storage medium and equipment

Info

Publication number: CN115393566A
Application number: CN202211069465.3A
Authority: CN
Inventors: 韩兆刚; 吴鹏; 甘津瑞; 张颉; 刘哲; 梁骁
Original assignee: State Grid Smart Grid Research Institute Co ltd; State Grid Corp of China SGCC; State Grid Sichuan Electric Power Co Ltd; State Grid Shanghai Electric Power Co Ltd; Minzu University of China
Current assignee: State Grid Smart Grid Research Institute Co ltd; State Grid Corp of China SGCC; State Grid Sichuan Electric Power Co Ltd; State Grid Shanghai Electric Power Co Ltd; Minzu University of China
Priority date: 2022-09-01
Filing date: 2022-09-01
Publication date: 2022-11-25

Abstract

The application discloses a fault identification and early warning method and device of power equipment, a storage medium and equipment. The method comprises the following steps: under the condition that the power equipment is detected, acquiring detection parameters of the power equipment, wherein the detection parameters comprise data of a plurality of data sources; performing fault prediction on the power equipment according to the detection parameters to obtain a prediction result; determining a corresponding augmented reality image according to the fault type of the prediction result under the condition that the prediction result represents the fault of the power equipment; and displaying the augmented reality image on the real-time image according to the real-time position of the electric power equipment in the displayed real-time image. The problem of among the correlation technique patrol and examine the in-process at power equipment and detect power equipment, need artifical analysis data or image, perhaps rely on single dimension's detected data, discern whether power equipment breaks down, it is big to have the discernment degree of difficulty, and the discernment is inefficient, and can't carry out the trouble early warning is solved.

Description

Fault identification and early warning method and device for power equipment, storage medium and equipment

Technical Field

The application relates to the field of equipment detection, in particular to a fault identification and early warning method and device for power equipment, a storage medium and equipment.

Background

With the development of the power equipment fault detection technology research, people have got rid of the defects of static shutdown inspection and mechanized omnibearing manual detection in the traditional detection technology to a certain extent. The intelligent dynamic detection functions such as infrared and visible light image registration, machine vision, intelligent robot fault detection and the like are technically realized. The system can realize automatic detection and calibration to a certain extent, reduces the proportion of manual detection, and realizes great breakthrough in the predictability and the early warning performance of the system faults of the power equipment. However, in practical application, a large amount of manual detection is still needed, a large part of detection is uncertain, and the manual detection still causes inevitable influence on the reliable and stable operation of the equipment in the whole time period.

The method aims at the problems that in the related art, the power equipment needs to be manually analyzed for data or images or depends on single-dimensional detection data to identify whether the power equipment fails, the identification difficulty is high, the identification efficiency is low, and failure early warning cannot be carried out in the power equipment inspection process, and an effective solution is not provided at present.

Disclosure of Invention

The main purpose of the application is to provide a fault identification and early warning method and system for power equipment, so that the problems that in the related technology, the power equipment is required to be manually analyzed for data or images in the process of routing inspection, or the detection data of a single dimension is relied on, whether the power equipment fails or not is identified, the identification difficulty is high, the identification efficiency is low, and fault early warning cannot be carried out are solved.

In order to achieve the above object, according to an aspect of the present application, there is provided a fault identification and early warning method for an electrical device, including: under the condition that the power equipment is detected, obtaining detection parameters of the power equipment, wherein the detection parameters comprise data of a plurality of data sources, and the data sources are used for carrying out data detection on the power equipment in a plurality of dimensions; performing fault prediction on the power equipment according to the detection parameters to obtain a prediction result, wherein the prediction result is used for representing whether the identified fault exists or not and identifying the fault type of the fault; determining a corresponding augmented reality image according to the fault type of the prediction result under the condition that the prediction result represents the fault of the power equipment; and displaying the augmented reality image on the real-time image according to the real-time position of the power equipment in the displayed real-time image so as to carry out fault early warning of the fault type.

Optionally, before displaying the augmented reality image on the real-time image according to the real-time location of the power device in the displayed real-time image, the method further includes: acquiring a real-time image according to an image acquisition device; identifying the real-time image and determining whether the power equipment exists in the real-time image; and under the condition that the power equipment exists in the real-time image, identifying the real-time position of the power equipment in the real-time image according to the real-time image of the power equipment.

Optionally, when the power device is detected, acquiring the detection parameter of the power device includes: detecting the power equipment in a preset detection mode; under the condition that the power equipment is detected, detecting parameters of the power equipment are collected through a plurality of data sources, wherein the data sources comprise at least one sensor for collecting data of the power equipment and/or the environment where the power equipment is located.

Optionally, performing fault prediction on the power device according to the detection parameter, and obtaining a prediction result includes: inputting the detection parameters into a preset fault prediction function, and determining fault types and prediction probabilities, wherein the fault types are multiple, and the fault prediction function is used for determining the prediction probabilities of faults of different fault types of the power equipment under the detection parameters; and under the condition that the prediction probability of any fault type in the plurality of fault types reaches a preset probability threshold value, determining that the power equipment fails.

Optionally, when the prediction result represents the failure of the power device, determining the corresponding augmented reality image according to the failure type of the prediction result includes: determining a target fault type with a prediction probability reaching the preset probability threshold; acquiring a corresponding augmented reality image according to the identification of the target fault type, wherein the augmented reality image comprises at least one of the following components: images, animations, sounds, text; the augmented reality images of a plurality of fault types are preset and stored in the fixed path.

Optionally, before displaying the augmented reality image on the real-time image according to the real-time location of the power device in the displayed real-time image, the method further includes: acquiring real-time images in the inspection process in real time, wherein the real-time images comprise non-target images not containing image areas of the electric power equipment and target images containing the image areas of the electric power equipment; identifying the real-time image and determining whether the real-time image is the target image; if the real-time image is the target image, identifying the power equipment in the target image; and positioning and tracking the power equipment according to the real space coordinates of the data source of the target image.

Optionally, displaying the augmented reality image on the real-time image according to the real-time location of the power device in the displayed real-time image includes: converting the real space coordinates into virtual scene coordinates; displaying the augmented reality image on a corresponding target image according to the virtual scene coordinates; and under the condition that the real-time image is a non-target image, stopping tracking and canceling to display the augmented reality image.

In order to achieve the above object, according to another aspect of the present application, there is provided a fault recognition and early warning apparatus for an electric power device, including: the device comprises an acquisition module and a detection module, wherein the acquisition module is used for acquiring detection parameters of the electric power equipment under the condition that the electric power equipment is detected, the detection parameters comprise data of a plurality of data sources, and the data sources are used for carrying out data detection on the electric power equipment in multiple dimensions; the prediction module is used for predicting the faults of the power equipment according to the detection parameters to obtain a prediction result, wherein the prediction result is used for representing whether the identified faults exist or not and identifying the fault types of the faults; the determining module is used for determining a corresponding augmented reality image according to the fault type of the prediction result under the condition that the prediction result represents the fault of the power equipment; and the display module is used for displaying the augmented reality image on the real-time image according to the real-time position of the power equipment in the displayed real-time image so as to carry out fault early warning of the fault type.

According to another aspect of the present application, there is also provided a computer-readable storage medium storing a program, wherein the program executes the fault identification and warning method for an electric power device according to any one of the above aspects.

According to another aspect of the present application, there is also provided an electronic device, including one or more processors and a memory, where the memory is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the fault identification and warning method for an electric power device according to any one of the above items.

Through the application, the following steps are adopted: under the condition that the power equipment is detected, obtaining detection parameters of the power equipment, wherein the detection parameters comprise data of a plurality of data sources, and the plurality of data sources are used for carrying out data detection on the power equipment in multiple dimensions; performing fault prediction on the power equipment according to the detection parameters to obtain a prediction result, wherein the prediction result is used for representing whether the identified fault exists or not and identifying the fault type of the fault; determining a corresponding augmented reality image according to the fault type of the prediction result under the condition that the prediction result represents the fault of the power equipment; and displaying the augmented reality image on the real-time image according to the real-time position of the power equipment in the displayed real-time image so as to perform fault early warning of the fault type.

The method has the advantages that fault prediction is carried out through data of multiple dimensions of multiple data sources, fault prediction is carried out more comprehensively and accurately, corresponding augmented reality images are determined through predicted fault types, the real-time positions of power equipment in real-time images are displayed, the fault types of the power equipment are automatically identified and predicted according to the data of the multiple data sources, the data are displayed through the augmented reality images, the purpose of auxiliary identification of inspection personnel is achieved, the efficiency of fault identification of the power equipment is improved, the inspection personnel carry out early warning on the augmented reality images, the prompted power equipment faults are convenient to further check, the technical effect of the identification difficulty of the inspection personnel on the power equipment is reduced, and the problems that in the related technology, the power equipment is detected in the power equipment inspection process, people need to analyze data or images, or the detection data of a single dimension are relied on, whether the power equipment is in a fault is identified, the identification difficulty is high, the identification efficiency is low, and fault early warning cannot be carried out are solved.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application. In the drawings:

fig. 1 is a flowchart of a fault identification and early warning method for an electrical device according to an embodiment of the present application;

FIG. 2 is a schematic diagram of an overall architecture of an application scenario of an AR auxiliary power equipment fault identification system provided according to an embodiment of the present application;

FIG. 3 is a block diagram of an AR auxiliary power device fault identification system provided in accordance with an embodiment of the present application;

FIG. 4 is a schematic diagram of an AR image assisting architecture provided in accordance with an embodiment of the present application;

FIG. 5 is a schematic diagram of a display page for AR assisted identification of a fault condition provided in accordance with an embodiment of the present application;

FIG. 6 is a schematic diagram of a display page of an AR auxiliary display failure type and treatment plan provided according to an embodiment of the present application;

FIG. 7 is a schematic diagram of a workflow of AR assisted display of fault types and treatment plans provided according to an embodiment of the present application;

FIG. 8 is a schematic diagram of a workflow of power equipment inspection in conjunction with AR provided in accordance with an embodiment of the present application;

fig. 9 is a schematic diagram of a fault identification and early warning apparatus for an electrical device according to an embodiment of the present application;

fig. 10 is a schematic diagram of an electronic device provided according to an embodiment of the present application.

Detailed Description

It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.

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 drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be used. 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.

The invention is described below with reference to preferred implementation steps, and fig. 1 is a flowchart of a fault identification and early warning method for electrical equipment according to an embodiment of the present application, and as shown in fig. 1, the method includes the following steps:

step S101, acquiring detection parameters of the power equipment under the condition that the power equipment is detected, wherein the detection parameters comprise data of a plurality of data sources, and the plurality of data sources are used for carrying out multi-dimensional data detection on the power equipment;

step S102, performing fault prediction on the power equipment according to the detection parameters to obtain a prediction result, wherein the prediction result is used for representing whether the identified fault exists or not and identifying the fault type of the fault;

step S103, determining a corresponding augmented reality image according to the fault type of the prediction result under the condition that the prediction result represents the fault of the power equipment;

and step S104, displaying the augmented reality image on the real-time image according to the real-time position of the power equipment in the displayed real-time image so as to carry out fault early warning of the fault type.

Through the steps, fault prediction is carried out through data of multiple dimensions of multiple data sources, fault prediction is carried out more comprehensively and accurately, corresponding augmented reality images are determined through the predicted fault types, the real-time positions of the power equipment in the real-time images are displayed, the fault types of the power equipment are automatically identified and predicted according to the data of the multiple data sources, the fault types are displayed through the augmented reality images, the purpose of auxiliary identification of inspection personnel is achieved, the efficiency of fault identification of the power equipment is improved, the inspection personnel further check the fault of the power equipment with the augmented reality image prompt, the technical effect of the difficulty of the inspection personnel in identifying the power equipment is reduced, and the problems that in the related technology, the power equipment is detected in the inspection process of the power equipment, the data or the images need to be analyzed manually, or the detection data of a single dimension are relied on, whether the power equipment is in fault identification, the identification difficulty is high, the identification efficiency is low, and fault early warning cannot be carried out are solved.

The main body for executing the above steps may be a processor of the power detection device, or a server remotely connected to the power detection device, where the server may be a device with data processing and computing capabilities, and may be a calculator, a processor, or the like. Above-mentioned electric power check out test set can be for patrolling and examining handheld or wearing equipment of personnel, can remove along with the process of patrolling and examining personnel, removes the in-process, detects the electric power equipment that patrolling and examining personnel's passway. The power detection equipment can comprise an image acquisition device and a sensing device, and the data of different dimensions of the power equipment can be detected. However, in the related art, after the power detection device detects the data, it is necessary to manually identify and observe the data to determine whether the power device has a fault, or determine whether the power device has a certain fault or a fault hidden trouble by combining simple data statistics with a preset empirical threshold. However, the method has the problems of low efficiency and high identification difficulty.

In the embodiment, detection parameters of the power equipment are obtained under the condition that the power equipment is detected, then fault prediction is carried out on the power equipment according to the detection parameters, fault types of the power equipment with faults possibly existing are determined, corresponding augmented reality images are determined according to the fault types, the augmented reality images are displayed on the collected real-time images, the faults are automatically identified according to the collected parameters, the faults are displayed on the real-time images by the aid of the augmented reality images, the positions where the faults possibly occur and the images where the faults possibly occur are indicated, follow-up fault processing strategies can be provided by the aid of the augmented reality images, fault warning and other conditions can be provided.

Before the step 101, the power equipment may be detected in various ways, for example, image recognition may be performed, an image in the inspection process is collected in real time, and the real-time image is recognized to determine whether the real-time image has the power equipment. Meanwhile, the image acquired in real time can also be used for displaying the augmented reality image of the power equipment subsequently. The detection of the power equipment can also be performed by images obtained by other means, for example, electromagnetic wave imaging or infrared imaging, and then the imaging is detected. The electronic tag can also be used for distinguishing and identifying the electric power equipment, for example, the radio frequency identification technology RFID, the RFID electronic tag is arranged on the electric power equipment, the RFID detection device is arranged on the electric power detection equipment, and the RFID tag can be detected under the condition that the electric power detection equipment is close to the electric power equipment, so that the electric power equipment can be distinguished and identified.

The above-mentioned detection parameters of obtaining the power equipment can obtain the data of carrying out the multidimensional detection to the power equipment through the various detection devices of the power detection equipment. It should be noted that, data collection of the power equipment may be continuous, for example, a plurality of data collection devices are provided in the substation, and after the data collection devices collect the data, the collected data is stored in a fixed path or a remote server. In this case, the detection parameter of the power acquisition device may be acquired from a fixed path or a storage medium storing the parameter.

The data of the multiple data sources refers to data of different dimensions of the multiple data sources, and includes parameter data obtained by detecting the power equipment by the detection device, and may also include data of other data sources, for example, historical data obtained and stored from a server, weather data obtained from a network, power policy data, and the like.

Optionally, when the power device is detected, acquiring the detection parameter of the power device includes: detecting the power equipment in a preset detection mode; under the condition that the power equipment is detected, detection parameters of the power equipment are collected through a plurality of data sources, wherein the plurality of data sources comprise at least one sensor for collecting data of the power equipment and/or the environment where the power equipment is located.

The data of the multiple data sources have certain influence on judging whether the power equipment is likely to break down. For example, the parameter data collected by the detection device, including temperature, whether the shape is complete, voltage, current and other parameters, can directly or indirectly indicate the state of the detection device. The historical data comprises normal data, and the following development change conditions of the power equipment can be reflected to a certain extent through comparison of data characteristics, namely whether a fault is likely to occur or not. The weather data, the power policy data and the like also have influence on the power equipment, for example, the shell is aged and is overlapped with long-term rain, so that electric leakage can be caused, the power policy data indicates that the next month meets the peak of electricity utilization, the requirement on the power equipment is also improved, and then the current condition parameters of the power equipment are combined to determine whether the power equipment fails or not.

When analyzing the data of the plurality of data sources to determine whether the power equipment fails, the method may be performed by means of multi-metadata fusion analysis. Specifically, fault generation probability calculation is carried out through multi-source data, and equipment fault early warning is carried out through whether the calculated probability value exceeds an alarm threshold value. If the probability of fire alarm generated by the equipment A is P = F (x, y, z), x, y and z are three factors (sensing data, environmental data, policy data and the like) for generating the fire alarm, F () is a prediction function, when P is greater than T%, the equipment is subjected to fire alarm early warning, a real fire alarm image is enhanced on a system display device, acousto-optic early warning is carried out, a subsequent safety measure plan is given, and an inspector can work according to the plan to eliminate a dangerous case.

In the step S102, the power equipment is subjected to fault prediction according to the detection parameters to obtain a prediction result, and the occurrence probability of different faults can be predicted through a plurality of probability functions, so as to determine the probability of various faults occurring in the power equipment. And under the condition that the probability reaches a preset threshold value, determining that the type of fault of the power equipment can be predicted.

Optionally, the predicting the fault of the power device according to the detection parameter includes: inputting the detection parameters into a preset fault prediction function, and determining the fault types and the prediction probabilities, wherein the fault types are multiple, and the fault prediction function is used for determining the prediction probabilities of faults of different fault types of the power equipment under the detection parameters; and under the condition that the prediction probability of any fault type in the plurality of fault types reaches a preset probability threshold, determining that the power equipment fails.

In other embodiments, when the detection parameters perform fault prediction on the power equipment, the fault prediction may be performed in a machine learning manner, specifically, the detection parameters are input into a preset fault prediction function, and the fault type and the prediction probability are determined. The fault prediction function is a classifier function and is formed by training a plurality of groups of training data, wherein each group of training data comprises input detection parameters and labels for detecting whether the parameters correspond to faults or not and fault types.

And under the condition that the prediction probability of any fault type in the multiple fault types reaches a preset probability threshold value, determining that the power equipment fails. And under the condition that the prediction probabilities of the multiple fault types reach a preset probability threshold, determining that the multiple faults can occur to the power equipment.

The types of the faults may be various, for example, leakage, fire, damage, explosion, etc., and therefore, in order to perform different faults in the step S103, in the case that the prediction result represents the fault of the power equipment, the corresponding augmented reality image is determined according to the type of the fault of the prediction result.

It should be noted that the augmented reality image includes at least one of the following: images, animations, sounds, text. The augmented reality image can display the faults of different fault types in an animation mode, then parameters of the faults, such as temperature, availability and the like, can be displayed in text, and strategies for fault processing, such as circuit closing, covering removal, reinforcement and the like, can be displayed in text. And prompting a fault elimination mode and strategy to assist in fault elimination.

Optionally, when the prediction result represents a fault of the power device, determining the corresponding augmented reality image according to the fault type of the prediction result includes: determining a target fault type with a prediction probability reaching a preset probability threshold; acquiring a corresponding augmented reality image according to the identification of the target fault type, wherein the augmented reality image comprises at least one of the following: images, animations, sounds, text; the augmented reality images of a plurality of fault types are preset and stored in the fixed path. Because the augmented reality image is fixed, data such as image and audio exist, and unnecessary occupation of system space can be avoided by storing the data in a fixed path.

It should be noted that the augmented reality image of the fault can be displayed at each position of the real-time image to prompt the inspection personnel to notice that the fault may occur. However, in order to further prompt the fault occurrence position, an augmented reality image of the fault can be directly displayed in the display area of the electronic equipment, so as to better prompt the fault occurrence position and the fault occurrence type. The efficiency of the personnel of patrolling and examining discovery trouble is further improved, reduce the time that the personnel of patrolling and examining confirmed the trouble.

Before the augmented reality image is displayed on the real-time image, the real-time image needs to be acquired, and the display area and the position of the power equipment in the real-time image need to be determined. It should be noted that the collected real-time image may be collected by an image collecting device on the power detection device, and after the power detection device is detected, the image collecting device is started to collect the real-time image, and the real-time image moves along with the movement of the power detection device, that is, along with the movement of the inspection staff. The method comprises the steps of collecting a real-time image, then determining whether the power equipment exists in the real-time image through image recognition, and displaying an augmented reality image of the power equipment in a corresponding area and a corresponding position under the condition of existence.

Optionally, before the augmented reality avatar is displayed on the real-time image according to the real-time location of the power device in the displayed real-time image, the method further includes: acquiring real-time images in the inspection process in real time, wherein the real-time images comprise non-target images of image areas not containing the power equipment and target images of image areas containing the power equipment; identifying the real-time image and determining whether the real-time image is a target image; identifying the power equipment in the target image under the condition that the real-time image is the target image; and positioning and tracking the power equipment according to the real space coordinates of the data source of the target image.

The positioning and tracking of the power equipment according to the real space coordinates of the data source of the target image can be performed by a three-dimensional tracking registration technology, that is, after the power equipment is determined in the real-time image, the power equipment is continuously positioned and tracked, and the display position and the display area of the power equipment are continuously output under the condition that the power equipment is displayed in the subsequent real-time image.

The positioning and tracking means that the change angle of different real-time images and the pose of the acquisition equipment when the images are acquired are determined according to the objects in the different real-time images, and then the position and the display area of the power equipment in the previous real-time image are subjected to coordinate transformation according to the change angle and the pose to obtain the position and the display area in the next real-time image.

Optionally, displaying the augmented reality image on the real-time image according to the real-time location of the power device in the displayed real-time image includes: converting the real space coordinate into a virtual scene coordinate; displaying the augmented reality image on the corresponding target image according to the virtual scene coordinates; and under the condition that the real-time image is a non-target image, stopping tracking and canceling the display of the augmented reality image.

And displaying the augmented reality image on the display area of the corresponding electronic equipment through coordinate conversion. And canceling tracking of the electronic device and display of the augmented reality image in the event that the electronic device disappears from the real-time image. The misjudgment of the polling personnel is avoided, other equipment is mistaken as power equipment, and the error rate of the polling personnel is reduced.

It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.

It should be noted that the present application also provides an alternative embodiment, which is described in detail below.

The embodiment provides an AR auxiliary power failure recognition and early warning system and method, by combining AR technology auxiliary power equipment failure recognition and early warning, inspection workers can be helped to visually research failure points, accurately master failure reasons, assist in judging failure processing modes, and accurately warn disasters caused by failures. Through AR mixed reality technology, effectively combine intelligent patrol and inspection with artifical patrol and inspection, rationally reduce artifical uncertainty and the unpredictable who patrols and inspects, improve power equipment failure handling efficiency, supplementary operation personnel trouble early warning decision-making.

The purpose is in order to solve the detection factor singleness in the current power equipment intelligence inspection technology, can't realize this problem of calamity condition early warning that probably causes. Most of the prior art judges the fault condition of the equipment only by simple image recognition technology and by combining auxiliary data in a database, and does not comprehensively analyze the fault of the equipment by combining various factors such as specific equipment environment, equipment running condition and the like. Meanwhile, the disaster condition possibly caused by the obtained equipment fault is not predicted and analyzed, the condition is still very simple in the fault routing inspection process of the power system, and visual interaction cannot be realized to provide assistance for operators.

Fig. 2 is a schematic diagram of an overall architecture of an application scenario of the AR auxiliary power equipment fault identification system according to an embodiment of the present application, and as shown in fig. 2, the application scenario of the power fault identification and early warning system includes: the system comprises an AR auxiliary power failure identification and early warning system (a system front-end platform and a system central control platform), a power monitoring central control platform, a power line, power equipment, various sensors and the like. The AR-assisted power failure identification and early warning system mainly aims at power patrol inspection application scenes and carries out failure identification and early warning on power lines and power equipment.

The system utilizes image data information (mainly images with fault parts) collected from power lines and power equipment and data information of various sensors (including running data and environmental data of equipment such as infrared rays, vibration, temperature and humidity) to perform multi-source data analysis to complete fault identification, and meanwhile, multi-dimensional data is combined to realize fault prediction. After data analysis and prediction are completed, the AR technology is used for presenting fault identification information and prediction results on a front-end interface of the system in an imaging mode, electric power inspection personnel can check various auxiliary information (fault types, treatment plans, disaster risks and the like) in a man-machine interaction mode, accordingly, the positions of equipment faults, early warning information and corresponding follow-up safety measure plans of inspection operation personnel are prompted by an augmented reality means, the inspection personnel can work according to the plans, dangerous cases are eliminated, and inspection accuracy and efficiency are improved. The auxiliary field inspection operator improves the quick response and response capability to the fault.

Specifically, the fault prediction is realized by combining the multidimensional data, the fault generation probability can be calculated through the multisource data, and the equipment fault early warning is performed by judging whether the calculated probability value exceeds the alarm threshold value or not. If the probability of fire alarm generated by the equipment A is P = F (x, y, z), x, y and z are three factors for generating fire alarm, such as sensing data, environmental data, policy data and the like, F () is a prediction function, when P is greater than T%, the equipment is subjected to fire alarm early warning, a real fire alarm image is enhanced on a system display device, acousto-optic early warning is carried out, a subsequent safety measure plan is given, and an inspector can work according to the plan to eliminate dangerous cases.

In addition, the system can upload the fault information and the prediction result to the power monitoring center control platform, complete the instruction data transmission between the center control platform and the system, and complete the information interaction between the front-end field inspection worker and the background center control expert. The inspection personnel can obtain the remote guidance of experts and further auxiliary information if necessary through the instruction data transmission with the central control platform, thereby realizing the specific and accurate processing of the fault.

Fig. 3 is a structural diagram of an AR-assisted power equipment fault identification system according to an embodiment of the present application, and as shown in fig. 3, is a structural diagram of an AR-assisted power fault identification and early warning system, where the system includes a sensor module, an image acquisition module, a communication interface, a system front-end platform (including a multi-source data fusion module, an equipment positioning module, a power fault identification module, a power fault early warning module, and an AR image auxiliary module), a display module, and a system central control platform (including a fault monitoring module, an expert system module, and a data storage module).

The system has the key points that AR display of the early warning and prediction information of the equipment is added; the equipment can be positioned by using RFID (Radio Frequency Identification), and the equipment can be positioned in a contactless and unconscious manner, so that equipment information is provided for routing inspection and AR-assisted fault monitoring and early warning. Except for the use of fault detection, the multi-source data fusion most importantly carries out fault early warning, and besides sensing data, non-sensing data such as policy data, environmental data and the like are accessed.

The sensor module refers to data information of various sensors installed on power lines and equipment, such as various sensors used for collecting power health parameters, such as a vibration sensor, an infrared camera, a temperature and humidity sensor, a partial discharge detector and the like. Various sensors are in contact/non-contact with power lines and equipment, the operation conditions of the sensors in a long period of time are monitored, and the operation data of the equipment are recorded. The equipment operation data comprise electric power health parameters such as recent vibration frequency, infrared radiation conditions, temperature and humidity conditions and partial discharge conditions of the equipment, the operation conditions and environmental factors of the equipment are considered, subsequent multi-source data fusion analysis is conveniently achieved, and specific fault judgment and possible disaster prediction are made by combining actual environmental characteristics and equipment conditions. A large number of electric power health parameters are beneficial to obtaining more accurate analysis results when multi-source data fusion analysis is carried out subsequently, and analysis errors and prediction errors caused by insufficient parameters are avoided.

The image acquisition module is a module for acquiring visible light images of the power line and the equipment, and the specific image acquisition equipment is selected according to needs, such as a head-mounted camera can be adopted when the image acquisition is carried out on the equipment on the flat ground, and an unmanned aerial vehicle camera can be selected when the aerial work is carried out. The image data collected by the module is mainly used for subsequent image recognition, AR technology and the like.

The communication interface integrates the data information of the two modules and transmits the data information to a system front-end platform, and the data information can be in various forms such as wired, wireless and optical fiber.

The system front-end platform has the main functions of providing auxiliary work of fault monitoring for field inspection operators, realizing power fault identification and early warning by multi-dimensional information such as multi-mode data acquisition and fusion analysis and integrated equipment positioning coordinates, and assisting the field operators to mark and early warn faults discovered in inspection and potential safety hazards which may occur in an AR image display mode, and is convenient and intuitive, and the purposes of quickly reacting and coping with the faults are achieved. The inspection personnel accessible looks over the fault conditions, handles the scheme and the disaster risk that probably causes with front end platform human-computer interaction, and these three kinds of information appear with the form of characters or image, and the laminating is on the equipment image in the front end screen simultaneously.

The multi-source data fusion module mainly achieves fusion analysis of data collected in the system and multi-dimensional related data outside the system, such as historical data, weather information, policy information and other information, and provides data support for later power failure identification and early warning. Under different weather conditions, the equipment operation faults represented by the same equipment operation condition are not necessarily the same, and the required fault maintenance schemes are not the same. The accuracy of follow-up power failure identification and early warning can be improved by data information with multiple sources as far as possible.

The equipment positioning module is used for positioning and determining a target inspection line or equipment and providing support for inspecting geographic information. The equipment positioning module of the system adopts the RFID technology, RFID passive tags are pasted on the inspection line and the equipment, when an inspector arrives near the line or the equipment to be inspected, the equipment positioning module (an RFID reader-writer) can automatically identify the RFID passive tags, and the acting distance can be set according to the distance between the equipment and the actual distribution condition, so that the inspection line point or the equipment is automatically identified in a non-contact manner, and coordinate information is provided for the system. Meanwhile, the label also contains data information of the device itself, such as number, type, use time and the like. The identification information about the equipment is used for identifying the equipment and uploading subsequent faults, and the use time and other data related to the operation of the equipment are used for subsequent fault identification and early warning.

The power failure identification module is used for intelligently identifying and positioning power failure conditions, and is mainly used for identifying power lines or equipment by means of multi-source data fusion information and comprehensively judging fault information by combining specific equipment positioning information. The core of the multi-source data fusion analysis is an image recognition algorithm for analyzing image information acquired by an image acquisition module, after an image recognition result is obtained, the multi-source data fusion analysis is combined with multi-source data comprehensive analysis, such as weather conditions (temperature and humidity), equipment running conditions (vibration frequency), equipment surface faults (image data) and the like, finally, the fault conditions of the power circuit and the equipment are judged according to various condition factors, and different fault conditions correspond to different processing plans. The fault data from the power fault identification module, including fault conditions and treatment schedules, is transmitted to the AR auxiliary module for use.

The power failure early warning module is used for giving an alarm in advance for accidents possibly caused by power failures, and mainly carries out early warning on the failures exceeding a threshold index through failure identification information and a deep learning algorithm. Faults that exceed the criteria may cause various types of disasters, such as fires, electrical leaks, lightning strikes, etc., and the severity of the disaster may be related to the type and severity of the fault. For example, for an iron tower, a fault condition may be nesting of birds, corresponding possible disasters which may be caused later may be fires, and severity degrees of possible fires which are formed for different current environmental conditions are different, so that the power fault early warning module can also predict the size of the possible fire and is reflected by images in a subsequent AR auxiliary module. The electric power fault early warning module is combined with a deep learning algorithm and multi-source data to analyze and predict disaster conditions possibly caused by faults and display the disaster conditions in an AR image auxiliary module in an image mode. The early warning data (including possible disaster) obtained by the power failure early warning module will be transmitted to the AR auxiliary module for use.

The AR image auxiliary module is a functional module for carrying out mixed reality integration on power failure positioning and early warning information, and supports AR reality. The display module is a functional module for mixed reality display of the fault and the early warning information by the patrol operators, is convenient and intuitive, and achieves the purposes of quickly responding to and coping with the fault.

The main functions of the system central control platform are to realize power failure monitoring, provide service guidance for failure early warning and provide management support for the system. When the electric power inspection personnel inspect, the fault data can be automatically uploaded to the central control platform, and meanwhile, the central control platform can realize remote guidance through instruction interaction.

The fault monitoring module is used for visually displaying identification and early warning data transmitted back by a system front-end platform, and power inspection fault monitoring is achieved. The expert system module is a module for providing multi-dimensional information and processing schemes for the system. The system front-end platform can provide multi-dimensional related data for the system front end according to a specific inspection scene, and provides data support for power failure identification and early warning; in addition, after fault identification and early warning are completed, the central control platform is requested to perform the next work, if the next work is performed at once or after the next work, the expert system module issues a work instruction to the inspection site, and real-time data interaction reaction is performed through the front-end platform of the system to complete remote work guidance. The data storage module stores all the inspection information, completes archiving and can be used for follow-up query and analysis.

Fig. 4 is a schematic diagram of an AR image-assisted architecture provided according to an embodiment of the present application, and as shown in fig. 4, is a structural diagram of an AR assistance module, where the structural diagram includes three parts, namely data information and control system, and a display, where image data is derived from an initial image acquisition module, and fault data and early warning data are respectively derived from a power failure recognition module and a power failure early warning module, the control system implements processing on the data, and the display displays a processed data image on a screen.

The image recognition module mainly realizes image recognition processing of image data. The module acquires the characteristic points of the image, compares the characteristic points with the image characteristic points stored in the database to realize a local identification function, and then delivers the identification result to the three-dimensional tracking registration module.

The three-dimensional tracking registration module can match image information acquired by the camera with an ImageTarget (a carrier of an image in a virtual space) object in a virtual space, perform coordinate positioning and image size matching on the image in a real space in the virtual space, and the image recognition module and the three-dimensional tracking registration module are both supported by corresponding image recognition and tracking algorithms (for example, the Vuforia Engine software can realize).

The virtual-real combination module displays the acquired fault condition, processing plan and disaster risk in the form of characters, images and the like, and sets AR display information of the images, such as size, color, relative position, particle animation setting and the like. The fault condition and the treatment plan are displayed in the form of characters, different disaster conditions are represented as different images, for example, a fire is represented in the form of flames, a lightning stroke is represented in the form of lightning, and the size of the image represents the predicted severity degree of the disaster. The generation and detail setting of the image are realized by setting parameters, and the parameters are predicted disaster conditions obtained by the power failure early warning module.

After the setting is finished, an information object and an image recognition (Imagetarget) object are bound to realize that virtual information follows a target image, after the setting is finished, an information pushing module sets interaction logic of an information button and display logic of the information, the two modules are supported by virtual space information editing capacity (realized by Unity3D software), the size, the color, the particle object and the like of the information in an actual project are set in a real-time 3D interaction content creation and operation platform (such as Unity 3D) viewing view, the relation between a position coordinate and the object is set by a script, the information button logic is set by trigger logic of the button object, the button simultaneously controls the display logic of the information, and after the information pushing module finishes the interaction and display logic of the information, a control system transmits the final image information to a display to finish a fault detection task. The image and the text information on the inspection personnel accessible display are audio-visual to know the fault condition of power equipment, handle the scheme and the disaster condition that probably causes to supplementary inspection personnel carry out the fault handling.

The information push module mainly realizes the logic setting of buttons of man-machine interaction and the corresponding information display. When the inspection personnel clicks the fault information near the equipment on the screen, the corresponding processing plan and the disaster situation image are displayed, and the original fault information is restored by clicking again, wherein the steps before and after clicking are shown in fig. 5 and 6. Fig. 5 is a schematic diagram of a display page for assisting the AR in identifying a fault condition provided according to an embodiment of the present application, and fig. 6 is a schematic diagram of a display page for assisting the AR in displaying a fault type and a treatment plan provided according to an embodiment of the present application.

Fig. 7 is a schematic diagram of a workflow of the AR-assisted display of the fault type and the processing plan provided according to the embodiment of the present application, and as shown in fig. 7, is a workflow diagram of an AR-assisted module, and the specific flow is as follows:

step one, identifying a fault image. The software moves a camera of the equipment to obtain a fault image of the target power equipment, extracts a characteristic value of the image and performs characteristic matching with a reference image in a database to realize the identification of the fault image;

and step two, three-dimensional tracking registration of the fault image. Acquiring a space coordinate of an identification image in a real scene through a registration program built in software, performing conversion calculation on the coordinate in the virtual scene and the coordinate in the real scene, and accurately positioning preset fault information in the virtual scene to a target image;

and step three, displaying fault information. The software moves the screen of the equipment, the image which is obtained by the combination of the real scene and the virtual scene captured by the camera in the three-dimensional registration is displayed on the screen, the user observes and clicks and confirms fault information, the software displays the damage possibly caused by the fault, and the software realizes the fault identification function;

and step four, displaying a fault processing plan and disaster risks. After the user determines that the information displayed in the previous step is correct by clicking a button on a screen, the software positions the fault processing plan and the predicted disaster risk in the virtual scene on the target image through the three-dimensional registration program again, and the user can visually observe the fault processing plan corresponding to the fault and the disaster risk condition possibly caused by the fault through screen display, know the processing method of the next step and obtain early warning, and when the user clicks and confirms the fault processing plan, the software deletes the fault hazard information, so that the software realizes the fault processing mode visualization function;

and step five, when the camera loses the target, the software can automatically delete the information for identifying the image, delete various information combined with the image and close the AR function except the image identification function, so that the identification efficiency is improved, and the information is accurately pushed only at the fault.

Fig. 5 is a schematic diagram of a display page of an AR-assisted fault recognition device according to an embodiment of the present disclosure, and as shown in fig. 5, the display page is an AR-assisted fault display image, where an AR image-assisted module displays fault information of a device beside an image of a faulty device in a text manner, and frames a faulty part in a square form, so that an inspector can conveniently and accurately find a faulty part and know a fault existing in the device. As for towers, they may have the failure of having bird nests growing on them, which may lead to a fire risk. The inspector can click the fault information on the screen and then change to fig. 6.

Fig. 6 is a schematic diagram of a display page of the AR-assisted display failure type and treatment plan provided according to the embodiment of the present application, and as shown in fig. 6, is a display diagram of the AR-assisted treatment plan and disaster risk. After clicking the fault information shown in fig. 5, the fault information is hidden, and then the processing plan is displayed in a text form, and the possible risk of disaster is displayed in an image form, all displayed near the frame of the fault portion. Different disasters are represented by different images, such as fire using flames, lightning using lightning, and image size representing the severity of the risk of the disaster that may result. After the patrol personnel click the processing plan, the processing plan and the disaster risk image are hidden and restored to the AR auxiliary fault condition display shown in the figure 5.

Fig. 8 is a schematic diagram of a workflow of power equipment inspection with AR according to an embodiment of the present application, and as shown in fig. 8, is a workflow diagram of an AR-assisted power failure identification and early warning system, and a specific flow is as follows:

step one, the polling personnel arrive in a certain range of the polling equipment and start polling.

And step two, acquiring data. The sensor module and the image acquisition module transmit sensor data and image data of equipment to equipment carried by an inspector through a communication interface, and an equipment positioning module in the equipment reads the position of the equipment and data information of the equipment;

and step three, multi-source data fusion analysis. The multi-source data fusion module performs fusion analysis on the acquired data in the system and multi-dimensional related data (such as historical data, weather information, policy information and the like) information outside the system, and provides data support for later power failure identification and early warning;

and fourthly, identifying and early warning the power failure. The power failure recognition module and the power failure early warning module respectively analyze the data to obtain the failure information, the processing plan and the disaster risk of the power equipment and the line, and transmit the data to the AR image auxiliary module;

and step five, identifying, tracking and displaying the image. The AR image auxiliary module identifies images, carries out three-dimensional tracking registration on the images and fault information (fault information, processing plans, disaster risks and the like), and finally displays images combined by virtual and real images;

and step six, man-machine interaction. The inspection personnel accessible clicks the screen and realizes the demonstration and hide of information, and the equipment trouble condition, the processing scheme and the calamity risk are known directly perceivedly. Meanwhile, instructions are interacted with the central control center to obtain guidance and work of the next step;

and step seven, deleting the image binding. When the camera loses the target, the software automatically deletes the information for identifying the image, deletes various information combined with the image, and closes the AR function except the image identification function.

Step eight, finishing the inspection. After the polling personnel finish polling the current equipment, the polling personnel leave the equipment within a certain range to perform polling of the next equipment.

This embodiment patrols and examines with AR technique and electric power and combines together to the supplementary personnel of patrolling and examining of form of AR helmet carry out fault detection and discernment, and the supplementary personnel of patrolling and examining of help liberate both hands, have reduced high altitude construction's danger and the potential safety hazard that probably exists, improve and patrol and examine efficiency, reduce and patrol and examine the cost, reduce the uncertainty and the unpredictable nature of artifical detection. This embodiment has increased multiple possible equipment trouble detection factor on current AR based fault detection technique, analyzes from the many-sided detection data of equipment, can obtain more comprehensive concrete accurate equipment trouble condition, helps promoting the intelligent accuracy of patrolling and examining the system. This embodiment passes through the display with the possible reason of trouble and the various calamities that the trouble probably caused visual, carries out further prediction to the influence condition of calamities simultaneously, helps patrolling and examining personnel to carry out deeper understanding to the emergency of equipment trouble to rational distribution overhauls the resource, in time prevents the loss of property of bigger degree.

The embodiment of the present application further provides a fault identification and early warning device for an electrical device, and it should be noted that the fault identification and early warning device for an electrical device according to the embodiment of the present application may be used to execute the fault identification and early warning method for an electrical device according to the embodiment of the present application. The fault identification and early warning device for the power equipment provided by the embodiment of the application is introduced below.

Fig. 9 is a schematic diagram of a fault identification and early warning apparatus for electrical equipment according to an embodiment of the present application, and as shown in fig. 9, the apparatus includes: an acquisition module 92, a prediction module 94, a determination module 96, and a display module 98, which are described in detail below.

The obtaining module 92 is configured to obtain detection parameters of the electrical device when the electrical device is detected, where the detection parameters include data of multiple data sources, and the multiple data sources are used for performing data detection on the electrical device in multiple dimensions; a prediction module 94, connected to the obtaining module 92, configured to perform fault prediction on the electrical equipment according to the detection parameters to obtain a prediction result, where the prediction result is used to characterize whether the fault is identified and identify a fault type of the fault; a determining module 96, connected to the predicting module 94, for determining a corresponding augmented reality image according to a fault type of the prediction result when the prediction result represents a fault of the power equipment; and the display module 98 is connected with the determining module 96 and is used for displaying the augmented reality image on the real-time image according to the real-time position of the electric equipment in the displayed real-time image so as to carry out fault early warning of the fault type.

The utility model provides a power equipment's fault identification and early warning device, carry out the fault prediction through the data of a plurality of dimensions of a plurality of data sources, more comprehensive and accurate carry out the fault prediction, and confirm the augmented reality image that corresponds through the fault type of prediction, show the real-time position of power equipment in the real-time image, reached automatic data according to a plurality of data sources, the fault type to power equipment discerns the prediction, and show through the augmented reality image, realize the purpose to patroller's auxiliary identification, the efficiency of power equipment fault identification has been improved, patroller carries out further the verification to the power equipment trouble that has the suggestion of augmented reality image, the technical effect of patroller's the identification degree of difficulty to power equipment has been reduced, and then detected power equipment at the power equipment in-process in the correlation technique, need artificial analysis data or image, or rely on the detection data of single dimension, whether discernment power equipment breaks down, there is the discernment degree of difficulty big, the discernment is low in efficiency, and can't carry out the problem of fault early warning.

The fault recognition and early warning device for the power equipment comprises a processor and a memory, wherein the acquiring module 92, the predicting module 94, the determining module 96, the displaying module 98 and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.

The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. The kernel can be set to be one or more than one, and the problems that in the related technology, data or images need to be artificially analyzed when the power equipment is detected in the inspection process of the power equipment, or whether the power equipment fails or not can be identified depending on detection data with a single dimensionality, the identification difficulty is high, the identification efficiency is low, and failure early warning cannot be carried out are solved by adjusting the kernel parameters.

The memory may include volatile memory in a computer readable medium, random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.

An embodiment of the present invention provides a computer-readable storage medium on which a program is stored, the program implementing a fault identification and early warning method of an electric power device when executed by a processor.

The embodiment of the invention provides a processor, which is used for running a program, wherein a fault identification and early warning method of electric equipment is executed when the program runs.

Fig. 10 is a schematic diagram of an electronic device according to an embodiment of the present application, and as shown in fig. 10, an embodiment of the present application provides an electronic device 100, where the device includes a processor, a memory, and a program stored in the memory and executable on the processor, and the processor implements the steps of the fault identification and warning method for any one of the above-mentioned electrical devices when executing the program.

The device herein may be a server, a PC, a PAD, a mobile phone, etc.

The present application also provides a computer program product adapted to execute a program initializing the steps of the fault identification and warning method as described above for any of the electrical devices when executed on the fault identification and warning device of the electrical device.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable power device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable power device, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable power device to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable power device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer implemented process such that the instructions which execute on the computer or other programmable device provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of additional identical elements in the process, method, article, or apparatus comprising the element.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.

The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art to which the present application pertains. Any modification, equivalent replacement, improvement or the like made within the spirit and principle of the present application shall be included in the scope of the claims of the present application.

Claims

1. A fault identification and early warning method for power equipment is characterized by comprising the following steps:

under the condition that the power equipment is detected, obtaining detection parameters of the power equipment, wherein the detection parameters comprise data of a plurality of data sources, and the data sources are used for carrying out data detection on the power equipment in a plurality of dimensions;

performing fault prediction on the power equipment according to the detection parameters to obtain a prediction result, wherein the prediction result is used for representing whether the identified fault exists or not and identifying the fault type of the fault;

determining a corresponding augmented reality image according to the fault type of the prediction result under the condition that the prediction result represents the fault of the power equipment;

and displaying the augmented reality image on the real-time image according to the real-time position of the power equipment in the displayed real-time image so as to carry out fault early warning of the fault type.

2. The method of claim 1, wherein the augmented reality avatar is displayed on the real-time image prior to displaying the augmented reality avatar on the real-time image according to a real-time location of the electrical device in the displayed real-time image, the method further comprising:

acquiring a real-time image according to an image acquisition device;

identifying the real-time image, and determining whether the power equipment exists in the real-time image;

and under the condition that the power equipment exists in the real-time image, identifying the real-time position of the power equipment in the real-time image according to the real-time image of the power equipment.

3. The method of claim 2, wherein, in the event that a power device is detected, obtaining detection parameters of the power device comprises:

detecting the power equipment in a preset detection mode;

under the condition that the power equipment is detected, acquiring detection parameters of the power equipment through a plurality of data sources, wherein the plurality of data sources comprise at least one sensor for acquiring data of the power equipment and/or the environment where the power equipment is located.

4. The method of claim 3, wherein predicting the failure of the power equipment based on the detected parameters comprises:

inputting the detection parameters into a preset fault prediction function, and determining a plurality of fault types and prediction probabilities, wherein the fault types are used for determining the prediction probabilities of faults of different fault types of the power equipment under the detection parameters;

and under the condition that the prediction probability of any fault type in the plurality of fault types reaches a preset probability threshold, determining that the power equipment fails.

5. The method of claim 4, wherein, in the event that the predicted outcome characterizes the power equipment fault, determining a corresponding augmented reality image according to the fault type of the predicted outcome comprises:

determining a target fault type with a prediction probability reaching the preset probability threshold;

acquiring a corresponding augmented reality image according to the identification of the target fault type, wherein the augmented reality image comprises at least one of the following components: images, animations, sounds, text; the augmented reality images of a plurality of fault types are preset and stored in the fixed path.

6. The method of claim 5, wherein the augmented reality representation is displayed on the real-time image prior to displaying the augmented reality representation on the real-time image based on a real-time location of the electrical device in the displayed real-time image, the method further comprising:

acquiring a real-time image in the inspection process in real time, wherein the real-time image comprises a non-target image not containing an image area of the power equipment and a target image containing the image area of the power equipment;

identifying the real-time image, and determining whether the real-time image is the target image;

if the real-time image is the target image, identifying the power equipment in the target image;

and positioning and tracking the power equipment according to the real space coordinates of the data source of the target image.

7. The method of claim 6, wherein displaying the augmented reality representation on the real-time image based on a real-time location of the electrical device in the displayed real-time image comprises:

converting the real space coordinates into virtual scene coordinates;

displaying the augmented reality image on a corresponding target image according to the virtual scene coordinates;

and under the condition that the real-time image is a non-target image, stopping tracking and canceling to display the augmented reality image.

8. The utility model provides a power equipment's fault identification and early warning device which characterized in that includes:

the device comprises an acquisition module, a detection module and a processing module, wherein the acquisition module is used for acquiring detection parameters of the power equipment under the condition that the power equipment is detected, the detection parameters comprise data of a plurality of data sources, and the data sources are used for carrying out data detection on the power equipment in a plurality of dimensions;

the prediction module is used for predicting the faults of the power equipment according to the detection parameters to obtain a prediction result, wherein the prediction result is used for representing whether the identified faults exist or not and identifying the fault types of the faults;

the determining module is used for determining a corresponding augmented reality image according to the fault type of the prediction result under the condition that the prediction result represents the fault of the power equipment;

and the display module is used for displaying the augmented reality image on the real-time image according to the real-time position of the power equipment in the displayed real-time image so as to carry out fault early warning of the fault type.

9. A computer-readable storage medium characterized in that the storage medium is used for storing a program, wherein the program executes the fault identification and early warning method of an electric power device according to any one of claims 1 to 7.

10. An electronic device comprising one or more processors and memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of fault identification and warning of an electrical power device of any of claims 1-7.