CN112367400A - Intelligent inspection method and system for power internet of things with edge cloud coordination - Google Patents
Intelligent inspection method and system for power internet of things with edge cloud coordination Download PDFInfo
- Publication number
- CN112367400A CN112367400A CN202011261336.5A CN202011261336A CN112367400A CN 112367400 A CN112367400 A CN 112367400A CN 202011261336 A CN202011261336 A CN 202011261336A CN 112367400 A CN112367400 A CN 112367400A
- Authority
- CN
- China
- Prior art keywords
- information
- things
- edge
- unit
- calculation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
- G07C1/20—Checking timed patrols, e.g. of watchman
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method and a system for intelligent inspection of an electric power internet of things with edge cloud coordination, which comprises the steps of collecting information collected by an unmanned aerial vehicle; performing convolution operation on the collected information to extract characteristic information, and transmitting the characteristic information and the total number of the serial numbers by using a 5G core network; carrying out full connection operation by using the feature extraction information and the serial number, and judging abnormal features; performing category identification on the information of the abnormal features; and outputting the abnormal information and the information category to finish the inspection. The hardware resource difference of each level is fully utilized, a task allocation scheme with unified efficiency and capacity is realized, the computing capacity of the whole system is accelerated, the hardware resource utilization rate and the inspection working efficiency of all equipment are ensured, the problem of large calculated amount of a unilateral server is solved, and better economic benefit is brought.
Description
Technical Field
The invention relates to the technical field of power internet of things, in particular to a method and a system for intelligently patrolling power internet of things with edge cloud coordination.
Background
The electric power system is an essential important component part forming the rapid operation of the current society, and under the promotion of the advanced development of communication technology, the informatization level of the electric power system and the use efficiency of basic equipment are effectively improved by integrating the electric power internet of things formed by the electric power system and the basic communication equipment system. In order to ensure the stability of information sharing and data transmission, fault maintenance and repair inspection of the power line of the power internet of things are also essential.
The power line inspection task is patrolled and examined the mode transition by the manual work to unmanned aerial vehicle in recent years, compares in the manual work and patrols and examines, because power line distribution point topography is complicated, area coverage is wide, and unmanned aerial vehicle patrols and examines and can reduce workman working strength better, reduces workman risk scheduling problem, can check out power line performance defect and damage problem more conveniently.
The common unmanned aerial vehicle inspection mode is that an unmanned aerial vehicle shooting video is directly retrieved manually, and the method needs workers to detect the position of a problematic power line from a disordered shooting scene, so that the time efficiency is low; the other type is that the unmanned aerial vehicle transmits video stream to the server, and the machine assists workers to complete inspection in a cooperative manner, so that the unmanned aerial vehicle is a more extensive inspection mode. Generally, an image processing technology and anomaly detection based on a neural network are used, after an unmanned aerial vehicle transmits a picture to a server through a network module, the server performs linear detection on the shot image, uses an edge detection algorithm to find out the picture position of a power line according to a marked straight line, uses a noise filtering algorithm to complete an image enhancement task, then shifts to the neural network to perform target detection on the power line, and uses a clustering or segmentation method to determine whether the power line is abnormal or not. Firstly, the calculation requirement is high, and the server is used for loading the target detection model to calculate the picture characteristics, so that a huge calculation amount is brought, and the server is required to have a considerable hardware configuration to complete the calculation task of the whole system. Secondly, the treatment efficiency is low. Because the picture that the server was handled is derived from the video that unmanned aerial vehicle shot at work, so unmanned aerial vehicle's mobility determines entire system's operating range, and the unilateral quantity that increases unmanned aerial vehicle only can distribute all calculation tasks to the server, can't make full use of unmanned aerial vehicle's throughput, and third, detection capability is restricted. Problems encountered in power line inspection are diversified, such as foreign matter suspension, fouling, bird nest, vegetation covering and the like, in order to improve the diversity of identification tags, a deeper neural network is needed, and a larger calculation requirement is brought; therefore, it is necessary to improve management efficiency and fully utilize hardware resources.
Disclosure of Invention
This section is for the purpose of summarizing some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. In this section, as well as in the abstract and the title of the invention of this application, simplifications or omissions may be made to avoid obscuring the purpose of the section, the abstract and the title, and such simplifications or omissions are not intended to limit the scope of the invention.
The invention is provided in view of the problems that the prior optimization distribution of the whole framework is too single, the mobile computing module is not completely cut and the edge computing is not uniform.
Therefore, the technical problem solved by the invention is as follows: the optimization allocation of the whole framework is too single, the cutting of the mobile computing module is incomplete, and the edge computing is not uniform.
In order to solve the technical problems, the invention provides the following technical scheme: collecting information collected by the unmanned aerial vehicle; carrying out convolution operation on the information of the mobile phone to extract characteristic information, and transmitting the characteristic information and the total number of the serial numbers by using a 5G core network; carrying out full connection operation by using the feature extraction information and the serial number, and judging abnormal features; performing category identification on the information of the abnormal features; and outputting the abnormal information and the information category to finish the inspection.
The invention relates to a preferable scheme of a power Internet of things intelligent inspection method based on edge cloud cooperation, wherein the method comprises the following steps: the total number of the sequence numbers comprises the following formula:
where l is the input image length, w is the input image width, k is the convolution kernel size, and m is the augmentation coefficient.
The invention relates to a preferable scheme of a power Internet of things intelligent inspection method based on edge cloud cooperation, wherein the method comprises the following steps: and the full-connection operation comprises the steps of cutting the characteristic information in the dimension direction according to the serial number, performing full-connection operation calculation on the characteristic model, and outputting the probability value of each label.
The invention relates to a preferable scheme of a power Internet of things intelligent inspection method based on edge cloud cooperation, wherein the method comprises the following steps: the cutting method comprises setting the feature extraction information as a multi-dimensional matrix { x }o,yo,zoAnd said xo,yo,zoSatisfy xn＝xoyoFor the serial number
Cut out information MiComprises the following steps:
wherein: x is the number ofoIs the length of the matrix, yoIs the width of the matrix, zoIs a matrixDimension.
The invention relates to a preferable scheme of a power Internet of things intelligent inspection method based on edge cloud cooperation, wherein the method comprises the following steps: the feature model includes tag types of the feature model including powerline, lawn, sky, tower, and unknown types.
The invention relates to a preferable scheme of a power Internet of things intelligent inspection method based on edge cloud cooperation, wherein the method comprises the following steps: the unknown type comprises the label probability value of the unknown type is the maximum, the serial number of the unknown type is marked, and the labeled signal information is subjected to category identification.
The invention relates to a preferable scheme of a power Internet of things intelligent inspection method based on edge cloud cooperation, wherein the method comprises the following steps: the performing of the category identification comprises
The number of the characteristic regions in each row,
in order to receive the value of the sequence number,
is a serial number xiAnd then returning the pixel point position of the characteristic region, wherein the calculation formula is as follows:
and cutting out a characteristic region picture according to the pixel point position, carrying out identification operation calculation of a category model, and outputting specific type information of the picture.
The invention relates to a preferable scheme of a power Internet of things intelligent inspection method based on edge cloud cooperation, wherein the method comprises the following steps: the collected information comprises image information, positioning information and time information.
The invention solves another technical problem that: the intelligent power Internet of things inspection system with the edge cloud coordination is provided, corresponding computing tasks are designed according to actual use scenes aiming at different layers, and therefore a task scheduling scheme of the whole system is optimized
In order to solve the technical problems, the invention provides the following technical scheme: a power Internet of things intelligent inspection system with edge cloud cooperation comprises a mobile computing module, a characteristic model and a data processing module, wherein the mobile computing module is used for acquiring data information and completing convolution part computation of the characteristic model; the edge calculation module is connected with the mobile calculation module through a 5G network and used for judging the abnormal characteristics of the information acquired by the mobile calculation module, and comprises a user plane unit of a 5G core network and a mobile edge calculation server, wherein the user plane unit of the 5G core network is used for checking the transmission of the acquired information, transmitting the information to the mobile edge calculation server for edge calculation, judging the abnormal characteristics of the information and transmitting a characteristic information label to the edge calculation module; the cloud computing module is connected with the mobile computing module through a 5G network and used for classifying the abnormal features and outputting the abnormal information and the abnormal features, the cloud computing module comprises a cloud server and a console, the cloud server is used for finishing the classification of the feature information and transmitting the classified information to the console, and the console is used for monitoring and making decisions of the overall system.
As an optimal scheme of the intelligent inspection system of the power internet of things with edge cloud coordination, the invention comprises the following steps: the mobile computing module comprises an unmanned aerial vehicle unit, a collecting unit, a computing unit, a storage unit and a 5G communication unit, wherein the unmanned aerial vehicle unit is used for providing the motion capability of the whole mobile computing module, the collecting unit is used for collecting image information and positioning information shot by the unmanned aerial vehicle unit currently, the computing unit is used for comparing the collected information of the collecting unit with the characteristic information labels calculated by the edge computing module, performing preliminary computation and providing corresponding characteristic extraction information, the storage unit is used for storing the collected information of the collecting unit and the extraction information given by the computing unit, and the 5G communication unit is used for connecting the edge computing module and the cloud computing module to perform mutual transmission of the information in the storage unit.
The invention has the beneficial effects that: the management efficiency is high, each layer of computing module has own computing task and transmission task, and compared with the characteristics of bidirectional transmission and unilateral computing task of the unmanned aerial vehicle and the server, the management or adjustment of the tasks can be more conveniently performed, and the management capability of the whole system is improved; the method of the invention fully utilizes the hardware resource difference of each level, realizes a task allocation scheme with unified efficiency and capacity, accelerates the computing capacity of the whole system, ensures the hardware resource utilization rate and the inspection work efficiency of all equipment, solves the problem of large computation amount of a unilateral server, and brings better economic benefit; the routing inspection real-time performance is good, the mobile computing module and the edge computing module are only used for abnormal detection and local picture cutting of images, the abnormal problem cannot be continuously detected in a normal picture area, the calculated amount of the model is greatly reduced, and in addition, the delay problem in the process of model weight transmission is reduced by utilizing a 5G network to transmit data, so that the working real-time performance of the system is ensured; the class identification label is wide, and whether high in the clouds calculation module need go to detect has unusual characteristics, and whole class model all is used for the classification of unusual label, has reduced model structure redundancy by a wide margin, through the combination of high performance server and deep neural network, compares unilateral server, can have more computing power to be used for label identification.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise. Wherein:
fig. 1 is a schematic flow chart of a smart inspection method for an electric power internet of things with edge cloud coordination according to a first embodiment of the invention;
fig. 2 is a working schematic diagram of a mobile computing module of a smart inspection system for an internet of things with edge cloud coordination according to a second embodiment of the present invention;
fig. 3 is a working schematic diagram of an edge computing module of the intelligent inspection system for an internet of things with edge cloud coordination according to the second embodiment of the present invention;
fig. 4 is a system working schematic diagram of an intelligent inspection system of an electric power internet of things with edge cloud coordination according to a second embodiment of the invention;
fig. 5 is a schematic diagram of a system work flow of the intelligent inspection system for the power internet of things with edge cloud coordination according to the second embodiment of the invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, specific embodiments accompanied with figures are described in detail below, and it is apparent that the described embodiments are a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present invention, shall fall within the protection scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those specifically described and will be readily apparent to those of ordinary skill in the art without departing from the spirit of the present invention, and therefore the present invention is not limited to the specific embodiments disclosed below.
Furthermore, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
The present invention will be described in detail with reference to the drawings, wherein the cross-sectional views illustrating the structure of the device are not enlarged partially in general scale for convenience of illustration, and the drawings are only exemplary and should not be construed as limiting the scope of the present invention. In addition, the three-dimensional dimensions of length, width and depth should be included in the actual fabrication.
Meanwhile, in the description of the present invention, it should be noted that the terms "upper, lower, inner and outer" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation and operate, and thus, cannot be construed as limiting the present invention. Furthermore, the terms first, second, or third are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The terms "mounted, connected and connected" in the present invention are to be understood broadly, unless otherwise explicitly specified or limited, for example: can be fixedly connected, detachably connected or integrally connected; they may be mechanically, electrically, or directly connected, or indirectly connected through intervening media, or may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Example 1
Referring to fig. 1, a first embodiment of the present invention provides a side-cloud-coordinated intelligent inspection method for an electric power internet of things, including:
s1: and collecting information collected by the unmanned aerial vehicle. It should be noted that the acquired information includes image information, positioning information, and time information.
S2: and carrying out convolution operation on the information of the mobile phone to extract the characteristic information, and transmitting the characteristic information and the total number of the serial numbers by using a 5G core network. In which it is to be noted that,
the total number of serial numbers includes, and the calculation formula of the total number of serial numbers is as follows:
where l is the input image length, w is the input image width, k is the convolution kernel size, and m is the augmentation coefficient.
S3: and performing full-connection operation by using the feature extraction information and the serial number, and judging abnormal features. In which it is to be noted that,
the full-connection operation comprises the steps of cutting the feature information in the dimension direction according to the serial number, performing full-connection operation calculation on the feature model, and outputting probability values of the labels;
further, the cutting method includes setting the feature extraction information as a multi-dimensional matrix { x }o,yo,zoAnd x iso,yo,zoSatisfy xn＝xoyoFor the serial number
Cut out information MiComprises the following steps:
wherein: x is the number ofoIs the length of the matrix, yoIs the width of the matrix, zoIs the matrix dimension; the feature models include tag types of the feature models including powerline, lawn, sky, tower, and unknown types.
S4: and identifying the category of the information of the abnormal features. In which it is to be noted that,
the unknown type comprises the label probability value of the unknown type is the maximum, the serial number of the unknown type is marked, and the labeled signal information is subjected to category identification.
S5: and outputting abnormal information and information types to finish the inspection. In which it is to be noted that,
the class identification comprises
The number of the characteristic regions in each row,
in order to receive the value of the sequence number,
is a serial number xiAnd then returning the pixel point position of the characteristic region, wherein the calculation formula is as follows:
and cutting out a characteristic region picture according to the position of the pixel point, carrying out identification operation calculation on the category model, and outputting specific type information of the picture.
In order to better verify and explain the technical effect adopted in the method, a visual inspection method based on the internet of things is selected for comparison test in the embodiment, and the test result is compared by means of scientific demonstration to verify the real effect of the method;
the method is a side-cloud-coordinated intelligent inspection method for the Internet of things of the electric power, three power line experiment groups with different lengths are selected to verify the method, namely power lines with the lengths of 1km, 5km and 10km respectively, wherein the traditional visual inspection method based on the Internet of things is used, information of the power lines is acquired and stored in modes of photographing, video recording and the like, and an inspector remotely checks and analyzes the acquired information to judge whether an abnormal condition occurs; by using the method, the information is collected by the unmanned aerial vehicle, the information of the abnormal condition is selected by utilizing edge calculation, the image is segmented, the type of the abnormal condition is identified, and the result is output; after three groups of power line experimental groups are patrolled by two methods, testing the patrolling time of the two methods by using MATLB software, wherein the testing result takes hours as an index, and is shown in the following table 1: experimental results of power line experimental group
As can be seen from table 1, in the three sets of experimental data, the two inspection methods are used along with the increase of the power line, but when the traditional visual inspection method is used, the inspection time is obviously shortened by using the method of the present invention compared with the inspection time used by using the method of the present invention, and especially when the inspection range is large, the shortening time is more, the method of the present invention only performs local cutting on abnormal images, reduces the calculated amount of the system, and improves the management efficiency; in addition, the method uses the unmanned aerial vehicle for inspection, can deal with different environments, and greatly improves the practicability.
Example 2
Referring to fig. 2 to 5, a second embodiment of the present invention is different from the first embodiment in that a smart inspection system for an internet of things with power coordinated by edge cloud is provided, and includes: the mobile computing module 100, the edge computing module 200, and the cloud computing module 300, wherein it should be noted that,
the mobile computing module 100 is used for collecting data information and completing convolution part computation of a feature model, and comprises an unmanned aerial vehicle unit 101, a collecting unit 102, a computing unit 103, a storage unit 104 and a 5G communication unit 105, wherein the unmanned aerial vehicle unit 101 is used for providing the motion capability of the whole mobile computing module, the collecting unit 102 is connected to the collecting unmanned aerial vehicle unit 101 and is used for collecting image information and positioning information currently shot by the unmanned aerial vehicle unit 101, the computing unit 103 is connected to the collecting unit 102 and an edge computing module 200 and is used for carrying out preliminary computation on the collected information and feature information labels of abnormal features and giving out corresponding feature extraction information, the storage unit 104 is connected to the collecting unit 102 and the computing unit 103 and is used for storing the collected information of the collecting unit 102 and the extraction information given by the computing unit 103, and the 5G communication unit 105 is used for connecting the edge computing module 200 and a cloud computing, mutual transmission of information in the storage unit is carried out; the edge computing module 200 is connected to the mobile computing module 100 through a 5G network, and is configured to determine an abnormal feature of information acquired by the mobile computing module 100, where the abnormal feature includes a user plane unit 201 of a 5G core network and a mobile edge computing server 202, the user plane unit 201 of the 5G core network is configured to check transmission of the acquired information, transmit the information to the mobile edge computing server 202 for edge computing, determine an abnormal feature of the information, and transmit a feature information tag to the mobile computing module 100; the cloud computing module 300 is connected to the mobile computing module 100 through a 5G network, and is configured to classify the abnormal features and output abnormal information and features, and includes a cloud server 301 and a console 302, where the cloud server 301 is configured to complete classification of the feature information and transmit the classification information to the console 302, and the console 302 is configured to monitor and make decisions on the overall system.
It should be understood that the system provided in the present embodiment, which relates to the connection relationship between the mobile computing module 100, the edge computing module 200 and the cloud computing module 300, may be, for example, a computer readable program, and is implemented by improving the program data interface of each module.
It should be recognized that embodiments of the present invention can be realized and implemented by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer readable memory. The methods may be implemented in a computer program using standard programming techniques, including a non-transitory computer-readable storage medium configured with the computer program, where the storage medium so configured causes a computer to operate in a specific and predefined manner, according to the methods and figures described in the detailed description. Each program may be implemented in a high level procedural or object oriented programming language to communicate with a computer system. However, the program(s) can be implemented in assembly or machine language, if desired. In any case, the language may be a compiled or interpreted language. Furthermore, the program can be run on a programmed application specific integrated circuit for this purpose.
Further, the operations of processes described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The processes described herein (or variations and/or combinations thereof) may be performed under the control of one or more computer systems configured with executable instructions, and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) collectively executed on one or more processors, by hardware, or combinations thereof. The computer program includes a plurality of instructions executable by one or more processors.
Further, the method may be implemented in any type of computing platform operatively connected to a suitable interface, including but not limited to a personal computer, mini computer, mainframe, workstation, networked or distributed computing environment, separate or integrated computer platform, or in communication with a charged particle tool or other imaging device, and the like. Aspects of the invention may be embodied in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, optically read and/or write storage medium, RAM, ROM, or the like, such that it may be read by a programmable computer, which when read by the storage medium or device, is operative to configure and operate the computer to perform the procedures described herein. Further, the machine-readable code, or portions thereof, may be transmitted over a wired or wireless network. The invention described herein includes these and other different types of non-transitory computer-readable storage media when such media include instructions or programs that implement the steps described above in conjunction with a microprocessor or other data processor. The invention also includes the computer itself when programmed according to the methods and techniques described herein. A computer program can be applied to input data to perform the functions described herein to transform the input data to generate output data that is stored to non-volatile memory. The output information may also be applied to one or more output devices, such as a display. In a preferred embodiment of the invention, the transformed data represents physical and tangible objects, including particular visual depictions of physical and tangible objects produced on a display.
As used in this application, the terms "component," "module," "system," and the like are intended to refer to a computer-related entity, either hardware, firmware, a combination of hardware and software, or software in execution. For example, a component may be, but is not limited to being: a process running on a processor, an object, an executable, a thread of execution, a program, and/or a computer. By way of example, both an application running on a computing device and the computing device can be a component. One or more components can reside within a process and/or thread of execution and a component can be localized on one computer and/or distributed between two or more computers. In addition, these components can execute from various computer readable media having various data structures thereon. The components may communicate by way of local and/or remote processes such as in accordance with a signal having one or more data packets.
It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.
Claims (10)
1. The intelligent inspection method for the power Internet of things with edge cloud coordination is characterized by comprising the following steps: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
collecting information collected by the unmanned aerial vehicle;
performing convolution operation on the collected information to extract characteristic information, and transmitting the characteristic information and the total number of the serial numbers by using a 5G core network;
carrying out full connection operation by using the feature extraction information and the serial number, and judging abnormal features;
performing category identification on the information of the abnormal features;
and outputting the abnormal information and the information category to finish the inspection.
2. The intelligent inspection method for the power internet of things with edge cloud coordination according to claim 1, characterized in that: the total number of sequence numbers includes,
the total number of the serial numbers is the product of the length and the width of the convolution layer output image, the total number of the serial numbers is obtained by dividing the pixel number of the original image, the pixel number of the local image and the increasing coefficient, and the calculation formula of the total number of the serial numbers is as follows:
where l is the input image length, w is the input image width, k is the convolution kernel size, and m is the augmentation coefficient.
3. The intelligent inspection method for the power internet of things with the cooperation of the edge clouds according to claim 1 or 2, characterized in that: the full-connection operation includes the steps of,
and cutting the characteristic information in a dimension direction according to the serial number, performing full-connection operation calculation on the characteristic model, and outputting probability values of the labels.
4. The intelligent inspection method for the power internet of things with edge cloud coordination according to claim 3, characterized in that: the cutting method comprises the following steps of,
setting the feature extraction information as a multi-dimensional matrix { x }o,yo,zoAnd said xo,yo,zoSatisfy xn＝xoyoFor the serial number
Cut out information MiComprises the following steps:
wherein: x is the number ofoIs the length of the matrix, yoIs the width of the matrix, zoIs the matrix dimension.
5. The intelligent inspection method for the power internet of things with edge cloud coordination according to claim 4, characterized in that: the feature model includes a set of feature models including,
the tag types of the feature model include power line, lawn, sky, iron tower, and unknown types.
6. The intelligent inspection method for the power internet of things with edge cloud coordination according to claim 5, characterized in that: the unknown type may be a type of information including,
the probability value of the label of the unknown type is maximum, the serial number of the unknown type is marked, and the type identification is carried out on the marked signal information.
7. The intelligent inspection method for the power internet of things with edge cloud coordination according to claim 5, characterized in that: the performing of the class identification may include performing the class identification,
is provided with
The number of the characteristic regions in each row,
for received sequence numbersThe value of the one or more of,
is a serial number xiAnd then returning the pixel point position of the characteristic region, wherein the calculation formula is as follows:
and cutting out a characteristic region picture according to the pixel point position, carrying out identification operation calculation of a category model, and outputting specific type information of the picture.
8. The intelligent inspection method for the power internet of things with edge cloud coordination according to claim 7, characterized in that: the information collected may include, for example,
image information, positioning information, time information.
9. An intelligent inspection system of an electric power internet of things with edge cloud coordination, which is characterized by comprising,
the mobile computing module (100) is used for collecting data information and completing convolution part computation of the feature model;
the edge computing module (200) is connected to the mobile computing module (100) through a 5G network, and is used for judging the abnormal features of the information acquired by the mobile computing module (100), and comprises a user plane unit (201) of a 5G core network and a mobile edge computing server (202), wherein the user plane unit (201) of the 5G core network is used for checking the transmission of the acquired information, transmitting the information to the mobile edge computing server (202) for edge computing, judging the abnormal features of the information, and transmitting a feature information label to the mobile computing module (100);
the cloud computing module (300) is connected to the mobile computing module (100) through a 5G network and used for classifying abnormal features and outputting the abnormal information and the abnormal features, the cloud computing module comprises a cloud server (301) and a console (302), the cloud server (301) is used for completing classification of feature information and transmitting the classification information to the console (302), and the console (302) is used for monitoring and making decisions of a total system.
10. The intelligent inspection system according to claim 9, characterized in that: the mobile computing module (100) comprises,
an unmanned aerial vehicle unit (101), a collection unit (102), a calculation unit (103), a storage unit (104) and a 5G communication unit (105), wherein the unmanned aerial vehicle unit (101) is used for providing the motion capability of the whole mobile calculation module, the collection unit (102) is used for collecting the image information and the positioning information currently shot by the unmanned aerial vehicle unit (101), the calculation unit (103) is used for carrying out preliminary calculation on the information collected by the collection unit (102) and the feature information labels calculated by the edge calculation module (200) and providing corresponding feature extraction information, the storage unit (104) is used for storing the collection information of the collection unit (102) and the extraction information provided by the calculation unit (103), the 5G communication unit (105) is used for connecting the edge calculation module (200) and the cloud calculation module (300), mutual transmission of information in the storage unit is performed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011261336.5A CN112367400B (en) | 2020-11-12 | 2020-11-12 | Intelligent inspection method and system for power internet of things with edge cloud coordination |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011261336.5A CN112367400B (en) | 2020-11-12 | 2020-11-12 | Intelligent inspection method and system for power internet of things with edge cloud coordination |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112367400A true CN112367400A (en) | 2021-02-12 |
| CN112367400B CN112367400B (en) | 2022-04-29 |
Family
ID=74515393
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011261336.5A Active CN112367400B (en) | 2020-11-12 | 2020-11-12 | Intelligent inspection method and system for power internet of things with edge cloud coordination |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112367400B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112947585A (en) * | 2021-04-09 | 2021-06-11 | 广东电网有限责任公司电力调度控制中心 | Power grid unmanned aerial vehicle inspection method, device and system based on 5G cloud edge-end cooperation |
| CN113011297A (en) * | 2021-03-09 | 2021-06-22 | 全球能源互联网研究院有限公司 | Power equipment detection method, device, equipment and server based on edge cloud cooperation |
| CN113095506A (en) * | 2021-03-25 | 2021-07-09 | 北京大学 | Machine learning method, system and medium based on end, edge and cloud cooperation |
| CN113660009A (en) * | 2021-09-29 | 2021-11-16 | 广东电网有限责任公司 | Testing system and testing method for power distribution and utilization communication |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107729808A (en) * | 2017-09-08 | 2018-02-23 | 国网山东省电力公司电力科学研究院 | A kind of image intelligent acquisition system and method for power transmission line unmanned machine inspection |
| US20190220967A1 (en) * | 2018-01-15 | 2019-07-18 | Tata Consultancy Services Limited | Systems and methods for automated inferencing of changes in spatio-temporal images |
| CN110287945A (en) * | 2019-07-04 | 2019-09-27 | 山东浪潮人工智能研究院有限公司 | Unmanned plane target detection method under a kind of 5G environment |
| CN110417120A (en) * | 2019-06-26 | 2019-11-05 | 广东康云科技有限公司 | A kind of substation's outdoor scene 3 D intelligent cruising inspection system and method |
| CN110544489A (en) * | 2019-04-16 | 2019-12-06 | 江苏慧中数据科技有限公司 | abnormal sound detection method based on edge cloud intelligent architecture |
| CN110633629A (en) * | 2019-08-02 | 2019-12-31 | 广东电网有限责任公司清远供电局 | Power grid inspection method, device, equipment and storage medium based on artificial intelligence |
| CN111272148A (en) * | 2020-01-20 | 2020-06-12 | 江苏方天电力技术有限公司 | Unmanned aerial vehicle autonomous inspection self-adaptive imaging quality optimization method for power transmission line |
| US20200192726A1 (en) * | 2018-12-12 | 2020-06-18 | Samsung Electronics Co., Ltd. | Method and apparatus for load balancing in neural network |
| CN111784026A (en) * | 2020-05-28 | 2020-10-16 | 国网信通亿力科技有限责任公司 | Cloud-side cooperative sensing-based all-dimensional physical examination system for electrical equipment of transformer substation |
| CN111784685A (en) * | 2020-07-17 | 2020-10-16 | 国网湖南省电力有限公司 | Power transmission line defect image identification method based on cloud edge cooperative detection |
| CN111860439A (en) * | 2020-07-31 | 2020-10-30 | 广东电网有限责任公司 | Unmanned aerial vehicle inspection image defect detection method, system and equipment |
-
2020
- 2020-11-12 CN CN202011261336.5A patent/CN112367400B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107729808A (en) * | 2017-09-08 | 2018-02-23 | 国网山东省电力公司电力科学研究院 | A kind of image intelligent acquisition system and method for power transmission line unmanned machine inspection |
| US20190220967A1 (en) * | 2018-01-15 | 2019-07-18 | Tata Consultancy Services Limited | Systems and methods for automated inferencing of changes in spatio-temporal images |
| US20200192726A1 (en) * | 2018-12-12 | 2020-06-18 | Samsung Electronics Co., Ltd. | Method and apparatus for load balancing in neural network |
| CN110544489A (en) * | 2019-04-16 | 2019-12-06 | 江苏慧中数据科技有限公司 | abnormal sound detection method based on edge cloud intelligent architecture |
| CN110417120A (en) * | 2019-06-26 | 2019-11-05 | 广东康云科技有限公司 | A kind of substation's outdoor scene 3 D intelligent cruising inspection system and method |
| CN110287945A (en) * | 2019-07-04 | 2019-09-27 | 山东浪潮人工智能研究院有限公司 | Unmanned plane target detection method under a kind of 5G environment |
| CN110633629A (en) * | 2019-08-02 | 2019-12-31 | 广东电网有限责任公司清远供电局 | Power grid inspection method, device, equipment and storage medium based on artificial intelligence |
| CN111272148A (en) * | 2020-01-20 | 2020-06-12 | 江苏方天电力技术有限公司 | Unmanned aerial vehicle autonomous inspection self-adaptive imaging quality optimization method for power transmission line |
| CN111784026A (en) * | 2020-05-28 | 2020-10-16 | 国网信通亿力科技有限责任公司 | Cloud-side cooperative sensing-based all-dimensional physical examination system for electrical equipment of transformer substation |
| CN111784685A (en) * | 2020-07-17 | 2020-10-16 | 国网湖南省电力有限公司 | Power transmission line defect image identification method based on cloud edge cooperative detection |
| CN111860439A (en) * | 2020-07-31 | 2020-10-30 | 广东电网有限责任公司 | Unmanned aerial vehicle inspection image defect detection method, system and equipment |
Non-Patent Citations (2)
| Title |
|---|
| 梁中豪等: "基于交通场景区域增强的单幅图像去雾方法", 《计算机应用》 * |
| 祝永坤等: "基于泛在物联网的多机编队智能自主巡检移动式机舱研制与应用", 《内蒙古电力技术》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113011297A (en) * | 2021-03-09 | 2021-06-22 | 全球能源互联网研究院有限公司 | Power equipment detection method, device, equipment and server based on edge cloud cooperation |
| CN113095506A (en) * | 2021-03-25 | 2021-07-09 | 北京大学 | Machine learning method, system and medium based on end, edge and cloud cooperation |
| CN112947585A (en) * | 2021-04-09 | 2021-06-11 | 广东电网有限责任公司电力调度控制中心 | Power grid unmanned aerial vehicle inspection method, device and system based on 5G cloud edge-end cooperation |
| CN113660009A (en) * | 2021-09-29 | 2021-11-16 | 广东电网有限责任公司 | Testing system and testing method for power distribution and utilization communication |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112367400B (en) | 2022-04-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112367400B (en) | Intelligent inspection method and system for power internet of things with edge cloud coordination | |
| CN108537154B (en) | Power transmission line bird nest identification method based on HOG characteristics and machine learning | |
| CN111428748B (en) | HOG feature and SVM-based infrared image insulator identification detection method | |
| CN110674861B (en) | Intelligent analysis method and device for power transmission and transformation inspection images | |
| CN108416294B (en) | Fan blade fault intelligent identification method based on deep learning | |
| CN112183667B (en) | Insulator fault detection method in cooperation with deep learning | |
| Wang et al. | Recognition and drop-off detection of insulator based on aerial image | |
| CN110580475A (en) | line diagnosis method based on unmanned aerial vehicle inspection, electronic device and storage medium | |
| Mao et al. | Development of power transmission line defects diagnosis system for UAV inspection based on binocular depth imaging technology | |
| CN113205063A (en) | Visual identification and positioning method for defects of power transmission conductor | |
| CN112613454A (en) | Electric power infrastructure construction site violation identification method and system | |
| Zheng et al. | Component identification and defect detection in transmission lines based on deep learning | |
| US12118807B2 (en) | Apparatus and method for three-dimensional object recognition | |
| CN113238578A (en) | Routing planning method and system for power tower unmanned aerial vehicle inspection route | |
| CN104239899A (en) | Electric transmission line spacer identification method for unmanned aerial vehicle inspection | |
| CN118297755B (en) | Building construction analysis management and control method and system based on Internet of things and big data technology | |
| Hao et al. | Detection of bird nests on power line patrol using single shot detector | |
| CN115660647A (en) | Maintenance method for building outer wall | |
| CN114881997A (en) | Wind turbine generator defect assessment method and related equipment | |
| CN115825984A (en) | Power transmission line inspection system and inspection method based on laser point cloud | |
| CN116363157A (en) | Overhead transmission line edge positioning method, system, electronic equipment and medium | |
| Chen et al. | Improved YOLOv5s model for key components detection of power transmission lines. | |
| CN117409083B (en) | Cable terminal identification method and device based on infrared image and improved YOLOV5 | |
| CN112802027A (en) | Target object analysis method, storage medium and electronic device | |
| CN117636129A (en) | Identification method of power construction supervision image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |