CN113419140A - Distribution network line fault diagnosis method and device considering human-computer-object cooperation - Google Patents
Distribution network line fault diagnosis method and device considering human-computer-object cooperation Download PDFInfo
- Publication number
- CN113419140A CN113419140A CN202110901513.XA CN202110901513A CN113419140A CN 113419140 A CN113419140 A CN 113419140A CN 202110901513 A CN202110901513 A CN 202110901513A CN 113419140 A CN113419140 A CN 113419140A
- Authority
- CN
- China
- Prior art keywords
- distribution line
- fault
- data
- returned
- image
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/081—Locating faults in cables, transmission lines, or networks according to type of conductors
- G01R31/086—Locating faults in cables, transmission lines, or networks according to type of conductors in power transmission or distribution networks, i.e. with interconnected conductors
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/088—Aspects of digital computing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Abstract
The application discloses a distribution network line fault diagnosis method and device considering man-machine-object cooperation, wherein the method comprises the following steps: acquiring a current unmanned aerial vehicle return image and current distribution line return data; comparing the returned image with the historical non-fault image in a depth belief network; and if the comparison is not the same, clustering the current distribution line returned data and the historical data of the distribution line fault information, and judging the fault type corresponding to the current distribution line returned data. The method and the device can effectively improve the precision and speed of diagnosis, quickly judge the specific faults of the distribution lines, optimize the fault analysis process and improve the reliability of regional power supply.
Description
Technical Field
The application relates to the technical field of power system fault diagnosis, in particular to a distribution network line fault diagnosis method and device considering human-computer-object cooperation.
Background
With the rapid development of economy in China, the demand for energy is increasing, and ultrahigh-voltage high-capacity power lines are being expanded greatly. The power line corridors in China need to pass through various complex geographic environments, most of the power line corridors pass through large-area reservoirs, lakes, Chongshan mountains and the like, and the detection of the power lines is difficult. Meanwhile, the inspection is influenced by too many human factors, the life safety of inspection workers can be endangered in dangerous areas, the manual input data volume is large, and errors are easy to occur in the manual input process of data. The unmanned aerial vehicle is used for inspecting the power line in a large area, a good application effect is achieved for early warning of natural disasters such as freezing, visible light and infrared thermal imaging observation is conducted on the line through high-precision video equipment, fault occurrence points of the power equipment are accurately found through observation, identification and relevant data comparison, and effective operation of power facilities is guaranteed. Use unmanned aerial vehicle to patrol and examine the line monitoring, with greatly reduced cost of patrolling and examining, improve and patrol and examine efficiency, guarantee patrols and examines personnel's life safety.
With the gradual implementation of smart power grids and the updating and upgrading of storage technologies, mass data of power grids can be stored, the application of sensors is increasingly wide for returned big data, the application of the sensors is gradually extended to the aspect of the power grids, and the returned data is mapped to the safety state of the power grids through real-time recording of the power grids. In recent years, through the application of a big data technology and the development of an artificial intelligence algorithm, a great deal of research is carried out on sensor return data of a distribution line, the potential risk of the distribution line is analyzed, and a favorable guarantee is provided for the safe and stable operation of a power grid.
Disclosure of Invention
The embodiment of the application provides a distribution network line fault diagnosis method and device considering human-computer-object cooperation, so that the diagnosis precision and speed can be effectively improved, the specific fault of a distribution line can be quickly judged, the fault analysis process can be optimized, and the regional power supply reliability can be improved.
In view of this, a first aspect of the present application provides a distribution network line fault diagnosis method considering human-computer-physical cooperation, where the method includes:
acquiring a current unmanned aerial vehicle return image and current distribution line return data;
comparing the returned image with the historical non-fault image in a depth belief network;
and if the comparison is not the same, clustering the current distribution line returned data and historical data of the distribution line fault information, and judging the fault type corresponding to the current distribution line returned data.
Optionally, before comparing the returned image with the historical non-fault image in the deep belief network, the method further includes:
and preprocessing the returned image.
Optionally, the preprocessing the returned image includes:
and storing the returned images according to the shooting date in a classified manner, and primarily screening the returned images to remove blurred and unidentifiable images.
Optionally, the comparing the returned image with the historical non-fault image in the deep belief network further includes:
and if the comparison result of the returned image and the historical non-fault image is the same, judging that the distribution line has no fault.
Optionally, before clustering the current distribution line returned data and the historical data of the distribution line fault information, the method further includes:
processing missing and abnormal data in the current distribution line returned data and the historical data of the distribution line fault information by adopting an average interpolation method;
normalizing the current distribution line returned data and the historical data of the distribution line fault information;
and determining the fault types of the distribution lines corresponding to the historical data of the distribution line fault information, wherein the fault types of the distribution lines comprise ground faults, short-circuit faults and overload faults.
Optionally, the clustering the current distribution line returned data and historical data of distribution line fault information, and determining a fault type corresponding to the current distribution line returned data includes:
clustering the current distribution line returned data and the historical data of the distribution line fault information by adopting fuzzy C-means clustering;
and obtaining the membership degree of the class center to which the sample point corresponding to the current distribution line returned data belongs, thereby determining the fault class of the current distribution line returned data.
The second aspect of the present application provides a distribution network line fault diagnosis device considering human-computer-physical cooperation, the device including:
the acquisition unit is used for acquiring the current unmanned aerial vehicle return image and the current distribution line return data;
the comparison unit is used for comparing the returned image with the historical non-fault image in a deep belief network;
and the fault judging unit is used for clustering the current distribution line returned data and the historical data of the distribution line fault information when the comparison is different, and judging the fault type corresponding to the current distribution line returned data.
Optionally, the method further includes:
and the preprocessing unit is used for preprocessing the returned image.
Optionally, the method further includes:
the interpolation processing unit is used for processing missing and abnormal data in the current distribution line returned data and the historical data of the distribution line fault information by adopting an average interpolation method;
the normalization unit is used for normalizing the current distribution line returned data and the historical data of the distribution line fault information;
and the fault determining unit is used for determining the fault types of the distribution lines corresponding to the historical data of the distribution line fault information, wherein the fault types of the distribution lines comprise ground faults, short-circuit faults and overload faults.
Optionally, the fault determining unit includes:
the clustering unit is used for clustering the current distribution line returned data and the historical data of the distribution line fault information by adopting fuzzy C-mean clustering;
and the fault determining unit is used for obtaining the membership degree of the class center to which the sample point corresponding to the current distribution line returned data belongs, so as to determine the fault class of the current distribution line returned data.
According to the technical scheme, the method has the following advantages:
in the embodiment of the application, a distribution network line fault diagnosis method considering man-machine-object cooperation is provided, and comprises the following steps:
acquiring a current unmanned aerial vehicle return image and current distribution line return data; comparing the returned image with the historical non-fault image in a depth belief network; and if the comparison is not the same, clustering the current distribution line returned data and the historical data of the distribution line fault information, and judging the fault type corresponding to the current distribution line returned data.
The method and the device have the advantages that the returned image information of the unmanned aerial vehicle and the returned data of the sensor are effectively fused, the returned image of the unmanned aerial vehicle is analyzed through the deep belief network, whether the power distribution line has a fault or not is judged, and preliminary fault analysis of the power distribution line is completed; if the distribution line has no fault, the fault analysis process is completed, if the distribution line is found to be possibly faulty after image recognition processing, the sensor return data in the distribution line needs to be analyzed by using the improved fuzzy C mean value clustering algorithm, the improved fuzzy C mean value clustering algorithm can effectively improve the training precision and speed of the algorithm, and has important significance in quickly judging the specific fault of the distribution line, optimizing the fault analysis process and improving the regional power supply reliability.
Drawings
FIG. 1 is a flowchart of a method of an embodiment of a distribution network line fault diagnosis method considering human-computer-physical cooperation according to the present application;
FIG. 2 is a flowchart of a method of another embodiment of a distribution network line fault diagnosis method considering human-machine-physical cooperation according to the present application;
fig. 3 is a schematic structural diagram of an embodiment of a distribution network line fault diagnosis device considering man-machine-object coordination according to the present application.
Detailed Description
In order to make the technical solutions of the present application better understood, 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 a part of the embodiments of the present application, and not all of the 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.
Fig. 1 is an embodiment of a distribution network line fault diagnosis method considering human-machine-physical cooperation according to the present application, as shown in fig. 1, where fig. 1 includes:
101. acquiring a current unmanned aerial vehicle return image and current distribution line return data;
it should be noted that, the method and the device summarize the images of the distribution lines acquired by the unmanned aerial vehicle in the area, specifically, the images are infrared and visible light images, the acquired return images can be stored in a classified mode according to shooting dates, the return infrared and visible light images are preliminarily screened, and the obviously blurred images which cannot be identified at all are removed; historical data of the distribution line returned by the sensor and various types of data of the current distribution line operation are collected.
102. Comparing the returned image with the historical non-fault image in a depth belief network;
it should be noted that, the method and the device for processing the infrared and visible light images shot by the unmanned aerial vehicle adopt the depth belief network to compare the current return image with the historical non-fault image, and judge whether the distribution line has faults or not. The deep belief network is a novel deep neural network, is composed of a plurality of limited Boltzmann machine stacks on the bottom layer and a BP neural network on the top layer, and is widely applied to the fields of image recognition, fault judgment and the like.
103. And if the comparison is not the same, clustering the current distribution line returned data and the historical data of the distribution line fault information, and judging the fault type corresponding to the current distribution line returned data.
It should be noted that, the infrared and visible light images returned by the unmanned aerial vehicle are compared with the historical images, the distribution line fault condition is preliminarily judged, and if the comparison result shows that the current returned image is not the same as the historical non-fault image, it is indicated that the current returned image may have a fault, therefore, the current distribution line returned data can be fused into the historical data of the distribution line fault information for clustering, wherein the fault information of the historical data of the distribution line fault information can be obtained in advance, so that the fault type of the current distribution line returned data can be identified after clustering is completed.
The method and the device have the advantages that the returned image information of the unmanned aerial vehicle and the returned data of the sensor are effectively fused, the returned image of the unmanned aerial vehicle is analyzed through the deep belief network, whether the power distribution line has a fault or not is judged, and preliminary fault analysis of the power distribution line is completed; if the distribution line has no fault, the fault analysis process is completed, if the distribution line is found to be possibly faulty after image recognition processing, the sensor return data in the distribution line needs to be analyzed by using the improved fuzzy C mean value clustering algorithm, the improved fuzzy C mean value clustering algorithm can effectively improve the training precision and speed of the algorithm, and has important significance in quickly judging the specific fault of the distribution line, optimizing the fault analysis process and improving the regional power supply reliability.
The application further provides another embodiment of a distribution network line fault diagnosis method considering human-computer-physical cooperation, as shown in fig. 2, where fig. 2 includes:
201. acquiring a current unmanned aerial vehicle return image and current distribution line return data;
202. preprocessing the returned image;
it should be noted that, the preprocessing the returned image includes: and storing the returned images according to the shooting date in a classified manner, and primarily screening the returned images to remove blurred and unidentifiable images.
Specifically, this application gathers the image of the distribution lines of the regional unmanned aerial vehicle collection in place, and is specific, and the image is infrared and visible light image, can deposit the passback image of acquireing according to shooting date classification to infrared and visible light image to the passback carry out preliminary screening, get rid of obvious fuzzy, can not discern the image completely.
203. Comparing the returned image with the historical non-fault image in a depth belief network;
it should be noted that the infrared and visible light images shot by the unmanned aerial vehicle are compared by using a deep belief network, and whether the distribution line has a fault or not is judged. The deep belief network is a novel deep neural network, is composed of a plurality of limited Boltzmann machine stacks at the bottom layer and a BP neural network at the top layer, and is widely applied to the fields of image recognition, fault judgment and the like.
And comparing the infrared and visible light images shot by the unmanned aerial vehicle by adopting a depth belief network, and judging whether the distribution line breaks down. The image recognition of the deep belief network comprises the following specific steps:
(1) a constrained boltzmann machine was introduced. Determining an energy representation possessed by a restricted boltzmann machine of state (v, h) according to the following formula;
where θ ═ ω ij, ai, bj is the restricted boltzmann machine parameter, and n and m are the numbers of neurons in the visible and hidden layers, respectively.
(2) A probability distribution is determined. Calculating the probability distribution of the state (v, h) limited boltzmann machine determined by the energy function according to the following formula;
in the formula, Sigma-exp (-E (v, h | theta)) is a normalization factor.
(3) Activating probabilities of the jth hidden element and the ith apparent element of each layer of the limited Boltzmann machine;
(4) contrast divergence, parameter variation calculation criteria and a parameter updating criterion considering the learning rate zeta.
1) And introducing contrast divergence to train the states of the explicit elements and the implicit elements. And deriving the log-likelihood function with respect to the model parameter theta by a weight parameter omega according to the following formulaijFor example;
in the formula<vihj>dataIn order to be expected for the distribution of the data,<vihj>datadefined for a constrained boltzmann machine.
2) And calculating the variation of each parameter. Updating the parameter variation calculation criterion according to the following formula;
3) the parameter update criterion of the learning rate ζ is considered. Updating a parameter updating criterion considering the learning rate ζ according to the following formula;
204. and if the comparison result of the returned image is the same as that of the historical non-fault image, judging that the distribution line has no fault.
It should be noted that, the infrared and visible light images returned by the unmanned aerial vehicle are compared with the historical images, the fault condition of the power distribution line is preliminarily determined, and if the comparison result shows that the current returned image is the same as the historical non-fault image, it is indicated that the current returned image may not have a fault.
205. And if the comparison is not the same, clustering the current distribution line returned data and the historical data of the distribution line fault information, and judging the fault type corresponding to the current distribution line returned data.
It should be noted that, in the present application, fuzzy C-means clustering is adopted to cluster the current distribution line returned data and the historical data of the distribution line fault information; and obtaining the membership degree of the class center to which the sample point corresponding to the current distribution line returned data belongs, thereby determining the fault class of the current distribution line returned data. And finally, verifying the result by adopting the test set data, and analyzing and judging the accuracy.
Specifically, a fuzzy C-means clustering algorithm is adopted to cluster the distribution line fault accidents in the historical data, and the distribution line fault accidents are merged into the current distribution line return data. The method is a novel distance calculation method aiming at the problem of distance calculation in the fuzzy C-means clustering algorithm, and is used for improving the existing fuzzy C-means clustering algorithm. The fuzzy C-means clustering algorithm obtains the membership degree of each sample point to all class centers by optimizing an objective function, thereby determining the class of the sample points to achieve the purpose of automatically classifying the sample data. The specific clustering process is as follows:
2051. the calculation formula for determining the cluster center initialization value of the fuzzy C-means cluster of each sample cluster is as follows:
in the formula (I), the compound is shown in the specification,
is the neighborhood radius, c is the number of categories; n is the number of samples within the neighborhood radius; m is a fault information data value of each distribution line; and n is the number of the fault information of the distribution line in a certain area.
2052. Initializing a membership matrix U, matrix elements muijRepresenting the degree of the ith object belonging to the jth class, and the elements in the matrix are normalized to be in the interval [0, 1 ]]Performing the following steps;
2053. in the t-th iteration, the membership matrix is updated according to the following formula:
wherein x is 1,2, and n, j is 1,2, c, muijIndicating the degree to which the ith object belongs to the jth class attribute.
In the iterative calculation of the t time, the clustering center value matrix is updated according to the following formula:
wherein j is 1,2ijThe cluster center value of the j-th class attribute representing the l-th class environmental factor, and the calculation formula of the coefficient K is as follows:
2054. if it is
Or when the preset iteration times are reached, the iteration is finished, and the optimal membership degree of the environment attribute value is output; otherwise, the process returns to step 1043 for the next iteration, where ε represents a minimum value.
In a specific embodiment, before clustering the current distribution line return data and the historical data of the distribution line fault information, the method further comprises the following steps:
processing missing and abnormal data in the current distribution line returned data and historical data of distribution line fault information by adopting an average interpolation method;
normalization processing is carried out on the current distribution line returned data and historical data of distribution line fault information;
and determining the fault types of the distribution lines corresponding to the historical data of the distribution line fault information, wherein the fault types of the distribution lines comprise ground faults, short-circuit faults and overload faults.
It should be noted that, the present application collects various data of the current distribution line returned data and the historical fault information of the distribution line returned data returned by the sensor, and for the collected current distribution line returned data, in order to ensure that the collected data in the area can be effectively clustered, missing and abnormal data can be processed by using an average interpolation method, and since various collected data dimensions are not completely the same, the collected data can be normalized. And determining the fault type of the historical fault information of the distribution line, wherein the fault type of the distribution line specifically comprises a ground fault, a short-circuit fault and an overload fault. And randomly selecting 80% of the data collected by the distribution lines as training samples, and the rest 20% as testing samples.
Specifically, the normalization method comprises the following steps:
in the formula (I), the compound is shown in the specification,
denotes the normalized value, xiRepresenting magnitude of fault information, x, of distribution lineminRepresenting the minimum value, x, of the distribution line fault information sequence in a samplemaxThe maximum value of the distribution line fault information sequence in one sample is represented.
The distribution line fault information historical data matrix in a certain area is as follows:
in the formula, m is a fault information data value of each distribution line; and n is the number of the fault information of the distribution line in a certain area.
The application also provides an embodiment of a distribution network line fault diagnosis device considering human-computer-physical cooperation, as shown in fig. 3, where fig. 3 includes:
the obtaining unit 301 is configured to obtain a current unmanned aerial vehicle return image and current distribution line return data;
a comparison unit 302, configured to compare the returned image with the historical non-fault image in a deep belief network;
and the fault judging unit 303 is configured to cluster the current distribution line returned data and the historical data of the distribution line fault information when the comparison is different, and judge a fault type corresponding to the current distribution line returned data.
In a specific embodiment, the method further comprises the following steps:
and the preprocessing unit is used for preprocessing the returned image.
In a specific embodiment, the method further comprises the following steps:
the interpolation processing unit is used for processing missing and abnormal data in the current distribution line returned data and the historical data of the distribution line fault information by adopting an average interpolation method;
the normalization unit is used for normalizing the current distribution line returned data and the historical data of the distribution line fault information;
and the fault determining unit is used for determining the fault types of the distribution lines corresponding to the historical data of the distribution line fault information, wherein the fault types of the distribution lines comprise ground faults, short-circuit faults and overload faults.
In a specific embodiment, the failure determination unit 303 includes:
the clustering unit is used for clustering the current distribution line returned data and the historical data of the distribution line fault information by adopting fuzzy C-mean clustering;
and the fault determining unit is used for obtaining the membership degree of the class center to which the sample point corresponding to the current distribution line returned data belongs, so as to determine the fault class of the current distribution line returned data.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The terms "first," "second," "third," "fourth," and the like in the description of the present application and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be understood that in the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" for describing an association relationship of associated objects, indicating that there may be three relationships, e.g., "a and/or B" may indicate: only A, only B and both A and B are present, wherein A and B may be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of single item(s) or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (10)
1. A distribution network line fault diagnosis method considering man-machine-object coordination is characterized by comprising the following steps:
acquiring a current unmanned aerial vehicle return image and current distribution line return data;
comparing the returned image with the historical non-fault image in a depth belief network;
and if the comparison is not the same, clustering the current distribution line returned data and historical data of the distribution line fault information, and judging the fault type corresponding to the current distribution line returned data.
2. The distribution network line fault diagnosis method considering human-machine coordination according to claim 1, wherein before comparing the returned image with the historical non-fault image in the deep belief network, further comprising:
and preprocessing the returned image.
3. The method according to claim 2, wherein the preprocessing the return image comprises:
and storing the returned images according to the shooting date in a classified manner, and primarily screening the returned images to remove blurred and unidentifiable images.
4. The distribution network line fault diagnosis method considering human-machine coordination according to claim 1, wherein after comparing the returned image with the historical non-fault image in the deep belief network, further comprising:
and if the comparison result of the returned image and the historical non-fault image is the same, judging that the distribution line has no fault.
5. The distribution network line fault diagnosis method considering human-machine coordination according to claim 1, wherein before the clustering the current distribution line return data and the historical data of distribution line fault information, further comprising:
processing missing and abnormal data in the current distribution line returned data and the historical data of the distribution line fault information by adopting an average interpolation method;
normalizing the current distribution line returned data and the historical data of the distribution line fault information;
and determining the fault types of the distribution lines corresponding to the historical data of the distribution line fault information, wherein the fault types of the distribution lines comprise ground faults, short-circuit faults and overload faults.
6. The distribution network line fault diagnosis method considering human-machine interaction as claimed in claim 1, wherein the clustering the current distribution line returned data and historical data of distribution line fault information to determine the fault type corresponding to the current distribution line returned data includes:
clustering the current distribution line returned data and the historical data of the distribution line fault information by adopting fuzzy C-means clustering;
and obtaining the membership degree of the class center to which the sample point corresponding to the current distribution line returned data belongs, thereby determining the fault class of the current distribution line returned data.
7. A distribution network line fault diagnosis device considering man-machine-object coordination is characterized by comprising:
the acquisition unit is used for acquiring the current unmanned aerial vehicle return image and the current distribution line return data;
the comparison unit is used for comparing the returned image with the historical non-fault image in a deep belief network;
and the fault judging unit is used for clustering the current distribution line returned data and the historical data of the distribution line fault information when the comparison is different, and judging the fault type corresponding to the current distribution line returned data.
8. The distribution network line fault diagnosis device considering man-machine-physical cooperation according to claim 7, further comprising:
and the preprocessing unit is used for preprocessing the returned image.
9. The distribution network line fault diagnosis device considering man-machine-physical cooperation according to claim 7, further comprising:
the interpolation processing unit is used for processing missing and abnormal data in the current distribution line returned data and the historical data of the distribution line fault information by adopting an average interpolation method;
the normalization unit is used for normalizing the current distribution line returned data and the historical data of the distribution line fault information;
and the fault determining unit is used for determining the fault types of the distribution lines corresponding to the historical data of the distribution line fault information, wherein the fault types of the distribution lines comprise ground faults, short-circuit faults and overload faults.
10. The distribution network line fault diagnosis device considering man-machine-physical cooperation according to claim 7, wherein the fault judgment unit comprises:
the clustering unit is used for clustering the current distribution line returned data and the historical data of the distribution line fault information by adopting fuzzy C-mean clustering;
and the fault determining unit is used for obtaining the membership degree of the class center to which the sample point corresponding to the current distribution line returned data belongs, so as to determine the fault class of the current distribution line returned data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110901513.XA CN113419140B (en) | 2021-08-06 | 2021-08-06 | Distribution network line fault diagnosis method and device considering human-computer-object cooperation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110901513.XA CN113419140B (en) | 2021-08-06 | 2021-08-06 | Distribution network line fault diagnosis method and device considering human-computer-object cooperation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113419140A true CN113419140A (en) | 2021-09-21 |
| CN113419140B CN113419140B (en) | 2023-01-24 |
Family
ID=77719695
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110901513.XA Active CN113419140B (en) | 2021-08-06 | 2021-08-06 | Distribution network line fault diagnosis method and device considering human-computer-object cooperation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113419140B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103824340A (en) * | 2014-03-07 | 2014-05-28 | 山东鲁能智能技术有限公司 | Intelligent inspection system and inspection method for electric transmission line by unmanned aerial vehicle |
| CN103823450A (en) * | 2014-03-07 | 2014-05-28 | 国家电网公司 | Geographic information system (GSI)-based unmanned aerial vehicle power line inspection scheduling terminal and method |
| CN109040278A (en) * | 2018-08-20 | 2018-12-18 | 山东润智能科技有限公司 | Hospital is electrical and dynamical system safe and intelligent manages cloud platform, method and system |
| CN109961003A (en) * | 2018-12-26 | 2019-07-02 | 安徽继远软件有限公司 | A kind of airborne auxiliary inspection device of embedded transmission line of electricity based on FPGA |
| CN110018389A (en) * | 2019-02-21 | 2019-07-16 | 国网山东省电力公司临沂供电公司 | A kind of transmission line of electricity on-line fault monitoring method and system |
| CN110208643A (en) * | 2019-04-28 | 2019-09-06 | 国网辽宁省电力有限公司电力科学研究院 | A kind of electric network failure diagnosis method based on PMU data and fault recorder data |
| CN110579690A (en) * | 2019-10-29 | 2019-12-17 | 厦门理工学院 | Positioning method for small current ground fault section of power distribution network |
| CN111596167A (en) * | 2020-05-14 | 2020-08-28 | 中国南方电网有限责任公司 | Fault section positioning method and device based on fuzzy c-means clustering algorithm |
| CN112561129A (en) * | 2020-11-27 | 2021-03-26 | 广东电网有限责任公司肇庆供电局 | First-aid repair material allocation method based on distribution line fault information |
| CN112991297A (en) * | 2021-03-15 | 2021-06-18 | 广东电网有限责任公司清远供电局 | Power transmission line fault diagnosis method and system, electronic equipment and storage medium |
-
2021
- 2021-08-06 CN CN202110901513.XA patent/CN113419140B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103824340A (en) * | 2014-03-07 | 2014-05-28 | 山东鲁能智能技术有限公司 | Intelligent inspection system and inspection method for electric transmission line by unmanned aerial vehicle |
| CN103823450A (en) * | 2014-03-07 | 2014-05-28 | 国家电网公司 | Geographic information system (GSI)-based unmanned aerial vehicle power line inspection scheduling terminal and method |
| CN109040278A (en) * | 2018-08-20 | 2018-12-18 | 山东润智能科技有限公司 | Hospital is electrical and dynamical system safe and intelligent manages cloud platform, method and system |
| CN109961003A (en) * | 2018-12-26 | 2019-07-02 | 安徽继远软件有限公司 | A kind of airborne auxiliary inspection device of embedded transmission line of electricity based on FPGA |
| CN110018389A (en) * | 2019-02-21 | 2019-07-16 | 国网山东省电力公司临沂供电公司 | A kind of transmission line of electricity on-line fault monitoring method and system |
| CN110208643A (en) * | 2019-04-28 | 2019-09-06 | 国网辽宁省电力有限公司电力科学研究院 | A kind of electric network failure diagnosis method based on PMU data and fault recorder data |
| CN110579690A (en) * | 2019-10-29 | 2019-12-17 | 厦门理工学院 | Positioning method for small current ground fault section of power distribution network |
| CN111596167A (en) * | 2020-05-14 | 2020-08-28 | 中国南方电网有限责任公司 | Fault section positioning method and device based on fuzzy c-means clustering algorithm |
| CN112561129A (en) * | 2020-11-27 | 2021-03-26 | 广东电网有限责任公司肇庆供电局 | First-aid repair material allocation method based on distribution line fault information |
| CN112991297A (en) * | 2021-03-15 | 2021-06-18 | 广东电网有限责任公司清远供电局 | Power transmission line fault diagnosis method and system, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113419140B (en) | 2023-01-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110598736B (en) | Power equipment infrared image fault positioning, identifying and predicting method | |
| CN109506963B (en) | A kind of intelligence train traction failure big data abnormality detection discrimination method | |
| CN111209434B (en) | Substation equipment inspection system and method based on multi-source heterogeneous data fusion | |
| CN102098180B (en) | Network security situational awareness method | |
| CN109214280B (en) | Shop identification method and device based on street view, electronic equipment and storage medium | |
| CN108537154A (en) | Transmission line of electricity Bird's Nest recognition methods based on HOG features and machine learning | |
| CN109359697A (en) | Graph image recognition methods and inspection system used in a kind of power equipment inspection | |
| CN109544548A (en) | Defect inspection method, device, server, equipment and the storage medium of cutlery box | |
| CN113391239B (en) | Mutual inductor anomaly monitoring method and system based on edge calculation | |
| CN111126820A (en) | Electricity stealing prevention method and system | |
| CN114694178A (en) | Method and system for monitoring safety helmet in power operation based on fast-RCNN algorithm | |
| CN116258980A (en) | Unmanned aerial vehicle distributed photovoltaic power station inspection method based on vision | |
| CN113205039A (en) | Power equipment fault image identification and disaster investigation system and method based on multiple DCNNs | |
| CN115171045A (en) | YOLO-based power grid operation field violation identification method and terminal | |
| CN110705693A (en) | Unmanned aerial vehicle abnormal behavior recognition module and recognition method thereof | |
| CN116310913B (en) | Natural resource investigation monitoring method and device based on unmanned aerial vehicle measurement technology | |
| CN113419140B (en) | Distribution network line fault diagnosis method and device considering human-computer-object cooperation | |
| CN112597238A (en) | Method, system, device and medium for establishing knowledge graph based on personnel information | |
| CN115797804A (en) | Abnormity detection method based on unbalanced time sequence aviation flight data | |
| Xia et al. | A multi-target detection based framework for defect analysis of electrical equipment | |
| CN106081911B (en) | A kind of derrick crane on-line monitoring system | |
| CN111582084A (en) | Weak supervision learning-based rail foreign matter detection method and system under empty base view angle | |
| CN109741580A (en) | A kind of multi-source warning information integrates sharing method and device | |
| CN113780224B (en) | Unmanned inspection method and system for transformer substation | |
| CN117114420B (en) | Image recognition-based industrial and trade safety accident risk management and control system and method |
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 |