CN116184122A - Fault device positioning method, device, equipment and storage medium - Google Patents
Fault device positioning method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN116184122A CN116184122A CN202310394949.3A CN202310394949A CN116184122A CN 116184122 A CN116184122 A CN 116184122A CN 202310394949 A CN202310394949 A CN 202310394949A CN 116184122 A CN116184122 A CN 116184122A
- Authority
- CN
- China
- Prior art keywords
- fault
- node device
- node
- sample
- network model
- 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.)
- Pending
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
- G01R31/088—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
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Automatic Tape Cassette Changers (AREA)
Abstract
The application discloses a fault device positioning method, device, equipment and storage medium, which relate to the technical field of online monitoring and comprise the following steps: obtaining a fault sample and a sample label; training a fault sample and a sample label by using an artificial neural network on each node device based on information forward propagation and error reverse propagation, and establishing a mapping relation between the device number and the characteristic information of each node device so as to obtain a distributed depth network model; and judging whether the fault node device is detected, if so, inputting the characteristic information of the fault node device into the distributed depth network model so as to position the fault node device based on the output of the distributed depth network model. In this way, an artificial neural network model can be built and trained at each node by using a distributed deep learning algorithm, when a fault occurs, fault characteristic information is input into the trained neural network model, and a fault device number is output to obtain, so that fault diagnosis of the node device is realized.
Description
Technical Field
The present invention relates to the field of online monitoring technologies, and in particular, to a fault device positioning method, device, equipment, and storage medium.
Background
Along with the development of science and technology, intelligent substation has deepened people's life to safe and reliable's protection system has powerfully ensured the steady operation of electric wire netting, and distance protection device is the protection device of extensive installation in the protection system, also is the key part in the protection system. In the prior art, fault diagnosis for a protection system still depends on an operator to judge a defect position according to a network message, and massive data generated by wide connection of secondary equipment in an interval cannot be rapidly analyzed, and problems such as loss and distortion of fault information can occur in the processes of acquisition, uploading and analysis, so that the judging result of the existing method is seriously influenced by the information confidence coefficient, and the efficiency is low.
Disclosure of Invention
Accordingly, the present invention is directed to a fault device positioning method, device, apparatus, and storage medium, which can construct an artificial neural network model at each node by using a distributed deep learning algorithm and train the artificial neural network model, and when a fault occurs, input fault characteristic information into the trained neural network model, and output a fault device number to realize fault diagnosis of the node device. The specific scheme is as follows:
in a first aspect, the present application discloses a fault device positioning method, applied to a node device, including:
obtaining a fault sample and a sample label corresponding to the fault sample;
training the fault samples and the sample labels by using an artificial neural network on each node device based on information forward propagation and error reverse propagation, and establishing a mapping relation between device numbers and characteristic information of each node device to obtain a distributed depth network model;
and judging whether a fault node device is detected, if so, inputting the characteristic information of the fault node device into the distributed depth network model so as to position the fault node device based on the output of the distributed depth network model.
Optionally, the obtaining the fault sample and the sample label corresponding to the fault sample includes:
and acquiring device information of the historical fault node device, an optical fiber link corresponding to the historical fault node device and a sample label corresponding to the historical fault node device based on a structured database.
Optionally, the training the fault samples and the sample labels by using an artificial neural network at each node device based on information forward propagation and error backward propagation includes:
training the fault sample and the sample label by using an artificial neural network based on information forward propagation to sequentially determine the output of an input layer, a hidden layer and an output layer in the artificial neural network;
a predicted output based on the information forward propagation is determined based on the outputs of the input layer, hidden layer, and output layer.
Optionally, the training the fault samples and the sample labels by using an artificial neural network at each node device based on information forward propagation and error backward propagation includes:
determining a loss function between the predicted output and the sample tag based on error back propagation;
and determining a weight parameter and a bias parameter of the artificial neural network through the loss function so as to reduce the error of the artificial neural network through the weight parameter and the bias parameter.
Optionally, the establishing a mapping relationship between the device number and the feature information of each node device includes:
and acquiring the device number and the characteristic information of each node device, and inputting the device number and the characteristic information into the artificial neural network for training so as to establish a mapping relation between the device number and the characteristic information of each node device.
Optionally, the characteristic information includes node voltage, node current, adjacent node voltage, adjacent node current when the node device fails.
Optionally, the inputting the characteristic information of the fault node device into the distributed depth network model so as to locate the fault node device based on the output of the distributed depth network model includes:
and inputting the node voltage, the node current, the adjacent node voltage and the adjacent node current when the node device fails into the distributed depth network model to obtain the device number of the failed node device and the number of the failed node device so as to position the failed node device by using the device number.
In a second aspect, the present application discloses a fault device positioning device, applied to a node device, comprising:
the data acquisition module is used for acquiring a fault sample and a sample label corresponding to the fault sample;
the model generation module is used for training the fault sample and the sample label by using an artificial neural network at each node device based on information forward propagation and error reverse propagation, and establishing a mapping relation between the device number and the characteristic information of each node device so as to obtain a distributed depth network model;
and the device positioning module is used for judging whether the fault node device is detected, if so, inputting the characteristic information of the fault node device into the distributed depth network model so as to position the fault node device based on the output of the distributed depth network model.
In a third aspect, the present application discloses an electronic device comprising:
a memory for storing a computer program;
and a processor for executing the computer program to implement the fault device localization method as described above.
In a fourth aspect, the present application discloses a computer readable storage medium for storing a computer program which, when executed by a processor, implements a fault device localization method as described above.
In the method, firstly, a fault sample and a sample label corresponding to the fault sample are obtained, then, based on information forward propagation and error reverse propagation, each node device trains the fault sample and the sample label by using an artificial neural network, a mapping relation between a device number and characteristic information of each node device is established to obtain a distributed depth network model, finally, whether the fault node device is detected is judged, if yes, the characteristic information of the fault node device is input to the distributed depth network model, and therefore, the fault node device is positioned based on the output of the distributed depth network model. Therefore, after the fault sample and the sample label are obtained, the artificial neural network can be used for training, the relation between the device number and the characteristic information of the node device is established, so that a distributed depth network model is obtained, and when the node device breaks down, the characteristic information of the fault node can be analyzed based on the distributed depth network model, so that the fault node can be positioned. In this way, an artificial neural network model can be built and trained at each node by using a distributed deep learning algorithm, when a fault occurs, fault characteristic information is input into the trained neural network model, and a fault device number is output to obtain, so that fault diagnosis of the node device is realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a fault device locating method provided in the present application;
FIG. 2 is a schematic diagram of a distributed deep network model provided in the present application;
FIG. 3 is a flowchart of a specific fault device location method provided in the present application;
fig. 4 is a topology structure diagram of an artificial neural network provided in the present application;
fig. 5 is a schematic structural diagram of a fault device positioning device provided in the present application;
fig. 6 is a block diagram of an electronic device provided in the present application.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the prior art, fault diagnosis for a protection system still depends on an operator to judge the defect position according to a network message, mass data generated by wide connection of secondary equipment in an interval cannot be rapidly analyzed, and problems such as loss and distortion of fault information can occur in the processes of acquisition, uploading and analysis, so that the judging result of the existing method is seriously influenced by the information confidence coefficient, and the efficiency is low.
In order to overcome the technical problems, the application provides a fault device positioning method, a device, equipment and a storage medium, wherein an artificial neural network model can be constructed and trained at each node by using a distributed deep learning algorithm, when a fault occurs, fault characteristic information is input into the trained neural network model, and a fault device number is obtained through output, so that fault diagnosis of the node device is realized.
Referring to fig. 1, an embodiment of the present invention discloses a fault device positioning method, which is applied to a node device, and includes:
and S11, acquiring a fault sample and a sample label corresponding to the fault sample.
In this embodiment, a distributed depth network model needs to be built first, as shown in fig. 2, which is a schematic structural diagram of the distributed depth network model, where each node device in the distributed depth network model, in this application, each distance protection device, is a node of the distributed depth network model, and building the distributed depth network model needs to obtain a fault sample first, and a sample tag corresponding to the fault sample, where the fault sample may be obtained from a preset structured database. The structured database is a database which is built in advance and is based on a large number of collected fault samples, and the fault samples comprise device information of a distance protection device which has historically failed and optical fiber link information corresponding to the distance protection device.
And step S12, training the fault samples and the sample labels by using an artificial neural network at each node device based on information forward propagation and error reverse propagation, and establishing a mapping relation between the device numbers and the characteristic information of each node device to obtain a distributed depth network model.
In this embodiment, the obtained fault samples and sample labels need to be input into an artificial neural network (Artificial Neural Network, ANN) so that the fault samples and the sample labels are trained by the artificial neural network based on forward propagation of information, so as to sequentially determine outputs of an input layer, a hidden layer and an output layer in the artificial neural network, and determine predicted outputs based on forward propagation of information through outputs of all neurons in each of the input layer, the hidden layer and the output layer. After the prediction output based on the information forward propagation is obtained, verification based on error reverse propagation is needed, a loss function between the prediction output and a sample label is needed to be determined through the error reverse propagation, and a weight parameter and a bias parameter of the artificial neural network are determined through the obtained loss function, and meanwhile, the error of the artificial neural network is reduced through the weight parameter and the bias parameter. And finally, establishing a mapping relation between the device number of the distance protection device and the characteristic information through the artificial neural network after error reduction so as to obtain a final distributed depth network model.
And S13, judging whether a fault node device is detected, if so, inputting the characteristic information of the fault node device into the distributed depth network model so as to position the fault node device based on the output of the distributed depth network model.
In this embodiment, after detecting that a node device that generates a fault exists, that is, after detecting that a distance protection device that generates a fault exists, the feature information of the node device that generates a fault may be set. And inputting the voltage and the current of the nodes and the voltage and the current of the adjacent nodes into a trained distributed depth network model, so that the distributed depth network model outputs the device number and the device number of all the node devices generating faults in the distributed depth network according to the input characteristic information and the pre-established mapping relation, and positioning the fault devices through the device numbers.
Therefore, in this embodiment, a fault sample and a sample label corresponding to the fault sample are first obtained, then the fault sample and the sample label are trained by using an artificial neural network at each node device based on forward information propagation and reverse error propagation, a mapping relationship between a device number and feature information of each node device is established to obtain a distributed depth network model, and finally whether a fault node device is detected is judged, if yes, the feature information of the fault node device is input to the distributed depth network model, so that the fault node device is positioned based on the output of the distributed depth network model. Therefore, after the fault sample and the sample label are obtained, the artificial neural network can be used for training, the relation between the device number and the characteristic information of the node device is established, so that a distributed depth network model is obtained, and when the node device breaks down, the characteristic information of the fault node can be analyzed based on the distributed depth network model, so that the fault node can be positioned. In this way, an artificial neural network model can be built and trained at each node by using a distributed deep learning algorithm, when a fault occurs, fault characteristic information is input into the trained neural network model, and a fault device number is output to obtain, so that fault diagnosis of the node device is realized.
Based on the foregoing embodiments, after the fault samples and the sample labels are obtained, the fault samples and the sample labels need to be trained by using the artificial neural network to obtain the distributed depth network model, so that the embodiment describes how to determine the distributed depth network model in detail. Referring to fig. 2, the embodiment of the invention discloses a fault device positioning method, which comprises the following steps:
and S21, acquiring a fault sample and a sample label corresponding to the fault sample.
And S22, training the fault sample and the sample label by using an artificial neural network based on information forward propagation so as to sequentially determine the output of an input layer, a hidden layer and an output layer in the artificial neural network.
In this embodiment, as shown in fig. 3, the fault samples and the sample tags need to be trained by using an artificial neural network at each node device through information forward propagation and error reverse propagation, and the fault samples and the sample tags are first trained by using information forward propagation. The artificial neural network comprises an input layer, a hidden layer and a characteristic set X acquired by a node i when the input layer of the output layer is a fault i ＝[x 1 ,x 2 ,…,x p ]The method comprises the steps of carrying out a first treatment on the surface of the The output layer is the device fault state y with the node number i i If the position with the number i fails, y is i =1, otherwise y i =0. In the forward propagation of information, the output of a neuron in an artificial neural network is as follows:
wherein, the liquid crystal display device comprises a liquid crystal display device,
an output representing neuron a located at layer n+1; m represents the total number of neurons of the n-th layer; ω represents the connection weight between neurons; b represents bias; the superscript of ω and b represents the index of the layer in which it is located, and the subscript represents the index of the neurons in the surface layer; the activation function σ adopts Sigmoid.
And step S23, determining the prediction output based on the forward propagation of the information based on the output of the input layer, the hidden layer and the output layer.
In this embodiment, after determining the output of the neurons in the artificial neural network, the output of each of the neurons in the input layer, the hidden layer and the output layer may be determined, so as to determine the predicted output based on the forward propagation of the information through the output of each of the neurons.
And step S24, determining a loss function between the predicted output and the sample label based on error back propagation.
In this embodiment, after obtaining the prediction output based on the information forward propagation, it is necessary to verify the prediction output based on the information forward propagation by using the error reverse propagation, and it is necessary to first determine a loss function J between the prediction output and the sample tag, where the loss function J is used to describe a gap between the prediction output and the real tag, and in combination with the data type of the protection system, cross entropy is selected as the loss function J, and an expression of the loss function is as follows:
wherein θ represents the weight parameter ω and the bias parameter b; n represents the total number of fault samples; t is t nq A real label representing the sample; y is nq Representing a predicted output of the artificial neural network; superscript n represents the sample index; the subscript q represents the index of the data within the sample.
And S25, determining a weight parameter and a bias parameter of the artificial neural network through the loss function so as to reduce the error of the artificial neural network through the weight parameter and the bias parameter.
In this embodiment, the weight parameter and the bias parameter of the artificial neural network are determined through the loss function, that is, the minimum value of the loss function J is solved through a back propagation algorithm to obtain the weight parameter ω and the bias parameter b in the neural network, and the obtained weight parameter and bias parameter are used to update the original parameters in the artificial neural network, so as to reduce the error of the artificial neural network.
Step S26, obtaining the device number and the characteristic information of each node device, and inputting the device number and the characteristic information into the artificial neural network for training so as to establish a mapping relation between the device number and the characteristic information of each node device, thereby obtaining a distributed depth network model.
In this embodiment, the device number and the feature information of each node device need to be acquired, where the feature information includes the voltage and the current when the node fails and the voltage and the current of the neighboring node at the time, after the device number and the feature information of each node device are determined, distributed computation needs to be performed at each node, the feature information is used as a feature quantity and is input into an artificial neural network to perform training, a mapping model of the failed device number and the feature information, that is, a mapping relation between the failed device number and the feature information is established, and the mapping relation is an abstract mapping relation, where the expression is as follows:
y i ＝f(X i )
wherein X is i Representing a characteristic information set acquired by an ith node during fault, namely a node voltage and current and an adjacent node voltage and current data set; y is i Representing the fault state of the node distance protection device, if the position with the node number of i fails, y i =1, otherwise y i =0; q is the total number of distance protection devices in the network.
In this way, when the node device fails and the information of the failed node is not acquired, the information of the adjacent node device can be acquired and input into the distributed depth network model, so that the device number of the failed node device can be obtained through judging the information of the adjacent node to position the failed node.
And step S27, judging whether a fault node device is detected, if so, inputting the characteristic information of the fault node device into the distributed depth network model so as to position the fault node device based on the output of the distributed depth network model.
It should be noted that, for more detailed description of step S21 and step S27, reference may be made to the foregoing embodiments, and details thereof are not described herein.
Therefore, after obtaining a fault sample and a sample label, the present embodiment firstly needs to train the fault sample and the sample label by using an artificial neural network based on information forward propagation, so as to sequentially determine outputs of an input layer, a hidden layer and an output layer in the artificial neural network, determine predicted outputs based on the information forward propagation based on the outputs of the input layer, the hidden layer and the output layer, determine a loss function between the predicted outputs and the sample label based on error backward propagation, determine weight parameters and bias parameters of the artificial neural network through the loss function, reduce errors of the artificial neural network through the weight parameters and the bias parameters, and finally determine whether a fault node device is detected, if so, input characteristic information of the fault node device into the distributed depth network model, so as to position the fault node device based on the output of the distributed depth network model. Therefore, when the node device fails and the information of the failed node is not acquired, the information of the adjacent node device can be acquired and input into the distributed depth network model, so that the device number of the failed node device can be obtained through judging the information of the adjacent node to position the failed node.
Referring to fig. 5, an embodiment of the present invention discloses a fault device positioning device, which is applied to a node device, and includes:
a data acquisition module 11, configured to acquire a fault sample and a sample tag corresponding to the fault sample;
the model generating module 12 is configured to train the fault sample and the sample label at each node device by using an artificial neural network based on information forward propagation and error reverse propagation, and establish a mapping relationship between a device number and feature information of each node device to obtain a distributed depth network model;
and the device positioning module 13 is configured to determine whether a fault node device is detected, and if so, input feature information of the fault node device to the distributed depth network model, so as to position the fault node device based on output of the distributed depth network model.
Therefore, in this embodiment, a fault sample and a sample label corresponding to the fault sample are first obtained, then the fault sample and the sample label are trained by using an artificial neural network at each node device based on forward information propagation and reverse error propagation, a mapping relationship between a device number and feature information of each node device is established to obtain a distributed depth network model, and finally whether a fault node device is detected is judged, if yes, the feature information of the fault node device is input to the distributed depth network model, so that the fault node device is positioned based on the output of the distributed depth network model. Therefore, after the fault sample and the sample label are obtained, the artificial neural network can be used for training, the relation between the device number and the characteristic information of the node device is established, so that a distributed depth network model is obtained, and when the node device breaks down, the characteristic information of the fault node can be analyzed based on the distributed depth network model, so that the fault node can be positioned. In this way, an artificial neural network model can be built and trained at each node by using a distributed deep learning algorithm, when a fault occurs, fault characteristic information is input into the trained neural network model, and a fault device number is output to obtain, so that fault diagnosis of the node device is realized.
In some embodiments, the data acquisition module 11 may specifically include:
and the data acquisition unit is used for acquiring the device information of the historical fault node device, the optical fiber link corresponding to the historical fault node device and the sample label corresponding to the historical fault node device based on the structured database.
In some embodiments, the model generating module 12 may specifically include:
the first output determining unit is used for training the fault sample and the sample label by using an artificial neural network based on information forward propagation so as to sequentially determine the output of an input layer, a hidden layer and an output layer in the artificial neural network;
and a second output determining unit for determining a predicted output based on the information forward propagation based on the outputs of the input layer, the hidden layer and the output layer.
In some embodiments, the model generating module 12 may specifically include:
a loss function determining unit configured to determine a loss function between the predicted output and the sample tag based on error back propagation;
and the parameter determining unit is used for determining the weight parameter and the bias parameter of the artificial neural network through the loss function so as to reduce the error of the artificial neural network through the weight parameter and the bias parameter.
In some embodiments, the model generating module 12 may specifically include:
and the mapping relation establishing unit is used for acquiring the device number and the characteristic information of each node device, and inputting the device number and the characteristic information into the artificial neural network for training so as to establish the mapping relation between the device number and the characteristic information of each node device.
In some embodiments, the device positioning module 13 may specifically include:
and the device positioning unit is used for inputting the node voltage, the node current, the adjacent node voltage and the adjacent node current when the node device fails into the distributed depth network model to obtain the device number of the failed node device and the number of the failed node device so as to position the failed node device by using the device number.
Further, the embodiment of the present application further discloses an electronic device, and fig. 6 is a structural diagram of the electronic device 20 according to an exemplary embodiment, where the content of the drawing is not to be considered as any limitation on the scope of use of the present application.
Fig. 6 is a schematic structural diagram of an electronic device 20 according to an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input output interface 25, and a communication bus 26. Wherein the memory 22 is configured to store a computer program that is loaded and executed by the processor 21 to implement the relevant steps in the fault device localization method disclosed in any of the foregoing embodiments. In addition, the electronic device 20 in the present embodiment may be specifically an electronic computer.
In this embodiment, the power supply 23 is configured to provide an operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and an external device, and the communication protocol to be followed is any communication protocol applicable to the technical solution of the present application, which is not specifically limited herein; the input/output interface 25 is used for acquiring external input data or outputting external output data, and the specific interface type thereof may be selected according to the specific application requirement, which is not limited herein.
The memory 22 may be a carrier for storing resources, such as a read-only memory, a random access memory, a magnetic disk, or an optical disk, and the resources stored thereon may include an operating system 221, a computer program 222, and the like, and the storage may be temporary storage or permanent storage.
The operating system 221 is used for managing and controlling various hardware devices on the electronic device 20 and computer programs 222, which may be Windows Server, netware, unix, linux, etc. The computer program 222 may further include a computer program that can be used to perform other specific tasks in addition to the computer program that can be used to perform the fault device localization method performed by the electronic apparatus 20 as disclosed in any of the previous embodiments.
Further, the application also discloses a computer readable storage medium for storing a computer program; wherein the computer program, when executed by a processor, implements the fault device localization method disclosed previously. For specific steps of the method, reference may be made to the corresponding contents disclosed in the foregoing embodiments, and no further description is given here.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, so that the same or similar parts between the embodiments are referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of functionality in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The foregoing has outlined the detailed description of the preferred embodiment of the present application, and the detailed description of the principles and embodiments of the present application has been provided herein by way of example only to facilitate the understanding of the method and core concepts of the present application; meanwhile, as those skilled in the art will have modifications in the specific embodiments and application scope in accordance with the ideas of the present application, the present description should not be construed as limiting the present application in view of the above.
Claims (10)
1. A fault device localization method, applied to a node device, comprising:
obtaining a fault sample and a sample label corresponding to the fault sample;
training the fault samples and the sample labels by using an artificial neural network on each node device based on information forward propagation and error reverse propagation, and establishing a mapping relation between device numbers and characteristic information of each node device to obtain a distributed depth network model;
and judging whether a fault node device is detected, if so, inputting the characteristic information of the fault node device into the distributed depth network model so as to position the fault node device based on the output of the distributed depth network model.
2. The fault device localization method of claim 1, wherein the obtaining a fault sample and a sample tag corresponding to the fault sample comprises:
and acquiring device information of the historical fault node device, an optical fiber link corresponding to the historical fault node device and a sample label corresponding to the historical fault node device based on a structured database.
3. The fault device localization method of claim 2, wherein training the fault samples and the sample tags at each node device using an artificial neural network based on information forward propagation and error reverse propagation comprises:
training the fault sample and the sample label by using an artificial neural network based on information forward propagation to sequentially determine the output of an input layer, a hidden layer and an output layer in the artificial neural network;
a predicted output based on the information forward propagation is determined based on the outputs of the input layer, hidden layer, and output layer.
4. The fault device localization method of claim 3, wherein training the fault samples and the sample tags at each node device based on information forward propagation and error reverse propagation using an artificial neural network comprises:
determining a loss function between the predicted output and the sample tag based on error back propagation;
and determining a weight parameter and a bias parameter of the artificial neural network through the loss function so as to reduce the error of the artificial neural network through the weight parameter and the bias parameter.
5. The fault device locating method according to claim 1, wherein the establishing a mapping relationship between the device number and the feature information of each node device includes:
and acquiring the device number and the characteristic information of each node device, and inputting the device number and the characteristic information into the artificial neural network for training so as to establish a mapping relation between the device number and the characteristic information of each node device.
6. The fault device localization method of any one of claims 1 to 5, wherein the characteristic information comprises a node voltage, a node current, a neighboring node voltage, a neighboring node current at the time of a node device fault.
7. The fault device localization method of claim 6, wherein the inputting the feature information of the fault node device to the distributed depth network model to localize the fault node device based on an output of the distributed depth network model comprises:
and inputting the node voltage, the node current, the adjacent node voltage and the adjacent node current when the node device fails into the distributed depth network model to obtain the device number of the failed node device and the number of the failed node device so as to position the failed node device by using the device number.
8. A fault device locating device, characterized by being applied to a node device, comprising:
the data acquisition module is used for acquiring a fault sample and a sample label corresponding to the fault sample;
the model generation module is used for training the fault sample and the sample label by using an artificial neural network at each node device based on information forward propagation and error reverse propagation, and establishing a mapping relation between the device number and the characteristic information of each node device so as to obtain a distributed depth network model;
and the device positioning module is used for judging whether the fault node device is detected, if so, inputting the characteristic information of the fault node device into the distributed depth network model so as to position the fault node device based on the output of the distributed depth network model.
9. An electronic device, comprising:
a memory for storing a computer program;
a processor for executing the computer program to implement the fault device localization method of any one of claims 1 to 7.
10. A computer readable storage medium for storing a computer program which, when executed by a processor, implements the fault device localization method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310394949.3A CN116184122A (en) | 2023-04-13 | 2023-04-13 | Fault device positioning method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310394949.3A CN116184122A (en) | 2023-04-13 | 2023-04-13 | Fault device positioning method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116184122A true CN116184122A (en) | 2023-05-30 |
Family
ID=86436834
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310394949.3A Pending CN116184122A (en) | 2023-04-13 | 2023-04-13 | Fault device positioning method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116184122A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117031182A (en) * | 2023-10-09 | 2023-11-10 | 威海锐恩电子股份有限公司 | Method and system for detecting abnormal telemetering value of substation terminal |
-
2023
- 2023-04-13 CN CN202310394949.3A patent/CN116184122A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117031182A (en) * | 2023-10-09 | 2023-11-10 | 威海锐恩电子股份有限公司 | Method and system for detecting abnormal telemetering value of substation terminal |
| CN117031182B (en) * | 2023-10-09 | 2024-01-09 | 威海锐恩电子股份有限公司 | Method and system for detecting abnormal telemetering value of substation terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109213842A (en) | A kind of intelligent customer service implementation method, device and storage medium | |
| CN116184122A (en) | Fault device positioning method, device, equipment and storage medium | |
| CN113746663B (en) | Performance degradation fault root cause positioning method combining mechanism data and dual drives | |
| CN108830335A (en) | Photovoltaic plant fault early warning method and system | |
| Lee et al. | Energy consumption prediction system based on deep learning with edge computing | |
| CN116245033A (en) | Artificial intelligent driven power system analysis method and intelligent software platform | |
| CN116205265A (en) | Power grid fault diagnosis method and device based on deep neural network | |
| CN113360555A (en) | Fault diagnosis and analysis method and system based on big data of power grid secondary equipment | |
| Milanovic et al. | Modeling business process availability | |
| CN106910075A (en) | Intelligent processing system and method that client mobile communication is complained | |
| CN117236380A (en) | Power system fault prediction method, system, electronic equipment and medium | |
| KR102107689B1 (en) | Apparatus and method for analyzing cause of network failure | |
| CN115603464B (en) | Intelligent generation management system for power grid operation ticket based on digital twin | |
| CN115618746B (en) | Intelligent equipment diagnosis and analysis method and system based on cloud service | |
| CN108023740A (en) | The indicating risk method and apparatus of exception information in monitoring | |
| CN116170203A (en) | Prediction method and system for security risk event | |
| Wang et al. | QoS Attributes Prediction with Attention-based LSTM Network for Mobile Services | |
| CN117454315B (en) | Man-machine terminal picture data interaction method and system | |
| CN112465259B (en) | Switch fault prediction method based on deep neural network | |
| CN117391456B (en) | Village management method and service platform system based on artificial intelligence | |
| CN114862121B (en) | Associated infrastructure system modeling method and device considering human factor influence | |
| CN117749523A (en) | Abnormal flow detection method, device, equipment and medium of intelligent Internet of things equipment | |
| CN114462494A (en) | Intelligent lock fault prediction method, system, electronic device and readable medium | |
| Borjas et al. | An architecture for integrating an Expert System with NEPLAN in a DMS/EMS operational environment | |
| Oprea | Mapping ontologies in an air pollution monitoring and control agent-based system |
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 |