CN111751655B - Fault self-healing method and device for distribution line, computer equipment and storage medium - Google Patents
Fault self-healing method and device for distribution line, computer equipment and storage medium Download PDFInfo
- Publication number
- CN111751655B CN111751655B CN202010479347.4A CN202010479347A CN111751655B CN 111751655 B CN111751655 B CN 111751655B CN 202010479347 A CN202010479347 A CN 202010479347A CN 111751655 B CN111751655 B CN 111751655B
- Authority
- CN
- China
- Prior art keywords
- distribution
- feeder
- information
- fault
- distribution line
- 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.)
- Active
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
- G01R31/50—Testing of electric apparatus, lines, cables or components for short-circuits, continuity, leakage current or incorrect line connections
- G01R31/58—Testing of lines, cables or conductors
-
- 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 utility model relates to a distribution network line fault self-healing method, a distribution network line fault self-healing device, a computer device and a storage medium, the distribution network line fault self-healing method comprises the steps of firstly obtaining a plurality of state information parameters of each distribution line, respectively inputting a plurality of information arrays into a fault detection model obtained by pre-training, and determining whether each distribution line has a fault according to the output result of the fault detection model. If when some distribution lines among many distribution lines broke down, control interconnection switch was closed, and trouble distribution lines and normal operating's distribution lines switch on, and the normal distribution lines of operation gives the distribution lines power supply that breaks down to for connecting the load power supply on the distribution lines that breaks down, with the trouble of elimination distribution lines. The distribution line fault self-healing method solves the problem that an existing distribution line fault processing method in the prior art is low in automation degree, and achieves the technical effect of improving distribution line fault processing automation.
Description
Technical Field
The application relates to the technical field of distribution networks, in particular to a fault self-healing method, device, equipment and storage medium for a distribution line.
Background
And the feeder line is a set of conductive equipment among different power distribution centers in a distribution network, one end of the feeder line is connected with a bus on the low-voltage side of the transformer substation to obtain electric energy, and the other end of the feeder line is connected to a distribution line through a distribution transformer or a distribution switch. Since the distribution line is connected to a load, the safe operation of the distribution line is directly related to the reliability of power supply on the customer side, and if the distribution line fails, the load connected to the distribution line inevitably fails, thereby lowering the reliability of power supply in the district. However, line faults are unavoidable due to various possible changes in the operating environment and equipment life and quality problems of the distribution line. Therefore, timely diagnosis and rapid recovery of distribution line faults are critical to the reliability of the operation of the distribution network. At present, the fault of the power distribution network line is mainly processed by acquiring and analyzing the fault information of the power distribution network line by using information acquisition equipment of secondary equipment of a ring main unit, and then, a worker performs field processing after determining the fault position. Therefore, the existing distribution line fault processing method has low automation degree.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a method, an apparatus, a device, and a storage medium for self-healing of a fault of a distribution line.
A fault self-healing method of a distribution line is applied to a distribution network system, the distribution network system comprises a plurality of distribution lines, two adjacent distribution lines are connected through a contact switch, and the method comprises the following steps:
acquiring a plurality of state information parameters of each distribution line, wherein the state information parameters are used for representing the operation state of the distribution line;
determining an information array of each distribution line according to the plurality of state information parameters to obtain a plurality of information arrays;
respectively inputting the plurality of information arrays into a fault detection model obtained by pre-training, and determining whether each distribution line has a fault according to an output result of the fault detection model;
and if the distribution lines in the plurality of distribution lines have faults, controlling the connection switch to be closed.
In one embodiment, the distribution line includes a feeder line, and the status information parameter includes at least: the feeder switch switching position information, the feeder current information, the feeder protection action information and the feeder overhaul state information.
In one embodiment, the plurality of information arrays are respectively input into a fault detection model obtained by pre-training to obtain a state characteristic parameter corresponding to each distribution line;
and determining whether the distribution line has a fault according to the state characteristic parameters.
In one embodiment, averaging a plurality of state characteristic parameters to obtain a result average;
and if the result mean value does not exceed the preset range, determining that part of the distribution lines in the plurality of distribution lines have faults, and controlling the connection switch to be closed.
In one embodiment, if the result mean value exceeds a preset range, all the distribution lines are determined to be in fault or all the distribution lines are determined to be in normal operation, and the contact switch is controlled to be switched off.
In one embodiment, obtaining historical status information parameters of a plurality of feeders comprises: historical feeder switch opening and closing position information, historical feeder current information, historical feeder protection action information and historical feeder overhaul state information;
performing training processing operations, the training processing operations comprising: inputting the state information parameters of the plurality of feeder lines into an initial fault detection model for processing to obtain output data of the initial fault detection model, and calculating an error between the output data and preset expected output data according to a preset loss function;
and when the error is smaller than a preset threshold value, taking the initial fault detection model as the fault detection model.
In one embodiment, the fault detection model is a two-dimensional matrix model.
A fault self-healing device for distribution lines, the device comprising:
the state information parameter acquisition module is used for acquiring a plurality of state information parameters of each distribution line, wherein the state information parameters are used for representing the running state of the distribution lines;
the information array determining module is used for determining the information array of each distribution line according to the plurality of state information parameters to obtain a plurality of information arrays;
the fault determining module is used for respectively inputting the plurality of information arrays into a fault detection model obtained through pre-training and determining whether each distribution line has a fault according to an output result of the fault detection model;
and the contact switch control module is used for controlling the contact switch to be closed if part of the distribution lines have faults.
A computer device comprising a memory storing a computer program and a processor implementing the steps of the method as described above when executing the computer program.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method as set forth above.
The embodiment of the application provides a distribution network line's fault self-healing method, acquires earlier every a plurality of state information parameters of distribution line then obtain a plurality of information arrays, then will a plurality of information arrays input the fault detection model that the training obtained in advance respectively, according to every can be confirmed to fault detection model's output result whether distribution line breaks down. If when some distribution lines among many distribution lines broke down, control tie switch is closed, trouble distribution lines and normal operating's distribution lines switch on, and the operation is normal distribution lines gives out the trouble distribution lines power supply to for connecting in breaking down load power supply on the distribution lines to eliminate distribution lines ' trouble, realize trouble distribution lines ' fault self-healing. The fault self-healing method for the distribution network line, provided by the embodiment of the application, solves the problem that the existing fault processing method for the distribution line in the prior art is low in automation degree, and achieves the technical effect of improving the fault processing automation of the distribution line.
Drawings
Fig. 1 is a schematic diagram of a distribution network system in one embodiment;
FIG. 2 is a schematic flow chart illustrating a method for self-healing a fault on a distribution line according to an embodiment;
fig. 3 is a schematic flow chart illustrating a method for self-healing a fault of a distribution line in an embodiment;
fig. 4 is a schematic flow chart illustrating a method for self-healing a fault of a distribution line in an embodiment;
FIG. 5 is a schematic flow chart illustrating a method for self-healing a fault on a distribution line according to an embodiment;
FIG. 6 is a block diagram of a fault self-healing device for distribution lines in one embodiment;
fig. 7 is an application environment diagram of the fault self-healing method for the distribution line in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Referring to fig. 1, a distribution network system 10 may be provided by the fault self-healing method for a distribution line according to the embodiment of the present disclosure, where the distribution network system 10 includes a plurality of distribution lines 100, and two adjacent distribution lines 100 are connected through a tie switch 140. Each of the distribution lines 100 may include: a feeder 110, a feeder switch 120, a feeder protection device, a load 130 connected to the feeder 110, and a central control device, etc. The following embodiment specifically illustrates an example in which the fault self-healing method for the distribution line is applied to a central control device in the distribution network system 10.
Referring to fig. 2, the method for self-healing a fault of a distribution line includes the following steps:
s100, obtaining a plurality of state information parameters of each distribution line, wherein the state information parameters are used for representing the operation state of the distribution line.
The distribution lines 100 refer to working lines in a power distribution network, and are used for realizing power transmission for the power distribution network, and each distribution line 100 may include: feeder 110, feeder switch 120, feeder protection equipment, and load 130 connected to feeder 110, among others. Two ends of the feeder 110 are respectively connected to different power distribution centers, such as a 110KV substation, a 10KV substation, and the like. The number of the feeder switches 120 may be one or more, and a plurality of the feeder switches 120 are respectively located at different nodes of the feeder 110 and at two ends of the feeder 110, and are used for controlling connection and disconnection between the feeder 110 and the distribution center at two ends. Different loads 130 may be connected to the feeder 110 and two ends of the feeder 110, and the feeder 110 is configured to transmit the electric energy of the power distribution center to the loads 130 to supply power to the loads 130. The status information parameter is used to characterize the operation status of the power distribution line, and may include, for example, the voltage strength, the current magnitude, the electric field strength, the load magnitude, the feeder status, the action status of the feeder protection device, and the like of the power distribution line 100. In this embodiment, the number and the type of the state information parameters are not limited at all, and may be specifically selected according to actual needs.
S200, determining an information array of each distribution line according to the plurality of state information parameters to obtain a plurality of information arrays.
The plurality of state information parameters refer to parameters representing the operation state of the distribution line 100, and the information array is formed by integrating and processing the operation state parameters according to a certain rule and has an array with the operation state information of the distribution line 100. For example, when the status information parameters are the voltage intensity, the current intensity, the electric field intensity, the load intensity, the feeder line status, and the action status of the feeder line protection device of the distribution line 100, the voltage intensity, the current intensity, the electric field intensity, the load intensity, the feeder line status, and the action status of the feeder line protection device of the distribution line 100 may be subjected to data processing by using a binary counting method to form parameters that are easy to identify and calculate. For example: when the voltage intensity, the current intensity, the electric field intensity and the load intensity exceed preset values, the running state parameters of the voltage, the current, the electric field and the load are all processed to be 1, and when the voltage intensity, the current intensity, the electric field intensity and the load intensity do not exceed the preset values, the running state parameters of the voltage, the current, the electric field and the load are all processed to be 0; when the operation state of the feeder 110 is normal, the operation state parameter of the feeder state is 0, and when the operation state of the feeder 110 is abnormal, for example, in a maintenance state, the operation state parameter of the feeder state is 1; when the feeder line protection device acts, the operating state parameter of the feeder line protection device is 1, and when the feeder line protection device does not act, the operating state parameter of the feeder line protection device is 0. By analogy, the status information parameters of each distribution line 100 are subjected to preliminary processing to form an array or rectangle of information containing 0 and 1, which can be subjected to calculation processing. The plurality of operation state parameters in each distribution line 100, that is, the plurality of state information parameters form an array, the plurality of distribution lines 100 correspond to different information arrays respectively, and the plurality of information arrays can be obtained by the plurality of distribution lines 100.
S300, respectively inputting the plurality of information arrays into a fault detection model obtained through pre-training, and determining whether each distribution line has a fault according to an output result of the fault detection model.
The fault detection model is a model obtained by pre-training, and a training mode can be determined according to actual conditions. The fault detection model includes various state parameters of the operating state parameters of the distribution line, such as voltage strength, current magnitude, electric field strength, load magnitude, feeder line state, and action state of feeder line protection equipment, for implementing detection on the distribution line 100. The input of the fault detection model is the plurality of information arrays, and each information array inevitably obtains a corresponding output result after being input to the fault detection model, and the output result can be an information array or a specific parameter or value. Whether the distribution line 100 has a fault can be judged according to the parameters or the values. For example, in step S200, a binary counting method is used to process a plurality of status information parameters of the distribution line 100, each parameter of the distribution line 100 corresponds to one information array, each information array is an information array regarding the operating status of the distribution line 100, which is composed of 0 and 1, for example, [ 0110 ], the information array is input into the fault detection model, and a characteristic value or an average value thereof is calculated to obtain a fixed value, for example, 0 or 1, 0 indicates that the distribution line 100 is in a normal operating status, and 1 indicates that the distribution line 100 is in a fault status.
S400, if a part of the distribution lines in the distribution lines have faults, controlling the connection switch to be closed.
The plurality of distribution lines 100 operate independently of each other, and one interconnection switch 140 is connected between the plurality of distribution lines 100. When any distribution line 100 breaks down, only need close this trouble distribution line 100 and other arbitrary normal operating the interconnection switch 140 between the distribution line 100, other normal work distribution line 100 alright for this trouble distribution line 100 power supply to the load 130 power supply of connecting with trouble distribution line 100, in order to reach the trouble of eliminating trouble distribution line 100, realize the purpose of self-healing. However, when all the distribution lines 100 have faults, the interconnection switch 140 is not required to be closed, and the interconnection switch 140 is required to be opened, so that the power distribution network can be conveniently repaired in a power failure mode. Similarly, when all the distribution lines 100 are normally operated, the interconnection switch 140 is not required to be closed, and the interconnection switch 140 is opened, so that the distribution lines 100 are independently operated, and the operation independence and stability of the distribution lines 100 are improved.
The embodiment provides a fault self-healing method for distribution network lines, which includes the steps of firstly obtaining a plurality of state information parameters of each distribution line, obtaining a plurality of information arrays, respectively inputting the plurality of information arrays into a fault detection model obtained through pre-training, and determining whether each distribution line has a fault according to an output result of the fault detection model. If when some distribution lines 100 among many distribution lines 100 break down, control tie switch 140 is closed, trouble distribution lines 100 and normal operating's distribution lines 100 switch-on, the operation is normal distribution lines 100 gives out the trouble distribution lines 100 supplies power to connect in breaking down load 130 on the distribution lines 100 supplies power, with the trouble of elimination distribution lines 100, realize the trouble self-healing of trouble distribution lines. The fault self-healing method for the distribution network line provided by the embodiment solves the problem that the existing fault processing method for the distribution line 100 in the prior art is low in automation degree, and achieves the technical effect of improving the automation of fault processing for the distribution line 100.
In one embodiment, the distribution line includes a feeder line, and the status information parameters include at least: the feeder switch switching position information, the feeder current information, the feeder protection action information and the feeder overhaul state information.
The state information parameter is used for characterizing the operation state of the distribution line, and for example, at least comprises: the feeder switch switching position information, the feeder current information, the feeder protection action information and the feeder overhaul state information. The switching position information of the feeder switch comprises two types: the feeder switch 120 is in an open position and the feeder switch 120 is in an closed position. The feeder current information includes two types: the feeder 110 current is greater than a predetermined current and the feeder 110 current is not greater than the predetermined current. The feeder protection action information includes two kinds: the feeder protection device is active and the feeder protection device is inactive. The feeder line overhaul state information comprises two types: the feeder 110 is in a service state and the feeder 110 is in a non-service state. The feeder switch opening and closing position information, the feeder current information, the feeder protection action information and the feeder overhaul state information can be acquired through corresponding electrical signals or sensors, electric meters and the like. The status information parameter may also include other information, and this embodiment is not particularly limited, and may be specifically selected according to an actual situation.
Referring to fig. 3, in one embodiment, step S300 includes:
s310, inputting the plurality of information arrays into a fault detection model obtained through pre-training respectively to obtain state characteristic parameters corresponding to each distribution line.
Each information array may be a matrix or an array, for example, each information array may be a matrix including 0 and 1, and the status characteristic parameter is an output result of the fault detection model, may be information, and may also be a specific value, for example, 0 or 1, for characterizing the operating status of the distribution line 100. As described above, the plurality of status information parameters of the distribution lines 100 may be processed by using a binary counting method or the like, so that each parameter of the distribution line 100 corresponds to one information array. Meanwhile, the maintenance state R in the fault detection model may also be constantly set to 0 to reduce the operation processing. For example, when the following condition occurs in the distribution line 100:
the first condition is as follows: the feeder line 110 is in a non-overhaul state, and R is 0; the feeder line protection device does not act, and X is 0; the current of the feeder line 110 exceeds a preset threshold, I is 1; the feeder switch 120 is in a closed position, and K is 1, the information array corresponding to the distribution line 100 is formed as follows: [0011] and (3) inputting [ 0011 ] into the fault detection model, and calculating to obtain that the characteristic value of [ 0011 ] is 0, namely the state characteristic parameter is 0.
Case two: the feeder line 110 is in a non-overhaul state, and R is 0; the feeder line protection device acts, and X is 1; the current of the feeder 110 does not exceed a preset threshold, I ═ 0; when the feeder switch 120 is in the open position, and K is 0, the information array corresponding to the distribution line 100 is formed as follows: [0100] and inputting [ 0100 ] into the fault detection model, and calculating to obtain that the characteristic value of [ 0100 ] is 1, namely the state characteristic parameter is 1.
The fault detection model may be obtained by pre-training, and the fault detection model may be a two-dimensional matrix model or other types of models, please refer to fig. 4, in an embodiment, S310 includes S311 to S313:
s311, obtaining historical state information parameters of the plurality of feeders, wherein the historical state information parameters at least comprise: historical feeder switch opening and closing position information, historical feeder current information, historical feeder protection action information and historical feeder overhaul state information.
The historical feeder switch open-close position information, the historical feeder current information, the historical feeder protection action information and the historical feeder overhaul state information are all used as training samples of the fault detection model, the historical feeder switch open-close position information, the historical feeder current information, the historical feeder protection action information and the historical feeder overhaul state information are the same parameters of the feeder 110, and the only difference is that the historical feeder switch open-close position information, the historical feeder current information, the historical feeder protection action information and the historical feeder overhaul state information are related information data acquired in advance, the feeder switch open-close position information, the historical feeder current information, the historical feeder protection action information and the historical feeder overhaul state information are the same parameters of the feeder 110, and the only difference is that the historical feeder switch open-close position information, the historical feeder protection action information and the historical feeder overhaul state information are related information data acquired in advance, and the feeder switch open-close position information, the historical feeder current information, the historical feeder protection action information and the historical feeder overhaul state information are acquired in advance, The feeder current information, the feeder protection action information and the feeder overhaul state information are information data to be detected, which are acquired by the feeder 110 in real time.
S312, executing training processing operation, wherein the training processing operation comprises the following steps: and inputting the state information parameters of the plurality of feeders into an initial fault detection model for processing to obtain output data of the initial fault detection model, and calculating an error between the output data and preset expected output data according to a preset loss function.
The initial fault detection model can be a two-dimensional rectangle, four parameters a, b, c and d are preset and represent the historical feeder switch opening and closing position information, the historical feeder current information, the historical feeder protection action information and the historical feeder overhaul state information respectively, and a two-dimensional matrix related to the feeder state information is formed. The loss function may be an error calculation formula or a deviation calculation formula, and is configured to calculate an error between the output data and preset expected output data to obtain a plurality of error values.
S313, when the error is smaller than a preset threshold value, taking the initial fault detection model as the fault detection model.
The preset threshold may be specifically set according to an actual situation, for example, 1%, 5%, 10%, and the like, and this embodiment is not specifically limited, and may be specifically set according to an actual situation.
And S320, determining whether the distribution line has a fault according to the state characteristic parameters.
The state characteristic parameters are determined according to the fault detection model and the information array, the state characteristic parameters are characteristic parameters with the feeder line 110 running state information, and whether the distribution line has a fault or not can be determined through the state characteristic parameters. For example, in the above embodiment, when the status characteristic parameter is 1, it indicates that the distribution line 100 has a fault, and when the status characteristic parameter is 0, it indicates that the distribution line 100 has no fault.
Referring to fig. 5, in one embodiment, step S400 includes:
and S410, averaging a plurality of state characteristic parameters to obtain a result average value.
The average value may be an average value, a weighted average value, or any other average value. For example, when a first group of a plurality of state feature parameters is obtained, which are respectively 0, 1, 0, 1, the result mean value is 0.5. And the second group of a plurality of state characteristic parameters are respectively 1, 1 and 1, and the result mean value is 1.
And S420, if the result mean value does not exceed a preset range, determining that part of the distribution lines in the plurality of distribution lines have faults, and controlling the connection switch to be closed.
The preset range is specifically set according to actual conditions, and this embodiment is not specifically limited. For example, the predetermined range is 0 to 1, and 0 and 1 are not included. Then in step S410, if the first set of the mean values of the results is 0.5 and is within the preset range, that is, the preset range is not exceeded, it is determined that a fault occurs on a part of the distribution lines 100 in the plurality of distribution lines 100, and the tie switch 140 is controlled to close to eliminate the fault on the faulty distribution line 100.
And S430, if the result mean value exceeds a preset range, determining that all the distribution lines have faults or all the distribution lines operate normally, and controlling the interconnection switch to be switched off.
Similarly, when the predetermined range is 0 to 1, 0 and 1 are not included. In the two sets of data in step S410, the second set of the result mean value is 1, and if the result mean value exceeds the preset range, it is determined that all the distribution lines 100 are normally operated, and the interconnection switch 140 is controlled to be turned off, so that the distribution lines 100 work independently without affecting each other.
It should be understood that, although the steps in the flowchart are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in the figures may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the steps or stages is not necessarily sequential, but may be performed alternately or alternatively with other steps or at least some of the steps or stages in other steps.
Referring to fig. 6, an embodiment of the present application provides a fault self-healing apparatus 20 for a distribution line, the apparatus including: the system comprises a state information parameter acquisition module 21, an information array determination module 22, a fault determination module 23 and a communication switch control module 24.
The status information parameter obtaining module 21 is configured to obtain a plurality of status information parameters of each distribution line, where the status information parameters are used to represent an operating status of the distribution line;
the information array determining module 22 is configured to determine an information array of each distribution line according to the plurality of status information parameters to obtain a plurality of information arrays;
the fault determining module 23 is configured to input the plurality of information arrays into a fault detection model obtained through pre-training, and determine whether each of the distribution lines has a fault according to an output result of the fault detection model;
the tie switch control module 24 is configured to control the tie switch to be closed if a fault occurs in a part of the distribution lines.
In one embodiment, the fault self-healing apparatus 20 of the distribution line includes a feeder, and the status information parameter includes at least: the feeder switch switching position information, the feeder current information, the feeder protection action information and the feeder overhaul state information.
In an embodiment, the fault determining module 23 is further configured to input the plurality of information arrays into a fault detection model obtained through pre-training, respectively, to obtain a state characteristic parameter corresponding to each distribution line; and determining whether the distribution line has a fault according to the state characteristic parameters.
In one embodiment, the fault determining module 23 is further configured to average a plurality of the state characteristic parameters to obtain a result average; and if the result mean value does not exceed the preset range, determining that part of the distribution lines in the plurality of distribution lines have faults, and controlling the connection switch to be closed.
In one embodiment, the fault determining module 23 is further configured to determine that all of the distribution lines have faults or all of the distribution lines operate normally if the result average value exceeds a preset range, and control the tie switch to be turned off.
In one embodiment, the fault determination module 23 is further configured to obtain historical status information parameters of a plurality of feeders, where the historical status information parameters at least include: historical feeder switch opening and closing position information, historical feeder current information, historical feeder protection action information and historical feeder overhaul state information; performing training processing operations, the training processing operations comprising: inputting the state information parameters of the plurality of feeder lines into an initial fault detection model for processing to obtain output data of the initial fault detection model, and calculating an error between the output data and preset expected output data according to a preset loss function; and when the error is smaller than a preset threshold value, taking the initial fault detection model as the fault detection model.
In one embodiment, in the fault self-healing device 20 of the distribution line, the fault detection model is a two-dimensional matrix model.
The specific definition of the fault self-healing device 20 for the distribution line can be referred to the above definition of the fault self-healing method for the distribution line, and is not described herein again. The modules in the fault self-healing device 20 of the distribution line may be implemented in whole or in part by software, hardware, or a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, there is provided a computer device comprising: the system comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the following steps when executing the computer program:
acquiring a plurality of state information parameters of each distribution line, wherein the state information parameters are used for representing the operation state of the distribution line;
determining an information array of each distribution line according to the plurality of state information parameters to obtain a plurality of information arrays;
respectively inputting the plurality of information arrays into a fault detection model obtained by pre-training, and determining whether each distribution line has a fault according to an output result of the fault detection model;
and if part of the distribution lines in the plurality of distribution lines have faults, controlling the connection switch to be closed.
In one embodiment, the processor, when executing the computer program, further implements: the distribution line comprises a feeder line, and the state information parameters at least comprise: the feeder switch switching position information, the feeder current information, the feeder protection action information and the feeder overhaul state information.
In one embodiment, the processor, when executing the computer program, further implements: respectively inputting the plurality of information arrays into a fault detection model obtained by pre-training to obtain a state characteristic parameter corresponding to each distribution line; and determining whether the distribution line has a fault according to the state characteristic parameters.
In one embodiment, the processor, when executing the computer program, further implements: averaging a plurality of state characteristic parameters to obtain a result average value; and if the result mean value does not exceed the preset range, determining that part of the distribution lines in the plurality of distribution lines have faults, and controlling the connection switch to be closed.
In one embodiment, the processor, when executing the computer program, further implements: and if the result mean value exceeds a preset range, determining that all the distribution lines have faults or all the distribution lines are normal in operation, and controlling the connection switch to be switched off.
In one embodiment, the processor, when executing the computer program, further implements: obtaining historical state information parameters of a plurality of feeders, wherein the historical state information parameters at least comprise: historical feeder switch opening and closing position information, historical feeder current information, historical feeder protection action information and historical feeder overhaul state information; performing training processing operations, the training processing operations comprising: inputting the state information parameters of the plurality of feeder lines into an initial fault detection model for processing to obtain output data of the initial fault detection model, and calculating an error between the output data and preset expected output data according to a preset loss function; and when the error is smaller than a preset threshold value, taking the initial fault detection model as the fault detection model.
In one embodiment, the processor, when executing the computer program, further implements: the fault detection model is a two-dimensional matrix model.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring a plurality of state information parameters of each distribution line, wherein the state information parameters are used for representing the operation state of the distribution line;
determining an information array of each distribution line according to the plurality of state information parameters to obtain a plurality of information arrays;
respectively inputting the plurality of information arrays into a fault detection model obtained by pre-training, and determining whether each distribution line has a fault according to an output result of the fault detection model;
and if the distribution lines in the plurality of distribution lines have faults, controlling the connection switch to be closed.
In one embodiment, the computer program when executed by the processor further implements: the distribution line comprises a feeder line, and the state information parameters at least comprise: the feeder switch switching position information, the feeder current information, the feeder protection action information and the feeder overhaul state information.
In one embodiment, the computer program when executed by the processor further implements: respectively inputting the plurality of information arrays into a fault detection model obtained by pre-training to obtain state characteristic parameters corresponding to each distribution line; and determining whether the distribution line has a fault according to the state characteristic parameters.
In one embodiment, the computer program when executed by the processor further implements: averaging a plurality of state characteristic parameters to obtain a result average value; and if the result mean value does not exceed the preset range, determining that part of the distribution lines in the plurality of distribution lines have faults, and controlling the connection switch to be closed.
In one embodiment, the computer program when executed by the processor further implements: and if the result mean value exceeds a preset range, determining that all the distribution lines have faults or all the distribution lines are normal in operation, and controlling the connection switch to be switched off.
In one embodiment, the computer program when executed by the processor further implements: obtaining historical state information parameters of a plurality of feeders, wherein the historical state information parameters at least comprise: historical feeder switch opening and closing position information, historical feeder current information, historical feeder protection action information and historical feeder overhaul state information; performing training processing operations, the training processing operations comprising: inputting the state information parameters of the plurality of feeder lines into an initial fault detection model for processing to obtain output data of the initial fault detection model, and calculating an error between the output data and preset expected output data according to a preset loss function; and when the error is smaller than a preset threshold value, taking the initial fault detection model as the fault detection model.
In one embodiment, the computer program when executed by the processor further implements: the fault detection model is a two-dimensional matrix model.
Referring to fig. 7, the method for self-healing a fault of a distribution line according to the embodiment of the present application may be applied to a computer device, and an internal structure diagram of the computer device may be as shown in fig. 7. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operating system and the computer program to run on the non-volatile storage medium. The database of the computer device is used for storing data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of fault self-healing of a distribution line.
All possible combinations of the technical features in the above embodiments may not be described for the sake of brevity, but should be considered as being within the scope of the present disclosure as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (7)
1. The utility model provides a fault self-healing method of distribution lines, its characterized in that is applied to distribution network system, distribution network system includes many distribution lines, adjacent two connect through the interconnection switch between the distribution line, the method includes:
acquiring a plurality of state information parameters of each distribution line, wherein the state information parameters are used for representing the operation state of the distribution line, the distribution line comprises a feeder line, and the state information parameters at least comprise: the feeder switch switching position information, the feeder current information, the feeder protection action information and the feeder overhaul state information are obtained;
determining an information array of each distribution line according to the plurality of state information parameters to obtain a plurality of information arrays;
respectively inputting the plurality of information arrays into a fault detection model obtained by pre-training, and determining whether each distribution line has a fault according to an output result of the fault detection model, wherein the fault detection model is a two-dimensional matrix model;
if a part of the distribution lines in the plurality of distribution lines have faults, controlling the connection switch to be closed;
the method for determining whether each distribution line has a fault according to the output result of the fault detection model comprises the following steps:
respectively inputting the plurality of information arrays into the fault detection model to obtain a state characteristic parameter corresponding to each distribution line, and determining whether the distribution line has a fault according to the state characteristic parameters;
if some of the distribution lines of the plurality of distribution lines have faults, controlling the contact switch to be closed, including:
averaging the state characteristic parameters to obtain a result average, if the result average does not exceed a preset range, determining that a part of the distribution lines in the distribution lines have faults, and controlling the connection switches to be closed;
wherein the training process of the fault detection model comprises the following steps:
obtaining historical state information parameters of a plurality of feeders, wherein the historical state information parameters at least comprise: historical feeder switch opening and closing position information, historical feeder current information, historical feeder protection action information and historical feeder overhaul state information;
inputting historical state information parameters of a plurality of feeder lines into an initial fault detection model for processing to obtain output data of the initial fault detection model, and calculating an error between the output data and preset expected output data according to a preset loss function;
and when the error is smaller than a preset threshold value, taking the initial fault detection model as the fault detection model.
2. A fault self-healing method for a distribution line according to claim 1, further comprising:
and if the result mean value exceeds a preset range, determining that all the distribution lines have faults or all the distribution lines operate normally, and controlling the connection switch to be switched off.
3. A method for self-healing faults on distribution lines as claimed in claim 1, wherein the plurality of distribution lines operate independently of one another.
4. The utility model provides a fault self-healing device of distribution lines, its characterized in that is applied to distribution network system, distribution network system includes many distribution lines, adjacent two connect through the contact switch between the distribution line, the device includes:
the distribution line state information parameter acquisition module is used for acquiring a plurality of state information parameters of each distribution line, wherein the state information parameters are used for representing the running state of the distribution line, the distribution line comprises a feeder line, and the state information parameters at least comprise: the feeder switch switching position information, the feeder current information, the feeder protection action information and the feeder overhaul state information are obtained;
the information array determining module is used for determining the information array of each distribution line according to the plurality of state information parameters to obtain a plurality of information arrays;
the fault determining module is used for respectively inputting the plurality of information arrays into a fault detection model obtained by pre-training, and determining whether each distribution line has a fault according to an output result of the fault detection model, wherein the fault detection model is a two-dimensional matrix model;
the interconnection switch control module is used for controlling the interconnection switch to be closed if a part of the distribution lines in the plurality of distribution lines have faults;
the fault determination module is specifically configured to: respectively inputting the plurality of information arrays into the fault detection model to obtain a state characteristic parameter corresponding to each distribution line, and determining whether the distribution line has a fault according to the state characteristic parameters;
the fault determination module is specifically configured to: averaging the state characteristic parameters to obtain a result average, and if the result average does not exceed a preset range, determining that part of the distribution lines in the distribution lines have faults and controlling the connection switches to be closed;
the fault determination module is specifically configured to: obtaining historical state information parameters of a plurality of feeders, wherein the historical state information parameters at least comprise: historical feeder switch opening and closing position information, historical feeder current information, historical feeder protection action information and historical feeder overhaul state information; inputting historical state information parameters of a plurality of feeder lines into an initial fault detection model for processing to obtain output data of the initial fault detection model, and calculating an error between the output data and preset expected output data according to a preset loss function; and when the error is smaller than a preset threshold value, taking the initial fault detection model as the fault detection model.
5. The fault self-healing device for the distribution line according to claim 4, wherein the fault determination module is specifically configured to: and if the result mean value exceeds a preset range, determining that all the distribution lines have faults or all the distribution lines are normal in operation, and controlling the connection switch to be switched off.
6. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor realizes the steps of the method of any one of claims 1 to 3 when executing the computer program.
7. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010479347.4A CN111751655B (en) | 2020-05-29 | 2020-05-29 | Fault self-healing method and device for distribution line, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010479347.4A CN111751655B (en) | 2020-05-29 | 2020-05-29 | Fault self-healing method and device for distribution line, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111751655A CN111751655A (en) | 2020-10-09 |
| CN111751655B true CN111751655B (en) | 2022-07-15 |
Family
ID=72674538
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010479347.4A Active CN111751655B (en) | 2020-05-29 | 2020-05-29 | Fault self-healing method and device for distribution line, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111751655B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112467686B (en) * | 2020-11-04 | 2023-09-01 | 深圳供电局有限公司 | Power distribution network fault recovery method, device, control equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101944777A (en) * | 2010-09-28 | 2011-01-12 | 上海市电力公司超高压输变电公司 | Intelligent self-healing monitoring method of extra high voltage power network |
| WO2011156400A1 (en) * | 2010-06-07 | 2011-12-15 | Abb Research Ltd. | Systems and methods for characterizing fault-clearing devices |
| CN102768327A (en) * | 2012-07-13 | 2012-11-07 | 深圳供电局有限公司 | Method and spare power automatic switching device for detecting faults on basis of GPS (global positioning system) synchronous phase differential method |
| CN104701831A (en) * | 2015-03-30 | 2015-06-10 | 国家电网公司 | Power distribution network self-healing control method |
| CN104755946A (en) * | 2012-09-15 | 2015-07-01 | 沙特阿拉伯石油公司 | Gsm/gprs system to detect and locate high impedance faults on medium voltage distribution networks in high resistivity areas |
| CN110262463A (en) * | 2019-07-09 | 2019-09-20 | 河海大学常州校区 | A kind of rail traffic platform door fault diagnosis system based on deep learning |
| CN110514930A (en) * | 2019-08-26 | 2019-11-29 | 安徽中祺智能电器股份有限公司 | A kind of the detection test method and device of intelligent distributed distribution terminal |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107872058B (en) * | 2017-11-22 | 2021-07-02 | 深圳供电局有限公司 | Distribution network integrated protection method fusing self-healing of line |
| CN110048384B (en) * | 2019-05-14 | 2021-05-25 | 国网北京市电力公司 | High-reliability self-healing method and system for distribution network |
| CN110703032A (en) * | 2019-08-26 | 2020-01-17 | 常州轻工职业技术学院 | Power grid fault positioning method |
| CN110888082B (en) * | 2019-11-27 | 2022-07-01 | 深圳供电局有限公司 | Relay protection secondary circuit node voltage fault positioning method and device |
-
2020
- 2020-05-29 CN CN202010479347.4A patent/CN111751655B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011156400A1 (en) * | 2010-06-07 | 2011-12-15 | Abb Research Ltd. | Systems and methods for characterizing fault-clearing devices |
| CN101944777A (en) * | 2010-09-28 | 2011-01-12 | 上海市电力公司超高压输变电公司 | Intelligent self-healing monitoring method of extra high voltage power network |
| CN102768327A (en) * | 2012-07-13 | 2012-11-07 | 深圳供电局有限公司 | Method and spare power automatic switching device for detecting faults on basis of GPS (global positioning system) synchronous phase differential method |
| CN104755946A (en) * | 2012-09-15 | 2015-07-01 | 沙特阿拉伯石油公司 | Gsm/gprs system to detect and locate high impedance faults on medium voltage distribution networks in high resistivity areas |
| CN104701831A (en) * | 2015-03-30 | 2015-06-10 | 国家电网公司 | Power distribution network self-healing control method |
| CN110262463A (en) * | 2019-07-09 | 2019-09-20 | 河海大学常州校区 | A kind of rail traffic platform door fault diagnosis system based on deep learning |
| CN110514930A (en) * | 2019-08-26 | 2019-11-29 | 安徽中祺智能电器股份有限公司 | A kind of the detection test method and device of intelligent distributed distribution terminal |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111751655A (en) | 2020-10-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9166407B2 (en) | Implementing substation automation load transfer function | |
| CN101577438B (en) | Equipment for high-capacity back-up power maintenance based on remote monitoring platform | |
| CN109474067B (en) | Power grid dispatching fault processing aid decision-making method | |
| CN108073551B (en) | High-voltage switch cabinet online fault diagnosis method based on multi-Agent cooperation | |
| CN113054706A (en) | Balance monitoring control system and method for power battery | |
| CN105896490B (en) | A kind of fault handling method and device of power distribution network | |
| CN107785998B (en) | Monitoring method of distribution automation equipment in distribution system | |
| CN111751655B (en) | Fault self-healing method and device for distribution line, computer equipment and storage medium | |
| CN114594349B (en) | Direct current insulation monitoring method and terminal in energy storage system | |
| CN115588961B (en) | Setting value self-adaptive setting method based on power distribution network full-model protection | |
| CN109193947A (en) | Power distribution room monitoring method, device, server and computer readable storage medium | |
| CN113608125B (en) | Battery fault identification method and device | |
| CN114186876B (en) | Intelligent electricity safety supervision and electric energy management method and system | |
| CN110470928B (en) | Online detection method for substation/distribution automation system | |
| CN115146727A (en) | Intelligent power utilization system fault detection method and system | |
| CN111751654A (en) | Power system fault processing method and device, computer equipment and medium | |
| CN114825625A (en) | Operation and maintenance system and method for battery energy storage power station | |
| CN112614008A (en) | Load transfer processing method and device | |
| CN107844894A (en) | A kind of power distribution network terminal O＆M state judging method based on big data | |
| CN113949163A (en) | Anomaly monitoring system applying big data to smart power grid | |
| CN114156901A (en) | Method for detecting state abnormity of low-voltage distribution transformer reactive power compensation device | |
| CN110994570A (en) | Power distribution network protection method and system, protection equipment and storage medium | |
| CN116626540B (en) | Method, system, terminal and storage medium for judging broken line fault interval | |
| CN117318282A (en) | Remote signaling port inspection system for load management | |
| CN115277079B (en) | Power terminal information attack monitoring method and 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |