CN115062730B - Power transmission line detection method, model training method, device, equipment and medium - Google Patents

Power transmission line detection method, model training method, device, equipment and medium Download PDF

Info

Publication number
CN115062730B
CN115062730B CN202210944464.2A CN202210944464A CN115062730B CN 115062730 B CN115062730 B CN 115062730B CN 202210944464 A CN202210944464 A CN 202210944464A CN 115062730 B CN115062730 B CN 115062730B
Authority
CN
China
Prior art keywords
power transmission
transmission line
collector
state data
data
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
Application number
CN202210944464.2A
Other languages
Chinese (zh)
Other versions
CN115062730A (en
Inventor
王于波
赵东艳
翟振
陈燕宁
董广智
张东
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Smartchip Microelectronics Technology Co Ltd
Beijing Core Kejian Technology Co Ltd
Original Assignee
Beijing Smartchip Microelectronics Technology Co Ltd
Beijing Core Kejian Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Smartchip Microelectronics Technology Co Ltd, Beijing Core Kejian Technology Co Ltd filed Critical Beijing Smartchip Microelectronics Technology Co Ltd
Priority to CN202210944464.2A priority Critical patent/CN115062730B/en
Publication of CN115062730A publication Critical patent/CN115062730A/en
Application granted granted Critical
Publication of CN115062730B publication Critical patent/CN115062730B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G01R31/50—Testing of electric apparatus, lines, cables or components for short-circuits, continuity, leakage current or incorrect line connections
    • G01R31/54—Testing for continuity
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • 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)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Supply And Distribution Of Alternating Current (AREA)
  • Remote Monitoring And Control Of Power-Distribution Networks (AREA)

Abstract

The disclosure relates to the technical field of power equipment, in particular to a power transmission line detection method, a model training method, a device, equipment and a medium, wherein the method comprises the following steps: acquiring at least one group of collector state data acquired by a power transmission line state collector, and acquiring at least one group of power transmission line state data according to the at least one group of collector state data; detecting at least one group of power transmission line state data to generate a power transmission line state detection result; and generating the power transmission line disconnection fault information in response to the detection results of at least two groups of continuous power transmission line state data meeting the condition that the state data exceeds the standard. According to the scheme, on the premise of consuming less resources, whether the target power transmission line between the two power transmission line towers has a fault or not can be accurately determined, so that the detection efficiency is improved, and the detection accuracy is improved.

Description

Power transmission line detection method, model training method, device, equipment and medium
Technical Field
The disclosure relates to the technical field of power equipment, in particular to a power transmission line detection method, a model training method, a device, equipment and a medium.
Background
With the development of power technology and the enlargement of the scale of the power grid, the operation environment of the power grid is increasingly complex, and the requirements on the stability and the reliability of the power grid are high in consideration of the fact that safe and stable operation of the power grid has extremely important influence on the development of national economy. Therefore, in recent years, a scheme for performing fine management on a power transmission line to improve the operation and maintenance efficiency of the power transmission line has received much attention in the industry.
In the related art, the voltage of the transmission line can be detected in sections in the whole transmission line, and when the detection result is judged to be abnormal, the disconnection fault of the corresponding section in the transmission line is determined, so that the position of the disconnection fault point of the transmission line is determined. However, in the above scheme, the transmission line voltage is detected in sections, which consumes more resources and results in lower detection efficiency; moreover, when a certain section of the power transmission line has a fault, the detection results corresponding to the section and other sections after the section are judged to be abnormal, so that the position of the fault point of the power transmission line cannot be accurately determined, and the detection accuracy is low.
Disclosure of Invention
In order to solve the problems in the related art, embodiments of the present disclosure provide a power transmission line detection method, a model training method, an apparatus, a device, and a medium.
In a first aspect, an embodiment of the present disclosure provides a power line detection method, where the method includes:
acquiring at least one group of collector state data acquired by a power transmission line state collector, and acquiring at least one group of power transmission line state data according to the at least one group of collector state data, wherein each group of power transmission line state data comprises the collector state data and collector attitude data corresponding to the collector state data, and the power transmission line state collector is fixed on a target power transmission line between two power transmission line towers;
detecting at least one group of power transmission line state data to generate a power transmission line state detection result;
and generating the power transmission line disconnection fault information in response to the detection results of at least two groups of continuous power transmission line state data meeting the condition that the state data exceeds the standard.
In one implementation of the present disclosure, generating power transmission line drop fault information in response to detection results of at least two sets of continuous power transmission line status data both satisfying a status data standard exceeding condition includes:
responding to the detection results of at least two groups of continuous power transmission line state data to meet the condition that the state data exceeds the standard, and acquiring attitude data of a target collector;
and generating power transmission line disconnection fault information in response to the situation that the difference between the collector attitude data in the latter group of power transmission line state data and the target collector attitude data in at least two groups of continuous power transmission line state data meets the standard exceeding condition of the collector attitude data.
In one implementation of the present disclosure, the method further comprises:
and generating power transmission line disconnection warning information in response to the situation that the difference between the collector attitude data in the latter group of power transmission line state data and the target collector attitude data in at least two groups of continuous power transmission line state data does not meet the standard exceeding condition of the collector attitude data.
In one implementation of the present disclosure, the collector state data includes an acceleration of the power line state collector in at least one direction and an angular velocity of rotation of the power line state collector about the one direction.
In one implementation of the present disclosure, the collector attitude data corresponding to the collector state data includes:
and according to the collector state data, calculating the pitch angle of the power transmission line state collector, the roll angle of the power transmission line state collector and the course angle of the power transmission line state collector by a quaternion algorithm.
In one implementation of the present disclosure, obtaining at least one set of collector status data collected by a power transmission line status collector includes:
acquiring continuous four groups of collector state data collected by a power transmission line state collector;
detecting at least one set of power line status data to generate a power line status detection result, comprising:
detecting the state data of a third group of collectors in the state data of the four groups of continuous collectors to generate a detection result of the state of the power transmission line;
the method further comprises the following steps:
and in response to the condition that the detection result of the power transmission line state does not meet the standard exceeding condition of the state data, deleting the first group of collector state data in the four groups of continuous collector state data, forwarding the second group to the fourth group of collector state data in the four groups of continuous collector state data, and storing the collector state data currently collected by the power transmission line state collector as the fourth group of collector state data in the four groups of continuous collector state data.
In one implementation of the present disclosure, detecting a third set of status data of four consecutive sets of status data of a collector to generate a power line status detection result includes
And acquiring a first power transmission line state detection model, and inputting the state data of the third group of collectors into the first power transmission line state detection model to acquire a power transmission line state detection result.
In one implementation manner of the present disclosure, before detecting a third group of status data of four consecutive groups of status data of the collector to generate a detection result of a power transmission line status, the method further includes:
acquiring weather data corresponding to the state data of the third group of collectors;
and acquiring a second power transmission line state detection model, and inputting the third group of collector state data and the weather data into the second power transmission line state detection model to acquire a power transmission line state detection result.
In a second aspect, an embodiment of the present disclosure provides a model training method, where the method includes:
acquiring at least one group of collector state data acquired by a power transmission line state collector and a power transmission line image corresponding to each group of collector state data, wherein the power transmission line state collector is fixed on a power transmission line between two power transmission line towers, and the power transmission line image at least comprises the power transmission line state collector and part or all of a target power transmission line;
acquiring at least one group of power transmission line state data according to at least one group of collector state data, wherein each group of power transmission line state data comprises collector state data and collector attitude data corresponding to the collector state data;
carrying out image recognition on the power transmission line image corresponding to the collector state data in each group of power transmission line state data to obtain a power transmission line state detection result corresponding to each group of power transmission line state data;
the method comprises the steps of obtaining a power transmission line state detection model, taking each group of power transmission line state data as input, taking a power transmission line state detection result corresponding to each group of power transmission line state data as output, and training the power transmission line state detection model to obtain a first power transmission line state detection model.
In one implementation of the present disclosure, the collector state data includes an acceleration of the power line state collector in at least one direction and an angular velocity of rotation of the power line state collector about the one direction.
In one implementation manner of the present disclosure, the collector attitude data corresponding to the collector state data includes:
and calculating the pitch angle of the power transmission line state collector, the roll angle of the power transmission line state collector and the course angle of the power transmission line state collector by a quaternion algorithm according to the collector state data.
In one implementation of the present disclosure, before each group of power line state data is used as an input, and a power line state detection result corresponding to each group of power line state data is used as an output, training a power line state detection model to obtain a first power line state detection model, the method further includes:
receiving a first updating weight parameter sent by a first edge server, and updating the power transmission line state detection model according to the first updating weight parameter;
with every group power transmission line state data as the input, will with the power transmission line state detection result that every group power transmission line state data corresponds as output, train power transmission line state detection model to acquire first power transmission line state detection model, include:
taking each group of power transmission line state data as input, taking a power transmission line state detection result corresponding to each group of power transmission line state data as output, and training the updated power transmission line state detection model;
in response to the trained power line state detection model converging, storing the trained power line state detection model as a first power line state detection model.
In one implementation of the present disclosure, the method further comprises:
and responding to the fact that the trained power line state detection model does not converge, acquiring a first gradient updating vector according to the trained power line state detection model, and sending the first gradient updating vector to the edge server.
In a third aspect, an embodiment of the present disclosure provides a model training method, where the method includes:
acquiring at least one group of collector state data acquired by a power transmission line state collector, a power transmission line image corresponding to each group of collector state data and weather data corresponding to each group of collector state data, wherein the power transmission line state collector is fixed on a power transmission line between two power transmission line towers, and the power transmission line image at least comprises the power transmission line state collector and part or all of a target power transmission line;
acquiring at least one group of power transmission line state data according to at least one group of collector state data, wherein each group of power transmission line state data comprises collector state data and collector attitude data corresponding to the collector state data;
carrying out image recognition on the power transmission line image corresponding to the collector state data in each group of power transmission line state data to obtain a power transmission line state detection result corresponding to each group of power transmission line state data;
the method comprises the steps of obtaining a power transmission line state detection model, taking each group of power transmission line state data and weather data corresponding to each group of power transmission line state data as input, taking a power transmission line state detection result corresponding to each group of power transmission line state data as output, and training the power transmission line state detection model to obtain a second power transmission line state detection model.
In one implementation of the present disclosure, the collector state data includes an acceleration of the power line state collector in at least one direction and an angular velocity of rotation of the power line state collector about the one direction.
In one implementation manner of the present disclosure, the collector attitude data corresponding to the collector state data includes:
and according to the collector state data, calculating the pitch angle of the power transmission line state collector, the roll angle of the power transmission line state collector and the course angle of the power transmission line state collector by a quaternion algorithm.
In one implementation of the present disclosure, each group of power line status data and the weather data corresponding to each group of power line status data are used as inputs, the power line status detection result corresponding to each group of power line status data is used as an output, and the power line status detection model is trained before obtaining the second power line status detection model, and the method further includes:
receiving a second updating weight parameter sent by a second edge server, and updating the power transmission line state detection model according to the second updating weight parameter;
with every group power transmission line state data and with the weather data that every group power transmission line state data corresponds as the input, will be with the power transmission line state testing result that every group power transmission line state data corresponds as output, train power transmission line state detection model to acquire second power transmission line state detection model, include:
taking each group of power transmission line state data and weather data corresponding to each group of power transmission line state data as input, taking a power transmission line state detection result corresponding to each group of power transmission line state data as output, and training the updated power transmission line state detection model;
in response to the trained power line state detection model converging, storing the trained power line state detection model as a second power line state detection model.
In one implementation of the present disclosure, the method further comprises:
and responding to the fact that the trained power line state detection model does not converge, acquiring a second gradient updating vector according to the trained power line state detection model, and sending the second gradient updating vector to the edge server.
In a fourth aspect, an embodiment of the present disclosure provides a power transmission line detection apparatus, including:
the first data acquisition module is configured to acquire at least one group of collector state data acquired by the power transmission line state collector and acquire at least one group of power transmission line state data according to the at least one group of collector state data, each group of power transmission line state data comprises collector state data and collector attitude data corresponding to the collector state data, and the power transmission line state collector is fixed on a target power transmission line between two power transmission line towers;
a data detection module configured to detect at least one set of power line status data to generate a power line status detection result;
and the fault warning module is configured to respond to the detection results of at least two groups of continuous power transmission line state data meeting the condition that the state data exceeds the standard, and generate power transmission line disconnection fault information.
In a fifth aspect, an embodiment of the present disclosure provides a model training apparatus, including:
the second data acquisition module is configured to acquire at least one group of collector state data acquired by the power transmission line state collector and a power transmission line image corresponding to each group of collector state data, the power transmission line state collector is fixed on a power transmission line between two power transmission line towers, and the power transmission line image at least comprises the power transmission line state collector and part or all of a target power transmission line;
the first data processing module is configured to acquire at least one group of power transmission line state data according to at least one group of collector state data, and each group of power transmission line state data comprises collector state data and collector attitude data corresponding to the collector state data;
the first image identification module is configured to perform image identification on the power transmission line image corresponding to the collector state data in each group of power transmission line state data so as to obtain a power transmission line state detection result corresponding to each group of power transmission line state data;
the first model training module is configured to acquire the power transmission line state detection models, take each group of power transmission line state data as input, take a power transmission line state detection result corresponding to each group of power transmission line state data as output, and train the power transmission line state detection models to acquire the first power transmission line state detection models.
In a sixth aspect, an embodiment of the present disclosure provides a model training apparatus, including:
the third data acquisition module is configured to acquire at least one group of collector state data acquired by the power transmission line state collector, a power transmission line image corresponding to each group of collector state data and weather data corresponding to each group of collector state data, the power transmission line state collector is fixed on a power transmission line between two power transmission line towers, and the power transmission line image at least comprises the power transmission line state collector and part or all of a target power transmission line;
the second data processing module is configured to acquire at least one group of power transmission line state data according to at least one group of collector state data, and each group of power transmission line state data comprises collector state data and collector attitude data corresponding to the collector state data;
the second image identification module is configured to perform image identification on the power transmission line image corresponding to the collector state data in each group of power transmission line state data so as to obtain a power transmission line state detection result corresponding to each group of power transmission line state data;
and the second model training module is configured to acquire the power transmission line state detection model, take each group of power transmission line state data and weather data corresponding to each group of power transmission line state data as input, take a power transmission line state detection result corresponding to each group of power transmission line state data as output, and train the power transmission line state detection model to acquire the second power transmission line state detection model.
In a seventh aspect, the disclosed embodiments provide an electronic device, including a memory and a processor, where the memory is configured to store one or more computer instructions, where the one or more computer instructions are executed by the processor to implement the method according to any one of the first aspect, any one of the implementations of the first aspect, the second aspect, any one of the implementations of the second aspect, the third aspect, and any one of the implementations of the third aspect.
In an eighth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions, when executed by a processor, implement the method as described in any one of the first aspect, the second aspect, the third aspect, and the third aspect.
According to the technical scheme provided by the embodiment of the disclosure, at least one group of collector state data collected by a power transmission line state collector is obtained, and at least one group of power transmission line state data is obtained according to the at least one group of collector state data, wherein each group of power transmission line state data comprises the collector state data and collector attitude data corresponding to the collector state data, and the power transmission line state collector is fixed on a target power transmission line between two power transmission line towers, so that the power transmission line state data can reflect the motion state of the target power transmission line and the attitude of the target power transmission line; detecting at least one group of power transmission line state data to generate a power transmission line state detection result; and generating the power transmission line disconnection fault information in response to the detection results of at least two groups of continuous power transmission line state data meeting the condition that the state data exceeds the standard. When the detection results of at least two groups of continuous power transmission line state data meet the condition that the state data exceed the standard, the motion state of a target power transmission line can be understood to reflect the motion state of the target power transmission line in continuous falling, and the posture of the target power transmission line can reflect that the posture of the target power transmission line exceeds the normal posture change range due to the fact that the target power transmission line is disconnected with a power transmission line tower, so that power transmission line breakage fault information used for indicating that the target power transmission line has a breakage fault is generated.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
Other features, objects, and advantages of the present disclosure will become more apparent from the following detailed description of non-limiting embodiments when taken in conjunction with the accompanying drawings. In the drawings.
Fig. 1 shows a flow diagram of a power line detection method according to an embodiment of the present disclosure.
FIG. 2 shows a flow diagram of a model training method according to an embodiment of the present disclosure.
FIG. 3 shows a flow diagram of a model training method according to an embodiment of the present disclosure.
Fig. 4 shows a block diagram of a power line detection device according to an embodiment of the present disclosure.
Fig. 5 shows a block diagram of a model training apparatus according to an embodiment of the present disclosure.
Fig. 6 shows a block diagram of a model training apparatus according to an embodiment of the present disclosure.
Fig. 7 shows a block diagram of an electronic device according to an embodiment of the present disclosure.
FIG. 8 shows a schematic block diagram of a computer system suitable for use in implementing a method according to an embodiment of the present disclosure.
Detailed Description
Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement them. Also, for the sake of clarity, parts not relevant to the description of the exemplary embodiments are omitted in the drawings.
In the present disclosure, it is to be understood that terms such as "including" or "having," etc., are intended to indicate the presence of the disclosed features, numerals, steps, actions, components, parts, or combinations thereof in the specification, and are not intended to preclude the possibility that one or more other features, numerals, steps, actions, components, parts, or combinations thereof are present or added.
It should be further noted that the embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
In the present disclosure, if an operation of acquiring user information or user data or an operation of presenting user information or user data to others is involved, the operations are all operations authorized, confirmed by a user, or actively selected by the user.
With the development of power technology and the enlargement of the scale of the power grid, the operation environment of the power grid is increasingly complex, and the requirements on the stability and the reliability of the power grid are high in consideration of the fact that safe and stable operation of the power grid has extremely important influence on the development of national economy. Therefore, in recent years, a scheme for performing fine management on a power transmission line to improve the operation and maintenance efficiency of the power transmission line has received much attention in the industry.
In the related art, the voltage of the transmission line can be detected in a subsection mode in the whole transmission line, and when the detection result is judged to be abnormal, the disconnection fault of the corresponding subsection in the transmission line is determined, so that the position of the disconnection fault point of the transmission line is determined. However, in the above scheme, the transmission line voltage is detected in sections, which consumes more resources and results in lower detection efficiency; moreover, when a certain section of the power transmission line has a fault, the detection results corresponding to the section and other sections after the section are judged to be abnormal, so that the position of the fault point of the power transmission line cannot be accurately determined, and the detection accuracy is low.
In order to solve the above problems, in the technical scheme of the present disclosure, at least one set of collector state data collected by a power transmission line state collector is obtained, and at least one set of power transmission line state data is obtained according to the at least one set of collector state data, where each set of power transmission line state data includes collector state data and collector attitude data corresponding to the collector state data, and since the power transmission line state collector is fixed on a target power transmission line between two power transmission line towers, the power transmission line state data can reflect a motion state of the target power transmission line and an attitude of the target power transmission line; detecting at least one group of power transmission line state data to generate a power transmission line state detection result; and generating the power transmission line disconnection fault information in response to the detection results of at least two groups of continuous power transmission line state data meeting the condition that the state data exceeds the standard. When the detection results of at least two groups of continuous power transmission line state data meet the condition that the state data exceed the standard, the motion state of a target power transmission line can be understood to reflect the motion state of the target power transmission line in continuous falling, and the posture of the target power transmission line can reflect that the posture of the target power transmission line exceeds the normal posture change range due to the fact that the target power transmission line is disconnected with a power transmission line tower, so that power transmission line breakage fault information used for indicating that the target power transmission line has a breakage fault is generated.
Fig. 1 shows a flow diagram of a power line detection method according to an embodiment of the present disclosure, as shown in fig. 1, the power line detection method comprises the following steps S101-S103:
in step S101, at least one set of collector status data collected by the power line status collector is obtained, and at least one set of power line status data is obtained according to the at least one set of collector status data.
Each group of power transmission line state data comprises collector state data and collector attitude data corresponding to the collector state data, and the power transmission line state collector is fixed on a target power transmission line between two power transmission line towers.
In step S102, at least one set of power line status data is detected to generate a power line status detection result.
In step S103, in response to the detection results of at least two groups of continuous power transmission line status data both satisfying the status data exceeding condition, power transmission line disconnection fault information is generated.
In one embodiment of the present disclosure, the collector status data may be understood as indicating a motion status of the power line status collector, and for example, the collector status data may include a speed of the collector in at least one direction, an acceleration of the collector in at least one direction, and the like.
In an embodiment of the present disclosure, the obtaining of at least one set of collector state data collected by the power transmission line state collector may be understood as receiving at least one set of collector state data sent by the power transmission line state collector, or may be reading at least one set of collector state data stored in advance.
For example, the power line detection method provided by the present disclosure may be applied to a server, where the power line status collector may transmit at least one set of collector status data to the data relay through a Long Range Radio (LoRa) protocol, and then the data relay forwards the at least one set of collector status data to the server through a General Packet Radio Service (GPRS) module.
The power transmission line state collector can use a lithium battery in the power transmission line state collector to supply power, the lithium battery is charged through a solar panel in the power transmission line state collector, and a main control Micro Control Unit (MCU) of the power transmission line state collector can use a Cortex-M0 inner core low-power consumption chip and is mainly responsible for processing and analyzing original data. The original attitude data acquisition chip of the power transmission line state acquisition device can use a six-axis sensor and is used for acquiring the state data of the acquisition device. The LORA module of the power transmission line state collector is used for reporting information so as to meet the requirements of low power consumption and long-distance short message transmission. The solar cell panel can provide 5V voltage when working normally, and the lithium battery is charged through the lithium battery management chip; the lithium battery outputs 3.3V voltage to the MCU, the six-axis sensor and the LoRa module through the voltage stabilizing chip; the MCU is communicated with the six-axis sensor by using an Inter-Integrated Circuit (IIC) bus; the MCU and the LoRa module communicate with each other by a Universal Asynchronous Receiver/Transmitter (UART).
The data repeater can get electricity from the power supply circuit through the mutual inductor, the lithium battery in the data repeater can be used as a standby power supply, and the normal transmission of data is supported through the lithium battery in the data repeater after the power supply circuit stops supplying power. The main control MCU of the data repeater can use a Cortex-M3 kernel low-power chip and is mainly responsible for processing and reporting the received data. The repeater can use the LORA module to report data and receive data. The communication end of the server can use a GSM module.
In one embodiment of the present disclosure, the collector attitude data may be understood as a real-time attitude for indicating the power line status collector.
In one embodiment of the present disclosure, the obtaining of at least one set of power line state data according to at least one set of collector state data may be understood as obtaining a corresponding set of power line state data according to each set of collector state data in at least one set of collector state data. Acquiring the power transmission line state data according to the collector state data can be understood as substituting the collector state data into a pre-acquired algorithm to calculate so as to acquire the power transmission line state data, and can also be understood as inputting the collector state data as input into a pre-acquired data acquisition model so as to acquire the power transmission line state data output by the data acquisition model.
In one embodiment of the present disclosure, detecting at least one set of power line status data to generate a power line status detection result may be understood as comparing a pre-acquired target power line status data range with each set of power line status data of the at least one set of power line status data to determine whether the compared power line status data is within the target power line status data range, if not, generating a power line status detection result indicating that a status data out-of-limits condition is satisfied, and if within the target power line status data range, generating a power line status detection result indicating that a status data out-of-limits condition is not satisfied; the power line state detection result output by the data detection model can be obtained by inputting the pre-obtained data detection model by taking each set of power line state data in at least one set of power line state data as input.
According to the technical scheme, at least one group of collector state data collected by a power transmission line state collector is obtained, and at least one group of power transmission line state data is obtained according to the at least one group of collector state data, wherein each group of power transmission line state data comprises the collector state data and collector posture data corresponding to the collector state data, and the power transmission line state collector is fixed on a target power transmission line between two power transmission towers, so that the power transmission line state data can reflect the motion state of the target power transmission line and the posture of the target power transmission line; detecting at least one group of power transmission line state data to generate a power transmission line state detection result; and generating the power transmission line disconnection fault information in response to the detection results of at least two groups of continuous power transmission line state data meeting the condition that the state data exceeds the standard. When the detection results of at least two groups of continuous power transmission line state data meet the condition that the state data exceed the standard, the motion state of a target power transmission line can be understood to reflect the motion state of the target power transmission line in continuous falling, and the posture of the target power transmission line can reflect that the posture of the target power transmission line exceeds the normal posture change range due to the fact that the target power transmission line is disconnected with a power transmission line tower, so that power transmission line breakage fault information used for indicating that the target power transmission line has a breakage fault is generated.
In one implementation manner of the present disclosure, the power transmission line disconnection fault information is generated in response to that the detection results of at least two sets of continuous power transmission line state data all satisfy the condition that the state data exceeds the standard, and the method can be implemented by the following steps:
responding to the detection results of at least two groups of continuous power transmission line state data to meet the condition that the state data exceeds the standard, and acquiring attitude data of a target collector;
and generating power transmission line disconnection fault information in response to the situation that the difference between the collector attitude data in the latter group of power transmission line state data and the target collector attitude data in at least two groups of continuous power transmission line state data meets the standard exceeding condition of the collector attitude data.
In one embodiment of the present disclosure, the target collector attitude data may be understood as an attitude of the power transmission line state collector used for indicating that the power transmission line is not disconnected. Obtaining the attitude data of the target collector can be understood as reading the attitude data of the target collector stored in advance, and can also be understood as receiving the attitude data of the target collector sent by other devices or systems.
In one embodiment of the present disclosure, the difference between the collector attitude data and the target collector attitude data satisfies the standard exceeding condition of the collector attitude data, and it can be understood that the difference between the collector attitude data and the target collector attitude data is smaller than the standard exceeding threshold of the collector attitude data, and it can also be understood that the difference between the collector attitude data and the target collector attitude data belongs to the standard exceeding range of the collector attitude data.
According to the technical scheme, the attitude data of the target collector is acquired by responding to the detection result of at least two groups of continuous power transmission line state data, and the attitude data of the target collector is acquired by responding to the condition that the difference between the attitude data of the collector in the next group of power transmission line state data and the attitude data of the target collector in the at least two groups of continuous power transmission line state data meets the condition that the attitude data of the collector exceeds the standard, so that the power transmission line disconnection fault information is generated, and the power transmission line disconnection fault information can be generated only when the attitude difference between the power transmission line state collector and the attitude of the target power transmission line is larger when the power transmission line state collector is determined not to be disconnected, so that the accuracy of the generated power transmission line disconnection fault information is improved.
In one implementation of the present disclosure, the method further comprises:
and generating power transmission line disconnection warning information in response to the situation that the difference between the collector attitude data in the latter group of power transmission line state data and the target collector attitude data in at least two groups of continuous power transmission line state data does not meet the standard exceeding condition of the collector attitude data.
In the technical scheme disclosed by the disclosure, the difference between the collector attitude data and the target collector attitude data in the latter group of power transmission line state data in at least two groups of continuous power transmission line state data does not satisfy the collector attitude data exceeding condition, it can be understood that the motion state of the target power transmission line can represent the motion state of the target power transmission line in continuous falling, and the attitude of the target power transmission line can represent the state that the attitude of the target power transmission line exceeds the normal attitude change range due to the fact that the target power transmission line is disconnected from a power transmission line tower, but the difference between the attitude of the power transmission line state collector and the attitude of the power transmission line state collector when the target power transmission line is not broken is still small, namely the target power transmission line can be in a state that the motion amplitude is large but the target power transmission line is still not broken, so that the target power transmission line can be broken by generating power transmission line breakage warning information, corresponding maintenance personnel can execute corresponding countermeasures, and the probability of the failure of the power transmission line where the target power transmission line is located is reduced.
In one implementation of the present disclosure, the collector state data includes an acceleration of the power line state collector in at least one direction and an angular velocity of rotation of the power line state collector about the one direction.
In the technical scheme of the disclosure, the collector state data is limited to include the acceleration of the power transmission line state collector in at least one direction and the angular velocity of the power transmission line state collector rotating around one direction, so that the motion state of the power transmission line state collector can be accurately known according to the collector state data.
In one implementation manner of the present disclosure, the collector attitude data corresponding to the collector state data includes:
and according to the collector state data, calculating the pitch angle of the power transmission line state collector, the roll angle of the power transmission line state collector and the course angle of the power transmission line state collector by a quaternion algorithm.
According to the technical scheme, the attitude of the power transmission line state collector can be accurately obtained according to the attitude data of the collector by limiting the attitude data of the collector corresponding to the state data of the collector to include the pitch angle of the power transmission line state collector, the roll angle of the power transmission line state collector and the course angle of the power transmission line state collector which are obtained through calculation by a quaternion algorithm according to the state data of the collector.
In an implementation manner of the present disclosure, obtaining at least one group of collector state data collected by the power transmission line state collector can be implemented by the following steps:
acquiring continuous four groups of collector state data collected by a power transmission line state collector;
detecting at least one set of power line status data to generate a power line status detection result, comprising:
detecting the state data of a third group of collectors in the state data of the four groups of continuous collectors to generate a detection result of the state of the power transmission line;
the method further comprises the following steps:
and in response to the detection result of the power transmission line state, the condition data exceeding the standard is not met, the first group of collector state data in the four groups of continuous collector state data is deleted, the second group to the fourth group of collector state data in the four groups of continuous collector state data are moved forward, and the collector state data currently collected by the power transmission line state collector is stored as the fourth group of collector state data in the four groups of continuous collector state data.
According to the technical scheme, the continuous four groups of collector state data collected by the power transmission line state collector are obtained, the third group of collector state data in the continuous four groups of collector state data is detected, so that a power transmission line state detection result is generated, the collector state data used for detection can be ensured to be the data collected by the power transmission line state collector when the data collection function is normal, and the accuracy of the power transmission line state detection result cannot be lower due to the fact that the data collection function of the power transmission line state collector is abnormal. By responding to the condition that the detection result of the power transmission line state does not meet the standard exceeding condition of the state data, deleting the first group of collector state data in the four groups of continuous collector state data, forwarding the second group to the fourth group of collector state data in the four groups of continuous collector state data, and storing the collector state data currently collected by the power transmission line state collector as the fourth group of collector state data in the four groups of continuous collector state data, the detection of the third group of collector state data in the four groups of continuous collector state data can be continued conveniently, and the detection result of the power transmission line state can be generated continuously.
In one implementation of the present disclosure, detecting a third set of status data of four consecutive sets of status data of a collector to generate a power line status detection result includes
And acquiring a first power transmission line state detection model, and inputting the state data of the third group of collectors into the first power transmission line state detection model to acquire a power transmission line state detection result.
In one embodiment of the present disclosure, the first power line state detection model may be pre-stored or may be obtained from another device or system. The first power line state detection model may be a Neural Network (NN) model, a Convolutional Neural Network (CNN) model, a Long Short Term Memory (LSTM) model, or the like. The power transmission line state detection model can be understood as a model for learning the rule between the collector state data and the power transmission line state detection result.
In the technical scheme, the third group of collector state data is input into the power transmission line state detection model by acquiring the first power transmission line state detection model so as to acquire a power transmission line state detection result, and the accuracy of the power transmission line state detection result can be ensured to be higher.
In one implementation manner of the present disclosure, before detecting the third group of collector state data in the four groups of continuous collector state data to generate a power transmission line state detection result, the method further includes:
acquiring weather data corresponding to the state data of the third group of collectors;
and acquiring a second power transmission line state detection model, and inputting the state data of the third group of collectors and the weather data into the second power transmission line state detection model to acquire a power transmission line state detection result.
The second power line condition detection model may be pre-stored or may be obtained from another device or system. The second power line state detection model may be a Neural Network (NN) model, a Convolutional Neural Network (CNN) model, or a Long Short Term Memory (LSTM) model. The power transmission line state detection model can be understood as a model for learning the rule between the collector state data and the power transmission line state detection result.
In one embodiment of the present disclosure, the weather data corresponding to the third group of collector status data may be understood as indicating the weather condition of the area where the target power line is located at the time of collecting the third group of collector status data. For example, the weather data may include at least one of wind speed, wind direction, air temperature, air humidity, air pressure, rain amount, and light intensity.
In the technical scheme, the weather data corresponding to the state data of the third group of collectors is acquired, the second power transmission line state detection model is acquired, the state data of the third group of collectors and the weather data are input into the power transmission line state detection model to acquire the detection result of the state of the power transmission line, the state data of the third group of collectors can be detected on the premise that the weather condition of the area where the target power transmission line is located is considered, misdetection caused by severe weather is avoided, and the accuracy of the detection result of the state of the power transmission line is improved.
Fig. 2 shows a flow chart of a model training method according to an embodiment of the present disclosure, as shown in fig. 2, the model training method comprises the following steps S201-S204:
in step S201, at least one group of collector state data collected by the power line state collector and a power line image corresponding to each group of collector state data are obtained.
The power transmission line state collector is fixed on a power transmission line between two power transmission line towers, and the power transmission line image at least comprises the power transmission line state collector and part or all of a target power transmission line.
In step S202, at least one set of power line status data is obtained according to at least one set of collector status data, where each set of power line status data includes collector status data and collector attitude data corresponding to the collector status data.
In step S203, image recognition is performed on the power line image corresponding to the collector state data in each set of power line state data to obtain a power line state detection result corresponding to each set of power line state data.
In step S204, a power line state detection model is obtained, each set of power line state data is used as an input, a power line state detection result corresponding to each set of power line state data is used as an output, and the power line state detection model is trained to obtain a first power line state detection model.
In one embodiment of the present disclosure, the collector status data may be understood as indicating a motion status of the power line status collector, and for example, the collector status data may include a speed of the collector in at least one direction, an acceleration of the collector in at least one direction, and the like.
In an embodiment of the present disclosure, the obtaining of at least one set of collector state data collected by the power transmission line state collector may be understood as receiving at least one set of collector state data sent by the power transmission line state collector, or may be reading at least one set of collector state data stored in advance.
In an embodiment of the present disclosure, the power line image corresponding to the collector state data may be understood as a power line image collected when the power line state collector collects the set of collector state data, and the power line image is obtained, and may be a power line image sent by a corresponding image collection device, or a power line image obtained in advance may be read.
In one embodiment of the present disclosure, the collector attitude data may be understood as a real-time attitude for indicating the power line status collector.
In one implementation of the present disclosure, the collector state data includes an acceleration of the power line state collector in at least one direction and an angular velocity of rotation of the power line state collector about the one direction.
In one embodiment of the present disclosure, the power line status detection result corresponding to the power line status data can be understood as indicating whether the target power line is in a disconnected state when the set of power line status data is collected.
In one embodiment of the present disclosure, the first power line state detection model may be pre-stored or may be obtained from another device or system. The first power line state detection model may be a Neural Network (NN) model, a Convolutional Neural Network (CNN) model, a Long Short Term Memory (LSTM) model, or the like. The first power transmission line state detection model can be understood as a model for learning the rule between the collector state data and the power transmission line state detection result.
According to the technical scheme provided by the embodiment of the disclosure, at least one group of collector state data collected by a power transmission line state collector and a power transmission line image corresponding to each group of collector state data are obtained, and at least one group of power transmission line state data is obtained according to the at least one group of collector state data; carrying out image recognition on the power transmission line image corresponding to the collector state data in each group of power transmission line state data so as to obtain a power transmission line state detection result corresponding to each group of power transmission line state data, and determining whether a target power transmission line where the power transmission line state collector is located is in a broken state or not when the corresponding collector state data is collected according to the power transmission line state detection result; the method comprises the steps of obtaining a power transmission line state detection model, taking each group of power transmission line state data as input, taking a power transmission line state detection result corresponding to each group of power transmission line state data as output, training the power transmission line state detection model, obtaining a first power transmission line state detection model, enabling the first power transmission line state detection model to learn rules between the power transmission line state data and the power transmission line state detection result, and detecting whether a target power transmission line between two power transmission line towers has a fault or not based on the first power transmission line state detection model, thereby improving detection efficiency and improving detection accuracy.
In one implementation of the present disclosure, the collector state data includes an acceleration of the power line state collector in at least one direction and an angular velocity of rotation of the power line state collector about the one direction.
In the technical scheme of the disclosure, the collector state data is limited to include the acceleration of the power transmission line state collector in at least one direction and the angular velocity of the power transmission line state collector rotating around one direction, so that the motion state of the power transmission line state collector can be accurately known according to the collector state data.
In one implementation of the present disclosure, the collector attitude data corresponding to the collector state data includes:
and according to the collector state data, calculating the pitch angle of the power transmission line state collector, the roll angle of the power transmission line state collector and the course angle of the power transmission line state collector by a quaternion algorithm.
According to the technical scheme, the attitude of the power transmission line state collector can be accurately obtained according to the attitude data of the collector by limiting the attitude data of the collector corresponding to the state data of the collector to include the pitch angle of the power transmission line state collector, the roll angle of the power transmission line state collector and the course angle of the power transmission line state collector which are obtained through calculation by a quaternion algorithm according to the state data of the collector.
In one implementation of the present disclosure, before each group of power line state data is used as an input, and a power line state detection result corresponding to each group of power line state data is used as an output, training a power line state detection model to obtain a first power line state detection model, the method further includes:
receiving a first updating weight parameter sent by a first edge server, and updating the power transmission line state detection model according to the first updating weight parameter;
with every group power transmission line state data as the input, will be with the power transmission line state detection result that every group power transmission line state data corresponds as output, train power transmission line state detection model to obtain first power transmission line state detection model, include:
taking each group of power transmission line state data as input, taking a power transmission line state detection result corresponding to each group of power transmission line state data as output, and training the updated power transmission line state detection model;
in response to the trained power line state detection model converging, storing the trained power line state detection model as a first power line state detection model.
In one implementation of the present disclosure, the method further comprises:
and responding to the fact that the trained power line state detection model does not converge, acquiring a first gradient updating vector according to the trained power line state detection model, and sending the first gradient updating vector to the edge server.
In one implementation of the present disclosure, the first edge server is configured to aggregate the gradient update vector, and update the weight parameter of the power line state detection model on the first edge server according to the aggregated gradient update vector, so as to obtain the updated weight parameter. The first edge server may be a cloud server or a server provided by an operator of the power line status collector. It should be noted that one first edge server may correspond to a plurality of model training ends, and one model training end may correspond to a plurality of power line state collectors, for example, an operator of a power line state collector may divide a governed area into a plurality of blocks, a plurality of model training ends in each block of area may correspond to one first edge server, and each model training end may correspond to a plurality of power line state collectors.
The power line state detection model on the first edge server can be a neural network model, a convolutional neural network model, a long-short term memory network model or the like.
In an implementation manner of the present disclosure, the first update weight parameter sent by the first edge server and received by the power line state collector is obtained by aggregating the first gradient update vectors sent by the plurality of model training terminals by the first edge server and updating the weight parameter of the power line state detection model on the first edge server according to the aggregated first gradient update vector, so that the power line state detection model updated on the model training terminals can reflect a common law between the power line state data and the power line state detection result learned by the power line state detection model on the first edge server in the previous round of training. Then the model training end can take each group of power transmission line state data as input, take the power transmission line state detection result corresponding to each group of power transmission line state data as output, train the updated power transmission line state detection model, so that the power transmission line state detection model on the model training end can also learn the rule between the power transmission line state data acquired by the model training end and the power transmission line state detection result in an individualized way on the basis of learning the common rule, and the power transmission line state detection model on the trained model training end can learn the private rule between the power transmission line state data acquired by the model training end and the power transmission line state detection result; when the power transmission line state detection model on the trained model training end is not converged, it is indicated that the power transmission line state detection model on the trained model training end still needs to be trained continuously, a first gradient update vector is obtained according to the power transmission line state detection model on the trained model training end, and the first gradient update vector is sent, so that the first edge server can continuously obtain corresponding first update weight parameters based on the first gradient update vectors uploaded by the plurality of model training ends, and the power transmission line state detection models on the model training ends are continuously trained; when the power transmission line state detection model on the trained model training end converges, it can be considered that the converged power transmission line state detection model can obtain a power transmission line state detection result with a high accuracy according to the power transmission line state data obtained by the model training end, and the converged power transmission line state detection model can be stored as the first power transmission line state detection model.
In the technical scheme, on one hand, the finally obtained target power transmission line state detection model can be a model which learns the common rule and the private rule, and can obtain a power transmission line state detection result with higher accuracy according to the power transmission line state data obtained by the model training end; on the other hand, as the process of continuously training the power transmission line state detection models on the model training ends is jointly executed by the model training ends and the first edge server, compared with the process of further training the power transmission line state detection models only by the model training ends, the power transmission line state detection model training method has the advantages of less required processing resources and higher training speed.
Fig. 3 shows a flow chart of a model training method according to an embodiment of the present disclosure, as shown in fig. 3, the model training method comprises the following steps S301-S304:
in step S301, at least one group of collector state data collected by the power line state collector, a power line image corresponding to each group of collector state data, and weather data corresponding to each group of collector state data are obtained.
The power transmission line state collector is fixed on a power transmission line between two power transmission line towers, and the power transmission line image at least comprises the power transmission line state collector and part or all of a target power transmission line.
In step S302, at least one group of power line status data is obtained according to at least one group of collector status data, where each group of power line status data includes the collector status data and collector attitude data corresponding to the collector status data.
In step S303, image recognition is performed on the power line image corresponding to the collector state data in each set of power line state data, so as to obtain a power line state detection result corresponding to each set of power line state data.
In step S304, a power line state detection model is obtained, each set of power line state data and weather data corresponding to each set of power line state data are used as input, a power line state detection result corresponding to each set of power line state data is used as output, and the power line state detection model is trained to obtain a second power line state detection model.
In one embodiment of the present disclosure, the collector status data may be understood as indicating a motion status of the power line status collector, and for example, the collector status data may include a speed of the collector in at least one direction, an acceleration of the collector in at least one direction, and the like.
In an embodiment of the present disclosure, the obtaining of at least one set of collector state data collected by the power transmission line state collector may be understood as receiving at least one set of collector state data sent by the power transmission line state collector, or may be reading at least one set of collector state data stored in advance.
In an embodiment of the present disclosure, the power line image corresponding to the collector state data may be understood as a power line image collected when the power line state collector collects the set of collector state data, and the power line image is obtained, and may be a power line image sent by a corresponding image collection device, or a power line image obtained in advance may be read.
In one embodiment of the present disclosure, the collector attitude data may be understood as a real-time attitude for indicating the power line status collector.
In one implementation of the present disclosure, the collector state data includes an acceleration of the power line state collector in at least one direction and an angular velocity of rotation of the power line state collector about the one direction.
In one embodiment of the present disclosure, the power line status detection result corresponding to the power line status data can be understood as indicating whether the target power line is in a disconnected state when the set of power line status data is collected.
In one embodiment of the present disclosure, the second power line state detection model may be pre-stored or may be obtained from another device or system. The second power line state detection model may be a Neural Network (NN) model, a Convolutional Neural Network (CNN) model, a Long Short Term Memory (LSTM) model, or the like. The second power transmission line state detection model can be understood as a model for learning the rule among the collector state data, the weather data and the power transmission line state detection result.
According to the technical scheme provided by the embodiment of the disclosure, at least one group of collector state data collected by a power transmission line state collector and a power transmission line image corresponding to each group of collector state data are obtained, and at least one group of power transmission line state data is obtained according to the at least one group of collector state data; carrying out image recognition on the power transmission line image corresponding to the collector state data in each group of power transmission line state data so as to obtain a power transmission line state detection result corresponding to each group of power transmission line state data, and determining whether a target power transmission line where the power transmission line state collector is located is in a disconnection state or not when the corresponding collector state data is collected according to the power transmission line state detection result; the method comprises the steps of obtaining a power transmission line state detection model, taking each group of power transmission line state data and weather data corresponding to each group of power transmission line state data as input, taking a power transmission line state detection result corresponding to each group of power transmission line state data as output, and training the power transmission line state detection model to obtain a second power transmission line state detection model. The second power transmission line state detection model can learn the rule among the power transmission line state data, the weather data and the power transmission line state detection result, whether the target power transmission line between the two power transmission line towers has the fault or not is detected based on the second power transmission line state detection model, so that the detection efficiency is improved, and the detection accuracy is improved.
In one implementation of the present disclosure, the collector state data includes an acceleration of the power line state collector in at least one direction and an angular velocity of rotation of the power line state collector about the one direction.
In the technical scheme, the collector state data are limited to comprise the acceleration of the power transmission line state collector in at least one direction and the angular speed of the power transmission line state collector rotating around one direction, so that the motion state of the power transmission line state collector can be accurately obtained according to the collector state data.
In one implementation of the present disclosure, the collector attitude data corresponding to the collector state data includes:
and according to the collector state data, calculating the pitch angle of the power transmission line state collector, the roll angle of the power transmission line state collector and the course angle of the power transmission line state collector by a quaternion algorithm.
According to the technical scheme, the attitude of the power transmission line state collector can be accurately obtained according to the attitude data of the collector by limiting the attitude data of the collector corresponding to the state data of the collector to include the pitch angle of the power transmission line state collector, the roll angle of the power transmission line state collector and the course angle of the power transmission line state collector which are obtained through calculation by a quaternion algorithm according to the state data of the collector.
In one implementation of the present disclosure, each group of power line status data and the weather data corresponding to each group of power line status data are used as inputs, the power line status detection result corresponding to each group of power line status data is used as an output, and the power line status detection model is trained before obtaining the second power line status detection model, and the method further includes:
receiving a second updating weight parameter sent by a second edge server, and updating the power transmission line state detection model according to the second updating weight parameter;
with every group power transmission line state data and with the weather data that every group power transmission line state data corresponds as the input, will be with the power transmission line state testing result that every group power transmission line state data corresponds as output, train power transmission line state detection model to acquire second power transmission line state detection model, include:
taking each group of power transmission line state data and weather data corresponding to each group of power transmission line state data as input, taking a power transmission line state detection result corresponding to each group of power transmission line state data as output, and training the updated power transmission line state detection model;
in response to the trained power line state detection model converging, storing the trained power line state detection model as a second power line state detection model.
In one implementation of the present disclosure, the method further comprises:
and responding to the non-convergence of the trained power transmission line state detection model, acquiring a second gradient update vector according to the trained power transmission line state detection model, and sending the second gradient update vector to the edge server.
In one implementation manner of the present disclosure, the second edge server is configured to aggregate the gradient update vector, and update the weight parameter of the power line state detection model on the second edge server according to the aggregated gradient update vector, so as to obtain an updated weight parameter. The second edge server may be a cloud server or a server provided by an operator of the power line status collector. It should be noted that one second edge server may correspond to multiple model training ends, and one model training end may correspond to multiple power line state collectors, for example, an operator of a power line state collector may divide a controlled area into multiple blocks, multiple model training ends in each block may correspond to one second edge server, and each model training end may correspond to multiple power line state collectors.
The power line state detection model on the second edge server can be a neural network model, a convolutional neural network model, a long-short term memory network model or the like.
In an implementation manner of the present disclosure, the second updated weight parameter sent by the second edge server and received by the power line state collector is obtained by aggregating the second gradient update vectors sent by the second edge server according to the plurality of model training terminals and updating the weight parameter of the power line state detection model on the second edge server according to the aggregated second gradient update vectors, so that the updated power line state detection model on the model training terminal can reflect a common rule between the power line state data, the weather data and the power line state detection result learned by the power line state detection model on the second edge server in the previous round of training. Then, the model training end can take each group of power transmission line state data and weather data corresponding to each group of power transmission line state data as input, take the power transmission line state detection result corresponding to each group of power transmission line state data as output, train the updated power transmission line state detection model, so that the power transmission line state detection model on the model training end can learn the common regularity, and also can learn the power transmission line state data acquired by the model training end per se and the rules between the weather data and the power transmission line state detection result in a personalized manner, so that the power transmission line state detection model on the trained model training end can learn the private rules between the power transmission line state data acquired by the model training end per se, the weather data and the power transmission line state detection result; when the power transmission line state detection model on the trained model training end is not converged, the power transmission line state detection model on the trained model training end still needs to be trained, a second gradient update vector is obtained according to the power transmission line state detection model on the trained model training end, and the second gradient update vector is sent, so that the second edge server can continuously obtain corresponding second update weight parameters based on the second gradient update vectors uploaded by the plurality of model training ends, and further, the power transmission line state detection model on each model training end is continuously trained; when the power transmission line state detection model on the trained model training end converges, it can be considered that the converged power transmission line state detection model can obtain a power transmission line state detection result with a high accuracy according to the power transmission line state data obtained by the model training end, and the converged power transmission line state detection model can be stored as a second power transmission line state detection model.
In the technical scheme, on one hand, the finally obtained target power transmission line state detection model can be a model which learns the common rule and the private rule, and can obtain a power transmission line state detection result with higher accuracy according to the power transmission line state data obtained by the model training end; on the other hand, as the process of continuously training the power transmission line state detection models on the model training ends is jointly executed by the model training ends and the second edge server, compared with the process of further training the power transmission line state detection models only by the model training ends, the power transmission line state detection model training method has the advantages of less required processing resources and higher training speed.
Fig. 4 shows a block diagram of a power line detection device according to an embodiment of the present disclosure. The apparatus may be implemented as part or all of an electronic device through software, hardware, or a combination of both.
As shown in fig. 4, the power line detection apparatus 400 includes:
the first data acquisition module 401 is configured to acquire at least one group of collector state data acquired by the power transmission line state collector, and acquire at least one group of power transmission line state data according to the at least one group of collector state data, where each group of power transmission line state data includes the collector state data and collector attitude data corresponding to the collector state data, and the power transmission line state collector is fixed on a target power transmission line between two power transmission towers;
a data detection module 402 configured to detect at least one set of power line status data to generate a power line status detection result;
and a fault alarm module 403 configured to generate power line disconnection fault information in response to detection results of at least two groups of consecutive power line status data both satisfying a status data standard exceeding condition.
According to the technical scheme provided by the embodiment of the disclosure, at least one group of collector state data collected by a power transmission line state collector is obtained, and at least one group of power transmission line state data is obtained according to the at least one group of collector state data, wherein each group of power transmission line state data comprises the collector state data and collector attitude data corresponding to the collector state data, and the power transmission line state collector is fixed on a target power transmission line between two power transmission towers, so that the power transmission line state data can reflect the motion state of the target power transmission line and the attitude of the target power transmission line; detecting at least one group of power transmission line state data to generate a power transmission line state detection result; and generating the power transmission line disconnection fault information in response to the detection results of at least two groups of continuous power transmission line state data meeting the condition that the state data exceeds the standard. When the detection results of at least two groups of continuous power transmission line state data meet the condition that the state data exceed the standard, the motion state of a target power transmission line can be understood to represent that the target power transmission line is in a motion state of continuous falling, and the posture of the target power transmission line can represent that the posture of the target power transmission line exceeds the normal posture change range due to the fact that the target power transmission line is disconnected with a power transmission line tower, so that power transmission line falling fault information used for indicating that the target power transmission line has a falling fault is generated.
Fig. 5 shows a block diagram of a model training apparatus according to an embodiment of the present disclosure. The apparatus may be implemented as part or all of an electronic device through software, hardware, or a combination of both.
As shown in fig. 5, the model training apparatus 500 includes:
a second data obtaining module 501, configured to obtain at least one set of collector state data collected by a power line state collector, and a power line image corresponding to each set of collector state data, where the power line state collector is fixed on a power line between two power line towers, and the power line image at least includes the power line state collector and part or all of a target power line;
a first data processing module 502 configured to obtain at least one set of power line state data according to at least one set of collector state data, each set of power line state data including collector state data and collector attitude data corresponding to the collector state data;
a first image recognition module 503, configured to perform image recognition on the power line image corresponding to the collector state data in each group of power line state data, so as to obtain a power line state detection result corresponding to each group of power line state data;
a first model training module 504 configured to obtain a power line state detection model, take each set of power line state data as input, take a power line state detection result corresponding to each set of power line state data as output, train the power line state detection model to obtain the first power line state detection model.
According to the technical scheme provided by the embodiment of the disclosure, at least one group of collector state data collected by a power transmission line state collector and a power transmission line image corresponding to each group of collector state data are obtained, and at least one group of power transmission line state data is obtained according to the at least one group of collector state data; carrying out image recognition on the power transmission line image corresponding to the collector state data in each group of power transmission line state data so as to obtain a power transmission line state detection result corresponding to each group of power transmission line state data, and determining whether a target power transmission line where the power transmission line state collector is located is in a disconnection state or not when the corresponding collector state data is collected according to the power transmission line state detection result; the method comprises the steps of obtaining a power transmission line state detection model, taking each group of power transmission line state data as input, taking a power transmission line state detection result corresponding to each group of power transmission line state data as output, training the power transmission line state detection model, obtaining a first power transmission line state detection model, enabling the first power transmission line state detection model to learn rules between the power transmission line state data and the power transmission line state detection result, and detecting whether a target power transmission line between two power transmission line towers has a fault or not based on the first power transmission line state detection model, thereby improving detection efficiency and improving detection accuracy.
Fig. 6 shows a block diagram of a model training apparatus according to an embodiment of the present disclosure. The apparatus may be implemented as part or all of an electronic device through software, hardware, or a combination of both.
As shown in fig. 6, the model training apparatus 600 includes:
a third data obtaining module 601, configured to obtain at least one set of collector state data collected by the power line state collector, a power line image corresponding to each set of collector state data, and weather data corresponding to each set of collector state data, where the power line state collector is fixed on a power line between two power line towers, and the power line image at least includes the power line state collector and part or all of a target power line;
a second data processing module 602 configured to obtain at least one set of power line state data according to at least one set of collector state data, where each set of power line state data includes collector state data and collector attitude data corresponding to the collector state data;
the second image recognition module 603 is configured to perform image recognition on the power line image corresponding to the collector state data in each group of power line state data, so as to obtain a power line state detection result corresponding to each group of power line state data;
a second model training module 604 configured to obtain the power line state detection model, take each set of power line state data and weather data corresponding to each set of power line state data as inputs, take a power line state detection result corresponding to each set of power line state data as an output, and train the power line state detection model to obtain a second power line state detection model.
According to the technical scheme provided by the embodiment of the disclosure, at least one group of collector state data collected by a power transmission line state collector and a power transmission line image corresponding to each group of collector state data are obtained, and at least one group of power transmission line state data is obtained according to the at least one group of collector state data; carrying out image recognition on the power transmission line image corresponding to the collector state data in each group of power transmission line state data so as to obtain a power transmission line state detection result corresponding to each group of power transmission line state data, and determining whether a target power transmission line where the power transmission line state collector is located is in a broken state or not when the corresponding collector state data is collected according to the power transmission line state detection result; the method comprises the steps of obtaining a power transmission line state detection model, taking each group of power transmission line state data and weather data corresponding to each group of power transmission line state data as input, taking a power transmission line state detection result corresponding to each group of power transmission line state data as output, and training the power transmission line state detection model to obtain a second power transmission line state detection model. The second power transmission line state detection model can learn the rule among the power transmission line state data, the weather data and the power transmission line state detection result, whether the target power transmission line between the two power transmission line towers has a fault or not is detected based on the second power transmission line state detection model, so that the detection efficiency is improved, and the detection accuracy is improved.
The present disclosure also discloses an electronic device, and fig. 7 shows a block diagram of the electronic device according to an embodiment of the present disclosure.
As shown in fig. 7, the electronic device includes a memory and a processor, where the memory is to store one or more computer instructions, where the one or more computer instructions are executed by the processor to implement a method according to an embodiment of the disclosure.
In a first aspect, an embodiment of the present disclosure provides a power line detection method, where the method includes:
acquiring at least one group of collector state data acquired by a power transmission line state collector, and acquiring at least one group of power transmission line state data according to the at least one group of collector state data, wherein each group of power transmission line state data comprises the collector state data and collector attitude data corresponding to the collector state data, and the power transmission line state collector is fixed on a target power transmission line between two power transmission line towers;
detecting at least one group of power transmission line state data to generate a power transmission line state detection result;
and generating the power transmission line disconnection fault information in response to the detection results of at least two groups of continuous power transmission line state data meeting the condition that the state data exceeds the standard.
In one implementation of the present disclosure, generating power transmission line drop fault information in response to detection results of at least two sets of continuous power transmission line status data both satisfying a status data standard exceeding condition includes:
responding to the detection results of at least two groups of continuous power transmission line state data to meet the condition that the state data exceeds the standard, and acquiring attitude data of a target collector;
and responding to the situation that the difference between the attitude data of the collector in the latter group of power transmission line state data and the attitude data of the target collector in at least two groups of continuous power transmission line state data meets the standard exceeding condition of the attitude data of the collector, and generating the power transmission line disconnection fault information.
In one implementation of the present disclosure, the method further comprises:
and generating power transmission line disconnection warning information in response to the situation that the difference between the collector attitude data in the latter group of power transmission line state data and the target collector attitude data in at least two groups of continuous power transmission line state data does not meet the standard exceeding condition of the collector attitude data.
In one implementation of the present disclosure, the collector state data includes an acceleration of the power line state collector in at least one direction and an angular velocity of rotation of the power line state collector about the one direction.
In one implementation of the present disclosure, the collector attitude data corresponding to the collector state data includes:
and according to the collector state data, calculating the pitch angle of the power transmission line state collector, the roll angle of the power transmission line state collector and the course angle of the power transmission line state collector by a quaternion algorithm.
In an implementation manner of the present disclosure, obtaining at least one set of collector status data collected by the power transmission line status collector includes:
acquiring continuous four groups of collector state data collected by a power transmission line state collector;
detecting at least one set of power line state data to generate a power line state detection result, comprising:
detecting the state data of a third group of collectors in the state data of the four groups of continuous collectors to generate a detection result of the state of the power transmission line;
the method further comprises the following steps:
and in response to the condition that the detection result of the power transmission line state does not meet the standard exceeding condition of the state data, deleting the first group of collector state data in the four groups of continuous collector state data, forwarding the second group to the fourth group of collector state data in the four groups of continuous collector state data, and storing the collector state data currently collected by the power transmission line state collector as the fourth group of collector state data in the four groups of continuous collector state data.
In one implementation of the present disclosure, detecting a third set of status data of four consecutive sets of status data of collectors to generate a power line status detection result includes
And acquiring a first power transmission line state detection model, and inputting the state data of the third group of collectors into the first power transmission line state detection model to acquire a power transmission line state detection result.
In one implementation manner of the present disclosure, before detecting the third group of collector state data in the four groups of continuous collector state data to generate a power transmission line state detection result, the method further includes:
acquiring weather data corresponding to the state data of the third group of collectors;
and acquiring a second power transmission line state detection model, and inputting the third group of collector state data and the weather data into the second power transmission line state detection model to acquire a power transmission line state detection result.
In a second aspect, an embodiment of the present disclosure provides a model training method, where the method includes:
acquiring at least one group of collector state data acquired by a power transmission line state collector and a power transmission line image corresponding to each group of collector state data, wherein the power transmission line state collector is fixed on a power transmission line between two power transmission line towers, and the power transmission line image at least comprises the power transmission line state collector and part or all of a target power transmission line;
acquiring at least one group of power transmission line state data according to at least one group of collector state data, wherein each group of power transmission line state data comprises collector state data and collector attitude data corresponding to the collector state data;
carrying out image recognition on the power transmission line image corresponding to the collector state data in each group of power transmission line state data to obtain a power transmission line state detection result corresponding to each group of power transmission line state data;
the method comprises the steps of obtaining a power transmission line state detection model, taking each group of power transmission line state data as input, taking a power transmission line state detection result corresponding to each group of power transmission line state data as output, and training the power transmission line state detection model to obtain a first power transmission line state detection model.
In one implementation of the present disclosure, the collector state data includes an acceleration of the power line state collector in at least one direction and an angular velocity of rotation of the power line state collector about the one direction.
In one implementation manner of the present disclosure, the collector attitude data corresponding to the collector state data includes:
and according to the collector state data, calculating the pitch angle of the power transmission line state collector, the roll angle of the power transmission line state collector and the course angle of the power transmission line state collector by a quaternion algorithm.
In one implementation of the present disclosure, each group of power line state data is used as an input, a power line state detection result corresponding to each group of power line state data is used as an output, and the power line state detection model is trained to obtain the first power line state detection model before the method further includes:
receiving a first updating weight parameter sent by a first edge server, and updating the power transmission line state detection model according to the first updating weight parameter;
with every group power transmission line state data as the input, will be with the power transmission line state detection result that every group power transmission line state data corresponds as output, train power transmission line state detection model to obtain first power transmission line state detection model, include:
taking each group of power transmission line state data as input, taking a power transmission line state detection result corresponding to each group of power transmission line state data as output, and training the updated power transmission line state detection model;
and responding to the convergence of the trained power transmission line state detection model, and storing the trained power transmission line state detection model as a first power transmission line state detection model.
In one implementation of the present disclosure, the method further comprises:
and responding to the non-convergence of the trained power transmission line state detection model, acquiring a first gradient update vector according to the trained power transmission line state detection model, and sending the first gradient update vector to the edge server.
In a third aspect, an embodiment of the present disclosure provides a model training method, where the method includes:
acquiring at least one group of collector state data acquired by a power transmission line state collector, a power transmission line image corresponding to each group of collector state data and weather data corresponding to each group of collector state data, wherein the power transmission line state collector is fixed on a power transmission line between two power transmission line towers, and the power transmission line image at least comprises the power transmission line state collector and part or all of a target power transmission line;
acquiring at least one group of power transmission line state data according to at least one group of collector state data, wherein each group of power transmission line state data comprises collector state data and collector attitude data corresponding to the collector state data;
carrying out image recognition on the power transmission line image corresponding to the collector state data in each group of power transmission line state data to obtain a power transmission line state detection result corresponding to each group of power transmission line state data;
the method comprises the steps of obtaining a power transmission line state detection model, taking each group of power transmission line state data and weather data corresponding to each group of power transmission line state data as input, taking a power transmission line state detection result corresponding to each group of power transmission line state data as output, and training the power transmission line state detection model to obtain a second power transmission line state detection model.
In one implementation of the present disclosure, the collector state data includes an acceleration of the power line state collector in at least one direction and an angular velocity of rotation of the power line state collector about the one direction.
In one implementation of the present disclosure, the collector attitude data corresponding to the collector state data includes:
and according to the collector state data, calculating the pitch angle of the power transmission line state collector, the roll angle of the power transmission line state collector and the course angle of the power transmission line state collector by a quaternion algorithm.
In one implementation of the present disclosure, each group of power line status data and the weather data corresponding to each group of power line status data are used as inputs, the power line status detection result corresponding to each group of power line status data is used as an output, and the power line status detection model is trained before obtaining the second power line status detection model, and the method further includes:
receiving a second updating weight parameter sent by a second edge server, and updating the power transmission line state detection model according to the second updating weight parameter;
with every group power transmission line state data and with the weather data that every group power transmission line state data corresponds as the input, will be with the power transmission line state testing result that every group power transmission line state data corresponds as output, train power transmission line state detection model to acquire second power transmission line state detection model, include:
taking each group of power transmission line state data and weather data corresponding to each group of power transmission line state data as input, taking a power transmission line state detection result corresponding to each group of power transmission line state data as output, and training the updated power transmission line state detection model;
and responding to the convergence of the trained power transmission line state detection model, and storing the trained power transmission line state detection model as a second power transmission line state detection model.
In one implementation of the present disclosure, the method further comprises:
and responding to the non-convergence of the trained power transmission line state detection model, acquiring a second gradient update vector according to the trained power transmission line state detection model, and sending the second gradient update vector to the edge server.
FIG. 8 shows a schematic block diagram of a computer system suitable for use in implementing a method according to an embodiment of the present disclosure.
As shown in fig. 8, the computer system includes a processing unit that can execute the various methods in the above-described embodiments according to a program stored in a Read Only Memory (ROM) or a program loaded from a storage section into a Random Access Memory (RAM). In the RAM, various programs and data necessary for the operation of the computer system are also stored. The processing unit, the ROM, and the RAM are connected to each other through a bus. An input/output (I/O) interface is also connected to the bus.
The following components are connected to the I/O interface: an input section including a keyboard, a mouse, and the like; an output section including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section including a hard disk and the like; and a communication section including a network interface card such as a LAN card, a modem, or the like. The communication section performs a communication process via a network such as the internet. The drive is also connected to the I/O interface as needed. A removable medium such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive as necessary, so that a computer program read out therefrom is mounted into the storage section as necessary. The processing unit can be realized as a CPU, a GPU, a TPU, an FPGA, an NPU and other processing units.
In particular, the above described methods may be implemented as computer software programs according to embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product comprising a computer program tangibly embodied on a machine-readable medium, the computer program comprising program code for performing the above-described method. In such an embodiment, the computer program may be downloaded and installed from a network via the communication section, and/or installed from a removable medium.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units or modules described in the embodiments of the present disclosure may be implemented by software or by programmable hardware. The units or modules described may also be provided in a processor, and the names of the units or modules do not in some cases constitute a limitation of the units or modules themselves.
As another aspect, the present disclosure also provides a computer-readable storage medium, which may be the computer-readable storage medium included in the electronic device or the computer system in the above embodiments; or it may be a separate computer readable storage medium not incorporated into the device. The computer readable storage medium stores one or more programs for use by one or more processors in performing the methods described in the present disclosure.
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is made without departing from the inventive concept. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.

Claims (10)

1. A method for power line detection, the method comprising:
acquiring at least one group of collector state data acquired by a power transmission line state collector, and acquiring at least one group of power transmission line state data according to the at least one group of collector state data, wherein each group of power transmission line state data comprises the collector state data and collector attitude data corresponding to the collector state data, and the power transmission line state collector is fixed on a target power transmission line between two power transmission line towers;
detecting at least one group of power transmission line state data to generate a power transmission line state detection result;
responding to the detection results of at least two groups of continuous power transmission line state data to meet the condition that the state data exceeds the standard, and generating power transmission line disconnection fault information;
the method for acquiring the state data of at least one group of collectors acquired by the power transmission line state collector comprises the following steps:
acquiring continuous four groups of collector state data collected by a power transmission line state collector;
the detecting at least one group of power line state data to generate a power line state detection result comprises:
detecting the state data of a third group of collectors in the four groups of continuous collector state data to generate a power transmission line state detection result;
the method further comprises the following steps:
and in response to the power transmission line state detection result not meeting the condition that the state data exceeds the standard, deleting a first group of collector state data in the four groups of continuous collector state data, forwarding a second group to a fourth group of collector state data in the four groups of continuous collector state data, and storing the collector state data currently collected by the power transmission line state collector as the fourth group of collector state data in the four groups of continuous collector state data.
2. A power transmission line detection method according to claim 1, wherein said generating power transmission line drop fault information in response to detection results of at least two successive sets of power transmission line status data each satisfying a status data out-of-limits condition comprises:
responding to the detection results of at least two groups of continuous power transmission line state data to meet the condition that the state data exceeds the standard, and acquiring attitude data of a target collector;
and generating the power transmission line disconnection fault information in response to the fact that the difference between the collector attitude data in the latter group of power transmission line state data in the at least two groups of continuous power transmission line state data and the target collector attitude data meets the standard exceeding condition of the collector attitude data.
3. A power transmission line detection method according to claim 2, characterized in that the method further comprises:
and generating power transmission line disconnection warning information in response to the situation that the difference between the collector attitude data in the latter group of power transmission line state data in the at least two groups of continuous power transmission line state data and the target collector attitude data does not meet the standard exceeding condition of the collector attitude data.
4. The power transmission line detection method of claim 1, wherein the collector status data comprises acceleration of the power transmission line status collector in at least one direction and angular velocity of rotation of the power transmission line status collector about one direction.
5. The power transmission line detection method according to claim 1, wherein the collector attitude data corresponding to the collector status data includes:
and according to the collector state data, calculating the pitch angle of the power transmission line state collector, the roll angle of the power transmission line state collector and the course angle of the power transmission line state collector by a quaternion algorithm.
6. The method for detecting power transmission lines according to claim 1, wherein the detecting a third group of collector status data of the four groups of collector status data to generate the power transmission line status detection result comprises:
and acquiring a first power transmission line state detection model, and inputting the state data of the third group of collectors into the first power transmission line state detection model to acquire a power transmission line state detection result.
7. The power line detection method of claim 1, wherein prior to detecting a third of the four consecutive sets of collector state data to generate the power line state detection result, the method further comprises:
acquiring weather data corresponding to the third group of collector state data;
and acquiring a second power transmission line state detection model, and inputting the third group of collector state data and the weather data into the second power transmission line state detection model to acquire a power transmission line state detection result.
8. A power transmission line detection device, comprising:
the first data acquisition module is configured to acquire at least one group of collector state data acquired by the power transmission line state collector and acquire at least one group of power transmission line state data according to the at least one group of collector state data, each group of power transmission line state data comprises the collector state data and collector attitude data corresponding to the collector state data, and the power transmission line state collector is fixed on a target power transmission line between two power transmission line towers;
the method for acquiring at least one group of collector state data collected by the power transmission line state collector comprises the following steps:
acquiring continuous four groups of collector state data collected by a power transmission line state collector;
a data detection module configured to detect at least one set of power line status data to generate a power line status detection result;
the detecting at least one group of power line state data to generate a power line state detection result comprises:
detecting the state data of a third group of collectors in the four groups of continuous collector state data to generate a power transmission line state detection result;
the fault warning module is configured to respond to the detection results of at least two groups of continuous power transmission line state data meeting the condition that the state data exceeds the standard, and generate power transmission line disconnection fault information;
and in response to the power transmission line state detection result not meeting the condition that the state data exceeds the standard, deleting a first group of collector state data in the four groups of continuous collector state data, forwarding a second group to a fourth group of collector state data in the four groups of continuous collector state data, and storing the collector state data currently collected by the power transmission line state collector as the fourth group of collector state data in the four groups of continuous collector state data.
9. An electronic device comprising a memory and a processor; wherein the memory is to store one or more computer instructions, wherein the one or more computer instructions are to be executed by the processor to implement the method steps of any one of claims 1-7.
10. A computer-readable storage medium having stored thereon computer instructions, characterized in that the computer instructions, when executed by a processor, carry out the method steps of any of claims 1-7.
CN202210944464.2A 2022-08-08 2022-08-08 Power transmission line detection method, model training method, device, equipment and medium Active CN115062730B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210944464.2A CN115062730B (en) 2022-08-08 2022-08-08 Power transmission line detection method, model training method, device, equipment and medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210944464.2A CN115062730B (en) 2022-08-08 2022-08-08 Power transmission line detection method, model training method, device, equipment and medium

Publications (2)

Publication Number Publication Date
CN115062730A CN115062730A (en) 2022-09-16
CN115062730B true CN115062730B (en) 2023-01-31

Family

ID=83207985

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210944464.2A Active CN115062730B (en) 2022-08-08 2022-08-08 Power transmission line detection method, model training method, device, equipment and medium

Country Status (1)

Country Link
CN (1) CN115062730B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009207273A (en) * 2008-02-27 2009-09-10 Tokyo Electric Power Co Inc:The System, method and program for detecting disconnection of high voltage distribution line
CN110187233A (en) * 2019-05-23 2019-08-30 国家电网有限公司 Holographic sensor, transmission line malfunction method of disposal and terminal device
CN113113967A (en) * 2021-04-08 2021-07-13 嘉兴学院 Power transmission line detection system
CN113660128A (en) * 2021-08-20 2021-11-16 北京神州新桥科技有限公司 Network device failure prediction method, electronic device, and storage medium
CN114088092A (en) * 2021-11-08 2022-02-25 广州吉欧电子科技有限公司 Tower inclination monitoring equipment and method based on double GNSS antennas and MEMS
WO2022158947A1 (en) * 2021-01-25 2022-07-28 엑사이트 Method for estimating overhead power transmission line by using acceleration and angular velocity or imu sensor

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110675387B (en) * 2019-09-26 2021-09-24 北京国网富达科技发展有限责任公司 Method and device for detecting structural defects of transmission line iron tower
US20220069577A1 (en) * 2020-09-01 2022-03-03 Delphire Inc. Systems, Methods and Apparatus for Critical Event Monitoring, Capture, and Response Near Overhead Electrical Power Lines and Associated Equipment and Facilities
CN112184678A (en) * 2020-09-30 2021-01-05 国网北京市电力公司 Image recognition method, image recognition device, computer-readable storage medium and processor

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009207273A (en) * 2008-02-27 2009-09-10 Tokyo Electric Power Co Inc:The System, method and program for detecting disconnection of high voltage distribution line
CN110187233A (en) * 2019-05-23 2019-08-30 国家电网有限公司 Holographic sensor, transmission line malfunction method of disposal and terminal device
WO2022158947A1 (en) * 2021-01-25 2022-07-28 엑사이트 Method for estimating overhead power transmission line by using acceleration and angular velocity or imu sensor
CN113113967A (en) * 2021-04-08 2021-07-13 嘉兴学院 Power transmission line detection system
CN113660128A (en) * 2021-08-20 2021-11-16 北京神州新桥科技有限公司 Network device failure prediction method, electronic device, and storage medium
CN114088092A (en) * 2021-11-08 2022-02-25 广州吉欧电子科技有限公司 Tower inclination monitoring equipment and method based on double GNSS antennas and MEMS

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
配电线路故障定位装置关键技术的研究;何松生 等;《电力电气》;20170228;31-35 *

Also Published As

Publication number Publication date
CN115062730A (en) 2022-09-16

Similar Documents

Publication Publication Date Title
CN111741133B (en) Cloud-side-end-collaborative meteorological intelligent early warning system
CN112734970B (en) Automatic inspection system and method for unmanned aerial vehicle in wind farm based on LoRaWAN positioning technology
CN114898232B (en) Photovoltaic power station unmanned aerial vehicle inspection method and system based on photovoltaic group string data analysis
CN103166323A (en) System for monitoring secondary circuit model on line in real time based on protection device
CN112506205B (en) Robot inspection task planning method and device
CN112819988A (en) Unmanned aerial vehicle power station intelligent inspection method and system based on 5G and network side server
CN207319050U (en) A kind of Centralized Monitoring operational system of photovoltaic power station
CN114221978A (en) Urban rail transit cloud platform system
CN112614130A (en) Unmanned aerial vehicle power transmission line insulator fault detection method based on 5G transmission and YOLOv3
CN115062730B (en) Power transmission line detection method, model training method, device, equipment and medium
CN113359829B (en) Unmanned aerial vehicle power plant intelligent inspection method based on big data
CN108806014A (en) A kind of remote computer machine room intelligent cruising inspection system based on cloud computer
CN114202910A (en) Instrument recognition device, instrument monitoring system and monitoring method thereof
CN107886590A (en) Operation on the sea cruising inspection system and method based on unmanned plane
CN114997645B (en) Method, system, computer device and medium for optimizing operation and maintenance scheduling of offshore wind farm
CN111857015B (en) Power transmission and transformation cloud intelligent controller
CN115700644A (en) Vision-based automatic inspection method and device for wind power station
CN114610050A (en) Inspection method and device for power system, electronic equipment and storage medium
CN111897655B (en) Power transmission and transformation high in clouds intelligent control ware
CN108023638A (en) A kind of Big Dipper terminal monitory system and monitoring method
CN218446730U (en) Power load prediction fingerprint image construction device based on Haisi 3559A
US11790516B1 (en) Method and system for monitoring GIS instrument sulfur hexafluoride data based on edge computing
CN108090988A (en) A kind of hand-held inspection terminal and cruising inspection system
CN218567647U (en) System fusion device suitable for ground remote sensing vertical observation equipment
CN210015520U (en) Intelligent transportation device based on narrow-band Internet of things NB-IOT

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