CN110942221A - Transformer substation fault rapid repairing method based on Internet of things - Google Patents

Transformer substation fault rapid repairing method based on Internet of things Download PDF

Info

Publication number
CN110942221A
CN110942221A CN201910712336.3A CN201910712336A CN110942221A CN 110942221 A CN110942221 A CN 110942221A CN 201910712336 A CN201910712336 A CN 201910712336A CN 110942221 A CN110942221 A CN 110942221A
Authority
CN
China
Prior art keywords
fault
sensor
equipment
image
detected value
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201910712336.3A
Other languages
Chinese (zh)
Inventor
高惠新
周刚
李霖
蔡亚楠
蔡宏飞
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.)
Jiaxing Power Supply Co of State Grid Zhejiang Electric Power Co Ltd
Original Assignee
Jiaxing Power Supply Co of State Grid Zhejiang Electric Power 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 Jiaxing Power Supply Co of State Grid Zhejiang Electric Power Co Ltd filed Critical Jiaxing Power Supply Co of State Grid Zhejiang Electric Power Co Ltd
Priority to CN201910712336.3A priority Critical patent/CN110942221A/en
Publication of CN110942221A publication Critical patent/CN110942221A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06313—Resource planning in a project environment
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02B—BOARDS, SUBSTATIONS OR SWITCHING ARRANGEMENTS FOR THE SUPPLY OR DISTRIBUTION OF ELECTRIC POWER
    • H02B3/00—Apparatus specially adapted for the manufacture, assembly, or maintenance of boards or switchgear
    • 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

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Educational Administration (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Development Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Power Engineering (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • Manufacturing & Machinery (AREA)
  • Primary Health Care (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Alarm Systems (AREA)

Abstract

The invention relates to the technical field of power failure maintenance, in particular to a transformer substation fault rapid repairing method based on the Internet of things, which comprises the following steps: establishing a sensor table and a sensor cooperation table when the sensor LiDetection value
Figure DDA0002154196810000011
Beyond its safety range, according to the cooperation of the sensors Li‑kDetected value of (2)
Figure DDA0002154196810000012
Judging whether equipment failure occurs, if so, sending an alarm, otherwise, repeating the operation periodicallyA step of; and simultaneously establishing a fault studying and judging subsystem and a fault repairing strategy making subsystem. The substantial effects of the invention are as follows: the accuracy of equipment fault detection is improved through sensor cooperation, a fault source is determined through a fault research and judgment subsystem, an optimal repair strategy is formulated through a fault repair strategy formulation subsystem, and the fault repair efficiency is improved; and a data collection mechanism is established, so that empirical data can be accumulated, reference is provided for subsequent fault repair, and the fault maintenance level is improved.

Description

Transformer substation fault rapid repairing method based on Internet of things
Technical Field
The invention relates to the technical field of power failure maintenance, in particular to a transformer substation fault rapid repairing method based on the Internet of things.
Background
With rapid development of economy and industry, the demand for electricity is also rapidly increasing. The size of the power grid is also continuously expanding. Meanwhile, the quality requirement of users on electric energy is higher and higher, and in order to meet the power consumption requirements of users, a large amount of modernization construction is carried out on a power grid. A large number of smart devices, networking devices, and automation devices are used in the power grid. The management and maintenance of these devices become the main burden of the operation and maintenance of the power grid. The intelligent equipment is various in types and various in models, and management of the intelligent equipment is heavy work. And the intelligent device has rich functions, but the failure probability is higher than that of the common device. Thus, the maintenance work of the power grid is challenging. If the failed equipment cannot be repaired in time, the potential safety hazard of the power grid is greatly increased, and risks or losses are brought to the power grid and the equipment used for the power grid. The fast overhaul of the equipment in the power grid becomes an important subject of the current power grid development.
Chinese patent CN105447772A, published 2016, 3, 30, an electric power rush-repair intelligent scheduling system, comprising a rush-repair intelligent scheduling center, a warehouse management information system, a vehicle-mounted GPS system and a GPS intelligent terminal, wherein the rush-repair intelligent scheduling center is in network communication with the warehouse management information system, and is in two-way communication with the vehicle-mounted GPS system and the GPS intelligent terminal through a GPRS wireless network; by utilizing the advantages of GIS geographic information processing and visualization, electric power pipe network facilities, traffic network facilities and various emergency repair resources are fused together and are displayed in a unified manner in the form of a map, GPS and GPRS technologies are combined to construct an electric power emergency repair intelligent mobile scheduling system, and intelligent positioning of electric power faults, planning and monitoring of the traveling path of an emergency repair vehicle, field information intercommunication, scheduling of personnel and equipment and the like can be realized, so that the efficiency of electric power emergency repair is improved, the repair of faults is accelerated, and the economic loss is reduced. However, the equipment failure can not be researched and judged, the field investigation needs to be carried out manually, and the equipment still needs to be returned to a warehouse to take spare parts or overhaul the equipment during or after the investigation, so that the overhaul efficiency is low.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the technical problem that a quick overhaul scheme of substation equipment is lacked at present. The transformer substation fault rapid repairing system based on the Internet of things is provided, and can judge fault sources and improve maintenance efficiency.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows: a transformer substation fault rapid repairing method based on the Internet of things is used for fault maintenance of a transformer substation with a ubiquitous power Internet of things and comprises the following steps: building a sensor meter that records the sensors LiName of (2), detected device information, and detected value; establishing a sensor cooperation table recording each sensor LiOf the cooperative sensor Li-kThe list of the cooperative sensors Li-kFor equipment failure, and the sensor LiSensors affected by the fault together; when the sensor LiDetection value
Figure RE-GDA0002288411780000021
When the safety interval is exceeded, the sensor L is read according to the sensor cooperation tableiOf the cooperative sensor Li-kDetected value of (2)
Figure RE-GDA0002288411780000022
And judging whether equipment failure occurs or not, if so, sending an alarm, otherwise, periodically and repeatedly checking whether the sensor L exists or notiDetected value of (2)
Figure RE-GDA0002288411780000023
Exceeding its safety interval;establishing a fault studying and judging subsystem, and judging a fault source when equipment fault alarm exists; establishing a fault repairing strategy making subsystem, and making a fault repairing strategy after determining a fault source, wherein the fault repairing strategy comprises emergency maintenance vehicle scheduling, determining emergency maintenance personnel, determining spare parts and determining a construction tool. Through sensor cooperation, accuracy of equipment fault detection is improved, a fault source is determined through a fault research and judgment subsystem, an optimal repair strategy is formulated through a fault repair strategy formulation subsystem, and fault repair efficiency is improved.
Preferably, the method for determining whether the equipment failure occurs is as follows: if the sensor LiDetection value
Figure RE-GDA0002288411780000024
And a cooperative sensor Li-kDetected value of (2)
Figure RE-GDA0002288411780000025
And if the safety interval is exceeded, judging that the equipment has a fault.
Preferably, the method further comprises the following steps: establishing an equipment failure portrait, wherein the establishment of the equipment failure portrait comprises the following steps: enumerating the sensors L that detect the devicei(ii) a Acquisition sensor LiDetected value of (2)
Figure RE-GDA0002288411780000026
Historical values of (a) and historical fault data of the device; computing sensor LiDetected value of (2)
Figure RE-GDA0002288411780000027
Correlation with equipment failure, selecting detection value
Figure RE-GDA0002288411780000028
Sensor L with higher than set threshold value relative to faulti(ii) a Will be selected out of the sensors LiDetected value of (2)
Figure RE-GDA0002288411780000029
Normalizing and associating the gray value, and associating the gray value with the sensor LiDetected value of (2)
Figure RE-GDA00022884117800000210
The images are arranged in sequence to form an image of the failure of the equipment. And a data collection mechanism is established, so that empirical data can be accumulated, reference is provided for subsequent fault repair, and the fault maintenance level is improved.
Preferably, the fault judging subsystem performs the following steps: reading historical fault data of the equipment, manually analyzing a fault source, and associating a historical fault image of the equipment with the fault source to serve as sample data; training a neural network model by using sample data, taking a historical failure sketch of equipment as the input of the neural network model, and taking a failure source as the output of the neural network model; reading sensor L of a malfunctioning deviceiDetected value of (2)
Figure RE-GDA00022884117800000211
And establishing a reference image according to the establishing method of the equipment fault image, introducing the reference image into the neural network model, and taking the output result of the neural network model as a fault source. The fault source of the equipment can be identified through the fault studying and judging subsystem, the accident troubleshooting time is saved, and the overhauling efficiency is improved.
Preferably, the fault repair strategy making subsystem performs the following steps: importing road GIS information of a region where a target power grid is located, marking all emergency repair vehicle positions on the road GIS information, and determining positions of emergency repair workers and warehouses; introducing a rush-repair vehicle driver duty table, and removing rush-repair vehicle drivers and corresponding rush-repair vehicles in a fatigue period according to the rush-repair vehicle driver duty table; introducing a rush-repair personnel duty list, removing rush-repair personnel in a fatigue period, and determining the number of the rush-repair personnel according to the fault; selecting a breakdown van and emergency repair workers by using an optimization algorithm, and formulating a driving route of the breakdown van to ensure that the breakdown van is connected with all the emergency repair workers, and gets spare parts and construction tools and reaches a fault site with the shortest time, wherein the boarding time of the emergency repair workers and the loading time of the spare parts are not considered; and using the selected breakdown van, the breakdown maintenance personnel and the breakdown van driving route as a failure recovery strategy. And the maintenance efficiency is improved by formulating the maintenance strategy with the highest efficiency.
Preferably, the fault repair strategy making subsystem further executes the following steps: wearing a heartbeat monitoring device for each emergency repair vehicle driver, and monitoring heartbeat data of each emergency repair vehicle driver; determining the rest state of a breakdown van driver according to the heartbeat data, determining whether the breakdown van driver is in a fatigue state or not according to the rest state, and if so, rejecting the breakdown van driver. Avoid breakdown van driver fatigue driving, lead to appearing the traffic accident or other condition that influence equipment maintenance.
Preferably, the fault judging subsystem further performs the steps of: establishing an equipment fault early warning portrait, wherein the establishment of the equipment fault early warning portrait comprises the following steps: enumerating the sensors L that detect the devicei(ii) a Acquisition sensor LiDetected value of (2)
Figure RE-GDA0002288411780000031
Historical values of (a) and historical fault data of the device; computing sensor LiDetected value of (2)
Figure RE-GDA0002288411780000032
Correlation with equipment failure, selecting detection value
Figure RE-GDA0002288411780000033
Several sensors L with a fault correlation higher than a set thresholdi(ii) a Will be selected out of the sensors LiTotal detection value at time T1 before equipment failure
Figure RE-GDA0002288411780000034
Respectively normalizing and associating the gray values, and associating the sensors L with the gray valuesiDetected value of (2)
Figure RE-GDA0002288411780000035
Sequentially arranged, and the formed images are used as the early warning images of the equipment faults and read out the selected sensor LiNormalizing and associating the gray values, and arranging in the same order as the failure warning portrait if the formed image isAnd sending out a fault early warning if the image is similar to the equipment fault early warning image. The early warning of equipment faults is provided, the fault times of the power grid equipment are reduced, and the fault shadow loss is reduced.
Preferably, the method for judging the similarity between the formed image and the equipment failure warning portrait comprises the following steps: obtaining a plurality of failure early warning pictures and the selected sensors L obtained in normal stateiDetected value of (2)
Figure RE-GDA0002288411780000041
The constructed image is used as a sample image; establishing an image recognition neural network, and training by using a sample image until the probability that the neural network correctly distinguishes the fault early warning portrait is higher than a set threshold value; inputting the latest image into the neural network, if the neural network judges the image as a failure early-warning portrait, then judging the image is similar to the failure early-warning portrait, otherwise, judging the image is not similar to the failure early-warning portrait. The neural network can realize better balance of quick judgment and accurate judgment.
Preferably, the method for judging the similarity between the formed image and the equipment failure warning portrait comprises the following steps: obtaining a plurality of failure early warning pictures and the selected sensors L obtained in normal stateiDetected value of (2)
Figure RE-GDA0002288411780000042
The constructed image is used as a sample image; establishing an image recognition neural network, and training by using a sample image until the probability that the image recognition neural network correctly distinguishes the fault early warning portrait is higher than a set threshold value; inputting the latest image into the image recognition neural network, if the image is judged to be a fault early warning portrait by the image recognition neural network, judging that the formed image is similar to the equipment fault early warning portrait, otherwise, judging that the formed image is not similar to the equipment fault early warning portrait. The image recognition neural network can realize better balance of quick judgment and accurate judgment.
Preferably, the sensors include a primary equipment operation temperature monitoring sensor, a lightning arrester leakage current monitoring sensor, a video monitoring image sensor, a perimeter intrusion prevention sensor, a tower theft prevention monitoring sensor, an SF6 gas density monitoring sensor, a fire smoke detection sensor and a rain sensor.
Preferably, the cooperative sensor Li-kAlso comprises a maneuvering sensor, the maneuvering sensor and the sensor LiThe mobile sensor is arranged on the mobile device and is provided with a plurality of detection stations for detecting a plurality of devices. The moving device is a robot, a rail trolley or a rotary holder.
The substantial effects of the invention are as follows: the accuracy of equipment fault detection is improved through sensor cooperation, a fault source is determined through a fault research and judgment subsystem, an optimal repair strategy is formulated through a fault repair strategy formulation subsystem, and the fault repair efficiency is improved; and a data collection mechanism is established, so that empirical data can be accumulated, reference is provided for subsequent fault repair, and the fault maintenance level is improved.
Drawings
FIG. 1 is a block diagram illustrating steps performed by a system according to an embodiment.
FIG. 2 is a block diagram illustrating a process of creating an equipment failure picture according to an embodiment.
FIG. 3 is a block diagram illustrating steps executed by the fault diagnosis subsystem according to an embodiment.
Fig. 4 is a flow chart illustrating steps performed by the failover policy making subsystem according to an embodiment.
FIG. 5 is a block diagram illustrating a process of creating an image of an equipment failure warning image according to an embodiment.
Detailed Description
The following provides a more detailed description of the present invention, with reference to the accompanying drawings.
The first embodiment is as follows:
a method for rapidly repairing faults of a transformer substation based on the Internet of things is used for fault maintenance of the transformer substation with a ubiquitous power Internet of things, and comprises the following steps as shown in figure 1: establishing a sensor meter which records the sensor LiName of, detectedDevice information and detection values; establishing a sensor cooperation table, wherein the sensor cooperation table records each sensor LiOf the cooperative sensor Li-kList of (2), collaboration sensor Li-kFor equipment failure, and the sensor LiTogether affected by the fault. Cooperative sensor Li-kAlso comprises a maneuvering sensor, the maneuvering sensor and the sensor LiThe mobile sensor is arranged on the mobile device and is provided with a plurality of detection stations for detecting a plurality of devices. The moving device is a robot, a rail trolley or a rotary holder. The sensors comprise a primary equipment operation temperature monitoring sensor, a lightning arrester leakage current monitoring sensor, a video monitoring image sensor, a perimeter anti-intrusion sensor, a tower anti-theft monitoring sensor, an SF6 gas density monitoring sensor, a fire smoke detection sensor and a rain sensor.
When the sensor LiDetection value
Figure RE-GDA0002288411780000051
When the safety interval is exceeded, the sensor L is read according to the sensor cooperation tableiOf the cooperative sensor Li-kDetected value of (2)
Figure RE-GDA0002288411780000052
If the sensor LiDetection value
Figure RE-GDA0002288411780000053
And a cooperative sensor Li-kDetected value of (2)
Figure RE-GDA0002288411780000054
If the current time exceeds the safety interval, the equipment is judged to be out of order, if the equipment is out of order, an alarm is sent out, otherwise, the existence of the sensor L is periodically and repeatedly checkediDetected value of (2)
Figure RE-GDA0002288411780000055
Beyond its safe range.
Creating a failure picture of the plant, as shown in FIG. 2The method comprises the following steps: enumerating the sensors L that detect the devicei(ii) a Acquisition sensor LiDetected value of (2)
Figure RE-GDA0002288411780000056
Historical values of (a) and historical fault data of the device; computing sensor LiDetected value of (2)
Figure RE-GDA0002288411780000057
Correlation with equipment failure, selecting detection value
Figure RE-GDA0002288411780000058
Sensor L with higher than set threshold value relative to faulti(ii) a Will be selected out of the sensors LiDetected value of (2)
Figure RE-GDA0002288411780000059
Normalizing and associating the gray value, and associating the gray value with the sensor LiDetected value of (2)
Figure RE-GDA00022884117800000510
The images are arranged in sequence to form an image of the failure of the equipment. And a data collection mechanism is established, so that empirical data can be accumulated, reference is provided for subsequent fault repair, and the fault maintenance level is improved.
Establishing a fault studying and judging subsystem, and judging a fault source when equipment fault alarm exists; establishing a fault repairing strategy making subsystem, and making a fault repairing strategy after determining a fault source, wherein the fault repairing strategy comprises emergency repair vehicle scheduling, determining emergency repairmen, determining spare parts and determining a construction tool.
As shown in fig. 3, the fault judging subsystem performs the following steps: reading historical fault data of the equipment, manually analyzing a fault source, and associating a historical fault image of the equipment with the fault source to serve as sample data; training a neural network model by using sample data, taking a historical failure sketch of equipment as the input of the neural network model, and taking a failure source as the output of the neural network model; reading sensor L of a malfunctioning deviceiDetected value of (2)
Figure RE-GDA0002288411780000061
And establishing a reference image according to the establishing method of the equipment fault image, introducing the reference image into the neural network model, and taking the output result of the neural network model as a fault source. The fault source of the equipment can be identified through the fault studying and judging subsystem, the accident troubleshooting time is saved, and the overhauling efficiency is improved.
As shown in fig. 4, the fault repair policy making subsystem performs the following steps: importing road GIS information of a region where a target power grid is located, marking all emergency repair vehicle positions on the road GIS information, and determining positions of emergency repair workers and warehouses; introducing a breakdown van driver duty table, removing breakdown van drivers in fatigue periods and corresponding breakdown vans according to the breakdown van driver duty table, wearing a heartbeat monitoring device for each breakdown van driver, and monitoring heartbeat data of each breakdown van driver; determining the rest state of a breakdown van driver according to the heartbeat data, determining whether the breakdown van driver is in a fatigue state or not according to the rest state, and if so, rejecting the breakdown van driver; introducing a rush-repair personnel duty list, removing rush-repair personnel in a fatigue period, and determining the number of the rush-repair personnel according to the fault; selecting a breakdown van and emergency repair workers by using an optimization algorithm, and formulating a driving route of the breakdown van to ensure that the breakdown van is connected with all the emergency repair workers, and gets spare parts and construction tools and reaches a fault site with the shortest time, wherein the boarding time of the emergency repair workers and the loading time of the spare parts are not considered; and using the selected breakdown van, the breakdown maintenance personnel and the breakdown van driving route as a failure recovery strategy.
An equipment failure early warning portrait is established, as shown in fig. 5, the establishment of the equipment failure early warning portrait includes the following steps: enumerating the sensors L that detect the devicei(ii) a Acquisition sensor LiDetected value of (2)
Figure RE-GDA0002288411780000062
Historical values of (a) and historical fault data of the device; computing sensor LiDetected value of (2)
Figure RE-GDA0002288411780000063
Correlation with equipment failure, selecting detection value
Figure RE-GDA0002288411780000064
Several sensors L with a fault correlation higher than a set thresholdi(ii) a Will be selected out of the sensors LiTotal detection value at time T1 before equipment failure
Figure RE-GDA0002288411780000065
Respectively normalizing and associating the gray values, and associating the sensors L with the gray valuesiDetected value of (2)
Figure RE-GDA0002288411780000066
Sequentially arranged, and the formed images are used as the early warning images of the equipment faults and read out the selected sensor LiNormalizing and associating the gray values of the real-time detection values, arranging the real-time detection values in the same sequence as the equipment fault early warning portrait, and sending out fault early warning if the formed image is similar to the equipment fault early warning portrait. The early warning of equipment faults is provided, the fault times of the power grid equipment are reduced, and the fault shadow loss is reduced.
The method for judging the similarity between the formed image and the equipment fault early warning portrait comprises the following steps: obtaining a plurality of failure warning pictures and the selected sensors L obtained in normal stateiDetected value of (2)
Figure RE-GDA0002288411780000071
The constructed image is used as a sample image; establishing an image recognition neural network, and training by using a sample image until the probability that the neural network correctly distinguishes the fault early warning portrait is higher than a set threshold value; inputting the latest constructed image into the neural network, if the neural network judges that the image is a failure early warning portrait, judging that the constructed image is similar to the equipment failure early warning portrait, otherwise, judging that the constructed image is not similar to the equipment failure early warning portrait. The neural network can realize better balance of quick judgment and accurate judgment.
The above-described embodiments are only preferred embodiments of the present invention, and are not intended to limit the present invention in any way, and other variations and modifications may be made without departing from the spirit of the invention as set forth in the claims.

Claims (10)

1. A method for rapidly repairing the fault of a transformer substation based on the Internet of things is used for the fault maintenance of the transformer substation with the ubiquitous power Internet of things and is characterized in that,
the method comprises the following steps:
building a sensor meter that records the sensors LiName of (2), detected device information, and detected value;
establishing a sensor cooperation table recording each sensor LiOf the cooperative sensor Li-kThe list of the cooperative sensors Li-kFor equipment failure and sensor LiSensors affected by the fault together;
when the sensor LiDetection value
Figure FDA0002154196780000011
When the safety interval is exceeded, the sensor L is read according to the sensor cooperation tableiOf the cooperative sensor Li-kDetected value of (2)
Figure FDA0002154196780000012
And judging whether equipment failure occurs or not, if so, sending an alarm, otherwise, periodically and repeatedly checking whether the sensor L exists or notiDetected value of (2)
Figure FDA0002154196780000013
Exceeding its safety interval;
establishing a fault studying and judging subsystem, and judging a fault source when equipment fault alarm exists;
establishing a fault repairing strategy making subsystem, and making a fault repairing strategy after determining a fault source, wherein the fault repairing strategy comprises emergency maintenance vehicle scheduling, determining emergency maintenance personnel, determining spare parts and determining a construction tool.
2. The method for rapidly repairing the fault of the transformer substation based on the Internet of things as claimed in claim 1,
the method for judging whether the equipment fault occurs comprises the following steps:
if the sensor LiDetection value
Figure FDA0002154196780000014
And a cooperative sensor Li-kDetected value of (2)
Figure FDA0002154196780000015
And if the safety interval is exceeded, judging that the equipment has a fault.
3. The method for rapidly repairing the fault of the transformer substation based on the internet of things as claimed in claim 1 or 2, further comprising:
establishing an equipment failure portrait, wherein the establishment of the equipment failure portrait comprises the following steps:
enumerating the sensors L that detect the devicei；
Acquisition sensor LiDetected value of (2)
Figure FDA0002154196780000016
Historical values of (a) and historical fault data of the device;
computing sensor LiDetected value of (2)
Figure FDA0002154196780000017
Correlation with equipment failure, selecting detection value
Figure FDA0002154196780000018
Sensor L with higher than set threshold value relative to faulti；
Will be selected out of the sensors LiDetected value of (2)
Figure FDA0002154196780000021
NormalizationAnd associating the gray value with the sensor LiDetected value of (2)
Figure FDA0002154196780000022
The images are arranged in sequence to form an image of the failure of the equipment.
4. The method for rapidly repairing the fault of the transformer substation based on the Internet of things as claimed in claim 3,
the fault studying and judging subsystem executes the following steps:
reading historical fault data of the equipment, manually analyzing a fault source, and associating a historical fault image of the equipment with the fault source to serve as sample data;
training a neural network model by using sample data, taking a historical failure sketch of equipment as the input of the neural network model, and taking a failure source as the output of the neural network model;
reading sensor L of a malfunctioning deviceiDetected value of (2)
Figure FDA0002154196780000023
And establishing a reference image according to the establishing method of the equipment fault image, introducing the reference image into the neural network model, and taking the output result of the neural network model as a fault source.
5. The method for rapidly repairing the fault of the transformer substation based on the Internet of things of claim 1 or 2, wherein the fault repairing strategy making subsystem executes the following steps:
importing road GIS information of a region where a target power grid is located, marking all emergency repair vehicle positions on the road GIS information, and determining positions of emergency repair workers and warehouses;
introducing a rush-repair vehicle driver duty table, and removing rush-repair vehicle drivers and corresponding rush-repair vehicles in a fatigue period according to the rush-repair vehicle driver duty table;
introducing a rush-repair personnel duty list, removing rush-repair personnel in a fatigue period, and determining the number of the rush-repair personnel according to the fault;
selecting a breakdown van and emergency repair workers by using an optimization algorithm, and formulating a driving route of the breakdown van so that the breakdown van can be connected with all the emergency repair workers, and can obtain spare parts and construction tools and reach a fault site with the shortest time;
and using the selected breakdown van, the breakdown maintenance personnel and the breakdown van driving route as a failure recovery strategy.
6. The method for rapidly repairing the fault of the transformer substation based on the Internet of things of claim 1 or 2, wherein the fault repairing strategy making subsystem further executes the following steps:
wearing a heartbeat monitoring device for each emergency repair vehicle driver, and monitoring heartbeat data of each emergency repair vehicle driver;
determining the rest state of a breakdown van driver according to the heartbeat data, determining whether the breakdown van driver is in a fatigue state or not according to the rest state, and if so, rejecting the breakdown van driver.
7. The method for rapidly repairing the fault of the transformer substation based on the internet of things as claimed in claim 1 or 2, wherein the fault studying and judging subsystem further performs the following steps:
establishing an equipment fault early warning portrait, wherein the establishment of the equipment fault early warning portrait comprises the following steps:
enumerating the sensors L that detect the devicei；
Acquisition sensor LiDetected value of (2)
Figure FDA0002154196780000031
Historical values of (a) and historical fault data of the device;
computing sensor LiDetected value of (2)
Figure FDA0002154196780000032
Correlation with equipment failure, selecting detection value
Figure FDA0002154196780000033
And phase of failureSeveral sensors L with a relevance higher than a set thresholdi；
Will be selected out of the sensors LiTotal detection value at time T1 before equipment failure
Figure FDA0002154196780000034
Respectively normalizing and associating the gray values, and associating the sensors L with the gray valuesiDetected value of (2)
Figure FDA0002154196780000035
Sequentially arranged to form an image as an equipment failure warning image,
reading the selected sensor LiNormalizing and associating the gray values of the real-time detection values, arranging the real-time detection values in the same sequence as the equipment fault early warning portrait, and sending out fault early warning if the formed image is similar to the equipment fault early warning portrait.
8. The method for rapidly repairing the fault of the transformer substation based on the Internet of things as claimed in claim 7,
the method for judging the similarity between the formed image and the equipment fault early warning portrait comprises the following steps:
obtaining a plurality of failure early warning pictures and the selected sensors L obtained in normal stateiDetected value of (2)
Figure FDA0002154196780000036
The constructed image is used as a sample image;
establishing an image recognition neural network, and training by using a sample image until the probability that the image recognition neural network correctly distinguishes the fault early warning portrait is higher than a set threshold value;
inputting the latest image into the image recognition neural network, if the image is judged to be a fault early warning portrait by the image recognition neural network, judging that the formed image is similar to the equipment fault early warning portrait, otherwise, judging that the formed image is not similar to the equipment fault early warning portrait.
9. The method for rapidly repairing the fault of the transformer substation based on the Internet of things is characterized in that the sensors comprise a primary equipment operation temperature monitoring sensor, a lightning arrester leakage current monitoring sensor, a video monitoring image sensor, a perimeter anti-intrusion sensor, a tower anti-theft monitoring sensor, an SF6 gas density monitoring sensor, a fire smoke detection sensor and a rain sensor.
10. The method for rapidly repairing substation faults based on the Internet of things as claimed in claim 1 or 2, wherein the cooperative sensor L isi-kAlso comprises a maneuvering sensor, the maneuvering sensor and the sensor LiThe mobile sensor is arranged on the mobile device and is provided with a plurality of detection stations for detecting a plurality of devices.
CN201910712336.3A 2019-08-02 2019-08-02 Transformer substation fault rapid repairing method based on Internet of things Pending CN110942221A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910712336.3A CN110942221A (en) 2019-08-02 2019-08-02 Transformer substation fault rapid repairing method based on Internet of things

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910712336.3A CN110942221A (en) 2019-08-02 2019-08-02 Transformer substation fault rapid repairing method based on Internet of things

Publications (1)

Publication Number Publication Date
CN110942221A true CN110942221A (en) 2020-03-31

Family

ID=69906074

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910712336.3A Pending CN110942221A (en) 2019-08-02 2019-08-02 Transformer substation fault rapid repairing method based on Internet of things

Country Status (1)

Country Link
CN (1) CN110942221A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111966758A (en) * 2020-06-30 2020-11-20 国网浙江省电力有限公司湖州供电公司 Power hidden danger checking method based on portrait data analysis technology
CN112327100A (en) * 2020-10-30 2021-02-05 浙江大学 Power failure detection method and system based on Internet of things
CN112699104A (en) * 2020-12-11 2021-04-23 国网宁夏电力有限公司吴忠供电公司 Data processing method of intelligent sensor of power equipment and intelligent sensor
CN112731827A (en) * 2020-12-11 2021-04-30 国网宁夏电力有限公司吴忠供电公司 Monitoring system for intelligent sensor for power equipment

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102607643A (en) * 2012-01-18 2012-07-25 西安交通大学 Overheat fault diagnosis and early warning system and method for electrical equipment of traction substation of electrified railway
CN202474601U (en) * 2011-11-17 2012-10-03 江苏省电力公司南京供电公司 Power grid fault rush repair system based on GIS
WO2015158198A1 (en) * 2014-04-17 2015-10-22 北京泰乐德信息技术有限公司 Fault recognition method and system based on neural network self-learning
CN105676085A (en) * 2016-01-31 2016-06-15 国家电网公司 Extra-high voltage GIS partial discharge detection method based on multi-sensor information fusion
CN107634988A (en) * 2017-08-25 2018-01-26 深圳市盛路物联通讯技术有限公司 A kind of method and server of the Fault Diagnosis for Substation based on Internet of Things

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN202474601U (en) * 2011-11-17 2012-10-03 江苏省电力公司南京供电公司 Power grid fault rush repair system based on GIS
CN102607643A (en) * 2012-01-18 2012-07-25 西安交通大学 Overheat fault diagnosis and early warning system and method for electrical equipment of traction substation of electrified railway
WO2015158198A1 (en) * 2014-04-17 2015-10-22 北京泰乐德信息技术有限公司 Fault recognition method and system based on neural network self-learning
CN105676085A (en) * 2016-01-31 2016-06-15 国家电网公司 Extra-high voltage GIS partial discharge detection method based on multi-sensor information fusion
CN107634988A (en) * 2017-08-25 2018-01-26 深圳市盛路物联通讯技术有限公司 A kind of method and server of the Fault Diagnosis for Substation based on Internet of Things

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111966758A (en) * 2020-06-30 2020-11-20 国网浙江省电力有限公司湖州供电公司 Power hidden danger checking method based on portrait data analysis technology
CN111966758B (en) * 2020-06-30 2024-02-02 国网浙江省电力有限公司湖州供电公司 Electric power hidden trouble investigation method based on image data analysis technology
CN112327100A (en) * 2020-10-30 2021-02-05 浙江大学 Power failure detection method and system based on Internet of things
CN112327100B (en) * 2020-10-30 2021-09-03 浙江大学 Power failure detection method and system based on Internet of things
CN112699104A (en) * 2020-12-11 2021-04-23 国网宁夏电力有限公司吴忠供电公司 Data processing method of intelligent sensor of power equipment and intelligent sensor
CN112731827A (en) * 2020-12-11 2021-04-30 国网宁夏电力有限公司吴忠供电公司 Monitoring system for intelligent sensor for power equipment
CN112699104B (en) * 2020-12-11 2023-04-07 国网宁夏电力有限公司吴忠供电公司 Data processing method of intelligent sensor of power equipment and intelligent sensor

Similar Documents

Publication Publication Date Title
CN110059631B (en) Contact net non-contact type monitoring defect identification method
CN110942221A (en) Transformer substation fault rapid repairing method based on Internet of things
CN106712713B (en) The monitoring system and monitoring and abnormal localization method of a kind of photovoltaic plant
CN102139700B (en) Vehicle working condition online monitoring system for rail transit
CN108398934B (en) equipment fault monitoring system for rail transit
CN110135273A (en) Contact net video image cloud intellectual monitoring and fault recognition method
CN102354179B (en) Remote monitoring and fault diagnosis system for lithium ion battery packs
CN103236181B (en) Traffic signal lamp state monitoring system and method based on machine vision
CN103632211A (en) Motor vehicle fault pre-warning and callback prediction system
CN111754483A (en) Method and system for identifying abnormal equipment based on thermal imager
CN102139701B (en) Train working condition on-line monitoring method for rail transit
CN112697798B (en) Infrared image-oriented diagnosis method and device for current-induced thermal defects of power transformation equipment
CN111045374A (en) Intelligent water affair Internet of things online monitoring platform and method
CN111381166A (en) Method and system for monitoring battery state
CN110807460A (en) Transformer substation intelligent patrol system based on image recognition and application method thereof
CN111222375A (en) Vehicle driving track generation method, system and server
CN115909092A (en) Light-weight power transmission channel hidden danger distance measuring method and hidden danger early warning device
CN110690699A (en) Transformer substation intelligent detection system based on ubiquitous power Internet of things
CN112432667A (en) Intelligent on-line monitoring system for conducting wire state of power transmission line
CN112001918A (en) AI algorithm based high-speed rail contact network equipment inspection method and system
CN117804526A (en) Underground pipe gallery environment detection system and method based on inspection robot
CN117236916B (en) Comprehensive safety inspection method for intelligent power plant
CN106408455A (en) Railway electric power supply and distribution facility informatization record data processing system and method
CN106355187A (en) Application of visual information to electrical equipment monitoring
CN117372954A (en) Charging station safety monitoring method, device, system and computer equipment

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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20200331