CN113708491A - Intelligent inspection system for traction substation - Google Patents
Intelligent inspection system for traction substation Download PDFInfo
- Publication number
- CN113708491A CN113708491A CN202110960978.2A CN202110960978A CN113708491A CN 113708491 A CN113708491 A CN 113708491A CN 202110960978 A CN202110960978 A CN 202110960978A CN 113708491 A CN113708491 A CN 113708491A
- Authority
- CN
- China
- Prior art keywords
- robot
- inspection robot
- inspection
- layer
- base station
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000007689 inspection Methods 0.000 title claims abstract description 143
- 238000012544 monitoring process Methods 0.000 claims abstract description 49
- 238000004891 communication Methods 0.000 claims abstract description 41
- 238000012545 processing Methods 0.000 claims abstract description 22
- 230000007547 defect Effects 0.000 claims abstract description 8
- 239000013307 optical fiber Substances 0.000 claims abstract description 8
- 238000000034 method Methods 0.000 claims description 32
- 230000008569 process Effects 0.000 claims description 25
- 238000001514 detection method Methods 0.000 claims description 23
- 238000007726 management method Methods 0.000 claims description 15
- 230000005540 biological transmission Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 230000005674 electromagnetic induction Effects 0.000 claims description 5
- 239000004576 sand Substances 0.000 claims description 5
- 238000003708 edge detection Methods 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 4
- 238000007405 data analysis Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 2
- 230000007246 mechanism Effects 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 17
- 238000010586 diagram Methods 0.000 description 9
- 239000013598 vector Substances 0.000 description 9
- 238000012549 training Methods 0.000 description 8
- 238000009826 distribution Methods 0.000 description 6
- 230000001276 controlling effect Effects 0.000 description 4
- 238000001914 filtration Methods 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 238000009529 body temperature measurement Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000002068 genetic effect Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 239000000654 additive Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000000875 corresponding effect Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 238000003909 pattern recognition Methods 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 238000004873 anchoring Methods 0.000 description 1
- 238000013476 bayesian approach Methods 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 230000003137 locomotive effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
- G07C1/20—Checking timed patrols, e.g. of watchman
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00001—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by the display of information or by user interaction, e.g. supervisory control and data acquisition systems [SCADA] or graphical user interfaces [GUI]
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00006—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment
- H02J13/00016—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment using a wired telecommunication network or a data transmission bus
- H02J13/00017—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment using a wired telecommunication network or a data transmission bus using optical fiber
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00006—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment
- H02J13/00022—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment using wireless data transmission
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00006—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment
- H02J13/00022—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment using wireless data transmission
- H02J13/00026—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment using wireless data transmission involving a local wireless network, e.g. Wi-Fi, ZigBee or Bluetooth
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00006—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment
- H02J13/00028—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment involving the use of Internet protocols
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00032—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for
- H02J13/00034—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for the elements or equipment being or involving an electric power substation
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J50/00—Circuit arrangements or systems for wireless supply or distribution of electric power
- H02J50/10—Circuit arrangements or systems for wireless supply or distribution of electric power using inductive coupling
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J7/00—Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries
- H02J7/0047—Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries with monitoring or indicating devices or circuits
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/66—Remote control of cameras or camera parts, e.g. by remote control devices
- H04N23/661—Transmitting camera control signals through networks, e.g. control via the Internet
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/695—Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/30—Transforming light or analogous information into electric information
- H04N5/33—Transforming infrared radiation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/183—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a single remote source
- H04N7/185—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a single remote source from a mobile camera, e.g. for remote control
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/22—Adaptations for optical transmission
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/024—Guidance services
Abstract
The application provides an intelligent inspection system for a traction substation, which comprises a base station layer, a communication layer and a terminal layer, wherein the base station layer is communicated with the terminal layer through the communication layer; the base station layer is used for receiving, processing and displaying data and is also used for realizing automatic identification and alarm of equipment defects through image processing and mode identification; the terminal layer comprises an inspection robot, a charging room and a fixed video monitoring module, the inspection robot is connected with the monitoring background through wireless communication, and the fixed video monitoring module is connected with the monitoring background through optical fiber communication; a charging mechanism is arranged in the charging chamber and used for charging the inspection robot; the fixed video monitoring module comprises a camera and a network video server, the camera is arranged on the holder and used for shooting a fixed monitoring point, the camera is connected with the network video server through optical fiber communication, and the network video server is communicated with the base station layer through a communication layer. This application can replace fortune dimension personnel to carry out the work of patrolling and examining routinely.
Description
Technical Field
The application belongs to the technical field of substations, and particularly relates to an intelligent inspection system for a traction substation.
Background
In the power supply system of the electrified railway, a traction substation takes charge of converting three-phase alternating-current high-voltage electric energy transmitted by a primary power supply system into electric energy with lower voltage suitable for the use requirement of an electric locomotive, and is the most important part in the whole system. Whether the traction substation runs safely or not is directly related to whether the railway electrification system can work continuously and stably.
In order to ensure the safe operation of the traction substations, the guard personnel is arranged in each traction substation to perform related work such as inspection, monitoring, emergency fault treatment, safety protection and the like on power supply equipment and facilities in the substation. The on-duty personnel adopt shift to make a turn to insist. The patrol operation and maintenance mode consumes a large amount of human resources, which not only increases the operation cost, but also has potential safety hazards; because of manual detection, inaccurate detection results caused by human factors often cause potential safety hazards of equipment, and meanwhile, the defects of high labor intensity, dispersed detection quality, multiple subjective factors, low operation and maintenance efficiency and the like exist.
Disclosure of Invention
In order to overcome the problems in the related art at least to a certain extent, the application provides an intelligent inspection system for a traction substation.
According to the embodiment of the application, the application provides an intelligent inspection system for a traction substation, which comprises a base station layer, a communication layer and a terminal layer, wherein the base station layer is communicated with the terminal layer through the communication layer;
the base station layer is used for receiving, processing, displaying and controlling data and is also used for realizing automatic identification and alarm of equipment defects through image processing and mode identification;
the terminal layer comprises an inspection robot, a charging room and a fixed video monitoring module, the inspection robot is connected with the monitoring background through wireless communication, and the fixed video monitoring module is connected with the monitoring background through optical fiber communication; the inspection robot returns to the charging chamber to charge after finishing an inspection task or when the electric quantity is insufficient;
the fixed video monitoring module comprises a camera and a network video server, the camera is arranged on a holder and used for shooting a fixed monitoring point, the camera is connected with the network video server through optical fiber communication, and the network video server is communicated with a base station layer through a communication layer.
In the intelligent inspection system for the traction substation, the base station layer comprises a monitoring background; the monitoring background comprises a database module, a model configuration module, an equipment interface module, a data processing module and a view display module;
the database module comprises a model library, a history library and a real-time library; the model configuration module comprises patrol model configuration and manual control;
the equipment interface module comprises a robot communication interface, a thermal infrared imager interface, a video server interface, a cradle head control interface, a motion control interface, a power management interface and a remote control interface;
the data processing module comprises real-time data processing, event alarm service, log service, patrol data analysis, equipment mode identification, map management and IEC61850 interface service;
the view display module is used for displaying video views, electronic maps, items, logs, trend graphs and user reports.
Further, the communication layer comprises a network switch, a wireless bridge base station and a wireless bridge mobile station; the wireless network bridge base station is arranged at the monitoring background, and the wireless network bridge mobile station is arranged on the inspection robot in the terminal layer; and the communication layer adopts a wifi802.11n wireless network transmission protocol to provide a transmission channel for network communication between the base station layer and the terminal layer.
In the intelligent inspection system of the traction substation, the inspection robot comprises an embedded main control system, and a power supply system, a navigation positioning system, a safety protection system, a motion control system, a left wheel driving system, a right wheel driving system and a holder system which are connected with the embedded main control system;
the navigation positioning system is used for navigating and positioning the inspection robot, the safety protection system is used for enabling the inspection robot to avoid collision, the motion control system is connected with the left wheel driving system and the right wheel driving system and used for controlling the left wheel and the right wheel to move, the holder system is internally provided with a visible light camera and an infrared thermal imager, and the visible light camera and the infrared thermal imager are used for shooting all parts in the traction substation.
Furthermore, the power supply system comprises a vehicle-mounted storage battery and a power management system, the power management system is used for monitoring the electric quantity of the vehicle-mounted storage battery and sending the monitored information to the embedded main control system, the embedded main control system generates a motion control instruction according to the received information and sends the motion control instruction to the motion control system, and the motion control system controls the left wheel driving system and the right wheel driving system to act so that the inspection robot moves to the charging chamber for charging;
the charging chamber adopts an electromagnetic induction type charging mode to charge the vehicle-mounted storage battery.
Further, the navigation positioning system comprises a speedometer, a robot motion controller, a robot controller and a laser sensor; the odometer is used for measuring the mileage of the routing inspection robot and feeding back the mileage to the robot motion controller, the robot motion controller feeds back the mileage to the robot manual control machine, and the laser sensor is used for detecting the distance between the routing inspection robot and the transformer substation and feeding back the distance measurement data to the robot manual control machine;
and the robot manual control machine carries out mapping positioning and navigation control according to the received mileage and ranging data and sends a control instruction to the robot motion controller and the laser sensor.
Furthermore, the positioning process of the navigation positioning system is as follows:
firstly, a navigation positioning system utilizes a laser sensor and a mileometer carried by an inspection robot to establish a two-dimensional map of a large-scale and sparse-feature environment of a substation;
secondly, matching detection information of the laser sensor with the established two-dimensional map to obtain positioning information of the inspection robot, wherein the positioning information comprises a position and a course;
and finally, the navigation positioning system adopts the positioning information to guide the inspection robot, so that the inspection robot reaches the specified position in the substation.
Furthermore, the process of matching the detection information of the laser sensor with the established two-dimensional map and obtaining the positioning information of the inspection robot comprises the following steps:
installing n (n is more than or equal to 3) signposts at fixed positions in a required positioning environment, establishing a global coordinate system XOY, and knowing the position of each signpost under the XOY coordinate system;
rotation center O of rotary laser sensorSEstablishing a sensor coordinate system XSOSYSThe detected road sign corresponding to X can be obtained by the laser sensor every time the laser sensor scans one circleSAngle of axis lambdai，i＝1，2，…，n；
After at least 3 road signs in the environment are detected, the rotation center O of the laser sensor is obtained through iterative calculationSCoordinates (X, y) in the global coordinate system XOY and X in the sensor coordinate systemSThe axis is at an angle theta to the X-axis in the global coordinate system.
Furthermore, the navigation positioning system adopts the positioning information to navigate the inspection robot, so that the specific process of the inspection robot reaching the specified position in the substation is as follows:
assuming a path starting point P under a global coordinate system XOY1(x1，y1) And end point P2(x2，y2) And obtaining the position deviation delta S and the course deviation delta theta of the robot and the driving path according to the following formula:
in the formula, the value range of theta angle data participating in delta theta calculation is [0, 360 ], and the positive and negative values of delta S and delta theta reflect whether the inspection robot is inclined to the right or the left relative to the running path;
assuming that the running speed of the inspection robot is V, multiplying the position deviation delta S and the course deviation delta theta respectively by a coefficient K according to the calculated position deviation delta S and the calculated course deviation delta thetaSAnd KθWherein the coefficient KSAnd KθAnd all the values are non-negative values, and the increment delta V of the speed control quantity of the left and right two wheels of the inspection robot is obtained as follows:
ΔV＝KSΔS+KθΔθ，
obtaining the running speed V of the left wheel of the inspection robot according to the speed control quantity increment delta VLAnd the running speed V of the right wheelRRespectively as follows:
in the formula, KPAs a function of the number of the coefficients,
in the formula, d represents the distance between the current position and the parking position of the robot, and r represents the set parking control range; when the inspection robot enters a set parking control range r, the inspection robot starts to decelerate, and when the parking error of the inspection robot is smaller than an allowable value epsilon, the inspection robot stops moving; y isPIndicates a stop point Pk(xP，yP) The ordinate of (c).
The cloud deck system comprises a cloud deck control system, a video server, a cloud deck, a visible light camera and an infrared thermal imager, wherein the visible light camera and the infrared thermal imager are arranged on the cloud deck, the cloud deck control system is used for controlling the cloud deck to drive the visible light camera and the infrared thermal imager to rotate, the visible light camera and the infrared thermal imager are connected with the video server, and the video server is communicated with a monitoring background of the base station layer through a communication layer so as to send images of the power substation shot by the visible light camera and the infrared thermal imager to the monitoring background;
and the data processing module in the monitoring background processes the received image in real time by adopting a dial plate positioning, edge detection, circle and ellipse fitting, pointer detection angulation and a character recognition algorithm.
According to the above embodiments of the present application, at least the following advantages are obtained: according to the intelligent inspection system for the traction substation, the inspection robot is arranged to replace operation and maintenance personnel to perform daily inspection work, so that the inspection frequency can be improved, and faults can be found in time; the data is fully electronic, statistics and collection are convenient, various charts can be generated, and viewing is convenient; faults can be prevented through background data prediction; the inspection robot can automatically and wirelessly charge, and completely realizes unattended operation and automatic operation without manual intervention.
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 scope of the invention, as claimed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of the specification of the application, illustrate embodiments of the application and together with the description, serve to explain the principles of the application.
Fig. 1 is a schematic structural diagram of an intelligent inspection system of a traction substation provided by an embodiment of the present application.
Fig. 2 is a schematic diagram of a navigation positioning system in the intelligent inspection system of the traction substation provided in the embodiment of the present application.
Fig. 3 is a schematic diagram of laser navigation performed by an inspection robot in the intelligent inspection system of the traction substation provided by the embodiment of the application.
Fig. 4 is a schematic diagram of navigation control of an inspection robot in the intelligent inspection system of the traction substation provided by the embodiment of the application.
Fig. 5 is a schematic diagram of position and course deviation in a navigation process of an inspection robot in the intelligent inspection system of the traction substation according to the embodiment of the present application.
Fig. 6 is a schematic path diagram of an inspection robot observing a road sign in an environment in the intelligent inspection system of a traction substation provided by the embodiment of the application.
Fig. 7 is a map created by an inspection robot using laser in the intelligent inspection system of the traction substation according to the embodiment of the present application.
Fig. 8 is a schematic diagram of a travel path of an inspection robot planned by using a genetic algorithm in the intelligent inspection system of the traction substation provided by the embodiment of the application.
Fig. 9 is an edge image obtained by extracting edge information of a gray image by using a classical Sobel detection operator in the intelligent patrol inspection system for a traction substation provided in the embodiment of the present application.
Description of reference numerals:
1. a base station layer; 2. a communication layer; 3. and a terminal layer.
Detailed Description
For the purpose of promoting a clear understanding of the objects, aspects and advantages of the embodiments of the present application, reference will now be made to the accompanying drawings and detailed description, wherein like reference numerals refer to like elements throughout.
The illustrative embodiments and descriptions of the present application are provided to explain the present application and not to limit the present application. Additionally, the same or similar numbered elements/components used in the drawings and the embodiments are used to represent the same or similar parts.
As used herein, "first," "second," …, etc., are not specifically intended to mean in a sequential or chronological order, nor are they intended to limit the application, but merely to distinguish between elements or operations described in the same technical language.
With respect to directional terminology used herein, for example: up, down, left, right, front or rear, etc., are simply directions with reference to the drawings. Accordingly, the directional terminology used is intended to be illustrative and is not intended to be limiting of the present teachings.
As used herein, the terms "comprising," "including," "having," "containing," and the like are open-ended terms that mean including, but not limited to.
As used herein, "and/or" includes any and all combinations of the described items.
References to "plurality" herein include "two" and "more than two"; reference to "multiple sets" herein includes "two sets" and "more than two sets".
Certain words used to describe the present application are discussed below or elsewhere in this specification to provide additional guidance to those skilled in the art in describing the present application.
Fig. 1 is a schematic structural diagram of an intelligent inspection system of a traction substation provided by an embodiment of the present application.
As shown in fig. 1, the intelligent patrol system for a traction substation provided by the embodiment of the present application includes a base station layer 1, a communication layer 2, and a terminal layer 3.
The base station layer 1 is a data receiving, processing, controlling and displaying center of the whole intelligent inspection system of the traction substation, and comprises a monitoring background.
The monitoring background comprises a database module, a model configuration module, an equipment interface module, a data processing module and a view display module.
The database module comprises a model base, a history base and a real-time base. The model configuration module comprises patrol model configuration and manual control.
The equipment interface module comprises a robot communication interface, a thermal infrared imager interface, a video server interface, a cradle head control interface, a motion control interface, a power management interface, a remote control interface and the like.
The data processing module comprises real-time data processing, event alarm service, log service, patrol data analysis, equipment mode identification, map management, IEC61850 interface service and the like.
The view display module comprises a video view, an electronic map, a matter view, a log view, a trend graph, a user report and the like.
The base station layer 1 realizes automatic identification and alarm of equipment defects through technologies such as image processing, pattern recognition and the like.
The communication layer 2 comprises a network switch, a wireless bridge base station and a wireless bridge mobile station, wherein the wireless bridge base station is arranged at the monitoring background, and the wireless bridge mobile station is arranged on the inspection robot in the terminal layer 3. The communication layer 2 adopts a wifi802.11n wireless network transmission protocol to provide a transparent transmission channel for network communication between the base station layer 1 and the terminal layer 3.
The terminal layer 3 comprises an inspection robot, a fixed video monitoring module and a charging room, wireless communication is adopted between the inspection robot and the monitoring background, and optical fiber communication can be adopted between the fixed video monitoring module and the monitoring background. The charging mechanism is arranged in the charging chamber, and the inspection robot automatically returns to the charging chamber to charge after finishing an inspection task or when the electric quantity is insufficient.
The fixed video monitoring module comprises a camera and a network video server, the camera is arranged on the holder and used for shooting a fixed monitoring point, the camera is connected with the network video server through optical fiber communication, and the network video server is communicated with the base station layer through a communication layer.
The intelligent inspection system for the traction substation provided by the embodiment of the application has the following functions:
and (3) detection function: detecting thermal defects of primary equipment by an online thermal infrared imager, wherein the thermal defects comprise infrared temperature measurement of a body and a joint of current heating type equipment and voltage heating type equipment; performing appearance inspection of primary equipment by using an online visible light camera, wherein the appearance inspection comprises damage, foreign matters, corrosion, loosening, oil leakage and the like; the position of the breaker and the knife switch; gauge reading, oil level gauge position; by the audio pattern recognition, abnormal sounds of the primary equipment and the like are analyzed.
And (4) navigation function: driving according to a pre-planned route and dynamically adjusting the posture of the vehicle body; differential steering, pivot turning and small turning radius; ultrasonic automatic obstacle stopping during laser navigation; planning an optimal path and walking in two directions, and calculating an optimal driving route after an observation target is specified.
Analysis and alarm functions: intelligently analyzing equipment faults or defects and automatically alarming; reports of infrared temperature measurement, equipment inspection and the like are automatically generated, the report format can be customized by a user, and the reports can be uploaded to an information integration platform through an IEC61580 interface; and an auxiliary system for providing an equipment fault reason analysis and processing scheme according to the equipment category and an equipment infrared image library to assist inspection personnel in judging the fault of the equipment.
And (4) control functions: equipment inspection personnel can perform inspection at the monitoring background; the vehicle body, the cradle head, the infrared camera and the visible light camera can be manually controlled; local and remote control of equipment inspection of the substation is realized; and the device is combined with a sequence control system to replace manual work to check the positions of the switches and the disconnecting links after operation.
The special patrol function is as follows: when the operating personnel are inconvenient to get close to the equipment due to bad weather or potential safety hazards in the vicinity of the equipment, the inspection robot can replace the operating personnel to arrive at the observation position of the designated equipment, and the operating personnel align the position of the cradle head of the inspection robot to the observed equipment to detect at the background through adjustment.
Fixed video point access function: the equipment inspection robot system can also be connected with a fixed video monitoring module of a substation, so that an observation dead angle which cannot be reached by the inspection robot is covered, and the video monitoring of the whole station is realized.
Interface with external system: the method comprises the steps of interfacing with a comprehensive automation system of a substation to obtain real-time load current of equipment so as to analyze temperature rise of the equipment; the system is used as an IEC61850 server and an integrated automation or intelligent substation information integrated system interface, and is matched with remote control or sequence control to check the position of the controlled equipment. And the infrared temperature measurement and equipment appearance abnormal information is uploaded through a production Management Information System (MIS) interface.
In this embodiment, the inspection robot includes an embedded main control system, and a power supply system, a navigation positioning system, a safety protection system, a motion control system, a left wheel driving system, a right wheel driving system, and a pan-tilt system that are connected to the embedded main control system.
The embedded main control system adopts an SBRIO digital module of NI, and adopts reconfigurable I/O (abbreviated as RIO) and FPGA technology to realize ultrahigh performance and self-defining function. The SBRIO digital module adopts a low-power consumption real-time embedded processor and a group of high-performance RIO FPGA chips, and is particularly suitable for independent embedded or distributed application with strict requirements on reliability.
In this embodiment, the power supply system includes a vehicle-mounted storage battery and a power management system, where the power management system is configured to monitor an electric quantity of the vehicle-mounted storage battery and send monitored information to the embedded master control system, the embedded master control system generates a motion control instruction according to the received information and sends the motion control instruction to the motion control system, and the motion control system controls the left wheel driving system and the right wheel driving system to operate, so that the inspection robot moves to the charging chamber to charge.
The charging chamber adopts the electromagnetic induction type mode of charging to on-vehicle battery charges, and its fundamental principle utilizes the electromagnetic induction principle, is similar to the transformer, sets up the power transmission coil at the charging chamber end, sets up the receiving coil at the robot end of patrolling and examining, and the power transmission coil leads to the alternating current of certain frequency, because electromagnetic induction produces certain electric current in the receiving coil to transfer the energy from the charging chamber end to the robot end of patrolling and examining.
After charging is finished, the power management system enters a standby state; if the inspection robot has an operation task, the embedded main control system controls the vehicle-mounted battery to be disconnected from the charging state through the power management system, and controls the left wheel driving system and the right wheel driving system to act through the motion control system, so that the inspection robot moves to a position to be operated to execute the operation task.
In the embodiment, the navigation positioning system employs a SLAM (Simultaneous Localization and Mapping) navigation technology.
As shown in fig. 2, the navigation positioning system includes an odometer, a robot motion controller, a robot controller, and a laser sensor. The mileometer is used for measuring the mileage of the patrol robot and feeding the mileage to the robot motion controller, the robot motion controller feeds the mileage to the robot manual control machine, and the laser sensor is used for detecting the distance between the patrol robot and the transformer substation and feeding ranging data to the robot manual control machine. And the robot manual control machine carries out mapping positioning and navigation control according to the received mileage and ranging data and sends a control command to the robot motion controller and the laser sensor. The remote monitoring host can also carry out data communication and remote control with the robot control machine in a wireless communication mode.
Specifically, the positioning process of the navigation positioning system is as follows:
firstly, a navigation positioning system utilizes a laser sensor and a mileometer carried by an inspection robot to establish a two-dimensional map of a large-scale and sparse-feature environment of a substation; secondly, matching detection information of the laser sensor with the established two-dimensional map to obtain positioning information of the inspection robot, wherein the positioning information comprises a position and a course; and finally, the navigation positioning system adopts the positioning information to guide the inspection robot to reach the specified position in the substation.
The key for realizing the laser navigation of the inspection robot is to determine the position of the inspection robot under a global coordinate system through a laser sensor. As shown in fig. 3, the principle of laser navigation is:
installing n (n is more than or equal to 3) signposts at fixed positions in a required positioning environment, establishing a global coordinate system XOY, and knowing the position of each signpost under the XOY coordinate system; rotation center O of rotary laser sensorSEstablishing a sensor coordinate system XSOSYSThe detected road sign corresponding to X can be obtained by the laser sensor every time the laser sensor scans one circleSAngle of axis lambdai(i ═ 1, 2, …, n); after at least 3 road signs in the environment are detected, the rotation center O of the sensor can be obtained through iterative calculationSCoordinates (X, y) in the global coordinate system XOY and X in the sensor coordinate systemSThe axis is at an angle theta to the X-axis in the global coordinate system.
As most paths in the routing inspection route in the substation are straight lines, the running path of the robot can be simplified into a straight path, and for long-distance turning in the routing inspection route, a plurality of straight paths can be used for replacing the long-distance turning, so that the robot navigation control can be summarized into the control of the position deviation delta S and the course deviation delta theta of the robot relative to the current running path. During actual navigation, high-precision positioning data output by a laser sensor in real time is utilized, and the speed of the left wheel and the speed of the right wheel of the robot are controlled in a closed-loop mode after being processed by the robot motion controller, so that the robot always runs along a preset routing inspection route.
As shown in fig. 4, the navigation control principle of the inspection robot is as follows:
the laser sensor prestores coordinate values of all road signs in the environment under a global coordinate system, and when the inspection robot navigates, the laser sensor automatically matches the detected road signs with the stored road signs, so as to calculate and obtain the position and course information of the inspection robot.
The position and course deviation in the navigation process of the inspection robot is shown in figure 5, the rotation center of the rotary laser sensor is coincided with the motion center of the inspection robot, and X in the sensor coordinate systemSThe axis is coincident with the longitudinal axis of the robot, so that the coordinates and the direction obtained by laser positioning are the position (x, y) and the course theta of the inspection robot under the global coordinate system.
As shown in fig. 5, knowing the starting point P1(x1, y1) and the ending point P2(x2, y2) of the path under the global coordinate system XOY, the position deviation Δ S and the heading deviation Δ θ between the robot and the driving path can be obtained by the following two equations:
in the formula (1), the value range of theta angle data participating in delta theta calculation is [0, 360 ], and the positive and negative values of delta S and delta theta reflect whether the inspection robot is inclined to the right or left relative to the running path.
Assuming that the operation speed of the inspection robot is V, in order to adjust the operation posture of the inspection robot, the calculated delta S and delta theta are multiplied by the coefficient K respectivelySAnd Kθ(all are non-negative values, and specific numerical values can be determined by field debugging), the speed control quantity increment delta V of the left and right two wheels of the inspection robot can be obtained as follows:
ΔV＝KSΔS+KθΔθ (2)
finally obtaining the running speed V of the left wheel of the inspection robotLAnd the running speed V of the right wheelRRespectively as follows:
in the formula (3), multiplying by the coefficient KPIs to ensure that the robot can set a stopping point Pk(xP，yP) Accurate docking, KPCan be determined as follows:
in the formula (4), d represents the distance between the current position and the parking position of the robot; as shown in fig. 5, r represents the set parking control range. And when the polling robot enters the set parking control range r, the polling robot starts to decelerate, and when the parking error of the polling robot is smaller than the allowable value epsilon, the polling robot stops moving.
Reliable positioning performance is a key element of the autonomous mobile system of the robot. The traditional positioning method is based on odometer estimation and has inevitable positioning error. In the SLAM problem, estimates of both the robot position and the map are highly correlated and cannot be independently obtained by either party, thus forming a complementary, coherent, continuously iterative process.
The SLAM problem is that the robot autonomously creates a map while estimating its own position using the map. In the process, the walking track of the robot and the position of the road sign are obtained through online calculation, and prior knowledge is not required to be provided.
Assuming that an inspection robot moves in an unknown environment and observes landmarks in the environment by using a sensor, as shown in fig. 6, an open triangle and a solid triangle respectively represent a true pose and an estimated pose of the robot, an open circle and a solid circle respectively represent a true position and an estimated position of the landmarks, a solid line and a dotted line respectively represent a true path and an estimated path of the robot, and an arrow represents observation.
xkIndicating the pose of the robotA vector, which includes a position and a direction.
ukRepresenting a control vector which acts on the robot at time k-1 to cause the robot to reach state x at time kk。
miA position vector representing the ith landmark, assuming its actual position is time-varying.
zikAnd the observed value of the robot to the ith road sign at the time k is shown.
X0:k＝{x0,x1,...,xk}＝{x0,k-1,...,xkRepresents historical data of robot poses, called trajectories.
U0：k＝{u0，u1，...，uk}＝{u0，k-1，...，ukRepresents historical data of control inputs.
m＝{m0，m1，...，mnRepresents the set of all signposts, called a map.
Z0：k＝{z0，z1，...，zk}＝{z0，k-1，...，zkRepresents a set of observations of the signpost.
From a probabilistic point of view, the SLAM problem is to solve the probability distribution:
P(xk，m|Z0：k，U0：k，x0) (5)
namely, all observation and control inputs before the given k moment and the initial pose of the robot are given, and the combined posterior probability distribution of the landmark and the pose of the robot at the k moment is solved. SLAM solutions typically employ recursive bayesian estimation. According to Bayes estimation theory, giving k-1 time probability distribution:
P(xk-1，m|Z0：k-1，U0：k-1，x0) (6)
given a priori estimates of the probability distributions at time k-1, a control input u may be usedkAnd observation zkTo update the posterior probability.
The observation model describes the robot pose and landmark position when knownWhile, observe zkThe probability of occurrence. The general form of the observation model is:
P(zk|xk，m) (7)
the motion model describes the transition probabilities between different states of the robot under the control input. The general form of the motion model is:
P(xk|xk-1，uk) (8)
in equation (8), the state transition process is assumed to be a Markov process, i.e., state xkOnly sum state xkAnd a control input ukRelevant and independent of all observations and maps.
The SLAM problem can be computed using a recursive bayesian approach. Bayesian estimation comprises two steps of prediction and updating:
to efficiently compute the a priori and a posteriori probabilities, the SLAM problem is first to solve the approximate representation problem of the observation model and the motion model. The present application employs SLAM based on extended kalman filtering.
Kalman filtering is an algorithm for information fusion in state space. The method is suitable for the condition that the process model and the observation model are linear and the noise is in Gaussian distribution. The Kalman filter contains a prediction period and an update period, producing an optimal estimate in the sense of minimum mean square error.
Given a system, the state variable at time k is xkThe process model is as follows:
Xk+1＝AXk+Bui+qk (10)
in the formula (10), ukRepresenting independent state vectors (usually control inputs), qkRepresenting white gaussian noise, the prediction period of Kalman filtering is:
in the formula (11), Pk、Uk、QkEach represents xk,uk,qkAnd (4) a variance matrix. If at time k + 1, the observation vector is:
zk+1＝HXk+1+rk+1 (12)
in the formula (12), rk+1Representing white Gaussian noise with a variance matrix of Rk+1Then the state estimation can be improved. Using a weighted average of the prediction vector and the observation vector as Xk+1Is estimated. The optimal weighting for the Kalman filter is:
in the formula (13), the vector vk+1Representing the error between the predicted and actual observations, commonly referred to as innovation. Sk+1Representing the variance of the innovation. Optimal weight Wk+1Referred to as Kalman gain. The updating process of the state estimation comprises the following steps:
in practice, the system is usually nonlinear, an extended kalman filter is required, and assuming that the process model is a nonlinear equation f and the observation model is a nonlinear equation h:
the basic idea of EKF is to linearize the functions f and h at the state mean. Thus, variance estimation of states in EKFs requires the use of Jacobian matrices at which the mean of the states is estimated.
The prediction period is as follows:
in the formula (17), Jacobian matrix
At point of function f
The partial derivatives of the X are treated,
at point of function f
The partial derivatives of u are:
similarly, by linearizing the observation function h, the Kalman gain can be calculated:
the updating process of the state estimation comprises the following steps:
the core of the EKF-SLAM method is to describe a motion model and an observation model by using a nonlinear equation. The motion model of the robot is as follows:
in the formula (21), the function f represents the robotEquation of kinematics of wkAdditive noise representing zero mean with variance Qk。
The observation model is as follows:
in the formula (22), the function h represents the observed geometric property, vkAdditive observed noise representing zero mean with variance Rk。
Combined posterior distribution P (x)k,m|Z0:k,U0:k,x0) The mean and variance of (a) are:
according to the standard extended Kalman filtering method, the calculation of the mean and variance includes two steps of time update and observation update.
The time is updated as:
f is a function f
Jacobian matrix of (a). For static signposts, they do not need to be time updated.
The observation is updated as:
the map created by the inspection robot using the laser is shown in fig. 7.
Firstly, a map is established by using a global coordinate system established by a laser sensor, and then the optimal path of the inspection robot is found by using a genetic search algorithm. The routing inspection robot travel path planned by the genetic algorithm is shown in fig. 8.
In the above embodiment, as shown in fig. 1, the cloud deck system includes a cloud deck control system, a video server, a cloud deck, and a visible light camera and a thermal infrared imager that are arranged on the cloud deck, where the cloud deck control system is configured to control the cloud deck to drive the visible light camera and the thermal infrared imager to rotate, the visible light camera and the thermal infrared imager are connected to the video server, and the video server communicates with the monitoring background of the base station layer 1 through the communication layer 2 to send the images of the power substation shot by the visible light camera and the thermal infrared imager to the monitoring background. The data processing module in the monitoring background processes the received image in real time by adopting dial plate positioning, edge detection, circle and ellipse fitting, pointer detection angulation, character recognition algorithm and the like, and has the advantages of high precision, high processing speed and the like.
In a specific embodiment, the positioning of the dial can be regarded as detecting the dial, and belongs to the field of target detection. The dial plate detection method and device are characterized in that a variable component model is adopted to achieve dial plate detection, the model represents a target object by describing each part of a target and the position relation among the parts, and when the position of the target changes or the type of the target changes, the model can accurately detect the target.
The deformable part model comprises two layers of filters, a root filter and a plurality of local filters, wherein the root filter is used for covering the whole target, the local filters are used for covering a certain main part of the target, the root filter is used for capturing the whole contour feature of the target, and the local filters are used for capturing a certain local feature of the target with obvious discrimination. For example, a face is modeled with two layers of filters, and the root filter can be trained to the rough lines and contours of the face, such as eyes, nose, mouth, and the like.
The variable component model carries out the process of mark detection, which comprises the following steps:
and S1, training a component model of the mark off line by using the Latent-SVM, wherein the component model comprises a root filter, a component filter and a space model of the component relative to the root position.
And S2, carrying out hog characteristic pyramid decomposition on the image to be detected.
S3, for the feature map of each layer of the pyramid, adopting a sliding window to perform sign detection, wherein the size of the sliding window is the size of the root filter, and the specific process is as follows:
firstly, calculating a hog feature graph and root filter response in a window;
then, calculating the maximum response of the component filter in the window and the characteristic diagram;
finally, the response of the root filter plus the maximum response of the component filter minus the distortion loss of the component, to obtain the score of the window, and comparing with the set threshold can determine whether the window is a mark.
The specific process of the off-line training is as follows:
before off-line training, training samples need to be labeled manually, and the positions of the markers and the positions of all parts in the images are marked.
The finally trained marking part model comprises the following components: one root filter, five component filters, and a spatial model of the component position relative to the root.
The filter is actually some weight vector, and the score of the filter F is obtained by calculating the dot product of the F and the feature map of the hog feature pyramid sub-window.
The off-line detection process of the hog characteristic pyramid comprises the following steps:
let H denote the hog feature pyramid, p ═ x, y, l denote the position of (x, y) in the l-level pyramid, and Φ (H, p, w, H) denote a w × H sub-window with p in the top left corner, then the score of filter F over the detection window can be expressed as F · Φ (H, p, w, H).
The symbol comprising n parts can be used (F)0,P1,...,PnB) represents, F0Representing a root filter, PiB is an offset for the model of the ith part. Each part model can be used (F)i,vi,di) Is represented by the formula FiIs as followsFilters of i components, viThe anchoring position of the component i relative to the root, diIs the loss of deformation of component i relative to the possible locations of the anchor locations.
The position of one model in the hog pyramid is defined by z ═ p0,...,pn) Is represented by the formula, wherein pi＝(xi,yi,li) Where i is 0, the position of the root filter is represented, and when i > 0, the position of the ith filter is represented. The score for position z is obtained by summing the scores for each filter minus the distortion loss for each component filter, plus an offset:
(dxi,dyi)＝(xi,yi)-(2(x0,y0)+vi) (28)
wherein (dx)i,dyi) For the displacement of the ith component relative to the anchor point, phid(dxi,dyi) Is a deformation feature. The score for position z may be represented by β · ψ (H, z), where β ═ F (z)0,...,Fn,d1,...,dn,b)，ψ(H,z)＝(φ(H,p0),...,φ(H,pn),-φd(dx1,dy1),...,-φd(dxn,dyn),1)。
Beta can be obtained through Latent-SVM training, and the Latent-SVM can fully utilize hidden information in the image. The score of sample x may be used
Expressed, β is a parameter of the model and z is a latent variable. Z (x) is the set of possible latent variables for sample x.
By training sample D ═ x1,y1＞,...,＜xn,yn＞)，yiE (-1,1) makes the objective function
In a specific embodiment, edge detection utilizes a classical Sobel detection operator to extract edge information of a gray image, so as to obtain an edge image as shown in fig. 9. The input gray image is processed to output a binary image with the same size, the pixel points containing the edge information are white, and other areas are black. These white pixels are called edge feature points. Subsequent fitting detection is mainly directed to these feature points.
In a specific embodiment, the fitting of the circle and the ellipse adopts a least square method, and an optimal parameter solution in the least square sense can be achieved. And fitting to obtain an ellipse of the instrument panel based on a least square method.
In one embodiment, the process of pointer detection and angulation is:
it is assumed that the pointer or the pointer extension line passes through the center or the vicinity of the center of the dial, and the color of the pointer is darker than the dial face.
Firstly, the dial is binarized, after binarization, the gray value of the pointer is 0, and the gray value of the dial is 255.
Then, in the dial area, for the fitted ellipse, connect the ellipse center point to the edge, rotating from 0 ° to 360 °. And counting the gray sum on the connecting line once every degree, and obtaining the minimum degree of the gray sum to be the pointer angle.
Because the pointer passes through the center of the dial plate, the difference between the pointer and the background of the dial plate is large, and the value of 0 is large, the angle of the pointer can have a lowest gray value, and the angle of the pointer can be calculated.
In a specific embodiment, the identification of the characters on the instrument dial is realized by adopting a convolutional neural network. Convolutional neural networks are one type of deep learning algorithm. The essence of deep learning is to learn more useful features by constructing a machine learning model with many hidden layers and massive training data, thereby finally improving the accuracy of classification or prediction,
the intelligent inspection system of traction substation that this application embodiment provided can replace the operation and maintenance personnel to carry out daily work of patrolling and examining through setting up the robot of patrolling and examining, improves and patrols and examines the frequency, in time discovers the trouble. The data in the intelligent inspection system for the traction substation provided by the embodiment of the application is fully electronic, statistics and collection are convenient, various charts can be generated, and the inspection is convenient; the occurrence of faults can be prevented through background data prediction. The intelligent system of patrolling and examining of traction substation that this application embodiment provided can make the robot of patrolling and examining automatically carry out wireless charging through setting up the room of charging, realizes unmanned on duty completely, and automatic operation need not artificial intervention.
The foregoing is merely an illustrative embodiment of the present application, and any equivalent changes and modifications made by those skilled in the art without departing from the spirit and principles of the present application shall fall within the protection scope of the present application.
Claims (10)
1. The intelligent inspection system for the traction substation is characterized by comprising a base station layer, a communication layer and a terminal layer, wherein the base station layer is communicated with the terminal layer through the communication layer;
the base station layer is used for receiving, processing, displaying and controlling data and is also used for realizing automatic identification and alarm of equipment defects through image processing and mode identification;
the terminal layer comprises an inspection robot, a charging room and a fixed video monitoring module, the inspection robot is connected with the monitoring background through wireless communication, and the fixed video monitoring module is connected with the monitoring background through optical fiber communication; the inspection robot returns to the charging chamber to charge after finishing an inspection task or when the electric quantity is insufficient;
the fixed video monitoring module comprises a camera and a network video server, the camera is arranged on a holder and used for shooting a fixed monitoring point, the camera is connected with the network video server through optical fiber communication, and the network video server is communicated with a base station layer through a communication layer.
2. The intelligent patrol inspection system for the traction substation according to claim 1, wherein the base station layer comprises a monitoring background; the monitoring background comprises a database module, a model configuration module, an equipment interface module, a data processing module and a view display module;
the database module comprises a model library, a history library and a real-time library; the model configuration module comprises patrol model configuration and manual control;
the equipment interface module comprises a robot communication interface, a thermal infrared imager interface, a video server interface, a cradle head control interface, a motion control interface, a power management interface and a remote control interface;
the data processing module comprises real-time data processing, event alarm service, log service, patrol data analysis, equipment mode identification, map management and IEC61850 interface service;
the view display module is used for displaying video views, electronic maps, items, logs, trend graphs and user reports.
3. The intelligent routing inspection system of traction substations according to claim 2, characterized in that the communication layer comprises a network switch, a wireless bridge base station and a wireless bridge mobile station; the wireless network bridge base station is arranged at the monitoring background, and the wireless network bridge mobile station is arranged on the inspection robot in the terminal layer; and the communication layer adopts a wifi802.11n wireless network transmission protocol to provide a transmission channel for network communication between the base station layer and the terminal layer.
4. The intelligent inspection system according to claim 1, wherein the inspection robot comprises an embedded main control system, and a power supply system, a navigation positioning system, a safety protection system, a motion control system, a left wheel driving system, a right wheel driving system and a holder system which are connected with the embedded main control system;
the navigation positioning system is used for navigating and positioning the inspection robot, the safety protection system is used for enabling the inspection robot to avoid collision, the motion control system is connected with the left wheel driving system and the right wheel driving system and used for controlling the left wheel and the right wheel to move, the holder system is internally provided with a visible light camera and an infrared thermal imager, and the visible light camera and the infrared thermal imager are used for shooting all parts in the traction substation.
5. The intelligent inspection system according to claim 4, wherein the power supply system comprises a vehicle-mounted storage battery and a power management system, the power management system is used for monitoring the electric quantity of the vehicle-mounted storage battery and sending the monitored information to the embedded main control system, the embedded main control system generates a motion control instruction according to the received information and sends the motion control instruction to the motion control system, and the motion control system controls the left wheel driving system and the right wheel driving system to act so that the inspection robot can move to the charging chamber for charging;
the charging chamber adopts an electromagnetic induction type charging mode to charge the vehicle-mounted storage battery.
6. The intelligent inspection system according to claim 4, wherein the navigation and positioning system includes an odometer, a robot motion controller, a robot controller and a laser sensor; the odometer is used for measuring the mileage of the routing inspection robot and feeding back the mileage to the robot motion controller, the robot motion controller feeds back the mileage to the robot manual control machine, and the laser sensor is used for detecting the distance between the routing inspection robot and the transformer substation and feeding back the distance measurement data to the robot manual control machine;
and the robot manual control machine carries out mapping positioning and navigation control according to the received mileage and ranging data and sends a control instruction to the robot motion controller and the laser sensor.
7. The intelligent routing inspection system of traction substations according to claim 6, wherein the positioning process of the navigation positioning system is as follows:
firstly, a navigation positioning system utilizes a laser sensor and a mileometer carried by an inspection robot to establish a two-dimensional map of a large-scale and sparse-feature environment of a substation;
secondly, matching detection information of the laser sensor with the established two-dimensional map to obtain positioning information of the inspection robot, wherein the positioning information comprises a position and a course;
and finally, the navigation positioning system adopts the positioning information to guide the inspection robot, so that the inspection robot reaches the specified position in the substation.
8. The intelligent inspection system according to claim 7, wherein the process of matching the detection information of the laser sensor with the established two-dimensional map and obtaining the positioning information of the inspection robot comprises:
installing n (n is more than or equal to 3) signposts at fixed positions in a required positioning environment, establishing a global coordinate system XOY, and knowing the position of each signpost under the XOY coordinate system;
rotation center O of rotary laser sensorSEstablishing a sensor coordinate system XSOSYSThe detected road sign corresponding to X can be obtained by the laser sensor every time the laser sensor scans one circleSAngle of axis lambdai，i＝1，2，…，n；
After at least 3 road signs in the environment are detected, the rotation center O of the laser sensor is obtained through iterative calculationSCoordinates (X, y) in the global coordinate system XOY and X in the sensor coordinate systemSThe axis is at an angle theta to the X-axis in the global coordinate system.
9. The intelligent inspection system according to claim 8, wherein the navigation and positioning system uses the positioning information to navigate the inspection robot, so that the specific process of the inspection robot reaching the specified position in the substation is as follows:
assuming a path starting point P under a global coordinate system XOY1(x1，y1) And end point P2(x2，y2) And obtaining the position deviation delta S and the course deviation delta theta of the robot and the driving path according to the following formula:
in the formula, the value range of theta angle data participating in delta theta calculation is [0, 360 ], and the positive and negative values of delta S and delta theta reflect whether the inspection robot is inclined to the right or the left relative to the running path;
assuming that the running speed of the inspection robot is V, multiplying the position deviation delta S and the course deviation delta theta respectively by a coefficient K according to the calculated position deviation delta S and the calculated course deviation delta thetaSAnd KθWherein the coefficient KSAnd KθAnd all the values are non-negative values, and the increment delta V of the speed control quantity of the left and right two wheels of the inspection robot is obtained as follows:
ΔV＝KsΔS+KθΔθ，
obtaining the running speed V of the left wheel of the inspection robot according to the speed control quantity increment delta VLAnd the running speed V of the right wheelRRespectively as follows:
in the formula, KPAs a function of the number of the coefficients,
in the formula, d represents the distance between the current position and the parking position of the robot, and r represents the set parking control range; when the inspection robot enters a set parking control range r, the inspection robot starts to decelerate, and when the parking error of the inspection robot is smaller than an allowable value epsilon, the inspection robot stops moving; y isPIndicates a stop point Pk(xP，yP) The ordinate of (c).
10. The intelligent inspection system for the traction power substations according to claim 4, wherein the cloud deck system comprises a cloud deck control system, a video server, a cloud deck, and a visible light camera and a thermal infrared imager which are arranged on the cloud deck, the cloud deck control system is used for controlling the cloud deck to drive the visible light camera and the thermal infrared imager to rotate, the visible light camera and the thermal infrared imager are connected with the video server, and the video server is communicated with the monitoring background of the base station layer through a communication layer so as to send images of the power substations, which are shot by the visible light camera and the thermal infrared imager, to the monitoring background;
and the data processing module in the monitoring background processes the received image in real time by adopting a dial plate positioning, edge detection, circle and ellipse fitting, pointer detection angulation and a character recognition algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110960978.2A CN113708491A (en) | 2021-08-20 | 2021-08-20 | Intelligent inspection system for traction substation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110960978.2A CN113708491A (en) | 2021-08-20 | 2021-08-20 | Intelligent inspection system for traction substation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113708491A true CN113708491A (en) | 2021-11-26 |
Family
ID=78653711
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110960978.2A Pending CN113708491A (en) | 2021-08-20 | 2021-08-20 | Intelligent inspection system for traction substation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113708491A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114582041A (en) * | 2022-05-07 | 2022-06-03 | 绿城科技产业服务集团有限公司 | Park patrol system based on video analysis algorithm |
| US11352035B1 (en) * | 2021-01-13 | 2022-06-07 | East China Jiaotong University | Auxiliary monitoring system for traction substation |
| CN114783080A (en) * | 2022-04-28 | 2022-07-22 | 云南电网有限责任公司电力科学研究院 | Power transmission network inspection method and device, computer equipment and storage medium |
| CN115188091A (en) * | 2022-07-13 | 2022-10-14 | 国网江苏省电力有限公司泰州供电分公司 | Unmanned aerial vehicle grid inspection system and method integrating power transmission and transformation equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102280826A (en) * | 2011-07-30 | 2011-12-14 | 山东鲁能智能技术有限公司 | Intelligent robot inspection system and intelligent robot inspection method for transformer station |
| CN104848851A (en) * | 2015-05-29 | 2015-08-19 | 山东鲁能智能技术有限公司 | Transformer substation patrol robot based on multi-sensor data fusion picture composition and method thereof |
| CN104914865A (en) * | 2015-05-29 | 2015-09-16 | 国网山东省电力公司电力科学研究院 | Transformer station inspection tour robot positioning navigation system and method |
| CN106003040A (en) * | 2016-06-20 | 2016-10-12 | 国网上海市电力公司 | Transformer substation inspection robot system with obstacle avoidance function |
| CN111611855A (en) * | 2020-04-17 | 2020-09-01 | 广东电网有限责任公司 | Three-dimensional visual robot intelligence system of patrolling and examining of transformer substation |
-
2021
- 2021-08-20 CN CN202110960978.2A patent/CN113708491A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102280826A (en) * | 2011-07-30 | 2011-12-14 | 山东鲁能智能技术有限公司 | Intelligent robot inspection system and intelligent robot inspection method for transformer station |
| CN104848851A (en) * | 2015-05-29 | 2015-08-19 | 山东鲁能智能技术有限公司 | Transformer substation patrol robot based on multi-sensor data fusion picture composition and method thereof |
| CN104914865A (en) * | 2015-05-29 | 2015-09-16 | 国网山东省电力公司电力科学研究院 | Transformer station inspection tour robot positioning navigation system and method |
| CN106003040A (en) * | 2016-06-20 | 2016-10-12 | 国网上海市电力公司 | Transformer substation inspection robot system with obstacle avoidance function |
| CN111611855A (en) * | 2020-04-17 | 2020-09-01 | 广东电网有限责任公司 | Three-dimensional visual robot intelligence system of patrolling and examining of transformer substation |
Non-Patent Citations (2)
| Title |
|---|
| 李红梅: "基于地图匹配的变电站巡检机器人激光导航系统设计", 制造业自动化, vol. 36, no. 1, pages 52 - 56 * |
| 肖鹏: "变电站智能巡检机器人激光导航系统研究", 自动化与仪表, vol. 27, no. 5, pages 5 - 9 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11352035B1 (en) * | 2021-01-13 | 2022-06-07 | East China Jiaotong University | Auxiliary monitoring system for traction substation |
| CN114783080A (en) * | 2022-04-28 | 2022-07-22 | 云南电网有限责任公司电力科学研究院 | Power transmission network inspection method and device, computer equipment and storage medium |
| CN114582041A (en) * | 2022-05-07 | 2022-06-03 | 绿城科技产业服务集团有限公司 | Park patrol system based on video analysis algorithm |
| CN114582041B (en) * | 2022-05-07 | 2023-02-17 | 绿城科技产业服务集团有限公司 | Park patrol system based on video analysis algorithm |
| CN115188091A (en) * | 2022-07-13 | 2022-10-14 | 国网江苏省电力有限公司泰州供电分公司 | Unmanned aerial vehicle grid inspection system and method integrating power transmission and transformation equipment |
| CN115188091B (en) * | 2022-07-13 | 2023-10-13 | 国网江苏省电力有限公司泰州供电分公司 | Unmanned aerial vehicle gridding inspection system and method integrating power transmission and transformation equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113708491A (en) | Intelligent inspection system for traction substation | |
| US11892855B2 (en) | Robot with perception capability of livestock and poultry information and mapping approach based on autonomous navigation | |
| US10471976B2 (en) | Railway maintenance device | |
| Chung et al. | The detection and following of human legs through inductive approaches for a mobile robot with a single laser range finder | |
| Luo et al. | A survey of intelligent transmission line inspection based on unmanned aerial vehicle | |
| Chen et al. | Robot navigation with map-based deep reinforcement learning | |
| CN102622615B (en) | Knife switch state closing reliability judging method based on distance between knife switch arm feature points | |
| CN102980454B (en) | Explosive ordnance disposal (EOD) method of robot EOD system based on brain and machine combination | |
| CN109612525A (en) | Environmental monitoring robot and its automatic detecting method | |
| CN116494201A (en) | Monitoring integrated power machine room inspection robot and unmanned inspection method | |
| Zhang et al. | Development and implementation of a robotic inspection system for power substations | |
| Wang et al. | Remote control system based on the Internet and machine vision for tracked vehicles | |
| CN109676618A (en) | Security protection crusing robot and its automatic detecting method | |
| CN116442219B (en) | Intelligent robot control system and method | |
| Mohamed et al. | GP-guided MPPI for efficient navigation in complex unknown cluttered environments | |
| Ai et al. | Research on AGV navigation system based on binocular vision | |
| CN115373383A (en) | Autonomous obstacle avoidance method and device for garbage recovery unmanned boat and related equipment | |
| CN113298044B (en) | Obstacle detection method, system, device and storage medium based on positioning compensation | |
| CN113218384B (en) | Indoor AGV self-adaptive positioning method based on laser SLAM | |
| Zhao et al. | Design and its visual servoing control of an inspection robot for power transmission lines | |
| CN112015180B (en) | Intelligent experiment trolley and control system thereof | |
| CN114290313A (en) | Inspection robot, automatic navigation inspection robot system and control method | |
| Saleh et al. | Local motion planning for ground mobile robots via deep imitation learning | |
| CN209717724U (en) | Security protection crusing robot | |
| Lu et al. | Design and implement of control system for power substation equipment inspection robot |
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 |