CN115313655A - Method, system, device, processor and readable storage medium for intelligent robot indoor inspection of unattended substation - Google Patents

Method, system, device, processor and readable storage medium for intelligent robot indoor inspection of unattended substation Download PDF

Info

Publication number
CN115313655A
CN115313655A CN202211031285.6A CN202211031285A CN115313655A CN 115313655 A CN115313655 A CN 115313655A CN 202211031285 A CN202211031285 A CN 202211031285A CN 115313655 A CN115313655 A CN 115313655A
Authority
CN
China
Prior art keywords
intelligent robot
equipment
inspection
sensor
layer
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
CN202211031285.6A
Other languages
Chinese (zh)
Inventor
邢智辉
刘烨
郭学艳
郑浩野
梁誉文
原宇光
刘更
杨轶森
朱洪堃
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.)
Shanghai Zexin Electric Power Technology Co ltd
State Grid Corp of China SGCC
State Grid Heilongjiang Electric Power Co Ltd
Original Assignee
Shanghai Zexin Electric Power Technology Co ltd
State Grid Corp of China SGCC
State Grid Heilongjiang 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 Shanghai Zexin Electric Power Technology Co ltd, State Grid Corp of China SGCC, State Grid Heilongjiang Electric Power Co Ltd filed Critical Shanghai Zexin Electric Power Technology Co ltd
Priority to CN202211031285.6A priority Critical patent/CN115313655A/en
Publication of CN115313655A publication Critical patent/CN115313655A/en
Pending legal-status Critical Current

Links

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
    • H02J13/00001—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
    • H02J13/00002—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
    • 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
    • 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
    • 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
    • H02J13/00036—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 switches, relays or circuit breakers
    • 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
    • H02J13/00036—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 switches, relays or circuit breakers
    • H02J13/0004—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 switches, relays or circuit breakers involved in a protection system

Landscapes

  • Engineering & Computer Science (AREA)
  • Power Engineering (AREA)
  • Human Computer Interaction (AREA)
  • Manipulator (AREA)

Abstract

The invention relates to an indoor inspection method for an intelligent robot of an unattended substation, which comprises the following steps: the intelligent robot receives a patrol instruction from the control end; positioning equipment needing to be inspected through a pre-constructed electronic map, planning an inspection path and moving the equipment to be inspected; the intelligent robot checks the equipment state by using various sensors, and if the equipment state is normal, the intelligent robot positions and reads the instrument on the equipment through an instrument recognition algorithm to obtain a corresponding inspection report and uploads the inspection report to a database of a control end; otherwise, the intelligent robot uploads the equipment abnormality information to the control end and gives an abnormality grade. The invention also relates to an intelligent robot indoor inspection system for the unattended transformer substation. The intelligent robot indoor inspection method, the intelligent robot indoor inspection system, the intelligent robot indoor inspection device, the intelligent robot indoor inspection processor and the computer readable storage medium can respond to requirements in time, are high in safety and have wide application range.

Description

Method, system, device, processor and readable storage medium for intelligent robot indoor inspection of unattended substation
Technical Field
The invention relates to the field of power systems, in particular to the field of intelligent inspection of transformer substations, and specifically relates to a method, a system, a device, a processor and a computer readable storage medium for indoor inspection of an intelligent robot of an unattended transformer substation.
Background
With the continuous development of science and technology, people can not use electricity in life or work, and the quality of power supply is closely related to the normal operation of the society. The instability of the power system brings inconvenience to daily production and life, and even causes huge property loss in severe cases, so that the guarantee of the stable operation of the power system is an important responsibility and obligation of power supply enterprises. In the whole power system, a transformer substation is an important part of the power system, and plays a role in regulation and distribution between a power generation end and a user end, and each internal device is an indispensable part for normal operation of a power grid. Therefore, in order to ensure the safety and stability of the equipment, the staff needs to regularly patrol the transformer substation.
Under the large background that a high-voltage power grid and an intelligent power grid are gradually promoted, newly-built substations are mostly matched high-voltage and extra-high-voltage unattended substations, and the voltage grade can even reach 1000KV. Compared with a traditional transformer substation, the transformer substation has great difference in multiple aspects such as equipment selection, wiring layout and the like, and inspection workers need to be familiar with the working environment again to know the details of the equipment. In addition, as the voltage grade of the transformer substation is increased, the complexity of various devices is increased, the requirement on safe operation is improved, and a new requirement is provided for professional literacy of workers.
Generally speaking, although the inspection methods are continuously improved, the traditional manual inspection methods still have more and more problems:
(1) The speed of maintenance personnel is far lower than the speed of equipment quantity increase, so that the equipment quantity required to be inspected by all people is greatly increased, the phenomena of untimely and uncertainties inspection are bound to occur, and the inspection efficiency is seriously reduced;
(2) In the traditional maintenance mode, equipment data needs to be collected manually, then the data are made into a report and uploaded to a power equipment control system, and due to the fact that the number of equipment is increased, the number of data false reports is increased, and therefore misoperation of power equipment often occurs;
(3) Due to safety considerations, the substation is generally remotely located, and therefore, when the power equipment control system needs to check specific equipment, a patrol worker cannot necessarily respond to the requirement in time.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a method, a system, a device, a processor and a computer readable storage medium thereof for intelligent robot indoor inspection of an unattended substation, which have the advantages of simple structure, high efficiency and wide application range.
In order to achieve the above objects, the method, system, apparatus, processor and computer readable storage medium thereof for intelligent robot indoor inspection of an unattended substation according to the present invention are as follows:
the intelligent robot indoor inspection method for the unattended substation is mainly characterized by comprising the following steps:
(1) The intelligent robot receives an inspection instruction from the control end and starts to inspect;
(2) Positioning equipment needing to be inspected through a pre-constructed electronic map, planning an inspection path and moving the equipment to be inspected;
(3) The intelligent robot checks the equipment state by using various sensors, and if the equipment state is normal, the step (5) is continued; otherwise, continuing to the step (4);
(4) The intelligent robot uploads the abnormal information of the equipment to the control end, gives an abnormal grade and continues to the step (6);
(5) The intelligent robot positions and reads the instrument on the equipment through an instrument recognition algorithm to obtain a corresponding patrol report and uploads the patrol report to a database of a control end;
(6) And (4) the intelligent robot patrols the next equipment on the patrol route, continues the step (3), and automatically returns to the charging seat if all the equipment is patrolled, and the patrol is completed.
Preferably, the step (5) specifically comprises the following steps:
(5.1) collecting equipment images, and marking the position and the type of the instrument on the equipment in advance;
(5.2) establishing and training a YOLOv3 target detection model;
(5.3) searching the position of the pointer instrument on the positioning equipment by using a YOLOv3 model and classifying the position of the pointer instrument;
(5.4) moving the high-definition camera to the position right facing the pointer instrument for shooting by using a mechanical arm and a holder carried by the intelligent robot;
(5.5) reading the indication number of the pointer instrument by utilizing an instrument reading algorithm;
(5.6) judging whether meters are not identified, if so, continuing to the step (5.4); otherwise, finishing the inspection of the current equipment.
Preferably, the step (5.5) specifically comprises the following steps:
(5.5.1) carrying out median filtering on the acquired instrument front image;
(5.5.2) respectively extracting a dial plate image and a pointer image through a semantic segmentation model;
(5.5.3) scanning the dial plate image and the pointer image from the image center to the two sides of the image according to the width of 30 pixels, and unfolding the semicircular dial plate image and the semicircular pointer image into rectangular images;
(5.5.4) vertically superposing the two rectangular images and drawing a line drawing;
(5.5.5) the relative position of the pointer on the dial in the line chart is positioned, and the pointer instrument scale number is obtained according to the prestored instrument scale range.
Preferably, the semantic segmentation model comprises a feature extraction layer and a feature fusion layer, wherein the 1 st to 5 th layers of the semantic segmentation model are the feature extraction layers, and each layer is subjected to two times of 3 × 3 convolution and one time of 2 × 2 maximum pooling; the 6 th to 9 th layers of the semantic segmentation model are feature fusion layers, and each layer is subjected to two times of 3 × 3 convolution and one time of 2 × 2 deconvolution; the semantic segmentation model is characterized in that shortcut connection paths are arranged between the 1 st layer and the 9 th layer, the 2 nd layer and the 8 th layer, the 3 rd layer and the 7 th layer and the 4 th layer and the 6 th layer, and attention modules are installed on the shortcut connection paths.
Preferably, the attention module is configured to calculate a spatial attention, specifically:
spatial attention is calculated according to the following formula:
Figure BDA0003817508150000031
wherein, F' avg Represents average pooling, F' max Which is indicative of the maximum pooling,
Figure BDA0003817508150000032
indicating a splicing operation, f same Represents the same padding convolution, M s Representing spatial attention.
The system for indoor inspection of the intelligent robot of the unattended transformer substation is mainly characterized by comprising a wheeled robot main body, a thermal infrared imager, an SF6 sensor, an ultrasonic partial discharge sensor and a lifting arm, wherein the thermal infrared imager and the ultrasonic partial discharge sensor are arranged on the wheeled robot main body through the lifting arm, the SF6 sensor is arranged on the wheeled robot main body, the thermal infrared imager, the SF6 sensor and the ultrasonic partial discharge sensor are used for carrying out equipment state inspection, the thermal infrared imager is used for detecting the running temperature state of equipment, and if an overheating area occurs, an overheating abnormal signal is sent out, and then an infrared image of the area is reported; the ultrasonic partial discharge sensor is used for detecting the partial discharge condition of the equipment, and if the partial discharge phenomenon occurs for a long time, the ultrasonic partial discharge sensor sends out a partial discharge abnormal signal and reports the position and the size of the partial discharge; the SF6 sensor is used for detecting the insulation protection state of the equipment, if the concentration of SF6 gas exceeds a threshold value, insulation gas leakage is represented, the insulation performance of the equipment is damaged, an insulation abnormal signal is sent out, and meanwhile, the concentration value of the SF6 gas is reported.
Preferably, the device abnormality levels are classified into a-level abnormality, a B-level abnormality and a C-level abnormality, wherein the C-level abnormality is determined if one sensor data is abnormal, the B-level abnormality is determined if two sensor data are abnormal, and the a-level abnormality is determined if all three sensor data are abnormal.
Preferably, the system further comprises a robot body, a lifting arm and a cradle head, wherein the robot body is used for moving to the front of the device to be checked, the lifting arm is installed on the robot body and used for aligning the sensor with a specific instrument, the cradle head is installed on the lifting arm and used for integrally installing the sensor, the robot body moves on an XY axis, the lifting arm moves on a Z axis, the cradle head moves along with the lifting arm to check the instrument, the system moves to the next device for continuous checking after checking is finished, and the system returns to a value charging seat after all devices are checked; the sensor include temperature and humidity sensor 7, SF6 sensor 6, robot pickup 11, all install on the robot.
This a device that is used for indoor inspection of intelligent robot of unmanned on duty transformer substation, its key feature is, the device include:
a processor configured to execute computer-executable instructions;
the intelligent robot indoor inspection system comprises a storage, a processor and a control module, wherein the storage stores one or more computer executable instructions, and when the computer executable instructions are executed by the processor, the storage realizes the steps of the intelligent robot indoor inspection method for the unattended substation.
The processor for the intelligent robot indoor inspection of the unattended substation is mainly characterized in that the processor is configured to execute computer executable instructions, and the computer executable instructions are executed by the processor to realize the steps of the method for the intelligent robot indoor inspection of the unattended substation.
The computer-readable storage medium is primarily characterized by having stored thereon a computer program executable by a processor to perform the steps of the above-described method for intelligent robot indoor inspection of an unattended substation.
The intelligent robot indoor inspection system and the method thereof can respond to the requirement in time, have low error and higher safety and have wide application range.
Drawings
Fig. 1 is a general flowchart of a method for intelligent robot indoor inspection of an unattended substation according to the present invention.
Fig. 2 is a flowchart of an instrument positioning algorithm of the method for intelligent robot indoor inspection of an unattended substation according to the present invention.
Fig. 3 is a flowchart of an instrument reading algorithm of the method for the intelligent robot indoor inspection of the unattended substation according to the present invention.
Fig. 4 is a right side view of the system for intelligent robot indoor inspection of an unattended substation of the present invention.
Fig. 5 is a left side view of the system for intelligent robot indoor inspection of an unattended substation of the present invention.
Fig. 6 is a parameter table diagram of the system for intelligent robot indoor inspection of an unattended substation according to the present invention.
Reference numerals:
1. infrared thermal imaging system
2. High definition camera
3. Lifting arm
4. Laser radar
5. Anti-falling sensor
6 SF6 sensor
7. Temperature and humidity sensor
8. Intelligent light supplement lamp
9. Tripod head orientation pickup
10. Cloud platform
11. Robot body directional pickup
12. Network debugging port
13. Hand switch
14. Power switch
15. Mobile phone terminal position
16. Emergency stop switch
17. System switch
18. Automatic charging contact
19. Universal wheel
20. Ultrasonic partial discharge sensor
21. Carrying handle
22 USB debugging port
23. Ultrasonic radar
24 HDMI debugging port
25. Driving wheel
Detailed Description
In order to more clearly describe the technical contents of the present invention, the following further description is given in conjunction with specific embodiments.
The invention discloses an indoor inspection system for an intelligent robot of an unattended substation, which comprises the following steps:
(1) The intelligent robot receives an inspection instruction from the control end and starts to inspect;
(2) Positioning equipment to be inspected through a pre-constructed electronic map, planning an inspection path, and moving to the equipment to be inspected;
(3) The intelligent robot checks the equipment state by using various sensors, and if the equipment state is normal, the step (5) is continued; otherwise, continuing the step (4);
(4) The intelligent robot uploads the abnormal information of the equipment to the control end, gives an abnormal grade and continues to the step (6);
(5) The intelligent robot positions and reads the instrument on the equipment through an instrument recognition algorithm to obtain a corresponding patrol report and uploads the patrol report to a database of a control end;
(6) And (4) the intelligent robot patrols the next equipment on the patrol route, continues the step (3), and automatically returns to the charging seat if all the equipment is patrolled, and the patrol is completed.
As a preferred embodiment of the present invention, the step (5) specifically comprises the following steps:
(5.1) collecting equipment images, and marking the position and the type of the instrument on the equipment in advance;
(5.2) establishing and training a YOLOv3 target detection model;
(5.3) searching the position of the pointer instrument on the positioning equipment by using a YOLOv3 model and classifying the position of the pointer instrument;
(5.4) moving the high-definition camera to the position right facing the pointer instrument for shooting by using a mechanical arm and a holder carried by the intelligent robot;
(5.5) reading the indication number of the pointer instrument by utilizing an instrument reading algorithm;
(5.6) judging whether meters are not identified, if so, continuing to the step (5.4); otherwise, finishing the inspection of the current equipment.
As a preferred embodiment of the present invention, the step (5.5) specifically comprises the following steps:
(5.5.1) carrying out median filtering on the acquired instrument front image;
(5.5.2) respectively extracting a dial plate image and a pointer image through a semantic segmentation model;
(5.5.3) scanning the dial plate image and the pointer image from the center of the image to the two sides of the image according to the width of 30 pixels, and unfolding the semicircular dial plate image and the semicircular pointer image into rectangular images;
(5.5.4) vertically superposing the two rectangular images and drawing a line drawing;
(5.5.5) positioning the relative position of the pointer on the dial in the line graph, and calculating the indicating number of the pointer and the meter according to the pre-stored scale range of the meter.
As a preferred embodiment of the present invention, the semantic segmentation model includes a feature extraction layer and a feature fusion layer, wherein the 1 st to 5 th layers of the semantic segmentation model are the feature extraction layers, and each layer is subjected to two times of 3 × 3 convolution and one time of 2 × 2 maximum pooling; the 6 th to 9 th layers of the semantic segmentation model are feature fusion layers, and each layer is subjected to two times of 3 × 3 convolution and one time of 2 × 2 deconvolution; the semantic segmentation model is characterized in that shortcut connection paths are arranged between the 1 st layer and the 9 th layer, the 2 nd layer and the 8 th layer, the 3 rd layer and the 7 th layer and the 4 th layer and the 6 th layer, and attention modules are installed on the shortcut connection paths.
As a preferred embodiment of the present invention, the attention module is configured to calculate spatial attention, specifically:
spatial attention is calculated according to the following formula:
Figure BDA0003817508150000061
wherein, F' avg Denotes average pooled, F' max The maximum pooling is indicated by the number of pools,
Figure BDA0003817508150000062
indicating a splicing operation, f same Represents the same padding convolution, M s Indicating spatial attention.
The system for the indoor inspection of the intelligent robot of the unattended substation comprises a wheeled robot main body, a thermal infrared imager 1, an SF6 sensor 6, an ultrasonic partial discharge sensor 20 and a lifting arm 3, wherein the thermal infrared imager 1 and the ultrasonic partial discharge sensor 20 are installed on the wheeled robot main body through the lifting arm 3, the SF6 sensor 6 is installed on the wheeled robot main body, the thermal infrared imager 1, the SF6 sensor 6 and the ultrasonic partial discharge sensor 20 are used for carrying out equipment state inspection, the thermal infrared imager 1 is used for detecting the running temperature state of equipment, and if an overheating area occurs, an overheating abnormal signal is sent out, and an infrared image of the area is reported at the same time; the ultrasonic partial discharge sensor 20 is used for detecting the partial discharge condition of the equipment, and if the partial discharge phenomenon occurs for a long time, a partial discharge abnormal signal is sent out, and the position and the size of the partial discharge are reported; the SF6 sensor 6 is used for detecting the insulation protection state of the equipment, if the concentration of SF6 gas exceeds a threshold value, insulation gas leakage is represented, the insulation performance of the equipment is damaged, an insulation abnormal signal is sent out, and meanwhile, the concentration value of the SF6 gas is reported.
In a preferred embodiment of the present invention, the device abnormality levels are classified into an a-level abnormality, a B-level abnormality, and a C-level abnormality, wherein the C-level abnormality is determined when one sensor data item is abnormal, the B-level abnormality is determined when two sensor data items are abnormal, and the a-level abnormality is determined when all three sensor data items are abnormal.
As a preferred embodiment of the present invention, the system further includes a robot body, a lifting arm 3, and a pan/tilt head 10, the robot body is used to move to the front of the device to be inspected, the lifting arm 3 is installed on the robot body and is used for aligning a sensor to a specific instrument, the pan/tilt head 10 is installed on the lifting arm 3 and is used to integrate and install the sensor, the robot body moves on the XY axis, the lifting arm 3 moves on the Z axis, the pan/tilt head 10 moves along with the lifting arm 3 and is aligned to the instrument for inspection, after the inspection is completed, the robot body moves to the next device for inspection, and after all the devices are inspected, the system returns to the charging seat; the sensors comprise a temperature and humidity sensor 7, an SF6 sensor 6 and a robot sound pick-up 11 which are all arranged on the robot body.
The invention relates to a device for indoor inspection of an intelligent robot of an unattended substation, which comprises:
a processor configured to execute computer-executable instructions;
the intelligent robot indoor inspection system comprises a storage, a processor and a control module, wherein the storage stores one or more computer executable instructions, and when the computer executable instructions are executed by the processor, the storage realizes the steps of the intelligent robot indoor inspection method for the unattended substation.
The processor for the intelligent robot indoor inspection of the unattended substation is configured to execute computer executable instructions, and when the computer executable instructions are executed by the processor, the steps of the method for the intelligent robot indoor inspection of the unattended substation are realized.
The computer-readable storage medium of the present invention, having stored thereon a computer program executable by a processor for carrying out the steps of the method for intelligent robot indoor inspection of an unmanned substation as described above.
The invention discloses an intelligent robot indoor inspection method and system for an unattended substation, wherein the general flow comprises the following steps: firstly, the intelligent robot receives a patrol inspection instruction. Planning a routing inspection path according to equipment needing routing inspection; secondly, after the intelligent robot reaches the equipment position, starting various sensors to judge whether the equipment operation state is normal or not; then, the intelligent robot positions and reads the instruments on the equipment through an instrument recognition algorithm, and moves to the next equipment after all the instruments are processed; and finally, returning to the charging seat if all the equipment is subjected to patrol.
Aiming at the defects in the prior art, the invention aims to provide an intelligent robot indoor inspection method and system for an unattended substation, and the method and system provided by the invention can be used for solving the defects in the prior art.
Referring to fig. 1, an indoor inspection method and system for an intelligent robot used in an unattended substation is characterized by comprising the following steps:
s1, the intelligent robot receives an inspection instruction from a control end and starts to inspect;
s2, positioning equipment to be inspected through a pre-constructed electronic map, planning an inspection path and moving the equipment to be inspected;
s3, the intelligent robot checks the equipment state by using various sensors, if the equipment state is normal, the step S5 is executed, and if the equipment state is abnormal, the step S4 is executed;
s4, for abnormal equipment, the intelligent robot uploads the abnormal information of the equipment to a control end, gives an abnormal grade, and then executes the step S6;
s5, for normal equipment, the intelligent robot positions and reads an instrument on the equipment through an instrument recognition algorithm to obtain a corresponding patrol report and uploads the patrol report to a control end database;
and S6, the intelligent robot starts to patrol the next device, if all the devices are patrolled, the intelligent robot automatically returns to the charging seat, and the patrol is completed.
As shown in fig. 4 and 5, the present device is composed of three major parts: 1. the robot body is used for moving to the front of the device to be checked and is provided with a lifting arm; 2. the lifting arm 3 is used for aligning the sensor to a specific instrument and is provided with a holder; 3. and the holder 10 is used for integrally mounting sensors such as a camera, an infrared instrument and a partial discharge sensor.
In brief, the robot body moves along the XY axes, the lifting arm moves along the Z axis, the cradle head is finally aligned with the instrument for inspection, after all instruments of one device are inspected, the robot body moves to the device to be taken off until all devices are inspected, and then the robot body returns to the charging seat.
On the installation position of the sensor, a temperature and humidity sensor 7, an SF6 sensor 6 and a robot body sound pick-up 11 are installed on the robot body, because the sensors are used for monitoring environmental parameters, the numerical difference between different instruments of the same equipment is small, the sensors are not required to be installed on a cloud deck, and other sensors are installed on the cloud deck.
In the figure, a cloud platform directional sound pickup 9 is positioned on a cloud platform and used for collecting equipment operation sound, a robot body sound pickup 11 is positioned on a robot body and used for collecting environmental sound, and the cloud platform directional sound pickup 9 and the robot body sound pickup are used for sound pickup in different directions. Fig. 6 is a table diagram showing technical parameters of the intelligent inspection robot according to the present invention.
The equipment state inspection is completed through an infrared imager, an ultrasonic partial discharge sensor and an SF6 sensor 6, and the method comprises the following steps:
(1) The infrared imager is used for detecting the running temperature state of the equipment, the running temperature of the power equipment is usually stabilized in a certain range, and the phenomenon of overhigh temperature often occurs in abnormal conditions, so that an overheat abnormal signal is sent out if an overheat area occurs, and an infrared image of the area is reported at the same time;
(2) The ultrasonic partial discharge sensor is used for detecting the partial discharge condition of equipment, the short-term partial discharge does not influence the insulation performance of the equipment, and the long-term partial discharge phenomenon can cause the deterioration of the dielectric performance of the equipment due to the cumulative effect, so that if the partial discharge phenomenon appears for a long time, a partial discharge abnormal signal is sent out, and the position and the size of the partial discharge are reported;
(3) The SF6 sensor 6 is used for detecting the insulation protection state of equipment, SF6 gas is the most commonly used insulation medium of power equipment, particularly high-voltage equipment, therefore if the concentration of the SF6 gas exceeds a threshold value, which represents that insulation gas leakage occurs and the insulation performance of the equipment is damaged, an insulation abnormal signal is sent out, and meanwhile, the concentration value of the SF6 gas is reported.
The equipment abnormity level is divided into three levels, if one sensor data is abnormal, the equipment abnormity level is C-level abnormity, if two sensor data are abnormal, the equipment abnormity level is B-level abnormity, and if all three sensor data are abnormal, the equipment abnormity level is A-level abnormity. By grading the abnormal state of the equipment, maintenance personnel can arrange a maintenance plan according to the severity of the abnormal equipment, and high-risk hidden dangers can be timely handled.
Specifically, referring to fig. 2, the meter identification algorithm is used for finding and reading a meter, and the meter to be found is a pointer-type meter, because a digital meter generally has a communication module, or can be simply additionally provided with a communication module, so that data of the digital meter is directly reported, and therefore, a polling robot is not required to identify and record, and the specific flow of the identification algorithm is as follows:
s1-1, collecting equipment images, and marking the positions and types of instruments on the equipment images in advance;
s1-2, establishing and training a YOLOv3 target detection model;
s1-3, positioning the position of an instrument on equipment by using a YOLOv3 model and classifying the instrument;
s1-4, moving the high-definition camera to a position right facing the pointer instrument for shooting by using a mechanical arm and a holder carried by the intelligent robot;
s1-5, obtaining a meter reading number by using a meter reading algorithm;
and S1-6, identifying the current instrument number, if the instruments are not identified, turning to the step S1-4, and if not, completing the inspection of the current equipment.
Specifically, referring to fig. 3, the meter reading algorithm is used for reading the indication number of the pointer-type meter, and the specific process is as follows:
s2-1, performing median filtering on the acquired instrument front image;
s2-2, respectively segmenting a dial plate and a pointer from the image through a semantic segmentation model;
s2-3, scanning the two sides of the image according to the width of 30 pixels by taking the center of the image as an original point, and unfolding the semicircular dial plate and the pointer image into a rectangular image;
s2-4, vertically superposing the two rectangular images and drawing a line graph;
and S2-5, positioning the relative position of the pointer in the line graph on the dial, and deducing the pointer number according to the pre-stored scale range of the instrument.
The semantic segmentation model is an improved U-Net model and is divided into two parts, namely feature extraction and feature fusion; the 1 st layer to the 5 th layer of the model are a characteristic extraction part, and each layer of operation is twice 3 multiplied by 3 convolution and once 2 multiplied by 2 maximum pooling; the 6 th to 9 th layers of the model are feature fusion layers, and each layer of operation is two times of 3 multiplied by 3 convolution and one time of 2 multiplied by 2 deconvolution; in addition, there are shortcut links between layers 1 and 9, 2 and 8, 3 and 7, and 4 and 6, with attention modules installed on the shortcut links.
The attention module is a spatial attention module, and the calculation method is as follows:
Figure BDA0003817508150000101
wherein, F' avg Represents average pooling, F' max The maximum pooling is indicated by the number of pools,
Figure BDA0003817508150000102
indicating a splicing operation, f same Represents the same padding convolution, M s Representing spatial attention.
Specifically, referring to fig. 6, the patrol report content includes:
(1) The current protection device number and the description, the state and whether the panel light is abnormal or not of all the panel lights;
(2) The current protection hard pressing plate state, pressing plate description and whether the pressing plate is abnormal or not;
(3) The method comprises the steps of obtaining a current protection panel photo, a hard press state photo and a section of patrol video not less than 15 seconds;
(4) And environment information such as tour time, temperature and humidity of the current cell and the like.
For a specific implementation scheme of this embodiment, reference may be made to relevant descriptions in the foregoing embodiments, which are not described herein again.
It is understood that the same or similar parts in the above embodiments may be mutually referred to, and the same or similar parts in other embodiments may be referred to for the content which is not described in detail in some embodiments.
It should be noted that the terms "first," "second," and the like in the description of the present invention are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. In addition, in the description of the present invention, the meaning of "a plurality" means at least two unless otherwise specified.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by suitable instruction execution devices. For example, if implemented in hardware, as in another embodiment, any one or combination of the following technologies, which are well known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried out in the method for implementing the above embodiment may be implemented by hardware related to instructions of a program, and the corresponding program may be stored in a computer readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a separate product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc.
In the description of the specification, reference to the description of "one embodiment," "some embodiments," "an example," "a specific example," or "some examples" or the like means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The intelligent robot indoor inspection system and the intelligent robot indoor inspection method for the unattended transformer substation can timely respond to requirements, have low error and higher safety, and have wide application range.
In this specification, the invention has been described with reference to specific embodiments thereof. It will, however, be evident that various modifications and changes may be made thereto without departing from the broader spirit and scope of the invention. The specification and drawings are, accordingly, to be regarded in an illustrative rather than a restrictive sense.

Claims (11)

1. A method for intelligent robot indoor inspection of an unattended substation is characterized by comprising the following steps:
(1) The intelligent robot receives an inspection instruction from the control end and starts to inspect;
(2) Positioning equipment needing to be inspected through a pre-constructed electronic map, planning an inspection path and moving the equipment to be inspected;
(3) The intelligent robot checks the equipment state by using various sensors, and if the equipment state is normal, the step (5) is continued; otherwise, continuing to the step (4);
(4) The intelligent robot uploads the equipment abnormal information to the control end, gives an abnormal grade and continues to the step (6);
(5) The intelligent robot positions and reads the instrument on the equipment through an instrument recognition algorithm to obtain a corresponding patrol report and uploads the patrol report to a database of a control end;
(6) And (4) the intelligent robot patrols the next equipment on the patrol route, continues to the step (3), automatically returns to the charging seat if all the equipment is patrolled, and finishes the patrol.
2. The method for the intelligent robot indoor inspection of the unattended substation according to claim 1, wherein the step (5) specifically comprises the following steps:
(5.1) collecting equipment images, and marking the position and the type of the instrument on the equipment in advance;
(5.2) establishing and training a YOLOv3 target detection model;
(5.3) searching the position of the pointer instrument on the positioning equipment by using a YOLOv3 model and classifying the position of the pointer instrument;
(5.4) moving the high-definition camera to the position right facing the pointer instrument to shoot by using the mechanical arm and the holder carried by the intelligent robot;
(5.5) reading the indication number of the pointer instrument by using an instrument reading algorithm;
(5.6) judging whether meters are not identified, if so, continuing to the step (5.4); otherwise, finishing the inspection of the current equipment.
3. The method for the intelligent robot indoor inspection of the unattended substation according to claim 2, wherein the step (5.5) specifically includes the steps of:
(5.5.1) carrying out median filtering on the acquired instrument front image;
(5.5.2) respectively extracting a dial plate image and a pointer image through a semantic segmentation model;
(5.5.3) scanning the dial plate image and the pointer image from the image center to the two sides of the image according to the width of 30 pixels, and unfolding the semicircular dial plate image and the semicircular pointer image into rectangular images;
(5.5.4) vertically superposing the two rectangular images and drawing a line drawing;
(5.5.5) positioning the relative position of the pointer on the dial in the line graph, and calculating the indicating number of the pointer and the meter according to the pre-stored scale range of the meter.
4. The method for the intelligent robot indoor inspection of the unattended substation according to claim 3, wherein the semantic segmentation model comprises a feature extraction layer and a feature fusion layer, layers 1-5 of the semantic segmentation model are the feature extraction layer, and each layer is subjected to two times of 3 x 3 convolution and one time of 2 x 2 maximum pooling; the 6 th layer to the 9 th layer of the semantic segmentation model are feature fusion layers, and each layer is subjected to two times of 3 × 3 convolution and one time of 2 × 2 deconvolution; the semantic segmentation model is characterized in that quick connection paths are arranged between the 1 st layer and the 9 th layer, between the 2 nd layer and the 8 th layer, between the 3 rd layer and the 7 th layer and between the 4 th layer and the 6 th layer, and attention modules are arranged on the quick connection paths.
5. The method for the intelligent robot indoor inspection of the unattended substation according to claim 4, wherein the attention module is used for calculating spatial attention, and specifically comprises:
spatial attention is calculated according to the following formula:
Figure FDA0003817508140000021
wherein, F' avg Denotes average pooled, F' max Which is indicative of the maximum pooling,
Figure FDA0003817508140000022
indicating a splicing operation, f same Representing the same filling convolution, M s Representing spatial attention.
6. A system for indoor inspection of an intelligent robot of an unattended substation is characterized by comprising a wheeled robot main body, a thermal infrared imager, an SF6 sensor, an ultrasonic partial discharge sensor and a lifting arm, wherein the thermal infrared imager and the ultrasonic partial discharge sensor are installed on the wheeled robot main body through the lifting arm, the SF6 sensor is installed on the wheeled robot main body, the thermal infrared imager, the SF6 sensor and the ultrasonic partial discharge sensor are used for carrying out equipment state inspection, the thermal infrared imager is used for detecting the running temperature state of equipment, and if an overheating area occurs, an overheating abnormal signal is sent out, and an infrared image of the area is reported; the ultrasonic partial discharge sensor is used for detecting the partial discharge condition of the equipment, and if the partial discharge phenomenon occurs for a long time, the ultrasonic partial discharge sensor sends out a partial discharge abnormal signal and reports the position and the size of the partial discharge; the SF6 sensor is used for detecting the insulation protection state of equipment, if the concentration of SF6 gas exceeds a threshold value, insulation gas leakage is represented, the insulation performance of the equipment is damaged, an insulation abnormal signal is sent, and meanwhile, the concentration value of the SF6 gas is reported.
7. The system for the indoor inspection of the intelligent robot of the unattended substation according to claim 6, wherein the equipment abnormality is classified into a class A abnormality, a class B abnormality and a class C abnormality, the class C abnormality is determined if one sensor data is abnormal, the class B abnormality is determined if two sensor data are abnormal, and the class A abnormality is determined if all three sensor data are abnormal.
8. The system for the indoor inspection of the intelligent robot of the unattended substation according to claim 6, wherein the system further comprises a robot body, a lifting arm and a cradle head, the robot body is used for moving to the front of a device to be inspected, the lifting arm is installed on the robot body and used for aligning a sensor with a specific instrument, the cradle head is installed on the lifting arm and used for integrally installing the sensor, the robot body moves on an XY axis, the lifting arm moves on a Z axis, the cradle head moves along with the lifting arm to inspect the instrument, the robot body moves to the next device after the inspection is finished, the system returns to a charging seat after the inspection of all the devices is finished; the sensor include temperature and humidity sensor 7, SF6 sensor 6, robot pickup 11, all install on the robot.
9. The utility model provides a device that is used for intelligent robot of unmanned on duty transformer substation to patrol and examine which characterized in that, the device include:
a processor configured to execute computer-executable instructions;
a memory storing one or more computer-executable instructions that, when executed by the processor, perform the steps of the method for intelligent robot indoor inspection of unmanned substations of any one of claims 1 to 5.
10. A processor for intelligent robot indoor inspection of an unattended substation, characterized in that the processor is configured to execute computer executable instructions which, when executed by the processor, implement the steps of the method for intelligent robot indoor inspection of an unattended substation according to any one of claims 1 to 5.
11. A computer-readable storage medium, having stored thereon a computer program executable by a processor for carrying out the steps of the method for intelligent robot indoor inspection of unmanned substations of any one of claims 1 to 5.
CN202211031285.6A 2022-08-26 2022-08-26 Method, system, device, processor and readable storage medium for intelligent robot indoor inspection of unattended substation Pending CN115313655A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211031285.6A CN115313655A (en) 2022-08-26 2022-08-26 Method, system, device, processor and readable storage medium for intelligent robot indoor inspection of unattended substation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211031285.6A CN115313655A (en) 2022-08-26 2022-08-26 Method, system, device, processor and readable storage medium for intelligent robot indoor inspection of unattended substation

Publications (1)

Publication Number Publication Date
CN115313655A true CN115313655A (en) 2022-11-08

Family

ID=83863927

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211031285.6A Pending CN115313655A (en) 2022-08-26 2022-08-26 Method, system, device, processor and readable storage medium for intelligent robot indoor inspection of unattended substation

Country Status (1)

Country Link
CN (1) CN115313655A (en)

Similar Documents

Publication Publication Date Title
CN112910094B (en) Remote automatic transformer substation inspection system and method based on ubiquitous power Internet of things
CN111311597B (en) Unmanned aerial vehicle inspection method and system for defective insulator
CN109800697B (en) Transformer target detection and appearance defect identification method based on VGG-net style migration
WO2018028005A1 (en) Fault detection algorithm for battery panel in large-scale photovoltaic power station
CN110647082A (en) Intelligent inspection system for machine room and working method of intelligent inspection system
CN111626139B (en) Accurate detection method for fault information of IT equipment in machine room
CN108955900A (en) A kind of booster stations temperature measurement early warning system and method based on infrared thermal imaging
CN114898232B (en) Photovoltaic power station unmanned aerial vehicle inspection method and system based on photovoltaic group string data analysis
CN103558818A (en) Cable 10kV high voltage ring main unit remote monitoring and control system
CN112083000B (en) Intelligent identification method and system for appearance defects of substation equipment
CN112698618A (en) Server alarm recognition system based on machine vision technology
CN112100039B (en) Equipment fault alarm method and system
CN106647813A (en) Intelligent vehicle-mounted dual-light inspection system expert diagnosing and abnormity processing method
CN110163990A (en) A kind of mobile robot method for inspecting and system
CN211979511U (en) Unmanned aerial vehicle inspection system capable of automatically identifying defective insulator strings
CN113486779A (en) Panoramic intelligent inspection system for power transmission line
CN115497187A (en) Intelligent inspection method and system for nuclear power plant
CN113343998A (en) Reading monitoring system and method for electric power mechanical meter, computer equipment and application
CN110111213A (en) Indoor substation inspection tour system, method, apparatus and readable storage medium storing program for executing
CN115313655A (en) Method, system, device, processor and readable storage medium for intelligent robot indoor inspection of unattended substation
CN116631087A (en) Unmanned aerial vehicle-based electric power inspection system
CN116465367A (en) Equipment checking method, device, equipment and medium
CN115980062A (en) Industrial production line whole-process vision inspection method based on 5G
CN113078729B (en) Operation detection method and device applied to transformer substation, electronic equipment and medium
CN114942075A (en) Power equipment fault detection and analysis method

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