CN116185028A - Obstacle crossing control system of photovoltaic intelligent cleaning robot - Google Patents
Obstacle crossing control system of photovoltaic intelligent cleaning robot Download PDFInfo
- Publication number
- CN116185028A CN116185028A CN202310158628.3A CN202310158628A CN116185028A CN 116185028 A CN116185028 A CN 116185028A CN 202310158628 A CN202310158628 A CN 202310158628A CN 116185028 A CN116185028 A CN 116185028A
- Authority
- CN
- China
- Prior art keywords
- module
- obstacle
- detection
- photovoltaic
- early warning
- 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
- 238000004140 cleaning Methods 0.000 title claims abstract description 32
- 238000001514 detection method Methods 0.000 claims abstract description 52
- 238000004458 analytical method Methods 0.000 claims abstract description 33
- 230000008447 perception Effects 0.000 claims abstract description 10
- 238000005259 measurement Methods 0.000 claims abstract description 9
- 230000006870 function Effects 0.000 claims abstract description 5
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 238000007637 random forest analysis Methods 0.000 claims description 9
- 230000007547 defect Effects 0.000 claims description 7
- 230000004075 alteration Effects 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000000034 method Methods 0.000 claims description 6
- 230000003647 oxidation Effects 0.000 claims description 6
- 238000007254 oxidation reaction Methods 0.000 claims description 6
- 238000003466 welding Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 238000003708 edge detection Methods 0.000 claims description 3
- 238000003709 image segmentation Methods 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000010248 power generation Methods 0.000 abstract description 8
- 238000006243 chemical reaction Methods 0.000 abstract description 4
- 238000012423 maintenance Methods 0.000 abstract description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
- G05D1/0251—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means extracting 3D information from a plurality of images taken from different locations, e.g. stereo vision
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/50—Photovoltaic [PV] energy
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Electromagnetism (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses a obstacle crossing control system of a photovoltaic intelligent cleaning robot, which comprises an early warning analysis module, a light Fu Banmian sensing module, a photovoltaic side sensing module, a robot control module and a file system module, wherein the early warning analysis module is used for detecting the obstacle crossing of the robot; the early warning analysis module receives data of the light Fu Banmian sensing module and the photovoltaic side sensing module, sets a threshold value to carry out security level warning, and sends an output result to the robot control module to carry out obstacle avoidance treatment; the light Fu Banmian perception module is used for carrying out surface detection and obstacle detection and distance measurement at the same time; the photovoltaic side sensing module is used for detecting smoothness of a splicing opening; the robot control module performs normal passing, plate surface obstacle avoidance, side obstacle avoidance and emergency braking actions, and an intelligent cleaning function is realized by controlling the position and the stepping number of the cleaning robot pulley; the file system module includes a log and a configuration file. The system of the invention completes the automatic obstacle crossing for various photovoltaic power generation plate obstacles. Therefore, manual intervention is reduced, the electric energy conversion efficiency is improved, and the maintenance cost is reduced.
Description
Technical Field
The invention belongs to the technical field of robots, and particularly relates to a robot obstacle crossing control system.
Background
The photovoltaic power generation equipment has large coverage area and is directly exposed to the external environment, so that the photovoltaic power generation equipment is greatly influenced by the environment. Dust, antenna, connection clearance are big, connect dislocation, surface deformation or protruding obstacle etc. are comparatively common influencing factors, directly influence photovoltaic power generation panel's generated energy and conversion efficiency. At present, many cleaning robots are low in intelligent degree, and can clean a plate surface, but are low in efficiency, and in many cases, when obstacles such as a photovoltaic power generation plate and an antenna which are spliced in a long distance are faced, the cleaning robots can only stop and can be completed by manual cooperation.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a photovoltaic intelligent cleaning robot obstacle crossing control system, which comprises an early warning analysis module, a light Fu Banmian sensing module, a photovoltaic side sensing module, a robot control module and a file system module; the early warning analysis module receives data of the light Fu Banmian sensing module and the photovoltaic side sensing module, sets a threshold value to carry out security level warning, and sends an output result to the robot control module to carry out obstacle avoidance treatment; the light Fu Banmian perception module is used for carrying out surface detection and obstacle detection and distance measurement at the same time; the photovoltaic side sensing module is used for detecting smoothness of a splicing opening; the robot control module performs normal passing, plate surface obstacle avoidance, side obstacle avoidance and emergency braking actions, and an intelligent cleaning function is realized by controlling the position and the stepping number of the cleaning robot pulley; the file system module includes a log and a configuration file. The system of the invention completes the automatic obstacle crossing for various photovoltaic power generation plate obstacles. Therefore, manual intervention is reduced, the electric energy conversion efficiency is improved, and the maintenance cost is reduced.
The technical scheme adopted by the invention for solving the technical problems comprises the following steps:
the obstacle crossing control system of the photovoltaic intelligent cleaning robot comprises an early warning analysis module, a light Fu Banmian perception module, a photovoltaic side perception module, a robot control module and a file system module;
the early warning analysis module receives data of the light Fu Banmian sensing module and the photovoltaic side sensing module, sets a threshold value to carry out security level warning, and sends an output result of the early warning analysis module to the robot control module to carry out obstacle avoidance treatment;
the light Fu Banmian sensing module adopts binocular vision to perform surface detection on the photovoltaic panel, performs obstacle detection and distance measurement at the same time, and sends detection results to the early warning analysis module;
the photovoltaic side face sensing module is used for detecting smoothness of a splicing opening of the photovoltaic panel by monocular vision and sending a detection result to the early warning analysis module;
the robot control module performs normal passing, board obstacle avoidance, side obstacle avoidance and emergency braking actions by receiving the data of the early warning analysis module, and achieves an intelligent cleaning function by controlling the position and the stepping number of the pulley of the cleaning robot;
the file system module comprises a log and a configuration file, wherein the log is used for recording data generated in the running process of the system and comprises time, content, executives, anomalies, identification results and processing results; the configuration file is used for dynamically configuring the photovoltaic panel sensing module and the early warning analysis module, wherein the configuration of the light Fu Banmian sensing module comprises the configuration of the identification category number and the model layer number; the configuration of the early warning analysis module comprises a switch of an obstacle avoidance option and setting of a threshold value.
Further, the result output by the early warning analysis module includes: normal passing, board obstacle avoidance, side obstacle avoidance and emergency braking.
Further, the content of the surface detection comprises chromatic aberration, broken gate, crack, non-erasable object, defect damage and welding spot oxidation spot; the obstacle detection includes a protrusion and a foreign matter; the distance measurement is the distance from the outline of the obstacle to the current detection mechanism.
Further, in the surface detection, firstly performing gray scale processing on an image containing chromatic aberration, broken grating, cracks, non-erasable objects, defect damage and welding spot oxidation spots, secondly performing contour extraction by adopting an edge detection operator, then performing binarization processing, and finally performing region extraction on the content of the surface detection by adopting a threshold segmentation algorithm on an abnormal region along a binary image region.
Further, in the surface detection, a depth random forest is adopted for target detection, sample data obtained after image segmentation is made into a label, then the depth random forest is input for detection model training, and the detection model is utilized for finishing the surface detection; the deep random forest can be used for classifying and distinguishing categories and can also provide detailed detection data for logs.
Further, the detection of the protrusions and the foreign matters adopts binocular vision to carry out three-dimensional reconstruction, the outline of the protrusions and the foreign matters is obtained, and the lengths of the protrusions and the foreign matters in the x direction, the y direction and the z direction are extracted to just surround the protrusions and the foreign matters.
Further, the distance measurement is specifically obtained by establishing a distance equation according to the distance from the center point of one surface of the obstacle along the cleaning direction to the double purpose and by adopting the triangle similarity principle.
Further, during smoothness detection, template making is performed in advance aiming at gaps, sharp points and burrs, and then a template matching algorithm is adopted for detection.
Further, the robot control module adopts a PID algorithm to control, and is matched with the early warning analysis module to control the cleaning robot pulley, so that obstacle avoidance and emergency braking are realized.
The beneficial effects of the invention are as follows:
the invention realizes the whole-course intellectualization of the obstacle crossing process of the photovoltaic power generation panel, the designed control system can save the manual labor, and the whole treatment process is safer and has high reliability.
Drawings
FIG. 1 is a block diagram of a system of the present invention.
Detailed Description
The invention will be further described with reference to the drawings and examples.
The invention provides a obstacle crossing control system of a photovoltaic intelligent cleaning robot, which is used for automatically crossing obstacles of various photovoltaic power generation plates through a machine vision technology and a mechanical structure. Therefore, manual intervention is reduced, the electric energy conversion efficiency is improved, and the maintenance cost is reduced.
As shown in fig. 1, the obstacle surmounting control system of the photovoltaic intelligent cleaning robot comprises the following functional modules:
early warning analysis module: the early warning analysis module receives data of the light Fu Banmian sensing module and the photovoltaic side sensing module, sets a threshold value to carry out security level warning, and sends output data to the robot control module to carry out obstacle avoidance processing. The result output by the early warning analysis module is that: normal passing, board obstacle avoidance, side obstacle avoidance and emergency braking.
Light Fu Banmian perception module: the photovoltaic panel sensing module adopts binocular vision to perform surface detection and simultaneously performs obstacle detection and ranging, wherein the surface comprises chromatic aberration, broken grids, cracks, non-erasable objects, defect damage and welding spot oxidation spots, the obstacle detection comprises bulges and foreign matters, and the ranging is mainly the distance from the outline of the obstacle to a current detection mechanism.
In surface detection, chromatic aberration, broken grating, cracks, non-erasable objects, defect damage and welding spot oxidation spots are firstly processed in gray scale by an image, then contour extraction is performed by an edge detection operator, then binarization processing is performed, finally a threshold segmentation algorithm is performed on an abnormal region along a binary image region, and region extraction is performed on surface elements.
The method comprises the steps of carrying out target detection by using a depth random forest, making labels on sample data obtained after image segmentation, inputting the depth random forest for detection model training, and then finishing surface detection by using the model, wherein the depth random forest can be used for classifying and distinguishing, and can also provide detailed detection data for a log system.
The detection of the bulge and the foreign matter mainly adopts binocular vision to carry out three-dimensional reconstruction, the outline of the bulge and the foreign matter is obtained, and the lengths of the bulge, the foreign matter in the x direction, the y direction, the z direction and the three directions are extracted to just surround the rectangle.
For distance measurement detection, a distance equation is established by adopting a triangle similarity principle according to the distance from a center store of one side of the bounding box along the cleaning direction to the dual purposes.
Photovoltaic side perception module: the photovoltaic side face sensing module adopts monocular vision to detect the smoothness of the splicing opening (the interface is compact and has no obvious gaps, sharp points or burrs), and the detection result is sent to the early warning analysis module.
And (3) making templates aiming at gaps, sharp points and burrs in advance, and detecting by adopting a template matching algorithm.
And the control module is used for: the control module is mainly used for normally passing through receiving data of the early warning analysis module, performing actions such as obstacle avoidance on the plate surface, obstacle avoidance on the side surface, emergency braking and the like, and realizing an intelligent cleaning function through controlling the position and the stepping number of the pulleys.
The control module adopts a known PID algorithm to control, and cooperates with the early warning analysis module to control the pulley, so that obstacle avoidance and emergency braking are realized.
A file system module: the file system module comprises a log and a configuration file, wherein the log is used for recording data generated in the running process of the system, including time, content, executives, anomalies, identification results and processing results, and the configuration file is used for carrying out dynamic configuration on the perception module and the early warning analysis module, and the perception module comprises identification category number and model layer number configuration; the early warning analysis module comprises a switch of an obstacle avoidance option and a threshold value.
Claims (9)
1. The obstacle crossing control system of the photovoltaic intelligent cleaning robot is characterized by comprising an early warning analysis module, a light Fu Banmian perception module, a photovoltaic side perception module, a robot control module and a file system module;
the early warning analysis module receives data of the light Fu Banmian sensing module and the photovoltaic side sensing module, sets a threshold value to carry out security level warning, and sends an output result of the early warning analysis module to the robot control module to carry out obstacle avoidance treatment;
the light Fu Banmian sensing module adopts binocular vision to perform surface detection on the photovoltaic panel, performs obstacle detection and distance measurement at the same time, and sends detection results to the early warning analysis module;
the photovoltaic side face sensing module is used for detecting smoothness of a splicing opening of the photovoltaic panel by monocular vision and sending a detection result to the early warning analysis module;
the robot control module performs normal passing, board obstacle avoidance, side obstacle avoidance and emergency braking actions by receiving the data of the early warning analysis module, and achieves an intelligent cleaning function by controlling the position and the stepping number of the pulley of the cleaning robot;
the file system module comprises a log and a configuration file, wherein the log is used for recording data generated in the running process of the system and comprises time, content, executives, anomalies, identification results and processing results; the configuration file is used for dynamically configuring the photovoltaic panel sensing module and the early warning analysis module, wherein the configuration of the light Fu Banmian sensing module comprises the configuration of the identification category number and the model layer number; the configuration of the early warning analysis module comprises a switch of an obstacle avoidance option and setting of a threshold value.
2. The obstacle surmounting control system for the intelligent photovoltaic cleaning robot according to claim 1, wherein the result output by the early warning analysis module comprises: normal passing, board obstacle avoidance, side obstacle avoidance and emergency braking.
3. The obstacle surmounting control system for a photovoltaic intelligent cleaning robot according to claim 1, wherein the content of the surface detection comprises chromatic aberration, broken grid, cracks, non-erasable objects, defect damage and welding spot oxidation spots; the obstacle detection includes a protrusion and a foreign matter; the distance measurement is the distance from the outline of the obstacle to the current detection mechanism.
4. The obstacle surmounting control system for a photovoltaic intelligent cleaning robot according to claim 3, wherein in the surface detection, an image containing chromatic aberration, broken grating, cracks, non-erasable objects, defect damage and welding spot oxidation spots is firstly subjected to gray scale processing, secondly subjected to contour extraction by an edge detection operator, then subjected to binarization processing, and finally subjected to region extraction on the surface detection content by a threshold segmentation algorithm along a binary image region.
5. The obstacle surmounting control system for the photovoltaic intelligent cleaning robot, which is characterized in that in the surface detection, a depth random forest is adopted for target detection, sample data obtained after image segmentation is made into a label, then the label is input into the depth random forest for detection model training, and the detection of the surface is completed by using a detection model; the deep random forest can be used for classifying and distinguishing categories and can also provide detailed detection data for logs.
6. The obstacle surmounting control system for the photovoltaic intelligent cleaning robot according to claim 3, wherein the detection of the protrusions and the foreign matters adopts binocular vision to carry out three-dimensional reconstruction, the outline of the protrusions and the foreign matters is obtained, and the lengths of the protrusions and the foreign matters in the x direction, the y direction and the z direction are extracted to just surround the rectangles of the protrusions and the foreign matters.
7. The obstacle surmounting control system for the photovoltaic intelligent cleaning robot according to claim 3, wherein the distance measurement is obtained by establishing a distance equation according to the principle of triangle similarity specifically from a center point of one surface of the obstacle along the cleaning direction to a double-purpose distance.
8. The obstacle surmounting control system for the photovoltaic intelligent cleaning robot according to claim 1, wherein during smoothness detection, template making is performed in advance for gaps, sharp points and burrs, and then detection is performed by adopting a template matching algorithm.
9. The obstacle surmounting control system of the photovoltaic intelligent cleaning robot according to claim 1, wherein the robot control module is controlled by a PID algorithm and is matched with the early warning analysis module to control the pulley of the cleaning robot, so that obstacle avoidance and emergency braking are realized.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310158628.3A CN116185028A (en) | 2023-02-23 | 2023-02-23 | Obstacle crossing control system of photovoltaic intelligent cleaning robot |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310158628.3A CN116185028A (en) | 2023-02-23 | 2023-02-23 | Obstacle crossing control system of photovoltaic intelligent cleaning robot |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116185028A true CN116185028A (en) | 2023-05-30 |
Family
ID=86436310
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310158628.3A Pending CN116185028A (en) | 2023-02-23 | 2023-02-23 | Obstacle crossing control system of photovoltaic intelligent cleaning robot |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116185028A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116505864A (en) * | 2023-06-25 | 2023-07-28 | 国家电投集团江西电力有限公司 | Photovoltaic panel cleaning and maintenance method used under narrow space condition |
-
2023
- 2023-02-23 CN CN202310158628.3A patent/CN116185028A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116505864A (en) * | 2023-06-25 | 2023-07-28 | 国家电投集团江西电力有限公司 | Photovoltaic panel cleaning and maintenance method used under narrow space condition |
CN116505864B (en) * | 2023-06-25 | 2023-10-20 | 国家电投集团江西电力有限公司 | Photovoltaic panel cleaning and maintenance method used under narrow space condition |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111754466B (en) | Intelligent detection method for damage condition of conveyor belt | |
CN116185028A (en) | Obstacle crossing control system of photovoltaic intelligent cleaning robot | |
CN111260629A (en) | Pantograph structure abnormity detection algorithm based on image processing | |
CN105181709A (en) | Combined multiple-light-source on-line detection device and method for appearance defects of brake pad | |
CN103308525B (en) | A kind of online test method for metal wire rod production and device | |
CN117152161B (en) | Shaving board quality detection method and system based on image recognition | |
CN115456999B (en) | Saw chain surface defect automatic detection system and defect detection method based on machine vision | |
CN107153067A (en) | A kind of surface defects of parts detection method based on MATLAB | |
CN112508911A (en) | Rail joint touch net suspension support component crack detection system based on inspection robot and detection method thereof | |
CN113470005A (en) | Welding spot detection device and welding spot detection method for cylindrical battery cap | |
CN114943704A (en) | Method, device and equipment for detecting defects of battery electrode die-cut piece | |
CN117252840B (en) | Photovoltaic array defect elimination evaluation method and device and computer equipment | |
CN117557570A (en) | Rail vehicle abnormality detection method and system | |
CN112557063A (en) | Vision-based tread detection system of straddle type single-track tire | |
CN115937683A (en) | High-altitude power transmission line foreign object target detection method and system based on laser obstacle clearing equipment | |
CN115106617A (en) | Scanning and tracking method for long weld joint in narrow space | |
CN113504243A (en) | Imaging device and imaging method for connecting area of contact net elastic sling and carrier cable | |
CN102310265B (en) | Method and device for detecting error for laser cutting processing system | |
CN112347858A (en) | Photovoltaic cleaning robot jamming detection method based on vision and pressure sensors | |
CN111054640A (en) | Automatic change mechanical detection device | |
CN113674213B (en) | Subway tunnel crack identification method based on rotating target detection technology | |
CN107607539A (en) | A kind of connecting rod is swollen cross section quality vision inspection apparatus and detection method | |
CN108861423A (en) | Belt conveyer electric control system based on PLC | |
Rodríguez-Araújo et al. | Automated in-line defect classification and localization in solar cells for laser-based repair | |
CN116087217B (en) | Industrial assembly line dynamic quality detection module and method based on machine vision |
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 |