CN111687858A - Photovoltaic cleaning robot with detect photovoltaic panel shading type - Google Patents
Photovoltaic cleaning robot with detect photovoltaic panel shading type Download PDFInfo
- Publication number
- CN111687858A CN111687858A CN202010569684.2A CN202010569684A CN111687858A CN 111687858 A CN111687858 A CN 111687858A CN 202010569684 A CN202010569684 A CN 202010569684A CN 111687858 A CN111687858 A CN 111687858A
- Authority
- CN
- China
- Prior art keywords
- brush
- photovoltaic
- mounting plate
- box
- photovoltaic panel
- 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 79
- 238000001514 detection method Methods 0.000 claims abstract description 25
- 239000004677 Nylon Substances 0.000 claims abstract description 24
- 229920001778 nylon Polymers 0.000 claims abstract description 24
- 239000013589 supplement Substances 0.000 claims description 16
- 238000009434 installation Methods 0.000 claims description 14
- 230000000712 assembly Effects 0.000 claims description 6
- 238000000429 assembly Methods 0.000 claims description 6
- 238000013461 design Methods 0.000 description 9
- 238000013527 convolutional neural network Methods 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 4
- 238000000034 method Methods 0.000 description 4
- 238000011176 pooling Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000006698 induction Effects 0.000 description 2
- 230000001502 supplementing effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J11/00—Manipulators not otherwise provided for
- B25J11/008—Manipulators for service tasks
- B25J11/0085—Cleaning
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
- B25J19/02—Sensing devices
- B25J19/021—Optical sensing devices
- B25J19/023—Optical sensing devices including video camera means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/141—Control of illumination
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02S—GENERATION OF ELECTRIC POWER BY CONVERSION OF INFRARED RADIATION, VISIBLE LIGHT OR ULTRAVIOLET LIGHT, e.g. USING PHOTOVOLTAIC [PV] MODULES
- H02S40/00—Components or accessories in combination with PV modules, not provided for in groups H02S10/00 - H02S30/00
- H02S40/10—Cleaning arrangements
-
- 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)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Photovoltaic Devices (AREA)
Abstract
The invention relates to a photovoltaic cleaning robot for detecting the shading type of a photovoltaic panel, which comprises a robot body, wherein the side wall of the front end of the robot body is fixedly provided with a photovoltaic panel shading detection device, the photovoltaic panel shading detection device is used for detecting the shading type of the photovoltaic panel in front of the photovoltaic cleaning robot, the photovoltaic panel shading detection device comprises an exposure main box and a hairbrush arranged at the bottom of the exposure main box, the exposure main box is fixedly arranged on the outer side wall of the front end of the robot body through a plurality of mounting holes arranged on the side wall of the exposure main box, a cavity is arranged in the exposure main box, the top end of the exposure main box is provided with a camera assembly, and the camera assembly comprises a camera module, camera drive plate and height adjustment nylon post, the fixed lower surface that sets up at the camera drive plate of camera module, the camera drive plate passes through height adjustment nylon post and sets up the top in exposure main box. The invention has the characteristics of simple structure, strong adaptability and high automation degree.
Description
Technical Field
The embodiment of the invention relates to the technical field of cleaning robots, in particular to a photovoltaic cleaning robot capable of detecting shading types of a photovoltaic panel.
Background
Solar photovoltaic has become an important power of energy revolution in the world as a renewable clean energy. The surface of the solar cell panel is easy to accumulate dirt such as wind sand, dust and the like, and if the solar cell panel is not timely cleaned scientifically and professionally, the generated power of the module is reduced by 40-60% to the maximum extent, and the generated energy is reduced by 20-30%. Therefore, the concept of improving the power generation capacity and the benefit of the power station by reasonably and scientifically cleaning the solar cell panel and carefully maintaining the components is accepted by the industry.
When the photovoltaic cleaning walking robot works, the process is basically full-automatic. At present, no mature movable detection mode exists in the market, and a specific sensing device or a fixing device is required to be added in a photovoltaic array for positioning so as to maintain the walking and cleaning of a machine on the photovoltaic array; and the more mature technology of autonomously selecting a cleaning route is to clean the direction manually and then perform N-shaped or Z-shaped path cleaning on the photovoltaic array which is vertically or horizontally distributed.
Such an induction mode and an automatic route planning by adding a specific induction device or a fixing device not only increase the equipment cost and reduce the efficiency because the equipment needs to return to the original site of the photovoltaic array after cleaning is completed every time, but also are easily influenced by the size and distribution of the photovoltaic array, and have poor applicability.
Disclosure of Invention
In view of the above problems in the prior art, a primary object of the present invention is to provide a photovoltaic cleaning robot capable of detecting shading patterns of a photovoltaic panel, which improves the automation degree of the photovoltaic cleaning robot, simplifies the detection structure of the photovoltaic cleaning robot, and improves the applicability of the photovoltaic cleaning robot, so that the photovoltaic cleaning robot can sense the relative pose of the photovoltaic cleaning robot on a photovoltaic array, provide a reliable basis for the automatic operation of the photovoltaic cleaning robot, save manpower, and reduce the maintenance cost of a power station.
The technical scheme of the invention is as follows:
a photovoltaic cleaning robot capable of detecting a photovoltaic panel shading type comprises a robot body, wherein a cleaning device is fixedly arranged at the front end of the robot body, the photovoltaic cleaning robot cleans a photovoltaic array through the cleaning device, a photovoltaic panel shading detection device is fixedly arranged on the side wall of the front end of the robot body and is used for detecting the photovoltaic panel shading type in front of the photovoltaic cleaning robot, the photovoltaic panel shading detection device comprises an exposure main box and a brush arranged at the bottom of the exposure main box, the exposure main box is fixedly arranged on the outer side wall of the front end of the robot body through a plurality of mounting holes formed in the side wall of the exposure main box, the exposure main box is square in shape, a cavity is arranged inside the exposure main box, and a camera component is arranged at the top end of the exposure main box, the camera subassembly includes camera module, camera drive plate and height adjustment nylon post, the camera module is fixed to be set up the lower surface of camera drive plate, the camera drive plate passes through height adjustment nylon post sets up the top of exposure owner box, just the camera module runs through the first locating hole that exposure owner box top set up is located in the cavity of exposure owner box.
The bottom of exposure owner box lateral wall outside extension all around is provided with the installation department, the installation department with the brush cooperatees, exposure owner box passes through the installation department sets up the top of brush.
The surface types of the photovoltaic panel comprise out-of-bounds, seam crossing, cell piece erecting and cell piece transverse placing.
The main box of exposure still includes light filling lamp subassembly, light filling lamp subassembly all includes the light filling lamp drive plate and sets up the light filling lamp of light filling lamp drive plate below, the light filling lamp drive plate pass through second fastening bolt with the top of the main box of exposure is connected, the upper end of light filling lamp is fixed to be set up in the light filling lamp drive plate, just the lower extreme of light filling lamp runs through in the second locating hole that sets up on the top of the main box of exposure to the inside extension of cavity of the main box of exposure.
The number of the light supplement lamp assemblies is four, and the four light supplement lamp assemblies are fixedly arranged at four corners of the top of the exposure main box respectively.
The installation department includes first mounting panel, second mounting panel, third mounting panel and fourth mounting panel, first mounting panel is fixed to be set up on the lateral wall of exposure owner box left side bottom, the second mounting panel is fixed to be set up on the lateral wall of exposure owner box front side bottom, the third mounting panel is fixed to be set up on the lateral wall of exposure owner box right side bottom, the fourth mounting panel is fixed to be set up the lateral wall of exposure owner box rear side bottom.
The plane of the lower surface of the first mounting plate, the second mounting plate, the third mounting plate and the fourth mounting plate and the plane of the bottom of the exposure main box are the same plane, and the first mounting plate, the second mounting plate, the third mounting plate and the fourth mounting plate and the exposure main box are integrally formed.
The hairbrush comprises a first hairbrush, a second hairbrush, a third hairbrush and a fourth hairbrush, wherein the first hairbrush, the second hairbrush, the third hairbrush and the fourth hairbrush are connected end to form a square structure with a square through hole in the middle;
the first brush is positioned below the first mounting plate, and the outer side wall of the first brush is flush with the outer side wall of the first mounting plate; the second brush is positioned below the second mounting plate, and the outer side wall of the second brush is positioned on the outer side wall of the second mounting plate and is flush with the outer side wall of the second mounting plate;
the third brush is positioned below the third mounting plate, and the outer side wall of the third brush is flush with the outer side wall of the third mounting plate; the fourth brush is located the below of fourth mounting panel, just the lateral wall of fourth brush is located the lateral wall parallel and level of fourth mounting panel.
The camera driving board is square, the camera module is fixedly arranged on the lower surface of the camera driving board, four corners of the camera driving board are respectively fixedly connected with the top end of the exposure main box through the height adjusting nylon columns, and the height adjusting nylon columns are respectively connected with the top end of the exposure main box and the camera driving board through first fastening bolts.
The plane of the upper surface of the first brush is parallel to the plane of the lower surface of the first mounting plate; the plane of the upper surface of the second brush is parallel to the plane of the lower surface of the second mounting plate; the plane of the upper surface of the third brush is parallel to the plane of the lower surface of the third mounting plate; the plane of the upper surface of the fourth brush is parallel to the plane of the lower surface of the fourth mounting plate.
The invention has the following advantages and beneficial effects: the embodiment of the invention provides a photovoltaic cleaning robot for detecting the shading type of a photovoltaic panel, which comprises a robot body, wherein a cleaning device is fixedly arranged at the front end of the robot body, the photovoltaic cleaning robot cleans a photovoltaic array through the cleaning device, a photovoltaic panel shading detection device is fixedly arranged on the side wall of the front end of the robot body and is used for detecting the shading type of the photovoltaic panel in front of the photovoltaic cleaning robot, the photovoltaic panel shading detection device comprises an exposure main box and a hairbrush arranged at the bottom of the exposure main box, the exposure main box is fixedly arranged on the outer side wall of the front end of the robot body through a plurality of mounting holes arranged on the side wall of the exposure main box, the exposure main box is square, a cavity is arranged in the exposure main box, a camera assembly is arranged at the top end of the exposure main box, and the camera assembly comprises a camera, a camera driving plate and a height adjusting nylon column, the camera module is fixedly arranged on the lower surface of the camera driving board, the camera driving board is arranged above the top end of the exposure main box through a height adjusting nylon column, and the camera module penetrates through a first positioning hole formed in the top end of the exposure main box and is located in a cavity of the exposure main box; through the design, the photovoltaic cleaning robot can detect the shading on the surface of the photovoltaic panel through the photovoltaic panel shading detection device fixedly arranged on the side wall of the front end of the robot body in the cleaning operation process so as to judge the surface type (namely boundary-out, seam crossing, vertical placement of the battery piece and transverse placement of the battery piece) of the photovoltaic panel in front of the photovoltaic cleaning robot at present and provide detection data for the photovoltaic cleaning robot, thereby realizing continuous automatic control and stable operation; in addition, the automation degree of the photovoltaic cleaning robot can be improved, the detection structure of the photovoltaic cleaning robot is simplified, the applicability of the photovoltaic cleaning robot is improved, the photovoltaic cleaning robot can sense the relative pose of the photovoltaic cleaning robot on a photovoltaic array, a reliable basis is provided for the automatic operation of the photovoltaic cleaning robot, the manpower is saved, and the maintenance cost of a power station is reduced.
Drawings
Fig. 1 is a schematic perspective view of a device for detecting a shading of a photovoltaic panel in a photovoltaic cleaning robot according to an embodiment of the present invention.
Fig. 2 is an exploded schematic view of a device for detecting a shading of a photovoltaic panel in a photovoltaic cleaning robot according to an embodiment of the present invention.
Fig. 3 is a schematic perspective view of a photovoltaic cleaning robot with a shading detection function for detecting a shading of a photovoltaic panel according to an embodiment of the present invention.
Fig. 4 is a schematic perspective view of another direction of a photovoltaic cleaning robot capable of detecting a shading type of a photovoltaic panel according to an embodiment of the present invention.
Fig. 5 is a schematic top view of a device for detecting a shading of a photovoltaic panel in a photovoltaic cleaning robot having a type of detecting a shading of a photovoltaic panel according to an embodiment of the present invention.
Fig. 6 is a schematic diagram illustrating a type of shading on a surface of a photovoltaic panel out of bounds according to an embodiment of the present invention.
Fig. 7 is a schematic diagram of a photovoltaic panel provided by an embodiment of the invention, wherein the surface shading is a cross-slit type.
Fig. 8 is a schematic view of the type of the surface shading of the photovoltaic panel provided by the embodiment of the invention being a vertical arrangement of the photovoltaic panel.
Fig. 9 is a schematic view of a photovoltaic panel with a horizontal shading type on the surface according to an embodiment of the present invention.
Fig. 10 is a schematic structural diagram of a convolutional neural network according to an embodiment of the present invention.
Detailed Description
The invention will be further described with reference to the drawings and specific examples.
As shown in fig. 1 to 10: the photovoltaic cleaning robot with the function of detecting the shading type of the photovoltaic panel comprises a body 100, wherein a cleaning device 101 is fixedly arranged at the front end of the body 100, the photovoltaic cleaning robot cleans a photovoltaic array through the cleaning device, a photovoltaic panel shading detection device 300 is fixedly arranged on the side wall of the front end of the body 100, the photovoltaic panel shading detection device 300 is used for detecting the shading type of the photovoltaic panel in front of the photovoltaic cleaning robot, the photovoltaic panel shading detection device comprises an exposure main box and a brush arranged at the bottom of the exposure main box, the exposure main box is fixedly arranged on the outer side wall of the front end of the body through a plurality of mounting holes arranged on the side wall of the exposure main box, the exposure main box 301 is square, and a cavity (not shown in the figure) is arranged inside the exposure main box 301, the lower extreme of exposure main box 301 is provided with the opening, just the cavity with the opening is linked together, the top of exposure main box 301 is provided with camera subassembly, camera subassembly includes camera module 303, camera drive plate 304 and height adjustment nylon column 305, camera module 303 is fixed to be set up the lower surface of camera drive plate 304, camera drive plate 304 passes through height adjustment nylon column 305 sets up the top of exposure main box 301, just camera module 303 runs through the first locating hole 306 that exposure main box 301 top set up is located in the cavity of exposure main box 301.
The bottom of exposure owner box 301 is lateral wall outside extension all around and is provided with the installation department, the installation department with the brush cooperatees, exposure owner box 301 passes through the installation department sets up the top of brush. Through the above design, the outer side wall outwards extends around the bottom of main exposure box 301 to be provided with the installation department, and the structure phase-match of installation department and brush 302 to can make main exposure box 301 pass through the installation department setting and be in the top of brush 302 and closely cooperate. Through the above design, that is, the lower end of the exposure box 300 is provided with the brush, and the plane where the bottom end of the brush is located and the plane where the bottom end of the machine body 100 is located are the same plane, so that the brush and the bottom of the exposure box 300 can be tightly fitted and installed; when the photovoltaic cleaning robot carries out the in-process of cleaning operation on the photovoltaic panel of photovoltaic array, the cavity of exposure box 300 passes through and forms the environment that is sealed relatively between brush and the upper surface of photovoltaic panel to guarantee exposure box 300's exposure effect, still can reduce the influence that external environment shot to the camera subassembly of exposure box 300 top installation to the at utmost simultaneously, thereby guarantee the stability of shooting the environment.
The surface types of the photovoltaic panel comprise out-of-bounds, seam crossing, cell piece erecting and cell piece transverse placing. The photovoltaic panel in front of the photovoltaic cleaning robot is positioned at the edge of the photovoltaic array when out of bounds, and the photovoltaic panel falls off the photovoltaic array when the photovoltaic cleaning robot continues to walk forwards. The photovoltaic panel that strides seam for photovoltaic cleaning machines people the place ahead is in the rear end edge of one photovoltaic panel in the photovoltaic array, is in the photovoltaic array simultaneously and adjacent rather than the front end edge of another photovoltaic panel that is located its place ahead, when photovoltaic cleaning machines people continues to walk forward, will stride from the gap between the two adjacent photovoltaic panels that are located its place ahead.
The main box 301 of exposure still includes light filling lamp subassembly, the light filling lamp subassembly includes light filling lamp drive plate 321 and sets up light filling lamp 317 of light filling lamp drive plate 321 below, light filling lamp drive plate 321 through second fastening bolt 350 with the top of the main box 301 of exposure is connected, the upper end of light filling lamp 317 is fixed to be set up in the light filling lamp drive plate 321, just the lower extreme of light filling lamp 317 runs through in the second locating hole 322 that sets up on the top of the main box 301 of exposure to the inside extension of cavity of the main box 301 of exposure. Through the above design, also be provided with four light filling lamp subassemblies on the photovoltaic panel shading detection device 300, and every the light filling lamp subassembly all includes light filling lamp drive plate 321 and sets up the light filling lamp 317 of light filling lamp drive plate 321 below, light filling lamp drive plate 321 is connected with the top of exposing main box 301 through second fastening bolt 350, and the fixed setting in light filling lamp drive plate 321 in upper end of light filling lamp 317, and the lower extreme of light filling lamp 317 runs through to the inside extension of cavity to exposing main box 301 in the second locating hole 322 that sets up on the top of exposing main box 301 to reach the purpose of conveniently adjusting and later maintenance.
The number of the light supplement lamp assemblies is four, and the four light supplement lamp assemblies are respectively and fixedly arranged at four corners of the top of the exposure main box 301. Through the above design, a light supplement lamp assembly is respectively disposed at four corners of the top of the main exposure box 301, so that the exposure effect of the main exposure box 301 can be improved.
The mounting portion includes a first mounting plate 337, a second mounting plate 338, a third mounting plate 339, and a fourth mounting plate (not shown in the figures), wherein:
the first mounting plate 337 is fixedly arranged on the outer side wall of the bottom of the left side of the exposure main box 301, the second mounting plate 338 is fixedly arranged on the outer side wall of the bottom of the front side of the exposure main box 301, the third mounting plate 339 is fixedly arranged on the outer side wall of the bottom of the right side of the exposure main box 301, and the fourth mounting plate is fixedly arranged on the outer side wall of the bottom of the rear side of the exposure main box 301;
the plane of the lower surfaces of the first mounting plate 337, the second mounting plate 338, the third mounting plate 339 and the fourth mounting plate is the same plane as the plane of the bottom of the exposure main box 301, and the first mounting plate 337, the second mounting plate 338, the third mounting plate 339 and the fourth mounting plate are integrally formed with the exposure main box 301.
Through the above design, the plane of the lower surfaces of the first mounting plate 337, the second mounting plate 338, the third mounting plate 339 and the fourth mounting plate and the plane of the bottom of the exposure main box 301 are the same plane, so that the upper end of the hairbrush 302 can be tightly matched with the lower ends of the first mounting plate 337, the second mounting plate 338, the third mounting plate 339 and the fourth mounting plate, and the cavity in the exposure main box 301 can be in a relatively closed environment; meanwhile, because the first mounting plate 337, the second mounting plate 338, the third mounting plate 339 and the fourth mounting plate and the main exposure box 301 are integrally formed, the firmness of the mounting part, that is, the first mounting plate 337, the second mounting plate 338, the third mounting plate 339 and the fourth mounting plate, which are combined with the main exposure box 301 can be improved, and the service life of the main exposure box 301 can be prolonged.
The brush 302 comprises a first brush 311, a second brush 312, a third brush 313 and a fourth brush 314, and the first brush 311, the second brush 312, the third brush 313 and the fourth brush 314 are connected end to form a square structure with a through hole 315 in the middle; the first brush 311 is positioned below the first mounting plate 337, and the outer side wall of the first brush 311 is flush with the outer side wall of the first mounting plate 337; the second brush 312 is positioned below the second mounting plate 338, and the outer side wall of the second brush 312 is flush with the outer side wall of the second mounting plate 338; the third brush 313 is positioned below the third mounting plate 339, and the outer side wall of the third brush 313 is flush with the outer side wall of the third mounting plate 339; the fourth brush 314 is located below the fourth mounting plate, and the outer sidewall of the fourth brush 314 is flush with the outer sidewall of the fourth mounting plate.
Through the above design, also be brush 302 by first brush 311, second brush 312, third brush 313 and fourth brush 314 end to end connection form, and the middle square structure that is through-hole 315 in the middle of forming, thereby it is inseparabler with the structure phase-match and the cooperation of exposure main box 301, and make things convenient for the maintenance in equipment and the later stage in earlier stage, still can improve first brush 311 simultaneously, second brush 312, the fastness that third brush 313 and fourth brush 314 combined together, and then improve fail safe nature, in order to prolong this brush 302 and photovoltaic cleaning machines people's life.
The camera driving board 304 is square, the camera module 303 is fixedly disposed on the lower surface of the camera driving board 304, four corners of the camera driving board 304 are fixedly connected to the top end of the main exposure box 301 through the height adjusting nylon columns 305, and the height adjusting nylon columns 305 are connected to the top end of the main exposure box 301 and the camera driving board 304 through the first fastening bolts 340.
Through the above design, that is, the number of the height-adjusting nylon columns 305 is four, the height-adjusting nylon columns 305 are respectively located at four corners of the camera driving board 304, fixing holes are formed in the height-adjusting nylon columns 305, the lower ends of the height-adjusting nylon columns 305 are fixedly connected with the exposure main box 301 through fixing screws 315, and the firmness of the combination of the height-adjusting nylon columns 305 and the exposure main box 301 can be improved; meanwhile, the height-adjusting nylon column 305 is respectively connected with the top end of the exposure box body 301 and the camera driving plate 304 through a first fastening bolt 340, so that the firmness of the combination of the height-adjusting nylon column 305 with the exposure box body 301 and the camera driving plate 304 is improved; in addition, the distance between the camera driving board 304 and the top end of the exposure main box 301 can be adjusted through the four height adjusting nylon columns 305, so that the distance between the camera module 303 and the surface of the photovoltaic panel in the photovoltaic array where the body 100 is located can be adjusted, and the operation is convenient and rapid.
The camera module 304 in the above-mentioned shading detection device 300 for photovoltaic panel adopts a high-speed camera module with 480P60 frames, and is placed right above a relatively airtight space by adopting a certain light supplementing mode, and the shading detection device 300 for photovoltaic panel is placed right in front of the photovoltaic cleaning robot.
The plane of the upper surface of the first brush 311 is parallel to the plane of the lower surface of the first mounting plate 337; the plane of the upper surface of the second brush 312 is parallel to the plane of the lower surface of the second mounting plate 338; the plane of the upper surface of the third brush 313 is parallel to the plane of the lower surface of the third mounting plate 339; the plane of the upper surface of the fourth brush 314 is parallel to the plane of the lower surface of the fourth mounting plate. Through the above design, the plane on which the upper surfaces of the brushes (i.e., the first brush 311, the second brush 312, the third brush 313 and the fourth brush 314) are located and the plane on which the lower surfaces of the mounting portions (i.e., the first mounting plate 337, the second mounting plate 338, the third mounting plate 339 and the fourth mounting plate) are located are parallel to each other, so that the brushes and the mounting portions can be tightly fitted.
The photovoltaic panel shading detection device 300 provided by the embodiment of the invention adopts a 480P60 frame high-speed camera module 303, and is arranged right in front of a machine, and the photovoltaic panel shading detection device is placed right above a relatively closed space in a certain light supplementing mode. The method comprises the steps of dynamically recording images under 4 conditions of boundary-out, seam crossing, cell piece vertical direction and cell piece transverse direction relative to a photovoltaic panel through a high-speed camera module, carrying out enhancement processing such as random cutting, rotation, scaling and horizontal turning on the images, and finally uniformly classifying the images into three categories of boundary-out or seam crossing, vertical placement relative to the cell pieces and horizontal placement relative to the cell pieces, and uniformly scaling the images into an RGB image data set with the size of 64 x 3.
A 7-layer convolutional neural network model was constructed, which was input to 64 × 3 RGB pictures, first passed through the first layer of 8 3 × 3 same convolution filters, convolutional layer Conv, and then through the pooling layer maxpool. Then the second layer is the convolutional layer of 16 3 by 3 same convolution filters, and then passes through the pooling layer. The third layer was then a convolution layer of 32 3 by 3 same convolution filters, followed by pooling layers. The fourth layer was then the convolutional layer of 64 3 by 3 same convolution filters, and then passed through the pooling layer. The fifth layer is a full-connection layer FC with 64 units, the sixth layer is a full-connection layer with 32 units, the last layer is expanded into full-connection layers with 3 types of output units, then the probability of 3 types of output units is calculated through a softmax regression unit, and the unit with the maximum probability is found out, namely the unit corresponding to the shading of the photovoltaic panel right in front of the current photovoltaic cleaning robot. The 7-layer convolutional neural network VGGNet-7 is subjected to deep learning training by utilizing the image data set, a good identification model is obtained, and the size of the model data is light to 505 KB.
Under the condition that the surface type of the photovoltaic panel needs to be sensed in the cleaning operation of the photovoltaic cleaning robot, the surface type of the front photovoltaic panel can be quickly judged only by inputting the latest picture shot by the high-speed camera module into the predicted convolutional neural network VGGNet-7 model. When the model identifies that the type of the shading of the photovoltaic panel is out of bounds or across seams, the photovoltaic cleaning robot is indicated to be in an out of bounds or across seams state, and the photovoltaic cleaning robot is fed back to the master control system in real time to enable the master control system to make data fusion or brake preparation in real time; when the type of the shading of the photovoltaic panel is identified by the model to be the condition of vertical arrangement relative to the battery piece, the photovoltaic cleaning robot is in a position parallel to the long edge of the photovoltaic panel at present; and when the type of the shading of the photovoltaic panel is identified by the model to be transverse relative to the battery piece, the photovoltaic cleaning robot is in a position parallel to the short edge of the photovoltaic panel.
Finally, it should be noted that: the above embodiments are only used for illustrating the technical solution of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. The utility model provides a photovoltaic cleaning machines people with detect photovoltaic panel shading type, photovoltaic cleaning machines people includes the fuselage, the front end of fuselage is fixed with cleaning device, photovoltaic cleaning machines people passes through cleaning device cleans the operation, its characterized in that to photovoltaic array: the fixed photovoltaic panel shading detection device that is provided with of front end lateral wall of fuselage, the fixed photovoltaic panel shading detection device that is used for detecting the photovoltaic panel shading type in front of the photovoltaic cleaning robot, the photovoltaic panel shading detection device includes exposure owner box and sets up the brush in exposure owner box bottom, a plurality of mounting holes that exposure owner box set up through its lateral wall are fixed to be set up on the lateral wall of fuselage front end, the shape of exposure owner box is square, and the inside cavity that is provided with of exposure owner box, the top of exposure owner box is provided with the camera subassembly, the camera subassembly includes camera module, camera drive plate and height adjustment nylon post, the camera module is fixed to be set up in the lower surface of camera drive plate, the camera drive plate passes through height adjustment nylon post and sets up in the top of exposure owner box, and the camera module penetrates through a first positioning hole arranged at the top end of the exposure main box and is positioned in the cavity of the exposure main box.
2. The photovoltaic cleaning robot capable of detecting the shading type of the photovoltaic panel as claimed in claim 1, wherein an installation part extends outwards from the outer side wall of the periphery of the bottom of the main exposure box, the installation part is matched with the brush, and the main exposure box is arranged on the top of the brush through the installation part.
3. The photovoltaic cleaning robot with the type of detecting the shading of the photovoltaic panel as recited in claim 1, wherein the surface types of the photovoltaic panel include out-of-bounds, across seams, cell pieces standing up, and cell pieces lying down.
4. The photovoltaic cleaning robot capable of detecting the shading type of the photovoltaic panel as claimed in claim 2, wherein the main exposure box further comprises a light supplement lamp assembly, the light supplement lamp assembly comprises a light supplement lamp driving board and a light supplement lamp arranged below the light supplement lamp driving board, the light supplement lamp driving board is connected with the top end of the main exposure box through a second fastening bolt, the upper end of the light supplement lamp is fixedly arranged in the light supplement lamp driving board, and the lower end of the light supplement lamp penetrates through a second positioning hole formed in the top end of the main exposure box and extends into the cavity of the main exposure box.
5. The photovoltaic cleaning robot capable of detecting the shading type of the photovoltaic panel as claimed in claim 4, wherein the number of the light supplement lamp assemblies is four, and the four light supplement lamp assemblies are respectively and fixedly arranged at four corners of the top of the main exposure box.
6. The photovoltaic cleaning robot with the shading detection function for the photovoltaic panel as claimed in claim 4, wherein the mounting portion comprises a first mounting plate, a second mounting plate, a third mounting plate and a fourth mounting plate, the first mounting plate is fixedly arranged on the outer side wall of the left bottom of the main exposure box, the second mounting plate is fixedly arranged on the outer side wall of the front bottom of the main exposure box, the third mounting plate is fixedly arranged on the outer side wall of the right bottom of the main exposure box, and the fourth mounting plate is fixedly arranged on the outer side wall of the rear bottom of the main exposure box.
7. The photovoltaic cleaning robot capable of detecting the shading of the photovoltaic panel as claimed in claim 6, wherein the lower surfaces of the first, second, third and fourth mounting plates are located on the same plane as the bottom of the main exposure box, and the first, second, third and fourth mounting plates are integrally formed with the main exposure box.
8. The photovoltaic cleaning robot capable of detecting the shading type of the photovoltaic panel as claimed in claim 6, wherein the brushes comprise a first brush, a second brush, a third brush and a fourth brush, and the first brush, the second brush, the third brush and the fourth brush are connected end to form a square structure with a square through hole in the middle;
the first brush is positioned below the first mounting plate, and the outer side wall of the first brush is flush with the outer side wall of the first mounting plate; the second brush is positioned below the second mounting plate, and the outer side wall of the second brush is positioned on the outer side wall of the second mounting plate and is flush with the outer side wall of the second mounting plate;
the third brush is positioned below the third mounting plate, and the outer side wall of the third brush is flush with the outer side wall of the third mounting plate; the fourth brush is located the below of fourth mounting panel, just the lateral wall of fourth brush is located the lateral wall parallel and level of fourth mounting panel.
9. The photovoltaic cleaning robot capable of detecting the shading type of the photovoltaic panel as claimed in claim 4, wherein the camera driving board is square, the camera module is fixedly disposed on the lower surface of the camera driving board, four corners of the camera driving board are fixedly connected to the top end of the main exposure box through the height adjusting nylon columns, respectively, and the height adjusting nylon columns are connected to the top end of the main exposure box and the camera driving board through first fastening bolts, respectively.
10. The photovoltaic cleaning robot of the type for detecting shading in a photovoltaic panel as recited in claim 8, wherein the upper surface of the first brush is disposed in a plane parallel to a plane of the lower surface of the first mounting plate; the plane of the upper surface of the second brush is parallel to the plane of the lower surface of the second mounting plate; the plane of the upper surface of the third brush is parallel to the plane of the lower surface of the third mounting plate; the plane of the upper surface of the fourth brush is parallel to the plane of the lower surface of the fourth mounting plate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010569684.2A CN111687858A (en) | 2020-06-20 | 2020-06-20 | Photovoltaic cleaning robot with detect photovoltaic panel shading type |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010569684.2A CN111687858A (en) | 2020-06-20 | 2020-06-20 | Photovoltaic cleaning robot with detect photovoltaic panel shading type |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111687858A true CN111687858A (en) | 2020-09-22 |
Family
ID=72482530
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010569684.2A Pending CN111687858A (en) | 2020-06-20 | 2020-06-20 | Photovoltaic cleaning robot with detect photovoltaic panel shading type |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111687858A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113083778A (en) * | 2021-05-03 | 2021-07-09 | 深圳怪虫机器人有限公司 | Self-cleaning device for cleaning camera on robot |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2957397A2 (en) * | 2014-06-20 | 2015-12-23 | Ricoh Company, Ltd. | Measurement system, object pickup system, measurement method, and carrier means |
| KR20180092383A (en) * | 2017-02-09 | 2018-08-20 | 유진기술 주식회사 | Solar photovoltaic panels cleaning robot system |
| WO2019076005A1 (en) * | 2017-10-20 | 2019-04-25 | 苏州瑞得恩光能科技有限公司 | Edge positioning apparatus for solar panel cleaning robot, and positioning method thereof |
| CN110112999A (en) * | 2019-06-06 | 2019-08-09 | 深圳怪虫机器人有限公司 | A kind of method of the robot autonomous selection cleaning route of photovoltaic |
| CN209460646U (en) * | 2019-04-28 | 2019-10-01 | 河海大学常州校区 | A kind of robot cleaner for photovoltaic module hardware system |
| CN110882971A (en) * | 2019-11-22 | 2020-03-17 | 深圳怪虫机器人有限公司 | Photovoltaic cleaning robot with distributed adsorption assembly |
| CN110882970A (en) * | 2019-11-22 | 2020-03-17 | 深圳怪虫机器人有限公司 | Photovoltaic cleaning robot with photovoltaic board detection component |
| CN110919666A (en) * | 2019-11-22 | 2020-03-27 | 深圳怪虫机器人有限公司 | Photovoltaic cleaning robot capable of automatically cleaning |
| CN216731824U (en) * | 2020-06-20 | 2022-06-14 | 深圳怪虫机器人有限公司 | Photovoltaic cleaning robot with detect photovoltaic panel shading type |
-
2020
- 2020-06-20 CN CN202010569684.2A patent/CN111687858A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2957397A2 (en) * | 2014-06-20 | 2015-12-23 | Ricoh Company, Ltd. | Measurement system, object pickup system, measurement method, and carrier means |
| KR20180092383A (en) * | 2017-02-09 | 2018-08-20 | 유진기술 주식회사 | Solar photovoltaic panels cleaning robot system |
| WO2019076005A1 (en) * | 2017-10-20 | 2019-04-25 | 苏州瑞得恩光能科技有限公司 | Edge positioning apparatus for solar panel cleaning robot, and positioning method thereof |
| CN209460646U (en) * | 2019-04-28 | 2019-10-01 | 河海大学常州校区 | A kind of robot cleaner for photovoltaic module hardware system |
| CN110112999A (en) * | 2019-06-06 | 2019-08-09 | 深圳怪虫机器人有限公司 | A kind of method of the robot autonomous selection cleaning route of photovoltaic |
| CN110882971A (en) * | 2019-11-22 | 2020-03-17 | 深圳怪虫机器人有限公司 | Photovoltaic cleaning robot with distributed adsorption assembly |
| CN110882970A (en) * | 2019-11-22 | 2020-03-17 | 深圳怪虫机器人有限公司 | Photovoltaic cleaning robot with photovoltaic board detection component |
| CN110919666A (en) * | 2019-11-22 | 2020-03-27 | 深圳怪虫机器人有限公司 | Photovoltaic cleaning robot capable of automatically cleaning |
| CN216731824U (en) * | 2020-06-20 | 2022-06-14 | 深圳怪虫机器人有限公司 | Photovoltaic cleaning robot with detect photovoltaic panel shading type |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113083778A (en) * | 2021-05-03 | 2021-07-09 | 深圳怪虫机器人有限公司 | Self-cleaning device for cleaning camera on robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110882970B (en) | Photovoltaic cleaning robot with photovoltaic panel detection assembly | |
| CN111687859A (en) | Method for acquiring optimal operation path by photovoltaic cleaning robot | |
| CN104467649A (en) | Photovoltaic module automatic sweeping device | |
| CN111687860A (en) | Method for photovoltaic cleaning robot to autonomously select cleaning operation path | |
| CN111687857A (en) | Photovoltaic cleaning robot capable of identifying photovoltaic array placement mode | |
| JP2020518072A (en) | Edge positioning device for solar panel cleaning robot and positioning method thereof | |
| WO2022267336A1 (en) | Photovoltaic cleaning robot based on visual slam | |
| CN216731824U (en) | Photovoltaic cleaning robot with detect photovoltaic panel shading type | |
| CN216731823U (en) | Photovoltaic cleaning robot capable of identifying photovoltaic array placement mode | |
| CN111687858A (en) | Photovoltaic cleaning robot with detect photovoltaic panel shading type | |
| CN111687856A (en) | Method for acquiring linear operation path by photovoltaic cleaning robot | |
| CN106272336A (en) | A kind of intelligent cleaning robot device for photovoltaic battery panel group and the localization method of cleaning robot | |
| CN111266325B (en) | Method for cleaning robot to constantly follow long-edge zigzag cleaning path | |
| CN114226323A (en) | Intelligent robot suitable for operation and maintenance dust removal of photovoltaic power station and control method | |
| CN216880648U (en) | Intelligent robot suitable for cleaning dust of operation and maintenance of photovoltaic power station | |
| CN211070997U (en) | Photovoltaic cleaning robot with photovoltaic board detection component | |
| CN115889271B (en) | Photovoltaic cleaning method combined with unmanned aerial vehicle | |
| CN116388669A (en) | Photovoltaic panel foreign matter detection and cleaning method based on Swin transducer | |
| Chellal et al. | Innovative robot design for cleaning solar panels | |
| CN210253241U (en) | Automatic change photovoltaic power plant of perpendicular two-way walking control and clean robot | |
| CN211137133U (en) | Patrol and examine robot and remove and use drive base | |
| CN109382346B (en) | Control method of intelligent absorbing and storing system of solar cell panel | |
| Balamurugan et al. | Integrated IoT System for Automatic Dust Cleaning of Solar Panels | |
| CN110224671B (en) | Output-stable high-efficiency photovoltaic cell assembly | |
| CN220986475U (en) | Sensing and positioning device for detecting photovoltaic module |
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 |