CN112621487B - Wall-climbing polishing device based on brain-computer control and control method thereof - Google Patents
Wall-climbing polishing device based on brain-computer control and control method thereof Download PDFInfo
- Publication number
- CN112621487B CN112621487B CN202011279972.0A CN202011279972A CN112621487B CN 112621487 B CN112621487 B CN 112621487B CN 202011279972 A CN202011279972 A CN 202011279972A CN 112621487 B CN112621487 B CN 112621487B
- Authority
- CN
- China
- Prior art keywords
- polishing
- wall
- climbing
- brain
- robot
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000005498 polishing Methods 0.000 title claims description 149
- 238000000227 grinding Methods 0.000 claims abstract description 43
- 230000009193 crawling Effects 0.000 claims abstract description 21
- 238000012545 processing Methods 0.000 claims abstract description 15
- 238000004891 communication Methods 0.000 claims abstract description 14
- 210000003128 head Anatomy 0.000 claims description 39
- 210000004556 brain Anatomy 0.000 claims description 19
- 239000011521 glass Substances 0.000 claims description 13
- 230000009194 climbing Effects 0.000 claims description 12
- 230000005540 biological transmission Effects 0.000 claims description 11
- 238000012634 optical imaging Methods 0.000 claims description 10
- 239000000463 material Substances 0.000 claims description 7
- 210000004761 scalp Anatomy 0.000 claims description 6
- 230000005611 electricity Effects 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 abstract description 6
- 239000000428 dust Substances 0.000 abstract description 4
- 230000000694 effects Effects 0.000 abstract description 3
- 239000000383 hazardous chemical Substances 0.000 abstract 1
- 231100000206 health hazard Toxicity 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 9
- 238000004519 manufacturing process Methods 0.000 description 6
- 238000013507 mapping Methods 0.000 description 6
- 241000252254 Catostomidae Species 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 210000003710 cerebral cortex Anatomy 0.000 description 3
- 238000009795 derivation Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- BQCADISMDOOEFD-UHFFFAOYSA-N Silver Chemical compound [Ag] BQCADISMDOOEFD-UHFFFAOYSA-N 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 239000011248 coating agent Substances 0.000 description 2
- 238000000576 coating method Methods 0.000 description 2
- 239000000306 component Substances 0.000 description 2
- 230000003750 conditioning effect Effects 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 239000003365 glass fiber Substances 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 239000003973 paint Substances 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 238000007517 polishing process Methods 0.000 description 2
- 230000001953 sensory effect Effects 0.000 description 2
- 229910052709 silver Inorganic materials 0.000 description 2
- 239000004332 silver Substances 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000003321 amplification Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000017531 blood circulation Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 210000004720 cerebrum Anatomy 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 239000003822 epoxy resin Substances 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 230000004060 metabolic process Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 210000000869 occipital lobe Anatomy 0.000 description 1
- 230000001936 parietal effect Effects 0.000 description 1
- 229920000647 polyepoxide Polymers 0.000 description 1
- 229920002689 polyvinyl acetate Polymers 0.000 description 1
- 239000011118 polyvinyl acetate Substances 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 229920005989 resin Polymers 0.000 description 1
- 239000011347 resin Substances 0.000 description 1
- 150000003378 silver Chemical class 0.000 description 1
- 238000005507 spraying Methods 0.000 description 1
- 239000007785 strong electrolyte Substances 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B24—GRINDING; POLISHING
- B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
- B24B19/00—Single-purpose machines or devices for particular grinding operations not covered by any other main group
- B24B19/14—Single-purpose machines or devices for particular grinding operations not covered by any other main group for grinding turbine blades, propeller blades or the like
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B24—GRINDING; POLISHING
- B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
- B24B27/00—Other grinding machines or devices
- B24B27/0007—Movable machines
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B24—GRINDING; POLISHING
- B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
- B24B49/00—Measuring or gauging equipment for controlling the feed movement of the grinding tool or work; Arrangements of indicating or measuring equipment, e.g. for indicating the start of the grinding operation
- B24B49/12—Measuring or gauging equipment for controlling the feed movement of the grinding tool or work; Arrangements of indicating or measuring equipment, e.g. for indicating the start of the grinding operation involving optical means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B24—GRINDING; POLISHING
- B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
- B24B51/00—Arrangements for automatic control of a series of individual steps in grinding a workpiece
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
一种基于脑机控制的爬壁打磨装置及其控制方法，其中装置包括激光雷达、爬壁打磨机器人、虚拟现实设备、控制器和通讯模块；激光雷达对待打磨设备的外形进行三维重建以生成三维地图；爬壁打磨机器人在待打磨设备的壁面上进行爬行及打磨，采集并反馈实时打磨数据及图像信息，以及根据三维地图生成爬行及打磨轨迹；虚拟现实设备用于显示由爬壁打磨机器人回传的实时打磨数据及图像信息；非侵入式脑机穿戴设备用于采集电波信号并生成脑电信号；控制器用于根据非侵入式脑机穿戴设备产生的脑电信号对爬壁打磨机器人的爬行及打磨轨迹进行调整。本发明杜绝了打磨过程中产生的粉尘对工作人员的健康危害，大大提高了风电叶片打磨的精度和局部细节的处理效果。
A wall-climbing grinding device based on brain-computer control and a control method thereof, wherein the device comprises a laser radar, a wall-climbing grinding robot, a virtual reality device, a controller and a communication module; the laser radar performs three-dimensional reconstruction of the shape of the device to be polished to generate a three-dimensional Map; the wall-climbing grinding robot crawls and grinds on the wall of the equipment to be polished, collects and feeds back real-time grinding data and image information, and generates crawling and grinding trajectories according to the three-dimensional map; virtual reality equipment is used to display the return from the wall-climbing grinding robot. The real-time grinding data and image information transmitted by the non-invasive brain-computer wearable device are used to collect electric wave signals and generate EEG signals; the controller is used to crawl the wall-climbing grinding robot according to the EEG signals generated by the non-invasive brain-computer wearable device. and grinding track to adjust. The invention eliminates the health hazards of the dust generated in the grinding process to the staff, and greatly improves the grinding precision of wind power blades and the processing effect of local details.
Description
Technical Field
The invention relates to the field of robots, in particular to a wall-climbing polishing device based on brain-computer control and a control method thereof.
Background
As one of key core components of a wind generating set, a wind power blade has wide application in the energy industry, and the manufacturing level thereof represents the core competitiveness of the national manufacturing industry. The wind power blade is mainly made of composite materials such as glass fiber reinforced polyvinyl acetate resin, glass fiber reinforced epoxy resin and paint which are difficult to process, is designed into a complex three-dimensional twisted curved surface, and mainly passes through the processing technologies such as positive mold, female mold turning, layering, heating curing, demolding, surface polishing and paint spraying, so that the defects of long manufacturing period and high difficulty exist. Moreover, after the demolding of the wind power blade is completed, the molded surface and the blade root of the wind power blade are polished, but the wind power blade is large in size and the outer shape of the curved surface is complex and changeable, so far, the surface polishing processing of the wind power blade is not automated in the whole process.
At present, the surface polishing process of wind power blades by wind power blade production backbone enterprises in China mainly adopts a manual polishing mode. The operation process is complex, and the method has the characteristics of high randomness of manual positioning, difficulty in accurate control of blade removal allowance and polishing position, easiness in rebounding of blade tip area polishing and the like, and the problems of low production efficiency (multiple workers need to be configured for continuous operation, high labor intensity), severe working environment (serious dust hazard and the need of wearing a gas mask for operation), poor operation stability (the polishing effect is easily influenced by the states of the workers, emotion, proficiency and the like), high cost (labor cost, labor protection articles, worker physical examination and the like) and the like in the manual polishing, so that urgent needs are provided for the efficient intelligent automatic processing mode of the wind power blade.
Therefore, the robot is used for realizing full-automatic polishing, and is a hotspot researched by experts of numerous scholars in recent years, two types of AGV polishing devices and non-AGV polishing devices are mainly applied in the market at present, the AGV polishing devices mainly adopt Mecanum wheel technology, carry on a laser automatic navigation system, and automatically polish the blade by matching a mobile robot with a polishing robot system and matching the polishing robot according to a system instruction, and the robot has the advantages of flexible operation, large polishing area and low equipment cost, and has the defects of low polishing precision and poor processing of local detail of a curved surface; the latter is mostly the cooperation and polishes, polishes the blade through moving a portal/vertical horizontal motion simultaneous a plurality of industrial robots, and equipment cost is very high, has the not good problem of local detail processing equally.
Disclosure of Invention
Based on the technical scheme, the invention provides a wall-climbing polishing device based on brain-computer control and a control method thereof, and aims to solve the technical problems that the existing robot for polishing fan blades is high in cost, low in polishing precision and not in-place local treatment.
In order to achieve the above object, the present invention provides a wall-climbing polishing device based on brain-computer control, comprising:
the laser radar is used for carrying out three-dimensional reconstruction on the appearance of the equipment to be polished so as to generate a three-dimensional map;
the wall-climbing polishing robot is used for crawling and polishing the wall surface of the equipment to be polished, collecting and feeding back real-time polishing data and image information, and generating crawling and polishing tracks according to a three-dimensional map, and the laser radar is arranged on the wall-climbing polishing robot;
the virtual reality equipment is worn on the head of an operator and is used for displaying real-time polishing data and image information returned by the wall-climbing polishing robot;
the noninvasive brain-computer wearable equipment is worn and tightly attached to the scalp of an operator and is used for acquiring electric wave signals and generating electroencephalogram signals;
the controller is in communication connection with the wall-climbing polishing robot, the virtual reality device and the non-invasive brain-computer wearable device, compiles real-time polishing data and image information returned by the wall-climbing polishing robot and transmits the compiled data and image information to the virtual reality device, and generates an instruction signal after processing an electroencephalogram signal generated by the non-invasive brain-computer wearable device by the controller, so that the wall-climbing polishing robot adjusts crawling and polishing tracks under the control of the instruction signal; and
two wireless communication modules are respectively arranged on the controller and the wall-climbing polishing robot so as to realize the two-way data communication between the controller and the wall-climbing polishing robot.
As a further preferable technical scheme of the invention, the wall-climbing polishing robot comprises a robot body, a vacuum generator, a polishing head and an industrial CCD camera; the robot body is driven by the crawler belt to realize crawling on the wall surface of equipment to be polished; the robot body is connected with a mechanical arm, a polishing head is arranged at the front end of the mechanical arm, and the polishing head is driven by the mechanical arm to realize polishing operation; the industrial CCD camera is arranged on the polishing head to be used for collecting real-time polishing images and positioning the polishing head.
As a further preferable technical scheme of the invention, the polishing head is also provided with a flow sensor and a torque sensor, and the mechanical arm is provided with three linear cylinders for controlling the polishing head.
As a further preferable technical solution of the present invention, the lidar is mounted on the top of the robot body, and the lidar is inclined downward toward the advancing direction of the robot body by an inclination angle of 15 to 45 degrees.
As a further preferred technical solution of the present invention, the virtual reality device is a pair of head-mounted glasses, and the head-mounted glasses include a glasses body, an optical imaging module, and a data transmission interface; the glasses body includes fixed connection's preceding shell and hou gai, and the back lid is equipped with the mounting hole, and optical imaging module sets up in the mounting hole, and the data transmission interface sets up in the front on the shell and with optical imaging module electric connection, the data transmission interface be used for being connected with the controller communication.
As a further preferred technical solution of the present invention, the non-invasive brain-computer wearable device includes a head cover, a plurality of electrode pads, a wire, and a data acquisition card for brain electricity, wherein the head cover is made of a flexible material, the plurality of electrode pads are arranged in an array and distributed on the head cover, and all the electrode pads are electrically connected to the data acquisition card for brain electricity through the wire.
As a further preferred technical scheme of the invention, the data acquisition card for the electroencephalogram comprises a preprocessor circuit, a data collector and a DSP main control; one end of the preprocessor circuit is connected with the electrode slice through a wire, and the other end of the preprocessor circuit is connected with the data collector; one end of the DSP master control is connected with the data acquisition unit, and the other end of the DSP master control is connected to the controller; the preprocessor circuit is used for amplifying and filtering the electric wave signals collected by the electrode plates, then transmitting the electric wave signals to the data collector, converting the electric wave signals into measurable voltage signals by the data collector, then forming electroencephalogram signals through DSP main control coding, and transmitting the electroencephalogram signals to the controller.
As a further preferable technical solution of the present invention, the controller is a PC host.
According to another aspect of the invention, the invention also provides a control method of the wall-climbing grinding device based on brain-computer control, which comprises the following steps:
performing three-dimensional reconstruction on the appearance of the equipment to be polished by adopting a laser radar to generate a three-dimensional map;
crawling and polishing are carried out on the wall surface of the equipment to be polished by adopting a wall-climbing polishing robot, real-time polishing data and image information are collected and fed back, and crawling and polishing tracks are generated according to a three-dimensional map;
wearing virtual reality equipment on the head of an operator to display real-time polishing data and image information returned by the wall-climbing polishing robot;
the noninvasive brain-computer wearable equipment is worn and attached to the scalp of an operator, so as to be used for collecting radio wave signals and generating brain electrical signals;
real-time polishing data and image information returned by the wall-climbing polishing robot are compiled and transmitted to virtual reality equipment, and electroencephalogram signals generated by non-invasive brain-computer wearable equipment are processed by a controller to generate instruction signals, so that the wall-climbing polishing robot adjusts crawling and polishing tracks under the control of the instruction signals.
Compared with the prior art, the wall climbing polishing device based on brain-computer control and the control method thereof have the following beneficial effects:
1) workers who polish the wind power blades are far away from a severe working environment, and direct damage to human bodies caused by dust contact is avoided;
2) the wall climbing polishing robot can work autonomously according to crawling and polishing tracks generated by a three-dimensional map, polishing images and polishing data are presented to an operator through virtual reality equipment, the operator wears remote assistance of non-invasive computer wearing equipment, short plates in the polishing precision of the existing-stage automatic wind-power blade polishing field are greatly improved, and the wall climbing polishing robot is very suitable for application in industrial high-precision operation and post-processing.
Drawings
The present invention will be described in further detail with reference to the accompanying drawings and specific embodiments.
Fig. 1 is a block diagram showing an example of a wall-climbing polishing device based on brain-computer control;
fig. 2 is a wearing schematic diagram of a non-invasive brain-machine wearable device;
FIG. 3 is a schematic view of the distribution of electrode sheets;
FIG. 4 is a connection block diagram of a data acquisition card for electroencephalogram;
FIG. 5 is a schematic structural diagram of a virtual reality device;
fig. 6 is a schematic structural diagram of a non-invasive brain-machine wearable device;
FIG. 7 is a schematic diagram of a derivation of a DNC many-to-many mapping;
FIG. 8 is a schematic diagram of a derivation of DNC many-to-one mapping;
fig. 9 is a flowchart for controlling a sanding motion of a robot based on brain waves.
In the figure: 101. headgear, 102, electrode slice, 103, wire, 1011, cingulum, 301, glasses body, 302, optical imaging module, 303, data transmission interface, 3011, preceding shell, 3012, back lid, 401, robot body, 402, sucking disc, 405, laser radar, 406, sanding head, 407, industrial CCD camera.
The objects, features and advantages of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
The invention will be further described with reference to the accompanying drawings and specific embodiments. In the preferred embodiments, the terms "upper", "lower", "left", "right", "middle" and "a" are used for descriptive purposes only and are not intended to limit the scope of the invention, and the relative relationship between the terms and the terms is not to be construed as the scope of the invention.
As shown in fig. 1, a wall-climbing grinding device based on brain machine control, including wall-climbing grinding robot, lidar 405, virtual reality equipment, non-invasive brain machine wearing equipment, controller and wireless communication module, wherein:
the wall-climbing polishing robot is used for crawling and polishing the wall surface of equipment to be polished, collecting and feeding back real-time polishing data and image information, and the equipment to be polished is a fan blade of a wind power generator set; the laser radar 405 is arranged on the wall-climbing grinding robot and used for performing three-dimensional reconstruction on the appearance of the equipment to be ground so as to generate a three-dimensional map, the wall-climbing grinding robot generates a climbing and grinding track according to the three-dimensional map, the laser radar 405 faces the advancing direction of the robot body 401 and inclines downwards at an inclination angle of 15-45 degrees, the laser radar 405 is used for performing three-dimensional reconstruction on the wall surface of the equipment to be ground, and the preferred inclination angle is 15 degrees; the virtual reality equipment is worn on the head of an operator and used for displaying real-time polishing data and image information returned by the wall-climbing polishing robot, a polishing image is presented in front of the eyes of the operator through a virtual reality technology, an operator is assisted in judging the polishing condition, and the operation is convenient for adjusting the working state of the wall-climbing polishing robot according to the image information; the noninvasive brain-computer wearable equipment is worn and tightly attached to the scalp of an operator and is used for collecting electric wave signals and generating electroencephalogram signals, and the electric wave signals are related signals for the operator to adjust and control the working state of the wall-climbing polisher robot; the controller is a core main control device, the controller can be a PC host, the PC host is in communication connection with the wall climbing polishing robot, the virtual reality device and the non-invasive brain-computer wearing device, real-time polishing data and image information returned by the wall climbing polishing robot are compiled and transmitted to the virtual reality device, electroencephalogram signals generated by the non-invasive brain-computer wearing device are processed by the controller to generate instruction signals, and the wall climbing polishing robot performs wall climbing, polishing and image acquisition operations under the control of the instruction signals; the controller and the wall-climbing polishing robot are respectively provided with a wireless communication module so as to realize bidirectional data communication between the controller and the wall-climbing polishing robot.
Referring to fig. 6, the wall-climbing polishing robot includes a robot body 401, a vacuum generator, a polishing head 406, and an industrial CCD camera 407; the walking mechanism of the robot body 401 is a crawler belt, a plurality of suckers 402 are arranged on the crawler belt, a vacuum generator is connected with each sucker 402 to provide negative pressure required by the sucker 402, a one-way valve cavity for controlling the sucker 402 is further arranged in the robot body 401, the one-way valve cavity can automatically close the suction holes of the suckers 402 which are not in contact with the wall surface according to pressure difference so as to realize automatic deformation attachment of the suckers 402 and the contact wall surface, the crawler belt is adsorbed on the wall surface in contact with the crawler belt through the negative pressure generated by the suckers 402, and the robot body 401 is driven by the crawler belt to realize crawling on equipment to be polished; the robot body 401 is connected with a mechanical arm, the polishing head 406 is arranged at the front end of the mechanical arm, and the polishing head 406 is driven by the mechanical arm to realize polishing operation; an industrial CCD camera 407 is mounted on the sanding head 406 for acquiring real-time sanding images while positioning the sanding head 406.
Furthermore, the polishing head 406 is a spherical hinge mechanism with a flow sensor, a torque sensor and three linear cylinders, the torque sensor is installed at the spherical hinge and used for measuring the contact force, the stroke size and speed of the torque sensor are mainly controlled by a valve with the flow sensor, the polishing part of the polishing head 406 can be attached to the surface of the wind power blade, and the polishing precision is improved. The real-time polishing data is real-time working data of the flow sensor and the torque sensor.
Referring to fig. 5, the virtual reality device is a pair of head-mounted glasses, and the head-mounted glasses include a glasses body 301, an optical imaging module 302, and a data transmission interface 303; glasses body 301 includes preceding shell 3011 and back cover 3012 of fixed connection, and back cover 3012 is equipped with the mounting hole, and optical imaging module 302 sets up in the mounting hole, and data transmission interface 303 sets up on preceding shell 3011 and with optical imaging module 302 electric connection, and data transmission interface 303 is used for being connected with the controller communication. The user can observe the real-time image that the wall climbing polishing robot advances, polishes the visual angle through this virtual reality equipment in real time, is favorable to the user to make reasonable judgement to the real-time condition of polishing.
Referring to fig. 2 and 3, the non-invasive brain-computer wearable device includes a head cover 101, a plurality of electrode pads 102, a lead 103, and a data acquisition card for electroencephalogram, wherein the plurality of electrode pads 102 are arranged in an array and distributed on the head cover 101, and all the electrode pads 102 are electrically connected to the data acquisition card for electroencephalogram through the lead 103. In order to make the electrode sheet 102 adhere to the cerebral cortex with the headgear 101, the headgear 101 is further connected with a buckle 1011 fitting to the chin of the wearer. The headgear 101 is made of a flexible material, which does not affect the collection of the electric wave signals, and is also beneficial to reducing the uncomfortable feeling of the user when wearing the headgear.
The electrode plate 102 is divided into a base material and a coating, wherein the base material adopts a 99.9% pure silver material with best conductivity, and the coating adopts silver salts of strong electrolyte; the conducting wire 103 is made of high-conductivity pure silver material, and the inside of the conducting wire 103 can be a single-strand conducting wire or two strands of conducting wires 103, wherein the former collects potential quantity, and the latter collects potential difference quantity, and the conducting wire can be selected according to specific signal requirements in actual use.
Referring to fig. 4, the data acquisition card for electroencephalogram includes a preprocessor circuit, a data acquisition unit, and a DSP main control; one end of the preprocessing circuit is connected with the electrode plate 102 through a wire 103, and the other end of the preprocessing circuit is connected with the data acquisition unit; one end of the DSP master control is connected with the data acquisition unit, and the other end of the DSP master control is connected to the controller.
The preprocessing circuit is a conditioning circuit comprising a preamplifier, a photoelectric isolation circuit, a filter circuit, a main amplification and level lifting circuit and the like, is mainly used for amplifying and filtering electric wave signals, eliminating invalid components and converting weak signals into a size range which can be identified by a sampling chip of a data acquisition unit; the data collector adopts an eight-channel AD7768 chip of ADI company, and is provided with a linear phase filter and a low-delay sinc5 filter; the DSP main control adopts an ADSP-BF703 chip which is one of Blackfin series, supports double-channel 16-bit or single-channel 32-bit MAC, and has a kernel providing performance up to 400 MHz; after the electric wave signal is preprocessed by the conditioning circuit, ADC sampling is completed on an AD7768 chip and converted into a voltage signal which can be measured, and the voltage signal is input into an ADSP-BF703 chip through an SPI bus; and finally, the DSP main control codes form a brain electric signal and transmit the brain electric signal to the controller.
The invention provides a semi-automatic mode wall-climbing polishing device based on computer control, which aims at the problems that the operation process is complex, the randomness of manual positioning is high, the blade removing allowance and the polishing position are difficult to control, the polishing of a blade tip area is easy to rebound and the like in the polishing of a wind power blade, and the problems that the existing manual polishing has low production efficiency, severe working environment, poor operation stability and high cost, and the precision is poor and the local detail processing is poor generally existing in the polishing mode of an industrial robot, and the like, and the invention provides the wall-climbing polishing device based on the computer control, which has the following working principle:
scanning the appearance of the wind power blade by a laser radar 405 carried on the wall-climbing grinding robot to carry out three-dimensional reconstruction, and automatically planning a grinding path by combining a preset operating system; the wall-climbing polishing robot feeds back polishing data and environment image data in real time and displays the data on virtual reality equipment worn by a worker, the worker makes further judgment according to the polishing condition presented in the virtual reality equipment and adjusts the polishing force, the polishing position and the polishing angle of the wall-climbing polishing robot; therefore, a semi-automatic control mode that the wall-climbing polishing robot takes the automatic control as the leading part and takes the human brain control as the auxiliary part is realized. The harm of dust produced in the polishing process to the health of workers is avoided, and the polishing precision of the wind power blade and the processing effect of local details are greatly improved.
The invention also provides a control method of the wall-climbing polishing device based on brain-computer control, which comprises the following steps:
performing three-dimensional reconstruction on the appearance of the equipment to be polished by using a laser radar 405 to generate a three-dimensional map;
step 100, crawling and polishing on the wall surface of equipment to be polished by adopting a wall-climbing polishing robot, collecting and feeding back real-time polishing data and image information, and generating crawling and polishing tracks according to a three-dimensional map;
step 200, wearing virtual reality equipment on the head of an operator to display real-time polishing data and image information returned by the wall-climbing polishing robot;
300, wearing and tightly attaching the non-invasive brain-computer wearable equipment to the scalp of an operator so as to collect electric wave signals and generate electroencephalogram signals;
and 400, compiling real-time polishing data and image information returned by the wall-climbing polishing robot, transmitting the compiled data and image information to virtual reality equipment, and generating an instruction signal after performing controller processing on an electroencephalogram signal generated by non-invasive brain-computer wearable equipment so as to enable the wall-climbing polishing robot to adjust crawling and polishing tracks under the control of the instruction signal.
The basic principle of using brain waves to remotely control the sanding robot is as follows: the signals fed back by the wall climbing robot comprise grinding real-time video stream, grinding head moving speed and stroke data converted by a torque sensor and a flow sensor, a user views the fed back grinding robot feedback signals through virtual reality equipment, and corresponding reaction signals (for example, a visual area is in occipital lobe of parietal occipital fissure and belongs to the seventeenth area of Brydeman, and an organism sensory area (to-be-measured area) is in a narrow and long area behind a central sulcus and belongs to the first, second and third areas of Brydeman) generated by a cerebral cortex are reduced through metabolism and blood flow increase of a cerebral cortex specific area in a brain motor imagination form (increase and reduction of grinding force, change of grinding head angle, re-grinding of a certain part and the like) as shown in the following table 1-1.
TABLE 1-1 cerebrum Structure and function
The electrode plate collects the weak electric signal fluctuation (analog quantity) of the body sensory area, and the weak electric signal fluctuation is amplified and processed by hardware filtering (eliminating Gaussian clutter and white noise) through a designed preprocessing circuit and then input into a controller (PC). During the whole brain wave recording process, the impedance between each electrode is kept below 10K omega, and the signal sampling rate is 1 KHz.
The controller performs the re-processing and classification of the hardware primary processing signal (similar to the left/right hand imagination, see fig. 9), specifically as follows: the method comprises the steps that firstly, a software band-pass filter is used for extracting electroencephalogram data in a frequency range of 1-50 Hz as processing and analyzing signals of a controller; the second step is to eliminate the phase difference between the data in the brain functional area through DFT algorithm (carry on the comparison in the frequency domain); the third step is to convert the collected time domain EEG signals into frequency domain signals by using FFT (Fourier transform); fourthly, signal partition is carried out, effective signals in the brain are usually a plurality of alpha waves (8-13Hz), beta waves (13-22Hz), theta waves (4-7Hz) and delta waves (0.5-3Hz), and the partition is used for splitting the four waves for analysis; and extracting effective signals in the corresponding area in the last step of the fifth step, namely removing similar signals (for example, imagine that the grinding head reduces grinding force and thinks that the signals for grinding in the next step sometimes have similar waveform segments) by using a micro-nerve computer, and extracting effective control signals (reducing the grinding force of the wall-climbing robot).
The extracted controller signal is named as '1' corresponding to the increase of the grinding force, '2' reducing the grinding force, 'a' moves forwards by 1mm in a mode, in order to reduce the data volume burden of wireless transmission, and is transmitted to the wall climbing robot to execute a corresponding instruction through a serial compiling mode (printf ('AX ═ d AY ═ d \ n', 1acx,2acy,5 acz);).
In order to further understand the disclosure, the following detailed description will discuss the method for processing the brain electrical signal by the controller.
The controller adopts an improved micro-neural computer for classification and identification of the electroencephalogram signals, namely, the electroencephalogram signals are processed through a structural system of a plurality of layers of DNCs (DNCs), the electroencephalogram signal solving problem is modeled through RNN (neural network), and the mapping relation between the signals and the solving result (corresponding control instruction) is constructed. Equation (1) is the type of many-to-many in the original DNC structure, we take the same notation as in equation (1), and for many-to-many mapping, the calculation diagram is determined by the following equation, and fig. 7 is a schematic diagram of the derivation flow and calculation flow of many-to-many mapping:
since in many-to-one mapping the learning signal is only present in the last time step, so upsilontOnly in the last time step. From this, equations (5) and (6) were derived.
However, in equation (1), the controller is constructed from a conventional LSTM network, which may not be able to achieve the conversion between the required amounts of space, taking into account the structure of the cyclic convolutional network. In order to effectively merge convolution operation and loop operation and improve calculation efficiency, the following formula is specifically designed as a building block of the controller network:
χt＝concat(It,St-1,Mt-1) (7)
zt＝σ(conv(χt,Wz)) (8)
rt＝σ(conv(χt,Wr)+1.0) (9)
ct＝tanh(conv(χt,Wi)) (10)
ht＝ht-1×rt+ct×zt (11)
in the formula (7), ItIs the input current signal of the network. St-1Is the state of the controller network, Mt-1Is the relevant memory information for the last time step. In order to solve the problem of similarity of electroencephalogram signals, the method preferably compares the signals without leading absolute component
Although specific embodiments of the present invention have been described above, it will be appreciated by those skilled in the art that these are merely examples and that many variations or modifications may be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims.
Claims (9)
1. The utility model provides a climb wall grinding device based on brain machine control which characterized in that includes:
the laser radar is used for carrying out three-dimensional reconstruction on the appearance of the equipment to be polished so as to generate a three-dimensional map;
the wall-climbing polishing robot is used for crawling and polishing the wall surface of the equipment to be polished, collecting and feeding back real-time polishing data and image information, and generating crawling and polishing tracks according to a three-dimensional map, and the laser radar is arranged on the wall-climbing polishing robot;
the virtual reality equipment is worn on the head of an operator and is used for displaying real-time polishing data and image information returned by the wall-climbing polishing robot;
the noninvasive brain-computer wearable equipment is worn and tightly attached to the scalp of an operator and is used for acquiring electric wave signals and generating electroencephalogram signals;
the controller is in communication connection with the wall-climbing polishing robot, the virtual reality equipment and the non-invasive brain-computer wearable equipment, compiles and transmits real-time polishing data and image information returned by the wall-climbing polishing robot to the virtual reality equipment, and generates an instruction signal after processing an electroencephalogram signal generated by the non-invasive brain-computer wearable equipment by the controller, so that the wall-climbing polishing robot adjusts crawling and polishing tracks under the control of the instruction signal; and
two wireless communication modules are respectively arranged on the controller and the wall-climbing polishing robot so as to realize the two-way data communication between the controller and the wall-climbing polishing robot.
2. The brain-machine-control-based wall-climbing grinding device according to claim 1, wherein the wall-climbing grinding robot comprises a robot body, a vacuum generator, a grinding head and an industrial CCD camera; the robot body is driven by the crawler belt to realize crawling on the wall surface of equipment to be polished; the robot body is connected with a mechanical arm, the polishing head is arranged at the front end of the mechanical arm, and the polishing head is driven by the mechanical arm to realize polishing operation; the industrial CCD camera is arranged on the polishing head to be used for collecting real-time polishing images and positioning the polishing head.
3. The brain-computer-controlled wall-climbing grinding device according to claim 2, wherein the grinding head is further provided with a flow sensor and a torque sensor, and the mechanical arm is provided with three linear cylinders for controlling the grinding head.
4. The brain-computer-controlled wall-climbing grinding device according to claim 2, wherein the laser radar is mounted on the top of the robot body, and the laser radar faces the advancing direction of the robot body and inclines downwards by an inclination angle of 15-45 degrees.
5. The brain-computer-controlled wall-climbing grinding device according to claim 1, wherein the virtual reality equipment is head-mounted glasses, and the head-mounted glasses comprise a glasses body, an optical imaging module and a data transmission interface; the glasses body includes fixed connection's preceding shell and hou gai, and the back lid is equipped with the mounting hole, and optical imaging module sets up in the mounting hole, and the data transmission interface sets up in the front on the shell and with optical imaging module electric connection, the data transmission interface be used for being connected with the controller communication.
6. The wall-climbing grinding device based on brain-computer control of claim 1, wherein the non-invasive brain-computer wearable device comprises a head cover, a plurality of electrode plates, a wire and a data acquisition card for brain electricity, the head cover is made of flexible material, the plurality of electrode plates are arranged in an array and distributed on the head cover, and all the electrode plates are electrically connected with the data acquisition card for brain electricity through the wire.
7. The brain-computer control-based wall-climbing grinding device according to claim 6, wherein the data acquisition card for electroencephalogram comprises a preprocessor circuit, a data acquisition unit and a DSP main control; one end of the preprocessor circuit is connected with the electrode slice through a wire, and the other end of the preprocessor circuit is connected with the data collector; one end of the DSP master control is connected with the data acquisition unit, and the other end of the DSP master control is connected to the controller; the preprocessor circuit is used for amplifying and filtering the electric wave signals collected by the electrode plates, then transmitting the electric wave signals to the data collector, converting the electric wave signals into measurable voltage signals by the data collector, then forming electroencephalogram signals through DSP main control coding, and transmitting the electroencephalogram signals to the controller.
8. The brain-based wall climbing sanding device of any one of claims 1-7 wherein the controller is a PC host.
9. The control method of the brain-computer-controlled wall-climbing grinding device according to any one of claims 1 to 8, characterized by comprising the following steps:
performing three-dimensional reconstruction on the appearance of the equipment to be polished by adopting a laser radar to generate a three-dimensional map;
crawling and polishing are carried out on the wall surface of the equipment to be polished by adopting a wall-climbing polishing robot, real-time polishing data and image information are collected and fed back, and crawling and polishing tracks are generated according to a three-dimensional map;
wearing virtual reality equipment on the head of an operator to display real-time polishing data and image information returned by the wall-climbing polishing robot;
the noninvasive brain-computer wearable equipment is worn and attached to the scalp of an operator, so as to be used for collecting electric wave signals and generating electroencephalogram signals;
real-time polishing data and image information returned by the wall-climbing polishing robot are compiled and transmitted to virtual reality equipment, and electroencephalogram signals generated by non-invasive brain-computer wearable equipment are processed by a controller to generate instruction signals, so that the wall-climbing polishing robot adjusts crawling and polishing tracks under the control of the instruction signals.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011279972.0A CN112621487B (en) | 2020-11-16 | 2020-11-16 | Wall-climbing polishing device based on brain-computer control and control method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011279972.0A CN112621487B (en) | 2020-11-16 | 2020-11-16 | Wall-climbing polishing device based on brain-computer control and control method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112621487A CN112621487A (en) | 2021-04-09 |
| CN112621487B true CN112621487B (en) | 2022-02-18 |
Family
ID=75303460
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011279972.0A Active CN112621487B (en) | 2020-11-16 | 2020-11-16 | Wall-climbing polishing device based on brain-computer control and control method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112621487B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115488736A (en) * | 2022-07-05 | 2022-12-20 | 港珠澳大桥管理局 | Automatic positioning polishing system and polishing method based on wall-climbing robot |
| CN118699978B (en) * | 2024-07-25 | 2025-09-30 | 重庆大学 | Intelligent grinding equipment and method for mechanically automated workpiece processing |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB0309662D0 (en) * | 2003-04-28 | 2003-06-04 | Crampton Stephen | Robot CMM arm |
| TWI257214B (en) * | 2004-12-10 | 2006-06-21 | Univ Nat Chiao Tung | Brainwave-controlled embedded Internet robot agent architecture |
| CN102894971A (en) * | 2011-07-29 | 2013-01-30 | 中国科学院沈阳自动化研究所 | Helmet for acquiring brain signal by combining electroencephalography with near-infrared spectroscopy |
| CN112651288B (en) * | 2014-06-14 | 2022-09-20 | 奇跃公司 | Method and system for generating virtual and augmented reality |
| TWI676536B (en) * | 2016-01-22 | 2019-11-11 | 大陸商鴻富錦精密工業（武漢）有限公司 | System and method for controlling robot based on brain electrical signal |
| CN106426122B (en) * | 2016-07-22 | 2019-09-03 | 浙江工业大学 | Four-way walking intelligent robot for underground pipelines |
| CN109015635A (en) * | 2018-08-08 | 2018-12-18 | 西安科技大学 | A kind of service robot control method based on brain-machine interaction |
| KR102148854B1 (en) * | 2018-10-31 | 2020-08-28 | (주)클래시스 | Ultrasound apparatus for treating brain disease |
| CN210589315U (en) * | 2019-09-29 | 2020-05-22 | 广东博智林机器人有限公司 | Polishing robot |
| CN110788690B (en) * | 2019-10-22 | 2020-08-28 | 清华大学 | Wall-climbing robot for large-scale storage tank weld grinding operation |
| CN111086113A (en) * | 2020-02-19 | 2020-05-01 | 李谋遵 | Cutting method of profiling stone cutting robot by using intelligent vision |
-
2020
- 2020-11-16 CN CN202011279972.0A patent/CN112621487B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112621487A (en) | 2021-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110123572B (en) | Rehabilitation robot training system for compensation movement multi-mode interaction of upper hemiplegia limbs | |
| CN112621487B (en) | Wall-climbing polishing device based on brain-computer control and control method thereof | |
| CN104666047B (en) | The bilateral mirror image rehabilitation system perceived based on biological information | |
| CN101947152B (en) | Electroencephalogram-voice control system and working method of humanoid artificial limb | |
| CN110123573B (en) | Rehabilitation robot training system for compensatory movement monitoring and inhibition of hemiplegic upper limb | |
| CN105078445A (en) | Old people healthy service system based on healthy service robot | |
| CN105078450B (en) | A kind of health service robot of achievable brain electro-detection | |
| CN102727361B (en) | Sitting and lying type lower limb rehabilitation robot | |
| CN111345970B (en) | Seven-degree-of-freedom upper limb exoskeleton rehabilitation robot | |
| CN104586608B (en) | The wearable power-assisted finger controlled based on myoelectricity and its control method | |
| CN110281108A (en) | A kind of robot flexibility intelligence polishing system based on six-dimension force sensor | |
| CN110058691A (en) | Based on Embedded wearable wireless dry electrode brain wave acquisition processing system and method | |
| CN102641196A (en) | Rehealthy training robot control system and control method thereof | |
| CN102698411B (en) | Recumbent lower limb rehabilitation robot | |
| US20230191590A1 (en) | Wearable cable-driven robotic arm system | |
| CN105310686B (en) | A kind of health service robot of achievable ECG detecting | |
| CN107224384B (en) | Master-slave arm robot and its control system and control method | |
| CN101897640A (en) | A new type of intelligent wheelchair system based on motor imagery EEG control | |
| CN109646242A (en) | A kind of Table top type upper limb rehabilitation robot and its application method | |
| CN107212883B (en) | A writing device and control method of a manipulator based on EEG control | |
| CN116507286A (en) | Ultrasonic image data collection, analysis and recognition integrated robot, platform | |
| CN108056865A (en) | A kind of multi-modal wheelchair brain control system and method based on cloud platform | |
| CN106491251A (en) | One kind is based on non-intrusion type brain-computer interface robotic arm control system and its control method | |
| CN113576857B (en) | Intelligent round needle system skin therapy health management instrument based on skin scraping and metering | |
| CN115050104B (en) | Continuous gesture action recognition method based on multichannel surface electromyographic signals |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |