CN104999164B - Underwater robot based on multiple filter treatment - Google Patents
Underwater robot based on multiple filter treatment Download PDFInfo
- Publication number
- CN104999164B CN104999164B CN201510470296.8A CN201510470296A CN104999164B CN 104999164 B CN104999164 B CN 104999164B CN 201510470296 A CN201510470296 A CN 201510470296A CN 104999164 B CN104999164 B CN 104999164B
- Authority
- CN
- China
- Prior art keywords
- equipment
- underwater
- sub
- image
- laser
- 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
- 238000003466 welding Methods 0.000 claims abstract description 39
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 34
- 239000003795 chemical substances by application Substances 0.000 claims abstract description 29
- 238000003384 imaging method Methods 0.000 claims abstract description 24
- 238000005493 welding type Methods 0.000 claims abstract description 11
- 238000001914 filtration Methods 0.000 claims description 38
- 238000001514 detection method Methods 0.000 claims description 21
- 239000004579 marble Substances 0.000 claims description 16
- 238000000605 extraction Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 7
- 230000002708 enhancing effect Effects 0.000 claims description 6
- 238000000034 method Methods 0.000 claims description 5
- 239000000203 mixture Substances 0.000 claims description 4
- 208000019300 CLIPPERS Diseases 0.000 claims description 3
- 229910001209 Low-carbon steel Inorganic materials 0.000 claims description 3
- 208000021930 chronic lymphocytic inflammation with pontine perivascular enhancement responsive to steroids Diseases 0.000 claims description 3
- 239000004020 conductor Substances 0.000 claims description 3
- 210000000245 forearm Anatomy 0.000 claims description 3
- 238000003709 image segmentation Methods 0.000 claims description 3
- 239000000463 material Substances 0.000 claims description 3
- 230000011514 reflex Effects 0.000 claims description 3
- 238000007789 sealing Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 description 6
- 238000013461 design Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 210000000080 chela (arthropods) Anatomy 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000003466 anti-cipated effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000005476 soldering Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K9/00—Arc welding or cutting
- B23K9/0061—Underwater arc welding
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K9/00—Arc welding or cutting
- B23K9/02—Seam welding; Backing means; Inserts
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K9/00—Arc welding or cutting
- B23K9/12—Automatic feeding or moving of electrodes or work for spot or seam welding or cutting
- B23K9/127—Means for tracking lines during arc welding or cutting
- B23K9/1272—Geometry oriented, e.g. beam optical trading
- B23K9/1274—Using non-contact, optical means, e.g. laser means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K9/00—Arc welding or cutting
- B23K9/24—Features related to electrodes
- B23K9/28—Supporting devices for electrodes
- B23K9/287—Supporting devices for electrode holders
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K9/00—Arc welding or cutting
- B23K9/32—Accessories
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30152—Solder
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Plasma & Fusion (AREA)
- Mechanical Engineering (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Optics & Photonics (AREA)
- Laser Beam Processing (AREA)
- Image Processing (AREA)
- Manipulator (AREA)
Abstract
The present invention relates to a kind of underwater robot based on multiple filter treatment, for automatic welding under water, including underwater human agent, laser imaging apparatus and weld seam recognition equipment, the laser imaging apparatus and the weld seam recognition equipment are all located on the underwater human agent, the laser imaging apparatus are used to shoot underwater laser image, the weld seam recognition equipment is connected with the laser imaging apparatus, for extracting underwater weld feature from the underwater laser image and determining welding type.By means of the invention it is possible to the accuracy of weld seam recognition is improved, for Underwater Welding provides important referential data.
Description
Technical field
The present invention relates to image filtering field, more particularly to a kind of underwater robot based on multiple filter treatment.
Background technology
Currently, there is problems with for Underwater Welding will solve：1st, human weld's mode precision and efficiency is not high；2、
Be present the concrete structure for needing to adapt to underwater environment in the mode of machinery welding, it is especially desirable to overcome at the image of all kinds of interference under water
Reason equipment；3rd, automatic welding device is lacked.Thus, in the prior art, it is impossible to carry out underwater installation by the way of machinery welding
Welding, cause current welding manner speed slow and not accurate enough.
For this reason, it may be necessary to a kind of mechanization automatic welding scheme that can process various interference under water, can improve water first
The imaging effect of lower laser image, but can adapt to underwater environment, is capable of identify that welding type, finally need it is a set of can from
The welding equipment of dynamic welding.
The content of the invention
In order to solve the technical problem of prior art presence, processed under water based on multiple filter the invention provides a kind of
Robot, to transform the concrete structure of existing underwater robot so that it can recycle sonar and sonar as jig
Image processing equipment improves laser imaging effect, using including the sub- equipment of medium filtering, low pass filtered marble equipment and homomorphic filtering
The image-preprocessing device of sub- equipment realizes the removal to all kinds of interference under water, using the image recognition based on neural network recognization
Technology improves the accuracy of weld seam recognition, and finally transforming welding equipment can complete automatic welding under water.
According to an aspect of the present invention, there is provided it is a kind of based on multiple filter treatment underwater robot, under water from
Dynamic welding, the underwater robot includes underwater human agent, laser imaging apparatus and weld seam recognition equipment, the laser into
As equipment and the weld seam recognition equipment are all located on the underwater human agent, the laser imaging apparatus are used to shoot water
Lower laser image, the weld seam recognition equipment is connected with the laser imaging apparatus, for being carried from the underwater laser image
The lower characteristics of weld seam of water intaking simultaneously determines welding type.
More specifically, in the underwater robot based on multiple filter treatment, also including：Electrode holders, for fixing
Welding rod, the welding rod is wet method coated electrode, and material is mild steel；Safety switch, its cathode conductor is connected to the electrode holders；
Earth clip, is fixed on workpiece to be welded；Electric welding machine, negative pole is connected to the electrode holders, plus earth；Electrode holders drive and set
It is standby, with the electric welding clipper joint, the weld seam for going to workpiece to be welded according to the electrode holders drive signal driving electrode holders
Position；Electrode holders motor, is a direct current generator, and the driving for the electrode holders driving equipment to the electrode holders provides dynamic
Power；The underwater human agent includes support, left pressure gram transparent tube, right pressure gram transparent tube, connecting hoop, storage platform, machine
Tool arm, manipulator, water proof sealing drum, transverse propeller, vertical screw, longitudinal screw and three direct current generators, the branch
Frame is used to be fixed on the underwater human agent under water, and the connecting hoop is fixedly connected with the support, the storage platform
It is connected respectively with the connecting hoop with the mechanical arm, the manipulator is connected with the mechanical arm, the mechanical arm includes big
Arm and the forearm being connected with large arm, three direct current generators drive respectively the transverse propeller, the vertical screw and
The longitudinal screw, with by the rotating of propeller, for underwater human agent provides 6 thrust powers of the free degree；
Mobile hard disk, on the underwater human agent, for having prestored the luminance threshold upper limit and luminance threshold lower limit；Sound
Equipment is received, on the underwater human agent, for the submarine target execution sound in front of the underwater human agent
IMAQ is received, to obtain sonar image；Sonar image processing equipment, connects respectively with the sonar and the mobile hard disk
Connect, including the first sub- equipment of detection, the second sub- equipment of detection and the sub- equipment of object range detection, the sub- equipment of first detection with
The sonar and the mobile hard disk are connected respectively, for using the luminance threshold upper limit to travel through sonar image to be partitioned into core
Target centroid region；The sub- equipment of second detection is connected respectively with the described first sub- equipment of detection and the mobile hard disk, is used for
Using the marginal point in the core objective region as seed point, using luminance threshold lower limit to the pixel of core objective areas adjacent
Point carries out brightness judgement, to obtain and is partitioned into final goal region；The sub- equipment of object range detection and the described second inspection
The connection of sub- equipment is surveyed, the central point in final goal region is calculated and is detected the distance of origin and defeated as target range to sonar image
Go out；The laser imaging apparatus, including laser, detector and microcontroller, the laser is to the underwater robot master
Submarine target in front of body sends laser beam, when the laser beam reflexes to the detector by submarine target, to be easy to institute
The shooting of detector is stated, the microcontroller is distinguished with the sonar image processing equipment, the laser and the detector
Connection, based on target range and laser, spread speed determines the gating time of the detector shutter under water, and in gating
Between when reaching, gate the shutter of the detector, trigger the detector and submarine target shot, to obtain underwater laser
Image；The weld seam recognition equipment includes that the sub- equipment of pretreatment, the sub- equipment of feature extraction and welding type recognize sub- equipment；It is described
Sub- equipment is pre-processed to be connected with the laser imaging apparatus, including the filter of the sub- equipment of medium filtering, low pass filtered marble equipment and homomorphism
Marble equipment；The sub- equipment of medium filtering is connected with the detector, for performing intermediate value filter to the underwater laser image
Ripple, to filter the spot noise in the underwater laser image, obtains the first filtering image；The low pass filtered marble equipment with it is described
The sub- equipment connection of medium filtering, for removing the random noise in first filtering image, obtains the second filtering image；It is described
The sub- equipment of homomorphic filtering is connected with the low pass filtered marble equipment, for performing image enhaucament to second filtering image, with
Obtain enhancing underwater picture；The sub- equipment of feature extraction be connected with the pretreatment sub- equipment, including image segmentation unit with
Eigenvector recognition unit, described image cutting unit is based on weld image gray threshold scope by the enhancing underwater picture
Weld seam target identification out obtaining Underwater weld seam image；The eigenvector recognition unit connects with described image cutting unit
Connect, 8 geometric properties of underwater weld target are determined based on the Underwater weld seam image：It is Euler's hole count, circularity, angle point number, convex
Concavity, smoothness, draw ratio, tight ness rating and main shaft angle, and 8 geometric properties composition characteristics is vectorial；The weld seam
The sub- equipment of type identification is connected with the sub- equipment of the feature extraction, using single hidden layer BP neural network of the output of 8 input 2, with water
Used as input layer, output layer is underwater weld type, the underwater weld type to 8 geometric properties of lower weld seam target
Including general type and cannot welds types；Main control device, is arranged on the underwater human agent, with the welding type
Recognize the connection of sub- equipment, when receive the underwater weld type for cannot welds types when, alarm signal is sent, when receiving
When the underwater weld type is general type, according to Underwater weld seam image, the relative position of laser image determines to be welded under water
Pincers drive signal.
More specifically, in the underwater robot based on multiple filter treatment：Submerged cable, for by the master control
Equipment is connected with jig waterborne, and the alarm signal is sent into the jig waterborne.
More specifically, in the underwater robot based on multiple filter treatment：It is the sub- equipment of medium filtering, described
Low pass filtered marble equipment and the sub- equipment of the homomorphic filtering are respectively adopted different fpga chips to realize.
More specifically, in the underwater robot based on multiple filter treatment：It is the sub- equipment of medium filtering, described
Low pass filtered marble equipment and the sub- equipment of the homomorphic filtering are integrated on one piece of surface-mounted integrated circuit.
More specifically, in the underwater robot based on multiple filter treatment：The main control device is data signal
Processor, the dsp chip of model TI companies.
Brief description of the drawings
Embodiment of the present invention is described below with reference to accompanying drawing, wherein：
Fig. 1 is the structure square frame of the underwater robot based on multiple filter treatment according to embodiment of the present invention
Figure.
Reference：1 underwater human agent；2 laser imaging apparatus；3 weld seam recognition equipment
Specific embodiment
The embodiment to the underwater robot based on multiple filter treatment of the invention is carried out in detail below with reference to accompanying drawings
Describe in detail bright.
Underwater Welding first has to accurately identify position while welding, general in the prior art to be carried out using image recognition mode, so
And, the shutter control of current underwater laser images is difficult, causes underwater laser image effect not good, while lacking suitably under water
Location equipment and image filtering equipment so that the precision of Underwater Welding is not high.
In order to overcome above-mentioned deficiency, the present invention has built a kind of underwater robot based on multiple filter treatment, using many
Weight filtering mode is pre-processed to image, optimizes underwater laser images technology and underwater installation location technology, meanwhile, transform water
Lower robot and welding equipment so that automatic welding is possibly realized under water.
Fig. 1 is the structure square frame of the underwater robot based on multiple filter treatment according to embodiment of the present invention
Figure, the underwater robot includes underwater human agent, laser imaging apparatus and weld seam recognition equipment, and the laser imaging sets
The standby and weld seam recognition equipment is all located on the underwater human agent, and the laser imaging apparatus are used for shooting and swash under water
Light image, the weld seam recognition equipment is connected with the laser imaging apparatus, for extracting water from the underwater laser image
Lower characteristics of weld seam simultaneously determines welding type.
Then, continue to carry out further the concrete structure of the underwater robot based on multiple filter treatment of the invention
Explanation.
The underwater robot also includes：Electrode holders, for fixing welding rod, the welding rod is wet method coated electrode, material
It is mild steel；Safety switch, its cathode conductor is connected to the electrode holders；Earth clip, is fixed on workpiece to be welded；Electric welding
Machine, negative pole is connected to the electrode holders, plus earth；Electrode holders driving equipment, and the electric welding clipper joint, for according to electric welding
Pincers drive signal drives the electrode holders to go to the position while welding of workpiece to be welded；Electrode holders motor, is a direct current generator,
Driving for the electrode holders driving equipment to the electrode holders provides power.
The underwater human agent includes support, left pressure gram transparent tube, right pressure gram transparent tube, connecting hoop, storing
Platform, mechanical arm, manipulator, water proof sealing drum, transverse propeller, vertical screw, longitudinal screw and three direct current generators, institute
Support is stated for the underwater human agent to be fixed under water, the connecting hoop is fixedly connected with the support, the storage
Thing platform and the mechanical arm are connected respectively with the connecting hoop, and the manipulator is connected with the mechanical arm, the mechanical arm bag
Large arm and the forearm being connected with large arm are included, three direct current generators drive the transverse propeller, the vertical spiral respectively
Oar and the longitudinal screw, by the rotating of propeller, to be moved for underwater human agent provides 6 propulsions of the free degree
Power.
The underwater robot also includes：Mobile hard disk, on the underwater human agent, for prestoring
The luminance threshold upper limit and luminance threshold lower limit.
The underwater robot also includes：Sonar, on the underwater human agent, for it is described under water
Submarine target in front of robot body performs sonar image collection, to obtain sonar image.
The underwater robot also includes：Sonar image processing equipment, with the sonar and the mobile hard disk point
Do not connect, including the first sub- equipment of detection, the second sub- equipment of detection and the sub- equipment of object range detection, described first detects that son sets
It is standby to be connected respectively with the sonar and the mobile hard disk, for using the luminance threshold upper limit to travel through sonar image to split
Go out core objective region；The sub- equipment of second detection is connected respectively with the described first sub- equipment of detection and the mobile hard disk,
For using the marginal point in the core objective region as seed point, using luminance threshold lower limit to core objective areas adjacent
Pixel carries out brightness judgement, to obtain and is partitioned into final goal region；The sub- equipment of object range detection and described
Two detections sub- equipment connection, calculate the central point in final goal region to sonar image detect origin distance and as target away from
From output.
The laser imaging apparatus, including laser, detector and microcontroller, the laser is to the underwater
Submarine target in front of human agent sends laser beam, with when the laser beam reflexes to the detector by submarine target, just
In the shooting of the detector, the microcontroller and the sonar image processing equipment, the laser and the detector
Connect respectively, based on target range and laser, spread speed determines the gating time of the detector shutter under water, and is selecting
When the logical time reaches, the shutter of the detector is gated, trigger the detector and submarine target is shot, to obtain under water
Laser image.
The weld seam recognition equipment includes that the sub- equipment of pretreatment, the sub- equipment of feature extraction and welding type recognize sub- equipment；
The sub- equipment of the pretreatment be connected with the laser imaging apparatus, including the sub- equipment of medium filtering, low pass filtered marble equipment and together
State filters sub- equipment；The sub- equipment of medium filtering is connected with the detector, in being performed to the underwater laser image
Value filtering, to filter the spot noise in the underwater laser image, obtains the first filtering image；The low pass filtered marble equipment with
The sub- equipment connection of medium filtering, for removing the random noise in first filtering image, obtains the second filtering image；
The sub- equipment of homomorphic filtering is connected with the low pass filtered marble equipment, increases for performing image to second filtering image
By force, obtaining enhancing underwater picture；The sub- equipment of feature extraction is connected with the sub- equipment of pretreatment, including image segmentation list
Unit and eigenvector recognition unit, described image cutting unit is based on weld image gray threshold scope schemes the enhancing under water
Weld seam target identification as in is out obtaining Underwater weld seam image；The eigenvector recognition unit is split single with described image
Unit's connection, 8 geometric properties of underwater weld target are determined based on the Underwater weld seam image：Euler's hole count, circularity, angle point
Number, convex-concave degree, smoothness, draw ratio, tight ness rating and main shaft angle, and 8 geometric properties composition characteristics is vectorial；It is described
Welding type recognizes that sub- equipment is connected with the sub- equipment of the feature extraction, using single hidden layer BP neural network of the output of 8 input 2,
Using 8 geometric properties of underwater weld target as input layer, output layer is underwater weld type, the underwater weld
Type includes general type and cannot welds types.
The underwater robot also includes：Main control device, is arranged on the underwater human agent, with the weld seam class
Type recognizes the connection of sub- equipment, when receive the underwater weld type for cannot welds types when, send alarm signal, work as reception
To the underwater weld type be general type when, according to Underwater weld seam image under water laser image relative position determine electricity
Soldering turret drive signal.
Alternatively, in the underwater robot based on multiple filter treatment：Submerged cable, for the master control to be set
It is standby to be connected with jig waterborne, the alarm signal is sent to the jig waterborne；The sub- equipment of medium filtering,
The low pass filtered marble equipment and the sub- equipment of the homomorphic filtering are respectively adopted different fpga chips to realize；The intermediate value filter
Marble equipment, the low pass filtered marble equipment and the sub- equipment of the homomorphic filtering are integrated on one piece of surface-mounted integrated circuit；It is described
Main control device is digital signal processor, the dsp chip of model TI companies.
In addition, FPGA (Field-Programmable Gate Array), i.e. field programmable gate array, he be
The product further developed on the basis of the programming devices such as PAL, GAL, CPLD.He is led as application specific integrated circuit (ASIC)
A kind of semi-custom circuit in domain and occur, both solved the deficiency of custom circuit, original programming device door is overcome again
The limited shortcoming of circuit number.
With the circuit design that hardware description language (Verilog or VHDL) is completed, can be by simple synthesis and cloth
Office, is quickly burned onto on FPGA and is tested, and is the technology main flow of modern IC designs checking.These editable elements can be by
For realize some basic logic gates (such as AND, OR, XOR, NOT) or more more complicated combination function such as
Decoder or mathematical equation.Inside most FPGA, also for example touched comprising memory cell in these editable elements
Hair device (Flip-flop) or other more complete block of memory.System designer can be as desired by editable company
Connect the logical block inside FPGA to couple together, just look like that a breadboard has been placed in a chip.One dispatches from the factory
The logical block of finished product FPGA afterwards and connection can change according to designer, so FPGA can complete required logic work(
Energy.
Speed of the FPGA in general than ASIC (application specific integrated circuit) is slow, realizes same function than ASIC circuit face
Product is big.But they also have the advantages that it is many such as can quick finished product, the mistake that can be modified in correction program and
Less expensive cost.Manufacturer is likely to the FPGA of the still edit capability difference that can provide cheap.Because these chips have poor
Editable ability, so these design exploitations be on common FPGA complete, design is then transferred to a class
It is similar on the chip of ASIC.Another method is with CPLD (Complex Programmable Logic Device, complexity
PLD).The exploitation of FPGA is very different relative to the exploitation of traditional PC, main control device.FPGA transporting parallel
Based on calculation, realized with hardware description language；Compared to PC or main control device (either von Neumann structure or Harvard knot
Structure) order operation have very big difference.
Early in 1980 mid-nineties 90s, FPGA takes root in PLD equipment.CPLD and FPGA include some relatively large numbers
The Programmadle logic unit of amount.The density of CPLD gates is between thousands of to tens of thousands of logic units, and FPGA is typically
It is tens of thousands of to millions of.The main distinction of CPLD and FPGA is their system architecture.CPLD is a somewhat restricted structure.
This structure is by the logical groups row of one or more editable result sum and the register of the locking of some relatively small amounts
Composition.Such result is a lack of editing flexibility, but but have it is anticipated that time delay and logic unit it is single to connection
The advantage of first height ratio.And FPGA is that have many connection units, although so allowing him can more flexibly to edit,
Structure is complicated more.
Using the underwater robot based on multiple filter treatment of the invention, in the prior art because underwater environment is special
The technical problem for being difficult to automatic Underwater Welding for very causing, has transformed the concrete structure of underwater robot and welding equipment, draws
A series of targetedly electronic assistance aids of adaptation underwater environments are entered, auxiliary underwater robot is automatic using welding equipment
Complete Underwater Welding work.
Although it is understood that the present invention is disclosed as above with preferred embodiment, but above-described embodiment and being not used to
Limit the present invention.For any those of ordinary skill in the art, in the case where technical solution of the present invention ambit is not departed from,
Many possible variations and modification are all made to technical solution of the present invention using the technology contents of the disclosure above, or is revised as
With the Equivalent embodiments of change.Therefore, every content without departing from technical solution of the present invention, according to technical spirit pair of the invention
Any simple modification, equivalent variation and modification made for any of the above embodiments, still fall within the scope of technical solution of the present invention protection
It is interior.
Claims (1)
1. a kind of underwater robot based on multiple filter treatment, for automatic welding under water, the underwater robot includes water
Lower robot body, laser imaging apparatus and weld seam recognition equipment, the laser imaging apparatus and the weld seam recognition equipment are all
On the underwater human agent, the laser imaging apparatus are used to shoot underwater laser image, and the weld seam recognition sets
It is standby to be connected with the laser imaging apparatus, for extracting underwater weld feature from the underwater laser image and determining weld seam class
Type；
Characterized in that, the underwater robot also includes：
Electrode holders, for fixing welding rod, the welding rod is wet method coated electrode, and material is mild steel；
Safety switch, its cathode conductor is connected to the electrode holders；
Earth clip, is fixed on workpiece to be welded；
Electric welding machine, negative pole is connected to the electrode holders, plus earth；
Electrode holders driving equipment, and the electric welding clipper joint, for driving the electrode holders to go to according to electrode holders drive signal
The position while welding of workpiece to be welded；
Electrode holders motor, is a direct current generator, and the driving for the electrode holders driving equipment to the electrode holders provides dynamic
Power；
The underwater human agent includes support, left pressure gram transparent tube, right pressure gram transparent tube, connecting hoop, storage platform, machine
Tool arm, manipulator, water proof sealing drum, transverse propeller, vertical screw, longitudinal screw and three direct current generators, the branch
Frame is used to be fixed on the underwater human agent under water, and the connecting hoop is fixedly connected with the support, the storage platform
It is connected respectively with the connecting hoop with the mechanical arm, the manipulator is connected with the mechanical arm, the mechanical arm includes big
Arm and the forearm being connected with large arm, three direct current generators drive respectively the transverse propeller, the vertical screw and
The longitudinal screw, with by the rotating of propeller, for underwater human agent provides 6 thrust powers of the free degree；
Mobile hard disk, on the underwater human agent, for having prestored under the luminance threshold upper limit and luminance threshold
Limit；
Sonar, on the underwater human agent, for the submarine target in front of the underwater human agent
Sonar image collection is performed, to obtain sonar image；
Sonar image processing equipment, is connected respectively with the sonar and the mobile hard disk, including the first sub- equipment of detection,
The second sub- equipment of detection and the sub- equipment of object range detection, the sub- equipment of first detection and the sonar and the movement
Hard disk is connected respectively, for using the luminance threshold upper limit to travel through sonar image to be partitioned into core objective region；Second inspection
Survey sub- equipment to be connected respectively with the described first sub- equipment of detection and the mobile hard disk, for the side in the core objective region
Edge point carries out brightness judgement using luminance threshold lower limit as seed point to the pixel of core objective areas adjacent, to obtain
And it is partitioned into final goal region；The sub- equipment of object range detection is connected with the described second sub- equipment of detection, calculates final
The central point of target area detects the distance of origin and as target range output to sonar image；
The laser imaging apparatus, including laser, detector and microcontroller, the laser is to the underwater robot master
Submarine target in front of body sends laser beam, when the laser beam reflexes to the detector by submarine target, to be easy to institute
The shooting of detector is stated, the microcontroller is distinguished with the sonar image processing equipment, the laser and the detector
Connection, based on target range and laser, spread speed determines the gating time of the detector shutter under water, and in gating
Between when reaching, gate the shutter of the detector, trigger the detector and submarine target shot, to obtain underwater laser
Image；
The weld seam recognition equipment includes that the sub- equipment of pretreatment, the sub- equipment of feature extraction and welding type recognize sub- equipment；
The sub- equipment of pretreatment is connected with the laser imaging apparatus, including the sub- equipment of medium filtering, low pass filtered marble equipment
With the sub- equipment of homomorphic filtering；The sub- equipment of medium filtering is connected with the detector, for being held to the underwater laser image
Row medium filtering, to filter the spot noise in the underwater laser image, obtains the first filtering image；The low pass filtered marble sets
It is standby to be connected with the sub- equipment of the medium filtering, for removing the random noise in first filtering image, obtain second and filter
Image；The sub- equipment of homomorphic filtering is connected with the low pass filtered marble equipment, for performing figure to second filtering image
Image intensifying, to obtain enhancing underwater picture；
The sub- equipment of feature extraction is connected with the sub- equipment of pretreatment, including image segmentation unit and eigenvector recognition list
Unit, described image cutting unit is based on weld image gray threshold scope by the weld seam target identification in the enhancing underwater picture
Out obtaining Underwater weld seam image；The eigenvector recognition unit is connected with described image cutting unit, based on the water
Lower weld image determines 8 geometric properties of underwater weld target：Euler's hole count, circularity, angle point number, convex-concave degree, smoothness, length
Footpath ratio, tight ness rating and main shaft angle, and 8 geometric properties composition characteristics is vectorial；
The welding type recognizes that sub- equipment is connected with the sub- equipment of the feature extraction, using single hidden layer BP god of the output of 8 input 2
Through network, using 8 geometric properties of underwater weld target as input layer, output layer is underwater weld type, described
Underwater weld type includes general type and cannot welds types；
Main control device, is arranged on the underwater human agent, recognizes that sub- equipment is connected with the welding type, when receiving
The underwater weld type for cannot welds types when, alarm signal is sent, when receiving the underwater weld type for conventional
During type, the relative position according to Underwater weld seam image laser image under water determines electrode holders drive signal.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610607478.XA CN106077889A (en) | 2015-08-04 | 2015-08-04 | The underwater robot processed based on multiple filter |
| CN201510470296.8A CN104999164B (en) | 2015-08-04 | 2015-08-04 | Underwater robot based on multiple filter treatment |
| CN201610573333.2A CN106112202B (en) | 2015-08-04 | 2015-08-04 | Underwater robot based on multiple filter processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510470296.8A CN104999164B (en) | 2015-08-04 | 2015-08-04 | Underwater robot based on multiple filter treatment |
Related Child Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610573333.2A Division CN106112202B (en) | 2015-08-04 | 2015-08-04 | Underwater robot based on multiple filter processing |
| CN201610607478.XA Division CN106077889A (en) | 2015-08-04 | 2015-08-04 | The underwater robot processed based on multiple filter |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104999164A CN104999164A (en) | 2015-10-28 |
| CN104999164B true CN104999164B (en) | 2017-05-31 |
Family
ID=54372164
Family Applications (3)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610607478.XA Pending CN106077889A (en) | 2015-08-04 | 2015-08-04 | The underwater robot processed based on multiple filter |
| CN201610573333.2A Active CN106112202B (en) | 2015-08-04 | 2015-08-04 | Underwater robot based on multiple filter processing |
| CN201510470296.8A Active CN104999164B (en) | 2015-08-04 | 2015-08-04 | Underwater robot based on multiple filter treatment |
Family Applications Before (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610607478.XA Pending CN106077889A (en) | 2015-08-04 | 2015-08-04 | The underwater robot processed based on multiple filter |
| CN201610573333.2A Active CN106112202B (en) | 2015-08-04 | 2015-08-04 | Underwater robot based on multiple filter processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (3) | CN106077889A (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107669425A (en) * | 2016-05-24 | 2018-02-09 | 孙霞 | Cardiological operation table |
| CN107274391A (en) * | 2017-06-07 | 2017-10-20 | 梧州市兴能农业科技有限公司 | A kind of underwater picture Objective extraction system |
| CN109544577B (en) * | 2018-11-27 | 2022-10-14 | 辽宁工程技术大学 | Improved straight line extraction method based on edge point grouping |
| CN110493509B (en) * | 2019-06-26 | 2021-03-19 | 盐城华昱光电技术有限公司 | Image information processing system and method of laser module |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101745765A (en) * | 2009-12-15 | 2010-06-23 | 哈尔滨工业大学 | Man-machine collaboration shared control remote welding method |
| CN203599683U (en) * | 2013-11-05 | 2014-05-21 | 西安扩力机电科技有限公司 | Underwater welding monitoring system |
| CN104588833A (en) * | 2015-01-24 | 2015-05-06 | 无锡桑尼安科技有限公司 | Underwater welding robot based on image identification |
| CN104625320A (en) * | 2015-01-24 | 2015-05-20 | 无锡桑尼安科技有限公司 | Underwater welding method |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003230959A (en) * | 2002-02-06 | 2003-08-19 | Toshiba Corp | Remote operation welding robot system |
| CN102042835B (en) * | 2010-11-05 | 2012-10-24 | 中国海洋大学 | Autonomous underwater vehicle combined navigation system |
| CN104607762A (en) * | 2013-11-05 | 2015-05-13 | 西安扩力机电科技有限公司 | Underwater welding wireless monitoring system |
| CN104607758A (en) * | 2013-11-05 | 2015-05-13 | 西安扩力机电科技有限公司 | Underwater welding monitoring system |
| CN204228171U (en) * | 2014-11-19 | 2015-03-25 | 山东华盾科技股份有限公司 | A kind of underwater robot guider |
| CN204397131U (en) * | 2015-01-24 | 2015-06-17 | 无锡桑尼安科技有限公司 | Based on the Underwater Welding robot of image recognition |
| CN105127626B (en) * | 2015-01-24 | 2016-08-24 | 南通巨升非晶科技有限公司 | Underwater weld automatic recognition system |
| CN204359703U (en) * | 2015-01-24 | 2015-05-27 | 无锡桑尼安科技有限公司 | Underwater weld automatic recognition system |
| CN105234597A (en) * | 2015-01-24 | 2016-01-13 | 宋健 | Automatic underwater weld joint recognition method |
-
2015
- 2015-08-04 CN CN201610607478.XA patent/CN106077889A/en active Pending
- 2015-08-04 CN CN201610573333.2A patent/CN106112202B/en active Active
- 2015-08-04 CN CN201510470296.8A patent/CN104999164B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101745765A (en) * | 2009-12-15 | 2010-06-23 | 哈尔滨工业大学 | Man-machine collaboration shared control remote welding method |
| CN203599683U (en) * | 2013-11-05 | 2014-05-21 | 西安扩力机电科技有限公司 | Underwater welding monitoring system |
| CN104588833A (en) * | 2015-01-24 | 2015-05-06 | 无锡桑尼安科技有限公司 | Underwater welding robot based on image identification |
| CN104625320A (en) * | 2015-01-24 | 2015-05-20 | 无锡桑尼安科技有限公司 | Underwater welding method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104999164A (en) | 2015-10-28 |
| CN106112202B (en) | 2018-10-02 |
| CN106112202A (en) | 2016-11-16 |
| CN106077889A (en) | 2016-11-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104999164B (en) | Underwater robot based on multiple filter treatment | |
| CN110530877B (en) | Welding appearance quality detection robot and detection method thereof | |
| CN109604777A (en) | Welding seam traking system and method based on laser structure light | |
| Liu et al. | The use of laser range finder on a robotic platform for pipe inspection | |
| CN102162577B (en) | Pipeline defect surface integrity detection device and detection method | |
| CN105571502A (en) | Measuring method of weld gap in friction-stir welding | |
| CN104985290A (en) | Neural-network-identification-based underwater weld joint tracking method | |
| CN116012336B (en) | Tunnel intelligent geological sketch and surrounding rock grade identification device and method | |
| Shi et al. | Automated underwater pipeline damage detection using neural nets | |
| CN105096325B (en) | Underwater equipment detection system based on laser image | |
| CN107030690A (en) | A kind of mechanical arm barrier-avoiding method of view-based access control model | |
| CN105665877A (en) | Method for performing underwater automatic welding by using underwater robot | |
| CN105059506A (en) | Intelligent underwater robot based on laser imaging detection | |
| CN105014196A (en) | Underwater weld seam tracking device based on neural network recognition | |
| CN104999201B (en) | A kind of method using underwater robot to carry out automatic welding under water | |
| CN104991259A (en) | Laser imaging detection method | |
| CN116678891A (en) | Detection method, device, system and platform suitable for sealing nail welding position | |
| CN104999200B (en) | Diver portable system | |
| CN105728975A (en) | Method for performing underwater automatic welding by using underwater robot | |
| CN105160638A (en) | Image processing based underwater welding line tracking system | |
| CN105076077A (en) | Method for recognizing fish body based on laser imaging detection | |
| CN113012115A (en) | Bolt three-dimensional imaging detection system and method | |
| CN105138008A (en) | Multifunctional submersible for underwater submerged reef detection | |
| CN105059507A (en) | Diving device | |
| CN105057884B (en) | The Underwater Welding platform processed based on laser image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB03 | Change of inventor or designer information |
Inventor after: Liang Shaorong Inventor before: Li Xiaochun |
|
| CB03 | Change of inventor or designer information | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20170315 Address after: 750000 Yinchuan Xixia District, Dalian West Road, No. 531 Ningxia industrial and commercial Career Technical College, Department of mechanical and electrical engineering, electrical and electronic technology training center Applicant after: Ningxia Rong photoelectric technology research and Development Co., Ltd. Address before: 056107 Handan Economic Development Zone, Hebei, Century Avenue, No. 9 Applicant before: Li Xiaochun |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |