Summary of the invention
In order to solve the technical problem that prior art exists, the invention provides a kind of underwater robot based on multiple filter process, to transform the concrete structure of existing underwater robot, make it can as jig, recycling sonar and sonar image processing equipment improve laser imaging effect, utilization comprises medium filtering subset, the image-preprocessing device of LPF subset and homomorphic filtering subset realizes the removal to all kinds of interference under water, the image recognition technology based on neural network recognization is utilized to improve the accuracy of weld seam recognition, finally transform welding equipment and can complete automatic welding under water.
According to an aspect of the present invention, provide a kind of underwater robot based on multiple filter process, for automatic welding under water, described underwater robot comprises underwater human agent, laser imaging apparatus and weld seam recognition equipment, described laser imaging apparatus and described weld seam recognition equipment are all positioned on described underwater human agent, described laser imaging apparatus is for taking underwater laser image, described weld seam recognition equipment is connected with described laser imaging apparatus, for extracting underwater weld feature and determine welding type from described underwater laser image.
More specifically, in the described underwater robot based on multiple filter process, also comprise: electrode holders, for fixing welding rod, described welding rod is wet method coated electrode, and material is mild steel, safety switch, its cathode conductor is connected to described electrode holders, earth clip, is fixed on workpiece to be welded, electric welding machine, negative pole is connected to described electrode holders, plus earth, electrode holders driving arrangement, is connected with described electrode holders, for driving described electrode holders to go to the position while welding of workpiece to be welded according to electrode holders drive singal, electrode holders drive motors is a direct current generator, for the driving of described electrode holders driving arrangement to described electrode holders provides power, described underwater human agent comprises support, left pressure gram transparent tube, right pressure gram transparent tube, connecting hoop, storage platform, mechanical arm, manipulator, water proof sealing drum, transverse propeller, vertical screw, longitudinal spiral oar and three direct current generators, described support is used for described underwater human agent to be fixed under water, described connecting hoop is fixedly connected with described support, described storage platform is connected with described connecting hoop respectively with described mechanical arm, described manipulator is connected with described mechanical arm, the forearm that described mechanical arm comprises large arm and is connected with large arm, described three direct current generators drive described transverse propeller respectively, described vertical screw and described longitudinal spiral oar, with the rotating by screw, for underwater human agent provides the thrust power of 6 frees degree, portable hard drive, is positioned on described underwater human agent, for having prestored the luminance threshold upper limit and luminance threshold lower limit, sonar, is positioned on described underwater human agent, for performing sonar image collection, to obtain sonar image to the submarine target in described underwater human agent front, sonar image treatment facility, be connected respectively with described sonar and described portable hard drive, comprise the first detection subset, second and detect subset and object range detection subset, described first detects subset is connected respectively with described sonar and described portable hard drive, travels through sonar image to be partitioned into core objective region for adopting the luminance threshold upper limit, described second detection subset detects subset with described first and described portable hard drive is connected respectively, for using the marginal point in described core objective region as Seed Points, luminance threshold lower limit is utilized to carry out brightness judgement to the pixel of core objective areas adjacent, to obtain and to be partitioned into final goal region, described object range detection subset and described second detects subset and is connected, and the central point calculating final goal region detects the distance of initial point to sonar image and exports as target range, described laser imaging apparatus, comprise laser instrument, detector and microcontroller, the submarine target of described laser instrument to described underwater human agent front gives off laser beam, with when described laser beam is reflexed to described detector by submarine target, be convenient to the shooting of described detector, described microcontroller and described sonar image treatment facility, described laser instrument is connected respectively with described detector, based target Distance geometry laser under water spread speed determines the gating time of described detector shutter, and when gating time arrives, the shutter of detector described in gating, trigger described detector to take submarine target, to obtain underwater laser image, described weld seam recognition equipment comprises pretreatment subset, feature extraction subset and welding type recognin equipment, described pretreatment subset is connected with described laser imaging apparatus, comprises medium filtering subset, LPF subset and homomorphic filtering subset, described medium filtering subset is connected with described detector, for performing medium filtering to described underwater laser image, with the spot noise in underwater laser image described in filtering, obtains the first filtering image, described LPF subset is connected with described medium filtering subset, for removing the random noise in described first filtering image, obtains the second filtering image, described homomorphic filtering subset is connected with described LPF subset, for performing image enhaucament, to obtain enhancing underwater picture to described second filtering image, described feature extraction subset is connected with described pretreatment subset, comprise image segmentation unit and eigenvector recognition unit, the weld seam target in described enhancing underwater picture identifies to obtain Underwater weld seam image based on weld image gray threshold scope by described image segmentation unit, described eigenvector recognition unit is connected with described image segmentation unit, 8 geometric properties based on described Underwater weld seam image determination underwater weld target: Euler's hole count, circularity, angle point number, convex-concave degree, smoothness, draw ratio, tight ness rating and main shaft angle, and by described 8 geometric properties composition characteristics vector, described welding type recognin equipment is connected with described feature extraction subset, adopt single hidden layer BP neutral net that 8 inputs 2 export, using 8 of underwater weld target geometric properties as input layer, output layer is underwater weld type, and described underwater weld type comprises general type and cannot welds types, main control device, be arranged on described underwater human agent, with described welding type recognin equipment connection, when receive described underwater weld type for cannot welds types time, send alarm signal, when to receive described underwater weld type be general type, according to the relative position determination electrode holders drive singal of Underwater weld seam image laser image under water.
More specifically, in the described underwater robot based on multiple filter process: submerged cable, for being connected with jig waterborne by described main control device, described alarm signal is sent to described jig waterborne.
More specifically, in the described underwater robot based on multiple filter process: described medium filtering subset, described LPF subset and described homomorphic filtering subset adopt different fpga chips to realize respectively.
More specifically, in the described underwater robot based on multiple filter process: described medium filtering subset, described LPF subset and described homomorphic filtering subset are integrated on one piece of surface-mounted integrated circuit.
More specifically, in the described underwater robot based on multiple filter process: described main control device is digital signal processor, model is the dsp chip of TI company.
Detailed description of the invention
Below with reference to accompanying drawings the embodiment of the underwater robot based on multiple filter process of the present invention is described in detail.
First Underwater Welding accurately will identify position while welding, in prior art, the general image recognition mode that adopts is carried out, but, the shutter control difficulty of current underwater laser images, cause underwater laser image effect not good, lack suitable Underwater Navigation equipment and image filtering equipment simultaneously, make the precision of Underwater Welding not high.
In order to overcome above-mentioned deficiency, the present invention has built a kind of underwater robot based on multiple filter process, multiple filter mode is adopted to carry out pretreatment to image, optimize underwater laser images technology and underwater installation location technology, simultaneously, transformation underwater robot and welding equipment, make automatic welding under water become possibility.
Fig. 1 is the block diagram of the underwater robot based on multiple filter process illustrated according to an embodiment of the present invention, described underwater robot comprises underwater human agent, laser imaging apparatus and weld seam recognition equipment, described laser imaging apparatus and described weld seam recognition equipment are all positioned on described underwater human agent, described laser imaging apparatus is for taking underwater laser image, described weld seam recognition equipment is connected with described laser imaging apparatus, for extracting underwater weld feature and determine welding type from described underwater laser image.
Then, continue to be further detailed the concrete structure of the underwater robot based on multiple filter process of the present invention.
Described underwater robot also comprises: electrode holders, and for fixing welding rod, described welding rod is wet method coated electrode, and material is mild steel; Safety switch, its cathode conductor is connected to described electrode holders; Earth clip, is fixed on workpiece to be welded; Electric welding machine, negative pole is connected to described electrode holders, plus earth; Electrode holders driving arrangement, is connected with described electrode holders, for driving described electrode holders to go to the position while welding of workpiece to be welded according to electrode holders drive singal; Electrode holders drive motors is a direct current generator, for the driving of described electrode holders driving arrangement to described electrode holders provides power.
Described underwater human agent comprises support, left pressure gram transparent tube, right pressure gram transparent tube, connecting hoop, storage platform, mechanical arm, manipulator, water proof sealing drum, transverse propeller, vertical screw, longitudinal spiral oar and three direct current generators, described support is used for described underwater human agent to be fixed under water, described connecting hoop is fixedly connected with described support, described storage platform is connected with described connecting hoop respectively with described mechanical arm, described manipulator is connected with described mechanical arm, the forearm that described mechanical arm comprises large arm and is connected with large arm, described three direct current generators drive described transverse propeller respectively, described vertical screw and described longitudinal spiral oar, with the rotating by screw, for underwater human agent provides the thrust power of 6 frees degree.
Described underwater robot also comprises: portable hard drive, is positioned on described underwater human agent, for having prestored the luminance threshold upper limit and luminance threshold lower limit.
Described underwater robot also comprises: sonar, is positioned on described underwater human agent, for performing sonar image collection, to obtain sonar image to the submarine target in described underwater human agent front.
Described underwater robot also comprises: sonar image treatment facility, be connected respectively with described sonar and described portable hard drive, comprise the first detection subset, second and detect subset and object range detection subset, described first detects subset is connected respectively with described sonar and described portable hard drive, travels through sonar image to be partitioned into core objective region for adopting the luminance threshold upper limit; Described second detection subset detects subset with described first and described portable hard drive is connected respectively, for using the marginal point in described core objective region as Seed Points, luminance threshold lower limit is utilized to carry out brightness judgement to the pixel of core objective areas adjacent, to obtain and to be partitioned into final goal region; Described object range detection subset and described second detects subset and is connected, and the central point calculating final goal region detects the distance of initial point to sonar image and exports as target range.
Described laser imaging apparatus, comprise laser instrument, detector and microcontroller, the submarine target of described laser instrument to described underwater human agent front gives off laser beam, with when described laser beam is reflexed to described detector by submarine target, be convenient to the shooting of described detector, described microcontroller and described sonar image treatment facility, described laser instrument is connected respectively with described detector, based target Distance geometry laser under water spread speed determines the gating time of described detector shutter, and when gating time arrives, the shutter of detector described in gating, trigger described detector to take submarine target, to obtain underwater laser image.
Described weld seam recognition equipment comprises pretreatment subset, feature extraction subset and welding type recognin equipment; Described pretreatment subset is connected with described laser imaging apparatus, comprises medium filtering subset, LPF subset and homomorphic filtering subset; Described medium filtering subset is connected with described detector, for performing medium filtering to described underwater laser image, with the spot noise in underwater laser image described in filtering, obtains the first filtering image; Described LPF subset is connected with described medium filtering subset, for removing the random noise in described first filtering image, obtains the second filtering image; Described homomorphic filtering subset is connected with described LPF subset, for performing image enhaucament, to obtain enhancing underwater picture to described second filtering image; Described feature extraction subset is connected with described pretreatment subset, comprise image segmentation unit and eigenvector recognition unit, the weld seam target in described enhancing underwater picture identifies to obtain Underwater weld seam image based on weld image gray threshold scope by described image segmentation unit; Described eigenvector recognition unit is connected with described image segmentation unit, 8 geometric properties based on described Underwater weld seam image determination underwater weld target: Euler's hole count, circularity, angle point number, convex-concave degree, smoothness, draw ratio, tight ness rating and main shaft angle, and by described 8 geometric properties composition characteristics vector; Described welding type recognin equipment is connected with described feature extraction subset, adopt single hidden layer BP neutral net that 8 inputs 2 export, using 8 of underwater weld target geometric properties as input layer, output layer is underwater weld type, and described underwater weld type comprises general type and cannot welds types.
Described underwater robot also comprises: main control device, be arranged on described underwater human agent, with described welding type recognin equipment connection, when receive described underwater weld type for cannot welds types time, send alarm signal, when to receive described underwater weld type be general type, according to the relative position determination electrode holders drive singal of Underwater weld seam image laser image under water.
Alternatively, in the described underwater robot based on multiple filter process: submerged cable, for being connected with jig waterborne by described main control device, described alarm signal is sent to described jig waterborne; Described medium filtering subset, described LPF subset and described homomorphic filtering subset adopt different fpga chips to realize respectively; Described medium filtering subset, described LPF subset and described homomorphic filtering subset are integrated on one piece of surface-mounted integrated circuit; Described main control device is digital signal processor, and model is the dsp chip of TI company.
In addition, FPGA (Field-Programmable Gate Array), i.e. field programmable gate array, he is the product further developed on the basis of the programming devices such as PAL, GAL, CPLD.He occurs as a kind of semi-custom circuit in special IC (ASIC) field, has both solved the deficiency of custom circuit, overcomes again the shortcoming that original programming device gate circuit number is limited.
With the circuit design that hardware description language (Verilog or VHDL) completes, can through simple comprehensive and layout, being burned onto fast on FPGA and testing, is the technology main flow of modern IC designs checking.These can be edited element and can be used to realize some basic logic gates (such as AND, OR, XOR, NOT) or more more complex combination function such as decoder or mathematical equation.Inside most FPGA, in these editable elements, also comprise memory cell such as trigger (Flip-flop) or other more complete block of memory.System designer can be coupled together the logical block of FPGA inside by editable connection as required, just looks like that a breadboard has been placed in a chip.One dispatch from the factory after the logical block of finished product FPGA can change according to designer with being connected, so FPGA can complete required logic function.
FPGA is in general slow than the speed of ASIC (special IC), realizes same function ratio ASIC circuit area and wants large.But they also have a lot of advantages such as can finished product fast, can be modified the mistake in correction program and more cheap cost.Manufacturer also may provide the FPGA of cheap still edit capability difference.Because these chips have poor can edit capability, so exploitations of these designs complete on common FPGA, then design is transferred to one and is similar on the chip of ASIC.Another method is with CPLD (Complex Programmable LogicDevice, CPLD).The exploitation of FPGA has a great difference relative to the exploitation of conventional P C, main control device.FPGA, based on concurrent operation, realizes with hardware description language; Very large difference is had compared to the operation in tandem of PC or main control device (no matter being von Neumann structure or Harvard structure).
As far back as 1980 mid-nineties 90s, FPGA takes root in PLD equipment.CPLD and FPGA includes the Programmadle logic unit of some relatively large amount.The density of CPLD gate is between several thousand to several ten thousand logical blocks, and FPGA normally arrives millions of several ten thousand.The main distinction of CPLD and FPGA is their system architecture.CPLD is a somewhat restrictive structure.This structure is arranged by the logical groups of one or more editable result sum and forms with the register of the locking of some relatively small amounts.Such result lacks editor's flexibility, but but have the time delay and logical block that can estimate to the advantage of linkage unit height ratio.And FPGA has a lot of linkage units, although allow him edit more flexibly like this, structure is complicated many.
Adopt the underwater robot based on multiple filter process of the present invention, for special due to underwater environment in prior art and the technical problem being difficult to automatic Underwater Welding that is that cause, transform the concrete structure of underwater robot and welding equipment, introduce the electronic assistance aids targetedly of a series of adaptation underwater environment, auxiliary underwater robot adopts welding equipment automatically to complete Underwater Welding work.
Be understandable that, although the present invention with preferred embodiment disclose as above, but above-described embodiment and be not used to limit the present invention.For any those of ordinary skill in the art, do not departing under technical solution of the present invention ambit, the technology contents of above-mentioned announcement all can be utilized to make many possible variations and modification to technical solution of the present invention, or be revised as the Equivalent embodiments of equivalent variations.Therefore, every content not departing from technical solution of the present invention, according to technical spirit of the present invention to any simple modification made for any of the above embodiments, equivalent variations and modification, all still belongs in the scope of technical solution of the present invention protection.