CN108747043A - A kind of plate with laser cutting machine and control method, computer - Google Patents
A kind of plate with laser cutting machine and control method, computer Download PDFInfo
- Publication number
- CN108747043A CN108747043A CN201810516777.1A CN201810516777A CN108747043A CN 108747043 A CN108747043 A CN 108747043A CN 201810516777 A CN201810516777 A CN 201810516777A CN 108747043 A CN108747043 A CN 108747043A
- Authority
- CN
- China
- Prior art keywords
- antibody
- cut
- cutting machine
- laser cutting
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
- B23K26/00—Working by laser beam, e.g. welding, cutting or boring
- B23K26/36—Removing material
- B23K26/38—Removing material by boring or cutting
-
- 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
- B23K26/00—Working by laser beam, e.g. welding, cutting or boring
- B23K26/70—Auxiliary operations or equipment
- B23K26/702—Auxiliary equipment
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Optics & Photonics (AREA)
- Plasma & Fusion (AREA)
- Mechanical Engineering (AREA)
- Laser Beam Processing (AREA)
Abstract
The invention belongs to laser cutting technique field, a kind of plate with laser cutting machine and control method, computer are disclosed, the location drawing picture data of plank to be cut are acquired;Image location information is logical to be obtained:The marginal information of each sequence image is obtained, and each sequence image is divided into identical region, adaptive vaccine extraction mechanism is used by immune genetic method, obtains aggregation location information;And location information is marked the three-dimensionalreconstruction of object;According to the label after three-dimensionalreconstruction, the adjusting of focal length is automatically controlled by central processing module;Plank is cut by laser after covering heat-sink shell on the cutting track of cutting board to be cut.The present invention improves nearly 10% compared with the prior art by immune genetic method, accuracy rate;Product qualification rate improves nearly 15%, and guarantee is provided for the benefit of enterprise;The control method of the present invention extends to other fine chemistry industries or other precision control production fields simultaneously.
Description
Technical field
The invention belongs to laser cutting technique field more particularly to a kind of plate with laser cutting machine and control method, calculating
Machine.
Background technology
Currently, the prior art commonly used in the trade is such:
Laser cutting, by cutting material, makes material be heated to vaporization temperature quickly using the irradiation of high power density laser beam
Degree, evaporation form hole, and the movement with light beam to material, hole is formed continuously (such as 0.1mm or so) joint-cutting of narrower in width,
Complete the cutting to material.Most of laser cutting machines all carry out control operation by numerical control program or make cutting robot.Swash
Light cutting is used as a kind of processing method of precision, can almost cut all materials, including metal sheet it is two-dimentional cut or
Three dimensional slots.
Extensive use has all been obtained in the cutting technique of automobile manufacturing field, the space curves such as car roof window.Germany
The automotive bobdy sheet metal for the laser cutting profile complexity that Volkswagen is 500W with power and various curved-surface pieces.In aerospace
Field, laser cutting technique are mainly used for the cutting of extraordinary aeronautical material, such as titanium alloy, aluminium alloy, nickel alloy, evanohm, no
Become rusty steel, beryllium oxide, composite material, plastics, ceramics and quartz etc..There is engine with the aerospace parts of laser cutting process
Burner inner liner, titanium alloy thin wall casing, aircraft ring frames, titanium alloy covering, wing stringer, empennage siding, Helicopter Main rotor, space flight
Aircraft ceramic insulation watt etc..However, existing plate with laser cutting machine laser regulating effect is poor, cause cut quality poor;It cuts simultaneously
The defects of crackle is easy tod produce when cutting, and then influence the quality of plate product.
In conclusion problem of the existing technology is:
Existing plate with laser cutting machine laser regulating effect is poor, causes cut quality poor;It easy tos produce and splits when cutting simultaneously
The defects of line, and then influence the quality of plate product.
In the prior art, in image processing method, commonly used nonnegative matrix processing method, binarization method are waiting for
In the plank different shape image real time transfer of cutting, there is that data accuracy is poor, affects the quality of product, the prior art
Immune genetic method is not bound with accurately to be handled.
Invention content
In view of the problems of the existing technology, the present invention provides a kind of plate with laser cutting machine and control method, calculating
Machine.
The invention is realized in this way a kind of plate with laser cutting machine control method, the plate with laser cutting machine control
Method includes:
Acquire the location drawing picture data of plank to be cut;
Image location information is logical to be obtained:The marginal information of each sequence image is obtained, and each sequence image is divided into
Identical region uses adaptive vaccine extraction mechanism, first, by institute until iteration to current algebraically by immune genetic method
The 20 optimal antibody occurred extract, and form vaccine library, and carried out more to vaccine library before next iteration starts
Newly;Secondly, a vaccine antibody is extracted from this 20 optimal antibody, the symbol in each gene position of vaccine antibody is taken as this
The maximum symbol of probability of occurrence in gene position is corresponded in 20 optimal antibody;According to inoculation probability PvIt chooses and passes through genetic manipulation shape
At new antibodies carry out vaccine inoculation, and compare the affinity of inoculation front and back antibody and antigen;Inoculation operation can improve antibody
Fitness then receive inoculation, otherwise abandon being inoculated with;The probability P of immunity inoculationv=0.7;Obtain aggregation location information;And it aligns
Confidence ceases the three-dimensionalreconstruction that object is marked;
According to the label after three-dimensionalreconstruction, the adjusting of focal length is automatically controlled by central processing module;
Plank is cut by laser after covering heat-sink shell on the cutting track of cutting board to be cut;
Further, immune genetic method includes:
Step 1, decision variable setting:
Decision variable X={ C;S } it is made of two parts vector, the value of all vector elements is 0 or 1, structure such as following formula
It is shown;
C={ C11,C12,C21,C22,...,Cn1,Cn2} (1);
S={ S1,S2,...,Sm}
In formula:N is the positional number of plank to be cut, and m is the feasible cutting position number of laser cutting machine;Ci1、Ci2(i=1,
2 ..., n) class of a curve whether the i-th feasible location of plank to be cut needs the position cut and needs to cut is indicated respectively
Type;Si(i=1,2 ..., m) indicate whether i-th of feasible cutting position of laser cutting machine actually has laser cutting machine light beam;
Step 2, initial population generate:
The initial value in population antibody in each gene position is generated according to random sampling shown in formula (1);
By improving the value of P in formula (2), whether representing laser cutting machine beam emissions in reduction antibody character string
Gene location there is the number of character " 1 ", sample Ci1、SiWhen the genic value of position, P values are 0.9;In sampling Ci2Value
When, P values are 0.5;The size of initial population is selected as 100;
Step 3, genetic manipulation:
As shown in formula (3);The select probability that the antibody vector distance value of fitness value calculation is determined by affinity and concentration
Decision, affinity and concentration calculation formula are respectively as shown in formula (4) and formula (5);
The select probability of concentration and affinity is:
In formula:α is the weight coefficient for adjusting select probability;PfiWith PdiRespectively determined by the affinity and concentration of antibody i
Fixed select probability;
The calculating of affinity:If there is N number of antibody in population, wherein the affinity of antibody i is fi, then PfiIt is selected using direct ratio
Strategy obtains:
Wherein, i=1,2 ..., N;
The calculating of concentration:When using vector away from antibody concentration is indicated,It calculates as follows:
Crossover operation uses the form of two-point crossover, crossover probability PcIt is set as 0.9, using dynamic in Population Variation operation
State aberration rate, as shown in formula (6);
PMg=PMmin+(PMmax-PMmin)·rg(6);
In formula:PMgIt is g for the aberration rate of population antibody, PMminWith PMmaxThe respectively minimum value of aberration rate and maximum
Value;R is contraction factor, and 0.99 is taken as in analysis;
Using adaptive vaccine extraction mechanism;First, the 20 optimal antibody that will occur until iteration to current algebraically
It extracts, forms vaccine library, and be updated to vaccine library before next iteration starts;Secondly, most from this 20
A vaccine antibody is extracted in excellent antibody, the symbol in each gene position of vaccine antibody is taken as in this 20 optimal antibody corresponding
The maximum symbol of probability of occurrence in gene position;According to inoculation probability PvIt chooses and carries out vaccine by the new antibodies that genetic manipulation is formed
Inoculation, and compare the affinity of inoculation front and back antibody and antigen;The fitness that inoculation operation can improve antibody then receives inoculation,
Otherwise it abandons being inoculated with;The probability P of immunity inoculationv=0.7;
Step 5, the evolution of vaccine library:
In promoting the evolutionary process of vaccine library using clone's genetic algorithm, clonal plant population is dimensioned to 100, each
Clone's quantity of a antibody is calculated using formula (7);Fixed aberration rate P is used in gene mutation operatorm=0.1;
During clone, the number q of each antibody duplicationiAs shown in formula
Wherein, if there is n antibody in initial population, i.e. A (k)={ a1,a2,…,an, the affinity of wherein antibody i is denoted as
For f (ai), the capacity of population A ' (k) after cloning is set as Nc, take Nc>n;
Wherein operator [x] indicates the maximum integer no more than x;
Step 6, population recruitment:
After immune operation, the affinity replaced in population with quantity with highest 5 antibody of affinity in vaccine library is worst
Individual;It is random to generate 85% antibody that affinity is poor in population when not searching more excellent solution in continuous 20 generation;
Further, immune genetic method further comprises end condition:It is used as eventually using 300 generation of fixed genetic algebra is reached
Only condition.
Further, the logical acquisition methods of image location information include:
(1) marginal information of each sequence image is obtained, and each sequence image is divided into identical region;
(2) average gradient in each region is calculated, the position of each region focus is obtained, it is clear to obtain each region
Clear image;
(3) aggregation location information is obtained by immune genetic method, interpolation fitting has been carried out to the focal position information, has been obtained
Obtain accurate location information;
Image three-dimensional reconstruction method includes:
(i) using the elevation information in obtained location information as Z axis, each point in each image generates X, Y, Z
Three-dimensional coordinate;
(ii) three-dimension object is reconstructed by the three-dimensional coordinate of each point in image.
Further, laser cutting method includes:
First, heat-sink shell is covered on the cutting track of cutting board to be cut;
Then, laser irradiation cuts the cutting board to be cut to the heat-sink shell and along the cutting track;
Finally, the heat-sink shell on the cutting board to be cut after cutting is completed in removal;
The cutting track includes regular track and irregular track, and the heat-sink shell covered on the rule track is
Multilayer, the heat-sink shell covered on the irregular track are at least one layer;
The number of plies of the heat-sink shell covered on regular track is less than the heat-sink shell covered on the irregular track
The number of plies.
Another object of the present invention is to provide a kind of computer journeys for realizing the plate with laser cutting machine control method
Sequence.
Another object of the present invention is to provide a kind of computers for realizing the plate with laser cutting machine control method.
Another object of the present invention is to provide a kind of computer readable storage mediums, including instruction, when it is in computer
When upper operation so that computer executes the plate with laser cutting machine control method.
Another object of the present invention is to provide a kind of plate with laser for realizing the plate with laser cutting machine control method
Cutting machine, the plate with laser cutting machine include:
Laser emitting module is connect with central processing module, emits laser for passing through laser generator;
Image capture module is connect with central processing module, the location drawing for acquiring plank to be cut by camera
As data;
Central processing module, with laser emitting module, image capture module, image processing module, automatic focusing module, cut
Module, data disaply moudle connection are cut, for controlling modules normal work;
Image processing module is connect with central processing module, for believing the position for obtaining plank sequence image to be cut
It ceases, and the three-dimensionalreconstruction of object is marked by the location information;
Automatic focusing module, connect with central processing module, for being automatically controlled by the label object after three-dimensionalreconstruction
The adjusting of focal length;
Cutting module is connect with central processing module, for carrying out cutting operation to plank;
Data disaply moudle is connect with central processing module, the image data for showing acquisition.
Another object of the present invention is to provide a kind of computers equipped with the plate with laser cutting machine.
Advantages of the present invention and good effect are:
The present invention acquires the location drawing picture data of plank to be cut by image capture module, utilizes image processing module pair
Collected sequence image carries out the location information that corresponding image processing operations obtain label object, finally by the position of acquisition
Confidence breath control automatic focusing module realizes that the adjust automatically of focal length, the present invention improve the defect of focus adjustment method under traditional approach,
Clearly image can be obtained, achievees the effect that good automatic focusing;Simultaneously by cutting module by being cut in progress laser
Before cutting, heat-sink shell is covered on the cutting track of the cutting board to be cut so that laser along the cutting track cut described in wait for
When cutting substrate, the heat-sink shell can partially absorb the thermal energy of the laser, in the base to be cut when to reduce cutting
The size of cutting position and the temperature gradient of surrounding non-cutting position on plate reduces the generation of thermal stress, and then reduces and split
The generation of the defects of line obtains the preferable product of quality.
Iteration to current algebraically is by the present invention first using adaptive vaccine extraction mechanism by immune genetic method
The 20 optimal antibody only occurred extract, formed vaccine library, and before next iteration starts to vaccine library into
Row update;Secondly, a vaccine antibody is extracted from this 20 optimal antibody, the symbol in each gene position of vaccine antibody takes
To correspond to the maximum symbol of probability of occurrence in gene position in this 20 optimal antibody;According to inoculation probability PvIt chooses by heredity behaviour
Make the new antibodies formed and carry out vaccine inoculation, and compares the affinity of inoculation front and back antibody and antigen;Inoculation operation can improve
The fitness of antibody then receives inoculation, otherwise abandons being inoculated with;The probability P of immunity inoculationv=0.7;Obtain aggregation location information;It is accurate
True rate improves nearly 10% compared with the prior art;Product qualification rate improves nearly 15%, and guarantee is provided for the benefit of enterprise;Simultaneously originally
The control method of invention extends to other fine chemistry industries or other precision control production fields.
Description of the drawings
Fig. 1 is plate with laser cutting machine structure block diagram provided in an embodiment of the present invention.
In figure:1, laser emitting module;2, image capture module;3, central processing module;4, image processing module;5, certainly
Dynamic focusing module;6, cutting module;7, data disaply moudle.
Fig. 2 is plate with laser cutting machine control method flow chart provided in an embodiment of the present invention.
Specific implementation mode
In order to further understand the content, features and effects of the present invention, the following examples are hereby given, and coordinate attached drawing
Detailed description are as follows.
The structure of the present invention is explained in detail below in conjunction with the accompanying drawings.
As shown in Figure 1, plate with laser cutting machine provided in an embodiment of the present invention includes:Laser emitting module 1, Image Acquisition
Module 2, central processing module 3, image processing module 4, automatic focusing module 5, cutting module 6, data disaply moudle 7.
Laser emitting module 1 is connect with central processing module 3, emits laser for passing through laser generator;
Image capture module 2 is connect with central processing module 3, the position for acquiring plank to be cut by camera
Image data;
Central processing module 3, with laser emitting module 1, image capture module 2, image processing module 4, automatic focusing mould
Block 5, cutting module 6, data disaply moudle 7 connect, for controlling modules normal work;
Image processing module 4 is connect with central processing module 3, for the position to obtaining plank sequence image to be cut
Information, and the three-dimensionalreconstruction of object is marked by the location information;
Automatic focusing module 5 is connect with central processing module 3, for being controlled automatically by the label object after three-dimensionalreconstruction
The adjusting of focal length processed;
Cutting module 6 is connect with central processing module 3, for carrying out cutting operation to plank;
Data disaply moudle 7 is connect with central processing module 3, the image data for showing acquisition.
Location information in image processing module 4 provided by the invention is obtained by following steps:
(1) marginal information of each sequence image is obtained, and each sequence image is divided into identical region;
(2) average gradient in each region is calculated, the position of each region focus is obtained, it is clear to obtain each region
Clear image;
(3) aggregation location information is obtained by immune genetic method, interpolation fitting has been carried out to the focal position information, has been obtained
Obtain accurate location information.
Three-dimensionalreconstruction in image processing module 4 provided by the invention includes the following steps:
(1) using the elevation information in obtained location information as Z axis, each point in each image generates X, Y, Z
Three-dimensional coordinate;
(2) three-dimension object is reconstructed by the three-dimensional coordinate of each point in image.
6 cutting method of cutting module provided by the invention is as follows:
First, heat-sink shell is covered on the cutting track of cutting board to be cut;
Then, laser irradiation cuts the cutting board to be cut to the heat-sink shell and along the cutting track;
Finally, the heat-sink shell on the cutting board to be cut after cutting is completed in removal.
Cutting track provided by the invention includes regular track and irregular track, is covered on the rule track described
Heat-sink shell is multilayer, and the heat-sink shell covered on the irregular track is at least one layer.
The number of plies of the heat-sink shell covered on rule track provided by the invention, which is less than on the irregular track, to be covered
The heat-sink shell the number of plies.
When the present invention is cut, laser is emitted by laser emitting module 1;Plate to be cut is acquired by image capture module 2
The location drawing picture data of material;Central processing module 3 transfers position of the image processing module 4 to acquisition plank sequence image to be cut
Information, and the three-dimensionalreconstruction of object is marked by the location information;By automatic focusing module 5 according to three-dimensionalreconstruction after
Label object automatically controls the adjusting of focal length;Cutting operation is carried out to plank by cutting module 6;Pass through data disaply moudle 7
Show the image data of acquisition.
With reference to concrete analysis, the invention will be further described.
Such as Fig. 2, plate with laser cutting machine control method provided in an embodiment of the present invention, including:
S101:Acquire the location drawing picture data of plank to be cut;
S102:Image location information is logical to be obtained:The marginal information of each sequence image is obtained, and each sequence image is drawn
It is divided into identical region, is by iteration to current algebraically first using adaptive vaccine extraction mechanism by immune genetic method
The 20 optimal antibody only occurred extract, formed vaccine library, and before next iteration starts to vaccine library into
Row update;Secondly, a vaccine antibody is extracted from this 20 optimal antibody, the symbol in each gene position of vaccine antibody takes
To correspond to the maximum symbol of probability of occurrence in gene position in this 20 optimal antibody;According to inoculation probability PvIt chooses by heredity behaviour
Make the new antibodies formed and carry out vaccine inoculation, and compares the affinity of inoculation front and back antibody and antigen;Inoculation operation can improve
The fitness of antibody then receives inoculation, otherwise abandons being inoculated with;The probability P of immunity inoculationv=0.7;Obtain aggregation location information;And
Location information is marked the three-dimensionalreconstruction of object;
S103:According to the label after three-dimensionalreconstruction, the adjusting of focal length is automatically controlled by central processing module;
S104:Plank is cut by laser after covering heat-sink shell on the cutting track of cutting board to be cut.
Immune genetic method includes:
Step 1, decision variable setting:
Decision variable X={ C;S } it is made of two parts vector, the value of all vector elements is 0 or 1, structure such as following formula
It is shown;
C={ C11,C12,C21,C22,...,Cn1,Cn2}(1);
S={ S1,S2,...,Sm}
In formula:N is the positional number of plank to be cut, and m is the feasible cutting position number of laser cutting machine;Ci1、Ci2(i=1,
2 ..., n) class of a curve whether the i-th feasible location of plank to be cut needs the position cut and needs to cut is indicated respectively
Type;Si(i=1,2 ..., m) indicate whether i-th of feasible cutting position of laser cutting machine actually has laser cutting machine light beam;
Step 2, initial population generate:
The initial value in population antibody in each gene position is generated according to random sampling shown in formula (1);
By improving the value of P in formula (2), whether representing laser cutting machine beam emissions in reduction antibody character string
Gene location there is the number of character " 1 ", sample Ci1、SiWhen the genic value of position, P values are 0.9;In sampling Ci2Value
When, P values are 0.5;The size of initial population is selected as 100;
Step 3, genetic manipulation:
As shown in formula (3);The select probability that the antibody vector distance value of fitness value calculation is determined by affinity and concentration
Decision, affinity and concentration calculation formula are respectively as shown in formula (4) and formula (5);
The select probability of concentration and affinity is:
In formula:α is the weight coefficient for adjusting select probability;PfiWith PdiRespectively determined by the affinity and concentration of antibody i
Fixed select probability;
The calculating of affinity:If there is N number of antibody in population, wherein the affinity of antibody i is fi, then PfiIt is selected using direct ratio
Strategy obtains:
Wherein, i=1,2 ..., N;
The calculating of concentration:When using vector away from antibody concentration is indicated,It calculates as follows:
Crossover operation uses the form of two-point crossover, crossover probability PcIt is set as 0.9, using dynamic in Population Variation operation
State aberration rate, as shown in formula (6);
PMg=PMmin+(PMmax-PMmin)·rg(6);
In formula:PMgIt is g for the aberration rate of population antibody, PMminWith PMmaxThe respectively minimum value of aberration rate and maximum
Value;R is contraction factor, and 0.99 is taken as in analysis;
Using adaptive vaccine extraction mechanism;First, the 20 optimal antibody that will occur until iteration to current algebraically
It extracts, forms vaccine library, and be updated to vaccine library before next iteration starts;Secondly, most from this 20
A vaccine antibody is extracted in excellent antibody, the symbol in each gene position of vaccine antibody is taken as in this 20 optimal antibody corresponding
The maximum symbol of probability of occurrence in gene position;According to inoculation probability PvIt chooses and carries out vaccine by the new antibodies that genetic manipulation is formed
Inoculation, and compare the affinity of inoculation front and back antibody and antigen;The fitness that inoculation operation can improve antibody then receives inoculation,
Otherwise it abandons being inoculated with;The probability P of immunity inoculationv=0.7;
Step 5, the evolution of vaccine library:
In promoting the evolutionary process of vaccine library using clone's genetic algorithm, clonal plant population is dimensioned to 100, each
Clone's quantity of a antibody is calculated using formula (7);Fixed aberration rate P is used in gene mutation operatorm=0.1;
During clone, the number q of each antibody duplicationiAs shown in formula
Wherein, if there is n antibody in initial population, i.e. A (k)={ a1,a2,…,an, the affinity of wherein antibody i is denoted as
For f (ai), the capacity of population A ' (k) after cloning is set as Nc, take Nc>n;
Wherein operator [x] indicates the maximum integer no more than x;
Step 6, population recruitment:
After immune operation, the affinity replaced in population with quantity with highest 5 antibody of affinity in vaccine library is worst
Individual;It is random to generate 85% antibody that affinity is poor in population when not searching more excellent solution in continuous 20 generation;
Immune genetic method further comprises end condition:Using reaching 300 generation of fixed genetic algebra as end condition.
Image location information leads to acquisition methods:
(1) marginal information of each sequence image is obtained, and each sequence image is divided into identical region;
(2) average gradient in each region is calculated, the position of each region focus is obtained, it is clear to obtain each region
Clear image;
(3) aggregation location information is obtained by immune genetic method, interpolation fitting has been carried out to the focal position information, has been obtained
Obtain accurate location information;
Image three-dimensional reconstruction method includes:
(i) using the elevation information in obtained location information as Z axis, each point in each image generates X, Y, Z
Three-dimensional coordinate;
(ii) three-dimension object is reconstructed by the three-dimensional coordinate of each point in image.
Further, laser cutting method includes:
First, heat-sink shell is covered on the cutting track of cutting board to be cut;
Then, laser irradiation cuts the cutting board to be cut to the heat-sink shell and along the cutting track;
Finally, the heat-sink shell on the cutting board to be cut after cutting is completed in removal;
The cutting track includes regular track and irregular track, and the heat-sink shell covered on the rule track is
Multilayer, the heat-sink shell covered on the irregular track are at least one layer;
The number of plies of the heat-sink shell covered on regular track is less than the heat-sink shell covered on the irregular track
The number of plies.
In the above-described embodiments, can come wholly or partly by software, hardware, firmware or its arbitrary combination real
It is existing.When using entirely or partly realizing in the form of a computer program product, the computer program product include one or
Multiple computer instructions.When loading on computers or executing the computer program instructions, entirely or partly generate according to
Flow described in the embodiment of the present invention or function.The computer can be all-purpose computer, special purpose computer, computer network
Network or other programmable devices.The computer instruction can store in a computer-readable storage medium, or from one
Computer readable storage medium is transmitted to another computer readable storage medium, for example, the computer instruction can be from one
A web-site, computer, server or data center pass through wired (such as coaxial cable, optical fiber, Digital Subscriber Line (DSL)
Or wireless (such as infrared, wireless, microwave etc.) mode is carried out to another web-site, computer, server or data center
Transmission).The computer read/write memory medium can be that any usable medium that computer can access either includes one
The data storage devices such as a or multiple usable mediums integrated server, data center.The usable medium can be magnetic Jie
Matter, (for example, floppy disk, hard disk, tape), optical medium (for example, DVD) or semiconductor medium (such as solid state disk Solid
State Disk (SSD)) etc..
The above is only the preferred embodiments of the present invention, and is not intended to limit the present invention in any form,
Every any simple modification made to the above embodiment according to the technical essence of the invention, equivalent variations and modification, belong to
In the range of technical solution of the present invention.
Claims (10)
1. a kind of plate with laser cutting machine control method, which is characterized in that the plate with laser cutting machine control method includes:
Acquire the location drawing picture data of plank to be cut;
Image location information is logical to be obtained:The marginal information of each sequence image is obtained, and each sequence image is divided into identical
Region will occur until iteration to current algebraically first using the adaptive vaccine extraction mechanism of immune genetic method
20 optimal antibody extract, and form vaccine library, and be updated to vaccine library before next iteration starts;Its
It is secondary, a vaccine antibody is extracted from this 20 optimal antibody, the symbol in each gene position of vaccine antibody is taken as this 20
The maximum symbol of probability of occurrence in gene position is corresponded in optimal antibody;According to inoculation probability PvIt chooses by genetic manipulation formation
New antibodies carry out vaccine inoculation, and compare the affinity of inoculation front and back antibody and antigen;Inoculation operation can improve the suitable of antibody
Response then receives inoculation, otherwise abandons being inoculated with;The probability P of immunity inoculationv=0.7;Obtain aggregation location information;And align confidence
The three-dimensionalreconstruction of object is marked in breath;
According to the label after three-dimensionalreconstruction, the adjusting of focal length is automatically controlled by central processing module;
Plank is cut by laser after covering heat-sink shell on the cutting track of cutting board to be cut.
2. plate with laser cutting machine control method as described in claim 1, which is characterized in that immune genetic method includes:
Step 1, decision variable setting:
Decision variable X={ C;S } it is made of two parts vector, the value of all vector elements is 0 or 1, and structure is shown below;
C={ C11,C12,C21,C22,...,Cn1,Cn2}(1);
S={ S1,S2,...,Sm}
In formula:N is the positional number of plank to be cut, and m is the feasible cutting position number of laser cutting machine;Ci1、Ci2(i=1,2 ..., n)
The curve type whether the i-th feasible location of plank to be cut needs the position cut and needs to cut is indicated respectively;Si(i
=1,2 ..., m) indicate whether i-th of feasible cutting position of laser cutting machine actually has laser cutting machine light beam;
Step 2, initial population generate:
The initial value in population antibody in each gene position is generated according to random sampling shown in formula (1);
By improving the value of P in formula (2), from the base reduced whether representing laser cutting machine beam emissions in antibody character string
Because the number of character " 1 " occurs in position, sample Ci1、SiWhen the genic value of position, P values are 0.9;In sampling Ci2When value, P takes
Value is 0.5;The size of initial population is selected as 100;
Step 3, genetic manipulation:
As shown in formula (3);The select probability decision that the antibody vector distance value of fitness value calculation is determined by affinity and concentration,
Affinity and concentration calculation formula are respectively as shown in formula (4) and formula (5);
The select probability of concentration and affinity is:
In formula:α is the weight coefficient for adjusting select probability;PfiWithRespectively determined by the affinity of antibody i and concentration
Select probability;
The calculating of affinity:If there is N number of antibody in population, wherein the affinity of antibody i is fi, then PfiUsing direct ratio selection strategy
It obtains:
Wherein, i=1,2 ..., N;
The calculating of concentration:When using vector away from antibody concentration is indicated,It calculates as follows:
Crossover operation uses the form of two-point crossover, crossover probability PcIt is set as 0.9, is become using dynamic in Population Variation operation
Different rate, as shown in formula (6);
PMg=PMmin+(PMmax-PMmin)·rg(6);
In formula:PMgIt is g for the aberration rate of population antibody, PMminWith PMmaxThe respectively minimum value and maximum value of aberration rate;R is
Contraction factor is taken as 0.99 in analysis;
Using adaptive vaccine extraction mechanism;First, 20 occurred until iteration to current algebraically optimal antibody are extracted
Out, vaccine library is formed, and vaccine library is updated before next iteration starts;Secondly, optimal anti-from this 20
A vaccine antibody is extracted in body, the symbol in each gene position of vaccine antibody is taken as corresponding to gene in this 20 optimal antibody
The maximum symbol of probability of occurrence on position;According to inoculation probability PvThe new antibodies progress vaccine formed by genetic manipulation is chosen to connect
Kind, and compare the affinity of inoculation front and back antibody and antigen;The fitness that inoculation operation can improve antibody then receives inoculation, instead
Abandon be inoculated with;The probability P of immunity inoculationv=0.7;
Step 5, the evolution of vaccine library:
In promoting the evolutionary process of vaccine library using clone's genetic algorithm, clonal plant population is dimensioned to 100, each is anti-
Clone's quantity of body is calculated using formula (7);Fixed aberration rate P is used in gene mutation operatorm=0.1;
During clone, the number q of each antibody duplicationiAs shown in formula
Wherein, if there is n antibody in initial population, i.e. A (k)={ a1,a2,…,an, the affinity of wherein antibody i is denoted as f
(ai), the capacity of population A ' (k) after cloning is set as Nc, take Nc>n;
Wherein operator [x] indicates the maximum integer no more than x;
Step 6, population recruitment:
After immune operation, the worst individual of affinity in population with quantity is replaced with highest 5 antibody of affinity in vaccine library;
It is random to generate 85% antibody that affinity is poor in population when not searching more excellent solution in continuous 20 generation.
3. plate with laser cutting machine control method as described in claim 1, which is characterized in that immune genetic method further comprises
End condition:Using reaching 300 generation of fixed genetic algebra as end condition.
4. plate with laser cutting machine control method as described in claim 1, which is characterized in that image location information leads to acquisition methods
Including:
(1) marginal information of each sequence image is obtained, and each sequence image is divided into identical region;
(2) average gradient in each region is calculated, the position of each region focus is obtained, obtains each region clearly
Image;
(3) aggregation location information is obtained by immune genetic method, interpolation fitting has been carried out to the focal position information, has obtained essence
True location information;
Image three-dimensional reconstruction method includes:
(i) using the elevation information in obtained location information as Z axis, each point in each image generates the three of X, Y, Z
Dimension coordinate;
(ii) three-dimension object is reconstructed by the three-dimensional coordinate of each point in image.
5. plate with laser cutting machine control method as described in claim 1, which is characterized in that laser cutting method includes:
First, heat-sink shell is covered on the cutting track of cutting board to be cut;
Then, laser irradiation cuts the cutting board to be cut to the heat-sink shell and along the cutting track;
Finally, the heat-sink shell on the cutting board to be cut after cutting is completed in removal;
The cutting track includes regular track and irregular track, and the heat-sink shell covered on the rule track is more
Layer, the heat-sink shell covered on the irregular track is at least one layer;
Layer of the number of plies of the heat-sink shell covered on regular track less than the heat-sink shell covered on the irregular track
Number.
6. a kind of computer program for realizing plate with laser cutting machine control method described in Claims 1 to 5 any one.
7. a kind of computer for realizing plate with laser cutting machine control method described in Claims 1 to 5 any one.
8. a kind of computer readable storage medium, including instruction, when run on a computer so that computer is executed as weighed
Profit requires the plate with laser cutting machine control method described in 1-5 any one.
9. a kind of plate with laser cutting machine for realizing plate with laser cutting machine control method described in claim 1, which is characterized in that
The plate with laser cutting machine includes:
Laser emitting module is connect with central processing module, emits laser for passing through laser generator;
Image capture module is connect with central processing module, the location drawing picture number for acquiring plank to be cut by camera
According to;
Central processing module, with laser emitting module, image capture module, image processing module, automatic focusing module, blanking punch
Block, data disaply moudle connection, for controlling modules normal work;
Image processing module is connect with central processing module, for the location information to obtaining plank sequence image to be cut, and
The three-dimensionalreconstruction of object is marked by the location information;
Automatic focusing module, connect with central processing module, for automatically controlling focal length by the label object after three-dimensionalreconstruction
Adjusting;
Cutting module is connect with central processing module, for carrying out cutting operation to plank;
Data disaply moudle is connect with central processing module, the image data for showing acquisition.
10. a kind of computer equipped with plate with laser cutting machine described in claim 9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810516777.1A CN108747043A (en) | 2018-05-25 | 2018-05-25 | A kind of plate with laser cutting machine and control method, computer |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810516777.1A CN108747043A (en) | 2018-05-25 | 2018-05-25 | A kind of plate with laser cutting machine and control method, computer |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108747043A true CN108747043A (en) | 2018-11-06 |
Family
ID=64005846
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810516777.1A Pending CN108747043A (en) | 2018-05-25 | 2018-05-25 | A kind of plate with laser cutting machine and control method, computer |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108747043A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113714662A (en) * | 2021-09-06 | 2021-11-30 | 玖陆零信安创(盐城)科技有限公司 | Cutting size adjusting mechanism for intelligent household wood board cutting equipment |
CN116275587A (en) * | 2023-04-17 | 2023-06-23 | 霖鼎光学(江苏)有限公司 | Control system for laser cutting of workpiece |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103350281A (en) * | 2013-06-20 | 2013-10-16 | 深圳市大族激光科技股份有限公司 | Automatic focusing device and automatic focusing method for laser marking machine |
CN104123706A (en) * | 2014-08-11 | 2014-10-29 | 徐州工程学院 | Image enhancement method based on adaptive immunity genetic algorithm |
CN104636825A (en) * | 2015-01-26 | 2015-05-20 | 国家电网公司 | Immune genetic method for planning and improving electric automobiles facing urban distribution network |
CN107507157A (en) * | 2017-09-29 | 2017-12-22 | 徐州工程学院 | A kind of improved image enchancing method |
CN107695533A (en) * | 2017-09-26 | 2018-02-16 | 武汉华星光电半导体显示技术有限公司 | Laser cutting method |
-
2018
- 2018-05-25 CN CN201810516777.1A patent/CN108747043A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103350281A (en) * | 2013-06-20 | 2013-10-16 | 深圳市大族激光科技股份有限公司 | Automatic focusing device and automatic focusing method for laser marking machine |
CN104123706A (en) * | 2014-08-11 | 2014-10-29 | 徐州工程学院 | Image enhancement method based on adaptive immunity genetic algorithm |
CN104636825A (en) * | 2015-01-26 | 2015-05-20 | 国家电网公司 | Immune genetic method for planning and improving electric automobiles facing urban distribution network |
CN107695533A (en) * | 2017-09-26 | 2018-02-16 | 武汉华星光电半导体显示技术有限公司 | Laser cutting method |
CN107507157A (en) * | 2017-09-29 | 2017-12-22 | 徐州工程学院 | A kind of improved image enchancing method |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113714662A (en) * | 2021-09-06 | 2021-11-30 | 玖陆零信安创(盐城)科技有限公司 | Cutting size adjusting mechanism for intelligent household wood board cutting equipment |
CN113714662B (en) * | 2021-09-06 | 2022-06-24 | 玖陆零信安创(盐城)科技有限公司 | Cutting size adjusting mechanism for intelligent household wood board cutting equipment |
CN116275587A (en) * | 2023-04-17 | 2023-06-23 | 霖鼎光学(江苏)有限公司 | Control system for laser cutting of workpiece |
CN116275587B (en) * | 2023-04-17 | 2023-10-27 | 霖鼎光学(江苏)有限公司 | Control system for laser cutting of workpiece |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105977649B (en) | The fast determination method of large-scale parabola antenna active panel adjustment amount towards figuration face | |
CN108747043A (en) | A kind of plate with laser cutting machine and control method, computer | |
EP3416008A1 (en) | Method for modeling additive manufacturing of a part | |
CN106960088B (en) | Three-dimensional process model automatic updating method facing process change | |
US11733678B2 (en) | Method for determining building instructions for an additive manufacturing method, method for generating a database with correction measures for controlling the process of an additive manufacturing method | |
CN114564880B (en) | Method for constructing digital twin module in additive manufacturing process | |
CN113158368B (en) | Method and equipment for predicting and controlling deformation of material-increasing and material-decreasing composite manufacturing part | |
US20200272128A1 (en) | Sensor based smart segmentation | |
CN109514069A (en) | The stress deformation control method and device of electron beam fuse increasing material manufacturing technique | |
CN106299722B (en) | Fast determination method towards paraboloidal large-scale figuration surface antenna active panel adjustment amount | |
CN109128168A (en) | A kind of synchronous powder feeding system increasing material manufacturing Process Planning Method based on structure feature | |
CN104978449A (en) | Aerodynamic optimization method of leading edge slats position and trailing edge flap position of two-dimensional three-section airfoil profile | |
CN112066977A (en) | Photoelectric measurement network multi-target matching and cataloguing method | |
CN114282320B (en) | Method for optimizing engineering parameters by using Bayesian optimization algorithm | |
Huang et al. | An on-machine tool path generation method based on hybrid and local point cloud registration for laser deburring of ceramic cores | |
CN106180720A (en) | A kind of have the metalwork laser gain material preparation method optimizing netted inner structure | |
CN117073671B (en) | Fire scene positioning method and system based on unmanned aerial vehicle multi-point measurement | |
Wan et al. | EAST discharge prediction without integrating simulation results | |
CN116518982B (en) | Low-altitude forestry monitoring remote sensing unmanned aerial vehicle path multi-target planning method | |
CN109702930A (en) | One kind being used for component accurately hot formed tangible mold design method | |
CN109702931A (en) | The accurate hot formed die-face design method of area of computer aided large-scale component | |
CN107239548B (en) | Report processing method based on SQL Server and HIVE | |
Lu et al. | Personalized federated learning on long-tailed data via adversarial feature augmentation | |
CN116448765A (en) | Identification positioning system for surface defects of manually laid prepreg | |
CN116244610A (en) | Distributed query system based on machine learning and optimization method thereof |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181106 |
|
RJ01 | Rejection of invention patent application after publication |