CN104978607B - A kind of pot seedling thin planting transplanting method for optimizing route based on Greedy genetic algorithm - Google Patents
A kind of pot seedling thin planting transplanting method for optimizing route based on Greedy genetic algorithm Download PDFInfo
- Publication number
- CN104978607B CN104978607B CN201510346330.0A CN201510346330A CN104978607B CN 104978607 B CN104978607 B CN 104978607B CN 201510346330 A CN201510346330 A CN 201510346330A CN 104978607 B CN104978607 B CN 104978607B
- Authority
- CN
- China
- Prior art keywords
- hole tray
- transplanting
- genetic algorithm
- seedling
- coding
- 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
- 230000002068 genetic effect Effects 0.000 title claims abstract description 45
- 238000000034 method Methods 0.000 title claims abstract description 21
- 230000037431 insertion Effects 0.000 claims abstract description 12
- 238000003780 insertion Methods 0.000 claims abstract description 12
- 230000036541 health Effects 0.000 claims abstract description 10
- 238000001467 acupuncture Methods 0.000 claims abstract description 6
- 238000005295 random walk Methods 0.000 claims abstract description 4
- 210000000349 chromosome Anatomy 0.000 claims description 22
- 238000005457 optimization Methods 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 6
- 230000013011 mating Effects 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 5
- 239000003550 marker Substances 0.000 claims description 5
- 230000035772 mutation Effects 0.000 claims description 5
- 238000003786 synthesis reaction Methods 0.000 claims description 5
- 230000015572 biosynthetic process Effects 0.000 claims description 4
- 230000000750 progressive effect Effects 0.000 claims description 3
- 108090000623 proteins and genes Proteins 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 2
- 239000007787 solid Substances 0.000 claims description 2
- 238000005303 weighing Methods 0.000 claims description 2
- 238000004043 dyeing Methods 0.000 claims 1
- 239000012636 effector Substances 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000003862 health status Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 1
Abstract
The invention discloses a kind of pot seedling thin planting based on Greedy genetic algorithm to transplant method for optimizing route.The health and fitness information of pot seedling in the transplanting hole tray of greenhouse pot seedling thin planting transplanter is known by machine vision, coding is marked to hole position in healthy seedling acupuncture point in transplanting hole tray and purpose hole tray respectively；The current path that greedy heredity selects excellent principle to carry out Local genetic algorithm by row subregion for purpose hole tray Hole optimizes；Purpose hole tray row Hole is encoded has seedling cavities coding comprehensive with what is do not planned in transplanting hole tray, generate the initial population that random walk coding forms Local genetic algorithm, circulation makes choice, intersects, makes a variation and weighs insertion operation until presetting convergence times, using the maximum individual of population's fitness as the local optimum path；The local optimum path of successively each row planning is merged, that is, generates whole purpose hole tray thin planting transplanting path.The present invention can generate the path optimizing of greenhouse pot seedling thin planting transplanting, improve transplanting work efficiency, meet control system real time planning requirement.
Description
Technical field
The present invention relates to the method for transplanting for being used for pot seedling in agricultural machinery, and Greedy genetic algorithm is based on more particularly, to one kind
Pot seedling thin planting transplanting method for optimizing route.
Background technology
In greenhouse hole plate seedling growth, the pot seedling in high density hole tray needs thin planting to be transplanted in low-density hole tray, while hole tray
Interior planting percent is between 80-95%.For tradition by manually carrying out identification transplanting operation, efficiency is low, and labor intensity is big, and transplants
The uniformity of seedling is bad；Greenhouse pot seedling thin planting transplanter is passed through by Machine Vision Detection pot seedling health status and positional information
End effector crawl transplanting, can solve the above problems.
Low-density hole tray hole is more, the randomness of healthy seedling present position is big in high density hole tray, transplanter control end
The priority selectivity that actuator is transplanted from origin to each cavities is more, that is, the length for carrying out thin planting transplanting path is variable；Due to
Hole data volume is big, and the method for the most short optimal path of controller calculating sifting can not meet the requirement of realtime control.This kind of alms bowl
The paths planning method of seedling thin planting transplanting has to be developed.
The content of the invention
It is an object of the invention to provide a kind of pot seedling thin planting based on Greedy genetic algorithm to transplant method for optimizing route, can
The travel distance of greenhouse pot seedling thin planting transplanter end effector is reduced, improves operating efficiency.
In order to achieve the above object, the technical solution adopted by the present invention is：
By machine vision, oneself knows the health and fitness information of pot seedling in the transplanting hole tray of greenhouse pot seedling thin planting transplanter to the present invention,
Coding is marked to hole position in healthy seedling acupuncture point in transplanting hole tray and purpose hole tray respectively；It is mesh that excellent principle is selected in greedy heredity
Hole tray Hole by row subregion carry out Local genetic algorithm current path optimization；Purpose hole tray row Hole is encoded and moved
The initial population for having seedling cavities coding comprehensive, generating random walk coding composition Local genetic algorithm do not planned in hole tray is planted,
Circulation makes choice, intersects, makes a variation and weighs insertion operation until presetting convergence times, regard the maximum individual of population's fitness as this
Local optimum path；The local optimum path of successively each row planning is merged, that is, generates whole purpose hole tray thin planting transplanting path.
It is described that coding is marked to hole position in healthy seedling acupuncture point in transplanting hole tray and purpose hole tray respectively, it is specially close
Each cavities for spending high transplanting hole tray and low density purpose hole tray has been fixed in the position of transplanter system, to transplanting hole tray
Interior health seedling cavities carries out arithmetic number mark by order from top to bottom, from left to right, each Hole in purpose hole tray is pressed from
Order under, from left to right carries out negative real number mark, and thus label coding is actual is implied with cavities position and pot seedling health
Information.
The purpose hole tray Hole is carried out the current path optimization of Local genetic algorithm by row subregion, and specific is purpose cave
Cavities of circling or whirl in the air negative flag coding is by hole tray row subregion, by row order from left to right or from right to left, successively with transplanting in hole tray
The current optimum path planning for having the positive label coding synthesis of seedling cavities, carrying out Local genetic algorithm do not planned.
Purpose hole tray row Hole coding has seedling cavities coding comprehensive with what is do not planned in transplanting hole tray, generate with
Machine path code forms the initial population of Local genetic algorithm, and circulation makes choice, intersects, makes a variation and weigh insertion operation until pre-
If convergence times, using the maximum individual of population's fitness as the local optimum path, specific Local genetic algorithm process description is such as
Under：
A) the initial population generation method of Local genetic algorithm is specially：Assuming that the negative mark of purpose hole tray row Hole
Remember that coded set is { -1, -2, -3, -4, -5, -6, -7, -8 }, transplanting the positive label coding collection of seedling cavities that has do not planned in hole tray is
{ 1,2,3 ... ..., 48,49,50 }, then transplant path and intersect at random from origin and positive and negative label coding collection, can be formed such as
（0,3, -2,8, -4,9, -7,10, -1,7, -6,13, -3,5, -5,16, -8,0）Initial population item chromosome, algorithm sets
Generation certain amount chromosome is put, that is, forms initial population；
B) individual population's fitness is specially：The position of the transplanting coordinate system of the actual mapping of coding in each chromosome
It is known that then the path length of the mapping of specific each chromosome can also calculate, it is set tol(x), whereinl minWithl maxKind is represented respectively
The most short and longest path of group's chromosome；Defining individual population's fitness isC= (l max- l(x))/( l max -l min )；
C) selection operation that Local genetic algorithm circulation carries out is：Initial population is as parent, according to random sequence, with
Chromosome fitness is select probability, select probabilityM>CChromosome as progeny population；
D) crossover operation that Local genetic algorithm circulation carries out is：After initial population selection operation generation progeny population, with
Machine sorts, and carries out crossover operation；1. hypothesis have O=（0,14, -4,9, -2,8, -7,12, -1,19, -3,13, -6,15, -8,26, -
5,0）, P=（0,13, -7,8, -4,9, -2,10, -1,7, -5,28, -8,5, -6,16, -3,0）, Q=（0,12, -6,30, -3,
19, -8,11, -1,16, -2,5, -4,14, -5,10, -7,0）Three progeny population chromosomes；2. produce 2 between 1 to 16 it
Between random number j and k, wherein j is as mating indicating bit, and k is as mating step-length, then the jth of three child chromosomes+1 to j
+ k progressive exchanges；If j+k >=16, order is taken as 16；If j=8, k=4 are individual after being intersected：O1=（0,14, -4,9, -2,
8, -7,12, -1,16, -2,5, -6,15, -8,26, -5,0）, P1=（0,13, -7,8, -4,9, -2,10, -1,19, -3,13, -8,
5, -6,16, -3,0）, Q1=（0,12, -6,30, -3,19, -8,11, -1,7, -5,28, -4,14, -5,10, -7,0）；3. scan
Except after the intersection of origin 0 position, replaced if identical with 800, you can obtain O2=（0,14, -4,9, -2,8, -7,12, -1,16,
800,5, -6,15, -8,26, -5,0）, P2=（0,13, -7,8, -4,9, -2,10, -1,19, -3,800, -8,5, -6,16,800,
0）, Q2=（0,12, -6,30, -3,19, -8,11, -1,7, -5,28, -4,14,800,10, -7,0）；4. scanning is upper except origin 0
One step individual, number 800 is replaced using an effectively position successively；If number 800 is in even bit, by the row institute in purpose hole tray
There is marker number sequential scan to remove each even bit after origin 0 with position to contrast, if not occurring, replaced with this
800；If number 800 is in odd bits, will transplant do not planned in hole tray all has seedling marker number sequential scan and position
Except each odd-even bit contrast after origin 0, the mark not occurred is randomly generated one to replace 800；It is i.e. available
O3=（0,14, -4,9, -2,8, -7,12, -1,16, -3,5, -6,15, -8,26, -5,0）, P3=（0,13, -7,8, -4,9, -2,
10, -1,19, -3,28, -8,5, -6,16, -5,0）, Q3=（0,12, -6,30, -3,19, -8,11, -1,7, -5,28, -4,14, -
2,10, -7,0）；
E) mutation operation that Local genetic algorithm circulation carries out is：The population produced to above-mentioned crossover operation is randomly ordered,
Carry out mutation operation；2 the random number r and s between 1 to 16 are produced, as individual except 2 change dystopys of origin 0：
If the label coding for becoming dystopy is negative, other negative flag coding random selections one are arranged from purpose hole tray, from change
Scanning is found the value and is exchanged with becoming dystopy in different individual：Assuming that r=2, offspring individual O3=（0,14, -4,9, -2,8, -7,12, -
1,16, -3,5, -6,15, -8,26, -5,0）, then one is produced in { -1, -2, -3, -5, -6, -7, -8 } except -4 reference numerals
Random number, is set to -7, then new offspring individual O after making a variation4=（0,14, -7,9, -2,8, -4,12, -1,16, -3,5, -6,15, -8,
26, -5,0）；
If becoming the label coding of dystopy as just, there is the positive label coding of seedling to select at random from do not planned in hole tray all are transplanted
Select one to be interchangeable, and travel through the replaced offspring individual of gene, if there is identical positive label coding, with former label coding
Number replaces：Assuming that s=9, offspring individual P3=（0,13, -7,8, -4,9, -2,10, -1,19, -3,28, -8,5, -6,16, -5,
0）, then a random number is produced in { 1,2,3 ... ..., 48,49,50 } except 19 reference numerals, is set to 20, then new son after making a variation
Generation individual P3=（0,13, -7,8, -4,9, -2,10, -1,20, -3,28, -8,5, -6,16, -5,0）；
F) the heavy insertion operation that Local genetic algorithm circulation carries out is：, intersection chosen to above-mentioned initial population, variation
The offspring individual produced afterwards carries out fitness calculating, is inserted into initial population again and replaces most unconformable parent individuality, keeps initial
Population scale；
Local genetic algorithm is reached by making choice, intersecting, making a variation and weighing insertion operation to the circulation of above-mentioned initial population
Default convergence times stop, and take the maximum individual of population's fitness in convergence generation to be used as the local optimum path.
After being obtained after the local optimum path that all purposes hole tray respectively arranges, according to row order from left to right or from right to left
Merge, generate the thin planting transplanting path of whole purpose hole tray.
The invention has the advantages that：
The present invention obtains high density by Machine Vision Detection and transplants hole tray pot seedling health status and positional information, with greedy
Heart genetic algorithm is technological means, completes rapid Optimum high density and transplants hole tray pot seedling to low-density purpose hole tray thin planting transplanting road
Footpath, so as to improve end effector operating efficiency.
Brief description of the drawings
Fig. 1 is the flow chart of pot seedling thin planting transplanting method for optimizing route of the present invention based on Greedy genetic algorithm.
Fig. 2 is the label coding figure for transplanting hole tray and purpose hole tray.
Fig. 3 is optimization algebraically variation diagram in local genetic optimization.
Fig. 4 is the single-row cavities part genetic optimization result of purpose hole tray.
Fig. 5 is thin planting transplanting path profile after each row order synthesis.
Embodiment
With reference to method flow diagram and embodiment, the invention will be further described.
Flow chart of the method for the present invention is as shown in Figure 1：The present invention knows that the health of pot seedling in hole tray is believed by machine vision
Breath, is marked coding to hole position in healthy seedling acupuncture point in transplanting hole tray and purpose hole tray respectively（As shown in Figure 2）.Greed is lost
The current path for selecting excellent principle to carry out Local genetic algorithm by row subregion for purpose hole tray Hole is passed to optimize；Purpose hole tray arranges
Hole is encoded has seedling cavities coding comprehensive with what is do not planned in transplanting hole tray, and generation random walk coding forms local heredity and calculates
The initial population of method, circulation make choice, intersect, make a variation and weigh insertion operation until presetting convergence times（As shown in Figure 3）, will
The maximum individual of population's fitness is used as the local optimum path（As shown in Figure 4）；By the local optimum path of successively each row planning
Merge, that is, generate whole purpose hole tray thin planting transplanting path（As shown in Figure 5）.
P1：Each cavities of the high transplanting hole tray of density and low density purpose hole tray is solid in the position of transplanter system
It is fixed, transplant pot seedling health and fitness information in hole tray and obtained also by machine vision, to healthy seedling cavities in transplanting hole tray by from top to bottom,
Order from left to right carries out arithmetic number mark, to each Hole in purpose hole tray by order from top to bottom, from left to right into
The negative real number mark of row, thus label coding is actual is implied with cavities position and pot seedling health and fitness information.As shown in Fig. 2, purpose hole tray 4
× 8 specifications, Hole label coding collection are { -1, -2, -3 ... ..., -32 }；5 × 10 specification of hole tray is transplanted, containing healthy pot seedling 42
Strain, label coding collection is { 1,2,3 ... ..., 40,41,42 }.
P2：Purpose hole tray Hole is carried out the current optimum path planning of genetic algorithm by row subregion, and specific is purpose cave
Cavities of circling or whirl in the air negative flag coding is by hole tray row subregion, by row order from left to right or from right to left, successively with transplanting in hole tray
The initial population for having the positive label coding synthesis of seedling cavities, carrying out Local genetic algorithm optimization do not planned.Mould is transplanted with Fig. 2 thin plantings
Exemplified by type, purpose hole tray left column label coding { -1, -2, -3, -4, -5, -6, -7, -8 }, transplanting hole tray has not planned seedling currently
Cavities label coding { 1,2,3 ... ..., 40,41,42 }, from origin, mutually random cross-synthesis, can form such as（0,3 ,-
2,8, -4,9, -7,10, -1,7, -6,13, -3,5, -5,16, -8,0）Initial population item chromosome, set generation certain
Quantity chromosome, that is, form initial population.
P3：The position of the transplanting coordinate system of the actual mapping of coding in each chromosome is it is known that then specific each chromosome
The path length of mapping can also calculate, be set tol(x), whereinl minWithl maxThe most short and most long of population chromosome is represented respectively
Path；Defining individual population's fitness isC= (l max- l(x))/( l max -l min ).Initial population is as parent, according to random
Sequentially, using chromosome fitness as select probability, select probabilityM>CChromosome as progeny population.
P4：It is randomly ordered after initial population selection operation generation progeny population, carry out crossover operation.1. hypothesis have O=
（0,14, -4,9, -2,8, -7,12, -1,19, -3,13, -6,15, -8,26, -5,0）, P=（0,13, -7,8, -4,9, -2,10, -
1,7, -5,28, -8,5, -6,16, -3,0）, Q=（0,12, -6,30, -3,19, -8,11, -1,16, -2,5, -4,14, -5,10, -
7,0）Three progeny population chromosomes；2. producing 2 the random number j and k between 1 to 16, wherein j is as mating instruction
Position, k is as mating step-length, then+1 to j+k progressive exchange of the jth of three child chromosomes；If j+k >=16, order is taken as 16；
If j=8, k=4 are individual after being intersected：O1=（0,14, -4,9, -2,8, -7,12, -1,16, -2,5, -6,15, -8,26, -
5,0）, P1=（0,13, -7,8, -4,9, -2,10, -1,19, -3,13, -8,5, -6,16, -3,0）, Q1=（0,12, -6,30, -3,
19, -8,11, -1,7, -5,28, -4,14, -5,10, -7,0）；3. scanning is used except a position after the intersection of origin 0 if identical
800 replace, you can obtain O2=（0,14, -4,9, -2,8, -7,12, -1,16,800,5, -6,15, -8,26, -5,0）, P2=（0,
13, -7,8, -4,9, -2,10, -1,19, -3,800, -8,5, -6,16,800,0）, Q2=（0,12, -6,30, -3,19, -8,
11, -1,7, -5,28, -4,14,800,10, -7,0）；4. scanning is except the previous step individual of origin 0, by number 800 successively using having
Effect position replaces；If number 800 is in even bit, by all marker number sequential scans of the row in purpose hole tray and a position
Except each even bit contrast after origin 0, if not occurring, 800 are replaced with this；, will if number 800 is in odd bits
That is not planned in transplanting hole tray all has seedling marker number sequential scan to remove each odd-even bit pair after origin 0 with position
Than the mark not occurred is randomly generated one to replace 800；It can obtain O3=（0,14, -4,9, -2,8, -7,12, -
1,16, -3,5, -6,15, -8,26, -5,0）, P3=（0,13, -7,8, -4,9, -2,10, -1,19, -3,28, -8,5, -6,16, -
5,0）, Q3=（0,12, -6,30, -3,19, -8,11, -1,7, -5,28, -4,14, -2,10, -7,0）.
P5：The population produced to above-mentioned crossover operation is randomly ordered, carries out mutation operation.2 are produced between 1 to 16
Random number r and s, as individual except 2 of origin 0 change dystopys：
If the label coding for becoming dystopy is negative, other negative flag coding random selections one are arranged from purpose hole tray, from change
Scanning is found the value and is exchanged with becoming dystopy in different individual：Assuming that r=2, offspring individual O3=（0,14, -4,9, -2,8, -7,12, -
1,16, -3,5, -6,15, -8,26, -5,0）, then one is produced in { -1, -2, -3, -5, -6, -7, -8 } except -4 reference numerals
Random number（It is set to -7）, then new offspring individual O after making a variation4=（0,14, -7,9, -2,8, -4,12, -1,16, -3,5, -6,15, -
8,26, -5,0）；
If becoming the label coding of dystopy as just, there is the positive label coding of seedling to select at random from do not planned in hole tray all are transplanted
Select one to be interchangeable, and travel through the replaced offspring individual of gene, if there is identical positive label coding, with former label coding
Number replaces：Assuming that s=9, offspring individual P3=（0,13, -7,8, -4,9, -2,10, -1,19, -3,28, -8,5, -6,16, -5,
0）, then a random number is produced in { 1,2,3 ... ..., 48,49,50 } except 19 reference numerals（It is set to 20）, then new son after making a variation
Generation individual P3=（0,13, -7,8, -4,9, -2,10, -1,20, -3,28, -8,5, -6,16, -5,0）.
P6：Local genetic algorithm circulates the heavy insertion operation carried out：, intersection chosen to above-mentioned initial population, variation
The offspring individual produced afterwards carries out fitness calculating, is inserted into initial population again and replaces most unconformable parent individuality, keeps initial
Population scale.
P7：Local genetic algorithm judges whether that reaching default convergence times stops, and does not reach and progress P3 is then circulated to population
To the selection of P6, intersection, variation and weight insertion operation；Enter next step P8 if reaching.
P8：Default convergence times are reached to stop, and defeated also optimum results.As shown in figure 3, took for the 70th generation as convergence generation
Number, the maximum individual of population's fitness are as the local optimum path（0,4, -4,11, -3,2, -1,1, -2,3, -5,5, -8,
7, -7,6, -6,0）, as shown in Figure 4.
P9：Judge purpose hole tray respectively row whether completed local path optimization, if do not complete if in order by column from
P2 steps start the cycle over, if Fig. 4 is by order from left to right；If each row have been completed, into next step P10.
P10：Merge the local optimum path all arranged, generate the thin planting transplanting path of whole purpose hole tray.Such as Fig. 5 institutes
Show, merging path is（0,4, -4,11, -3,2, -1,1, -2,3, -5,5, -8,7, -7,6, -6,14, -15,15, -16,22, -
13,18, -9,9, -10,8, -11,10, -12,12, -14,23, -24,24, -23,13, -21,19, -18,17, -20,30, -22,
21, -19,16, -17,36, -30,25, -31,33, -29,20, -28,29, -27,28, -25,27, -26,31, -32,0）.
Claims (5)
1. a kind of pot seedling thin planting transplanting method for optimizing route based on Greedy genetic algorithm, by machine vision, oneself knows greenhouse alms bowl
The health and fitness information of pot seedling in the transplanting hole tray of seedling thin planting transplanter；It is characterized in that：Respectively to healthy seedling acupuncture point in transplanting hole tray
Coding is marked with hole position in purpose hole tray；Greedy heredity select excellent principle for purpose hole tray Hole by row subregion carry out office
The current path optimization of portion's genetic algorithm；Purpose hole tray row Hole is encoded has seedling cavities volume with what is do not planned in transplanting hole tray
Code is comprehensive, and generation random walk coding forms the initial population of Local genetic algorithm, and circulation makes choice, intersects, making a variation and again
Insertion operation is until presetting convergence times, using the maximum individual of population's fitness as the local optimum path；To successively each row it advise
The local optimum path drawn merges, that is, generates whole purpose hole tray thin planting transplanting path.
2. a kind of pot seedling thin planting transplanting method for optimizing route based on Greedy genetic algorithm according to claim 1, it is special
Sign is：It is described that coding is marked to hole position in healthy seedling acupuncture point in transplanting hole tray and purpose hole tray respectively, it is specially close
Each cavities for spending high transplanting hole tray and low density purpose hole tray has been fixed in the position of transplanter system, to transplanting hole tray
Interior health seedling cavities carries out arithmetic number mark by order from top to bottom, from left to right, each Hole in purpose hole tray is pressed from
Order under, from left to right carries out negative real number mark, and thus label coding is actual is implied with cavities position and pot seedling health
Information.
3. a kind of pot seedling thin planting transplanting method for optimizing route based on Greedy genetic algorithm according to claim 1, it is special
Sign is：The purpose hole tray Hole is carried out the current path optimization of Local genetic algorithm by row subregion, and specific is purpose cave
Cavities of circling or whirl in the air negative flag coding is by hole tray row subregion, by row order from left to right or from right to left, successively with transplanting in hole tray
The current optimum path planning for having the positive label coding synthesis of seedling cavities, carrying out Local genetic algorithm do not planned.
4. a kind of pot seedling thin planting transplanting method for optimizing route based on Greedy genetic algorithm according to claim 1, it is special
Sign is：Purpose hole tray row Hole coding has seedling cavities coding comprehensive with what is do not planned in transplanting hole tray, generate with
Machine path code forms the initial population of Local genetic algorithm, and circulation makes choice, intersects, makes a variation and weigh insertion operation until pre-
If convergence times, using the maximum individual of population's fitness as the local optimum path, specific Local genetic algorithm process description is such as
Under：
A) the initial population generation method of Local genetic algorithm is specially：Assuming that the negative flag of purpose hole tray row Hole is compiled
Code collection is { -1, -2, -3, -4, -5, -6, -7, -8 }, transplant hole tray in do not plan have the positive label coding collection of seedling cavities for 1,2,
3 ... ..., 48,49,50 }, then transplanting path intersects at random from origin and positive and negative label coding collection, can be formed such as（0,3 ,-
2,8, -4,9, -7,10, -1,7, -6,13, -3,5, -5,16, -8,0）Initial population item chromosome, algorithm set generation
Certain amount chromosome, that is, form initial population；
B) individual population's fitness is specially：The position for transplanting coordinate system of the actual mapping of coding in each chromosome it is known that
Then the path length of the mapping of specific each chromosome can also calculate, and be set tol(x), whereinl minWithl maxPopulation dye is represented respectively
The most short and longest path of colour solid；Defining individual population's fitness isC= (l max- l(x))/( l max -l min )；
C) selection operation that Local genetic algorithm circulation carries out is：Initial population is as parent, according to random sequence, with dyeing
Body fitness is select probability, select probabilityM>CChromosome as progeny population；
D) crossover operation that Local genetic algorithm circulation carries out is：After initial population selection operation generation progeny population, random row
Sequence, carries out crossover operation；1. hypothesis have O=（0,14, -4,9, -2,8, -7,12, -1,19, -3,13, -6,15, -8,26, -5,
0）, P=（0,13, -7,8, -4,9, -2,10, -1,7, -5,28, -8,5, -6,16, -3,0）, Q=（0,12, -6,30, -3,19, -
8,11, -1,16, -2,5, -4,14, -5,10, -7,0）Three progeny population chromosomes；2. 2 are produced between 1 to 16
Random number j and k, wherein j is as mating indicating bit, and k is used as mating step-length, then the jth of three child chromosomes+1 to j+k
Progressive exchange；If j+k >=16, order is taken as 16；If j=8, k=4 are individual after being intersected：O1=（0,14, -4,9, -2,8, -7,
12, -1,16, -2,5, -6,15, -8,26, -5,0）, P1=（0,13, -7,8, -4,9, -2,10, -1,19, -3,13, -8,5, -6,
16, -3,0）, Q1=（0,12, -6,30, -3,19, -8,11, -1,7, -5,28, -4,14, -5,10, -7,0）；3. scanning removes origin
A position after 0 intersection, is replaced if identical with 800, you can obtains O2=（0,14, -4,9, -2,8, -7,12, -1,16,800,
5, -6,15, -8,26, -5,0）, P2=（0,13, -7,8, -4,9, -2,10, -1,19, -3,800, -8,5, -6,16,800,0）, Q2
=（0,12, -6,30, -3,19, -8,11, -1,7, -5,28, -4,14,800,10, -7,0）；4. scanning is except the previous step of origin 0
Individual, number 800 is replaced using an effectively position successively；If number 800 is in even bit, by all marks of the row in purpose hole tray
Remember that number order scanning removes each even bit after origin 0 with position and contrasts, if not occurring, 800 are replaced with this；
If number 800 is in odd bits, will transplant do not planned in hole tray all has seedling marker number sequential scan with position except original
Each odd-even bit contrast after point 0, randomly generates one to replace 800 by the mark not occurred；It can obtain O3=
（0,14, -4,9, -2,8, -7,12, -1,16, -3,5, -6,15, -8,26, -5,0）, P3=（0,13, -7,8, -4,9, -2,10, -
1,19, -3,28, -8,5, -6,16, -5,0）, Q3=（0,12, -6,30, -3,19, -8,11, -1,7, -5,28, -4,14, -2,
10, -7,0）；
E) mutation operation that Local genetic algorithm circulation carries out is：The population produced to above-mentioned crossover operation is randomly ordered, carries out
Mutation operation；2 the random number r and s between 1 to 16 are produced, as individual except 2 change dystopys of origin 0：
If the label coding for becoming dystopy is negative, other negative flag coding random selections one are arranged from purpose hole tray, from variation
Scanning is found the value and is exchanged with becoming dystopy in body：Assuming that r=2, offspring individual O3=（0,14, -4,9, -2,8, -7,12, -1,
16, -3,5, -6,15, -8,26, -5,0）, then produced in { -1, -2, -3, -5, -6, -7, -8 } except -4 reference numerals one with
Machine number, is set to -7, then new offspring individual O after making a variation4=（0,14, -7,9, -2,8, -4,12, -1,16, -3,5, -6,15, -8,
26, -5,0）；
If becoming the label coding of dystopy as just, that is not planned out of transplanting hole tray all has the positive label coding of seedling to randomly choose one
It is a to be interchangeable, and the replaced offspring individual of gene is traveled through, if there is identical positive label coding, with former label coding number generation
Replace：Assuming that s=9, offspring individual P3=（0,13, -7,8, -4,9, -2,10, -1,19, -3,28, -8,5, -6,16, -5,0）, then
A random number is produced in { 1,2,3 ... ..., 48,49,50 } except 19 reference numerals, is set to 20, then new offspring individual after making a variation
P3=（0,13, -7,8, -4,9, -2,10, -1,20, -3,28, -8,5, -6,16, -5,0）；
F) the heavy insertion operation that Local genetic algorithm circulation carries out is：Produced after, intersection chosen to above-mentioned initial population, variation
Raw offspring individual carries out fitness calculating, is inserted into initial population again and replaces most unconformable parent individuality, keeps initial population
Scale；
Local genetic algorithm is reached default by making choice, intersecting, making a variation and weighing insertion operation to the circulation of above-mentioned initial population
Convergence times stop, and take the maximum individual of population's fitness in convergence generation to be used as the local optimum path.
5. a kind of pot seedling thin planting transplanting method for optimizing route based on Greedy genetic algorithm according to claim 1, it is special
Sign is：After being obtained after the local optimum path that all purposes hole tray respectively arranges, according to row order from left to right or from right to left
Merge, generate the thin planting transplanting path of whole purpose hole tray.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510346330.0A CN104978607B (en) | 2015-06-23 | 2015-06-23 | A kind of pot seedling thin planting transplanting method for optimizing route based on Greedy genetic algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510346330.0A CN104978607B (en) | 2015-06-23 | 2015-06-23 | A kind of pot seedling thin planting transplanting method for optimizing route based on Greedy genetic algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104978607A CN104978607A (en) | 2015-10-14 |
| CN104978607B true CN104978607B (en) | 2018-04-20 |
Family
ID=54275089
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510346330.0A Active CN104978607B (en) | 2015-06-23 | 2015-06-23 | A kind of pot seedling thin planting transplanting method for optimizing route based on Greedy genetic algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104978607B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106598043B (en) * | 2016-11-08 | 2018-10-30 | 中国科学院自动化研究所 | Parallel robot high-speed picking-up method for optimizing route towards multiple dynamic objects |
| CN107145961A (en) * | 2017-03-24 | 2017-09-08 | 南京邮电大学 | A kind of tour schedule planing method based on improved adaptive GA-IAGA |
| CN109459052B (en) * | 2018-12-28 | 2022-10-11 | 上海大学 | Full-coverage path planning method for sweeper |
| CN110889552B (en) * | 2019-11-26 | 2023-05-23 | 中国计量大学 | Apple automatic boxing path optimization method based on optimal parameter genetic algorithm |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102870534A (en) * | 2012-09-21 | 2013-01-16 | 浙江大学 | Genetic algorithm based automatic bowl transporting route optimization method of plug seedlings |
| CN102939815A (en) * | 2012-10-11 | 2013-02-27 | 江苏大学 | Seedling taking and seedling planting path planning for pot seedling transplanting robot |
| CN103955753A (en) * | 2014-04-14 | 2014-07-30 | 浙江大学 | Automatic plug seedling transplanting path optimization method based on artificial ant colony |
-
2015
- 2015-06-23 CN CN201510346330.0A patent/CN104978607B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102870534A (en) * | 2012-09-21 | 2013-01-16 | 浙江大学 | Genetic algorithm based automatic bowl transporting route optimization method of plug seedlings |
| CN102939815A (en) * | 2012-10-11 | 2013-02-27 | 江苏大学 | Seedling taking and seedling planting path planning for pot seedling transplanting robot |
| CN103955753A (en) * | 2014-04-14 | 2014-07-30 | 浙江大学 | Automatic plug seedling transplanting path optimization method based on artificial ant colony |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104978607A (en) | 2015-10-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104978607B (en) | A kind of pot seedling thin planting transplanting method for optimizing route based on Greedy genetic algorithm | |
| Jiang et al. | A simple and fast hypervolume indicator-based multiobjective evolutionary algorithm | |
| Tse et al. | A memetic algorithm for multiple-drug cancer chemotherapy schedule optimization | |
| CN104156780B (en) | A kind of bow member type chip mounter integrated optimization method based on coevolution | |
| CN103279332A (en) | Data flow parallel processing method based on GPU-CUDA platform and genetic algorithm | |
| CN101256648A (en) | Genetic operation operator based on indent structure for producing quening system | |
| CN108038575A (en) | Waypoint location planing method based on modified NSGA II | |
| CN105992230A (en) | Wireless network planning method and device | |
| CN108492025A (en) | High-end equipment manufacturing coordinated dispatching method based on mixing difference genetic algorithm | |
| CN106611378A (en) | Priority encoding-based hybrid genetic algorithm for solving job-shop scheduling problem | |
| CN102870534B (en) | Genetic algorithm based automatic bowl transporting route optimization method of plug seedlings | |
| CN106843997A (en) | A kind of parallel virtual machine polymerization based on Spark with optimization MBBO algorithms | |
| CN109819891A (en) | Small stream sweet-smelling grass tissue-cultured seedling60Co- gamma Rays method for mutation breeding | |
| Evren | Interactive compromise programming | |
| CN106875031A (en) | A kind of many Job Shop Scheduling method and devices | |
| CN116777087A (en) | Intelligent agriculture layout method and system | |
| Räihä et al. | Complementary crossover for genetic software architecture synthesis | |
| CN112214885A (en) | Irrigation area crop irrigation water quantity optimal distribution method under insufficient irrigation condition | |
| CN116307214A (en) | Automatic cotton distribution method based on NSGA-II algorithm and related device | |
| Bhatt et al. | In search of no-loss strategies for the game of tic-tac-toe using a customized genetic algorithm | |
| CN107886572A (en) | A kind of non-topological coherence three-dimensional geological block method for tracing of view-based access control model observation | |
| CN106406233B (en) | A kind of tact balance method of flexible machine addend control production unit | |
| CN115129017B (en) | Hot-cold processing discrete manufacturing production scheduling method based on hybrid Archimedes algorithm | |
| Sözen | Solving Travelling Salesman Problem: A Hybrid Optimization Algorithm | |
| De Beukelaer | Discrete optimization algorithms for marker-assisted plant breeding |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20151014 Assignee: ZHEJIANG KALUOLAINA WEAVING Co.,Ltd. Assignor: ZHEJIANG SCI-TECH University Contract record no.: X2021330000803 Denomination of invention: A greedy genetic algorithm based method for optimizing transplanting path of potted seedlings with sparse planting Granted publication date: 20180420 License type: Common License Record date: 20211215 |
|
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20151014 Assignee: Zhejiang Hongyuan Intelligent Technology Co.,Ltd. Assignor: ZHEJIANG SCI-TECH University Contract record no.: X2023330000751 Denomination of invention: A greedy genetic algorithm based method for optimizing the transplanting path of potted seedlings with sparse planting Granted publication date: 20180420 License type: Common License Record date: 20230928 |
|
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20151014 Assignee: Wenzhou Chaoxin Software Development Co.,Ltd. Assignor: ZHEJIANG SCI-TECH University Contract record no.: X2023330000834 Denomination of invention: A greedy genetic algorithm based method for optimizing the transplanting path of potted seedlings with sparse planting Granted publication date: 20180420 License type: Common License Record date: 20231109 Application publication date: 20151014 Assignee: GLOBALS ELECTRONICS (WENZHOU) Co.,Ltd. Assignor: ZHEJIANG SCI-TECH University Contract record no.: X2023330000820 Denomination of invention: A greedy genetic algorithm based method for optimizing the transplanting path of potted seedlings with sparse planting Granted publication date: 20180420 License type: Common License Record date: 20231107 |
|
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20151014 Assignee: Zhejiang Boshang Textile Co.,Ltd. Assignor: ZHEJIANG SCI-TECH University Contract record no.: X2024330000028 Denomination of invention: A greedy genetic algorithm based method for optimizing the transplanting path of bowl seedlings with sparse planting Granted publication date: 20180420 License type: Common License Record date: 20240403 |
|
| EE01 | Entry into force of recordation of patent licensing contract |