CN103020731A - Vegetable cultivation crop arrangement method based on particle swarm - Google Patents
Vegetable cultivation crop arrangement method based on particle swarm Download PDFInfo
- Publication number
- CN103020731A CN103020731A CN2012104607156A CN201210460715A CN103020731A CN 103020731 A CN103020731 A CN 103020731A CN 2012104607156 A CN2012104607156 A CN 2012104607156A CN 201210460715 A CN201210460715 A CN 201210460715A CN 103020731 A CN103020731 A CN 103020731A
- Authority
- CN
- China
- Prior art keywords
- solution
- fitness
- vegetables
- vegetable
- suboptimal
- 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.)
- Granted
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a vegetable cultivation crop arrangement optimization method based on a particle swarm. According to the method, on the basis of analyzing the influence on the vegetable quality and yield caused by the vegetable variety, region, cultivation mode and cultivation facility and limitation of various constraint conditions, the operation of minimizing vegetable crop number and optimizing the vegetable quality and yield as an optimization target, the vegetable cultivation crop arrangement is mapped as the traveling saleman problem, and an optimized particle swarm algorithm for combining the tabu search and simulated annealing algorithm is provided for solving the model. According to the method, automation and optimization of the vegetable cultivation crop arrangement can be realized, the labor intensity of yield arrangement personnel is reduced, the reasonability of the yield arrangement plan is improved, the vegetable crop number is reduced, the management difficulty is lowered, the vegetable quality and the vegetable yield are improved, the economic benefits are increased, and the function of saving energy and reducing consumption can be realized.
Description
Technical field
The present invention relates to vegetables scheduling of production field, relate in particular to the automatic arrangement method of growing vegetables crops for rotation based on population.
Background technology
In the past growing vegetables crops for rotation scheme of arrangement is fully by manually working out by the personal experience, plantation crops for rotation arrangement mainly is subjected to the impact of the factors such as labour, planting facility (open country, booth etc.), land area, cropping pattern (broadcast sowing, dibbling, field planting etc.), zone, weather, when arranging the vegetables crops for rotation, even experienced supvr also considers not comprehensive easily.Therefore, be necessary to find a kind of intelligent arrangement method to realize the automatic establishment of production planning and sequencing, can take into account the factor of the aspects such as existing resource, output, quality and harvest time.
We start with from minimizing the crops for rotation number, improve vegetables overall productivity and quality etc., quantize all kinds of factors to the impact of production planning and sequencing, thereby the vegetables production planning and sequencing are mapped as the traveling salesman problem of Problem with Some Constrained Conditions with the method for mathematical modeling.Although traveling salesman problem can provide optimum solution in theory, be proved to be a np hard problem, the time of finding the solution is exponential increase with problem scale, is difficult to optimum or the suboptimal solution of the problem that obtains with conventional method.In recent years, in order to address this problem, the researcher makes up the method for solving that the artificial intelligence approaches such as method, way improvement method, synthetic heuristics, neural network, genetic algorithm, swarm intelligence have been set up traveling salesman problem based on way both at home and abroad.Such as, Nan Xu has proposed a kind of method Traveling Salesman Problem of chaotic neural network, and Cai Rongying has then proposed the iterate improvement ant colony optimization algorithm, and Liu Qiang solves traveling salesman problem with particle swarm optimization algorithm.Said method has greatly promoted the research of traveling salesman problem and the application in the Practical Project, but still has weak point.Relative the fixing of the form of locally optimal solution and globally optimal solution is absorbed in easily local optimum or causes speed of convergence slower, greatly affects accuracy and the efficient of algorithm.
Summary of the invention
(1) technical matters to be solved
The purpose of this invention is to provide a kind of growing vegetables crops for rotation arrangement method based on population, to minimize vegetables crops for rotation number, improve vegetables overall yield and quality, reducing vegetables is target in the ground time.
(2) technical scheme
The invention provides a kind of arrangement method of the growing vegetables crops for rotation based on population, the method comprises:
S1, all vegetables crops for rotation are mapped as n node one by one, and set up evaluation function:
Wherein, P is overall quality and the output of vegetables, and C is total crops for rotation number, z
iThe weight coefficient of the planting facility of i stubble vegetables, a
iBe the cultivated area of i stubble vegetables, m
IjThe output of i stubble vegetables j kind quality, q
IjThe weight coefficient of i stubble vegetables j kind quality, Q
iThe kind number of i stubble vegetables, t
IjBe i stubble vegetables j kind quality in the ground time.k
1, k
2It is weight coefficient;
The parameter of S2, initialization evaluation function; Definition fitness function f (L, G) and the scale of maximum iteration time and initialization population, position and the speed of particle;
S3, based on evaluation function, from initialized population, select locally optimal solution, suboptimal solution and globally optimal solution, suboptimal solution;
S4, utilize simulated annealing, initialization temperature and annealing coefficient;
S5, judge whether each other neighborhood solution of part/globally optimal solution, suboptimal solution, if execution in step S6 then; Otherwise accepting the best solution of fitness is current new state, directly execution in step S7;
S6, outside neighborhood, generate at random two new solution S
L, S
G, and S
L, S
GNot in each self-corresponding taboo list; Calculate S
L, S
GFitness f (the S of the new particle that obtains
L, S
G) whether be better than current any solution f (L, G), if then accept S
L, S
GThe new particle that calculates is current new state, and with S
L, S
GPut into corresponding taboo list, and the initialization taboo time, simultaneously, the scanning taboo list will discharge from taboo list above the state of taboo time, otherwise accepts S with probability a
L, S
GThe new particle that calculates is current new state, accepts to have the optimum of best fitness, new particle that suboptimal solution calculates as current state take probability (1-a);
New speed and the reposition of S7, calculating particle;
S8, reduction temperature T, and whether judge T less than 0, if then based on above-mentioned new speed and position, upgrade local optimum, suboptimal solution and global optimum, suboptimal solution, execution in step S9, otherwise execution in step S5;
S9, judge whether to reach maximum iteration time, if, then export optimal path, otherwise execution in step S4.
Preferably, among the described step S1 all vegetables crops for rotation are mapped as n node one by one according to planting facility, cropping pattern and kind.
Preferably, fitness function f (L, G) is defined as described in the step S2:
f(L，G)＝arg?max
(L，G)p(X(L，G))
In iteration,
X
t+1(L，G)＝ω*X
t(L，G)+c
1*rand()*(L-X
t(L，G))+c
2*rand()*(G-X
t(L，G))
T is iterations, L ∈ { locally optimal solution, local suboptimal solution }, G ∈ { globally optimal solution, overall suboptimal solution }, ω, c
1, c
2Be weight coefficient, rand () is random function.
Preferably, among the described step S5 otherwise to accept the best solution of fitness be that current new state specifically comprises;
Local optimum, suboptimal solution and global optimum, suboptimal solution are put into respectively fitness function, calculate the fitness of gained reposition, select best global solution and the local system of solutions of fitness to close;
Preferably, among the described step S6 local optimum, suboptimal solution and global optimum, suboptimal solution are put into respectively fitness function, calculate respectively the fitness of new particle, choose the f (L, G) of fitness optimum, and probability a=exp ((p (S
L, S
G)-p (L, G))/T).
(3) beneficial effect
Analyzing on current planting conditions (total area, in ground area, planting facility), labour, planting area and the basis of goods and materials on the impact of institute's varieties of plant, to minimize vegetables crops for rotation number, improve vegetables overall yield and quality, minimizing is optimization aim at the ground fate, set up the optimized mathematical model that the growing vegetables crops for rotation arrange automatically, and proposed a kind of growing vegetables crops for rotation based on population in conjunction with tabu search and simulated annealing and automatically arrange algorithm that model is found the solution.
The method can realize the automatic arrangement of growing vegetables crops for rotation, reduced row's product personnel's labour intensity, utilize intelligent optimization algorithm, by quantizing vegetables overall yield and quality, reasonable arrangement is produced, both improve yield and quality, kept again the soil fertility in soil fertility and soil, taken into account simultaneously labour's the crop rotation of rationally using and guarantee the soil.
Description of drawings
Fig. 1 is the flow chart of steps of method provided by the present invention.
Embodiment
Below in conjunction with the drawings and specific embodiments the present invention is described in further details.
The present invention is mapped as traveling salesman problem with the arrangement of growing vegetables crops for rotation, and has proposed a kind of population optimization algorithm in conjunction with tabu search and simulated annealing objective function is found the solution.As shown in Figure 1, be flow chart of steps of the present invention:
S1, all vegetables crops for rotation are mapped as n node one by one, and set up evaluation function:
Wherein, P is overall quality and the output of vegetables, and C is total crops for rotation number, z
iThe weight coefficient of the planting facility of i stubble vegetables, a
iBe the cultivated area of i stubble vegetables, m
IjThe output of i stubble vegetables j kind quality, q
IjThe weight coefficient of i stubble vegetables j kind quality, Q
iThe kind number of i stubble vegetables, t
IjBe i stubble vegetables j kind quality in the ground time.k
1, k
2It is weight coefficient;
The parameter of S2, initialization evaluation function; Definition fitness function f (L, G) and the scale of maximum iteration time and initialization population, position and the speed of particle;
S3, based on evaluation function, from initialized population, select locally optimal solution, suboptimal solution and globally optimal solution, suboptimal solution; Wherein, part/global solution is a series of position, namely travels through the path of node.
S4, utilize simulated annealing, initialization temperature T and annealing coefficient;
S5, judge whether each other neighborhood solution of part/globally optimal solution, suboptimal solution, if execution in step S6 then; Otherwise accepting the best solution of fitness is current new state, directly execution in step S7;
S6, outside neighborhood, generate at random two new solution S
L, S
G, and S
L, S
GNot in each self-corresponding taboo list; Calculate S
L, S
GFitness f (the S of the new particle that obtains
L, S
G) whether be better than current any solution f (L, G), if then accept S
L, S
GThe new particle that calculates is current new state, and with S
L, S
GPut into corresponding taboo list, and the initialization taboo time, simultaneously, the scanning taboo list will discharge from taboo list above the state of taboo time, otherwise accepts S with probability a
L, S
GThe new particle that calculates is current new state, accepts to have the optimum of best fitness, new particle that suboptimal solution calculates as current state take probability (1-a);
Here used the thought of tabu search algorithm and simulated annealing, the taboo list representative:
Locally optimal solution and suboptimal solution be neighborhood each other, if their neighborhood each other then needs to walk around, reselects; Global optimum and suboptimal solution are too; Use taboo list and shortened search time, with certain probability selection current state, then can jump out locally optimal solution.
New speed and the reposition of S7, calculating particle;
S8, reduction temperature T, and whether judge T less than 0, if then based on above-mentioned new speed and position, upgrade local optimum, suboptimal solution and global optimum, suboptimal solution, execution in step S9, otherwise execution in step S5;
S9, judge whether to reach maximum iteration time, if, then export optimal path, otherwise execution in step S4.
Preferably, among the described step S1 all vegetables crops for rotation are mapped as n node one by one according to planting facility, cropping pattern and kind.
Preferably, fitness function f (L, G) is defined as described in the step S2:
f(L，G)＝arg?max
(L，G)p(X(L，G))
In iteration,
X
t+1(L，G)＝ω*X
t(L，G)+c
1*rand()*(L-X
t(L，G))+c
2*rand()*(G-X
t(L，G))
T is iterations, L ∈ { locally optimal solution, local suboptimal solution }, G ∈ { globally optimal solution, overall suboptimal solution }, ω, c
1, c
2Be weight coefficient, rand () is random function.This function has determined the adaptive value of particle.
Preferably, among the described step S5 otherwise to accept the best solution of fitness be that current new state specifically comprises;
Local optimum, suboptimal solution and global optimum, suboptimal solution are put into respectively fitness function, calculate the fitness of gained reposition, select best global solution and the local system of solutions of fitness to close;
Preferably, among the described step S6 local optimum, suboptimal solution and global optimum, suboptimal solution are put into respectively fitness function, calculate respectively the fitness of new particle, choose the f (L, G) of fitness optimum, and probability a=exp ((p (S
L, S
G)-p (L, G))/T).
Concrete calculating and step:
(1) all vegetables crops for rotation are mapped as n node one by one according to planting facility, cropping pattern and kind, quantize vegetables overall quality and output with unified evaluation function, the evaluation function formula is:
Wherein, C is total crops for rotation number, z
iThe weight coefficient of the planting facility of i stubble dish, a
iBe the cultivated area of i stubble dish, m
IjThe output of i stubble dish j kind quality, q
IjThe weight coefficient of i stubble dish j kind quality, Q
iThe kind number of i stubble dish, t
IjBe i stubble dish j kind quality in the ground time.k
1, k
2Be weight coefficient, value is respectively 1.1 and 0.9 in the present embodiment, and evaluation function specifically is solved to:
(2) initiation parameter, definition fitness function f (L, G) and maximum iteration time are 100 times, and the initialization population, comprise position and the speed of scale and particle;
Wherein, fitness function f (L, G) is defined as:
f(L，G)＝argmax
(L，G)p(X(L，G))
X
T+1(L, G) is used for representative function X (L, G) and obtains L ∈ { L by iterative computation
1, L
2Be local optimum, suboptimum disaggregation, G ∈ { G
1, G
2Global optimum, suboptimum disaggregation, t represents iterations, rand () is random function;
X
T+1(L, G)=ω * X
t(L, G)+c
1* rand () * (L-X
t(L, G))+c
2* rand () * (G-X
t(L, G)) (3) based on evaluation function, selects locally optimal solution L from initialized population
1, suboptimal solution L
2With globally optimal solution G
1, suboptimal solution G
2
(4) utilize simulated annealing, the initialization temperature is 1000; Annealing coefficient is 0.95;
(5) judging part/global optimum, suboptimal solution neighborhood whether each other, if then carry out (6), is current new state otherwise then accept the best solution of fitness, directly carries out (7);
Wherein, current new state is the target location that the transfering state of a upper node namely shifts, and is communicated with if two solutions are eight neighborhoods, then thinks each other neighborhood solution of two solutions; Local optimum, suboptimal solution and global optimum, suboptimal solution are put into respectively fitness function, calculate the fitness of gained reposition, select best global solution and the local system of solutions of fitness to close;
(6) outside neighborhood, generate at random two new node S
L, S
G, and S
L, S
GNot in each self-corresponding taboo list; Utilize tabu search, taboo list representative: locally optimal solution and suboptimal solution be neighborhood each other, if their neighborhood each other then needs to walk around, reselects; Global optimum and suboptimal solution are too;
Judge S
L, S
GFitness f (the S of the new particle that calculates
L, S
G) whether be better than current any solution f (L, G), namely judge fitness difference DELTA u=f (S
L, S
G)-max (f (G1), f (G2));
If S item is accepted in Δ u＞0
L, S
GThe new particle that calculates is current new state, and with S
L, S
GPut into corresponding taboo list, and the initialization taboo time, simultaneously, the scanning taboo list will discharge from taboo list above the state of taboo time; Otherwise then accept S with probability a
L, S
GThe new particle that calculates is current new state, accepts to have the optimum of maximum adaptation degree, new particle that suboptimal solution calculates as current state take probability (1-a);
Reposition S
LWith L
1And L
2Neighborhoods each other not, S
GWith G
1And G
2Neighborhood each other not; Concrete is calculated as, with S
LAnd S
GPut into following formula and calculate new particle position:
X
T+1(L, G)=ω * X
t(L, G)+c
1* rand () * (L-X
t(L, G))+c
2* rand () * (G-X
t(L, G)); ω is 0.5, c
1Be 0.3, c
2Be 0.2;
Then calculate the evaluating deg f (S of new particle
L, S
G), in like manner, local optimum, suboptimal solution and global optimum, suboptimal solution are put into respectively following formula, then calculate respectively the evaluating deg of new particle, and choose the f (L, G) of evaluating deg optimum, if f is (S
L, S
G)＞f (L, G) then accepts S
LAnd S
GThe particle that calculates is current new state; Otherwise, with probability a=exp ((f (S
L, S
G)-f (L, G))/T) accept S
LAnd S
GThe particle that calculates is current new state, with probability 1-a=(1-exp ((f (S
L, S
G)-f (L, G))/T)) accepting the particle that f (L, G) calculates is current new state;
(7) new speed and the reposition of calculating particle;
The current location of the particle that step S6 calculates is as the reposition of particle, and new speed then is v
T+1=X
T+1-X
t
(8) carry out annealing operation, reduce temperature T, and whether judge T less than 0, if then based on above-mentioned new speed and position, upgrade local optimum, suboptimal solution and global optimum, suboptimal solution, execution in step (9), otherwise execution in step (5);
Wherein, the annealing formula is T=0.95*T, temperature T is reduced during the course gradually, only after a production schedule arrangement is finished, upgrade local optimum, suboptimal solution by the current fitness that calculates particle, and in conjunction with local optimum, the suboptimal solution of all particles, upgrade global optimum, suboptimal solution.
(9) if reach maximum iteration time, then export optimal path, otherwise turn (4);
The above only is preferred implementation of the present invention; should be pointed out that for those skilled in the art, under the prerequisite that does not break away from the technology of the present invention principle; can also make some improvement and replacement, these improvement and replacement also should be considered as protection scope of the present invention.
Claims (5)
1. arrangement method based on the growing vegetables crops for rotation of population is characterized in that the method comprises:
S1, all vegetables crops for rotation are mapped as n node one by one, and set up evaluation function:
Wherein, P is overall quality and the output of vegetables, and C is total crops for rotation number, z
iThe weight coefficient of the planting facility of i stubble vegetables, a
iBe the cultivated area of i stubble vegetables, m
IjThe output of i stubble vegetables j kind quality, q
IjThe weight coefficient of i stubble vegetables j kind quality, Q
iThe kind number of i stubble vegetables, t
IjBe i stubble vegetables j kind quality in the ground time.k
1, k
2It is weight coefficient;
The parameter of S2, initialization evaluation function; Definition fitness function f (L, G) and maximum iteration time, and position and the speed of the scale of initialization population, particle;
S3, based on evaluation function, from initialized population, select locally optimal solution, suboptimal solution and globally optimal solution, suboptimal solution;
S4, utilize simulated annealing, initialization temperature T and annealing coefficient;
S5, judge whether each other neighborhood solution of part/globally optimal solution, suboptimal solution, if execution in step S6 then; Otherwise accepting the best solution of fitness is current new state, directly execution in step S7;
S6, outside neighborhood, generate at random two new solution S
L, S
G, and S
L, S
GNot in each self-corresponding taboo list; Calculate S
L, S
GFitness f (the S of the new particle that obtains
L, S
G) whether be better than current any solution f (L, G), if then accept S
L, S
GThe new particle that calculates is current new state, and with S
L, S
GPut into corresponding taboo list, and the initialization taboo time, simultaneously, the scanning taboo list will discharge from taboo list above the state of taboo time, otherwise accepts S with probability a
L, S
GThe new particle that calculates is current new state, accepts to have the optimum of best fitness, new particle that suboptimal solution calculates as current state take probability (1-a);
New speed and the reposition of S7, calculating particle;
S8, reduction temperature T, and whether judge T less than 0, if then based on above-mentioned new speed and position, upgrade local optimum, suboptimal solution and global optimum, suboptimal solution, execution in step S9, otherwise execution in step S5;
S9, judge whether to reach maximum iteration time, if, then export optimal path, otherwise execution in step S4.
2. method as claimed in claim 1 is characterized in that, among the described step S1 all vegetables crops for rotation is mapped as n node one by one according to planting facility, cropping pattern and kind.
3. method as claimed in claim 1 is characterized in that the f of fitness function described in the step S2 (L, G) is defined as:
f(L，G)＝arg?max
(L，G)p(X(L，G))
In iteration,
X
i+1(L，G)＝ω*X
t(L，G)+c
1*rand()*(L-X
t(L，G))+c
2*rand()*(G-X
t(L，G))；
T is iterations, L ∈ { locally optimal solution, local suboptimal solution }, G ∈ { globally optimal solution, overall suboptimal solution }, ω, c
1, c
2Be weight coefficient, rand () is random function.
4. method as claimed in claim 1 is characterized in that, among the described step S5 otherwise to accept the best solution of fitness be that current new state specifically comprises;
Local optimum, suboptimal solution and global optimum, suboptimal solution are put into respectively fitness function, calculate the fitness of gained reposition, select best global solution and the local system of solutions of fitness to close.
5. method as claimed in claim 1 is characterized in that, among the described step S6 local optimum, suboptimal solution and global optimum, suboptimal solution is put into respectively fitness function, calculates respectively the fitness of new particle, chooses the f (L, G) of fitness optimum; And probability a=exp ((p (S
L, S
G)-p (L, G))/T).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210460715.6A CN103020731B (en) | 2012-11-15 | 2012-11-15 | Based on the arrangement method of the growing vegetables crops for rotation of population |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210460715.6A CN103020731B (en) | 2012-11-15 | 2012-11-15 | Based on the arrangement method of the growing vegetables crops for rotation of population |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103020731A true CN103020731A (en) | 2013-04-03 |
| CN103020731B CN103020731B (en) | 2015-09-30 |
Family
ID=47969313
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210460715.6A Active CN103020731B (en) | 2012-11-15 | 2012-11-15 | Based on the arrangement method of the growing vegetables crops for rotation of population |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103020731B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105550521A (en) * | 2015-12-21 | 2016-05-04 | 四川航天系统工程研究所 | Catering optimization method based on intelligent particle step length transform |
| CN111382933A (en) * | 2020-03-04 | 2020-07-07 | 海南金盘智能科技股份有限公司 | Method and system for generating transformer scheduling scheme |
| US20200356078A1 (en) * | 2019-05-10 | 2020-11-12 | Mjnn Llc | Efficient selection of experiments for enhancing performance in controlled environment agriculture |
| CN114254902A (en) * | 2021-12-13 | 2022-03-29 | 四川启睿克科技有限公司 | Multi-production-line personnel scheduling method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102013037A (en) * | 2010-12-16 | 2011-04-13 | 上海电机学院 | Method and device for searching path based on particle swarm optimization (PSO) |
| CN102222268A (en) * | 2011-06-02 | 2011-10-19 | 西安电子科技大学 | Method for scheduling flow shop based on multi-swarm hybrid particle swarm algorithm |
| CN102278996A (en) * | 2011-04-29 | 2011-12-14 | 西南交通大学 | Ant colony optimization processing method of large-scale multi-target intelligent moving route selection |
-
2012
- 2012-11-15 CN CN201210460715.6A patent/CN103020731B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102013037A (en) * | 2010-12-16 | 2011-04-13 | 上海电机学院 | Method and device for searching path based on particle swarm optimization (PSO) |
| CN102278996A (en) * | 2011-04-29 | 2011-12-14 | 西南交通大学 | Ant colony optimization processing method of large-scale multi-target intelligent moving route selection |
| CN102222268A (en) * | 2011-06-02 | 2011-10-19 | 西安电子科技大学 | Method for scheduling flow shop based on multi-swarm hybrid particle swarm algorithm |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105550521A (en) * | 2015-12-21 | 2016-05-04 | 四川航天系统工程研究所 | Catering optimization method based on intelligent particle step length transform |
| CN105550521B (en) * | 2015-12-21 | 2018-06-26 | 四川航天系统工程研究所 | Pantry optimization method based on particle intelligent transformation step-length |
| US20200356078A1 (en) * | 2019-05-10 | 2020-11-12 | Mjnn Llc | Efficient selection of experiments for enhancing performance in controlled environment agriculture |
| CN111382933A (en) * | 2020-03-04 | 2020-07-07 | 海南金盘智能科技股份有限公司 | Method and system for generating transformer scheduling scheme |
| CN111382933B (en) * | 2020-03-04 | 2023-05-09 | 海南金盘智能科技股份有限公司 | Method and system for generating transformer scheduling scheme |
| CN114254902A (en) * | 2021-12-13 | 2022-03-29 | 四川启睿克科技有限公司 | Multi-production-line personnel scheduling method |
| CN114254902B (en) * | 2021-12-13 | 2024-04-02 | 四川启睿克科技有限公司 | Multi-production-line personnel scheduling method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103020731B (en) | 2015-09-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Khoshnevisan et al. | Comparison of energy consumption and GHG emissions of open field and greenhouse strawberry production | |
| US11957094B2 (en) | Centralized predictive controller for management and optimal operation of microgrid powered greenhouses | |
| CN103020731B (en) | Based on the arrangement method of the growing vegetables crops for rotation of population | |
| CN108077042A (en) | A kind of winter wheat time of infertility irrigates early warning decision method | |
| CN105678629A (en) | Planting industry problem solution system based on internet of things | |
| CN108781926A (en) | Greenhouse irrigation system based on neural network prediction and method | |
| CN104573860A (en) | Automatic large-scale vegetable planting enterprise planting plan generation method | |
| CN203775797U (en) | Multilayer three-dimensional greenhouse | |
| Bagnerini et al. | Mixed-integer linear programming for the scheduling of seedings in an industrial adaptive vertical farm | |
| Braik et al. | Review of agrivoltaics systems potential in Palestine | |
| CN101766091B (en) | Stereoscopic agricultural production method | |
| Mai et al. | The path planning of agricultural agv in potato ridge cultivation | |
| Rudoy et al. | Key challenges and opportunities of scientific and technological development of Russia’s crop industry | |
| Khatri et al. | Hydroponics: Advantages and Challenges in Soilless Farming | |
| Liao et al. | Factors influencing the recessive morphology of farmland use under labor changes based on production input willingness and behavior of farmers | |
| De Juan et al. | Management of water consumption in agriculture: A model for the economic optimisation of water use: application to a sub-humid area | |
| Barghash et al. | Applying Operation Research Methodologies to Hydroponic Crop Scheduling in a Closed System: An Integer Programming Approach | |
| Baruah et al. | Present status and future demand for energy for bullock-operated paddy-farms in Assam (India) | |
| Liu et al. | Research on agricultural machine scheduling in hilly areas based on Improved Non-dominated Sorting Genetic Algorithm-III | |
| CN102999787B (en) | The optimization method that a kind of growing vegetables crops for rotation arrange | |
| CN106718321A (en) | Greenhouse three-dimensional module formula has native cultivating device and method | |
| Parameswari et al. | Vertical Farming: Revolutionizing Sustainable Agriculture in the 21st Century | |
| Kartika et al. | Organic Agricultural Discourse in the Highlands and Lowlands. Case Study: Subang Regency, West Java Province | |
| Zhao et al. | An optimal model of a agriculture circular system for paddy & edible fungus & dry land | |
| Lecler et al. | A framework and methods to assess irrigation and drainage decisions. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |