CN112734136B - Particle swarm optimization-based rotation irrigation group optimization method and system - Google Patents
Particle swarm optimization-based rotation irrigation group optimization method and system Download PDFInfo
- Publication number
- CN112734136B CN112734136B CN202110104378.6A CN202110104378A CN112734136B CN 112734136 B CN112734136 B CN 112734136B CN 202110104378 A CN202110104378 A CN 202110104378A CN 112734136 B CN112734136 B CN 112734136B
- Authority
- CN
- China
- Prior art keywords
- irrigation
- group
- optimization
- particles
- rotation
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Mining
Abstract
The invention relates to a particle swarm optimization-based rotation irrigation group optimization method and system, which are characterized by comprising the following steps of: 1) establishing a multi-target wheel irrigation set optimization model by taking the minimum flow average difference and the shortest path of a switch valve of each wheel irrigation set as optimization targets, and determining constraint conditions of the multi-target wheel irrigation set optimization model; 2) solving the multi-target rotation irrigation group optimization model established in the step 1) by adopting a discrete particle swarm optimization algorithm, and performing grouping optimization on the rotation irrigation groups based on the obtained solution. The drip irrigation rotation irrigation set optimization mathematical model and the intelligent solution algorithm are established, the problems of time consumption, labor consumption and low efficiency of manual calculation of the rotation tank set are solved, the universality is good, and the drip irrigation rotation set optimization mathematical model and the intelligent solution algorithm are suitable for the division problem of most drip irrigation rotation irrigation sets. Therefore, the invention can be widely applied to the field of drip irrigation.
Description
Technical Field
The invention relates to a particle swarm optimization-based wheel irrigation group optimization method and system, and belongs to the technical field of drip irrigation.
Background
The under-mulch drip irrigation is a modern water-saving irrigation technology suitable for mechanized field cultivation aiming at the large-scale planting characteristics and assembly integration of Xinjiang on the basis of combining the advantages of a drip irrigation technology and a mulching film planting technology. The drip irrigation rotation irrigation mode has relatively centralized water amount and simple and convenient management, is an irrigation engineering mode suitable for centralized continuous large-scale land management, and is also a main application mode of the current Xinjiang under-film drip irrigation engineering. By 2019, the under-film drip irrigation scale of the Xinjiang Uygur autonomous region exceeds 5000 ten thousand mu (containing 1500 ten thousand mu of weapons), and accounts for about 60 percent of the proportion of the nation.
The drip irrigation rotation irrigation group takes the irrigation range of the control area of one branch pipe as a basic irrigation unit, one or more branch pipes form a rotation irrigation group (for example, in 1-1,1-2,1-3,2-1,2-2, 2-3, the front number represents a branch pipe, the rear number represents a branch pipe number, and the whole rotation irrigation group is formed). And (3) switching valves according to the rotation irrigation group division sequence planned by the engineering to complete regional plot irrigation by managers, namely forming a drip irrigation rotation irrigation grouping working system. With the innovation of the large agricultural operation system of the Xinjiang war group, part of enterprises realize standardization and unification of the group land planting by carrying out unified operation management on the group land agricultural planting land and farmers, and the standardized scene is relatively stable in crop planting and operation relationship. Under this kind of mode, a peasant household often need control several hundreds of thousands of mu field irrigation tasks, because there are unreasonable scheduling problem in the irrigation wheel irrigation group design, often leads to peasant household ooff valve intensity of labour big, and the ooff valve route sets up the unreasonable round trip that leads to of unreasonable and runs, work efficiency low grade problem.
The traditional rotation irrigation group design is mainly based on the 'micro irrigation engineering technical standard' standard, basic data such as water sources, crops, weather and local irrigation are obtained in the early stage, calculation is carried out according to a hydraulic calculation formula and the requirement of pipe network flow balance, and rotation irrigation group division is obtained by a manual calculation and adjustment method. And the manual experience adjusting method is low in efficiency, time-consuming and labor-consuming. Meanwhile, the existing drip irrigation rotation irrigation group is mainly divided according to the flow, the lift balance and other angles, and the problems of calculation for reducing the labor intensity of farmers and calculation for planning paths of switching valves in practical application scenes are lacked.
Disclosure of Invention
Aiming at the problems, the invention aims to provide a method and a system for optimizing a rotation irrigation group based on a particle swarm optimization algorithm, so as to solve the problems that the manual division efficiency of the current rotation irrigation group is low and the labor intensity of opening and closing valves of farmers is high.
In order to realize the purpose, the invention adopts the following technical scheme:
the invention provides a first aspect of a rotation irrigation group optimization method based on a particle swarm optimization algorithm, which comprises the following steps:
1) establishing a multi-target wheel irrigation set mathematical optimization model by taking the minimum flow average difference and the shortest path of a switch valve of each wheel irrigation set as optimization targets, and determining constraint conditions of the multi-target wheel irrigation set mathematical optimization model;
2) solving the multi-target rotation irrigation set mathematical model established in the step 1) by adopting a discrete particle swarm algorithm, and performing grouping optimization on the rotation irrigation set based on the obtained solution.
Further, in the step 1), the method for establishing the multi-target rotation irrigation set mathematical optimization model and determining the constraint conditions thereof comprises the following steps:
1.1) establishing a multi-target rotation irrigation set mathematical model by taking the minimum flow average difference and the shortest path of a switch valve of each rotation irrigation set as optimization targets;
1.2) determining constraint conditions of the multi-target rotation irrigation set mathematical model according to related execution technical standards.
Further, in the step 1.1), the established multi-target rotation irrigation group optimization model is as follows:
wherein, the model f 1 (x) Representing the mean square error of flow of the irrigation block, model f 2 (x) Representing the path distance of the manual switch valve of the wheel irrigation group; j represents the number of the irrigation rotation group, i represents the number of the drip irrigation branch pipe; c represents the flow rate of the rotation irrigation groupVariance; alpha is alpha j Representing the average flow of each rotation irrigation group; f j The flow sum of the jth rotation irrigation group is; m represents the number of rotation irrigation groups; d represents the sum of all the switching valve paths; s j The shortest path is calculated for the jth irrigation round group by adopting Dijkstra algorithm.
Further, in the step 1.2), the constraint conditions include a flow constraint, a group flow difference constraint and a variable constraint.
Further, the calculation formula of each constraint condition is as follows:
flow constraint:
wherein f is i Designing flow for the branch number, wherein the flow of the jth wheel irrigation group should be smaller than the designed flow, and F is the designed flow of the wheel irrigation group; x ij Showing the opening and closing states of the ith branch pipe in the jth rotation irrigation group, X ij 0 and 1 respectively indicate that the state of the ith branch pipe is off and on in the jth wheel irrigation group; n represents the number of branch pipes of the drip irrigation rotation irrigation group;
group flow difference constraints:
ΔF＝MAX(F j )-MIN(F j )＜β
wherein, the delta F is the flow difference of the rotation irrigation set; f j The flow sum of the jth rotation irrigation group is; beta is a flow difference threshold value, and the default is 5% of the design flow;
③ variable constraint:
X ij ＝{0,1}
wherein, X ij Showing the opening and closing states of the ith branch pipe in the jth rotation irrigation group, X ij The status of the ith branch pipe in the jth wheel irrigation group is off and on respectively represented by 0 and 1.
Further, in the step 2), the method for solving the multi-target rotation irrigation set optimization model established in the step 1) by adopting a discrete particle swarm optimization comprises the following steps:
2.1) according to the number M of the irrigation rounds, the number N of the branch pipes, the design flow F and the number F of the branch pipes i And multi-target rotation irrigation groupEstablishing a target function by using a model, and setting parameters;
2.2) initializing the discrete particle group particles with the encoding mode of X ij Each row represents a rotation irrigation group, and variables in each row randomly generate 0 and 1 to represent that the branch pipe in the rotation irrigation group is in an off state and an on state;
specifically, a grid-based mode is adopted to establish an initial solution, drip irrigation areas are equally divided according to a grid mode, a random point is randomly generated in each grid area, each random point represents a wheel irrigation group, the random points bring peripheral switch valves into the wheel irrigation group in a shortest path mode by a greedy strategy, and the wheel irrigation group initial solution is established to obtain:
wherein, X ij Showing the opening and closing states of the ith branch pipe in the jth rotation irrigation group, X ij 0 and 1 respectively indicate that the state of the ith branch pipe is off and on in the jth wheel irrigation group; n represents the number of branch pipes of the drip irrigation rotation irrigation group; m represents the number of rotation irrigation groups;
2.3) calculating the fitness value of the initialized particles and copying non-inferior solutions into a non-inferior solution set; updating the individual speed and position of the particle, judging whether the particle swarm particles generated in the step 2.2) meet the constraint condition, discarding the particle swarm particles if the particle swarm particles do not meet the constraint condition, and returning to the step 2.2) to continue generating new particles;
the velocity update formula is:
V id ＝ωV id +c1·rand()·(p id -x id )+c2·rand()·(p gd -x id )
the particle position update formula is:
wherein:
wherein, omega represents the inertia weight, and the value is 0.5 in the invention; c1 and c2 represent acceleration factors, and take random numbers in (0,1) in the invention; p is a radical of id Representing a local optimal position of the particle; p is a radical of gd Representing a global optimal position of the particle; x is the number of id Indicating the position of the particle; and x id ，p id ，p gd But only 0 or 1; rand () means to take [0,1 ]]Two random numbers within the range; v id Indicating the rate of change of position due to v id Indicates probability, so the value is limited to [0,1 ]]To (c) to (d);
2.4) calculating the particle density of the non-inferior solution set, and finding out new global extremum and individual extremum;
2.5) judging whether the updated particles meet constraint conditions, if not, repairing the updated particles, and if so, entering the step 2.6);
2.6) judging the space distance of the particles to avoid falling into local optimum; respectively calculating the space distance between the particles and the global optimal particles, comparing the space distance with a threshold value, if the space distance is smaller than the threshold value, reinitializing the particles, and otherwise, turning to the step 2.7);
threshold definition:
wherein, T and T max Respectively representing the current iteration times and the maximum iteration times, ub and lb represent the upper and lower lines of the particles, and k represents an adjusting parameter;
2.7) updating the position and the speed of the particles, and selecting global particles and individual extreme values;
2.8) judging whether a convergence condition or the maximum iteration times is reached, if the condition is reached, outputting a result, and if the condition is reached, outputting the number of the branch pipes of each wheel irrigation group according to the Dijkstra algorithm, otherwise, turning to the step 2.3).
Further, in the step 2.4), the method for finding out new global extremum and individual extremum includes:
firstly, all targets of a multi-target optimization problem jointly guide particles to fly in a solution space to obtain a non-inferior optimal solution, and global optimal particles and individual optimal particles are updated;
secondly, using the objective functions f 1 And f 2 Calculating a particle fitness value, selecting global optimal particles and individual optimal particles corresponding to each objective function, and taking the global particle mean value corresponding to each objective function as global particles;
thirdly, selecting the individual optimal particles according to the individual optimal particle dispersion degree of each target function, wherein the dispersion degree is according to the space distance between the two particles;
the calculation formula of the particle space distance is as follows:
wherein l represents the particle space distance; x 1 (d) And X 2 (d) Representing two particles in the population, D represents the number of the particles, and D represents the D-dimension particle;
and finally, if the distance between the two optimal particles is larger than the global particle distance, taking the average value of the two optimal particles, otherwise, randomly selecting one of the individual optimal particles.
In a second aspect of the present invention, a rotation irrigation group optimization system based on a particle swarm optimization is provided, which includes: the optimization model establishing module is used for establishing a multi-target rotation irrigation set optimization model by taking the minimum flow average difference and the shortest path of a switch valve of each rotation irrigation set as optimization targets and determining constraint conditions of the multi-target rotation irrigation set optimization model; and the optimization model solving module is used for solving the established multi-target rotation irrigation group optimization model by adopting a discrete particle swarm algorithm and performing grouping optimization on the rotation irrigation group based on the obtained optimal solution.
Further, the optimization model establishing module comprises a model determining module, and the model determining module is used for determining that the minimum flow average difference and the shortest path of the switching valve of each wheel irrigation group are taken as optimization targets, and establishing a multi-target wheel irrigation group optimization model based on the determined optimization targets; and the constraint condition determining module is used for determining the constraint conditions of the multi-target rotation irrigation set optimization model.
Further, the multi-target rotation irrigation group optimization model determined in the model determination module is as follows:
wherein, the model f 1 (x) Representing the mean square error of flow of the irrigation block, model f 2 (x) Representing the path distance of the manual switch valve of the wheel irrigation group; j represents the number of the irrigation rotation group, i represents the number of the drip irrigation branch pipe; c represents the mean square error of the flow of the rotation irrigation group; alpha is alpha j Representing the average flow of each rotation irrigation group; f j The flow sum of the jth rotation irrigation group is; m represents the number of rotation irrigation groups; d represents the sum of all the switching valve paths; s j The shortest path is calculated for the jth irrigation round group by adopting Dijkstra algorithm.
Due to the adoption of the technical scheme, the invention has the following advantages: 1. the method establishes the multi-target wheel irrigation group optimization model and the intelligent solution algorithm, solves the problems of time consumption, labor consumption and low efficiency of manual calculation of the wheel tank group, has better universality, and is suitable for the division problem of most drip irrigation wheel irrigation groups. 2. Aiming at the problem that only the flow of a pipe network is considered in hydraulic calculation of a traditional wheel irrigation group, from the perspective of use of users, the shortest requirement of a manual switch valve path is considered, a model which gives consideration to both the flow of the pipe network and the shortest path is provided, the labor intensity of the switch valve of farmers can be reduced, and a solution is provided for the practical application scene of drip irrigation engineering. Therefore, the invention can be widely applied to the technical field of drip irrigation.
Drawings
FIG. 1 is a flow chart of a method for optimizing a rotation irrigation group based on a particle swarm optimization in an embodiment of the invention;
fig. 2 is a flowchart of solving a model by using a particle swarm algorithm in the embodiment of the present invention.
Detailed Description
The invention is described in detail below with reference to the figures and examples.
According to the crop rotation group optimization method based on the particle swarm optimization, the problem of manual path planning under the condition of meeting the drip irrigation flow balance condition is solved by establishing a model taking the minimum flow average difference and the shortest path of a switch valve of each crop rotation group as optimization targets and solving a mathematical model by using the discrete particle swarm optimization, so that an optimal crop rotation group division scheme is obtained, and the existing drip irrigation working regime is optimized.
Specifically, as shown in fig. 1 and 2, the method for optimizing a rotation irrigation group based on a particle swarm optimization provided by the invention comprises the following steps:
1) and establishing a multi-target wheel irrigation set optimization model by taking the minimum flow average difference and the shortest path of a switch valve of each wheel irrigation set as optimization targets, and determining constraint conditions of the multi-target wheel irrigation set optimization model.
Specifically, the method comprises the following steps:
1.1) establishing a multi-target rotation irrigation set optimization model by taking the minimum flow average difference and the shortest path of a switch valve of each rotation irrigation set as optimization targets.
The established multi-target rotation irrigation group optimization model comprises the following steps:
wherein, the model f 1 (x) Representing the mean square error of flow of the irrigation block, model f 2 (x) Representing the path distance of the manual switch valve of the wheel irrigation group; j represents the number of the irrigation rotation group, i represents the number of the drip irrigation branch pipe; c represents the mean square error of the flow of the rotation irrigation group; alpha is alpha j Representing the average flow of each rotation irrigation group; f j Representing the flow sum of the jth rotation irrigation group; m represents the number of rotation irrigation groups; d represents the sum of all the switching valve paths; s j Shows that the shortest path is calculated for the jth irrigation round group by Dijkstra algorithm.
Model f 1 (x) In (3), the calculation formula of each parameter is as follows:
wherein, X ij Showing the opening and closing state of the ith branch pipe in the jth rotation irrigation group when X is ij 0 and 1 respectively indicate that the state of the ith branch pipe is off and on in the jth wheel irrigation group; f. of i The flow rate is designed for the ith branch.
Model f 2 (x) In (3), the calculation formula of each parameter is as follows:
S j ＝Dijkstra((x 1j ,y 1j ),(x 2j ,y 2j ),…,(x ij ,y ij ),…,(x Nj ,y Nj ) Equation 8)
And setting coordinates for each branch pipe number by taking the upper left corner as a starting point according to the engineering drawing. c, d represent any two branch numbers, x c ，x d ，y c ，y d Respectively represent the x, y horizontal and vertical coordinates of the branch numbers c and d, L cd Represents the distance between any two points; n represents the number of branch pipes of the drip irrigation rotation irrigation group; x ij Represents the ith rootThe opening and closing state of the branch pipe in the jth wheel irrigation group; (x) ij ,y ij ) Is shown when X ij Coordinates of branch number i when 1.
1.2) determining constraint conditions of the multi-target rotation irrigation group optimization model according to related execution technical standards, such as micro irrigation engineering technical standards.
The constraint conditions include flow constraint, group flow difference constraint and variable constraint, and specifically, the calculation formula is as follows:
flow constraint:
wherein f is i Designing flow for the branch number, wherein the flow of the jth wheel irrigation group should be smaller than the designed flow, and F is the wheel irrigation group.
Group flow difference constraints:
ΔF＝MAX(F j )-MIN(F j ) < beta formula 11
Wherein, Δ F is the flow difference of the rotation irrigation set, β is the flow difference threshold, and the default is 5% of the design flow.
③ variable constraint:
X ij 0,1 equation 12
Wherein, X ij Showing the opening and closing state of the ith branch pipe in the jth rotation irrigation group when X is ij The status of the ith branch pipe in the jth wheel irrigation group is off and on respectively represented by 0 and 1.
2) Solving the multi-target rotation irrigation group optimization model established in the step 1) by adopting a discrete particle swarm optimization algorithm, and performing grouping optimization on the rotation irrigation groups based on the obtained optimal solution.
Specifically, the method comprises the following steps:
2.1) according to the number M of the irrigation rounds, the number N of the branch pipes, the design flow F and the number F of the branch pipes i And constructing an objective function by the multi-objective rotation irrigation group mathematical model, wherein the maximum iteration times are set to be 300 times by parameters, and the total number of particles is 100. The maximum iteration number and the total number of particles can be adjusted according to actual needs.
2.2) initializing the discrete particle group particles with the encoding mode of X ij Each row represents a rotation group, and the variables in each row randomly generate 0 and 1, which represent the states of the drip irrigation branch pipes in the rotation group as off and on.
The invention adopts a grid-based mode to establish an initial solution, equally divides a drip irrigation area according to the grid mode, randomly generates a random point in each grid area, each random point represents a wheel irrigation group, and the random points bring peripheral switch valves into the wheel irrigation group according to the shortest path mode by a greedy strategy, thereby establishing the wheel irrigation group initial solution.
2.3) calculating the fitness value of the initialized particles and copying the non-inferior solution into a non-inferior solution set. Updating the individual speed and position of the particles according to formulas 14 and 15, judging whether the particle swarm particles generated in the step 2.2) meet the constraint condition, discarding the particles if the particle swarm particles do not meet the constraint condition, and returning to the step 2.2) to continuously generate new particles.
And (3) updating the speed:
V id ＝ωV id +c1·rand()·(p id -x id )+c2·rand()·(p gd -x id ) Equation 14
Particle position:
wherein:
wherein, omega represents the inertia weight, and the value is 0.5 in the invention; c1 and c2 represent acceleration factors, and take random numbers in (0,1) in the invention; p is a radical of id Representing a local optimal position of the particle; p is a radical of gd Representing a global optimal position of the particle; x is the number of id Bit representing a particlePlacing; and x id ，p id ，p gd But only 0 or 1; rand () means to take [0,1]Two random numbers within the range; v id Indicating the rate of change of position due to v id Indicates probability, so the value is limited to [0,1 ]]In the meantime.
2.4) calculating the particle density of the non-inferior solution set, and finding out new global extremum and individual extremum.
The specific method comprises the following steps: through the common guidance of each target of the multi-target optimization problem, the particles fly in the solution space to obtain a non-inferior optimal solution, the particle density of the non-inferior solution set is calculated, the overall optimal particles and the individual optimal particles are updated, and the target function f is used for each 1 And f 2 Calculating a particle fitness value, selecting global optimal particles and individual optimal particles corresponding to each objective function, adopting a global particle mean value corresponding to each objective function as global particles, selecting the individual optimal particles according to the discrete degree of the individual optimal particles of each objective function, wherein the discrete degree is calculated according to the space distance between the two particles by a space distance formula 17, if the distance between the two optimal particles is greater than the global particle distance, taking the average value of the two optimal particles, and otherwise, randomly selecting one of the individual optimal particles.
The particle space distance is:
wherein, X 1 (d) And X 2 (d) Is two particles in the population, D is the number of particles, and D represents the D-dimension particle.
2.5) judging whether the updated particles meet the constraint conditions, if not, repairing the particles, and if so, entering the step 2.6).
2.6) judging the space distance of the particles, avoiding falling into local optimum, and designing a random initialization mechanism to improve algorithm diversity and global search capability. And respectively calculating the space distance between the particles and the global optimal particles, comparing the space distance with a threshold value, and if the space distance is smaller than the threshold value, re-initializing the particles. Otherwise, the next step is carried out.
Threshold definition:
wherein, T and T max The current iteration times and the maximum iteration times are respectively, ub and lb are upper and lower lines of the particles, k is an adjusting parameter, and the threshold value is smaller and smaller along with the increase of the iteration times.
2.7) updating the position and the speed of the particles and selecting the global particles and the individual extreme values.
2.8) judging whether a convergence condition or the maximum iteration times is reached, if the condition is reached, outputting a result, and if the condition is reached, outputting the branch pipe number of each wheel irrigation group according to Dijkstra algorithm, otherwise, turning to the step 2.3).
The invention also provides a rotation irrigation group optimization system based on the particle swarm optimization, which comprises the following steps: the optimization model establishing module is used for establishing a multi-target rotation irrigation set optimization model by taking the minimum flow average difference and the shortest path of a switch valve of each rotation irrigation set as optimization targets and determining constraint conditions of the multi-target rotation irrigation set optimization model; and the optimization model solving module is used for solving the established multi-target rotation irrigation group optimization model by adopting a discrete particle swarm algorithm and performing grouping optimization on the rotation irrigation group based on the obtained optimal solution.
Further, the optimization model establishing module comprises a model determining module, and the model determining module is used for determining that the minimum flow mean difference and the shortest path of the switching valve of each wheel irrigation group are taken as optimization targets, and establishing a multi-target wheel irrigation group optimization model based on the determined optimization targets; and the constraint condition determining module is used for determining the constraint conditions of the multi-target rotation irrigation set optimization model.
Further, the multi-target rotation irrigation group optimization model determined in the model determination module is as follows:
wherein, the model f 1 (x) Represents the mean square error of the flow of the rotation irrigation group, and a model f 2 (x) Representing the path distance of the manual switch valve of the wheel irrigation group; j represents the number of the irrigation rotation group, i represents the number of the drip irrigation branch pipe; c represents the mean square error of the flow of the rotation irrigation group; alpha is alpha j Representing the average flow of each rotation irrigation group; f j The flow sum of the jth rotation irrigation group is; m represents the number of rotation irrigation groups; d represents the sum of all the switching valve paths; s j Shows that the shortest path is calculated for the jth irrigation round group by Dijkstra algorithm.
The above embodiments are only used for illustrating the present invention, and the structure, connection mode, manufacturing process, etc. of the components may be changed, and all equivalent changes and modifications performed on the basis of the technical solution of the present invention should not be excluded from the protection scope of the present invention.
Claims (6)
1. A rotation irrigation group optimization method based on a particle swarm optimization algorithm is characterized by comprising the following steps:
1) establishing a multi-target wheel irrigation set mathematical optimization model by taking the minimum flow average difference and the shortest path of a switch valve of each wheel irrigation set as optimization targets, and determining constraint conditions of the multi-target wheel irrigation set mathematical optimization model;
the method for establishing the multi-target rotation irrigation set mathematical optimization model and determining the constraint conditions comprises the following steps of:
1.1) establishing a multi-target rotation irrigation set mathematical model by taking the minimum flow average difference and the shortest path of a switch valve of each rotation irrigation set as optimization targets;
the established multi-target rotation irrigation group optimization model is as follows:
wherein, the model f 1 (x) Representing the mean square error of flow of the irrigation block, model f 2 (x) Representing the path distance of the manual switch valve of the wheel irrigation group; j represents a rotation irrigation group number; c represents the mean square error of the flow of the rotation irrigation group; alpha is alpha j Representing the average flow of each rotation irrigation group; f j The flow sum of the jth rotation irrigation group is; m represents the number of rotation irrigation groups; d represents the sum of all the switching valve paths; s j The shortest path is calculated for the jth irrigation round group by adopting Dijkstra algorithm;
1.2) determining constraint conditions of the multi-target rotation irrigation set mathematical model according to related execution technical standards;
2) solving the multi-target rotation irrigation set mathematical model established in the step 1) by adopting a discrete particle swarm algorithm, and performing grouping optimization on the rotation irrigation set based on the obtained solution.
2. The particle swarm optimization-based rotation irrigation group optimization method of claim 1, wherein: in the step 1.2), the constraint conditions include a flow constraint, a group flow difference constraint and a variable constraint.
3. The particle swarm optimization-based rotation irrigation group optimization method of claim 2, wherein: the calculation formula of each constraint condition is as follows:
flow constraint:
wherein f is i Designing flow for the branch number, wherein the flow of the jth wheel irrigation group should be smaller than the designed flow, and F is the designed flow of the wheel irrigation group; x ij Showing the opening and closing states of the ith branch pipe in the jth rotation irrigation group, X ij 0 and 1 respectively indicate that the state of the ith branch pipe is off and on in the jth wheel irrigation group; n represents the number of branch pipes of the drip irrigation rotation irrigation group;
group flow difference constraints:
ΔF＝MAX(F j )-MIN(F j )<β
wherein, the delta F is the flow difference of the rotation irrigation set; f j The flow sum of the jth rotation irrigation group is; beta is the flow differenceA threshold value of 5% of the design flow by default;
③ variable constraint:
X ij ＝{0,1}
wherein, X ij Showing the opening and closing states of the ith branch pipe in the jth rotation irrigation group, X ij The status of the ith branch pipe in the jth wheel irrigation group is off and on respectively represented by 0 and 1.
4. The particle swarm optimization-based rotation irrigation group optimization method of claim 1, wherein: in the step 2), the method for solving the multi-target rotation irrigation set optimization model established in the step 1) by adopting the discrete particle swarm optimization comprises the following steps:
2.1) according to the number M of the irrigation rounds, the number N of the branch pipes, the design flow F and the number F of the branch pipes i Constructing a target function by the multi-target rotation irrigation group optimization model, and setting parameters;
2.2) initializing the discrete particle group particles with the encoding mode of X ij Each row represents a rotation irrigation group, and variables in each row randomly generate 0 and 1 to represent that the branch pipe in the rotation irrigation group is in an off state and an on state;
specifically, a grid-based mode is adopted to establish an initial solution, drip irrigation areas are equally divided according to a grid mode, a random point is randomly generated in each grid area, each random point represents a wheel irrigation group, the random points bring peripheral switch valves into the wheel irrigation group in a shortest path mode by a greedy strategy, and the wheel irrigation group initial solution is established to obtain:
wherein, X ij Showing the opening and closing states of the ith branch pipe in the jth rotation irrigation group, X ij 0 and 1 respectively indicate that the state of the ith branch pipe is off and on in the jth wheel irrigation group; n represents the number of branch pipes of the drip irrigation rotation irrigation group; m represents the number of rotation irrigation groups;
2.3) calculating the fitness value of the initialized particles and copying non-inferior solutions into a non-inferior solution set; updating the individual speed and position of the particle, judging whether the particle swarm particles generated in the step 2.2) meet the constraint condition, discarding the particle swarm particles if the particle swarm particles do not meet the constraint condition, and returning to the step 2.2) to continue generating new particles;
the velocity update formula is:
V id ＝ωV id +c1·rand()·(p id -x id )+c2·rand()·(p gd -x id )
the particle position update formula is:
wherein:
wherein, omega represents the inertia weight, and the value in the invention is 0.5; c1 and c2 represent acceleration factors, and take random numbers in (0,1) in the invention; p is a radical of id Representing a local optimal position of the particle; p is a radical of gd Representing a global optimal position of the particle; x is the number of id Indicating the position of the particle; and x id ，p id ，p gd But only 0 or 1; rand () means to take [0,1]Two random numbers within the range; v id Indicating the rate of change of position due to v id Indicates probability, so the value is limited to [0,1 ]]To (c) to (d);
2.4) calculating the particle density of the non-inferior solution set, and finding out new global extremum and individual extremum;
2.5) judging whether the updated particles meet constraint conditions, if not, repairing the updated particles, and if so, entering the step 2.6);
2.6) judging the space distance of the particles to avoid falling into local optimum; respectively calculating the space distance between the particles and the global optimal particles, comparing the space distance with a threshold value, if the space distance is smaller than the threshold value, reinitializing the particles, and otherwise, turning to the step 2.7);
threshold definition:
wherein, T and T max Respectively representing the current iteration times and the maximum iteration times, ub and lb represent the upper and lower lines of the particles, and k represents an adjusting parameter;
2.7) updating the position and the speed of the particles, and selecting global particles and individual extreme values;
2.8) judging whether a convergence condition or the maximum iteration times is reached, if the condition is reached, outputting a result, and if the condition is reached, outputting the number of the branch pipes of each wheel irrigation group according to the Dijkstra algorithm, otherwise, turning to the step 2.3).
5. The particle swarm optimization-based rotation irrigation group optimization method of claim 4, wherein: in the step 2.4), the method for finding out new global extremum and individual extremum includes:
firstly, all targets of a multi-target optimization problem jointly guide particles to fly in a solution space to obtain a non-inferior optimal solution, and global optimal particles and individual optimal particles are updated;
secondly, using the objective functions f 1 And f 2 Calculating a particle fitness value, selecting global optimal particles and individual optimal particles corresponding to each objective function, and taking the global particle mean value corresponding to each objective function as global particles;
thirdly, selecting the individual optimal particles according to the individual optimal particle dispersion degree of each target function, wherein the dispersion degree is according to the space distance between the two particles;
the calculation formula of the particle space distance is as follows:
wherein l represents the particle space distance; x 1 (d) And X 2 (d) Representing two particles in the population, D represents the number of the particles, and D represents the D-dimension particle;
and finally, if the distance between the two optimal particles is larger than the global particle distance, taking the average value of the two optimal particles, otherwise, randomly selecting one of the individual optimal particles.
6. The utility model provides a rotation irrigation group optimizing system based on particle swarm optimization, its characterized in that includes: the optimization model establishing module is used for establishing a multi-target rotation irrigation set optimization model by taking the minimum flow average difference and the shortest path of a switch valve of each rotation irrigation set as optimization targets and determining constraint conditions of the multi-target rotation irrigation set optimization model; the optimization model solving module is used for solving the established multi-target wheel irrigation group optimization model by adopting a discrete particle swarm algorithm and carrying out grouping optimization on the wheel irrigation group based on the obtained optimal solution;
the optimization model establishing module comprises a model determining module and a multi-target rotation irrigation set optimizing module, wherein the model determining module is used for determining that the minimum flow mean difference and the shortest path of a switching valve of each rotation irrigation set are taken as optimization targets, and establishing a multi-target rotation irrigation set optimizing model based on the determined optimization targets; the constraint condition determining module is used for determining the constraint conditions of the multi-target rotation irrigation group optimization model;
the multi-target rotation irrigation set optimization model determined in the model determination module is as follows:
wherein, the model f 1 (x) Representing the mean square error of flow of the irrigation block, model f 2 (x) Representing the path distance of the manual switch valve of the wheel irrigation group; j represents a rotation irrigation group number; c represents the mean square error of the flow of the rotation irrigation group; alpha is alpha j Representing the average flow of each rotation irrigation group; f j The flow sum of the jth rotation irrigation group is; m represents the number of rotation irrigation groups; d represents the sum of all the switching valve paths; s. the j The shortest path is calculated for the jth irrigation round group by adopting Dijkstra algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110104378.6A CN112734136B (en) | 2021-01-26 | 2021-01-26 | Particle swarm optimization-based rotation irrigation group optimization method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110104378.6A CN112734136B (en) | 2021-01-26 | 2021-01-26 | Particle swarm optimization-based rotation irrigation group optimization method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112734136A CN112734136A (en) | 2021-04-30 |
| CN112734136B true CN112734136B (en) | 2022-08-02 |
Family
ID=75593643
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110104378.6A Active CN112734136B (en) | 2021-01-26 | 2021-01-26 | Particle swarm optimization-based rotation irrigation group optimization method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112734136B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117035373B (en) * | 2023-10-09 | 2024-01-23 | 中国电建集团山东电力管道工程有限公司 | Intelligent management method and system for pipeline prefabrication production line |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102156914A (en) * | 2011-03-30 | 2011-08-17 | 东华大学 | Method for cooperatively and optimally allocating water volume in non-flood season |
| CN106651011A (en) * | 2016-11-30 | 2017-05-10 | 中国农业大学 | Particle swarm algorithm-based canal system optimization water distribution method |
| CN106960129A (en) * | 2017-04-01 | 2017-07-18 | 中工武大设计研究有限公司 | A kind of rotation flow partition method |
| CN107122847A (en) * | 2017-04-07 | 2017-09-01 | 中国科学院东北地理与农业生态研究所 | A kind of canal system based on double-deck particle swarm algorithm matches somebody with somebody water optimizing method |
| CN107578116A (en) * | 2017-07-20 | 2018-01-12 | 东华大学 | Irrigating water quality Optimal Configuration Method based on Bi-objective immunity particle cluster algorithm |
| CN109496520A (en) * | 2018-11-27 | 2019-03-22 | 湖北工业大学 | A kind of multiple target water-fertilizer integral system rotation flow partition method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7058478B2 (en) * | 2003-04-25 | 2006-06-06 | George Alexanian | Irrigation controller water management with temperature budgeting |
| CN110178518B (en) * | 2019-07-03 | 2021-09-28 | 鄄城县亿碧源节水设备科技有限公司 | Liquid manure irrigation system |
-
2021
- 2021-01-26 CN CN202110104378.6A patent/CN112734136B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102156914A (en) * | 2011-03-30 | 2011-08-17 | 东华大学 | Method for cooperatively and optimally allocating water volume in non-flood season |
| CN106651011A (en) * | 2016-11-30 | 2017-05-10 | 中国农业大学 | Particle swarm algorithm-based canal system optimization water distribution method |
| CN106960129A (en) * | 2017-04-01 | 2017-07-18 | 中工武大设计研究有限公司 | A kind of rotation flow partition method |
| CN107122847A (en) * | 2017-04-07 | 2017-09-01 | 中国科学院东北地理与农业生态研究所 | A kind of canal system based on double-deck particle swarm algorithm matches somebody with somebody water optimizing method |
| CN107578116A (en) * | 2017-07-20 | 2018-01-12 | 东华大学 | Irrigating water quality Optimal Configuration Method based on Bi-objective immunity particle cluster algorithm |
| CN109496520A (en) * | 2018-11-27 | 2019-03-22 | 湖北工业大学 | A kind of multiple target water-fertilizer integral system rotation flow partition method |
Non-Patent Citations (3)
| Title |
|---|
| Multi-objective particle swarm optimization applied to water distribution systems design: An approach with human interaction;IdelMontalvo et al.;《Mathematical and Computer Modelling》;20100219;第52卷(第7-8期);第1219-1227页 * |
| 滴灌轮灌分组优化模型与算法;李伟等;《农业工程学报》;20210523;第37卷(第10期);第73-81页 * |
| 考虑水头损失的管道灌溉分水口轮灌分组优化模型;李彬等;《灌溉排水学报》;20210115;第40卷(第1期);第144-148页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112734136A (en) | 2021-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111639811B (en) | Multi-agricultural-machine collaborative operation remote management scheduling method based on improved ant colony algorithm | |
| CN106529674B (en) | Multiple no-manned plane cooperates with mine to target assignment method | |
| CN1312629C (en) | Modeling method of uncertain hydraulics model for urban seweage and drainage system | |
| CN109945881A (en) | A kind of method for planning path for mobile robot of ant group algorithm | |
| CN109144102A (en) | A kind of Path Planning for UAV based on improvement bat algorithm | |
| CN108805349A (en) | A kind of crop-planting spatial configuration optimal method based on improvement cuckoo algorithm | |
| CN112734136B (en) | Particle swarm optimization-based rotation irrigation group optimization method and system | |
| CN109345068B (en) | A kind of Hydropower Plant Reservoir two stages random optimization dispatching method based on remaining benefits approximation to function | |
| CN112636368B (en) | Automatic power generation control method for multi-source multi-region interconnected power system | |
| CN101710384A (en) | Improved particle filtering method based on niche genetic algorithm | |
| CN113985888B (en) | Forklift path planning method and system based on improved ant colony algorithm | |
| CN106169109A (en) | A kind of Optimized Scheduling of Hydroelectric Power method based on chaos difference particle cluster algorithm | |
| CN109753680A (en) | A kind of swarm of particles intelligent method based on chaos masking mechanism | |
| CN112071122A (en) | Unmanned aerial vehicle group path planning method for information acquisition | |
| CN110490422A (en) | A kind of target fighting efficiency method for situation assessment based on game cloud model | |
| CN112215715A (en) | Irrigation area water and soil resource balance optimization configuration method based on underground water level regulation | |
| CN110579961B (en) | Three-dimensional planting-oriented garden intelligent water supply method and system | |
| CN109496520B (en) | Multi-target water and fertilizer integrated system irrigation rotation group division method | |
| CN116029405A (en) | Multi-target dynamic water distribution method based on irrigation area canal system | |
| CN110321995A (en) | A kind of difference Particle Swarm Mixed Algorithm based on Stochastic inertia weight | |
| CN110399697A (en) | Control distribution method based on the aircraft for improving genetic learning particle swarm algorithm | |
| CN110118382A (en) | General operation regulation strategy identification and evaluation method for heat exchange station | |
| CN112484732B (en) | IB-ABC algorithm-based unmanned aerial vehicle flight path planning method | |
| CN111397607A (en) | Information filtering method adopting parallel fusion mechanism | |
| CN111160654A (en) | Transportation path optimization method for reducing total cost based on fuzzy C-means-simulated annealing algorithm |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |