CN116644575B - Intelligent design adjusting equipment for saline-alkali degree of wetland - Google Patents
Intelligent design adjusting equipment for saline-alkali degree of wetland Download PDFInfo
- Publication number
- CN116644575B CN116644575B CN202310596473.1A CN202310596473A CN116644575B CN 116644575 B CN116644575 B CN 116644575B CN 202310596473 A CN202310596473 A CN 202310596473A CN 116644575 B CN116644575 B CN 116644575B
- Authority
- CN
- China
- Prior art keywords
- plant
- land
- planting
- alkali
- unit
- 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
- 238000013461 design Methods 0.000 title claims abstract description 66
- 239000003513 alkali Substances 0.000 title claims abstract description 60
- 241000196324 Embryophyta Species 0.000 claims abstract description 122
- 239000002689 soil Substances 0.000 claims abstract description 61
- 230000000694 effects Effects 0.000 claims abstract description 42
- 238000000034 method Methods 0.000 claims abstract description 30
- 238000007599 discharging Methods 0.000 claims abstract description 23
- 238000012216 screening Methods 0.000 claims abstract description 23
- 241000287828 Gallus gallus Species 0.000 claims description 29
- 235000013330 chicken meat Nutrition 0.000 claims description 29
- 150000003839 salts Chemical class 0.000 claims description 15
- 241000282421 Canidae Species 0.000 claims description 12
- 241000282461 Canis lupus Species 0.000 claims description 9
- 241001354532 Holozonia filipes Species 0.000 claims description 7
- 238000011161 development Methods 0.000 claims description 7
- 230000033001 locomotion Effects 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 230000007423 decrease Effects 0.000 claims description 3
- 230000003247 decreasing effect Effects 0.000 claims description 3
- 230000006978 adaptation Effects 0.000 claims 2
- 230000008901 benefit Effects 0.000 abstract description 6
- 230000007613 environmental effect Effects 0.000 abstract description 5
- 230000004083 survival effect Effects 0.000 description 16
- 239000000243 solution Substances 0.000 description 13
- 238000013480 data collection Methods 0.000 description 8
- 230000033228 biological regulation Effects 0.000 description 5
- 230000001105 regulatory effect Effects 0.000 description 4
- 230000015784 hyperosmotic salinity response Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 239000003516 soil conditioner Substances 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 239000013543 active substance Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000004927 clay Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004720 fertilization Effects 0.000 description 1
- 239000001963 growth medium Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000009335 monocropping Methods 0.000 description 1
- 235000015097 nutrients Nutrition 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 239000011148 porous material Substances 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 239000012266 salt solution Substances 0.000 description 1
- 239000013535 sea water Substances 0.000 description 1
- 239000002344 surface layer Substances 0.000 description 1
- 235000013311 vegetables Nutrition 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/06—Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Geometry (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Cultivation Of Plants (AREA)
Abstract
The invention discloses intelligent design and adjustment equipment for the saline-alkali degree of a wetland, which comprises a data acquisition unit, a plant planting land planning and design unit, a plant planting design unit, an adjustment unit and an adjustment object. The data acquisition unit is used for collecting the required soil alkalinity and salinity, the planting area, the transverse and longitudinal alkali discharging blind ditch area, the plant activity, the plant effect and the soil alkalinity and salinity data; the plant planting mode design unit adopts COOT algorithm to carry out land planning strategy design based on land saliency, planting area and transverse and longitudinal alkali discharging blind ditch area; the plant screening design unit adopts GJO algorithm to carry out strategy design of specific plant species mode based on plant effect, plant storage activity and soil pH value; the adjusting unit issues an adjusting instruction based on a design strategy, and an adjusting object comprises adjusting the saline-alkali soil and screening the planted plants. The method can intelligently adjust the saline-alkali degree of the wetland, has good environmental benefit, and has practical significance in ecological restoration.
Description
Technical Field
The invention belongs to the technical field of intelligent regulation of equipment, and particularly relates to intelligent design and regulation equipment for the saline-alkali degree of a wetland.
Background
Under the background of strictly controlling the reclamation construction of the shoal, the advantages of the shoal resources are utilized, the coastal ecological wetland is constructed, and the method is an effective way for scientifically developing the wetland resources and protecting the ecological environment at the present stage. Two defects exist in the research on the adjustment of the saline-alkali degree of the wetland, on one hand, the problems of secondary salinization and hardening of soil can not be fundamentally solved; on the other hand, the survival rate of the plants on the saline-alkali soil is lower.
The existing wetland saline-alkali degree adjusting equipment comprises the following steps:
first kind: the technical mode of saline-alkali soil treatment is changed by the modes of deep ploughing, soil conditioner and soil measurement formula fertilization. According to the mode, the soil conditioner is additionally applied to the soil, so that the content of surface active substances in the soil is increased, the surface tension of soil clay particles is reduced, soil pores are increased, a granular structure is formed, the soil is loosened, hardening is broken, accumulation of salt on the surface layer of the soil is not facilitated, and a good rhizosphere environment is created for root system growth and development. The microelements can regulate the balance of soil nutrients, improve the stress resistance and continuous cropping resistance of vegetables, and greatly improve the problems of secondary salinization and hardening of soil. The method is an important regulation index for regulating the salt and alkali degree from the fundamental solution of soil secondary salinization and hardening, and the scheme lacks measures for fundamentally solving the soil secondary salinization and hardening.
Second kind: salt solutions with different concentrations are applied to the culture medium and plant leaves to research the salt tolerance of root systems and the leaves, the coastal elevation and the sea distance of a restoration position and the influence conditions of sea water and sea waves are comprehensively considered in vegetation restoration practice, and proper plant varieties are determined, but different plants have differences in tolerance mechanisms to salt stress. The vegetation survival rate on the wetland is also an important regulation index for regulating the salt and alkali degree, and the scheme lacks specific measures for monitoring the vegetation survival rate of the wetland and improving the vegetation survival rate.
The problem in the scheme is that the problems of secondary salinization and hardening of soil can not be fundamentally solved, the survival rate of wetland vegetation can not be monitored, and the survival rate of the vegetation can not be improved. The first scheme changes the technical mode of saline-alkali soil treatment to improve the secondary salinization and hardening of the soil, and the problems of the secondary salinization and the hardening of the soil can not be fundamentally solved. The second scheme determines proper plant varieties by researching the salt tolerance of plant root systems and leaves, does not monitor the survival rate of wetland vegetation, and does not take specific measures to improve the survival rate of vegetation.
Therefore, the intelligent wetland saline-alkali degree adjusting equipment is needed, the problems of secondary salinization and hardening of soil can be fundamentally solved, the wetland vegetation survival rate can be monitored, the vegetation survival rate is improved, good environmental benefits are achieved, and the intelligent wetland saline-alkali degree adjusting equipment has practical significance in ecological restoration.
Disclosure of Invention
The invention aims to: aiming at the problems pointed out in the background art, the invention provides intelligent design and adjustment equipment for the saline-alkali degree of the wetland, which is used for carrying out land planning strategy design by adopting a COOT algorithm based on saline-alkali land area data and saline-alkali data, and carrying out specific plant species strategy design by adopting a GJO algorithm based on plant effect data, plant survival rate data and soil data on the planned land, so that the intelligent design and adjustment equipment for the saline-alkali degree of the wetland can carry out intelligent adjustment, has good environmental benefit and has practical significance in ecological restoration.
The technical scheme is as follows: the invention provides intelligent design and adjustment equipment for the saline-alkali degree of a wetland, which comprises a data acquisition unit A, a data acquisition unit B, a planting method design unit, a plant screening design unit, an adjustment object A and an adjustment object B;
the data acquisition unit A is connected with the planting method design unit; the data acquisition unit B is connected with the planted plant screening design unit; the planting method design unit and the planting plant screening design unit are connected with the adjusting unit; the adjusting unit is connected with the adjusting object A and the adjusting object B;
the data acquisition unit A acquires data of land saliency, planting area and transverse and longitudinal alkali discharging blind ditch area, and the data acquisition unit B acquires data of land saliency, plant activity, each plant effect and soil acidity and alkalinity; the plant effect refers to the effect of a certain plant on improving the soil salinity and alkalinity, the plant effect is preset in a database, the planted plant is identified according to the data acquisition unit B, and the plant effect is subjected to data comparison with the plant effect in the database, so that each plant effect data is obtained;
the planting method design unit utilizes a COOT algorithm to carry out land planning strategy design based on land saliency, planting area and transverse and longitudinal alkali discharging blind ditch area data acquired by the data acquisition unit A, and outputs planting areas of various plants with the lowest land saliency and corresponding transverse and longitudinal alkali discharging blind ditch area arrangement schemes;
the plant screening design unit acquires the land salt alkalinity, plant storage activity, plant effect and soil pH value data of each planting land by utilizing the data acquisition unit B after acquiring the planting areas of various plants with the lowest land salt alkalinity and the corresponding transverse and longitudinal alkali discharging blind ditch area arrangement schemes, and performs specific plant species mode strategy design by utilizing a GJO algorithm to output the most suitable plant species of each land;
the adjusting unit is based on the output of the planting method designing unit, the adjusting object A is utilized to adjust the planting area of various plants with the lowest saline-alkali degree of the reference land and the corresponding transverse and longitudinal alkali-discharging blind ditch area arrangement scheme, the adjusting unit is based on the output of the planted plant screening designing unit, and the adjusting object B is utilized to select the plant types planted in each planting area land under the condition of meeting the saline-alkali degree requirement of the land.
Further, the planting method design unit performs specific operations of land planning strategy design by using COOT algorithm based on land saliency, planting area and transverse and longitudinal alkali discharging blind ditch area data acquired by the data acquisition unit A, wherein the specific operations comprise:
step 1: initializing parameters in a COOT algorithm, initializing a population, and randomly selecting a plurality of group lengths from the population; the population refers to the input land salinization degree, planting area and transverse and longitudinal alkali-discharging blind ditch area;
step 2: calculating a population fitness value, wherein a fitness function aims at reducing the land salinization degree, and a solution with the minimum fitness is taken as a global optimal solution:wherein C is i The salt alkalinity of the land of the ith small block;
step 3: the control parameter A, B for calculating the position update is calculated by the formulas (1), (2).
Wherein L is the current iteration number, iter is the maximum iteration number, A is the control parameter of the algorithm exploration stage, and B is the control parameter of the algorithm development stage;
step 4: calculating a parameter K by the formula (3):
K＝1+(iMODNL) (3)
wherein i is the serial number of the current individual, NL is the number of white crown chickens, and K is the serial number of the chickens corresponding to the individual i;
step 5: solving the population position according to the moving mode of the group length adjusting position, and if the rand is more than 0.5, moving the individual hundred-crown chickens according to a formula (4):
CootPos(i)＝LeaderPos(k)+2·R1·cos(2Rπ)·(LeaderPos(k)-CootPos(i)) (4)
wherein, leaderPos (k) is the k position of the leader chicken, R1 is a random number in [0,1], R is a random number in [ -1,1 ];
step 6: if rand is less than or equal to 0.5 and the hundred crown chickens are not the first individuals of the population, then the average position of the two individuals performs chain motion according to equation (5):
CootPos(i)＝0.5·(CootPos(i-1)+CootPos(i)) (5)
step 7: if rand is less than or equal to 0.5 and the hundred-crown chicken is the first individual in the population, the hundred-crown chicken performs individual random movement according to the formula (6):
CootPos(i)＝CootPos(i)+A·R2·(Q-CootPos(i)) (6)
wherein R2 is a random value in [0,1 ];
step 8: calculating the population fitness value again, and judging whether to update the group length position according to the calculated new fitness value;
step 9: updating the group leader location according to equation (7):
gBest is the position of the optimal individual in the population; r3 and R4 are random numbers in [0,1], and R is a random number in [ -1,1 ];
step 10: comparing all the group length fitness values with the global optimal solution, and updating the global optimal solution according to the fitness value of the current hundred-crown chicken group length;
step 11: and judging whether the maximum iteration times are reached, if so, outputting the current optimal solution, and if not, returning to the step 5.
Further, the plant screening design unit performs policy design of a specific plant species mode by utilizing GJO algorithm, and the specific steps of outputting the most suitable plant species of each land are as follows:
step 1: initializing parameters and populations in an algorithm, wherein the populations refer to collected soil salinity and alkalinity, plant activity, plant effects and soil pH value data of each planting soil;
step 2: calculating a fitness value, wherein a fitness function aims at reducing the salt alkalinity of the land, an individual with the greatest fitness is taken as a male jackal wolf, and a second largest individual is taken as a female jackal wolf:
wherein VCR is vegetation coverage, aveg is the occupied area of surviving plants, asa is the total area of saline-alkali soil;
step 3: calculating the escape energy of the prey according to formula (8):
E＝E 1 ·E 0 E 0 ＝2·r-1 E 1 ＝c 1 ·(1-(t/T)) (8)
wherein E is 1 Indicating the process of decline of hunting energy, E 0 Representing the initial state of hunting energy, r is [0,1]Random numbers in the range, T is the maximum iteration number; c is a constant, the value is 1.5, and the current iteration times are obtained; linearly decreasing from 1.5 to 0 throughout the iteration;
step 4: calculating the parameter r according to formula (9) 1 ：
r 1 ＝0.05·LF(y)
Wherein μ and v are random numbers in the range of (0, 1); beta is a default constant, and the value is 1.5;
step 5: if |E| is not less than 1, searching for a prey in the exploration stage according to formulas (10), (11) and (12):
Y 1 (t)＝Y M (t)-E·∣Y M (t)-r1·Prey(t)∣ (10)
Y 2 (t)＝Y FM (t)-E·∣Y FM (t)-r1·Prey(t)∣ (11)
wherein t is the current iteration number; prey (t) is the position of the Prey for the first iteration; y is Y M (t)，Y FM (t) the positions of male and female jackia wolves at the t-th iteration, respectively; y is Y 1 (t)，Y 2 (t) the updated positions of male and female jackwolves corresponding to the prey at the t-th iteration, respectively;
step 6: if |E| < 1, then enter the development phase to enclose and attack the prey according to formulas (12), (13), (14):
Y 1 (t)＝Y M (t)-E·∣r1·Y M (t)-Prey(t)∣ (13)
Y 2 (t)＝Y FM (t)-E·∣r1·Y FM (t)-Prey(t)∣ (14)
step 7: updating the jackal wolf position according to formula (12):
step 8: comparing the fitness values of all jackal wolves, wherein the individual with the optimal fitness value is used as male jackal wolves, the individual with the suboptimal fitness value is used as female jackal wolves, and the positions of corresponding prey are correspondingly updated;
step 9: judging whether the maximum iteration times are reached, if so, outputting the current optimal solution, namely the most suitable plant type of each land, and if not, returning to the step 5.
The beneficial effects are that:
1. according to the invention, according to the soil data collection unit and the plant data collection unit, the needed saline-alkali soil area data, the saline-alkali value data, the plant survival rate, the effect data of each plant and the soil data are collected; the method increases the area of the blind ditches with the alkali discharge and the land vegetation, fundamentally solves the problems of secondary salinization and hardening of soil, improves the utilization rate of the soil, improves the survival rate of plants, has good environmental benefit, and has practical significance in ecological restoration.
2. According to the invention, the COOT algorithm is adopted to carry out land planning on the saline-alkali soil, so that the area of the transverse and longitudinal alkali discharge blind ditches is more reasonable and effective, and meanwhile, the GJO algorithm is adopted to carry out a specific plant species planting mode, so that the vegetation planting area is more specific, and the vegetation survival rate is improved.
Drawings
FIG. 1 is a schematic diagram illustrating the operation of the hardware architecture of the present invention;
FIG. 2 is a flow chart of COOT algorithm employed in the present invention;
FIG. 3 is a flowchart of the GJO algorithm employed in the present invention;
fig. 4 is a plan view of a saline-alkali soil in the present invention.
Detailed Description
The invention is described in further detail below with reference to the accompanying drawings.
The invention provides intelligent design and adjustment equipment for the saline-alkali degree of a wetland, which comprises a data acquisition unit, a planting method design unit, a plant screening design unit, an adjustment object A and an adjustment object B. The data acquisition unit comprises a data acquisition unit A and a data acquisition unit B, wherein the data acquisition unit A is mainly used for collecting soil data, the data acquisition unit B is used for collecting plant data, and the adjusting object A and the adjusting object B are respectively used for adjusting the soil salinity and alkalinity and screening plants.
The data acquisition unit A is connected with the planting method design unit; the data acquisition unit B is connected with the plant screening design unit. The planting method design unit and the planting plant screening design unit are connected with the adjusting unit, the planting plant screening design unit is also connected with the planting method design unit, and the adjusting unit is connected with the adjusting object A and the adjusting object B.
The soil data collection of the data collection unit A is used for collecting the data of land saliency, planting area and transverse and longitudinal alkali discharge blind ditch area, and the plant data collection of the data collection unit B is used for collecting the data of land saliency, plant activity, each plant effect, soil pH value and the like. The plant effect refers to the effect of a certain plant on improving the soil salinity and alkalinity, is preset in a database, identifies the planted plant according to the data acquisition unit B, and performs data comparison with the plant effect in the database so as to acquire the data of each plant effect.
The planting method design unit utilizes COOT algorithm to carry out land planning strategy design based on land saliency, planting area and transverse and longitudinal alkali discharging blind ditch area data acquired by the data acquisition unit A, and outputs planting areas of various plants with the lowest land saliency and corresponding transverse and longitudinal alkali discharging blind ditch area arrangement schemes. After the plant screening design unit obtains the planting areas of various plants with the lowest saline-alkali degree of the land and the corresponding transverse and longitudinal alkali discharging blind ditch area arrangement scheme, the data acquisition unit B is utilized to acquire the land saline-alkali degree, plant storage activity, plant effects and soil pH value data of each planting land, and the GJO algorithm is utilized to carry out specific plant species mode strategy design, so that the most suitable plant species of each land are output.
The adjusting unit issues an adjusting instruction based on the design strategy of the planting method design unit and the planting plant screening design unit, and aims to adjust the salt alkalinity of the wetland and restore the ecological environment while improving the environmental benefit. The adjusting unit is based on the output of the planting method designing unit, adjusts the planting area of various plants with the lowest saline-alkali degree of the reference land and the corresponding transverse and longitudinal alkali-discharging blind ditch area arrangement scheme by utilizing the adjusting object A, and selects the plant types planted in each planting area land by utilizing the adjusting object B under the condition of meeting the saline-alkali degree requirement of the land based on the output of the planted plant screening designing unit.
The adjusting object A is land salinization degree, planning is made to the planting land area and the outer transverse and longitudinal ditch area of planting land based on the adjusting instruction of the adjusting unit, the adjusting object B is the screened plants, and the plants with high survival rate and good effect under the condition that the land salinization degree reaches the standard are screened based on the adjusting instruction of the adjusting unit.
In addition, the regulating object A can also feed back soil data collection of the data acquisition unit A, and the regulating object B feeds back plant data collection of the data acquisition unit B, so that the purpose of verifying that equipment regulation is correct and effective after a certain time passes is achieved.
The planting method design unit reasonably plans the saline-alkali soil area by adopting a COOT optimization algorithm, and the implementation process is as follows:
1) Initializing, initializing parameters in an algorithm and a population, and randomly selecting a plurality of group lengths in the population.
2) Calculating a population fitness value, wherein a fitness function aims at reducing the land salinization degree, and a solution with the minimum fitness is taken as a global optimal solution:
wherein C is i The land salinity of the ith small block.
3) A, B parameters were calculated by formulas (1), (2).
Wherein L is the current iteration number, iter is the maximum iteration number, A is the control parameter of the algorithm exploration stage, and B is the control parameter of the algorithm development stage.
4) Calculating a parameter K by the formula (3):
K＝1+(iMODNL) (3)
wherein i is the serial number of the current individual, NL is the number of white crown chickens, and K is the serial number of the chickens corresponding to the individual i.
5) Solving the population position according to the moving mode of the group length adjusting position, and if the rand is more than 0.5, moving the individual hundred-crown chickens according to a formula (4):
CootPos(i)＝LeaderPos(k)+2·R1·cos(2Rπ)·(LeaderPos(k)-CootPos(i)) (4)
wherein, leader pos (k) is the k position of the leader chicken, R1 is a random number in [0,1], and R is a random number in [ -1,1 ].
6) If rand is less than or equal to 0.5 and the hundred crown chickens are not the first individuals of the population, then the average position of the two individuals performs chain motion according to equation (5):
CootPos(i)＝0.5·(CootPos(i-1)+CootPos(i)) (5)
7) If rand is less than or equal to 0.5 and the hundred-crown chicken is the first individual in the population, the hundred-crown chicken performs individual random movement according to the formula (6):
CootPos(i)＝CootPos(i)+A·R2·(Q-CootPos(i)) (6)
wherein R2 is a random value in [0,1 ].
8) And calculating the population fitness value again, and judging whether to update the group leader position according to the calculated new fitness value.
9) Updating the group leader location according to equation (7):
gBest is the position of the optimal individual in the population; r3 and R4 are random numbers in [0,1], and R is random number in [ -1,1 ].
10 Comparing all the group length fitness values with the global optimal solution, and updating the global optimal solution according to the fitness value of the current hundred-crown chicken group length;
11 Judging whether the maximum iteration times are reached, if so, outputting the current optimal solution, and if not, returning to the step 5).
For the plant screening design unit, after the planting area of various plants with the lowest land saline-alkali degree and the corresponding transverse and longitudinal alkali-discharging blind ditch area arrangement scheme are designed by COOT algorithm, the plant type mode design is carried out by adopting GJO optimization algorithm for each divided land area, and the implementation process is as follows:
step 1: initializing parameters and populations in an initializing algorithm;
step 2: calculating a fitness value, wherein a fitness function aims at reducing the salt alkalinity of the land, an individual with the greatest fitness is taken as a male jackal wolf, and a second largest individual is taken as a female jackal wolf:
wherein VCR is vegetation coverage, aveg is the occupied area of surviving plants, asa is the total area of saline-alkali soil;
step 3: calculating the escape energy of the prey according to formula (8):
E＝E 1 ·E 0 E 0 ＝2·r-1 E 1 ＝c 1 ·(1-(t/T)) (8)
wherein E is 1 Indicating the process of decline of hunting energy, E 0 Representing the initial state of hunting energy, r is [0,1]Random numbers in the range, T is the maximum iteration number; c is a constant, the value is 1.5, and the current iteration times are obtained; linearly decreasing from 1.5 to 0 throughout the iteration;
step 4: calculating the parameter r according to formula (9) 1 ：
r 1 ＝0.05·LF(y)
Wherein μ and v are random numbers in the range of (0, 1); beta is a default constant, and the value is 1.5;
step 5: if |E| is not less than 1, searching for a prey in the exploration stage according to formulas (10), (11) and (12):
Y 1 (t)＝Y M (t)-E·∣Y M (t)-r1·Prey(t)∣ (10)
Y 2 (t)＝Y FM (t)-E·∣Y FM (t)-r1·Prey(t)∣ (11)
wherein t is the current iteration number; prey (t) is the position of the Prey for the first iteration; y is Y M (t)，Y FM (t) the positions of male and female jackia wolves at the t-th iteration, respectively; y is Y 1 (t)，Y 2 (t) the updated positions of male and female jackwolves corresponding to the prey at the t-th iteration, respectively;
step 6: if |E| < 1, then enter the development phase to enclose and attack the prey according to formulas (12), (13), (14):
Y 1 (t)＝Y M (t)-E·∣r1·Y M (t)-Prey(t)∣ (13)
Y 2 (t)＝Y FM (t)-E·∣r1·Y FM (t)-Prey(t)∣ (14)
step 7: the jackal wolf position is updated according to equation (12).
Step 8: comparing the fitness values of all jackal wolves, wherein the individual with the optimal fitness value is used as male jackal wolves, the individual with the suboptimal fitness value is used as female jackal wolves, and the positions of corresponding prey are correspondingly updated;
step 9: judging whether the maximum iteration times are reached, if so, outputting the current optimal solution, namely the most suitable plant type of each land, and if not, returning to the step 5.
As shown in fig. 4, fig. 4 shows that in the embodiment of the invention, various plant planting areas of the saline-alkali soil are divided by using a COOT algorithm based on the saline-alkali soil, the planting area and the area data of the transverse and longitudinal alkali-discharging blind ditches, so that the occupied area for planting plants is reasonably planned, wherein the addition of the transverse and longitudinal alkali-discharging blind ditches can effectively prevent the salt returning phenomenon caused by the rising of underground water so as to prevent water and soil loss. The method is also based on the soil saliency, plant storage activity, plant effects and soil pH value data of each planting land, and utilizes GJO algorithm to screen out plants with high survival rate and good effect under the condition that the soil saliency reaches the standard, and to plan specific planting modes of the plants on the saline-alkali soil.
The foregoing embodiments are merely illustrative of the technical concept and features of the present invention, and are intended to enable those skilled in the art to understand the present invention and to implement the same, not to limit the scope of the present invention. All equivalent changes or modifications made according to the spirit of the present invention should be included in the scope of the present invention.
Claims (1)
1. The intelligent design and adjustment equipment for the saline-alkali degree of the wetland is characterized by comprising a data acquisition unit G, a data acquisition unit H, a planting method design unit, a plant screening design unit, an adjustment object M and an adjustment object N;
the data acquisition unit G is connected with the planting method design unit; the data acquisition unit H is connected with the planted plant screening design unit; the planting method design unit and the planting plant screening design unit are connected with the adjusting unit; the adjusting unit is connected with the adjusting object M and the adjusting object N; the adjusting object M is the land salinization degree, and the adjusting object N is the screened plant;
the data acquisition unit G acquires data of land saliency, planting area and transverse and longitudinal alkali discharging blind ditch area, and the data acquisition unit H acquires data of land saliency, plant activity, each plant effect and soil acidity and alkalinity; the plant effect refers to the effect of a certain plant on improving the soil salinity and alkalinity, the plant effect is preset in a database, the planted plant is identified according to a data acquisition unit H, and the plant effect is subjected to data comparison with the plant effect in the database, so that each plant effect data is obtained;
the planting method design unit utilizes a COOT algorithm to carry out land planning strategy design based on land saliency, planting area and transverse and longitudinal alkali discharging blind ditch area data acquired by the data acquisition unit G, and outputs planting areas of various plants with the lowest land saliency and corresponding transverse and longitudinal alkali discharging blind ditch area arrangement schemes;
the plant screening design unit acquires the land salt alkalinity, plant storage activity, plant effect and soil pH value data of each planting land by utilizing the data acquisition unit H after acquiring the planting areas of various plants with the lowest land salt alkalinity and the corresponding transverse and longitudinal alkali discharging blind ditch area arrangement schemes, and performs specific plant species mode strategy design by utilizing a GJO algorithm to output the most suitable plant species of each land;
the adjusting unit is used for adjusting the planting area of each plant with the lowest saline-alkali degree of the reference land and the corresponding transverse and longitudinal alkali-discharging blind ditch area arrangement scheme based on the output of the planting method design unit, and is used for selecting the plant type planted in each planting area land under the condition of meeting the saline-alkali degree requirement of the land according to the output of the planted plant screening design unit;
the planting method design unit utilizes COOT algorithm to carry out specific operation of land planning strategy design based on land saliency, planting area and transverse and longitudinal alkali discharging blind ditch area data acquired by the data acquisition unit G, wherein the specific operation comprises the following steps:
step 1.1: initializing parameters in a COOT algorithm, initializing a population, and randomly selecting a plurality of leader chickens in the population; the population refers to the input land salinization degree, planting area and transverse and longitudinal alkali-discharging blind ditch area;
step 1.2: calculating a population fitness value, wherein a fitness function aims at reducing the land salinization degree, and a solution with the minimum fitness is taken as a global optimal solution:wherein C is i The salt alkalinity of the land of the ith small block;
step 1.3: the control parameter A, B for the location update is calculated by equations (1), (2):
wherein L is the current iteration number, iter is the maximum iteration number, A is the control parameter of the algorithm exploration stage, and B is the control parameter of the algorithm development stage;
step 1.4: calculating a parameter K by the formula (3):
K＝1+(i MOD NL) (3)
wherein i is the serial number of the current individual, NL is the number of white crown chickens, and K is the serial number of the chickens corresponding to the individual i;
step 1.5: solving the population position according to the movement mode of the adjustment position of the leader chicken, and if the rand is more than 0.5, moving the white crown chicken individuals according to a formula (4):
CootPos(i)＝LeaderPos(k)+2·R1·cos(2Rπ)·(LeaderPos(k)-CootPos(i)) (4)
wherein, leaderPos (k) is the k position of the leader chicken, R1 is a random number in [0,1], R is a random number in [ -1,1 ];
step 1.6: if rand is less than or equal to 0.5 and the white crown chicken is not the first individual of the population, then the average position of the two individuals performs chain motion according to equation (5):
CootPos(i)＝0.5·(CootPos(i-1)+CootPos(i)) (5)
step 1.7: if rand is less than or equal to 0.5 and the white crown chicken is the first individual in the population, the white crown chicken randomly moves the individuals according to formula (6):
CootPos(i)＝CootPos(i)+A·R2·(Q-CootPos(i)) (6)
wherein R2 is a random value in [0,1 ];
step 1.8: calculating the population fitness value again, and judging whether to update the position of the leader chicken according to the calculated new fitness value;
step 1.9: updating the leader chicken position according to formula (7):
gBest is the position of the optimal individual in the population; r3 and R4 are random numbers in [0,1], and R is a random number in [ -1,1 ];
step 1.10: comparing all the adaptation values of the leader chickens with the global optimal solution, and updating the global optimal solution according to the adaptation values of the current leader chickens;
step 1.11: judging whether the maximum iteration times are reached, if so, outputting a current optimal solution, and if not, returning to the step 1.5;
the plant screening design unit utilizes GJO algorithm to carry out strategy design of specific plant species mode, and the specific steps of outputting the most suitable plant species of each land are as follows:
step 2.1: initializing parameters and populations in an algorithm, wherein the populations refer to collected soil salinity and alkalinity, plant activity, plant effects and soil pH value data of each planting soil;
step 2.2: calculating a fitness value, wherein a fitness function aims at reducing the salt alkalinity of the land, an individual with the greatest fitness is taken as a male jackal wolf, and a second largest individual is taken as a female jackal wolf:
wherein VCR is vegetation coverage, aveg is the occupied area of surviving plants, asa is the total area of saline-alkali soil;
step 2.3: calculating the escape energy of the prey according to formula (8):
wherein E is 1 Indicating the process of decline of hunting energy, E 0 Representing the initial state of hunting energy, r is [0,1]Random numbers in the range, T is the maximum iteration number; c 1 The value is 1.5, which is a constant and is the current iteration number; linearly decreasing from 1.5 to 0 throughout the iteration;
step 2.4: calculating the parameter r according to formula (9) 1 ：
r 1 ＝0.05·LF(y)
Wherein μ and v are random numbers in the range of (0, 1); beta is a default constant, and the value is 1.5;
step 2.5: if |E| is not less than 1, searching for a prey in the exploration stage according to formulas (10), (11) and (12):
Y 1 (t)＝Y M (t)-E·∣Y M (t)-r 1 ·Prey(t)∣ (10)
Y 2 (t)＝Y FM (t)-E·∣Y FM (t)-r 1 ·Prey(t)∣ (11)
wherein t is the current iteration number; prey (t) is the position of the Prey for the first iteration; y is Y M (t)，Y FM (t) the positions of male and female jackia wolves at the t-th iteration, respectively; y is Y 1 (t)，Y 2 (t) the updated positions of male and female jackwolves corresponding to the prey at the t-th iteration, respectively;
step 2.6: if |E| < 1, then enter the development phase to enclose and attack the prey according to formulas (12), (13), (14):
Y 1 (t)＝Y M (t)-E·∣r 1 ·Y M (t)-Prey(t)∣ (13)
Y 2 (t)＝Y FM (t)-E·∣r 1 ·Y FM (t)-Prey(t)∣ (14)
step 2.7: updating the jackal wolf position according to the formula (12);
step 2.8: comparing the fitness values of all jackal wolves, wherein the individual with the optimal fitness value is used as male jackal wolves, the individual with the suboptimal fitness value is used as female jackal wolves, and the positions of corresponding prey are correspondingly updated;
step 2.9: judging whether the maximum iteration times are reached, if so, outputting the current optimal solution, namely the most suitable plant type of each land, and if not, returning to the step 2.5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310596473.1A CN116644575B (en) | 2023-05-25 | 2023-05-25 | Intelligent design adjusting equipment for saline-alkali degree of wetland |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310596473.1A CN116644575B (en) | 2023-05-25 | 2023-05-25 | Intelligent design adjusting equipment for saline-alkali degree of wetland |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116644575A CN116644575A (en) | 2023-08-25 |
| CN116644575B true CN116644575B (en) | 2024-03-26 |
Family
ID=87622462
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310596473.1A Active CN116644575B (en) | 2023-05-25 | 2023-05-25 | Intelligent design adjusting equipment for saline-alkali degree of wetland |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116644575B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106444378A (en) * | 2016-10-10 | 2017-02-22 | 重庆科技学院 | Plant culture method and system based on IoT (Internet of things) big data analysis |
| CN109005216A (en) * | 2018-07-04 | 2018-12-14 | 青岛全域盐碱地稻作改良研究院有限公司 | Four-dimensional improvement system and its application based on Internet of Things and intelligence sensor |
| CN109906833A (en) * | 2019-02-27 | 2019-06-21 | 深圳集智云创科技开发有限公司 | A kind of greenhouse intelligent management system based on big data |
| CN110096752A (en) * | 2019-04-03 | 2019-08-06 | 沈阳环境科学研究院 | Wetland plant configuration method based on optimal method |
| CN111724271A (en) * | 2020-04-27 | 2020-09-29 | 齐实 | High-salinity and alkalinity area greening plant growing method based on growth nutrition space |
| CN112099557A (en) * | 2020-09-24 | 2020-12-18 | 苏州七采蜂数据应用有限公司 | Internet-based household plant planting method and system |
| CN112189550A (en) * | 2020-09-30 | 2021-01-08 | 中原工学院 | Intelligent plant cultivation system based on data driving and use method thereof |
| CN113841595A (en) * | 2021-11-09 | 2021-12-28 | 湘潭大学 | Energy-saving intelligent accurate irrigation system based on combination of soil humidity and depth |
| EP3979193A1 (en) * | 2020-10-02 | 2022-04-06 | Sensilize Ltd | System for evaluating and monitoring plants |
| CN114863271A (en) * | 2022-04-18 | 2022-08-05 | 中国矿业大学(北京) | Mining area ecological environment remote sensing method considering rock-soil difference and plant diversity |
| CN115062958A (en) * | 2022-06-14 | 2022-09-16 | 江苏百绿园林集团有限公司 | Intelligent garden planning scheme adjusting system and method based on virtual information |
| WO2022257243A1 (en) * | 2021-06-07 | 2022-12-15 | 西安邮电大学 | Water quality early-warning method and system |
| CN115752666A (en) * | 2022-10-28 | 2023-03-07 | 昆明理工大学 | Tobacco leaf dynamic weighing method of multi-strategy wolf pack algorithm ELM |
| CN115778372A (en) * | 2022-12-13 | 2023-03-14 | 杭州电子科技大学 | Knee joint angle estimation method based on surface electromyogram signals |
| CN115858534A (en) * | 2022-12-16 | 2023-03-28 | 西南交通大学 | Service value chain service data feature selection method based on jackal optimization algorithm |
-
2023
- 2023-05-25 CN CN202310596473.1A patent/CN116644575B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106444378A (en) * | 2016-10-10 | 2017-02-22 | 重庆科技学院 | Plant culture method and system based on IoT (Internet of things) big data analysis |
| CN109005216A (en) * | 2018-07-04 | 2018-12-14 | 青岛全域盐碱地稻作改良研究院有限公司 | Four-dimensional improvement system and its application based on Internet of Things and intelligence sensor |
| CN109906833A (en) * | 2019-02-27 | 2019-06-21 | 深圳集智云创科技开发有限公司 | A kind of greenhouse intelligent management system based on big data |
| CN110096752A (en) * | 2019-04-03 | 2019-08-06 | 沈阳环境科学研究院 | Wetland plant configuration method based on optimal method |
| CN111724271A (en) * | 2020-04-27 | 2020-09-29 | 齐实 | High-salinity and alkalinity area greening plant growing method based on growth nutrition space |
| CN112099557A (en) * | 2020-09-24 | 2020-12-18 | 苏州七采蜂数据应用有限公司 | Internet-based household plant planting method and system |
| CN112189550A (en) * | 2020-09-30 | 2021-01-08 | 中原工学院 | Intelligent plant cultivation system based on data driving and use method thereof |
| EP3979193A1 (en) * | 2020-10-02 | 2022-04-06 | Sensilize Ltd | System for evaluating and monitoring plants |
| WO2022257243A1 (en) * | 2021-06-07 | 2022-12-15 | 西安邮电大学 | Water quality early-warning method and system |
| CN113841595A (en) * | 2021-11-09 | 2021-12-28 | 湘潭大学 | Energy-saving intelligent accurate irrigation system based on combination of soil humidity and depth |
| CN114863271A (en) * | 2022-04-18 | 2022-08-05 | 中国矿业大学(北京) | Mining area ecological environment remote sensing method considering rock-soil difference and plant diversity |
| CN115062958A (en) * | 2022-06-14 | 2022-09-16 | 江苏百绿园林集团有限公司 | Intelligent garden planning scheme adjusting system and method based on virtual information |
| CN115752666A (en) * | 2022-10-28 | 2023-03-07 | 昆明理工大学 | Tobacco leaf dynamic weighing method of multi-strategy wolf pack algorithm ELM |
| CN115778372A (en) * | 2022-12-13 | 2023-03-14 | 杭州电子科技大学 | Knee joint angle estimation method based on surface electromyogram signals |
| CN115858534A (en) * | 2022-12-16 | 2023-03-28 | 西南交通大学 | Service value chain service data feature selection method based on jackal optimization algorithm |
Non-Patent Citations (4)
| Title |
|---|
| A new optimization method based on COOT bird natural life model;Iraj Naruei , Farshid Keynia ；;Expert Systems with Applications;第183卷;pp1-25 * |
| Golden jackal optimization: A novel nature-inspired optimizer for engineering applications;Nitish Chopra , Muhammad Mohsin Ansari；;Expert Systems with Applications;第198卷;pp1-15 * |
| M地区盐碱地综合改良项目管理研究与实施;张奇;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;第1-75页 * |
| 新疆阿拉尔地区土壤盐渍化的发育规律及防治技术;余宝宝;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;第1-89页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116644575A (en) | 2023-08-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lv et al. | Adjusting sowing date and cultivar shift improve maize adaption to climate change in China | |
| CN109258417B (en) | Automatic irrigation method | |
| Stewart et al. | A management system for the conjunctive use of rainfall and limited irrigation of graded furrows | |
| CN116644575B (en) | Intelligent design adjusting equipment for saline-alkali degree of wetland | |
| Shakir et al. | Canal water management: Case study of upper Chenab Canal in Pakistan | |
| CN112183966B (en) | Ecological stability-oriented surface water and underground water combined regulation and control method | |
| Chikowo et al. | Aggregating field-scale knowledge into farm-scale models of African smallholder systems: summary functions to simulate crop production using APSIM | |
| CN108966722A (en) | A method of apply four-dimensional improved method to carry out alkaline land improving | |
| Hossain et al. | Differential growth in rice production in eastern India: Agroecological and socio-economic constraints | |
| CN116941400A (en) | Fertilization control system based on thing networking | |
| CN114757405B (en) | Water resource balance optimization configuration method for irrigation area | |
| CN114902936B (en) | Intelligent alkali discharging layer structure and system based on sensor sensing technology | |
| Rao et al. | Irrigation scheduling of rice with a crop growth simulation model | |
| Khasanov et al. | PORTABLE DRIP IRRIGATION SYSTEM | |
| Henriksen et al. | Inventory of Norwegian grain production: Data from three average-and three high yielding cereal farms located in the major grain producing areas of Norway | |
| Akbar et al. | IMPACT OF PERMANENT BED RENOVATION PRACTICE ON IRRIGATION PERFORMANCE AND PRODUCTIVITY. | |
| CN110915597B (en) | Flue-cured tobacco efficient irrigation method based on narrow-plant wide-row cultivation | |
| Rahman et al. | Evaluation of CERES-Wheat model for wastewater irrigation and fertilizer interactions in wheat cultivation | |
| Shen et al. | Integrated paths to sustainable groundwater management | |
| Mosharafian et al. | A Supplemental Lighting Control Approach in Controlled Environment Agriculture to Reduce Peak Power Consumption | |
| CN118261739A (en) | Intelligent optimization management system and method for pasture planting in saline-alkali soil | |
| Foomani et al. | The Impact of Different Intermittent Irrigation Management and Planting Distances on Yield and Yield Components of Rice Plant in Northern Iran | |
| Dadhich et al. | Irrigation Scheduling under Deficit Irrigation | |
| CN118318663A (en) | Method for three-dimensionally controlling desertification based on plant system | |
| Rui et al. | Long‐term crop yield benefits of subsurface drainage on poorly drained soils |
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 |