CN113110061B - Intelligent irrigation fuzzy control method and system based on improved particle swarm optimization - Google Patents
Intelligent irrigation fuzzy control method and system based on improved particle swarm optimization Download PDFInfo
- Publication number
- CN113110061B CN113110061B CN202110483088.7A CN202110483088A CN113110061B CN 113110061 B CN113110061 B CN 113110061B CN 202110483088 A CN202110483088 A CN 202110483088A CN 113110061 B CN113110061 B CN 113110061B
- Authority
- CN
- China
- Prior art keywords
- particle
- avg
- fuzzy controller
- water content
- particle swarm
- 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
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses an intelligent irrigation fuzzy control method and system based on improved particle swarm optimization, wherein the method comprises the following steps: setting the optimal water content of the soil, and acquiring the actual water content of the soil in the area to be irrigated through the monitoring nodes; controlling to obtain parameter adjustment quantity of the fuzzy controller according to the difference value between the optimal water content and the actual water content and the error change rate of the difference value as the input of the fuzzy controller; optimizing quantization factors and scale factors in the fuzzy controller by adopting an improved particle swarm optimization algorithm based on the parameter adjustment quantity; applying the optimized quantization factor and scale factor to the fuzzy controller to realize intelligent irrigation; the problem of large time lag and overshoot caused by the adoption of the traditional irrigation technology is avoided, the requirement of saving water resources is met, and the accuracy of irrigation control is improved. In addition, the improved particle swarm optimization optimizes the quantization factor and the scale factor in the fuzzy controller, and effectively improves the optimization precision and the convergence speed of the algorithm.
Description
Technical Field
The invention belongs to the technical field of intelligent irrigation optimization, and relates to an intelligent irrigation fuzzy control method and system based on improved particle swarm optimization.
Background
As a population and an agricultural kingdom, China solves the problem of the saturation of the population of the world 1/5 by means of 7 percent of farmland and 6 percent of available water resources in the world, and contributes outstanding force to the global agricultural production. Agricultural irrigation water is the largest fresh water consumption in the world, accounts for more than 70% of the global water consumption, and the utilization rate of the irrigation water is only 43%. Since 2016, Chinese litchi planting area exceeds 860 million mu, annual output is more than 200 million tons, and the total value of world litchi production is about 62.85%. However, the litchi orchard still adopts the traditional irrigation technology, has the problems of large time lag and overshoot, and causes serious waste of water resources. Along with the development of wisdom agriculture, urgent need develop a litchi garden intelligence irrigation system, make things convenient for the fruit grower to carry out real-time appropriate amount of meticulous management, and then improve water resource utilization ratio and economic benefits.
Disclosure of Invention
In view of the above problems, the invention provides an intelligent irrigation fuzzy control method and system based on improved particle swarm optimization, which at least solves some of the above technical problems, and the method can solve the problem that fuzzy control parameters of an intelligent irrigation system for a litchi orchard are difficult to determine by adopting a traditional empirical method.
In a first aspect, an embodiment of the present invention provides an intelligent irrigation fuzzy control method based on improved particle swarm optimization, including:
setting the optimal water content of the soil, and acquiring the actual water content of the soil in the area to be irrigated through the monitoring nodes;
controlling to obtain a parameter adjustment quantity of the fuzzy controller according to the difference value between the optimal water content and the actual water content and the error change rate of the difference value as the input of the fuzzy controller;
optimizing quantization factors and scale factors in the fuzzy controller by adopting an improved particle swarm optimization based on the parameter adjustment quantity;
and applying the optimized quantization factor and scale factor to the fuzzy controller to realize intelligent irrigation.
In one embodiment, optimizing the quantization factor and the scale factor in the fuzzy controller by using an improved particle swarm optimization based on the parameter adjustment amount comprises:
initializing a particle swarm based on irrigation quantity, and randomly generating particle positions and speeds;
assigning the position and the speed of each particle to a quantization factor and a scale factor in the fuzzy controller in sequence; measuring the individual performance by the integral of the product of time and the absolute value of the error, and constructing an objective function; adjusting the inertia weight by adopting a self-adaptive mode;
selecting SA;
when the termination condition is met, terminating iteration and outputting an optimal particle fitness value; and updates the particle position and velocity at the next time.
In one embodiment, the adaptive adjustment of the inertia weight includes:
particle p of the kth iterationiHas a fitness of fiThe current optimum fitness value is fmCalculating the average fitness of the whole population as favg(ii) a Will be better than favgThe particles were then averaged to give f'avgThe reference index for precocity is Δ ═ fm-f’avg|；
Calculating the inertia weight according to the following formula:
(1)fiis better than f'avgWhen it comes, the particles are better particles, and a smaller w:
(2)fiis superior to favgBut is inferior to f'avgWhen the particle is general, keeping the inertia weight w as a fixed value;
(3)fisecond to favgWhen the particle is poor, the global optimization is increased by adopting the following formula
Adjusting:
wherein w represents an inertia weight; k is a radical of1Representing the last iteration; k is a radical of2The next iteration is indicated.
In one embodiment, updating the particle position and velocity at the next time comprises:
the particle position and velocity are updated according to:
vij(k+1)＝w·vij(k)+c1r1(k)[pij(k)-xij(k)]+c2r2(k)[p′ij(k)-xij(k)]
xij(k+1)＝xij(k)+vij(k+1)
in the formula: c. C1、c2Is a learning factor, r1、r2Is [0, 1 ]]A uniform random number within the range, k being a certain iteration, i being a dimension, i being 1, 2.. D, D being a positive integer, representing a spatial dimension; j is the index of the current particle; w is an inertia weight; p is a radical ofijFor individual extrema, from a number of individual extrema pijOne of them is recorded as p'ij；xijIs the position of the jth particle in i-dimensional space, vijVelocity, v, of the j-th particle in i-dimensional spaceij∈[-vmax，vmax]，vmaxIs the boundary velocity constant.
In one embodiment, SA selection is performed, including:
the energy of the system changes from the previous state to the next state, and the corresponding energy is changed from E1Change to E2The probability of (d) is expressed as:
pijis relative to pgPoor solution, resulting in p at distanceijTo pgProbability of transition of
pgFor global extrema, the probability of being selected is calculated as:
in the formula:
is pijThe absolute position of the particles is determined,
for the absolute position of the optimal particle, t is a parameter of simulated annealing, and the larger t is, the more likely a point closest to the optimal point is to be selected; n is the total number of particles of the PSO model, and j is the index of the current particle.
In a second aspect, an embodiment of the present invention further provides an intelligent irrigation fuzzy control system optimized based on an improved particle swarm optimization, including:
the setting and obtaining module is used for setting the optimal water content of the soil and obtaining the actual water content of the soil in the area to be irrigated through the monitoring nodes; controlling to obtain a parameter adjustment quantity of the fuzzy controller according to the difference value between the optimal water content and the actual water content and the error change rate of the difference value as the input of the fuzzy controller;
the optimization module is used for optimizing the quantization factor and the scale factor in the fuzzy controller by adopting an improved particle swarm algorithm based on the parameter adjustment quantity;
and the application module is used for applying the optimized quantization factor and the optimized scale factor to the fuzzy controller to realize intelligent irrigation.
Compared with the prior art, the invention discloses and provides an intelligent irrigation fuzzy control method based on improved particle swarm optimization, which has the following advantages:
according to the invention, the self-adaptive simulated annealing particle swarm hybrid algorithm is applied to the optimization of the scale factor and the quantization factor of the intelligent irrigation fuzzy controller, so that the problems of large time lag and overshoot caused by the adoption of the traditional irrigation technology are avoided, and the serious waste of water resources is also avoided; the requirement of saving water resources is met, and the precision of irrigation control is improved.
The improved particle swarm algorithm optimizes the quantization factor and the scale factor in the fuzzy controller, and effectively improves the optimization precision and the convergence speed of the algorithm.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow chart of an intelligent irrigation fuzzy control method based on improved particle swarm optimization according to an embodiment of the present invention;
FIG. 2 is a flowchart of optimizing quantization factors and scale factors in the fuzzy controller by using an improved particle swarm optimization according to an embodiment of the present invention;
FIG. 3 is a flow chart of the APSO algorithm;
FIG. 4 is a flow chart of the AHSAPSO algorithm;
FIG. 5 is a Griewank function iterative evolutionary graph;
FIG. 6 is an iterative evolutionary graph of the Rastrigin function;
FIG. 7 is an Ackley function iterative evolutionary graph;
FIG. 8 is a diagram of a fuzzy control system for intelligent irrigation of a litchi garden;
FIG. 9 is a graph of comparison of fuzzy control simulation after AHSAPSO optimization;
fig. 10 is a block diagram of an intelligent irrigation fuzzy control system optimized based on an improved particle swarm optimization according to an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Referring to the attached drawing 1, the embodiment of the invention discloses an intelligent irrigation fuzzy control method based on improved particle swarm optimization, which specifically comprises the following steps:
s100, setting the optimal water content of the soil, and acquiring the actual water content of the soil in the area to be irrigated through the monitoring nodes;
s200, controlling to obtain a parameter adjustment quantity of the fuzzy controller according to the difference value between the optimal water content and the actual water content and the error change rate of the difference value as the input of the fuzzy controller;
s300, optimizing a quantization factor and a scale factor in the fuzzy controller by adopting an improved particle swarm optimization based on the parameter adjustment amount; quantization factor k, in particular for errors in a fuzzy controllereQuantization factor k of error change rateecAnd a control quantity scale factor ku。
S400, applying the optimized quantization factor and the optimized scale factor to the fuzzy controller to realize intelligent irrigation.
In the embodiment of the invention, the adaptive simulated annealing particle swarm hybrid algorithm is applied to the optimization of the scale factor and the quantization factor of the intelligent irrigation fuzzy controller, so that the problems of large time lag and overshoot caused by the adoption of the traditional irrigation technology are avoided, and the serious waste of water resources is also avoided; the requirement of saving water resources is met, and the precision of irrigation control is improved. In addition, the improved particle swarm optimization optimizes the quantization factor and the scale factor in the fuzzy controller, and effectively improves the optimization precision and the convergence speed of the algorithm.
In one embodiment, referring to fig. 2, in the step S300, optimizing the quantization factor and the scale factor in the fuzzy controller by using an improved particle swarm optimization method includes:
s3001, initializing a particle swarm based on irrigation quantity, and randomly generating particle positions and speeds;
s3002, assigning each particle position and velocity to quantization factor k of error in the fuzzy controller in sequenceeQuantization factor k of error change rateecAnd a control quantity scale factor ku(ii) a Measuring the individual performance by the integral of the product of time and the absolute value of the error, and constructing an objective function; adjusting the inertia weight by adopting a self-adaptive mode;
s3003, selecting SA;
s3004, when the termination condition is met, terminating the iteration and outputting an optimal particle fitness value; and updates the particle position and velocity at the next time. Namely: and after a certain number of iterations, terminating the iteration when the optimal solution of the group is not updated. And after the particle swarm optimization is iterated once, selecting the corrected optimal individual from all the individuals by using a simulated annealing algorithm as the optimal reference position of the next iteration.
All the above steps are described in detail below by way of example.
1. Initializing a particle swarm and randomly generating the position and the speed of particles;
x: initializing a population position; n: the population scale; d: the dimension of the particle; c. C1、c2: a learning factor; m: the number of iterations; w: and (4) inertia weight.
2. Self-adaptive adjustment of inertia weight
Particle p of the kth iterationiThe fitness of the current optimal fitness value is fmCalculating the average fitness of the whole population as favg. Then get the advantage over favgThe particles were then averaged to give f'avgThe reference index for precocity is Δ ═ fm-f’avgL. Smaller Δ indicates a population tending to converge early. And according to different particle fitness, adopting different adjustment strategies for the inertia weight. when w is large, the particle has the ability to jump out of local optimum; when w is small, the algorithm speed can be improved by local rapid convergence.
Referring to fig. 3, the inertia weights are adaptively adjusted according to the following formula:
(1)fiis better than f'avgWhen the particle is a preferable particle, a smaller w:
(2)fiis superior to favgBut is inferior to f'avgWhen the particle is described, the inertia weight value w is generally kept constant, for example, 0.65;
(3)fisecond to favgWhen the particle is relatively poor, the global optimization degree should be increased, and the following method is adopted for adjustment:
wherein w represents an inertia weight; k is a radical of1Representing the last iteration; k is a radical of2The next iteration is indicated.
3. Updating particle position and velocity
The particle position and velocity are updated according to:
vij(k+1)＝w·vij(k)+c1r1(k)[pij(k)-xij(k)]+c2r2(k)[p′ij(k)-xij(k)]
xij(k+1)＝xij(k)+vij(k+1)
in the formula: c. C1、c2Called the learning factor, r1、r2Is [0, 1 ]]A uniform random number within the range, k being a certain iteration, i being a dimension, i being 1, 2.. D, D being a positive integer, representing a spatial dimension; j is the index of the current particle; w is an inertia weight; p is a radical ofijIs an individual extremum, from a number of individual extremums pijOne of them is recorded as p'ij；xijIs the position of the particle, vijIs the velocity, v, of the particleij∈[-vmax，vmax]，vmaxIs the boundary velocity constant. Namely: and randomly initializing a population in a D-dimensional solution space, and performing iterative optimization on each particle in the solution space according to the individual extremum and the global extremum.
SA selection
Referring to fig. 4, the algorithm idea of SA selection is: the energy of the system changes from the previous state to the next state, and the corresponding energy is changed from E1Change to E2The probability of (d) is expressed as:
the better the performance is considered, pijThere is theoretically a relatively high probability of selection, according to the meaning of the Metropolis mechanism, pijIs relative to pgBad special solutions, then p can be obtained at this distanceijTo p is pgProbability of transition of
pgFor global extrema, the probability of being selected can be calculated as follows:
in the formula:
is pijThe absolute position of the particles is determined,
for the absolute position of the optimal particle, t is a parameter of simulated annealing, and the larger t is, the more likely a point closest to the optimal point is to be selected; n is the total number of particles of the PSO model, and j is the index of the current particle.
5. Algorithm feasibility and effectiveness judgment
The following global optimal solutions for the Griewank function, the rasstrigin function, and the Ackley function are used, see table 1.
TABLE 1 classical test function
6. Algorithm progressivity verification
The three test functions are operated 50 times respectively by using a standard particle swarm algorithm PSO, an adaptive particle swarm algorithm APSO (figure 3) and an adaptive simulated annealing particle swarm hybrid algorithm AHSAPSO (figure 4), so that an adaptability value curve obtained by averaging global optimal values of the functions optimized by the three algorithms and iterating 200 times is obtained, and the adaptability value curve is specifically shown in table 2 and figures 5-7.
TABLE 2 comparison of the optimal values of the three functions
| PSO | APSO | AHSAPSO | |
| Griewank | 0.1328 | 1.4810×10-6 | 1.6333×10-4 |
| Rastrigin | 18.9042 | 8.9573 | 0.9950 |
| Ackley | 1.6462 | 1.1552 | 0.0026 |
Table 3 parameter settings for three optimization algorithms:
the AHSAPSO algorithm provided by the invention has good optimization effect on three classical multi-peak complex functions after 200 iterations. The standard PSO algorithm and the self-adaptive APSO algorithm are trapped in local maxima early, local optima are difficult to jump out, calculation tends to pause gradually, and a more accurate global optimum solution cannot be found effectively. The AHSAPSO algorithm is better than the other two algorithms in combination, and the Griewank function is not different from the minimum value of the three algorithms even though the function does not reach the minimum value.
7. Intelligent irrigation fuzzy control system
Referring to fig. 8, the intelligent irrigation fuzzy control system mainly comprises four parts, namely fuzzification, fuzzy reasoning, a knowledge base and clarification, the system selects a difference e between the corresponding optimal soil water content and the actually measured soil water content and an error change rate ec thereof as input of a two-dimensional Mamdani type fuzzy controller, the output quantity of the two-dimensional Mamdani type fuzzy controller is irrigation quantity u, and an irrigation command is generated through fuzzy decision to perform irrigation.
8. Establishing fuzzy control system optimization simulation model
The particle swarm algorithm is characterized in that next search information is determined according to an objective function value of a requirement problem, and the objective function is embodied through individual fitness. In order to ensure that the fuzzy control system can have no overshoot and high stability, the invention adopts ITAE criterion (integral of product of time and absolute value of error) to measure individual performance, and can comprehensively reflect performance indexes of quick response, transition process, overshoot and the like of the system. The objective function is as follows:
in the formula: t is a certain moment, T is the time of the whole process, | e (T) | is the absolute value of the error of the corresponding optimal soil moisture content and the actually measured soil moisture content.
Assuming that the irrigation system model composed of the actuating mechanism and the controlled object is a typical second-order transfer function, the mathematical expression is as follows:
the purpose of the transfer function is to translate into a matlab acceptable form; and (4) building a fuzzy control system optimization simulation model by using a Simulink tool box in Matlab.
9. Algorithm optimization parameter flow
As shown in the attached figure 2, the difference e between the corresponding optimal soil moisture content and the actually measured soil moisture content and the error change rate ec thereof are selected as the input of the two-dimensional Mamdani type fuzzy controller, and the output quantity is the irrigation quantity u. Randomly initializing the positions of the particles, transmitting the initialized values to a Simulink model for calculating the fitness of the particles, if the termination condition is met, finishing the calculation, otherwise, updating the positions of the particles by using an improved particle swarm algorithm, and calculating the fitness by using the Simulink model again, and repeating the steps until the exit condition is met. Namely: optimizing quantization factors and scale factors in the fuzzy controller by adopting an improved particle swarm optimization; quantization factor k of the optimized erroreQuantization factor k of error change rateecAnd a control quantity scale factor kuThe method is applied to a fuzzy controller to realize intelligent irrigation.
10. Simulation experiment
The adaptive simulated annealing particle swarm hybrid algorithm is applied to the optimization of the proportional factor and the quantization factor of the intelligent irrigation fuzzy controller of the litchi orchard, the optimal quantization proportional factor parameter is obtained through the optimization of a target function and is brought into the fuzzy controller to carry out a simulation experiment, and the simulation result is shown in the attached figure 9.
The standard particle swarm algorithm is improved, the fitness mean value is used for adaptively adjusting the inertia weight, meanwhile, the simulated annealing algorithm is mixed to form the adaptive simulated annealing particle swarm hybrid algorithm, and the classical test function test proves that the optimization accuracy and the convergence rate of the algorithm are effectively improved. Finally, the adaptive simulated annealing particle swarm hybrid algorithm is applied to optimization of the proportional factor and the quantization factor of the intelligent irrigation fuzzy controller for the litchi orchard, simulation and experiments show that 20s is needed when fuzzy control enters a steady state, about 3.8% of overshoot is obtained, only 12s is needed when the fuzzy control after AHSAPSO optimization reaches the steady state, the overshoot is about 0.9%, the fuzzy control after the AHSAPSO algorithm optimization has shorter overshoot time, more excellent transient performance and higher control precision. After optimization, the intelligent irrigation fuzzy control system controls the average value of the water content of the litchi garden soil to be 16.43 percent, is closer to the optimal water content of the litchi garden soil preset by the system to be 16 percent, can quickly adjust the water content of the soil to be maintained at the optimal level, and has higher control precision, better robustness and practicability.
Aiming at the problem that fuzzy control parameters of an intelligent orchard irrigation system are difficult to determine by adopting a traditional empirical method, the intelligent irrigation fuzzy control method based on the improved particle swarm algorithm provided by the embodiment of the invention provides an adaptive simulated annealing particle swarm hybrid algorithm (AHSAPSO) on the basis of the traditional particle swarm algorithm, verifies the feasibility and the effectiveness of the method by solving the global optimal solution of three classical test functions of Griewank, Rastrigin and Ackley, and verifies the progressiveness of the method by comparing the method with a standard particle swarm algorithm (PSO) and an adaptive particle swarm Algorithm (APSO). The invention applies the self-adaptive simulated annealing particle swarm hybrid algorithm to the optimization of the proportional factor and the quantization factor of the intelligent irrigation fuzzy controller of the litchi orchard, and verifies the superiority of the method.
Based on the same inventive concept, the embodiment of the invention also provides an intelligent irrigation fuzzy control system based on the improved particle swarm optimization, and as the principle of the problem solved by the system is similar to that of the method, the implementation of the system can refer to the implementation of the method, and repeated details are omitted.
The embodiment of the invention provides an intelligent irrigation fuzzy control system based on improved particle swarm optimization, which is shown in figure 10 and comprises the following components:
the setting and obtaining module is used for setting the optimal water content of the soil and obtaining the actual water content of the soil in the area to be irrigated through the monitoring nodes; controlling to obtain a parameter adjustment quantity of the fuzzy controller according to the difference value between the optimal water content and the actual water content and the error change rate of the difference value as the input of the fuzzy controller;
the optimization module is used for optimizing the quantization factor and the scale factor in the fuzzy controller by adopting an improved particle swarm algorithm based on the parameter adjustment quantity;
and the application module is used for applying the optimized quantization factor and the optimized scale factor to the fuzzy controller to realize intelligent irrigation.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (4)
1. An intelligent irrigation fuzzy control method based on improved particle swarm optimization is characterized by comprising the following steps:
setting the optimal water content of the soil, and acquiring the actual water content of the soil in the area to be irrigated through the monitoring nodes;
controlling to obtain a parameter adjustment quantity of the fuzzy controller according to the difference value between the optimal water content and the actual water content and the error change rate of the difference value as the input of the fuzzy controller;
optimizing quantization factors and scale factors in the fuzzy controller by adopting an improved particle swarm optimization based on the parameter adjustment quantity;
applying the optimized quantization factor and scale factor to the fuzzy controller to realize intelligent irrigation;
optimizing the quantization factor and the scale factor in the fuzzy controller by adopting an improved particle swarm optimization based on the parameter adjustment quantity, wherein the optimization comprises the following steps:
initializing a particle swarm based on irrigation quantity, and randomly generating particle positions and speeds;
assigning the position and the speed of each particle to a quantization factor and a scale factor in the fuzzy controller in sequence; measuring the individual performance by the integral of the product of time and the absolute value of the error, and constructing an objective function; adjusting the inertia weight by adopting a self-adaptive mode;
selecting SA;
when the termination condition is met, terminating iteration and outputting an optimal particle fitness value; and updates the particle position and velocity at the next time.
Wherein, the adoption of the self-adaptive mode to adjust the inertia weight comprises the following steps:
particle p of the kth iterationiHas a fitness of fiThe current optimum fitness value is fmCalculating the average fitness of the whole population as favg(ii) a Will be better than favgThe particles were then averaged to give f'avgThe reference index for precocity is Δ ═ fm-f’avg|；
Calculating the inertia weight according to the following formula:
(1)fiis better than f'avgWhen the number of particles is larger, the particles are better, and the convergence is accelerated
Smaller w:
(2)fiis superior to favgBut is inferior to f'avgWhen the particle is general, keeping the inertia weight w as a fixed value;
(3)fisecond to favgAnd then, the particles are relatively poor, the global optimizing strength is increased, and the following formula is adopted for adjustment:
wherein w represents an inertia weight; k is a radical of1Representing the last iteration; k is a radical of2The next iteration is indicated.
2. The intelligent irrigation fuzzy control method based on the improved particle swarm optimization algorithm according to claim 1, wherein the step of updating the particle position and the particle speed at the next moment comprises the following steps:
the particle position and velocity are updated according to:
vij(k+1)＝w·vij(k)+c1r1(k)[pij(k)-xij(k)]+c2r2(k)[p′ij(k)-xij(k)]
xij(k+1)＝xij(k)+vij(k+1)
in the formula: c. C1、c2Is a learning factor, r1、r2Is [0, 1 ]]A uniform random number within the range, k being a certain iteration, i being a dimension, i being 1,2, … D, D being a positive integer, representing the spatial dimension; j is the index of the current particle; w is an inertia weight; p is a radical ofijFor individual extrema, from a number of individual extrema pijOne of them is recorded as p'ij；xijIs the position of the jth particle in i-dimensional space, vijVelocity, v, of the j-th particle in i-dimensional spaceij∈[-vmax,vmax]，vmaxIs the boundary velocity constant.
3. The intelligent irrigation fuzzy control method based on improved particle swarm optimization according to claim 2, wherein the SA selection is performed and comprises the following steps:
the energy of the system changes from the previous state to the next state, and the corresponding energy is changed from E1Change to E2The probability of (d) is expressed as:
pijis relative to pgPoor solution, resulting in p at distanceijTo pgProbability of transition of
pgFor global extrema, the probability of being selected is calculated as:
in the formula:
is pijThe absolute position of the particles is determined,
for the absolute position of the optimal particle, t is a parameter of simulated annealing, and the larger t is, the more likely a point closest to the optimal point is to be selected; n is the total number of particles of the PSO model, and j is the index of the current particle.
4. Intelligent irrigation fuzzy control system based on improved particle swarm optimization is characterized by comprising:
the setting and obtaining module is used for setting the optimal water content of the soil and obtaining the actual water content of the soil in the area to be irrigated through the monitoring nodes; controlling to obtain a parameter adjustment quantity of the fuzzy controller according to the difference value between the optimal water content and the actual water content and the error change rate of the difference value as the input of the fuzzy controller;
the optimization module is used for optimizing the quantization factor and the scale factor in the fuzzy controller by adopting an improved particle swarm algorithm based on the parameter adjustment quantity;
the application module is used for applying the optimized quantization factor and the optimized scale factor to the fuzzy controller to realize intelligent irrigation;
the optimization module is specifically configured to: initializing a particle swarm based on irrigation quantity, and randomly generating particle positions and speeds; assigning the position and the speed of each particle to a quantization factor and a scale factor in the fuzzy controller in sequence; measuring the individual performance by the integral of the product of time and the absolute value of the error, and constructing an objective function; adjusting the inertia weight by adopting a self-adaptive mode; selecting SA; when the termination condition is met, terminating iteration and outputting an optimal particle fitness value; and updating the particle position and speed at the next moment;
wherein, the adoption of the self-adaptive mode to adjust the inertia weight comprises the following steps:
particle p of the kth iterationiHas a fitness of fiThe current optimum fitness value is fmCalculating the average fitness of the whole population as favg(ii) a Will be better than favgThe particles were then averaged to give f'avgThe reference index for precocity is Δ ═ fm-f’avg|；
Calculating the inertia weight according to the following formula:
(1)fiis better than f'avgWhen it comes, the particles are better particles, and a smaller w:
(2)fiis superior to favgBut is inferior to f'avgWhen the particle is general, keeping the inertia weight w as a fixed value;
(3)fisecond to favgAnd then, the particles are relatively poor, the global optimizing strength is increased, and the following formula is adopted for adjustment:
wherein w represents an inertia weight; k is a radical of1Representing the last iteration; k is a radical of2Representing the next iteration.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110483088.7A CN113110061B (en) | 2021-04-30 | 2021-04-30 | Intelligent irrigation fuzzy control method and system based on improved particle swarm optimization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110483088.7A CN113110061B (en) | 2021-04-30 | 2021-04-30 | Intelligent irrigation fuzzy control method and system based on improved particle swarm optimization |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113110061A CN113110061A (en) | 2021-07-13 |
| CN113110061B true CN113110061B (en) | 2022-05-10 |
Family
ID=76720803
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110483088.7A Active CN113110061B (en) | 2021-04-30 | 2021-04-30 | Intelligent irrigation fuzzy control method and system based on improved particle swarm optimization |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113110061B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113741177A (en) * | 2021-09-26 | 2021-12-03 | 华南农业大学 | Control method for orange fruit coloring and mature period irrigation simulation |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110308649A (en) * | 2019-07-11 | 2019-10-08 | 东南大学 | A kind of pid parameter optimization method based on PSO-SOA blending algorithm |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107272403A (en) * | 2017-06-14 | 2017-10-20 | 浙江师范大学 | A kind of PID controller parameter setting algorithm based on improvement particle cluster algorithm |
| US10921760B2 (en) * | 2018-06-12 | 2021-02-16 | PassiveLogic, Inc. | Predictive control loops using time-based simulation and building-automation systems thereof |
| CN109947124A (en) * | 2019-04-25 | 2019-06-28 | 南京航空航天大学 | Improve particle swarm algorithm Optimization of Fuzzy PID unmanned helicopter attitude control method |
| CN111129548B (en) * | 2019-12-27 | 2021-06-22 | 南京航空航天大学 | Improved particle swarm optimization fuzzy PID fuel cell temperature control method |
| CN111413863B (en) * | 2020-03-27 | 2023-04-07 | 南京理工大学 | Particle swarm fuzzy Smith temperature control method based on 3D printing nozzle |
| CN111967181A (en) * | 2020-07-20 | 2020-11-20 | 西安工程大学 | Irrigation time calculation method based on APSO-ELM and fuzzy logic |
-
2021
- 2021-04-30 CN CN202110483088.7A patent/CN113110061B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110308649A (en) * | 2019-07-11 | 2019-10-08 | 东南大学 | A kind of pid parameter optimization method based on PSO-SOA blending algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113110061A (en) | 2021-07-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104776446B (en) | Combustion optimization control method for boiler | |
| CN111474965B (en) | Fuzzy neural network-based method for predicting and controlling water level of series water delivery channel | |
| CN107272403A (en) | A kind of PID controller parameter setting algorithm based on improvement particle cluster algorithm | |
| CN109818775B (en) | Short-term network flow prediction method | |
| CN105207253B (en) | Consider wind-powered electricity generation and the probabilistic AGC stochastic and dynamics Optimization Scheduling of frequency | |
| CN111520878A (en) | Air conditioner temperature control system based on RBF neural network and control method thereof | |
| CN104834215A (en) | Variation particle swarm optimized BP neural network proportion integration differentiation (PID) control algorithm | |
| CN110110380B (en) | Piezoelectric actuator hysteresis nonlinear modeling method and application | |
| CN113253779A (en) | Heat pump temperature control system based on particle swarm fuzzy PID algorithm | |
| CN110033081A (en) | A kind of method and apparatus of determining learning rate | |
| CN113110061B (en) | Intelligent irrigation fuzzy control method and system based on improved particle swarm optimization | |
| CN111222286A (en) | Parameter optimization method based on power transmission line state estimation | |
| CN108121206B (en) | Composite self-adaptive internal model control optimization method based on efficient improved differential evolution algorithm | |
| CN104050505A (en) | Multilayer-perceptron training method based on bee colony algorithm with learning factor | |
| CN112950963A (en) | Self-adaptive signal control optimization method for main branch intersection of city | |
| CN102393645A (en) | Control method of high-speed electro-hydraulic proportional governing system | |
| CN116436033A (en) | Temperature control load frequency response control method based on user satisfaction and reinforcement learning | |
| CN114909706A (en) | Secondary network balance regulation and control method based on reinforcement learning algorithm and pressure difference control | |
| CN112180733B (en) | Fuzzy logic-based building energy consumption system prediction control parameter setting method | |
| CN108490791B (en) | Temperature controlled load cost control strategy | |
| CN113885328A (en) | Nuclear power tracking control method based on integral reinforcement learning | |
| CN113852098A (en) | Automatic power generation control scheduling method based on multi-target dragonfly algorithm | |
| CN116307440B (en) | Workshop scheduling method based on reinforcement learning and multi-objective weight learning, device and application thereof | |
| CN111427261A (en) | PID parameter setting method based on cat swarm algorithm | |
| CN108805264B (en) | Method for evaluating power output of carrier-based aircraft by using RBF (radial basis function) based on rapid learning rate |
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 |