CN113569470B - Fruit and vegetable respiration rate model parameter estimation method based on improved particle swarm optimization - Google Patents
Fruit and vegetable respiration rate model parameter estimation method based on improved particle swarm optimization Download PDFInfo
- Publication number
- CN113569470B CN113569470B CN202110804035.0A CN202110804035A CN113569470B CN 113569470 B CN113569470 B CN 113569470B CN 202110804035 A CN202110804035 A CN 202110804035A CN 113569470 B CN113569470 B CN 113569470B
- Authority
- CN
- China
- Prior art keywords
- fruit
- particle
- respiration rate
- vegetable
- particles
- 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
- 239000002245 particle Substances 0.000 title claims abstract description 121
- 235000012055 fruits and vegetables Nutrition 0.000 title claims abstract description 92
- 230000029058 respiratory gaseous exchange Effects 0.000 title claims abstract description 85
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000005457 optimization Methods 0.000 title description 2
- 230000006870 function Effects 0.000 claims description 28
- 230000036387 respiratory rate Effects 0.000 claims description 20
- 239000013598 vector Substances 0.000 claims description 18
- 239000011521 glass Substances 0.000 claims description 12
- 235000013399 edible fruits Nutrition 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 6
- 238000002474 experimental method Methods 0.000 claims description 5
- 235000021384 green leafy vegetables Nutrition 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 4
- 238000007542 hardness measurement Methods 0.000 claims description 3
- 235000013311 vegetables Nutrition 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 4
- 238000009448 modified atmosphere packaging Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 239000000047 product Substances 0.000 description 3
- 240000008067 Cucumis sativus Species 0.000 description 2
- 235000010799 Cucumis sativus var sativus Nutrition 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 241000272814 Anser sp. Species 0.000 description 1
- 102000004190 Enzymes Human genes 0.000 description 1
- 108090000790 Enzymes Proteins 0.000 description 1
- 230000004099 anaerobic respiration Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004151 fermentation Effects 0.000 description 1
- 238000000855 fermentation Methods 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000002503 metabolic effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003204 osmotic effect Effects 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 239000012466 permeate Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000004202 respiratory function Effects 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
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- 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]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Hardware Design (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- Geometry (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Breeding Of Plants And Reproduction By Means Of Culturing (AREA)
Abstract
The invention discloses a fruit and vegetable respiration rate model parameter estimation method based on an improved particle swarm algorithm, which solves the problems that the accuracy of predicting the respiration rate of fruit and vegetable products is not high, the fitting effect is unstable only for single fruit and vegetable varieties in the prior art, and provides a fruit and vegetable respiration rate model based on the influences of storage temperature, storage time and fruit and vegetable maturity. The invention comprises the following steps: (1) constructing a fruit and vegetable respiration rate model; (2) initializing particle swarm parameters; (3) calculating fitness value, updating particle speed and position; (4) updating the globally optimal particles; (5) updating the global worst particles; (6) adjusting the learning weight; (7) If the convergence condition or the maximum iteration number is reached, the next step is carried out, otherwise, the step (3) is returned to; (8) outputting an optimal value.
Description
Technical field:
the invention belongs to the technical field of fruit and vegetable modified atmosphere packaging, and relates to a fruit and vegetable respiration rate model parameter estimation method based on an improved particle swarm algorithm.
The background technology is as follows:
the modified atmosphere packaging is the most effective fruit and vegetable fresh-keeping method at present. In the fruit and vegetable modified atmosphere packaging application, there are two dynamic processes: on the one hand, the picked fruits and vegetables still have respiratory function, and O in the package is consumed 2 Gradually reducing its concentration to release CO 2 So that the concentration thereof gradually increases. On the other hand, different partial pressures of gas inside and outside the package lead to gas permeation. O outside the package 2 At a concentration higher than the concentration in the package, resulting in O 2 Osmotic diffusion into the package interior; while the CO inside the package 2 Concentration higher than the outside concentration of the package, resulting in CO 2 The permeate diffuses out of the package. When respiration of fruits and vegetables consumes O 2 Is equal to the penetration of O through the film 2 And the fruit and vegetable breathe to release CO 2 Is equal to the rate of film exudation of CO 2 At the rate, a relationship to O is established within the package 2 And CO 2 Pneumatically regulated dynamicsBalancing the environment.
The modified atmosphere packaging design is used for matching the respiration rate of fruits and vegetables with the air permeability of the film to form optimal storage conditions, namely the gas dynamic balance environment. Under the air-conditioned dynamic balance environment, the respiration speed of fruits and vegetables is reduced to the minimum metabolic level, so that the shelf life of the fruits and vegetables is prolonged.
The establishment of the fruit and vegetable respiration rate model is the basis for correctly designing the modified atmosphere package. The poorly designed modified atmosphere packaging cannot prolong the shelf life of fruit and vegetable products, and can cause a series of problems such as anaerobic respiration and fermentation, accelerate the spoilage of fruits and vegetables, and even cause the problem of food quality safety. Factors influencing the respiration rate of fruits and vegetables mainly comprise storage temperature, storage time and maturity of fruits and vegetables. At present, there are no fruit and vegetable respiration models considering the comprehensive influences of storage temperature, storage time and fruit and vegetable maturity at home and abroad, and more Michaelies-Menten models based on enzyme dynamics theory and statistical respiration rate models are used. However, both modeling methods suffer from deficiencies: the Mi model cannot explain the respiration mechanism of fruits and vegetables, and the accuracy of predicting the respiration rate of fruit and vegetable products is not high; the respiratory rate model based on statistics is superior to a Mi model in accuracy, but the model generally adopts a multi-element function with gas concentration or temperature as independent variables to calculate the respiratory rate of fruits and vegetables, so that the model can only aim at a single fruit and vegetable variety, and the fitting effect is unstable.
The invention comprises the following steps:
the invention aims to provide a fruit and vegetable respiration rate model parameter estimation method based on an improved particle swarm algorithm, which solves the problems that the accuracy of predicting fruit and vegetable product respiration rate is not high, and the fitting effect is unstable only for a single fruit and vegetable variety in the prior art, and provides a fruit and vegetable respiration rate model based on the influence of storage temperature, storage time and fruit and vegetable maturity.
In order to achieve the above purpose, the invention adopts the following technical scheme:
a fruit and vegetable respiration rate model parameter estimation method based on an improved particle swarm algorithm is characterized by comprising the following steps of: the method comprises the following steps:
(1) Constructing a fruit and vegetable respiration rate model;
(2) Initializing particle swarm parameters;
(3) Calculating a fitness value, and updating the particle speed and the position;
(4) Updating the global optimal particles;
(5) Updating the global worst particles;
(6) Adjusting learning weights;
(7) If the convergence condition or the maximum iteration number is reached, the next step is carried out, otherwise, the step (3) is returned to;
(8) Outputting an optimal value;
the method specifically comprises the following steps:
(1) The fruit and vegetable respiration rate model based on the common influence of temperature, maturity and storage time is established as follows:
wherein,and->Respectively the storage temperature T, the maturity Ma and the storage time T under the condition O 2 And CO 2 mL/(kg.h); />And->Respectively is O 2 And CO 2 mL/(kg.h); alpha and beta are O respectively 2 And CO 2 A temperature coefficient of the respiratory rate model; mu and v are O respectively 2 And CO 2 Maturity coefficients of the respiratory rate model; ρ and σ are O respectively 2 And CO 2 A stored time coefficient of the respiratory rate model;
(2) The fruit and vegetable are subjected to postharvest treatment, the hardness of the fruit and vegetable before and after the experiment is measured by using a fruit hardness tester, the hardness of the stem of the green leaf vegetable is measured, and the hardness of the pulp tissue is measured for the rest. Under different storage temperature conditions, measuring CO in modified atmosphere package 2 、O 2 Respectively calculating the CO according to the gas concentration 2 、O 2 Is a respiratory rate of (2);
(3) Construction of CO 2 、O 2 And solving parameters of the fruit and vegetable respiration rate model by improving an fitness function of the respiration rate model through a particle swarm algorithm.
The post-picking treatment and hardness measurement in the step (2) means that the picked fruits and vegetables are washed, air-dried and tested at the experimental temperature T test Precooling for 30min, and measuring hardness of fruits and vegetables by using a fruit hardness tester;
measuring CO in the modified atmosphere package under different storage temperature conditions in the step (2) 2 、O 2 Is used for calculating the gas concentration and CO 2 、O 2 The respiration rate of (2) is that a glass pot with a cover is selected, the glass pot is closed after fruits and vegetables are put in the glass pot, and O in the glass pot is measured by a headspace gas analyzer through a small hole on the cover every 4 hours 2 And CO 2 Concentration, slightly open the lid every other day to prevent O 2 Oxygen-free respiration due to too low concentration, and time O at t 2 And CO 2 The respiration rate is calculated according to formulas (3) and (4);
wherein,respectively, the O is related to the fruits and the vegetables at the time t 2 And CO 2 mL/(kg.h);respectively t time O 2 And CO 2 Concentration,%; />Respectively the initial time O 2 And CO 2 Concentration,%; v (V) f Is headspace free volume, mL; t, t i H is the current time and the initial time respectively; w is the quality of fruits and vegetables and kg.
The different storage temperature conditions in the step (2) are respectively precooling and experiment at 5, 15 and 25 ℃.
Step (3) comprises the following steps:
s1, randomly initializing position vectors and speed vectors of particles, wherein the initial position of each particle is set to be an individual optimal value, the optimal value of a population is set to be a global optimal value, and the position vectors of the particle population are parameters to be estimated by a fruit and vegetable respiration rate modelAnd->
S2, respectively constructing CO 2 、O 2 Fitness function of the respiratory rate model:
wherein CO 2 The fitness function of the respiration rate is as follows:
wherein O is 2 The fitness function of the respiration rate is as follows:
s3, updating the speed and the position of each particle, calculating the fitness of the particles, and evaluating a fitness function;
s4, constructing an adaptability matrix FIT with the number of 0.1N according to the sequence from big to small ij Where i=1, 2, …,0.1N; j=1, 2, …, D, N is the number of particles and D is the particle dimension;
determining the selection probability of the global optimum vector element according to the following formula, and selecting the particle FIT according to the probability ij Construction of gbest * Replacing the global optimal particles and updating the global optimal value;
s5, sorting the fitness of all particles from large to small, randomly selecting two particles gbest from 0.1N particles with worst fitness according to the sequence from large to small a 、gbest b And intersecting according to the following formula to generate gworts instead of gworts;
wherein T is the total iteration number, T is the current iteration number, and epsilon is a random number of (0, 1);
s6, calculating the Euclidean distance between each particle and the global optimal particle, and calculating the Euclidean distance between each particle and the global optimal particle gbest by the following formula
Dynamically adjusting the learning weight according to the following formula, and updating each particle speed:
s7, judging an algorithm termination condition, and if algorithm convergence meets the requirement or reaches the maximum iteration number, outputting a global optimal valueIs->The algorithm ends. Otherwise, returning to Step3.
In the step S3, the processing unit,
wherein the population is a population X= { X of N particles 1 ,x 2 ,…x N At the iteration time t, the position coordinate of the ith particle in the D-dimensional space is x i (t)=(x i1 ,x i2 ,…,x iD ) The method comprises the steps of carrying out a first treatment on the surface of the Particle i velocity coordinate v i (t)=(v i1 ,v i2 ,…,v iD );
Wherein the particle i experiences the optimum pbest i (t)=(pbesy i1 ,pbest i2 ,…,pbest iD ) As an individual optimal location; best position gbest (t) = (pbest) experienced by all particles 1 (t),pbest 2 (t),…,pbest D (t)) as a global optimum position coordinate position;
wherein the position x i (t) and velocity v i And (t) is adjusted at time t+1 according to the formulas (7) and (8):
v ij (t+1)=wv ij (t)+c 1 r 1 (pbest ij (t)-x ij (t))+c 2 r 2 (gbest j (t)-x ij (t)) (7)
x ij (t+1)=x ij (t)+v ij (t+1) (8)
compared with the prior art, the invention has the following advantages and effects:
1. the invention provides a fruit and vegetable respiration rate model based on the influence of storage temperature, storage time and fruit and vegetable maturity for determining the respiration rate of fruits and vegetables; the variation is carried out on the global optimal particles and the global worst particles, the learning weight is dynamically adjusted, and a wild goose particle swarm algorithm is provided; further estimating the parameters of the fruit and vegetable respiration rate model by improving a particle swarm algorithm.
2. The invention takes the influence of storage temperature, storage time and fruit and vegetable maturity on the respiration rate into consideration to carry out fruit and vegetable respiration rate modeling, and is more in line with the change rule of fruit and vegetable respiration rate compared with the existing fruit and vegetable respiration rate model. The improved particle swarm algorithm is simple in structure, easy to implement and high in algorithm convergence speed, and overcomes the defect that the particle swarm algorithm is easy to fall into a local optimal value. The fruit and vegetable respiration rate model fitted by the improved particle swarm algorithm has high parameter precision, wide application range and practical application value.
Description of the drawings:
FIG. 1 is a flow chart of a method for estimating parameters of a fruit and vegetable respiration rate model according to the invention;
FIG. 2 is a view of fruit and vegetable O in the embodiment 2 A fitness function value convergence process of the breathing rate;
FIG. 3 is a schematic view of fruit and vegetable CO in the embodiment 2 And (5) convergence process of fitness function value of the breathing rate.
The specific embodiment is as follows:
the present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The invention relates to a fruit and vegetable respiration rate model parameter estimation method based on an improved particle swarm algorithm, which is shown in fig. 1 and comprises the following steps:
(1) Starting;
(2) Constructing a fruit and vegetable respiration rate model;
(3) Initializing particle swarm parameters;
(4) Calculating a fitness value, and updating the particle speed and the position;
(5) Updating the global optimal particles;
(6) Updating the global worst particles;
(7) Adjusting learning weights;
(8) If the convergence condition or the maximum iteration number is reached, the next step is carried out, otherwise, the step (4) is returned to;
(9) Outputting an optimal value;
(10) And (5) ending.
The method specifically comprises the following steps:
the first step, considering the influence of storage temperature, storage time and fruit and vegetable maturity on the change of fruit and vegetable respiration rate, establishing a fruit and vegetable respiration rate model based on the common influence of temperature, maturity and storage time as follows:
wherein,and->Respectively the storage temperature T, the maturity Ma and the storage time T under the condition O 2 And CO 2 mL/(kg.h); />And->O respectively 2 And CO 2 mL/(kg.h); alpha and beta are O respectively 2 And CO 2 A temperature coefficient of the respiratory rate model; mu and v are O respectively 2 And CO 2 Maturity coefficients of the respiratory rate model; ρ, s are O respectively 2 And CO 2 A stored time coefficient of the respiratory rate model.
And secondly, carrying out postharvest treatment on fruits and vegetables, respectively measuring the hardness of the fruits and vegetables before and after the experiment by using a fruit hardness tester, measuring the hardness of the stems of green leaf vegetables, and measuring the hardness of the pulp tissues of the rest. Under different storage temperature conditions, measuring CO in modified atmosphere package 2 、O 2 Respectively calculating the CO according to the gas concentration 2 、O 2 Is used for the breathing rate of (a).
Third step, constructing CO 2 、O 2 Fitness function of the breathing rate model. Solving the fruit and vegetable respiration rate model parameters by improving a particle swarm algorithm, comprising the following steps:
step1, randomly initializing position vectors and speed vectors of particles, wherein the initial position of each particle is set to be an individual optimal value, and the optimal value of a population is set to be a global optimal value. The particle swarm position vector is a parameter to be estimated by the fruit and vegetable respiration rate model. Wherein the particle swarm position vector is the parameter to be estimated by the fruit and vegetable respiration rate modelAnd->
Step2, respectively constructing CO 2 、O 2 Fitness function of the breathing rate model.
Wherein, regarding CO 2 The fitness function of the respiration rate is as follows:
wherein, regarding O 2 The fitness function of the respiration rate is as follows:
step3, updating the speed and the position of each particle, calculating the fitness of the particles, and evaluating a fitness function.
Step4, constructing an adaptability matrix FIT with the number of 0.1N according to the order from big to small ij Where i=1, 2, …,0.1N; j=1, 2, …, D, N is the number of particles and D is the particle dimension.
Determining the selection probability of the global optimum vector element according to the following formula, and selecting the particle FIT according to the probability ij Construction of gbest * And replacing the global optimal particles and updating the global optimal value.
Step5, sorting the fitness of all particles from big to small, randomly selecting two particles gbest from 0.1N particles with worst fitness according to the sequence from big to small a 、gbest b And crossed according to the following formula, resulting in a gwortx substitution gworts.
Wherein T is the total iteration number, T is the current iteration number, and e is a random number of (0, 1). Step6, calculating the Euclidean distance between each particle and the global optimal particle, and calculating the Euclidean distance between each particle and the global optimal particle gbest by the following formula
Dynamically adjusting the learning weight according to the following formula, and updating each particle speed:
step7, judging an algorithm termination condition, and outputting a global optimal value if algorithm convergence meets the requirement or reaches the maximum iteration numberIs->The algorithm ends. Otherwise, returning to Step3.
Examples:
referring to fig. 1, the invention provides a fruit and vegetable respiration rate model parameter estimation method based on an improved particle swarm algorithm, and the whole process mainly comprises fruit and vegetable respiration rate models, an improved particle swarm algorithm and model parameter estimation, and the method comprises the following steps:
firstly, establishing a fruit and vegetable respiration rate model based on the common influence of temperature, maturity and storage time, wherein the formula (1) and the formula (2) are O respectively 2 And CO 2 Is a respiratory rate of (2):
wherein,and->Respectively the storage temperature T, the maturity Ma and the storage time T under the condition O 2 And CO 2 mL/(kg.h); />And->O respectively 2 And CO 2 mL/(kg.h); alpha and beta are O respectively 2 And CO 2 A temperature coefficient of the respiratory rate model; mu, v divisionIs other than O 2 And CO 2 Maturity coefficients of the respiratory rate model; ρ, s are O respectively 2 And CO 2 A stored time coefficient of the respiratory rate model.
And secondly, carrying out postharvest treatment on fruits and vegetables, respectively measuring the hardness of the fruits and vegetables before and after the experiment by using a fruit hardness tester, measuring the hardness of the stems of green leaf vegetables, and measuring the hardness of the pulp tissues of the rest. Under different storage temperature conditions, measuring CO in modified atmosphere package 2 、O 2 Respectively calculating the CO according to the gas concentration 2 、O 2 Is used for the breathing rate of (a).
Wherein, the post-picking treatment and hardness measurement in the second step means that the picked fruits and vegetables are cleaned, air-dried and tested at the experimental temperature T test Precooling for 30min, and measuring hardness of the fruits and vegetables by using a fruit hardness tester. The object of measurement in this example is green leaf vegetables, the hardness of the stems of which is measured, and the hardness of freshly picked fruits and vegetables is measured as described above, and is denoted as M f ,kgf/cm 2
Wherein, the step two is to measure CO in the modified atmosphere package under the condition of different storage temperatures 2 、O 2 Is used for calculating the gas concentration and CO 2 、O 2 The respiration rate "of (1) means that a glass tank with a cover is selected, the glass tank is closed after fruits and vegetables are put in the glass tank, and O in the glass tank is measured by a headspace gas analyzer through a small hole on the cover every 4 hours 2 And CO 2 Concentration, slightly open the lid every other day to prevent O 2 Oxygen-free respiration due to too low concentration, and time O at t 2 And CO 2 The respiration rate is calculated according to formulas (3), (4).
Wherein,respectively, the O is related to the fruits and the vegetables at the time t 2 And CO 2 mL/(kg.h);respectively t time O 2 And CO 2 Concentration,%; />Respectively the initial time O 2 And CO 2 Concentration,%; v (V) f Is headspace free volume, mL; t, t i H is the current time and the initial time respectively; w is the quality of fruits and vegetables, kg
The second step is to pre-cool and test at 5, 15 and 25 deg.c.
Third step, constructing CO 2 、O 2 The fitness function of the respiration rate model solves the parameters of the fruit and vegetable respiration rate model by improving a particle swarm algorithm, and comprises the following steps:
step1, randomly initializing position vectors and speed vectors of particles, wherein the initial position of each particle is set to be an individual optimal value, and the optimal value of a population is set to be a global optimal value. Wherein the position vector dimension of the particle swarm is 4, namely the parameter to be estimated by the fruit and vegetable respiration rate modelAnd->Wherein, the population number N is 50, and the maximum iteration number T is 2000.
Step2, respectively constructing CO 2 、O 2 Fitness function of the breathing rate model.
Wherein, regarding CO 2 The fitness function of the breathing rate is as follows (5):
wherein, regarding O 2 The fitness function of the breathing rate is as shown in the formula (6):
step3, updating the speed and the position of each particle, calculating the fitness of the particles, and evaluating a fitness function.
Wherein the population is a population X= { X of N particles 1 ,x 2 ,…x N At the iteration time t, the position coordinate of the ith particle in the D-dimensional space is x i (t)=(x i1 ,x i2 ,…,x iD ) The method comprises the steps of carrying out a first treatment on the surface of the Particle i velocity coordinate v i (t)=(v i1 ,v i2 ,…,v iD );
Wherein the particle i experiences the optimum pbest i (t)=(pbesy i1 ,pbest i2 ,…,pbest iD ) As the individual optimal location. Best position gbest (t) = (pbest) experienced by all particles 1 (t),pbest 2 (t),…,pbest D (t)) as a global optimum position coordinate position.
Wherein the position x i (t) and velocity v i And (t) is adjusted at time t+1 according to the formulas (7) and (8):
v ij (t+1)=wv ij (t)+c 1 r 1 (pbest ij (t)-x ij (t))+c 2 r 2 (gbest j (t)-x ij (t)) (7)
x ij (t+1)=x ij (t)+v ij (t+1) (8)
step4, constructing an adaptability matrix FIT with the number of 0.1N according to the order from big to small ij Where i=1, 2, ×,0.1N; j=1, 2, ×, D, N is the population number, D is the particle swarm position vector dimension.
Determining a probability of selection of the global optimum vector element according to equation (9), selecting the particle FIT according to the probability ij Construction of gbest * And replacing the global optimal particles and updating the global optimal value.
Step5, sorting the fitness of all particles from big to small, randomly selecting two particles gbest from 0.1N particles with worst fitness according to the sequence from big to small a 、gbest b And crossed according to the following formula, resulting in a gwortx substitution gworts.
Wherein T is the maximum iteration number, T is the current iteration number, and ε is a random number of (0, 1).
Step6, calculating the Euclidean distance between each particle and the global optimal particle, and calculating the Euclidean distance between each particle and the global optimal particle gbest according to the formula (11)
According to equation (12), dynamically adjusting the learning weights to update each particle velocity:
step7, judging algorithm termination conditions, and if the fitness function is converged to be smaller than epsilon or reaches the maximum iteration number, outputting a global optimal valueIs->The algorithm ends. Otherwise, returning to Step3.
FIG. 2 is a view of fruit and vegetable O in the embodiment 2 The fitness function value of the respiration rate convergesFIG. 3 shows the CO content of the fruits and vegetables in the embodiment 2 And (5) convergence process of fitness function value of the breathing rate.
Experimental example:
in the embodiment, cucumber is taken as an experimental object, and the cucumber is stored for 7 days at the temperature of 5, 15 and 25 ℃ and subjected to particle swarm parameter estimation, 2000 steps of iteration and CO 2 The fitness function value of the respiration rate is reduced to 1.3, O 2 The fitness function value of the respiration rate was reduced to 2.9. Wherein, experimental respiration rate and predicted respiration rate are shown in table 1, and estimated respiration rate model parameters are shown in table 2.
Table 1 respiration rate values
TABLE 2 respiratory rate model parameters
The foregoing description of the preferred embodiments of the present invention is not intended to limit the scope of the invention, and it should be noted that modifications and variations could be made by persons skilled in the art without departing from the principles of the present invention.
Claims (1)
1. A fruit and vegetable respiration rate model parameter estimation method based on an improved particle swarm algorithm is characterized by comprising the following steps of: the method comprises the following steps:
(1) Constructing a fruit and vegetable respiration rate model;
(2) Initializing particle swarm parameters;
(3) Calculating a fitness value, and updating the particle speed and the position;
(4) Updating the global optimal particles;
(5) Updating the global worst particles;
(6) Adjusting learning weights;
(7) If the convergence condition or the maximum iteration number is reached, the next step is carried out, otherwise, the step (3) is returned to;
(8) Outputting an optimal value;
the method specifically comprises the following steps:
(1) The fruit and vegetable respiration rate model based on the common influence of temperature, maturity and storage time is established as follows:
wherein,and->Respectively the storage temperature T, the maturity Ma and the storage time T under the condition O 2 And CO 2 mL/(kg.h); />And->O respectively 2 And CO 2 mL/(kg.h); alpha and beta are O respectively 2 And CO 2 A temperature coefficient of the respiratory rate model; mu, v are O respectively 2 And CO 2 Maturity coefficients of the respiratory rate model; ρ and σ are O respectively 2 And CO 2 A stored time coefficient of the respiratory rate model;
(2) Fruit and vegetable is subjected toAfter-picking treatment, respectively measuring hardness of fruits and vegetables before and after experiments by using a fruit hardness tester, measuring hardness of stems of green leaf vegetables, and measuring hardness of pulp tissues of the rest; under different storage temperature conditions, measuring CO in modified atmosphere package 2 、O 2 Respectively calculating the CO according to the gas concentration 2 、O 2 Is a respiratory rate of (2);
(3) Construction of CO 2 、O 2 Solving parameters of the fruit and vegetable respiration rate model through an improved particle swarm algorithm according to an fitness function of the respiration rate model;
the post-picking treatment and hardness measurement in the step (2) means that the picked fruits and vegetables are washed, air-dried and tested at the experimental temperature T test Precooling for 30min, and measuring hardness of fruits and vegetables by using a fruit hardness tester; measuring CO in the modified atmosphere package under different storage temperature conditions in the step (2) 2 、O 2 Is used for calculating the gas concentration and CO 2 、O 2 The respiration rate of (2) is that a glass pot with a cover is selected, the glass pot is closed after fruits and vegetables are put in the glass pot, and O in the glass pot is measured by a headspace gas analyzer through a small hole on the cover every 4 hours 2 And CO 2 Concentration, slightly open the lid every other day to prevent O 2 Oxygen-free respiration due to too low concentration, and time O at t 2 And CO 2 The respiration rate is calculated according to formulas (3) and (4);
wherein,respectively, the O is related to the fruits and the vegetables at the time t 2 And CO 2 mL/(kg.h); />Respectively t time O 2 And CO 2 Concentration,%; />Respectively the initial time O 2 And CO 2 Concentration,%; v (V) f Is headspace free volume, mL; t, t i H is the current time and the initial time respectively; w is the mass of fruits and vegetables, kg;
the step (2) is to pre-cool and test at 5, 15 and 25 ℃ respectively under different storage temperature conditions;
step (3) comprises the following steps:
s1, randomly initializing a position vector and a speed vector of particles, wherein the initial position of each particle is set to be an individual optimal value, and the optimal value of a population is set to be a global optimal value; wherein the position vector dimension of the particle swarm is 4, namely the parameter to be estimated by the fruit and vegetable respiration rate modelAnd->
S2, respectively constructing CO 2 、O 2 A fitness function of the respiratory rate model;
wherein, regarding CO 2 The fitness function of the respiration rate is as follows:
wherein, regarding O 2 The fitness function of the respiration rate is as follows:
s3, updating the speed and the position of each particle, calculating the fitness of the particles, and evaluating a fitness function;
s4, constructing an adaptability matrix FIT with the number of 0.1N according to the sequence from big to small ij Where i=1, 2, …,0.1N; j=1, 2, …, D, N is the number of particles and D is the particle dimension;
determining the selection probability of the global optimum vector element according to the following formula, and selecting the particle FIT according to the probability ij Construction of gbest * Replacing the global optimal particles and updating the global optimal value;
s5, sorting the fitness of all particles from large to small, randomly selecting two particles gbest from 0.1N particles with worst fitness according to the sequence from large to small a 、gbest b And intersecting according to the following formula to generate gworts instead of gworts;
wherein T is the maximum iteration number, T is the current iteration number, and ε is a random number of (0, 1);
s6, calculating the Euclidean distance between each particle and the global optimal particle, and calculating the Euclidean distance between each particle and the global optimal particle gbest by the following formula
Dynamically adjusting the learning weight according to the following formula, and updating each particle speed:
s7, judging an algorithm termination condition, if the algorithm convergence meets the requirementSolving or reaching the maximum iteration number and outputting a global optimal valueIs->Ending the algorithm; otherwise, returning to Step3;
s3, wherein the population X= { X is composed of N particles 1 ,x 2 ,…x N At the iteration time t, the position coordinate of the ith particle in the D-dimensional space is x i (t)=(x i1 ,x i2 ,…,x iD ) The method comprises the steps of carrying out a first treatment on the surface of the Particle i velocity coordinate v i (t)=(v i1 ,v i2 ,…,v iD );
Wherein the particle i experiences the optimum pbest i (t)=(pbesy i1 ,pbest i2 ,…,pbest iD ) As individual optimal positions, the best positions all particles have undergone
gbest(t)=(pbest 1 (t),pbest 2 (t),…,pbest D (t)) as a global optimum position coordinate position;
wherein the position x i (t) and velocity v i And (t) is adjusted at time t+1 according to the formulas (7) and (8):
v ij (t+1)=wv ij (t)+c 1 r 1 (pbest ij (t)-x ij (t))+c 2 r 2 (gbest j (t)-x ij (t)) (7)
x ij (t+1)=x ij (t)+v ij (t+1) (8)。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110804035.0A CN113569470B (en) | 2021-07-16 | 2021-07-16 | Fruit and vegetable respiration rate model parameter estimation method based on improved particle swarm optimization |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110804035.0A CN113569470B (en) | 2021-07-16 | 2021-07-16 | Fruit and vegetable respiration rate model parameter estimation method based on improved particle swarm optimization |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113569470A CN113569470A (en) | 2021-10-29 |
CN113569470B true CN113569470B (en) | 2024-04-05 |
Family
ID=78165048
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110804035.0A Active CN113569470B (en) | 2021-07-16 | 2021-07-16 | Fruit and vegetable respiration rate model parameter estimation method based on improved particle swarm optimization |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113569470B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102096732A (en) * | 2011-01-07 | 2011-06-15 | 山东理工大学 | Fruit and vegetable respiration rate modeling method |
WO2017119987A1 (en) * | 2016-01-07 | 2017-07-13 | The Climate Corporation | Generating digital models of crop yield based on crop planting dates and relative maturity values |
CN107121407A (en) * | 2017-06-02 | 2017-09-01 | 中国计量大学 | The method that near-infrared spectrum analysis based on PSO RICAELM differentiates Cuiguan pear maturity |
CN108399450A (en) * | 2018-02-02 | 2018-08-14 | 武汉理工大学 | Improvement particle cluster algorithm based on biological evolution principle |
CN111462044A (en) * | 2020-03-05 | 2020-07-28 | 浙江省农业科学院 | Greenhouse strawberry detection and maturity evaluation method based on deep learning model |
-
2021
- 2021-07-16 CN CN202110804035.0A patent/CN113569470B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102096732A (en) * | 2011-01-07 | 2011-06-15 | 山东理工大学 | Fruit and vegetable respiration rate modeling method |
WO2017119987A1 (en) * | 2016-01-07 | 2017-07-13 | The Climate Corporation | Generating digital models of crop yield based on crop planting dates and relative maturity values |
CN107121407A (en) * | 2017-06-02 | 2017-09-01 | 中国计量大学 | The method that near-infrared spectrum analysis based on PSO RICAELM differentiates Cuiguan pear maturity |
CN108399450A (en) * | 2018-02-02 | 2018-08-14 | 武汉理工大学 | Improvement particle cluster algorithm based on biological evolution principle |
CN111462044A (en) * | 2020-03-05 | 2020-07-28 | 浙江省农业科学院 | Greenhouse strawberry detection and maturity evaluation method based on deep learning model |
Non-Patent Citations (2)
Title |
---|
Determining Vital Signs with CW Doppler Radar Based on Particle Swarm Optimization;Jian-Shun Ciou等;《IEEE Asia-Pacific Microwave Conference》;501-503 * |
基于IPSO-SA算法的温室番茄产量预测方法;张立彬等;《浙江工业大学学报》;第47卷(第5期);527-533 * |
Also Published As
Publication number | Publication date |
---|---|
CN113569470A (en) | 2021-10-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Genkawa et al. | Development of a low-moisture-content storage system for brown rice: storability at decreased moisture contents | |
Cooper et al. | Effects of nighttime temperature during kernel development on rice physicochemical properties | |
Yang et al. | Modeling the effect of O2 and CO2 on respiration and quality of stored tomatoes | |
Paniagua et al. | Interaction of temperature control deficiencies and atmosphere conditions during blueberry storage on quality outcomes | |
Van Iersel | Carbon use efficiency depends on growth respiration, maintenance respiration, and relative growth rate. A case study with lettuce | |
US20150257401A1 (en) | Control apparatus for controlled atmosphere cells for storing perishable items | |
Dillahunty et al. | Effect of moisture content and temperature on respiration rate of rice | |
CN113569470B (en) | Fruit and vegetable respiration rate model parameter estimation method based on improved particle swarm optimization | |
An et al. | Effect of hypobaric packaging on respiration and quality of strawberry and curled lettuce | |
CN104034854A (en) | A shelf life prediction method of seasoned lobsters | |
CN105243599A (en) | Method for building rice storage quality evaluation model | |
Fasina et al. | Mass transfer and solute diffusion in brined cucumbers | |
CN106359546A (en) | Physical fresh keeping method of lentinus edodes | |
CN111027784B (en) | Method for predicting shelf life of cold fresh chicken | |
Moog et al. | Fungal Susceptibility at Four Temperature‐Moisture Combinations and Carbon Dioxide Kit Color Reader Evaluation | |
SE513894C2 (en) | Procedure for airtight storage of moist grain in the presence of a biocontrol agent | |
Lareo et al. | Influence of temperature on shelf life of butterhead lettuce leaves under passive modified atmosphere packaging | |
CN109486898B (en) | Method for rapidly predicting growth condition of aspergillus fungi in rice based on electronic nose | |
Trigo-Stockli et al. | Effect of rice storage conditions on the quality of milled rice | |
Li et al. | Effects of modified atmosphere packaging with various sizes of silicon gum film window on the storage of Agrocybe chaxingu Huang and the modelling of its respiration rate | |
El-Kholy et al. | Performance analysis and quality evaluation of wheat storage in horizontal silo bags | |
CN110734866A (en) | active freeze-dried powder for preventing and treating loquat postharvest diseases and preparation method and application thereof | |
Şen et al. | Effects of CPPU and 1-MCP on the storage ability of'Hayward'kiwifruit | |
CN109393012A (en) | A kind of air regulating fresh-keeping method saved for fresh fruit | |
Park et al. | Storage Life of „Fuji‟ Apple Stored in the Controlled Atmosphere Container |
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 |