CN116360266A - Pig house temperature energy-saving control method based on multi-objective optimization algorithm - Google Patents
Pig house temperature energy-saving control method based on multi-objective optimization algorithm Download PDFInfo
- Publication number
- CN116360266A CN116360266A CN202310352933.6A CN202310352933A CN116360266A CN 116360266 A CN116360266 A CN 116360266A CN 202310352933 A CN202310352933 A CN 202310352933A CN 116360266 A CN116360266 A CN 116360266A
- Authority
- CN
- China
- Prior art keywords
- control
- temperature
- pig house
- period
- optimization
- 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.)
- Pending
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 provides a pig house temperature energy-saving control method based on a multi-objective optimization algorithm, which comprises the following steps: firstly, a CFD is adopted to establish a house internal temperature field response model under a pig house mechanical ventilation mode, and an elman neural network is combined to obtain a temperature field rapid prediction model. And dividing the time period to be regulated into a plurality of regulation subtime periods, acquiring average values of internal and external environmental factors in a house 5 minutes before the subtime period as input of a regulation model, aiming at controlling the minimum effect and energy consumption, constructing an adaptability evaluation function by using the neural network rapid prediction model, optimizing control parameters by using an improved INFO algorithm added with chaotic mapping and a self-adaptive t distribution strategy, and selecting an optimal solution from a non-inferior solution set by using a preference decision method based on energy consumption priority to control the subtime period. The method combines the numerical simulation and the Internet of things technology, and simultaneously carries out control parameter optimization through a multi-objective optimization algorithm, thereby being beneficial to saving energy consumption and improving benefits.
Description
Technical Field
The invention belongs to the field of agricultural cultivation, relates to a numerical simulation technology and an Internet of things technology, and particularly relates to a pig house temperature energy-saving control method based on a multi-objective optimization algorithm.
Background
The breeding environment is an important aspect affecting the growth of pigs and the economic benefit of production, wherein the temperature is most obviously affected, and in hot seasons, when the temperature in a pig house exceeds a comfortable area, the pigs can suffer from heat stress phenomena such as skin vasodilation, body temperature rise, heart rate acceleration and the like, and the heat stress can directly lead to the reduction of the feed intake of the pigs, so that the growth quality of the pigs is affected. The influence factors of the internal heat environment condition of the pig house are mainly the external climate of the house and the heat generated by pigs in the house, the high-temperature weather of China is mainly concentrated in 5-10 months, and ventilation and cooling operation is required to be carried out on the pig house according to the weather condition within a period of several months, so that the occurrence of high-temperature stress of pigs and epidemic diseases are prevented. Therefore, the temperature regulation and control of the pig house is very important for the growth of pigs, meanwhile, the temperature regulation and control work is a great expenditure for the production management of the pig house, the traditional constant value has a plurality of inconveniences, the temperature difference between the front end and the rear end of the pig house is overlarge due to overlarge set value, the uniformity is poor, and the energy consumption is overlarge; when the outdoor temperature is too low, the indoor temperature is too high, and the control error is too high. Therefore, the energy-saving optimal control of the temperature has important significance for healthy growth of pigs and improvement of industrial benefit.
The pigsty environment is poor, the sensor test is not easy to install and maintain, the sensor measurement mode is limited by the number of measurement points and the limitation of measurement range, and the overall environment trend is difficult to characterize. And the modeling method based on Computational Fluid Dynamics (CFD) can simulate the house environment under various working conditions by rapidly changing boundary conditions, valuable information can be obtained more easily, and the efficiency can be improved to a great extent. However, the traditional CFD model has slow calculation convergence and long time consumption, and is difficult to apply to actual control engineering, so the invention provides a CFD-neural network model, and the solving speed is greatly increased. Meanwhile, in the current agricultural production, the control of the environment is more biased to the control precision level, and the energy consumption of a control actuator is ignored, so that the development of facility agriculture in the direction of energy conservation and emission reduction is not facilitated. Therefore, it is quite significant to comprehensively consider the design of the control scheme with multiple targets such as control precision, control energy consumption and the like. In addition, the algorithm aiming at multi-objective optimization has the defects of low convergence speed, easiness in being trapped in local optimization and the like, and the invention aims at the defects and improves the used algorithm to a certain extent, so that the running time and the local optimization problem of the algorithm are reduced.
Disclosure of Invention
In order to solve the problems, the invention discloses a pig house temperature energy-saving control method based on a multi-objective optimization algorithm, and the control parameters of a control actuator can be calculated according to the environmental conditions before the start of a control period so as to ensure that the pig house environmental suitability and the actuator energy consumption under the control condition are simultaneously optimal.
In order to achieve the above purpose, the technical scheme of the invention is as follows:
a pig house temperature energy-saving control method based on a multi-objective optimization algorithm comprises the following steps:
step 1: establishing a response model of the temperature of the pig house in a wet curtain-fan ventilation mode through CFD, designing an experimental sample through a Latin hypercube sampling method, completing CFD simulation for a plurality of times, and forming a sample database between control conditions and temperature response;
step 2: training the database by using an elman neural network to obtain an approximate model of control conditions and temperature response;
step 3: taking the minimum of an index model of the pig house environment temperature control precision and an actuator control energy consumption model of the pig house for ventilation and cooling as an optimization target, and calculating an objective function result through a neural network model to serve as an adaptability function of a multi-objective optimization algorithm;
step 4: dividing the time of the pig house needing to be mechanically regulated into a plurality of regulating sub-periods, acquiring an environmental factor average value 5 minutes before the current regulating sub-period as an initial state input, then using an actuator control variable as a constraint, optimizing by using the fitness function in the step 3 through an improved INFO vector weighted average optimization algorithm,
step 5: selecting an optimal solution from a group of non-inferior solutions by adopting preferential selection of energy consumption, taking the optimal solution as an optimal control parameter to carry out actual regulation and control, and inputting the optimal solution into a control program of an actuator;
step 6: and judging whether the next optimization period is reached, if so, re-executing the step 4 to perform period optimization, thereby achieving the purpose of energy-saving control.
Further, the sample database in the step 1 is at the outdoor air temperature T out Wet curtain temperature T at air inlet w Curtain temperature T in Initial environmental temperature T of pig house 0 And under the control of variables such as the average weight M of pigs, the outlet wind speed V of the variable frequency fan and the like, the temperature values of a plurality of monitoring points in the pig house are obtained.
Further, the neural network model of step 2 obtains the T in the sample in step 1 in ，T 0 M and V are input, and the temperature response value t of the designated point of the temperature field i Training is carried out by using an elman neural network for output, and a quick response model of each point temperature under different control conditions is obtained.
Further, the control objective function of the step 4 is controlled by the control effect J 1 And energy consumption J 2 The control effect is divided into control accuracy and control uniformity, wherein the control accuracy is the difference between each observation point and the target value, and the control uniformity is the temperature difference between each observation point, so that the objective function is as follows:
Further, the step 4 performs optimizing operation by using an improved INFO algorithm, and includes the following steps:
step 41: according to the objective function, designing a multi-objective optimization model as follows:
wherein f (J) is an optimization target, the mode is the minimum solution fitness, T max ,T min Respectively the upper and lower limits of the spray water temperature, v max ,v min Variable frequency fan windUpper and lower speed limits;
step 42: determining the dimension of an optimizing variable, and adopting circle chaotic mapping to replace random initialization according to a constraint range to generate Np individuals, wherein Np is the population number;
step 43: for Np population individuals, calculating an objective function value f (J) corresponding to each individual of the primary population by utilizing an objective function formed by the neural network model in the step 2 1 ) And f (J) 2 )；
Step 44: according to each objective function value result of the individuals, non-dominant ranking and crowding degree calculation are carried out, and the individuals with the best performance and the worst individuals are selected according to the ranking result;
step 45: according to the flow of INFO algorithm, updating the position of vector by three steps of updating rule, vector combination and local search, completing search on solution space, introducing self-adaptive t distribution and dynamic selection strategy to increase disturbance, expanding local search capability, and introducing the method as follows: this is achieved by defining a dynamic selection probability p, where p is:
it is the current iteration number, maxIt is the maximum iteration number, and when p < rand, t distribution variation based on the iteration number is generated, and the position of the new vector is:
Temp＝New_X+New_X*trnd(j)
step 46: completing the current iteration to obtain a new offspring population, merging the new offspring population with a parent population, then re-ordering the offspring population, taking the previous Np individuals as the new generation population, judging whether the maximum number of iterations is reached, if not, enabling the iteration number to be +1, and cycling the step 3 until the iteration is ended, and if so, stopping cycling;
step 47: selecting a group with the smallest non-dominant ranking value as an optimal non-dominant solution set for the population obtained after the circulation is finished, and selecting the group with the smallest non-dominant ranking value as the optimal non-dominant solution set according to the preference principle in J 1 In the range of less than or equal to 1, is selected so that J 2 The smallest solution is taken as the global optimal solution, and the control efficiency is obtained in the optimization periodThe fruit index is not more than 1, and the optimal spray water temperature T of the wet curtain with minimum energy consumption is controlled wbest And the optimal fan wind speed v best The parameter is substituted into an actual control program, and control is performed in the present period.
Further, the regulation and control mode in the step 6 is that the whole regulation and control period is firstly divided into a plurality of sub-period optimization periods with equal duration, the environment initial value 5 minutes before the sub-period optimization period is firstly calculated, the environment initial value is substituted into a multi-objective optimization algorithm to perform optimization, finally, the control in the optimization period is performed according to the optimization decision, and the regulation and control in the whole period are continuously circulated until the regulation and control in the whole period are completed.
The invention has the beneficial effects that:
1. the INFO algorithm is utilized to carry out multi-objective optimization of pigsty environment control parameters, the defect that the traditional PID control is too pursued in precision can be overcome, the control parameters obtained by the method ensure the environment control effect, the control energy consumption of an actuator is reduced to the minimum, the effect of energy conservation and emission reduction is achieved, and simulation experiments show that compared with the original control strategy, the control strategy optimized by the multi-objective optimization algorithm can save at least 34% of energy consumption.
2. The intelligent optimization algorithm is easy to solve the problems of long searching time, local optimum trapping and the like, two improvements are made to the INFO algorithm in order to improve the operation speed of the algorithm, the improved algorithm can better perform global searching in the early stage, the local optimum can be better jumped out in the later stage, the searching speed is accelerated, the efficiency and instantaneity of the algorithm are enhanced, the non-dominant ordering thought is introduced, the Pareto solution set is obtained, and the defect that the distribution of weights in single-objective optimization is too subjective is overcome.
3. The time of regulating and controlling the subperiod is reasonably divided, so that the change of the self-adaptive external conditions of the environment regulation and control is realized, the defects that the excessive environmental factor of the regulation and control time is too large to predict and the regulation effect is lagged and cannot be represented due to too short regulation and control time are overcome, and meanwhile, compared with the constant value control, the control mode of rolling and optimizing in the subperiod can be used for more matching the change of the internal and external environments, the control effect is better, and the energy is saved.
Drawings
FIG. 1 is a schematic overall design flow diagram of the pig house environmental energy conservation control method of the present invention.
FIG. 2 is a flow chart of the construction of the CFD numerical simulation model of the pigsty environment.
FIG. 3 is a detailed flow chart of each module of the pig house environment energy-saving control method of the invention.
FIG. 4 is a flow chart of pig house temperature control according to the present invention.
Detailed Description
The present invention is further illustrated in the following drawings and detailed description, which are to be understood as being merely illustrative of the invention and not limiting the scope of the invention.
The invention provides a pig house temperature energy-saving control method based on a multi-objective optimization algorithm, and the control parameters of a control actuator can be designed according to the current environment condition of the pig house so that the pig house temperature control effect and the actuator energy consumption under the control condition can be simultaneously optimized.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a pig house temperature energy-saving control method based on a multi-objective optimization algorithm comprises the following steps:
step 1: according to pig house physical structure construction pig house three-dimensional model, carry out actual measurement to pig house structure at first, including pig house size, length, width, height, pig house size, window size, wet curtain-fan etc. executor mounted position, utilize com sol fluid simulation software to adopt cartesian coordinate system to carry out 1:1, building a physical model, dividing grids, determining boundary conditions of an entrance and a pig body, and calculating pig body heat according to the weight and the number of pigs. In the numerical simulation, a CFD model gas flow model is a standard k-epsilon model, a turbulence module and a fluid heat transfer module are coupled through speed, absolute pressure and temperature, numerical simulation calculation is realized by adopting a Reynolds average method, three-dimensional temperature field information in the pig house is obtained after the simulation is finished, and the accuracy of the model is continuously improved according to a measurement result.
Step 2: determining CFD modelsBoundary conditions in (a) including the outdoor air temperature T out Wet curtain temperature T at air inlet w Curtain temperature T in Initial environmental temperature T of pig house 0 Average weight M of pigs, number S of pigs in the housing, outlet wind speed V of variable frequency fan, wherein,
T in ＝T out -η(T out -T w ) (1)
and for T therein in ，T 0 And designing 50 groups of CFD experiments based on the tensile Ding Chao cubic sampling of four variables M and V, and completing multiple CFD experiments according to the four groups of CFD experiments to obtain database samples of the response of the temperature values under different control conditions.
Step 3: for the experimental sample obtained in the last step, T is adopted in ，T 0 The training set and the test set are divided according to 8:2, an elman neural network model is adopted for training, and the number of hidden layer nodes of the neural network directly influences the result of the model, so that the defects of hidden layer nodes are carried out according to the training effect of the training set, and the training method comprises the following steps:
hiddennum＝sqrt(m+n)+a (2)
and (3) taking m as the number of nodes of an input layer and n as the number of nodes of an output layer, taking an integer between 1 and 10, roughly determining the number of nodes of an hidden layer to be between 3 and 12, sequentially carrying out experiments by taking the target error of a training set as an evaluation index, selecting the hidden layer node with the minimum target error of the training set as the best hidden layer node, completing training, and obtaining other parameters including training times of 1000 times and learning rate of 0.01, wherein the model effect is judged according to Root Mean Square Error (RMSE), obtaining an approximate optimization model of the CFD model after completing training, wherein the calculation time of the model is greatly reduced, and the accuracy can be used for approximate replacement of the CFD model.
Step 4: determining an objective function J of a control process, calculating a temperature control target value in a pig living area according to national management standards of pig house raising environment and the density of the confined pigs, adopting a control index model for representing the environment in the pig house by using a control precision index and a control uniformity index, and selecting a pig living area levelSince the surface is calculated at a plurality of observation points, J 1 The method comprises the following steps:
wherein m is the number of temperature observation points, t i Is the output value of the temperature model of the observation point i, t target Is the temperature control target of the observation point i. Actuator control energy consumption model J for determining ventilation and cooling of pig house 2 ：
J 2 ＝∑γ k ×p k (4)
Wherein gamma is k For the execution motion amplitude, p, of the kth actuator k The standard unit energy consumption of the kth actuator is adopted, so that the optimization targets are as follows:
f(J)＝f(J 1 ,J 2 ) (5)
step 5: an INFO multi-objective optimization algorithm is operated, and the dimension of a variable is determined to be 2, namely the wet curtain spray water temperature T w And the wind speed v of the variable frequency fan, the variation range is T w ∈[22,27]，v∈[0,5]The number of the optimized objective functions is 2, namely J 1 And J 2 The multi-objective optimization model is:
in order to improve the operation speed of the algorithm and enhance the real-time performance, the INFO algorithm is improved as follows: the method comprises the following steps:
step 1: determining the dimension of an optimizing variable, and adopting circle chaotic mapping to replace random initialization according to a constraint range to generate Np individuals, wherein Np is the population number;
step 2: for Np population individuals, calculating an objective function value f (J) corresponding to each individual of the primary population by utilizing an objective function formed by the neural network model in the step 2 1 ) And f (J) 2 )；
Step 3: according to each objective function value result of the individuals, non-dominant ranking and crowding degree calculation are carried out, and the individuals with the best performance and the worst individuals are selected according to the ranking result;
step 4: according to the flow of INFO algorithm, updating the position of vector by three steps of updating rule, vector combination and local search, completing search on solution space, introducing self-adaptive t distribution and dynamic selection strategy to increase disturbance, expanding local search capability, and introducing the method as follows: this is achieved by defining a dynamic selection probability p, where p is:
it is the current iteration number, maxIt is the maximum iteration number, and when p < rand, t distribution variation based on the iteration number is generated, and the position variation formula is as follows:
Temp＝New_X+New_X*trnd(j) (8)
step 5: completing the current iteration to obtain a new offspring population, merging the new offspring population with a parent population, then re-ordering the offspring population, taking the previous Np individuals as the new generation population, judging whether the maximum number of iterations is reached, if not, enabling the iteration number to be +1, and cycling the step 3 until the iteration is ended, and if so, stopping cycling;
step 6: selecting a group with the smallest non-dominant ranking value as an optimal non-dominant solution set for the population obtained after the circulation is finished, and selecting the group with the smallest non-dominant ranking value as the optimal non-dominant solution set according to the preference principle in J 1 In the range of less than or equal to 1, is selected so that J 2 The minimum solution is used as a global optimal solution, and at the moment, the optimal spray water temperature T of the wet curtain with the minimum energy consumption is obtained in the period of optimizing so that the control effect index is not more than 1 wbest And the optimal fan wind speed v best The parameter is substituted into an actual control program, and control is performed in the present period.
Step 7: in the whole regulation and control period, the whole regulation and control period is firstly divided into a plurality of sub-period optimization periods with equal time length, the time length is determined according to the regulation effect, 25 minutes are taken from eight in the morning to eight in the evening as one regulation and control sub-period, the environment initial value of 5 minutes before the sub-period optimization period is firstly read, the environment initial value is substituted into a multi-objective optimization algorithm to carry out optimization, finally, the control in the optimization period is carried out according to the optimization decision, and the circulation is continued until the regulation and control in the whole period is completed.
The technical means disclosed by the scheme of the invention is not limited to the technical means disclosed by the embodiment, and also comprises the technical scheme formed by any combination of the technical features. It should be noted that modifications and adaptations to the invention may occur to one skilled in the art without departing from the principles of the present invention and are intended to be within the scope of the present invention.
Claims (7)
1. A pig house temperature energy-saving control method based on a multi-objective optimization algorithm is characterized by comprising the following steps of: the method comprises the following steps:
step 1: establishing a response model of the temperature of the pig house in a wet curtain-fan ventilation mode through CFD, designing an experimental sample through a Latin hypercube sampling method, completing CFD simulation for a plurality of times, and forming a sample database between different control conditions and temperature responses;
step 2: training the database by using an elman neural network to obtain an approximate model between a control condition and a temperature response, wherein the approximate model solves the problem of slow convergence of a CFD model and can be used for constructing an adaptability function in a subsequent multi-objective optimization algorithm;
step 3: taking the minimum pig house environment temperature control effect and the minimum actuator control energy consumption for mechanical ventilation and cooling as optimization objective functions, and calculating the fitness value of each objective function through the neural network model;
step 4: acquiring an environmental factor average value 5 minutes before a current regulation subperiod as an initial state input, then using an actuator control variable as a constraint, and optimizing by using an improved INFO algorithm according to the fitness function in the step 3;
step 5: selecting an optimal solution from a group of non-inferior solutions by adopting preferential selection of energy consumption, taking the optimal solution as an optimal control parameter to carry out actual regulation and control, and inputting the optimal solution into a control program of an actuator;
step 6: and judging whether the next optimization period is reached, if so, re-executing the step 5 to perform dynamic optimization, thereby achieving the purpose of energy-saving control.
2. The pig house temperature energy-saving control method based on the multi-objective optimization algorithm according to claim 1, wherein the method is characterized in that: the key parameters in the CFD model boundary conditions of the step 1 include the outdoor air temperature T out Wet curtain temperature T at air inlet w Curtain temperature T in Initial environmental temperature T of pig house 0 Average weight M of pigs, number S of pigs in the housing, and outlet wind speed V of variable-frequency fans.
3. The pig house temperature energy-saving control method based on the multi-objective optimization algorithm according to claim 2, wherein the method is characterized in that: the elman neural network input in the step 3 is T in the sample in the step 1 in ，T 0 M, V, output is the temperature response t of the designated point of the temperature field i 。
4. The pig house temperature energy-saving control method based on the multi-objective optimization algorithm according to claim 1, wherein the method is characterized in that: the objective function of the INFO algorithm of the step 3 is controlled by the control effect J 1 And energy consumption effect J 2 The control effect is divided into control accuracy, i.e., the difference between each observation point and the target value, and control uniformity, i.e., the temperature difference between each observation point, thus two objective function expressions J 1 ,J 2 The method comprises the following steps:
5. The pig house temperature energy-saving control method based on the multi-objective optimization algorithm according to claim 1, wherein the method is characterized in that: the INFO algorithm optimization model in the step 4 is as follows:
6. The pig house temperature energy-saving control method based on the multi-objective optimization algorithm according to claim 1, wherein the method is characterized in that: the improved INFO algorithm of step 4 comprises the following steps:
step 41: determining the dimension of an optimizing variable, and adopting circle chaotic mapping to replace random initialization according to a constraint range to generate Np individuals, wherein Np is the population number;
step 42: calculating objective function values of the first population by using objective functions formed by the neural network model in the step 2 for Np population individuals;
step 43: according to each objective function value result of the individuals, non-dominant ranking and crowding degree calculation are carried out, and the individuals with the best performance and the worst individuals are selected according to the ranking result;
step 44: according to the flow of INFO algorithm, updating the position of vector by three steps of updating rule, vector combination and local search, completing search on solution space, introducing self-adaptive t distribution and dynamic selection strategy to increase disturbance, expanding local search capability, and introducing the method as follows: this is achieved by defining a dynamic selection probability p, where p is:
it is the current iteration number, maxIt is the maximum iteration number, and when p < rand, t distribution variation based on the iteration number is generated, and the position of the new vector is:
Temp＝New_X+New_X*trnd(j)
step 45: completing the current iteration to obtain a new offspring population, merging the new offspring population with a parent population, then re-ordering the offspring population, taking the previous Np individuals as the new generation population, judging whether the maximum number of iterations is reached, if not, enabling the iteration number to be +1, and cycling the step 3 until the iteration is ended, and if so, stopping cycling;
step 46: selecting a group with the smallest non-dominant ranking value as an optimal non-dominant solution set for the population obtained after the circulation is finished, and selecting the group with the smallest non-dominant ranking value as the optimal non-dominant solution set according to the preference principle in J 1 In the range of less than or equal to 1, is selected so that J 2 The minimum solution is used as a global optimal solution, and at the moment, the optimal spray water temperature T of the wet curtain with the minimum energy consumption is obtained in the period of optimizing so that the control effect index is not more than 1 wbest And the optimal fan wind speed v best The parameter is substituted into an actual control program, and control is performed in the present period.
7. The pig house temperature energy-saving control method based on the multi-objective optimization algorithm according to claim 1, wherein the method is characterized in that: the regulation and control mode of the step 6 is that the whole regulation and control period is firstly divided into a plurality of sub-period optimization periods with equal duration, the environment initial value of 5 minutes before the sub-period optimization period is firstly calculated, the environment initial value is substituted into a multi-objective optimization algorithm to carry out optimization, and finally, the control in the optimization period is carried out according to the optimization decision, and the regulation and control in the whole period are continuously circulated until the regulation and control in the whole period are completed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310352933.6A CN116360266A (en) | 2023-04-04 | 2023-04-04 | Pig house temperature energy-saving control method based on multi-objective optimization algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310352933.6A CN116360266A (en) | 2023-04-04 | 2023-04-04 | Pig house temperature energy-saving control method based on multi-objective optimization algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116360266A true CN116360266A (en) | 2023-06-30 |
Family
ID=86915800
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310352933.6A Pending CN116360266A (en) | 2023-04-04 | 2023-04-04 | Pig house temperature energy-saving control method based on multi-objective optimization algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116360266A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118068687A (en) * | 2024-04-22 | 2024-05-24 | 山东欧菲特能源科技有限公司 | Refrigerator frequency converter control optimization method based on improved PID |
-
2023
- 2023-04-04 CN CN202310352933.6A patent/CN116360266A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118068687A (en) * | 2024-04-22 | 2024-05-24 | 山东欧菲特能源科技有限公司 | Refrigerator frequency converter control optimization method based on improved PID |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106920006B (en) | Subway station air conditioning system energy consumption prediction method based on ISOA-LSSVM | |
| Zhang et al. | Optimal design of building environment with hybrid genetic algorithm, artificial neural network, multivariate regression analysis and fuzzy logic controller | |
| CN112149209B (en) | Optimization method for multi-performance oriented design of building | |
| CN110805997A (en) | Energy-saving control method for central air-conditioning system | |
| CN114692265B (en) | Zero-carbon building optimization design method based on deep reinforcement learning | |
| CN104633856A (en) | Method for controlling artificial environment by combining CFD numerical simulation and BP neural network | |
| CN111291442A (en) | Passive energy-saving reverse design system and design method for high-rise residence | |
| CN114662201B (en) | Optimizing method for intelligent regulation and control of natural ventilation | |
| CN113283156A (en) | Subway station air conditioning system energy-saving control method based on deep reinforcement learning | |
| CN114200986B (en) | Greenhouse environment optimization design method considering crop production benefits and energy saving | |
| CN111881505A (en) | Multi-objective optimization transformation decision method for existing building based on GA-RBF algorithm | |
| CN114036861B (en) | Three-dimensional temperature field prediction method based on infoGAN | |
| CN116360266A (en) | Pig house temperature energy-saving control method based on multi-objective optimization algorithm | |
| CN115907191B (en) | Self-adaptive building photovoltaic epidermis model prediction control method | |
| CN113268913B (en) | Intelligent building air conditioner cooling machine system operation optimization method based on PSO-ELM algorithm | |
| CN114322199A (en) | Ventilation system autonomous optimization operation regulation and control platform and method based on digital twins | |
| CN115983438A (en) | Method and device for determining operation strategy of data center terminal air conditioning system | |
| CN116522795A (en) | Comprehensive energy system simulation method and system based on digital twin model | |
| CN113947261A (en) | Optimization decision support method for building energy conservation transformation | |
| CN108089443B (en) | Intelligent sensitive plate temperature modeling method based on mixed elite captivity optimization | |
| CN111597609B (en) | Basic operation unit containing solar radiation and building energy consumption rapid simulation method applying same | |
| CN113962819A (en) | Method for predicting dissolved oxygen in industrial aquaculture based on extreme learning machine | |
| CN105550437A (en) | Reverse design method for indoor environment based on genetic algorithm | |
| CN106803209A (en) | The crop of real-time data base and advanced control algorithm cultivates pattern analysis optimization method | |
| CN113188243B (en) | Comprehensive prediction method and system for air conditioner energy consumption |
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 |