CN114488811B - Greenhouse environment energy-saving control method based on second-order Woltai model prediction - Google Patents

Greenhouse environment energy-saving control method based on second-order Woltai model prediction Download PDF

Info

Publication number
CN114488811B
CN114488811B CN202210087874.XA CN202210087874A CN114488811B CN 114488811 B CN114488811 B CN 114488811B CN 202210087874 A CN202210087874 A CN 202210087874A CN 114488811 B CN114488811 B CN 114488811B
Authority
CN
China
Prior art keywords
order
model
truncated
control
greenhouse
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
Application number
CN202210087874.XA
Other languages
Chinese (zh)
Other versions
CN114488811A (en
Inventor
蔚瑞华
徐立鸿
蔡文韬
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tongji University
Original Assignee
Tongji University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Tongji University filed Critical Tongji University
Priority to CN202210087874.XA priority Critical patent/CN114488811B/en
Publication of CN114488811A publication Critical patent/CN114488811A/en
Application granted granted Critical
Publication of CN114488811B publication Critical patent/CN114488811B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
    • Y02A40/10—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture
    • Y02A40/25—Greenhouse technology, e.g. cooling systems therefor

Abstract

The invention relates to a greenhouse environment energy-saving control method based on second-order Woltai model prediction, which comprises the following steps: 1) Constructing a second-order Volterra greenhouse environment model, and carrying out model parameter identification by combining greenhouse historical environment data; 2) Constructing a loss function considering control target tracking error and energy consumption index, and taking the loss function as an objective function of the optimal problem; 3) The size of a weight factor in the loss function is adjusted according to actual requirements; 4) Optimizing the loss function in the feasible region of the actuator by adopting a traversal method, and obtaining the output value of the actuator meeting the requirement as the system input at the next moment. Compared with the prior art, the method has the characteristics of accurate environment prediction, good control effect and less energy consumption requirement, can effectively improve the economic benefit of greenhouse control of an automation part, has the advantages of high universality, high expansibility and the like, provides theoretical guidance and decision support for improving the greenhouse production benefit, and ensures the reliability and energy conservation of greenhouse environment control.

Description

Greenhouse environment energy-saving control method based on second-order Woltai model prediction
Technical Field
The invention relates to the technical field of agricultural facility environment control, in particular to a greenhouse environment energy-saving control method based on second-order Woltay model prediction.
Background
In the aspect of greenhouse control, a control technology (MPC) based on model prediction is often adopted in the current intelligent greenhouse, and compared with PID control only applicable to a single-loop stable system, the model prediction control can obtain a better control effect in multivariable system control, and is a control method commonly used in the current control field. For the acquisition of the prediction model, common modeling methods are: a mechanism modeling method and a data driving modeling method. The mechanism model has high accuracy and good interpretability, and has rich theoretical support, so the application is wide, but the model parameters are extremely large, the identification difficulty is extremely large, and the available prediction model is difficult to build in a short time; although the data-driven modeling modes such as a neural network model and a decision tree model can be efficiently modeled, the prediction effect is limited by the quality of a data set, and the machine learning method currently lacks of interpretability, so that the reliability of the machine learning method applied to prediction control is lower than that of the mechanism method.
In addition, most of model predictive control methods need to solve the optimal solution of the non-convex optimization problem to obtain an optimal control strategy, in order to prevent the non-convex optimization problem from being trapped in the local optimal solution, an evolutionary method is generally adopted to solve the problem, and the method needs to obtain the global optimal solution through a large amount of iterative computation, so that a series of problems of high computation cost, high program complexity and the like are brought.
Therefore, the current greenhouse development situation and actual production needs in China are met, and the problems widely existing in the existing predictive control method are considered, so that the novel greenhouse environment predictive control method which is good in control performance, convenient and fast in model establishment, low in calculation cost and easy to expand is required to be established with the aim of practicality and economic benefit.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a greenhouse environment energy-saving control method based on second-order Woltay model prediction, which is applied to the field of agricultural greenhouse environment control.
The aim of the invention can be achieved by the following technical scheme:
a greenhouse environment energy-saving control method based on second-order Woltai model prediction comprises the following steps:
1) Constructing a second-order Volterra greenhouse environment model, and carrying out model parameter identification by combining greenhouse historical environment data;
2) Constructing a loss function considering control target tracking error and energy consumption index, and taking the loss function as an objective function of the optimal problem;
3) The size of a weight factor in the loss function is adjusted according to actual requirements;
4) Optimizing the loss function in the feasible region of the actuator by adopting a traversal method, and obtaining the output value of the actuator meeting the requirement as the system input at the next moment.
In the step 1), the second-order volterra greenhouse environment model specifically adopts a multi-input single-output second-order volterra series, and the expression is as follows:
wherein y (k) is the model output at time k, namely the controlled variable of the system, h 0 For a fixed offset of the model, n u And n d Respectively represent the control variables u as model inputs m1 And disturbance d m2 And m1=1, …, n u ，m2＝1,…,n d ，Respectively the control variables u m1 And disturbance d m2 Is the order of the linear part and the nonlinear part, < >>Respectively the control variables u m1 And disturbance d m2 The weights of the linear and nonlinear parts are applied, i and j being the current iteration value of the linear and nonlinear applied cutoff order, respectively.
In the step 1), the parameter identification is carried out on the second-order Volterra greenhouse environment model by a least square method.
The specific process of parameter identification is as follows:
in the identification process of the first-order truncated orders, initializing the value of each truncated order to 1, uniformly taking the value of 0 by the second-order truncated orders at the moment, adopting a least square method, identifying to obtain a preliminary model parameter under the current condition, recording fitting errors, sequentially increasing the first-order truncated order value of each model input variable by 1, and identifying again by adopting the least square method, stopping iteration when the number of steps fitting errors under the truncated orders is smaller than the last error reduction of 5%, and taking the last identified truncated order as the final truncated order value of the model input variable;
after the first-order truncated orders are identified, the same method is applied to the second-order truncated orders, the previously identified first-order truncated orders are carried into the second-order truncated orders for calculation, and the truncated order value which enables the error between the model output value and the acquired data to be the smallest and enables the value of the truncated order to be the smallest can be identified by traversing the error of each truncated order;
after the first-order truncated order and the second-order truncated order of all the model input variables are determined, the weight of each model input variable is identified by adopting a least square method again, and a complete second-order Volterra greenhouse environment model is formed.
The model output is specifically the temperature or humidity of a greenhouse, the control variable is specifically the opening of an actuator, the actuator comprises a skylight, a sunshade net and a fan, and the disturbance is specifically the environmental state factor of the greenhouse and comprises outdoor temperature, sunlight and wind speed.
In the step 2), the expression of the loss function J is:
J＝(1-λ)(y(k+1|k)-r(k+1|k)) 2 +λ(Δu(k+1|k) 2 +u(k+1|k) 2 )
where r (k+ 1|k) is the set value of the controlled variable at k+1, λ is the weight factor used to balance the tracking error of the system and the variation of the controller, y (k+ 1|k) is the model output of the controlled variable at k+1, and Δu (k+ 1|k) is the control variable increment.
The calculation formula of the control variable increment Deltau (k+ 1|k) is as follows:
Δu(k+1|k)＝u(k+1|k)-u(k)
where u (k+ 1|k) and u (k) represent the actuator output values of the system at times k+1 and k, respectively.
In the step 3), the sensitivity of the control error and the energy consumption is adjusted by adjusting the weight factor in the loss function.
In the step 4), the loss function is used as an optimizing objective function, the control variable increment deltau (k+ 1|k) at the next moment is used as the variable to be solved, and the problem of optimizing the minimum value with constraint is formed, and then:
Δu * ＝argminJ(Δu(k+1|k),u(k+1|k))
wherein, the liquid crystal display device comprises a liquid crystal display device,Δu * for optimal control variable increment, u max And u min The maximum and minimum values of the feasible region range of the control variable, respectively.
Step 4) is executed every 5 minutes to solve the optimal control input value of the greenhouse environment at the current moment.
Compared with the prior art, the invention has the following advantages:
1. the model establishment cost is reasonable: compared with a pure mechanism model, the greenhouse environment model based on the second-order Woltay series has fewer parameters to be identified, can realize the fitting of data without using a parameter identification method with high time complexity, and has less time spent in the fitting process and relatively less time consumption for solving a prediction result compared with a machine learning method which is used for modeling data drive.
2. The method has strong interpretability: compared with a direct data-driven prediction method adopting machine learning, the control method based on the second-order Woltay series model takes the current values of the environmental disturbance action and the actuator as the input of the model, takes the environment variable as the output value of the model, and has a similar mathematical principle with a mechanism model, so that the prediction output of the second-order Woltay series model has stronger interpretability for the machine learning method and higher credibility in actual control.
3. The control method has good economic benefit: compared with the existing greenhouse environment control method, the method disclosed by the invention has the advantages that the energy consumption is also used as a comprehensive consideration index, the overall economic benefit of the greenhouse can be improved by reducing the energy consumption of the actuator on the premise of ensuring the controllable greenhouse environment, and an adjustable weight factor is provided, so that a user can adjust the emphasis of the method on controlling errors and optimizing the energy consumption according to actual demands.
4. The universality and the expansibility are strong: the method is simple in principle, easy to program and modify, capable of working as an independent control method and capable of being integrated into the existing control method as a plug-in unit to realize function expansion, and has certain universality.
Drawings
FIG. 1 is a schematic flow diagram of the method of the present invention.
FIG. 2 is a graph showing the effect of a second order Volterra series model on the fitting of the greenhouse ambient temperature.
Detailed Description
The technical solutions in the technical embodiments of the present invention will be described in detail, clearly and completely with reference to the accompanying drawings in the embodiments of the present invention.
Examples
As shown in fig. 1, the invention provides a greenhouse environment energy-saving control method based on second-order volterra model prediction, which comprises the following steps:
s1: according to a general expression of the second-order Volterra series, combining with greenhouse historical environment data, utilizing a least square method to identify the truncated order and coefficient of each parameter of the Volterra series, and establishing a second-order Volterra greenhouse environment model;
s2: constructing a loss function which simultaneously takes the tracking error of the control target and the energy consumption index into consideration, and adopting a weight factor to adjust the balance of the error and the energy consumption as an objective function of the optimal problem;
s3: according to actual demands, the magnitude of a weight factor in the loss function is adjusted, so that the control method is adjusted in the control styles of 'aggressive' and 'smooth';
s4: and optimizing the loss function within the feasible domain range of the controller by adopting a traversing method every 5 minutes, and obtaining the output value of the controller or the actuator meeting the requirements as the system input of the next moment.
In step S1, a general expression of a second-order Volterra series is written, and the weight coefficients of all parameters in the Volterra series are identified, specifically comprising the following steps:
s101: according to the basic mathematical form of the second-order volterra series model, the expression of the second-order volterra series for the multiple-input single-output form is:
wherein y (k) is the model output at time k, h 0 For a fixed offset of the model, n u And n d Respectively represent the control variables u as model inputs m1 And disturbance d m2 And m1=1, …, n u ，m2＝1,…,n d ，Respectively the control variables u m1 And disturbance d m2 Is the order of the linear part and the nonlinear part, < >>Respectively the control variables u m1 And disturbance d m2 The invention takes greenhouse environment parameters (such as temperature and humidity) as model output, takes opening information of an actuator as model input, and takes environment state factor information as disturbance.
S102: in order to obtain the truncated order and the weight coefficient of each variable of the second-order volterra series, system identification is needed, in the identification process of the first-order truncated order, the value of each truncated order is initialized to be a smaller value (1 is taken in the invention, the second-order truncated order is uniformly taken as 0), a least square method is used for identifying a preliminary model parameter under the current condition, fitting errors are recorded, then the first-order truncated order value of each variable is sequentially increased by 1, the least square method is used for identification again, iteration is stopped when the number of the truncated order is smaller than the last error reduction amount by 5%, the last-identified truncated order is taken as the final truncated order value of the variable, and after the first-order truncated order is identified, the same method is applied to the second-order truncated order, but the first-order truncated order which is identified previously is required to be brought into calculation, the error under each truncated order is obtained through the method, and the output error and the smaller-order truncated order value of the variable can be acquired through the model.
After the first-order and second-order cutoff orders of all the variables are determined, the weights of all the variables are identified again by using a least square method, and a complete second-order Volterra greenhouse environment model is formed.
Fig. 2 shows a fitting result of the above identification steps on experimental greenhouse data (wherein the model output is indoor temperature, the actuator is a skylight and a fan, and disturbance factors are outdoor temperature, sun light and wind speed), so that it can be seen that the second-order volterra series model can be used for fitting greenhouse environment data more accurately, and the model prediction control capability is provided for the subsequent model prediction control.
In step S2, in order to simultaneously consider the control tracking error and the energy consumption of the system, the loss function of the control method is defined as follows:
J＝(1-λ)(y(k+1|k)-r(k+1|k)) 2 +λ(Δu(k+1|k) 2 +u(k+1|k) 2 )
where r (k+ 1|k) represents a set value of a controlled variable (indoor temperature or humidity) at a time t=k+1, λ is a weight factor for balancing tracking errors of the system and a variation of the controller, an emphasis point of the method between control accuracy and energy consumption optimization can be adjusted by adjusting the value, and Δu (k+ 1|k) represents a control variable increment, and a specific calculation mode thereof can be defined by the following formula:
Δu(k+1|k)＝k(k+1|k)-u(k)
where u (k+ 1|k) and u (k) represent actuator output values of the system at times t=k+1 and t=k, respectively.
Because the energy consumption calculation modes of the actuators in the actual greenhouse are different, the energy consumption of part of the actuators is from the change of the state (such as a skylight and a sunshade net), the energy consumption of part of the actuators is from the continuous state (such as a fan), and the increment or the output value of the controller is respectively brought into calculation according to the attribute of the actuators in the actual calculation.
In the step S3, the sensitivity of the method to control errors and energy consumption can be adjusted by adjusting the weight factor lambda in the step S2 so as to adjust the method according to actual demands;
in step S4, the loss function in step S2 is used as an optimizing objective function, and the control variable increment (actuator output change value) Δu (k+ 1|k) at the next moment is used as a to-be-solved variable, so as to form a constraint minimum value optimizing problem:
Δu * ＝argminJ(Δu(k+1|k),u(k+1|k))
the greenhouse environment output in the loss function, i.e., the y (k+ 1|k) term, can be obtained by taking k (k+ 1|k) =Δu (k+ 1|k) +k (k) into the second-order volterra series model obtained in the previous step.
Because the number of the actuators is limited in actual greenhouse control, and the two-state actuators only have 2 states, the searching range is greatly reduced, and compared with the conventional optimizing method, the traversing method has the advantages. Therefore, the optimization problem is solved by adopting a traversal method in practical application, and the tri-state actuator needs to be subjected to step processing in advance (as the greenhouse applied by the invention divides the skylight opening into 6 steps of 0%,20%,40%,60%,80% and 100%). And then, carrying out value taking on each actuator in a feasible domain to form a series of control strategies, and carrying out calculation in the loss function to obtain the control strategy for minimizing the output value of the loss function.
In the following process, step S4 will be performed every 5 minutes to solve the greenhouse environment optimum control input value at the present moment.
When the weight coefficient of the loss function is 0.15, the control method provided by the invention has the advantages that the indoor temperature exceeds the upper limit of the temperature, the movement amplitude and the frequency of the skylight are within the acceptable range, the balance between the control error and the energy consumption of the control model is realized, and a better control effect is obtained.

Claims (5)

1. The greenhouse environment energy-saving control method based on the second-order Woltai model prediction is characterized by comprising the following steps of:
1) Constructing a second-order Volterra greenhouse environment model, and carrying out model parameter identification by combining greenhouse historical environment data;
2) Constructing a loss function considering control target tracking error and energy consumption index, and taking the loss function as an objective function of the optimal problem;
3) The size of a weight factor in the loss function is adjusted according to actual requirements;
4) Optimizing the loss function in the feasible region of the actuator by adopting a traversal method, and obtaining the output value of the actuator meeting the requirement as the system input at the next moment;
in the step 1), the second-order volterra greenhouse environment model specifically adopts a multi-input single-output second-order volterra series, and the expression is as follows:
wherein y (k) is the model output at time k, namely the controlled variable of the system, h 0 For a fixed offset of the model, n u And n d Respectively represent the control variables u as model inputs m1 And disturbance d m2 And m1=1, …, n u ，m2＝1,…,n d ，Respectively the control variables u m1 And disturbance d m2 Is the order of the linear part and the nonlinear part, < >>Respectively the control variables u m1 And disturbance d m2 The weights of the linear and nonlinear parts are acted, i and j are the current iteration values of the linear and nonlinear action cut-off orders respectively;
in the step 1), the parameter identification is carried out on the second-order Volterra greenhouse environment model by a least square method;
the specific process of parameter identification is as follows:
in the identification process of the first-order truncated orders, initializing the value of each truncated order to 1, uniformly taking the value of 0 by the second-order truncated orders at the moment, adopting a least square method, identifying to obtain a preliminary model parameter under the current condition, recording fitting errors, sequentially increasing the first-order truncated order value of each model input variable by 1, and identifying again by adopting the least square method, stopping iteration when the number of steps fitting errors under the truncated orders is smaller than the last error reduction of 5%, and taking the last identified truncated order as the final truncated order value of the model input variable;
after the first-order truncated orders are identified, the same method is applied to the second-order truncated orders, the previously identified first-order truncated orders are carried into the second-order truncated orders for calculation, and the truncated order value which enables the error between the model output value and the acquired data to be the smallest and enables the value of the truncated order to be the smallest can be identified by traversing the error of each truncated order;
after the first-order truncated order and the second-order truncated order of all the model input variables are determined, the weight of each model input variable is identified by adopting a least square method again, and a complete second-order Volterra greenhouse environment model is formed;
in the step 2), the expression of the loss function J is:
J＝(1-λ)(y(k+1|k)-r(k+1|k)) 2 +λ(Δu(k+1|k) 2 +u(k+1|k) 2 )
wherein r (k+ 1|k) is a set value of a controlled variable at k+1, lambda is a weight factor for balancing tracking errors of a system and variation of a controller, y (k+ 1|k) is model output of the controlled variable at k+1, and Deltau (k+ 1|k) is a control variable increment;
in the step 4), the loss function is used as an optimizing objective function, the control variable increment deltau (k+ 1|k) at the next moment is used as the variable to be solved, and the problem of optimizing the minimum value with constraint is formed, and then:
wherein Deltau * For optimal control variable increment, u max And u min The maximum and minimum values of the feasible region range of the control variable, respectively.
2. The greenhouse environment energy-saving control method based on the second-order Woltay model prediction according to claim 1, wherein the model output is specifically temperature or humidity of a greenhouse, the control variable is specifically opening degree of an actuator, the actuator comprises a skylight, a sunshade net and a fan, and the disturbance is specifically greenhouse environment state factors including outdoor temperature, sunlight and wind speed.
3. The greenhouse environment energy-saving control method based on the second-order Woltay model prediction according to claim 1, wherein the calculation formula of the control variable increment Deltau (k+ 1|k) is as follows:
Δu(k+1|k)＝u(k+1|k)-u(k)
where u (k+ 1|k) and u (k) represent the actuator output values of the system at times k+1 and k, respectively.
4. The greenhouse environment energy-saving control method based on the second-order volterra model prediction according to claim 1, wherein in the step 3), the sensitivity of the control error and the energy consumption is adjusted by adjusting the weight factor in the loss function.
5. The greenhouse environment energy-saving control method based on the second-order Woltai model prediction according to claim 1, wherein the step 4) is performed every 5 minutes to solve the optimal control input value of the greenhouse environment at the current moment.
CN202210087874.XA 2022-01-25 2022-01-25 Greenhouse environment energy-saving control method based on second-order Woltai model prediction Active CN114488811B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210087874.XA CN114488811B (en) 2022-01-25 2022-01-25 Greenhouse environment energy-saving control method based on second-order Woltai model prediction

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210087874.XA CN114488811B (en) 2022-01-25 2022-01-25 Greenhouse environment energy-saving control method based on second-order Woltai model prediction

Publications (2)

Publication Number Publication Date
CN114488811A CN114488811A (en) 2022-05-13
CN114488811B true CN114488811B (en) 2023-08-29

Family

ID=81474813

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210087874.XA Active CN114488811B (en) 2022-01-25 2022-01-25 Greenhouse environment energy-saving control method based on second-order Woltai model prediction

Country Status (1)

Country Link
CN (1) CN114488811B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114996824B (en) * 2022-07-05 2023-05-19 广州高新工程顾问有限公司 BIM-based green building interior decoration design and dynamic optimization method

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111365828A (en) * 2020-03-06 2020-07-03 上海外高桥万国数据科技发展有限公司 Model prediction control method for realizing energy-saving temperature control of data center by combining machine learning
CN113112077A (en) * 2021-04-14 2021-07-13 太原理工大学 HVAC control system based on multi-step prediction deep reinforcement learning algorithm

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11966670B2 (en) * 2018-09-06 2024-04-23 Terrafuse, Inc. Method and system for predicting wildfire hazard and spread at multiple time scales
KR20210023603A (en) * 2019-08-23 2021-03-04 엘지전자 주식회사 A device for generating a temperature prediction model and a method for providing a simulation environment

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111365828A (en) * 2020-03-06 2020-07-03 上海外高桥万国数据科技发展有限公司 Model prediction control method for realizing energy-saving temperature control of data center by combining machine learning
CN113112077A (en) * 2021-04-14 2021-07-13 太原理工大学 HVAC control system based on multi-step prediction deep reinforcement learning algorithm

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
面向控制的温室系统小气候环境模型要求与现状;徐立鸿;苏远平;梁毓明;;农业工程学报(19);全文 *

Also Published As

Publication number Publication date
CN114488811A (en) 2022-05-13

Similar Documents

Publication Publication Date Title
CN107966902B (en) Constraint 2D tracking control method for uncertain intermittent process
US20210341895A1 (en) Pid controller autotuner using machine learning approaches
CN114488811B (en) Greenhouse environment energy-saving control method based on second-order Woltai model prediction
Pal et al. Self-tuning fuzzy PI controller and its application to HVAC systems
Yue et al. The prediction of greenhouse temperature and humidity based on LM-RBF network
CN114036813A (en) Greenhouse temperature and humidity method controlled by particle swarm BP neural network PID
Siddiqui et al. Sliding mode controller design for second-order unstable processes with dead-time
Garcia-Manas et al. Experimental evaluation of feedforward tuning rules
KR101576004B1 (en) Boiler-Turbine coordinated control method and apparatus using Dynamic matrix control in thermal power plant
Manna et al. A novel MRAC-MPPT scheme to enhance speed and accuracy in PV systems
CN116526473A (en) Particle swarm optimization LSTM-based electrothermal load prediction method
CN103941782A (en) Advanced temperature and humidity control method applied to greenhouse
CN102156407A (en) Predictive control method and device for ARM (advanced RISC machines)-based embedded type model
CN112180733B (en) Fuzzy logic-based building energy consumption system prediction control parameter setting method
CN116449897B (en) Greenhouse environment optimal control method, server and system
KR20200057836A (en) Apparatus and Method for Controlling Multiple windows in a greenhouse
CN103592844A (en) Incremental PI parameter time varying intelligent optimal control
CN108333947B (en) Single-integer-coefficient prediction function control parameter setting method based on intelligent optimization
CN115236969A (en) PID parameter optimization method by particle swarm algorithm
CN109039166B (en) Method for self-correcting speed loop PI-IP control parameter of permanent magnet synchronous linear servo system
CN113641101A (en) Multi-channel pool control parameter optimization algorithm based on numerical simulation
Thatipamala et al. On-line state estimation and adaptive optimization using state equations for continuous production of bioethanol
CN116149262B (en) Tracking control method and system of servo system
El Aoud et al. Self-tuning method of fuzzy system: An application on greenhouse process
Proell et al. Comparison of different optimization and control schemes in an industrial scale microalgae fermentation

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