Greenhouse environment intelligent regulation and control system based on internet of things

Abstract

The application discloses a greenhouse environment intelligent regulation and control system based on Internet of Things, and relates to the technical field of intelligent regulation and control, comprising a construction module and a regulation and control module, a mapping relationship is constructed according to historical greenhouse data and a heat balance equation, a regulation and control moment corresponding to a regulation and control parameter is adjusted according to a fuzzy PID algorithm, and a first regulation and control instruction is sent. The application introduces the heat balance equation to construct a nonlinear mapping model between crop parameters and environment regulation and control parameters, improves the prediction and regulation and control precision of the system on key environment variables such as temperature and humidity, predicts the future optimal regulation and control moment and parameters through historical data and the heat balance model, realizes early intervention, avoids the hysteresis of traditional feedback control, effectively maintains the dynamic stability of the crop growth environment, and through accurate prediction and time-sharing regulation and control, the system can avoid excessive heating, invalid irrigation and other energy consumption behaviors.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology, and in particular to an intelligent control system for greenhouse environment based on the Internet of Things. Background Technology

[0002] In recent years, with the continuous advancement of microcomputer technology, the application of modern measurement and control technology, wireless network technology, remote telemetry technology, and expert system technology in greenhouse control and management has improved the sophistication of greenhouse control systems. New control ideas and algorithms have been used to improve the control of greenhouse systems. The integrated greenhouse environmental control system with computer technology at its core has realized the intelligentization and networking of greenhouse environmental regulation technology.

[0003] Currently, Chinese invention patent CN120447347A discloses a method for controlling the environment of vegetable and fruit greenhouse cultivation based on intelligent regulation. This method obtains the data deviation of each type of sensor in each control device by measuring the range of data changes of each type of sensor at all changing times, and presets several combinations of adjustment parameters. It then obtains the adjusted PID output value of each control device under each combination of adjustment parameters, and obtains the degree of regulation optimization for each combination of adjustment parameters based on the adjusted PID output value, data deviation, and improved environmental influence coefficient. Based on the degree of regulation optimization, the control devices in the greenhouse are regulated. However, the related technology establishes a rapid mapping relationship, which enables rapid regulation of parameters that are not easily known based on easily known parameters. This is not conducive to the simplification and economy of sensor deployment, nor to the speed of environmental regulation. It does not consider the time delay of parameter regulation, which is not conducive to the accuracy and timeliness of environmental regulation, and has certain limitations. Summary of the Invention

[0004] The technical problem solved by this invention is that the establishment of a rapid mapping relationship in related technologies, which enables rapid adjustment of parameters that are not easily known based on easily known parameters, is not conducive to the simplification and economy of sensor deployment, nor is it conducive to the speed of environmental control. It does not take into account the time delay of parameter control, which is not conducive to the accuracy and timeliness of environmental control, and has certain limitations.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution: an intelligent control system for greenhouse environment based on the Internet of Things, comprising a construction module and a control module; The module constructs a mapping relationship between crop parameters and control parameters based on historical greenhouse data and heat balance equations, and tunes the control time corresponding to the control parameters according to the fuzzy PID algorithm. The control module sends a first control instruction based on the current crop parameters. The first control instruction includes the control parameters at the predicted time and the control time corresponding to the control parameters at the predicted time.

[0006] As a preferred embodiment of the IoT-based intelligent control system for greenhouse environment described in this invention, the construction module retrieves historical greenhouse data, which includes historical greenhouse internal temperature, historical energy generated by artificial light sources, historical energy generated by humidifiers, historical energy generated by dehumidifiers, historical energy generated by air conditioners, historical fresh air input energy or historical fresh air exhaust energy, historical crop density, historical constant pressure specific heat capacity inside the greenhouse, historical warm air volumetric flow rate, historical cold air volumetric flow rate generated by air conditioners, historical humidifier air volume, historical dehumidifier air volume, historical crop type, and historical crop growth stage.

[0007] As a preferred embodiment of the intelligent control system for greenhouse environment based on the Internet of Things described in this invention, the first historical time period is set as the monitoring cycle, and within the monitoring cycle, the temperature expression is obtained based on historical greenhouse data and the heat balance equation. Based on the temperature expression, a dynamic curve of temperature change over time is obtained. This dynamic curve is set as the reference temperature curve, with the horizontal axis of the reference temperature curve representing the acquisition time and its corresponding acquisition number. The monitoring time period corresponding to the reference temperature curve is set as the reference time period. Jump to other monitoring time periods. Jumping means random jumping. Other monitoring time periods have the same number of data collections as the monitoring time period, and the data collection times corresponding to other monitoring time periods are different from those of the monitoring time period. In addition, each monitoring time period is a common factor of the number of minutes corresponding to a unit of day.

[0008] As a preferred embodiment of the IoT-based intelligent greenhouse environment control system described in this invention, the system acquires historical warm air volumetric flow rate, historical air conditioning cold air volumetric flow rate, historical humidifier air volume, historical dehumidifier air volume, and historical artificial light source energy at each collection moment within the monitoring period. It also acquires the average temperature inside the greenhouse at the corresponding moment. Based on these historical data, a temperature curve is fitted. The vertical coordinate values ​​of the temperature curve and the reference temperature curve at the same collection number are subtracted to obtain a time series of the difference. The average value of the time series of the difference is calculated and denoted as the first average value. The first average value represents the temperature deviation between the monitoring period and the previous monitoring period.

[0009] As a preferred embodiment of the intelligent control system for greenhouse environment based on the Internet of Things described in this invention, any monitoring time period is selected, the midpoint of the monitoring time period is selected, and the time difference between the midpoints of any two monitoring time periods is calculated and recorded as the time interval. Iterate through the temperature deviations corresponding to each monitoring time period; Select any monitoring time period other than the reference time period, calculate the time interval between this time period and the reference time point, and use the time interval, the historical warm air volume flow rate, the historical air conditioning cold air volume flow rate, the historical humidifier air volume, the historical dehumidifier air volume, the historical artificial light energy, the historical crop density, the historical crop type, and the historical crop growth stage as independent variables. Iterate through the average temperature inside the greenhouse at each moment within the monitoring time period, calculate the average value of the greenhouse average temperature, and use the average value of the greenhouse average temperature as the dependent variable to perform multiple regression analysis and obtain the multiple regression equation.

[0010] As a preferred embodiment of the IoT-based intelligent control system for greenhouse environment described in this invention, the crop parameters include crop density, crop type, and crop growth stage. The control parameters include the fourth difference corresponding to the volumetric flow rate of warm air, the fourth difference corresponding to the volumetric flow rate of cold air generated by the air conditioner, the fourth difference corresponding to the air volume of the humidifier, the fourth difference corresponding to the air volume of the dehumidifier, and the fourth difference corresponding to the energy generated by the artificial light source.

[0011] As a preferred embodiment of the intelligent control system for greenhouse environment based on the Internet of Things described in this invention, the logic for constructing the mapping relationship between crop parameters and control parameters includes: selecting any time interval, retrieving the multivariate regression equation corresponding to that time interval, inputting the current crop parameters, the current warm air volume flow rate, the current air conditioning cold air volume flow rate, the current humidifier air volume, the current dehumidifier air volume, and the current artificial light source energy into the multivariate regression equation, and obtaining the average value of the average temperature inside the greenhouse corresponding to the multivariate regression equation, which is recorded as the theoretical temperature value; Obtain the monitoring time period corresponding to the time interval, obtain the historical average temperature inside the greenhouse before the current time period, and calculate the average value of the historical average temperature inside the greenhouse, which is recorded as the actual temperature value. The system continuously adjusts the current volumetric flow rate of warm air, the current volumetric flow rate of cold air generated by the air conditioner, the current air volume of the humidifier, the current air volume of the dehumidifier, and the current energy generated by the artificial light source until the dependent variable value of the multiple regression equation corresponding to the adjusted current volumetric flow rate of warm air, the current volumetric flow rate of cold air generated by the air conditioner, the current air volume of the humidifier, the current air volume of the dehumidifier, and the current energy generated by the artificial light source equals the theoretical temperature value, at which point the continuous adjustment stops.

[0012] As a preferred embodiment of the intelligent control system for greenhouse environment based on the Internet of Things described in this invention, the system acquires the current volumetric flow rate of warm air, the current volumetric flow rate of cold air generated by the air conditioner, the current air volume of the humidifier, the current air volume of the dehumidifier, and the current energy generated by the artificial light source. Calculate the fourth difference between the current warm air volume flow rate, the current air conditioning cold air volume flow rate, the current humidifier air volume, the current dehumidifier air volume, and the current artificial light source energy and their corresponding initial values ​​after adjustment, and set the fourth difference as the corresponding adjustment parameter; Obtain the time interval and sampling number corresponding to the current moment, and construct a mapping relationship between crop parameters, time interval, sampling number and control parameters.

[0013] As a preferred embodiment of the IoT-based intelligent greenhouse environment control system described in this invention, the logic for adjusting the control time corresponding to the control parameters includes: obtaining the current actual temperature value and setting a fuzzy rule for the current actual temperature value. The logic for formulating the fuzzy rule includes: Plot the curve of the current actual temperature value, calculate the difference between two adjacent points of the current actual temperature value curve and the rate of change of the difference between two adjacent points of the current actual temperature value, and convert the difference between two adjacent points of the current actual temperature value curve and the rate of change of the difference between two adjacent points of the current actual temperature value curve into fuzzy values ​​E and EC. The membership degrees of E and EC in each fuzzy subset are calculated separately, and the membership degrees are obtained by calculating the membership degree function. Set the fuzzy universe of discourse for the output quantities kp, ki, and kd to be between the threshold of the first universe of discourse and the threshold of the second universe of discourse. Set kp as the proportional coefficient, ki as the integral coefficient, and kd as the differential coefficient. Set the fuzzy subsets to negative large, negative medium, negative small, zero, positive small, positive medium, and positive large; The values ​​of kp, ki, and kd are set based on the difference between two adjacent points on the current actual temperature curve and the rate of change of the difference between two adjacent points on the current actual temperature curve, and a control model for the current actual temperature value is constructed. The current actual temperature value curve is subjected to fuzzy control, and the coefficients of the fuzzy rules are updated according to the particle swarm algorithm.

[0014] As a preferred embodiment of the IoT-based intelligent control system for greenhouse environments described in this invention, the control module acquires current crop parameters and predicted time, assigns the predicted time to the corresponding monitoring time period, calculates the time difference between the acquisition time and the predicted time within any monitoring time period, selects the acquisition time with the smallest time difference, acquires the acquisition sequence number corresponding to the acquisition time with the smallest time difference, matches the predicted time interval corresponding to the monitoring time period, retrieves the mapping relationship based on the predicted time interval, predicted crop parameters, and acquisition sequence number, inputs the predicted time interval, predicted crop parameters, and acquisition sequence number into the mapping relationship, matches the predicted control parameters corresponding to the predicted time interval, predicted crop parameters, and acquisition sequence number, and sends a first control command based on the predicted control parameters. The first control command includes the predicted control parameters and their corresponding control time.

[0015] The beneficial effects of this invention are as follows: Control parameters are adjusted in real time according to crop growth stages and external climate fluctuations, significantly reducing system overshoot. A heat balance equation is introduced to construct a nonlinear mapping model between crop parameters and environmental control parameters, effectively overcoming the problems of large inertia and lag in greenhouse systems. This improves the system's accuracy in predicting and controlling key environmental variables such as temperature and humidity. Fuzzy logic can handle uncertainties such as sensor noise and external disturbances, ensuring stable operation even under human interference or sudden environmental changes, significantly enhancing the system's anti-interference capability and robustness. By predicting the optimal control time and parameters in the future using historical data and the heat balance model, early intervention is achieved, avoiding the lag of traditional feedback control and effectively maintaining the dynamic stability of the crop growth environment. Through precise prediction and time-sharing control, the system can avoid energy-consuming behaviors such as overheating and ineffective irrigation. Attached Figure Description

[0016] Figure 1 This is a basic flowchart of an intelligent control system for greenhouse environment based on the Internet of Things, provided as an embodiment of the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0018] It should be understood that the step numbers used herein are for ease of description only and are not intended to limit the order in which the steps are performed. It should also be understood that the terminology used in this specification is for the purpose of describing specific embodiments only and is not intended to limit the invention.

[0019] As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0020] The terms "comprising" and "including" indicate the presence of the described feature, whole, step, operation, element, and / or component, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or collections thereof. The term “and / or” refers to any combination of one or more of the associated listed items, as well as all possible combinations, and includes these combinations.

[0021] With the continuous advancement of microcomputer technology, the application of modern measurement and control technology, wireless network technology, remote telemetry technology, and expert system technology in greenhouse control and management has improved the sophistication of greenhouse control systems. New control concepts and algorithms have been used to improve greenhouse system control. The integrated greenhouse environmental control system, with computer technology at its core, has realized the intelligentization and networking of greenhouse environmental regulation technology.

[0022] Based on this, the embodiments of this application provide an intelligent control system for greenhouse environment based on the Internet of Things.

[0023] This application provides an intelligent control system for greenhouse environment based on the Internet of Things (IoT), which is specifically described through the following embodiments. First, an intelligent control system for greenhouse environment based on the Internet of Things (IoT) is described in this application embodiment.

[0024] This application provides an IoT-based intelligent greenhouse environment control system, relating to the field of intelligent control. This IoT-based intelligent greenhouse environment control system can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, etc.; the server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application implementing an IoT-based intelligent greenhouse environment control system, but is not limited to the above forms.

[0025] This application can also be used in numerous general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0026] Example, refer to Figure 1 As an embodiment of the present invention, an intelligent control system for greenhouse environment based on the Internet of Things is provided, including a construction module and a control module; The module constructs a mapping relationship between crop parameters and control parameters based on historical greenhouse data and heat balance equations, and tunes the control time corresponding to the control parameters according to the fuzzy PID algorithm. The control module sends a first control instruction based on the current crop parameters. The first control instruction includes the control parameters at the predicted time and the control time corresponding to the control parameters at the predicted time.

[0027] More preferably, the control parameters are adjusted in real time according to the crop growth stage and external climate fluctuations, significantly reducing system overshoot. A nonlinear mapping model between crop parameters and environmental control parameters is constructed by introducing a heat balance equation, effectively overcoming the problems of large inertia and large lag in greenhouse systems, and improving the system's prediction and control accuracy for key environmental variables such as temperature and humidity. Fuzzy logic can handle uncertainties such as sensor noise and external disturbances, enabling the system to maintain stable operation under human interference or sudden environmental changes, significantly improving the system's anti-interference ability and robustness. By predicting the optimal control time and parameters in the future through historical data and heat balance model, early intervention is achieved, avoiding the lag of traditional feedback control, and effectively maintaining the dynamic stability of the crop growth environment. Through accurate prediction and time-sharing control, the system can avoid energy-consuming behaviors such as overheating and ineffective irrigation.

[0028] The module retrieves historical greenhouse data, including historical greenhouse internal temperature, historical energy generated by artificial light sources, historical energy generated by humidifiers, historical energy generated by dehumidifiers, historical energy generated by air conditioning, historical fresh air input energy or historical fresh air exhaust energy, historical crop density, historical specific heat capacity under constant pressure inside the greenhouse, historical volumetric flow rate of warm air, historical volumetric flow rate of cold air generated by air conditioning, historical air volume of humidifiers, historical air volume of dehumidifiers, historical crop types, and historical crop growth stages.

[0029] More preferably, the historical crop growth stages include the germination period, seedling period, flowering period, and fruiting period.

[0030] More preferably, the historical greenhouse data is represented as a time series, and the historical greenhouse data is represented as data collected by IoT sensors at any collection point. At any collection point, there are sensors that detect various types of historical greenhouse data, and there are also backup sensors that detect various types of historical greenhouse data. When a sensor fails, the backup sensor is switched to perform the detection, ensuring that the time series of historical greenhouse data remains continuous. Continuity means that at each collection time within the detection period, valid data of the corresponding type of historical greenhouse data can be detected.

[0031] More preferably, the application scenario of this application is a large-scale planting greenhouse, and the collection points, i.e., the IoT sensors, are distributed in a scattered manner. Therefore, the distribution locations are numbered, and the number is represented as X. ijkL Where i represents the collection point in the i-th column from left to right, facing the inside of the greenhouse from the entrance; j represents the collection point in the j-th row from the ground to the top of the greenhouse, facing the inside of the greenhouse from the entrance; k represents the sensor type corresponding to the k-th type of historical greenhouse data; L is 1 or 2. When L is 1, it represents a sensor; when L is 2, it represents a backup sensor.

[0032] More preferably, a switching logic is configured for the sensor and the backup sensor. The switching logic includes acquiring the current monitoring data of any sensor type at any acquisition point, and acquiring the monitoring data of the sensor at the previous acquisition time, which is recorded as the previous monitoring data. Calculate the first difference between the current monitoring data and the previous detection data, select the absolute value of the first difference, calculate the first ratio of the absolute value of the first difference to the previous detection data, set the first value as the rate of change threshold, compare the first ratio with the first value, and trigger the switching operation when the first value is greater than or equal to the first value; do not trigger the switching operation when the first value is less than the first value. When a switching operation is triggered, the current monitoring data is automatically corrected so that the first ratio of the corrected current monitoring data is equal to the first value, and the sensor is switched to the backup sensor. When no switching operation is triggered, the current sensor continues to work.

[0033] More preferably, the historical crop density is expressed as the ratio of the number of historical crops to the portion of the greenhouse floor area occupied by the corresponding crop type.

[0034] More preferably, the historical fresh air input energy or historical fresh air exhaust energy is expressed as the heat input or exhaust of the fresh air system per unit time. When the historical fresh air energy is the historical fresh air input energy, its value is positive, and when the historical fresh air energy is the historical fresh air exhaust energy, its value is negative.

[0035] More preferably, the temperature expression is: ; in, The average temperature inside the greenhouse is represented by , and represents any point in time within the monitoring period. This represents the average temperature inside the greenhouse at any point in time within the monitoring period. The energy generated by the artificial light source at time t is the instantaneous energy of the artificial light source at time t. This refers to the energy generated by the humidifier or dehumidifier at time t, specifically the instantaneous energy generated by the humidifier or dehumidifier at time t. This represents the standard instantaneous energy exchanged between the canopy and air of a crop species at the average temperature inside the greenhouse; that is, the instantaneous energy exchanged between the canopy and air of a crop species at time t under the average temperature inside the greenhouse. The energy generated by the historical air conditioning system, that is, the instantaneous energy generated by the historical air conditioning system at time t. The energy input or output of historical fresh air refers to the instantaneous energy generated by the historical fresh air input or output at time t. This represents the standard energy produced by crop transpiration, that is, the instantaneous energy produced by crop transpiration at time t. Historical crop density, This refers to the volume of the greenhouse's interior space. The internal space of the greenhouse is the historical specific heat capacity under constant pressure at the average temperature inside the greenhouse.

[0036] More preferably, only one of the humidifier and dehumidifier is always in operation. When the humidifier is working, the corresponding historical energy is set to a positive value; when the dehumidifier is working, the corresponding historical energy is set to a negative value. Essentially, the humidifier and dehumidifier are the same type of device, so they can be used... It also refers to both humidifiers and dehumidifiers.

[0037] More preferably, the energy generated by historical artificial light sources, historical humidifiers, historical dehumidifiers, historical air conditioners, historical fresh air input energy, or historical fresh air exhaust energy are collectively referred to as historical energy. Each type of historical energy represents the integral area within the micro-element interval corresponding to the instantaneous power generated by the corresponding device at any given moment. The expression for calculating historical energy is as follows: ; in, For historical energy, Let be the time point before time t, where the difference between time t and time t is equal to the first duration. It is represented as a curve of time versus power, where any point on P(t) represents the instantaneous power value of the device at the corresponding moment, and d is the symbol for the infinitesimal element.

[0038] More preferably, and The acquisition logic is the same, and will be discussed in subsequent analyses. and This is collectively referred to as standard energy; or The acquisition logic includes retrieving the crop database, inputting the crop type and the average temperature inside the greenhouse into the crop database, matching the standard energy exchanged between the canopy and the air at the average temperature inside the greenhouse corresponding to the crop type and the average temperature inside the greenhouse, and matching the standard energy generated by crop transpiration. Among them, the standard energy exchanged between the canopy and the air at the average temperature inside the greenhouse corresponding to the crop type and the average temperature inside the greenhouse is expressed as the energy exchanged between the canopy and the air at the average temperature inside the greenhouse corresponding to the crop type and the average temperature inside the greenhouse within 1 second, and the standard energy generated by crop transpiration is expressed as the energy generated by crop transpiration within 1 second. When the number of crop types in the greenhouse is 1, calculate t and The second difference is calculated, the ratio of the first difference to 1 second is calculated, the product of the second ratio and the standard energy is calculated, and the product of the second ratio and the standard energy is set as... or ; When the number of crop types in the greenhouse is greater than one, calculate the product of the second ratio and the standard energy for each crop type to obtain the greenhouse floor area. Calculate the third ratio of the floor area occupied by any crop type to the greenhouse floor area. Calculate the product of the third ratio and the product of the second ratio and the standard energy for that crop type. Set the product of the third ratio and the second ratio and the standard energy for that crop type as the value for that crop type. Quantity or The components are iterated through each crop type to obtain the values ​​for each crop type. Quantity or Quantity; Corresponding to each crop type Quantity or Add the components together to get the first sum, and set the first sum as... or .

[0039] The first historical time period is set as the monitoring period. Within the monitoring period, the temperature expression is obtained based on historical greenhouse data and the heat balance equation. Based on the temperature expression, a dynamic curve of temperature change over time is obtained. This dynamic curve is set as the reference temperature curve, with the horizontal axis of the reference temperature curve representing the acquisition time and its corresponding acquisition number. The monitoring time period corresponding to the reference temperature curve is set as the reference time period. Jump to other monitoring time periods. Jumping means random jumping. Other monitoring time periods have the same number of data collections as the monitoring time period, and the data collection times corresponding to other monitoring time periods are different from those of the monitoring time period. In addition, each monitoring time period is a common factor of the number of minutes corresponding to a unit of day. The historical volumetric flow rate of warm air, the historical volumetric flow rate of cold air generated by air conditioning, the historical air volume of humidifier, the historical air volume of dehumidifier, and the historical energy generated by artificial light source are obtained at each collection time within the monitoring period. The average temperature inside the greenhouse at the corresponding time is also obtained. Based on the historical volumetric flow rate of warm air, the historical volumetric flow rate of cold air generated by air conditioning, the historical air volume of humidifier, the historical air volume of dehumidifier, the historical energy generated by artificial light source, and the average temperature inside the greenhouse at the corresponding time within the monitoring period, a temperature curve is fitted. The ordinate values ​​of the temperature curve and the reference temperature curve at the same collection number are subtracted to obtain the time series of the difference. The average value of the time series of the difference is calculated and recorded as the first average value. The first average value represents the temperature deviation between the monitoring period and the monitoring period. Select any monitoring time period, select the midpoint of the monitoring time period, calculate the time difference between the midpoints of any two monitoring time periods, and record it as the time interval; Iterate through the temperature deviations corresponding to each monitoring time period; Select any monitoring time period other than the reference time period, calculate the time interval between the reference time point and the time interval between the reference time point, and use the time interval, the historical warm air volume flow rate, the historical air conditioning cold air volume flow rate, the historical humidifier air volume, the historical dehumidifier air volume, the historical artificial light energy, the historical crop density, the historical crop type, and the historical crop growth stage as independent variables. Iterate through the average temperature inside the greenhouse at each moment within the monitoring time period, calculate the average value of the average temperature inside the greenhouse, and use the average value of the average temperature inside the greenhouse as the dependent variable to perform multiple regression analysis and obtain the multiple regression equation. More preferably, the expression for the multiple regression equation is: ; in, This represents the average temperature inside the greenhouse. The number of types of independent variables. Let i be the value of the i-th independent variable collected at the j-th collection time within the monitoring period. It is a constant. To and The corresponding coefficient, i.e. It is a constant.

[0040] More preferably, a correspondence between the multiple regression equation and the time interval is constructed, and the corresponding multiple regression equation is obtained by inputting the time interval.

[0041] Crop parameters include crop density, crop type, and crop growth stage; The control parameters include the fourth difference corresponding to the volumetric flow rate of warm air, the fourth difference corresponding to the volumetric flow rate of cold air generated by the air conditioner, the fourth difference corresponding to the air volume of the humidifier, the fourth difference corresponding to the air volume of the dehumidifier, and the fourth difference corresponding to the energy generated by the artificial light source.

[0042] The logic for constructing the mapping relationship between crop parameters and control parameters includes selecting any time interval, retrieving the multivariate regression equation corresponding to that time interval, inputting the current crop parameters, current warm air volume flow rate, current air conditioning cold air volume flow rate, current humidifier air volume, current dehumidifier air volume, and current artificial light source energy into the multivariate regression equation, and obtaining the average value of the average temperature inside the greenhouse corresponding to the multivariate regression equation, which is recorded as the theoretical temperature value. Obtain the monitoring time period corresponding to the time interval, obtain the historical average temperature inside the greenhouse before the current time period, and calculate the average value of the historical average temperature inside the greenhouse, which is recorded as the actual temperature value. The system continuously adjusts the current volumetric flow rate of warm air, the current volumetric flow rate of cold air generated by the air conditioner, the current air volume of the humidifier, the current air volume of the dehumidifier, and the current energy generated by the artificial light source until the dependent variable value of the multiple regression equation corresponding to the adjusted current volumetric flow rate of warm air, the current volumetric flow rate of cold air generated by the air conditioner, the current air volume of the humidifier, the current air volume of the dehumidifier, and the current energy generated by the artificial light source equals the theoretical temperature value, at which point the continuous adjustment stops.

[0043] Obtain the current volumetric flow rate of warm air, the current volumetric flow rate of cold air produced by the air conditioner, the current air volume of the humidifier, the current air volume of the dehumidifier, and the current energy generated by the artificial light source; Calculate the fourth difference between the current warm air volume flow rate, the current air conditioning cold air volume flow rate, the current humidifier air volume, the current dehumidifier air volume, and the current artificial light source energy and their corresponding initial values ​​after adjustment, and set the fourth difference as the corresponding adjustment parameter; Obtain the time interval and sampling number corresponding to the current moment, and construct a mapping relationship between crop parameters, time interval, sampling number and control parameters.

[0044] More preferably, the corresponding control parameters are matched by inputting crop parameters, time intervals, and sampling number sequences into the mapping relationship.

[0045] The logic for adjusting the control time corresponding to the control parameters includes obtaining the current actual temperature value and setting fuzzy rules for the current actual temperature value. The logic for setting the fuzzy rules includes: Plot the curve of the current actual temperature value, calculate the difference between two adjacent points of the current actual temperature value curve and the rate of change of the difference between two adjacent points of the current actual temperature value, and convert the difference between two adjacent points of the current actual temperature value curve and the rate of change of the difference between two adjacent points of the current actual temperature value curve into fuzzy values ​​E and EC. The membership degrees of E and EC in each fuzzy subset are calculated separately, and the membership degrees are obtained by calculating the membership degree function. Set the fuzzy universe of discourse for the output quantities kp, ki, and kd to be between the threshold of the first universe of discourse and the threshold of the second universe of discourse. Set kp as the proportional coefficient, ki as the integral coefficient, and kd as the differential coefficient. Set the fuzzy subsets to negative large, negative medium, negative small, zero, positive small, positive medium, and positive large; The values ​​of kp, ki, and kd are set based on the difference between two adjacent points on the current actual temperature curve and the rate of change of the difference between two adjacent points on the current actual temperature curve, and a control model for the current actual temperature value is constructed. The current actual temperature value curve is subjected to fuzzy control, and the coefficients of the fuzzy rules are updated according to the particle swarm algorithm.

[0046] More preferably, the update logic for the coefficients of the fuzzy rule includes: Set the initial number of particles, number of iterations, inertia weight, and acceleration coefficient. Randomly initialize the position and velocity of each particle and use the position and velocity of the particles as the input to the current actual temperature value control model. Run the current actual temperature value control model to obtain the fitness evaluation value of the particles. Iterate through the fitness evaluation values ​​of the particles, select the fitness evaluation value of the particle with the largest value, obtain the particle position corresponding to the fitness evaluation value of the particle with the largest value, and set the particle position as the optimal position. The coefficients of the fuzzy rules are updated based on the optimal position. The calculation ends when the fitness evaluation value of the particle with the largest value reaches the first fitness threshold or the number of iterations is reached. The actual temperature value is updated based on the coefficients of the fuzzy rules to control the model, and the control time is input for the control parameters corresponding to any predicted time.

[0047] The control module acquires the current crop parameters and the predicted time, assigns the predicted time to the corresponding monitoring time period, calculates the time difference between the acquisition time and the predicted time within any monitoring time period, selects the acquisition time with the smallest time difference, obtains the acquisition sequence number corresponding to the acquisition time with the smallest time difference, matches the predicted time interval corresponding to the monitoring time period, retrieves the mapping relationship based on the predicted time interval, predicted crop parameters, and acquisition sequence number, inputs the predicted time interval, predicted crop parameters, and acquisition sequence number into the mapping relationship, matches the predicted control parameters corresponding to the predicted time interval, predicted crop parameters, and acquisition sequence number, and sends the first control instruction based on the predicted control parameters. The first control instruction includes the predicted control parameters and their corresponding control time.

[0048] More preferably, the control parameters are adjusted in real time according to the crop growth stage and external climate fluctuations, significantly reducing system overshoot. A nonlinear mapping model between crop parameters and environmental control parameters is constructed by introducing a heat balance equation, effectively overcoming the problems of large inertia and large lag in greenhouse systems, and improving the system's prediction and control accuracy for key environmental variables such as temperature and humidity. Fuzzy logic can handle uncertainties such as sensor noise and external disturbances, enabling the system to maintain stable operation under human interference or sudden environmental changes, significantly improving the system's anti-interference ability and robustness. By predicting the optimal control time and parameters in the future through historical data and heat balance model, early intervention is achieved, avoiding the lag of traditional feedback control, and effectively maintaining the dynamic stability of the crop growth environment. Through accurate prediction and time-sharing control, the system can avoid energy-consuming behaviors such as overheating and ineffective irrigation.

[0049] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0050] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the protection scope of the present invention.

Claims

1. An intelligent control system for greenhouse environment based on the Internet of Things, characterized in that, Includes building modules and control modules; The module constructs a mapping relationship between crop parameters and control parameters based on historical greenhouse data and heat balance equations, and tunes the control time corresponding to the control parameters according to the fuzzy PID algorithm. The control module sends a first control instruction based on the current crop parameters. The first control instruction includes the control parameters at the predicted time and the control time corresponding to the control parameters at the predicted time.

2. The intelligent control system for greenhouse environment based on the Internet of Things as described in claim 1, characterized in that, The module retrieves historical greenhouse data, including historical greenhouse internal temperature, historical energy generated by artificial light sources, historical energy generated by humidifiers, historical energy generated by dehumidifiers, historical energy generated by air conditioning, historical fresh air input energy or historical fresh air exhaust energy, historical crop density, historical specific heat capacity under constant pressure inside the greenhouse, historical volumetric flow rate of warm air, historical volumetric flow rate of cold air generated by air conditioning, historical air volume of humidifiers, historical air volume of dehumidifiers, historical crop types, and historical crop growth stages.

3. The intelligent control system for greenhouse environment based on the Internet of Things as described in claim 2, characterized in that, The first historical time period is set as the monitoring period. Within the monitoring period, the temperature expression is obtained based on historical greenhouse data and the heat balance equation. Based on the temperature expression, a dynamic curve of temperature change over time is obtained. This dynamic curve is set as the reference temperature curve, with the horizontal axis of the reference temperature curve representing the acquisition time and its corresponding acquisition number. The monitoring time period corresponding to the reference temperature curve is set as the reference time period. Jump to other monitoring time periods. Jumping means random jumping. Other monitoring time periods have the same number of data collections as the monitoring time period, and the data collection times corresponding to other monitoring time periods are different from those of the monitoring time period. In addition, each monitoring time period is a common factor of the number of minutes corresponding to a unit of day.

4. The intelligent greenhouse environment control system based on the Internet of Things as described in claim 3, characterized in that, The historical volumetric flow rate of warm air, the historical volumetric flow rate of cold air generated by air conditioning, the historical air volume of humidifier, the historical air volume of dehumidifier, and the historical energy generated by artificial light source are obtained at each collection moment within the monitoring period. The average temperature inside the greenhouse at the corresponding moment is also obtained. Based on the historical volumetric flow rate of warm air, the historical volumetric flow rate of cold air generated by air conditioning, the historical air volume of humidifier, the historical air volume of dehumidifier, the historical energy generated by artificial light source, and the average temperature inside the greenhouse at the corresponding moment within the monitoring period, a temperature curve is fitted. The ordinate values ​​of the temperature curve and the reference temperature curve at the same collection number are subtracted to obtain the time series of the difference. The average value of the time series of the difference is calculated and recorded as the first average value. The first average value represents the temperature deviation between the monitoring period and the monitoring period.

5. The intelligent control system for greenhouse environment based on the Internet of Things as described in claim 4, characterized in that, Select any monitoring time period, select the midpoint of the monitoring time period, calculate the time difference between the midpoints of any two monitoring time periods, and record it as the time interval; Iterate through the temperature deviations corresponding to each monitoring time period; Select any monitoring time period other than the reference time period, calculate the time interval between this time period and the reference time point, and use the time interval, the historical warm air volume flow rate, the historical air conditioning cold air volume flow rate, the historical humidifier air volume, the historical dehumidifier air volume, the historical artificial light energy, the historical crop density, the historical crop type, and the historical crop growth stage as independent variables. Iterate through the average temperature inside the greenhouse at each moment within the monitoring time period, calculate the average value of the greenhouse average temperature, and use the average value of the greenhouse average temperature as the dependent variable to perform multiple regression analysis and obtain the multiple regression equation.

6. The intelligent control system for greenhouse environment based on the Internet of Things as described in claim 1, characterized in that, Crop parameters include crop density, crop type, and crop growth stage; The control parameters include the fourth difference corresponding to the volumetric flow rate of warm air, the fourth difference corresponding to the volumetric flow rate of cold air generated by the air conditioner, the fourth difference corresponding to the air volume of the humidifier, the fourth difference corresponding to the air volume of the dehumidifier, and the fourth difference corresponding to the energy generated by the artificial light source.

7. The intelligent greenhouse environment control system based on the Internet of Things as described in claim 6, characterized in that, The logic for constructing the mapping relationship between crop parameters and control parameters includes selecting any time interval, retrieving the multivariate regression equation corresponding to that time interval, inputting the current crop parameters, current warm air volume flow rate, current air conditioning cold air volume flow rate, current humidifier air volume, current dehumidifier air volume, and current artificial light source energy into the multivariate regression equation, and obtaining the average value of the average temperature inside the greenhouse corresponding to the multivariate regression equation, which is recorded as the theoretical temperature value. Obtain the monitoring time period corresponding to the time interval, obtain the historical average temperature inside the greenhouse before the current time period, and calculate the average value of the historical average temperature inside the greenhouse, which is recorded as the actual temperature value. The system continuously adjusts the current volumetric flow rate of warm air, the current volumetric flow rate of cold air generated by the air conditioner, the current air volume of the humidifier, the current air volume of the dehumidifier, and the current energy generated by the artificial light source until the dependent variable value of the multiple regression equation corresponding to the adjusted current volumetric flow rate of warm air, the current volumetric flow rate of cold air generated by the air conditioner, the current air volume of the humidifier, the current air volume of the dehumidifier, and the current energy generated by the artificial light source equals the theoretical temperature value, at which point the continuous adjustment stops.

8. The intelligent control system for greenhouse environment based on the Internet of Things as described in claim 7, characterized in that, Obtain the current volumetric flow rate of warm air, the current volumetric flow rate of cold air produced by the air conditioner, the current air volume of the humidifier, the current air volume of the dehumidifier, and the current energy generated by the artificial light source; Calculate the fourth difference between the current warm air volume flow rate, the current air conditioning cold air volume flow rate, the current humidifier air volume, the current dehumidifier air volume, and the current artificial light source energy and their corresponding initial values ​​after adjustment, and set the fourth difference as the corresponding adjustment parameter; Obtain the time interval and sampling number corresponding to the current moment, and construct a mapping relationship between crop parameters, time interval, sampling number and control parameters.

9. The intelligent control system for greenhouse environment based on the Internet of Things as described in claim 8, characterized in that, The logic for adjusting the control time corresponding to the control parameters includes obtaining the current actual temperature value and setting fuzzy rules for the current actual temperature value. The logic for setting the fuzzy rules includes: Plot the curve of the current actual temperature value, calculate the difference between two adjacent points of the current actual temperature value curve and the rate of change of the difference between two adjacent points of the current actual temperature value, and convert the difference between two adjacent points of the current actual temperature value curve and the rate of change of the difference between two adjacent points of the current actual temperature value curve into fuzzy values ​​E and EC. The membership degrees of E and EC in each fuzzy subset are calculated separately, and the membership degrees are obtained by calculating the membership degree function. Set the fuzzy universe of discourse for the output quantities kp, ki, and kd to be between the threshold of the first universe of discourse and the threshold of the second universe of discourse. Set kp as the proportional coefficient, ki as the integral coefficient, and kd as the differential coefficient. Set the fuzzy subsets to negative large, negative medium, negative small, zero, positive small, positive medium, and positive large; The values ​​of kp, ki, and kd are set based on the difference between two adjacent points on the current actual temperature curve and the rate of change of the difference between two adjacent points on the current actual temperature curve, and a control model for the current actual temperature value is constructed. The current actual temperature value curve is subjected to fuzzy control, and the coefficients of the fuzzy rules are updated according to the particle swarm algorithm.

10. The intelligent control system for greenhouse environment based on the Internet of Things as described in claim 9, characterized in that, The control module acquires the current crop parameters and the predicted time, assigns the predicted time to the corresponding monitoring time period, calculates the time difference between the acquisition time and the predicted time within any monitoring time period, selects the acquisition time with the smallest time difference, obtains the acquisition sequence number corresponding to the acquisition time with the smallest time difference, matches the predicted time interval corresponding to the monitoring time period, retrieves the mapping relationship based on the predicted time interval, predicted crop parameters, and acquisition sequence number, inputs the predicted time interval, predicted crop parameters, and acquisition sequence number into the mapping relationship, matches the predicted control parameters corresponding to the predicted time interval, predicted crop parameters, and acquisition sequence number, and sends the first control instruction based on the predicted control parameters. The first control instruction includes the predicted control parameters and their corresponding control time.

Images