Multi-span greenhouse environment control method, controller and control decision support system

Abstract

A method, controller and control decision support system for controlling the environment of a multi-span greenhouse, relating to the field of automatic control technology. The method includes: obtaining relevant information at a target time in the multi-span greenhouse production process, the relevant information including crop growth status data, greenhouse environment status data, market economic data and outdoor meteorological forecast data in the control time domain starting from the target time; solving the optimal control problem of the multi-span greenhouse in the control time domain based on the relevant information, obtaining the optimal control function of the greenhouse environment adjustment equipment and the optimal trajectory of the greenhouse environment state; generating a parameter setting decision suggestion for the controller based on the optimal control function and the optimal trajectory of the greenhouse environment state; updating the parameter setting of the controller based on the parameter setting decision suggestion; updating and solving the optimal control problem at the target time of each day, and generating a parameter setting decision suggestion for the controller. The implementation of the technical solution provided in the present application can improve the level of intelligence of multi-span greenhouse environmental control.

Description

Technical Field

[0001] The present application relates to the field of automatic control technology, and in particular to a method, a controller and a control decision support system for a multi-span greenhouse environment. Background Art

[0002] Multi-span greenhouses have the advantages of large cultivation space, high degree of mechanization, year-round controllable environment, uniform light and heat environment, and high land utilization rate. They can greatly increase crop yield per unit area and resource utilization efficiency, and reduce labor production intensity. They are an important type of multi-span greenhouse in the global facility horticulture industry, and the scale of the industry is expanding year by year. Environmental control is the core of multi-span greenhouse production management. Multi-span greenhouses have complex structures, numerous environmental adjustment devices, and the multi-span greenhouse environment interacts with crop growth. The precise control of the environment cannot be achieved through manual control, and an automated control system is required.

[0003] The existing multi-span greenhouse environment controller adopts a closed-loop feedback control mechanism, which collects the environmental data in the multi-span greenhouse in real time through sensors, compares these data with the target set values, and dynamically adjusts the operating status of the environmental conditioning equipment according to the changes in the outdoor environment to achieve full automatic control of the multi-span greenhouse environment. In the actual production process, planting managers need to manually set the setting points of environmental factors such as air temperature, humidity, CO2, and light in the multi-span greenhouse based on their own experience by observing the growth status of crops, analyzing historical data, and reading weather forecasts.

[0004] However, this empirical control method requires a high level of professional skills from the growers. If the growers are inexperienced or unfamiliar with the system functions, it may affect the environmental control effect of the multi-span greenhouse; even for experienced growers, it is difficult to achieve efficient management of the multi-span greenhouse environment based on economic benefits due to the inability to predict future dynamics and balance the energy consumption and crop output of the multi-span greenhouse. In addition, most of the existing multi-span greenhouse environmental controllers rely on remote control, and the local greenhouse environmental adjustment equipment lacks human-computer interaction and autonomous operation capabilities. Due to the limitations of network communication, there are major problems with system reliability. Therefore, how to improve the intelligence level and reliability of multi-span greenhouse environmental controllers has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] The present application provides a multi-span greenhouse environmental control method, a controller and a control decision support system, which can improve the intelligence level of multi-span greenhouse environmental control.

[0006] In a first aspect of the present application, a method for controlling a multi-span greenhouse environment is provided, which is applied to a controller, wherein the controller is communicatively connected with a plurality of greenhouse environment regulating devices of the multi-span greenhouse, and the method for controlling the multi-span greenhouse environment comprises:

[0007] Acquire relevant information at a target time during the multi-span greenhouse production process, wherein the relevant information includes crop growth status data, greenhouse environment status data, market economic data, and outdoor weather forecast data within a control time domain starting from the target time;

[0008] Solving the optimal control problem of the multi-span greenhouse in a control time domain starting from the target time based on the relevant information, obtaining the optimal control function of the greenhouse environment adjustment device and the optimal trajectory of the greenhouse environment state in the control time domain, wherein the greenhouse environment state constraint of the optimal control problem is used to make the amplitude of the optimal trajectory of the greenhouse environment state within each hour of the control time domain within a preset range;

[0009] Based on the optimal control function and the optimal trajectory of the greenhouse environment state, generating a parameter setting decision suggestion for the controller, the parameter setting decision suggestion including a decision suggestion for equipment operation constraints, a decision suggestion for greenhouse environment setting points, and a decision suggestion for upper and lower deviations of the greenhouse environment setting points, the decision suggestion for upper and lower deviations corresponding to the amplitude of the optimal trajectory of the greenhouse environment state;

[0010] updating parameter settings of the controller based on the parameter setting decision suggestion of the controller;

[0011] The optimal control problem of the multi-span greenhouse is updated and solved at the target time of each day, and a parameter setting decision suggestion for the controller is generated.

[0012] In a second aspect of the present application, a multi-span greenhouse environment control decision support system is provided, comprising a computer program, wherein the computer program implements the multi-span greenhouse environment control method when executed by a processor.

[0013] In a third aspect of the present application, a controller is provided, characterized in that it includes a local controller, a cloud platform and a sensor;

[0014] The cloud platform is provided with a multi-span greenhouse environment control decision support system for implementing the multi-span greenhouse environment control method described above;

[0015] The cloud platform is used to implement remote control and control decision support of greenhouse environment conditioning equipment;

[0016] The local controller is used to implement manual control and automatic control of the greenhouse environment adjustment equipment;

[0017] The sensor is used to obtain greenhouse and outdoor environmental status data.

[0018] In summary, one or more technical solutions provided in this application have at least the following technical effects or advantages:

[0019] The multi-span greenhouse environment control method obtains complete relevant information including crop growth status data, greenhouse environment status data, market economic data and outdoor meteorological forecast data at the target time, and solves the optimal control problem based on this information, obtains the optimal control function of the greenhouse environment adjustment equipment and the optimal trajectory of the greenhouse environment state, and then generates a controller parameter setting decision suggestion including equipment operation constraints, greenhouse environment setting points and their upper and lower deviations. Finally, the controller parameter setting is updated based on the decision suggestion, and the optimization calculation results are dynamically updated at the daily target time. This method based on optimal control theory transforms greenhouse environmental control from traditional empirical decision-making to data-driven intelligent decision-making, which not only reduces the dependence on the professional and technical level of growers, but also realizes economic benefit-oriented environmental control by considering market economic data. In particular, by introducing greenhouse environmental state constraints to ensure that the amplitude of the optimal trajectory of the environmental state is within the preset range, which corresponds to the controller parameter setting, the drastic fluctuation of environmental parameters can be effectively avoided. At the same time, the optimization mechanism updated daily enables the control strategy to adapt to external environmental changes and crop growth dynamic needs in a timely manner, improving the foresight and accuracy of greenhouse environmental control. This method not only solves the problem in existing technologies that growers find it difficult to predict future dynamics and balance energy consumption and crop output, but also provides a reliable execution basis for the greenhouse environment controller by generating clear parameter setting decision recommendations, thereby improving the intelligence level of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 It is a flow chart of a method for controlling the environment of a multi-span greenhouse provided in an embodiment of the present application;

[0022] Figure 2 This is a controller architecture diagram provided by an embodiment of the present application;

[0023] Figure 3 This is a system architecture diagram of a controller using a master-slave station design provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0025] Please refer to Figure 1 , Figure 1 1 is a flow chart of a method for controlling the environment of a multi-span greenhouse provided in an embodiment of the present application. The method for controlling the environment of a multi-span greenhouse is applied to a controller, and the controller is communicatively connected with a plurality of greenhouse environment regulating devices of the multi-span greenhouse. The method may include the following steps:

[0026] S101. Obtain relevant information at a target time in a multi-span greenhouse production process, wherein the relevant information includes crop growth status data, greenhouse environment status data, market economic data, and outdoor weather forecast data within a control time domain starting from the target time.

[0027] Among them, the target time refers to the specific time point at which the multi-span greenhouse environment controller makes control decisions during the production process. In the embodiment of the present application, it can be understood as a fixed time point every day, such as 8:00 in the morning every day, when the control decision support system starts to execute the greenhouse environment setting point optimal control algorithm. The target time is used to determine the time node for obtaining production-related information, including crop growth status data, greenhouse environment status data, market economic data, and outdoor meteorological forecast data in the control time domain starting from this moment. This information will serve as the basis for generating the next 24-hour greenhouse environment control parameter decision recommendation. By setting a fixed target time, on the one hand, it is convenient for greenhouse managers to form a regular production management rhythm, and on the other hand, it can ensure that the control decision support system always makes decisions based on the latest production-related information, thereby improving the accuracy and timeliness of control decisions.

[0028] In the production process of multi-span greenhouses, in order to achieve intelligent and precise control of the greenhouse environment, it is first necessary to obtain complete production-related information at the target time. Specifically, the greenhouse environment status data such as air temperature, humidity, radiation, and CO2 concentration in the greenhouse are collected in real time through the greenhouse environment sensors; at the same time, market economic data such as crop sales prices and energy prices are obtained. These data will be used to construct the cost function so that the control decision can take into account economic benefits; in addition, it is also necessary to obtain outdoor meteorological forecast data within the control time domain (preferably 2-3 days) starting from the target time, including outdoor air temperature, humidity, radiation, CO2 concentration, wind speed, wind direction, and rainfall.

[0029] By obtaining the above-mentioned relevant information, a data foundation can be laid for the subsequent generation of control decision suggestions based on the optimal control algorithm of the greenhouse environment setting point, which is helpful to realize the intelligent regulation of the greenhouse environment and ultimately achieve the purpose of improving the production efficiency of facility horticulture. This systematic data acquisition method has changed the traditional practice of greenhouse environment control based solely on experience, and has given control decisions a scientific basis.

[0030] Based on the above embodiment, as an optional embodiment, in S101: the step of obtaining relevant information at the target time in the multi-span greenhouse production process may further include the following steps:

[0031] S201. If the target time is a planting day, determine crop growth status data through manual measurement.

[0032] At the target time, when the crops are just transplanted into the greenhouse, it is necessary to accurately obtain the initial growth status data of the crops, which will be used as the initial parameters of the greenhouse crop growth model. Specifically, the dry matter mass, leaf area, plant height and other growth indicators of the crops are obtained through manual measurement.

[0033] During the measurement, firstly, representative samples are randomly selected from the planted crops, and leaf area measurement and biomass weighing are performed on these samples to obtain the initial data of crop growth status. This manual measurement method can accurately obtain the growth status of crops at the time of planting, provide reliable initial parameters for the operation of the subsequent greenhouse crop growth model, and thus improve the simulation accuracy of the model for the crop growth and development process. By obtaining accurate initial growth status data, it is helpful for the control decision support system to better predict the growth and development status of crops throughout the production cycle, so as to formulate a more reasonable greenhouse environment regulation strategy, and finally achieve the goal of improving crop yield and quality. This method of obtaining crop growth status data through manual measurement on the planting day is an important basic work for realizing precise control of the greenhouse environment.

[0034] S202. If the target time is not the planting day, the crop growth status data at the target time is determined by a greenhouse crop growth model based on the greenhouse environment status data from the planting day to the target time, wherein the greenhouse crop growth model is used to characterize the impact of the greenhouse environment on crop growth and development.

[0035] Specifically, when the target time is not the planting day, since the crops have been growing in the multi-span greenhouse for a period of time, in order to avoid frequent manual measurements causing damage to the crops and reducing management efficiency, the greenhouse crop growth model is used to determine the current growth status of the crops. Specifically, the greenhouse crop growth model describes the impact of the greenhouse environment (including air temperature, humidity, radiation, and CO2 concentration in the greenhouse) on crop growth and development through mathematical equations. The input variables of the model include the measured greenhouse environment status data from the planting day to the target time, and the output variables include crop dry matter mass, leaf area, fruit yield and other growth indicators.

[0036] For example, the multi-span greenhouse crop growth model describes the effect of the multi-span greenhouse environment (including air temperature, humidity, radiation, and CO2 concentration in the multi-span greenhouse) on crop growth and development; the multi-span greenhouse crop growth model can be described by the following formula:

[0037] ;

[0038] In the formula, x is the crop growth state variable, such as crop dry matter, leaf area, fruit yield, etc.; d is the external input variable, such as air temperature, humidity, radiation, CO2 concentration in the multi-span greenhouse; p is the model parameter; t is time; t0 is the initial time, such as the planting time and target time of multi-span greenhouse crops; x0 is the initial state, such as the crop dry matter at the initial time, etc. The multi-span greenhouse crop growth model includes the growth, development and yield simulation of facility horticultural crops such as fruit vegetables and leafy vegetables.

[0039] Since the greenhouse crop growth model inputs the measured greenhouse environmental status data, the above-mentioned model-based crop growth status determination method can continuously and accurately track the crop growth and development process, and provide a reliable initial crop growth state for the control decision support system to generate a more reasonable greenhouse environmental regulation strategy within the control time domain, ultimately achieving the goal of improving the production efficiency of facility horticulture.

[0040] S102. Solve the optimal control problem of the multi-span greenhouse in the control time domain starting from the target time based on the relevant information, and obtain the optimal control function of the greenhouse environment adjustment equipment and the optimal trajectory of the greenhouse environment state in the control time domain. The greenhouse environment state constraint of the optimal control problem is used to make the amplitude of the optimal trajectory of the greenhouse environment state within each hour in the control time domain within a preset range.

[0041] Among them, the control time domain refers to the time interval for optimizing the greenhouse environment control starting from the target time. In the embodiment of the present application, it can be understood that the time span of 2-3 days is preferred. This is because the prediction accuracy of the weather forecast will decrease with the increase of the forecast time, and the amount of calculation to solve the optimal control problem will also increase with the increase of the control time domain. The setting of the control time domain is used to determine the time range for solving the optimal control problem. Within this time range, it is necessary to foreseeably consider the impact of future outdoor meteorological changes and greenhouse control on crop growth. Reasonable control time domain settings can ensure the accuracy of control decisions while taking into account computational efficiency.

[0042] For example, when the control time domain is set to 2 days, the control decision support system will solve the optimal control problem at the target time based on the weather forecast data for the next 2 days, thereby generating more forward-looking controller parameter setting decision recommendations, helping the greenhouse environment controller to better cope with the environmental control challenges brought about by weather changes.

[0043] Among them, the optimal control problem refers to a mathematical optimization problem of solving a control strategy that can maximize the net income of greenhouse crop production based on a greenhouse crop production process model within a given control time domain by constructing a cost function and applying necessary control constraints and state constraints. In the embodiment of the present application, it can be understood as a complete mathematical description including a greenhouse crop production process model, a cost function, a control constraint, a state constraint, an initial state, and a terminal state, wherein the greenhouse crop production process model describes the influence of greenhouse structure, outdoor weather, and equipment control on greenhouse environment and crop growth and development, the cost function is expressed as the difference between the greenhouse crop production income and the energy consumption cost of greenhouse environment regulation equipment, the control constraint limits the output range and control logic of the greenhouse environment regulation equipment, and the state constraint ensures that the greenhouse environment and crop growth state are maintained within a reasonable range. The construction and solution of the optimal control problem are used to convert the greenhouse environment regulation target into a quantifiable and optimizable mathematical problem, and obtain the optimal greenhouse environment regulation strategy through numerical calculation, so as to maximize the economic benefits while ensuring the normal growth of crops. This method based on optimal control theory can simultaneously consider multiple control targets, weigh the benefits and costs brought by different control decisions, and provide a scientific basis for the parameter setting of the greenhouse environment controller.

[0044] Correspondingly, the optimal control function and the optimal trajectory of the greenhouse environment state refer to the two key results obtained by solving the optimal control problem, wherein the optimal control function describes the change of the optimal operating state of the greenhouse environment regulating equipment over time, and the optimal trajectory of the greenhouse environment state describes the change of the greenhouse environment state over time under the optimal control. In the embodiment of the present application, it can be understood that the optimal control function represents the optimal operating instruction sequence of each greenhouse environment regulating equipment (such as skylight, high-pressure spray, external shading, fan cooling, curtain, heating equipment, circulating fan, fill light, carbon dioxide, non-standard equipment, etc.) in the control time domain, and the optimal trajectory of the greenhouse environment state represents the optimal change curve of environmental factors such as air temperature, humidity, CO2 concentration, radiation, etc. in the greenhouse, and the amplitude of these curves in each hour is limited to a preset range. The calculation of the optimal control function and the optimal trajectory of the greenhouse environmental state is used to provide a basis for the subsequent generation of parameter setting decision recommendations for the multi-span greenhouse environmental controller. By analyzing the optimal control function and the optimal trajectory of the greenhouse environmental state, the equipment operation constraint recommendations can be determined. By analyzing the optimal trajectory of the greenhouse environmental state, the environmental setting point and its upper and lower deviation recommendations can be determined, thereby converting the theoretical optimal solution into a practical and executable control parameter setting.

[0045] Based on the above embodiments, as an optional embodiment, the optimal control problem includes defining a greenhouse crop production process model, which is used to characterize the impact of the multi-span greenhouse structure, outdoor weather, and greenhouse environmental conditioning equipment control on the environment and crops of the multi-span greenhouse.

[0046] Exemplarily, the greenhouse crop production process model can be described by the following formula:

[0047] ;

[0048] In the formula, The variables of greenhouse environment and crop growth status, such as air temperature, humidity, radiation, CO2 concentration, crop dry matter mass, leaf area, fruit yield, etc. in the greenhouse; For multi-span greenhouse control, such as the start and stop and operating frequency of fan cooling equipment; for external input variables, such as the outdoor environment; are model parameters, including constant parameters, multi-span greenhouse structure and cultivation parameters; For time; The initial time, such as the planting time of greenhouse crops and the target time; It is the initial state, such as the air temperature and crop dry matter mass in the multi-span greenhouse at the initial moment.

[0049] Specifically, the greenhouse crop production process model is used to characterize the impact of the greenhouse structure, outdoor weather, and greenhouse environmental conditioning equipment control on the environment and crops of the greenhouse. The model can accurately describe the relationship between the various elements in the greenhouse environmental regulation process. Specifically, the state variables of the model include the greenhouse environmental elements and crop growth indicators, the control variables represent the operating status of the greenhouse environmental conditioning equipment, the external input variables reflect the outdoor environmental conditions, the model parameters include the structural characteristics and cultivation parameters of the greenhouse, the time variables and the initial moment are used to describe the dynamic change process of the system, and the initial state defines the system state at the calculation starting point. By establishing a complete greenhouse crop production process model, the dynamic changes of the greenhouse environment and the growth response of crops under different control strategies can be accurately predicted, providing a reliable mathematical basis for solving the optimal control problem. Compared with the traditional empirical control method, this method based on the mechanism model can better reflect the physical nature of greenhouse environmental regulation and improve the scientificity and accuracy of control decisions.

[0050] Based on the above embodiment, as an optional embodiment, the optimal control problem includes defining a cost function, which is used to characterize the difference between the crop production income and the operating energy consumption cost of the greenhouse environment conditioning equipment of the multi-span greenhouse.

[0051] Exemplarily, the cost function can be specifically described by the following formula:

[0052] ;

[0053] In the formula, Control quantities of greenhouse environment adjustment equipment, such as the start / stop status and operating frequency of fan cooling equipment, skylight opening, sunshade equipment opening / closing degree, etc.; are system state variables, including greenhouse environment state variables (such as greenhouse air temperature, humidity, radiation, CO2 concentration, etc.) and crop growth state variables (such as crop dry matter mass, leaf area, fruit yield, etc.); are external input variables, such as outdoor meteorological conditions (such as outdoor air temperature, humidity, radiation, CO2 concentration, wind speed, wind direction, and rainfall); System parameters, including constant parameters, multi-span greenhouse structure parameters (such as thermal insulation performance, ventilation performance, etc.) and cultivation parameters (such as crop variety characteristics, cultivation density, etc.); is the time variable; The initial moment, such as the planting moment of greenhouse crops or the target moment; is the termination time, which is generally the end time of the control time domain; is the terminal income term, which represents the total crop production income at the end of the control time domain, and is related to the terminal state Related; is the process benefit item, which represents the operating cost of the greenhouse environment conditioning equipment at time t.

[0054] Specifically, the cost function contains two main parts: one is the total income of greenhouse crop production, which reflects the economic value of crops at the end time and can be calculated through terminal state indicators such as crop dry matter mass and fruit yield; the other is the operating cost of greenhouse environmental conditioning equipment in the entire control time domain, which requires consideration of the energy consumption characteristics and energy prices of various types of equipment. By comprehensively balancing these two parts, the greenhouse environmental regulation problem can be transformed into an optimization problem of maximizing economic benefits. When solving the optimal control problem, the system will automatically find the optimal control strategy to maximize the cost function, that is, to maximize the net production income while ensuring the growth needs of crops. This optimization method based on economic benefits not only changes the traditional control thinking of simply pursuing the standard of environmental parameters, but also helps growers make more economical control decisions in complex production environments. At the same time, because the cost function takes into account the cumulative effect in the entire control time domain, the control decision has a stronger foresight, and can weigh the possible future benefits and costs when generating the control strategy, thereby achieving the long-term optimization of greenhouse production.

[0055] Based on the above embodiment, as an optional embodiment, the optimal control problem includes defining control constraints, and the control constraints include the output boundaries of the greenhouse environment adjustment equipment of the multi-span greenhouse and the control logic in the automatic control program in the controller.

[0056] Exemplarily, the control constraint can be described by the following formula:

[0057] ;

[0058] In the formula, For the Greenhouse environmental conditioning equipment Control variables at time; For the Greenhouse environmental conditioning equipment The lower limit value of the control variable at time; For the Greenhouse environmental conditioning equipment The upper limit value of the control variable at the moment; is the time variable; is the initial time, i.e. the target time; is the end time; The serial number of the greenhouse environment conditioning equipment.

[0059] Specifically, for each greenhouse environment conditioning device, there are physical limitations and safe operating ranges, such as the limit on the skylight opening, the range of the fan operating frequency, etc. These limitations are reflected by setting the upper and lower limits of the control variables. At the same time, in actual production, the operation of the equipment also needs to follow specific control logic. For example, in the greenhouse cooling process, the skylight needs to be opened for a certain period of time before the high-pressure spray is allowed to start. This type of control logic also needs to be fully reflected in the control constraints. By setting these control constraints, it can be ensured that the solution to the optimal control problem not only meets the physical limitations of the equipment, but also meets the operating requirements of the controller, avoiding the generation of control strategies that are unexecutable or inconsistent with the controller program logic. This optimization method that takes into account actual control constraints improves the practicality and reliability of control decisions, so that the theoretical optimal solution can better guide actual production.

[0060] On the basis of the above embodiments, as an optional embodiment, the optimal control problem includes defining state constraints, the state constraints include greenhouse environment state constraints and crop growth state constraints; wherein the greenhouse environment state constraints are implemented by a cost function and a penalty function, which are used to keep the optimal trajectory of the greenhouse environment state unchanged within each hour of the control time domain, or, to maintain the amplitude range of the optimal trajectory of the greenhouse environment state within each hour of the control time domain, wherein the amplitude range of the optimal trajectory of the greenhouse environment state is set by the grower according to the crop growth requirements and greenhouse energy-saving requirements, and the amplitude range of the optimal trajectory of the greenhouse environment state remains unchanged within 24 hours.

[0061] Exemplarily, the state constraint can be described by the following formula:

[0062] ;

[0063] In the formula, For the The state variables are The values ​​at the moment include greenhouse environment state variables and crop growth state variables; For the The state variables are The lower limit of the moment; For the The state variables are The upper limit of the moment; is the time variable; is the initial time, i.e. the target time; is the end time; is the number of the state variable.

[0064] Specifically, the setting goal of the greenhouse environment state constraint is to make the optimal trajectory of the greenhouse environment state remain stable or fluctuate within a preset amplitude range within every hour of the control time domain. This amplitude range is set by the grower according to the crop growth requirements and greenhouse energy saving requirements, and is preferably kept unchanged within 24 hours to ensure the stability of environmental regulation, and is also more in line with the design habits of the parameter setting input window of the greenhouse environment controller. For example, for the air temperature in the greenhouse, the grower can set the temperature fluctuation range allowed per hour according to the crop growth stage and energy saving requirements. By introducing such a state constraint in the optimal control problem, the greenhouse environment can be avoided from drastic fluctuations, which not only protects the crops from the influence of environmental stress, but also reduces the equipment loss and energy waste caused by the frequent start and stop of the equipment. At the same time, the crop growth state constraint ensures that the growth index of the crop is maintained within a reasonable range to avoid abnormal growth. This optimization method based on state constraints not only improves the stability and reliability of greenhouse environmental regulation, but also makes the control decision more in line with the actual production needs and meets the parameter setting requirements of the controller. In particular, through the setting of the penalty function, the system can automatically weigh the environmental stability and control effect during the optimization process, so as to obtain a control strategy that meets the needs of crop growth and greenhouse energy saving and is convenient for actual implementation. In addition, since the state constraints take into account the environmental fluctuation control on an hourly scale, the control parameter decision recommendations finally generated are easier to be adopted and executed by existing greenhouse environmental controllers.

[0065] At the implementation level, the system uses a penalty function method to handle amplitude constraints. The specific approach is to add a penalty term to the cost function. When the amplitude exceeds the preset range, the penalty term will generate negative benefits, thereby automatically suppressing excessive environmental fluctuations during the optimization process. This soft constraint processing method is easier to solve than direct hard constraints and can significantly improve the computational efficiency of the optimization algorithm. At the same time, by adjusting the weight coefficient of the penalty term, the system can flexibly balance the relationship between environmental stability and control benefits.

[0066] As a special case, when the optimal trajectory of the greenhouse environment is required to remain constant every hour, the value of the amplitude range is set to 0. The optimization results in this extreme case are easier to convert into actual controller parameter settings, but may sacrifice certain control flexibility and economic benefits. Therefore, in practical applications, it is necessary to reasonably set the value of the amplitude range according to the physiological characteristics and production goals of specific crops.

[0067] The above-mentioned state constraint design based on amplitude constraint not only ensures the stability and reliability of the multi-span greenhouse environmental control, but also provides a clear operation guide for the actual execution of control decisions. The system automatically balances environmental stability and control benefits through mathematical optimization, which not only meets the requirements of crop growth for environmental stability, but also takes into account the economic efficiency of equipment operation, providing strong support for the precise control of the multi-span greenhouse environment.

[0068] S103. Based on the optimal control function and the optimal trajectory of the greenhouse environment state, generate parameter setting decision suggestions for the controller, the parameter setting decision suggestions include decision suggestions for equipment operation constraints, decision suggestions for greenhouse environment setting points, and decision suggestions for upper and lower deviations of greenhouse environment setting points, and the decision suggestions for upper and lower deviations correspond to the amplitude of the optimal trajectory of the greenhouse environment state.

[0069] Specifically, the decision suggestions for equipment operation constraints are determined by analyzing the optimal control function and the optimal trajectory of the greenhouse environment state. First, the operation period of the greenhouse environment regulation equipment is determined according to the optimal control function, and then the extreme value of the optimal trajectory of the greenhouse environment state during the equipment operation period is analyzed to determine the decision suggestions for equipment operation constraints.

[0070] For example, by analyzing the optimal control function of the heating device and the optimal trajectory of the greenhouse air temperature in the corresponding period, a device operation constraint decision suggestion of "when the greenhouse air temperature is greater than 20°C, the heating device is not allowed to be turned on" can be generated. These device operation constraint decision suggestions are preferably kept unchanged within 24 hours to ensure the stability of the control logic.

[0071] Based on the above embodiment, as an optional embodiment, S103, based on the optimal control function and the optimal trajectory of the greenhouse environment state, the step of generating a parameter setting decision suggestion for the controller may further include the following steps:

[0072] S301. Determine the operating time period of the greenhouse environment regulating device in the control time domain and the extreme value of the optimal trajectory of the greenhouse environment state in the operating time period based on the optimal control function.

[0073] Specifically, it is necessary to first analyze the timing characteristics of the optimal control function, identify the start and stop times of the greenhouse environment conditioning equipment, and thus determine the equipment's operating time. For example, by analyzing the optimal control function of the external shading equipment, the opening and closing times of the external shading under different outdoor radiation conditions can be identified. Then, for each determined equipment operating time period, analyze the extreme value of the optimal trajectory of the greenhouse environment state within that time period.

[0074] For example, taking the external sunshade as an example, by analyzing the optimal trajectory of outdoor radiation during its operation period, the radiation threshold that triggers the opening and closing of the external sunshade can be determined. The above analysis process not only considers the characteristics of a single period, but also needs to comprehensively consider the statistical characteristics of multiple similar operation periods to ensure that the generated equipment operation constraints are generally applicable.

[0075] S302. Generate a decision suggestion for the equipment operation constraint based on the extreme value of the optimal trajectory of the greenhouse environment state, and the decision suggestion for the equipment operation constraint remains unchanged within 24 hours.

[0076] Specifically, it is necessary to first extract the key thresholds of environmental parameters based on the extreme value characteristics of the optimal trajectory of the greenhouse environmental state. For example, by analyzing the extreme values ​​of the optimal trajectory of greenhouse relative humidity during the operation period of the high-pressure spray equipment, the humidity thresholds suitable as equipment operation constraints can be determined. When determining these thresholds, not only the characteristics of a single operation period should be considered, but also the data of multiple similar operation periods should be statistically analyzed to ensure the representativeness and rationality of the thresholds. Then, these thresholds are combined with the control logic of the equipment to form a complete equipment operation constraint decision recommendation.

[0077] For example, an operation constraint suggestion of "when the relative humidity of the greenhouse is greater than 85%, the high-pressure spray equipment is not allowed to be turned on" can be generated. These equipment operation constraint decision suggestions remain unchanged within 24 hours. The purpose of this design is to ensure the continuity and stability of the control logic and avoid system fluctuations caused by frequent adjustments.

[0078] S303, generating a decision suggestion for the greenhouse environment setting point according to the average value of the optimal trajectory of the greenhouse environment state in each hour of the control time domain.

[0079] Specifically, it is necessary to first segment the optimal trajectory of the greenhouse environment state according to the hourly time, for example, to divide the trajectory into time periods such as 08:00-09:00 and 09:00-10:00. Then, for each one-hour time period, calculate the arithmetic mean of the optimal trajectory of the greenhouse environment state in that time period. For example, when calculating the air temperature setting point in the greenhouse, the temperature setting point decision recommendation for that time period can be obtained by taking the average value of the optimal temperature trajectory in the hour from 10:00 to 11:00. This average value calculation not only takes into account the overall level of the optimal trajectory, but also can smooth out short-term fluctuations in the trajectory, making the generated setting point more stable and reliable. It is worth noting that this average value calculation method based on the hourly scale matches the parameter setting characteristics of the actual greenhouse environment controller, which is convenient for the controller to execute.

[0080] S304. Determine an upper deviation decision suggestion for the greenhouse environment setting point according to the difference between the maximum value and the average value of the optimal trajectory of the greenhouse environment state in each hour of the control time domain.

[0081] Specifically, it is necessary to first find the maximum value of the optimal trajectory of the greenhouse environment state in each one-hour period. Then, the maximum value is subtracted from the calculated average value of the period to obtain the upper deviation value of the period.

[0082] For example, when calculating the upper deviation of the air temperature in the greenhouse, if the maximum value of the temperature optimal trajectory in the hour from 14:00 to 15:00 is 29°C and the average value is 28°C, then the upper deviation decision recommendation for the temperature in this period is 1°C. This calculation method based on the actual fluctuation characteristics of the optimal trajectory not only takes into account the dynamic characteristics of the optimization control, but also ensures the practicality of the control parameters.

[0083] It is worth noting that since the optimal trajectory has taken into account the balance between crop growth requirements and energy efficiency in the solution process, the upper deviation determined based on its fluctuation range is reasonable.

[0084] S305. Determine a lower deviation decision suggestion for the greenhouse environment setting point according to the difference between the average value and the minimum value of the optimal trajectory of the greenhouse environment state in each hour of the control time domain.

[0085] Specifically, by calculating the difference between the average and minimum values ​​of the optimal trajectory of the greenhouse environment state in each hour of the control time domain, a lower deviation decision suggestion for the greenhouse environment setting point is generated. This method of determining the lower deviation based on the statistical characteristics of the optimal trajectory makes the lower limit setting of the greenhouse environment control more reasonable, avoiding the problem of energy waste or insufficient environmental control caused by improper lower deviation setting in traditional control.

[0086] S104: Update the parameter settings of the controller based on the parameter setting decision suggestion of the controller.

[0087] Specifically, the generated parameter setting decision suggestions need to be pushed to the growers or directly sent to the controller. When pushed to the growers, the growers can set the 24-hour greenhouse environment setting point, the upper and lower deviations of the greenhouse environment setting point, and the equipment operation constraints of the multi-span greenhouse environment controller through the operation interface of the cloud platform or the local controller according to the decision suggestions of the previous 24 hours in the pushed control time domain. For example, the grower can set the air temperature control parameters in the greenhouse for a certain hour as follows: set point 28℃, upper deviation 1.0℃, lower deviation 2.0℃, and set the equipment operation constraint of "allowing the cooling device to be turned on when the air temperature in the greenhouse is greater than 30℃". When the automatic sending method is adopted, the control decision support system can directly convert the parameter setting decision suggestions into an instruction format that can be recognized by the controller, and automatically complete the parameter update.

[0088] S105. Update and solve the optimal control problem of the multi-span greenhouse at the target time every day, and generate parameter setting decision suggestions for the controller.

[0089] Specifically, at the target time of each day, the control decision support system first needs to obtain the latest production-related information. For the crop growth status, the system uses the greenhouse crop growth model and the measured greenhouse environment data of the previous day to update the calculation; at the same time, it obtains the current greenhouse environment status, energy prices and other market economic data, as well as the weather forecast data for the next 2-3 days. Based on this updated information, the system re-solves the optimal control problem and calculates the new optimal control function and the optimal trajectory of the greenhouse environment status. Then, the system converts these optimization results into new parameter setting decision recommendations, including updated equipment operation constraints, greenhouse environment setting points and their upper and lower deviations. For example, if the temperature is predicted to rise significantly in the next few days, the system will adjust the operation constraints and temperature control parameters of the greenhouse cooling equipment accordingly to better cope with the challenges of high temperature weather.

[0090] Through the above-mentioned dynamic optimization operation mechanism, continuous improvement of greenhouse environmental control can be achieved. Through daily updated optimization calculations, the control strategy can adapt to changes in the external environment and the dynamic needs of crop growth in a timely manner, improving the adaptability and accuracy of greenhouse environmental regulation. Since the optimization process takes into account weather changes in the next 2-3 days, the generated control strategy has a certain degree of foresight, which helps to cope with the challenges brought by environmental changes in advance. At the same time, this regular optimization mechanism also provides a guarantee for the economic benefits of greenhouse production. The system can dynamically balance production inputs and expected returns based on the latest market price information.

[0091] The above embodiment introduces the implementation process of the multi-span greenhouse environment control decision method. Based on the above embodiment, the system architecture of the controller will be introduced below.

[0092] Specifically, the controller may include a local controller, a cloud platform, and a sensor;

[0093] The cloud platform is provided with a multi-span greenhouse environment control decision support system for implementing the multi-span greenhouse environment control method described above;

[0094] The cloud platform is used to implement remote control and control decision support for greenhouse environment conditioning equipment;

[0095] Local controller, used to implement manual and automatic control of greenhouse environment conditioning equipment;

[0096] Sensors are used to obtain environmental status data in the greenhouse and outdoors.

[0097] In the process of multi-span greenhouse environment control, in order to realize intelligent and precise control of greenhouse environment, the controller provided in this embodiment includes a local controller, a cloud platform and a sensor. Among them, the cloud platform may include a PC and an intelligent mobile terminal, which is provided with a multi-span greenhouse environment control decision support system for implementing the above multi-span greenhouse environment control method to ensure the scientificity and foresight of the control decision. The cloud platform not only undertakes the remote control function, but also provides growers with parameter setting decision suggestions based on optimal control theory through the control decision support system, which changes the traditional practice of greenhouse environment control based on experience alone. The local controller is responsible for the specific control execution of the greenhouse environment adjustment equipment, including manual control and automatic control modes, which not only meets the needs of different operating scenarios, but also ensures the reliability of the system. The sensor may include an outdoor meteorological sensor and an indoor environmental sensor, which provides the necessary data basis for the automatic control of the local controller and the decision support of the cloud platform by collecting the environmental status data of the greenhouse and the outdoors in real time.

[0098] Optionally, the cloud platform is developed based on the Java language, with good code portability and stability; the main framework integrates the Spring Boot framework, using its automatic configuration and independent operation features to simplify the application configuration and deployment process and shorten the development cycle; the persistence layer uses the MyBatis framework to implement object-relational mapping, enhance the flexibility of SQL operations and improve data access efficiency; the view layer uses the Vue.js framework to provide a responsive user interface and support efficient data binding and component-based development.

[0099] The local controller adopts the design concept of independent operation. Even when the communication with the cloud platform is interrupted, it can still independently complete the control of the greenhouse environment adjustment equipment based on the latest set control parameters and real-time collected environmental data, thereby ensuring the continuity and safety of greenhouse production. The cloud platform deploys a control decision support system to solve the optimal control problem and generate scientific and reasonable control parameter setting decision suggestions at the target time of each day based on the latest production-related information, including crop growth status data, greenhouse environmental status data, market economic data, and future weather forecast data. This layered architecture that combines local control with cloud decision-making not only ensures the reliability of the control system, but also improves the intelligence level of control decision-making.

[0100] The configuration and layout of sensors directly affect the control effect. The greenhouse environmental sensors monitor the greenhouse air temperature, humidity, radiation, CO2 concentration and other environmental parameters, and provide real-time feedback for the closed-loop control of the local controller; the outdoor meteorological sensors monitor the outdoor air temperature, humidity, radiation, CO2 concentration, wind speed, wind direction and rainfall and other parameters, which are used for the operation strategy adjustment of the local controller and provide important environmental information for the cloud platform control decision support system. This multi-level data collection system ensures the accuracy and timeliness of control decisions.

[0101] Based on the above embodiment, as an optional embodiment, the cloud platform obtains parameter setting decision suggestions of the local controller in the control time domain starting from the target time through the multi-span greenhouse environment control decision support system, and pushes the parameter setting decision suggestions to the growers, so that the growers can set the parameter setting decision suggestions through the cloud platform or the local controller; or, the cloud platform sends the parameter setting decision suggestions to the local controller to realize greenhouse environment managed control.

[0102] In order to give full play to the advantages of the multi-span greenhouse environment control decision support system and take into account the different management needs of growers, this embodiment provides two control decision execution modes.

[0103] In the first mode, the cloud platform calculates the parameter setting decision suggestions of the local controller in the control time domain starting from the target time through the multi-span greenhouse environment control decision support system, and pushes these suggestions to the growers. According to the decision suggestions of the previous 24 hours in the control time domain pushed, the growers can set the 24-hour greenhouse environment setting point, the upper and lower deviations of the greenhouse environment setting point, and the equipment operation constraints of the multi-span greenhouse environment controller through the remote operation interface of the cloud platform or the on-site operation interface of the local controller. This mode retains the decision-making initiative of the growers, allowing them to make appropriate adjustments to the decision suggestions provided by the system based on their own experience and actual production conditions, thereby realizing human-machine collaborative decision-making.

[0104] In the second mode, the cloud platform can directly send parameter setting decision suggestions to the local controller to achieve managed control of the greenhouse environment. This mode is suitable for users who have fully verified the system control effect or lack professional planting experience. By automatically executing the parameter setting decision suggestions generated based on the optimal control theory, it can ensure that the greenhouse environment control always follows the principle of maximizing economic benefits and avoids the subjectivity and uncertainty that may be caused by human decision-making. At the same time, since the control decision support system has fully considered the crop growth needs, energy efficiency and market economic factors when generating parameter setting decision suggestions, the managed control mode can realize intelligent and precise control of the greenhouse environment.

[0105] The design of the above two control decision execution modes reflects the flexibility and adaptability of the system. Growers can choose the appropriate execution mode according to their own needs and management strategies. For experienced growers, they can choose to receive decision suggestions and set control parameters independently, so that they can learn from the system's optimization suggestions and integrate their own planting experience; for novice growers or users who pursue a high degree of automation, they can choose the managed control mode to let the system independently complete the entire process from decision generation to parameter setting.

[0106] Based on the above embodiment, as an optional embodiment, the local controller includes a CPU control unit, a switch, a gateway, and a host computer;

[0107] The local controller is further used to calculate the control amount according to the greenhouse environment setting point set by the grower, the upper and lower deviations of the greenhouse environment setting point, and the equipment operation constraints, and control the greenhouse environment adjustment equipment according to the control amount;

[0108] The greenhouse environment set point of the local controller includes setting the greenhouse environment target value in each hour of 24 hours;

[0109] The host computer is used to receive the grower's parameter settings for the local controller and display the operating status of the greenhouse environment conditioning equipment and the data collected by the sensors. The settings and displays of the host computer are synchronized with the cloud platform.

[0110] In order to ensure that the local controller can independently realize precise control of the greenhouse environment, this embodiment has carried out detailed design of the hardware composition and functional implementation of the local controller. The local controller includes core components such as a CPU control unit, a switch, a gateway and a host computer. Through the collaborative work of these components, efficient management and control of the greenhouse environment regulation equipment can be achieved. Among them, the CPU control unit, as the core processing unit of the local controller, is responsible for executing control algorithms, processing sensor data and generating device control instructions; the switch is used for data transmission between internal components; the gateway realizes the communication connection between the local controller and the cloud platform to ensure two-way transmission of data. The CPU control unit is connected to the energy device and powered by the energy device.

[0111] In actual operation, the local controller calculates the precise control value based on the greenhouse environment setting point set by the grower, the upper and lower deviations of the greenhouse environment setting point, and the equipment operation constraints, combined with the real-time collected environmental data, and controls the operation status of the greenhouse environment adjustment equipment accordingly. This multi-parameter-based control strategy makes greenhouse environment regulation more accurate and efficient. In particular, in the design of greenhouse environment setting points, the local controller supports the separate setting of greenhouse environment target values ​​within each hour of 24 hours. This fine-grained control method can better meet the needs of crop growth around the clock and realize dynamic optimization and regulation of the greenhouse environment.

[0112] In order to improve the system's operational convenience and real-time monitoring, the local controller is equipped with a host computer as a human-computer interaction interface. The host computer is not only used to receive the grower's parameter settings for the local controller, but also to display in real time the operating status of the greenhouse environment adjustment equipment and the environmental data collected by the sensor. More importantly, the host computer's settings and display functions are synchronized with the cloud platform. This design ensures the consistency of local operation and remote control, avoids conflicts in parameter settings, and improves the reliability of system operation. Through the settings of the host computer, growers can monitor and adjust the greenhouse environment directly on site without relying on a network connection.

[0113] Based on the above embodiment, as an optional embodiment, the CPU control unit communicates with the host computer through the switch, and performs two-way data transmission with the cloud platform through the switch and the gateway, is connected to the on-site electric control cabinet through hard wiring, and communicates with the sensor through hard wiring or wide area network;

[0114] When the number of on-site electrical control cabinets is greater than the preset number, the local controller adopts the master-slave control mode, and the CPU control unit establishes a communication connection with the distributed control units of the on-site electrical control cabinets in the multi-span greenhouse through the communication bus. The distributed control unit communicates with the greenhouse environment conditioning equipment integrated with the on-site electrical control cabinets and the sensors near the on-site electrical control cabinets.

[0115] For example, please refer to Figure 2 and Figure 3 , Figure 2 A controller architecture diagram provided in an embodiment of the present application, Figure 3 A system architecture diagram of a controller using a master-slave station design provided in an embodiment of the present application.

[0116] In order to achieve efficient communication between components within the local controller and reliable connection with external devices, this embodiment designs a communication architecture based on the CPU control unit in detail. Figure 2 As shown in the figure, the CPU control unit, as the core of the control system, exchanges data with other components through a variety of communication methods. Specifically, the CPU control unit establishes a communication connection with the host computer through the switch to ensure that the local human-computer interaction interface can receive control instructions in real time and display the system status; at the same time, it transmits data in both directions with the cloud platform through the switch and gateway to achieve information exchange between local control and cloud decision-making. At the equipment control level, the CPU control unit is directly connected to the on-site electrical control cabinet by hard wiring. This connection method has the characteristics of strong anti-interference ability and stable transmission; for the connection of sensors, the system provides two communication methods: hard wiring and wide area network. It can be flexibly configured according to the actual installation environment and sensor type, which improves the adaptability of the system.

[0117] As the scale of the multi-span greenhouse expands, the number of on-site electrical control cabinets may exceed the preset number. At this time, a simple centralized control structure may lead to problems such as complex system wiring, high construction costs, and difficult maintenance. Figure 3 As shown, this embodiment provides a system architecture upgrade solution based on the master-slave control mode. In this mode, the CPU control unit of the local controller establishes a communication connection with the distributed control units in the on-site electric control cabinets distributed throughout the multi-span greenhouse through a communication bus. Each distributed control unit is responsible for communicating with the greenhouse environment conditioning equipment integrated with the electric control cabinet where it is located and nearby sensors to achieve local data acquisition and control execution. This hierarchical and partitioned control architecture significantly reduces the wiring complexity of the system, while improving the scalability and maintainability of the control system.

[0118] Based on the above embodiment, as an optional embodiment, the local controller is provided with an automatic control mode and a manual control mode;

[0119] When the local controller implements the automatic control of the greenhouse environment conditioning equipment, the control amount is calculated based on the control logic in the automatic control program in the local controller with the goal of minimizing energy consumption;

[0120] When a local controller implements manual control of greenhouse environmental conditioning equipment, the local controller directly controls the operation of the equipment based on instructions input by the grower.

[0121] In order to adapt to different production scenarios and ensure the flexibility and reliability of greenhouse environment control, this embodiment designs a dual-mode control mechanism of the local controller. The local controller is provided with an automatic control mode and a manual control mode, which can be switched according to actual needs, providing a larger operating space for greenhouse environment control.

[0122] In the automatic control mode, the local controller takes the lowest energy consumption as the optimization goal, and calculates the optimal control quantity through the control logic of the automatic control program in the controller and the controller parameter settings. Specifically, the controller will take into account the operating characteristics and energy consumption characteristics of various greenhouse environmental regulation equipment based on the real-time collected environmental data, combined with equipment operating constraints, greenhouse environmental setting points, upper and lower deviations of setting points, and automatically calculate the equipment operation plan that can achieve the environmental control goal with the lowest energy consumption. For example, when cooling is required, the system will give priority to low-energy consumption methods such as natural ventilation, and only start high-energy consumption refrigeration equipment when necessary, thereby ensuring that the greenhouse environment meets the needs of crop growth while minimizing energy consumption.

[0123] In manual control mode, the local controller directly responds to the control instructions input by the grower through the host computer or cloud platform to achieve direct control of the greenhouse environment conditioning equipment. This mode is particularly suitable for equipment debugging, emergency handling or special working conditions. For example, during equipment maintenance, maintenance personnel can directly control the operating status of specific equipment; before extreme weather comes, growers can manually adjust the equipment operation strategy and make preventive preparations in advance. The setting of manual control mode provides the necessary manual intervention path for system operation and improves the system's emergency handling capabilities.

[0124] On the basis of the above-mentioned embodiment, as an optional embodiment, the embodiment of the present application further provides a multi-span greenhouse environment control decision support system, including a computer program, which implements the above-mentioned multi-span greenhouse environment control method when executed by a processor.

[0125] In order to achieve the standardization of the multi-span greenhouse environment control method, this embodiment provides a multi-span greenhouse environment control decision support system, which is packaged in the form of a computer program. When the computer program is executed by a processor, it can realize all the functions of the multi-span greenhouse environment control method. This system implementation based on a computer program not only ensures the standardized execution of the control method, but also improves the maintainability and scalability of the system.

[0126] Specifically, the computer program includes a complete control decision support algorithm implementation, which can complete the entire process from obtaining information related to greenhouse production, solving optimal control problems, generating parameter setting decision suggestions, to updating controller parameter settings when the processor executes. The program implements a greenhouse crop growth model and a greenhouse crop production process model to accurately describe the relationship between the outdoor environment, greenhouse structure, greenhouse control, greenhouse environment and crop growth; at the same time, the program also includes an optimal control algorithm based on a cost function to maximize economic benefits while ensuring crop growth needs. This programmed implementation method ensures the scientificity and consistency of control decisions.

[0127] By implementing the control decision support system in the form of a computer program, the system has good maintainability and scalability. On the one hand, the modular design of the program makes system maintenance and upgrading more convenient, and specific functional modules can be optimized or updated according to actual needs; on the other hand, the standardized program interface design also facilitates the functional expansion of the system, and new model parameters or control strategies can be flexibly added according to the characteristics of different crop varieties or different types of greenhouses. This software implementation method provides reliable technical support for the promotion and application of multi-span greenhouse environmental control technology.

[0128] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for controlling the environment of a multi-span greenhouse, characterized in that: Applied to a controller, the controller is communicatively connected with a plurality of greenhouse environment regulating devices of a multi-span greenhouse, and the multi-span greenhouse environment control method comprises: Acquire relevant information at a target time during the multi-span greenhouse production process, wherein the relevant information includes crop growth status data, greenhouse environment status data, market economic data, and outdoor weather forecast data within a control time domain starting from the target time; Solving the optimal control problem of the multi-span greenhouse in a control time domain starting from the target time based on the relevant information, obtaining the optimal control function of the greenhouse environment adjustment device and the optimal trajectory of the greenhouse environment state in the control time domain, wherein the greenhouse environment state constraint of the optimal control problem is used to make the amplitude of the optimal trajectory of the greenhouse environment state within each hour of the control time domain within a preset range; Based on the optimal control function and the optimal trajectory of the greenhouse environment state, generating a parameter setting decision suggestion for the controller, the parameter setting decision suggestion including a decision suggestion for equipment operation constraints, a decision suggestion for greenhouse environment setting points, and a decision suggestion for upper and lower deviations of the greenhouse environment setting points, the decision suggestion for upper and lower deviations corresponding to the amplitude of the optimal trajectory of the greenhouse environment state; updating parameter settings of the controller based on the parameter setting decision suggestion of the controller; updating and solving the optimal control problem of the multi-span greenhouse at the target time of each day, and generating a parameter setting decision suggestion for the controller; Based on the optimal control function and the optimal trajectory of the greenhouse environment state, generating a parameter setting decision suggestion for the controller, including: Determine, based on the optimal control function, the operating period of the greenhouse environment conditioning device within the control time domain, and the extreme value of the optimal trajectory of the greenhouse environment state within the operating period; generating a decision suggestion for the equipment operation constraint based on the extreme value of the optimal trajectory of the greenhouse environment state, wherein the decision suggestion for the equipment operation constraint remains unchanged within 24 hours; Generate a decision suggestion for the greenhouse environment setting point according to the average value of the greenhouse environment state optimal trajectory within each hour of the control time domain; Determining an upper deviation decision suggestion for the greenhouse environment setting point according to the difference between the maximum value and the average value of the optimal trajectory of the greenhouse environment state in each hour of the control time domain; According to the difference between the average value and the minimum value of the optimal trajectory of the greenhouse environment state in each hour of the control time domain, a lower deviation decision suggestion of the greenhouse environment setting point is determined.

2. The multi-span greenhouse environment control method according to claim 1, characterized in that: The optimal control problem includes defining a greenhouse crop production process model, a cost function, control constraints, and state constraints; The greenhouse crop production process model is used to characterize the impact of the multi-span greenhouse structure, outdoor weather, and greenhouse environment conditioning equipment control on the environment and crops of the multi-span greenhouse; The cost function is used to characterize the difference between the crop production income and the operating energy consumption cost of the greenhouse environment conditioning equipment of the multi-span greenhouse; The control constraints include output boundaries of greenhouse environment conditioning equipment of the multi-span greenhouse and control logic in the automatic control program in the controller; The state constraints include the greenhouse environment state constraints and the crop growth state constraints; Wherein, the greenhouse environmental state constraint is implemented by the cost function and the penalty function, which is used to keep the optimal trajectory of the greenhouse environmental state unchanged within each hour of the control time domain, or to maintain the amplitude range of the optimal trajectory of the greenhouse environmental state within each hour of the control time domain, wherein the amplitude range of the optimal trajectory of the greenhouse environmental state is set by the grower according to the crop growth requirements and greenhouse energy-saving requirements, and the amplitude range of the optimal trajectory of the greenhouse environmental state remains unchanged within 24 hours.

3. The multi-span greenhouse environment control method according to claim 1, characterized in that: The obtaining of relevant information at a target time during the production process of the multi-span greenhouse includes: If the target time is a planting day, determining the crop growth status data by manual measurement; If the target time is not the planting day, the crop growth status data at the target time is determined based on the greenhouse environment status data from the planting day to the target time through a greenhouse crop growth model, wherein the greenhouse crop growth model is used to characterize the impact of the greenhouse environment on crop growth and development.

4. A multi-span greenhouse environmental control decision support system, comprising a computer program, characterized in that: When the computer program is executed by a processor, the multi-span greenhouse environment control method according to any one of claims 1 to 3 is implemented.

5. A controller, characterized in that: Includes local controller, cloud platform and sensors; The cloud platform is provided with a multi-span greenhouse environment control decision support system for implementing the multi-span greenhouse environment control method according to any one of claims 1 to 3; The cloud platform is used to implement remote control and control decision support of greenhouse environment conditioning equipment; The local controller is used to implement manual control and automatic control of the greenhouse environment adjustment equipment; The sensor is used to obtain greenhouse and outdoor environmental status data.

6. The controller according to claim 5, characterized in that: The cloud platform obtains parameter setting decision suggestions of the local controller in the control time domain starting from the target time through the multi-span greenhouse environment control decision support system, and pushes the parameter setting decision suggestions to the grower, so that the grower sets the parameter setting decision suggestions through the cloud platform or the local controller; and / or, The cloud platform sends the parameter setting decision suggestions to the local controller to achieve greenhouse environment managed control.

7. The controller according to claim 5, characterized in that: The local controller includes a CPU control unit, a switch, a gateway, and a host computer; The local controller is further used to calculate the control amount according to the greenhouse environment setting point set by the grower, the upper and lower deviations of the greenhouse environment setting point, and the equipment operation constraints, and control the greenhouse environment adjustment equipment according to the control amount; The greenhouse environment setting point of the local controller includes setting a greenhouse environment target value in each hour of 24 hours; The host computer is used to receive the parameter settings of the local controller by the grower, and display the operating status of the greenhouse environment adjustment equipment and the data collected by the sensor. The settings and displays of the host computer are synchronized with the cloud platform.

8. The controller according to claim 7, characterized in that: The CPU control unit communicates with the host computer through the switch, performs two-way data transmission with the cloud platform through the switch and the gateway, is connected to the on-site electric control cabinet through hard wiring, and communicates with the sensor through hard wiring or wide area network; When the number of the on-site electrical control cabinets is greater than the preset number, the local controller adopts a master-slave control mode, and the CPU control unit establishes a communication connection with the distributed control units of the on-site electrical control cabinets in the multi-span greenhouse through a communication bus, and the distributed control unit is communicated with the greenhouse environment conditioning equipment integrated with the on-site electrical control cabinet and the sensors near the on-site electrical control cabinet.

9. The controller according to claim 7, characterized in that: The local controller is provided with an automatic control mode and a manual control mode; When the local controller implements automatic control of the greenhouse environment conditioning equipment, the control amount is calculated based on the control logic in the automatic control program in the local controller with the goal of minimizing energy consumption; When the local controller implements manual control of the greenhouse environment conditioning equipment, the local controller directly controls the operation of the equipment based on instructions input by the grower.

Images