Agricultural greenhouse artificial intelligence regulation and control system and method based on waste heat utilization of power plant

Abstract

The invention belongs to the technical field of agricultural intelligent regulation and control, and particularly provides an agricultural greenhouse artificial intelligence regulation and control system and method based on waste heat utilization of a power plant. An agricultural greenhouse artificial intelligence regulation and control system based on power plant waste heat utilization comprises a greenhouse environment regulation and control module, a data acquisition module, a prediction module, a crop model module, an intelligent decision module and a control module. The data acquisition module can collect existing waste heat input, waste heat output and future weather information, the prediction module predicts the future thermal load demand of the greenhouse according to the current external environment and future weather forecast, and the crop model module stores environment parameters suitable for the current growth cycle of crops. The intelligent decision-making module can integrate three-party information of the real-time environment, the future prediction and the crop demand to formulate an optimal control strategy, and the control module executes precise regulation and control on the greenhouse environment, so that the production of the crops in the optimal growth environment is ensured, and the quality and the yield of the crops are improved.

Description

Technical Field

[0001] This application belongs to the field of agricultural intelligent control technology, specifically an artificial intelligence control system and method for agricultural greenhouses based on the utilization of waste heat from power plants. Background Technology

[0002] Waste heat from power plants is a valuable energy source that can be recycled to heat agricultural greenhouses, thus realizing the resource utilization of industrial waste heat and energy conservation and carbon reduction in agriculture. The use of waste heat from power plants to heat agricultural greenhouses is achieved through a waste heat greenhouse system. Its control strategy involves opening the heat source valve when the greenhouse temperature is below a set value and closing the heat source valve when the greenhouse temperature is above the set value.

[0003] Generally, greenhouses are large in area, and their heating and cooling rates are slow, exhibiting a certain degree of lag. They are also susceptible to significant fluctuations due to external weather conditions. Simple feedback control in waste heat greenhouse systems struggles to achieve precise and stable regulation. When the weather changes, operational strategies cannot be adjusted in advance, leading to insufficient heating during cold waves or cloudy days. Furthermore, the parameters of existing waste heat greenhouse systems, such as temperature, humidity, and ventilation control subsystems, are fixed, lacking collaborative optimization mechanisms. They fail to consider the differentiated needs of crops at different growth stages (such as seedling, flowering, and fruiting stages), thus limiting the improvement of crop yield and quality. Summary of the Invention

[0004] Based on the above-mentioned technical problems, this application provides an artificial intelligence control system and method for agricultural greenhouses based on the utilization of waste heat from power plants, in order to solve the technical problems of existing waste heat greenhouse systems, such as the lag in temperature control, the susceptibility to large fluctuations due to weather factors, and the inability to adapt to the differentiated needs of crops at different growth stages.

[0005] To achieve the above objectives, the technical solution adopted in this application is as follows: Firstly, this application provides an artificial intelligence control system for agricultural greenhouses based on the utilization of waste heat from power plants, comprising:

[0006] The greenhouse environment control module includes multiple greenhouse environment control devices, which are used to control the temperature, humidity, ventilation and light intensity inside the greenhouse.

[0007] The data acquisition module is used to acquire environmental data inside the greenhouse, waste heat data from the power plant, and external environmental forecast data.

[0008] The prediction module is used to predict the future heat load and environmental change trends of the greenhouse based on the external environment forecast data and historical data.

[0009] The crop model module stores the ideal environmental parameters for at least one crop at different growth stages.

[0010] The intelligent decision-making module is communicatively connected to the data acquisition module, the prediction module, and the crop model module, respectively. It is used to formulate a collaborative control strategy for multiple greenhouse environmental control devices based on real-time data from the data acquisition module, prediction results from the prediction module, and current ideal environmental parameters from the crop model module.

[0011] The control module is connected to the intelligent decision-making module and the greenhouse environment control equipment, and is used to execute the collaborative control strategy.

[0012] In one possible implementation, the data acquisition module includes:

[0013] The greenhouse environment sensor array is used to collect data on air temperature, air humidity, light intensity, and CO2 concentration inside the greenhouse.

[0014] The waste heat monitoring unit is used to collect temperature and flow data of waste heat from the power plant.

[0015] The data interface unit is used to access external weather forecast data and power plant production plan data.

[0016] In one possible implementation, the plurality of greenhouse environment control devices are as follows:

[0017] The heat source regulation unit is used to regulate the supply of waste heat from the power plant or auxiliary heat sources to the greenhouse.

[0018] Ventilation unit, used to regulate the amount of ventilation in the greenhouse;

[0019] Shading units are used to regulate the intensity of light entering the greenhouse;

[0020] Humidity control unit, used to regulate the air humidity inside the greenhouse;

[0021] The CO2 replenishment unit is used to replenish CO2 gas into the greenhouse.

[0022] In one possible implementation, the heat source regulating unit includes a heat exchanger connected to the waste heat pipeline of the power plant, a heat storage device, and a valve for regulating the flow rate of the pipeline; the heat storage device is a hot water storage tank or a phase change material heat storage tank.

[0023] In one possible implementation, the prediction module uses a machine learning model to predict changes in the greenhouse's heat load and key environmental parameters over the next 6 to 72 hours.

[0024] In one possible implementation, the crop model module stores ideal environmental parameters, including daytime target temperature curves that vary with light intensity, nighttime target temperature, and corresponding target humidity and CO2 concentration ranges.

[0025] Compared with existing technologies, the beneficial effects of the artificial intelligence control system for agricultural greenhouses based on the utilization of waste heat from power plants provided in this application are:

[0026] This application provides an artificial intelligence-based agricultural greenhouse control system based on power plant waste heat utilization. The system includes a greenhouse environment control module, a data acquisition module, a prediction module, a crop model module, an intelligent decision-making module, and a control module. It integrates data acquisition, prediction, crop modeling, intelligent decision-making, and control execution into a closed-loop system, unifying information flow and control flow. The data acquisition module collects current waste heat input, waste heat output, and future weather information. The prediction module forecasts the greenhouse's future heat load demand based on the current external environment and future weather forecasts. The crop model module stores suitable environmental parameters for the current crop growth cycle. The intelligent decision-making module integrates real-time environmental, future forecast, and crop demand information to formulate the optimal control strategy, which is then executed by the control module. This configuration overcomes the limitations of traditional systems that rely on only a single parameter, enabling precise control of the greenhouse environment and helping to ensure crops grow in optimal conditions, thus improving crop quality and yield.

[0027] Secondly, this application provides an artificial intelligence-based control method for agricultural greenhouses based on the utilization of waste heat from power plants, implemented using any of the above-mentioned methods, comprising the following steps:

[0028] Real-time collection of environmental data inside the greenhouse and waste heat data from the power plant, as well as acquisition of external environmental forecast data;

[0029] Based on the aforementioned external environment forecast data and historical operating data, predict the future heat load and environmental change trends of the greenhouse;

[0030] Based on the type of crop currently planted and its growth stage, the corresponding ideal environment parameters are retrieved from the pre-stored crop model;

[0031] Based on real-time environmental data, predicted future environmental change trends, and the ideal environmental parameters, coordinated control commands for the heat source regulation unit, ventilation unit, shading unit, humidity regulation unit, and CO2 replenishment unit are calculated through an optimization algorithm.

[0032] The coordinated control commands are executed to drive the corresponding environmental control equipment to operate;

[0033] Monitor the actual environmental data after the environmental control equipment is in operation, and compare it with the expected target to optimize subsequent forecasting and decision-making.

[0034] Compared with the prior art, the artificial intelligence control method for agricultural greenhouses based on the utilization of waste heat from power plants provided in this application, which is implemented using any of the above-mentioned implementation methods, has the same technical effect and will not be described in detail here. Attached Figure Description

[0035] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0036] Figure 1 A framework diagram of an artificial intelligence control system for agricultural greenhouses based on the utilization of waste heat from power plants, provided in an embodiment of this application;

[0037] Figure 2 A flowchart illustrating an artificial intelligence-based control method for agricultural greenhouses based on the utilization of waste heat from power plants, provided as an embodiment of this application; Detailed Implementation

[0038] To make the technical problems, technical solutions, and beneficial effects to be solved by this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and are not intended to limit the scope of this application.

[0039] It should be noted that when a component is referred to as being "fixed to" or "set on" another component, it can be directly on or indirectly on that other component. When a component is referred to as being "connected to" another component, it can be directly connected to or indirectly connected to that other component.

[0040] It should be understood that the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0041] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" or "several" means two or more, unless otherwise explicitly specified.

[0042] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0043] Please refer to the following: Figures 1 to 2 The following describes an artificial intelligence control system and method for agricultural greenhouses based on the utilization of waste heat from power plants, as provided in the embodiments of this application.

[0044] Please see Figure 1 In a first aspect, embodiments of this application provide an artificial intelligence control system for agricultural greenhouses based on the utilization of waste heat from power plants, including a greenhouse environment control module, a data acquisition module, a prediction module, a crop model module, an intelligent decision-making module, and a control module.

[0045] The greenhouse environment control module includes multiple greenhouse environment control devices, which are used to control the temperature, humidity, ventilation, and light intensity inside the greenhouse. The data acquisition module is used to acquire environmental data inside the greenhouse, waste heat data from the power plant, and external environmental forecast data. The prediction module is used to predict the future heat load and environmental change trends of the greenhouse based on external environmental forecast data and historical data. The crop model module stores the ideal environmental parameters corresponding to at least one crop at different growth stages. The intelligent decision-making module is communicatively connected to the data acquisition module, prediction module, and crop model module, and is used to formulate a collaborative control strategy for multiple greenhouse environment control devices based on real-time data from the data acquisition module, prediction results from the prediction module, and the current ideal environmental parameters from the crop model module. The control module is connected to the intelligent decision-making module and the greenhouse environment control devices to execute the collaborative control strategy.

[0046] Compared with the prior art, the beneficial effects of the artificial intelligence control system for agricultural greenhouses based on the utilization of waste heat from power plants provided in this application are:

[0047] This application provides an artificial intelligence-based agricultural greenhouse control system based on power plant waste heat utilization. The system includes a greenhouse environment control module, a data acquisition module, a prediction module, a crop model module, an intelligent decision-making module, and a control module. It integrates data acquisition, prediction, crop modeling, intelligent decision-making, and control execution into a closed-loop system, unifying information flow and control flow. The data acquisition module collects existing waste heat input (greenhouse interior temperature), waste heat output (power plant waste heat temperature and flow rate), and future weather information (obtained via a network). The prediction module forecasts the greenhouse's future heat load demand based on the current external environment and future weather forecasts. The crop model module stores suitable environmental parameters for the current crop growth cycle. The intelligent decision-making module integrates real-time environmental, future prediction, and crop demand information to formulate the optimal control strategy, which is then executed by the control module. This reduces the impact of sudden weather changes (such as cold waves) on the greenhouse interior temperature, ensuring stable crop growth in a suitable environment. This configuration overcomes the limitations of traditional systems that rely on only a single parameter, enabling precise control of the greenhouse environment and helping to ensure crops grow in the optimal environment, thus improving crop quality and yield.

[0048] The data acquisition module includes a greenhouse environment sensor group, a waste heat monitoring unit, and a data interface unit. The greenhouse environment sensor group is used to collect data on air temperature, air humidity, light intensity, and CO2 concentration inside the greenhouse; the waste heat monitoring unit is used to collect temperature and flow data of waste heat from the power plant; and the data interface unit is used to connect to external weather forecast data and power plant production plan data.

[0049] The greenhouse environmental sensor array may specifically include digital air temperature and humidity sensors, light intensity sensors, CO2 concentration sensors, and soil temperature and humidity sensors. The waste heat monitoring unit includes platinum resistance temperature sensors (such as Pt100) and electronic flow meters installed on the waste heat transmission pipeline from the power plant to the greenhouse. The data interface unit has network communication capabilities, acquiring temperature, humidity, wind speed, and sunshine forecasts for the next 72 hours via a 4G / 5G module or Ethernet interface, and obtaining production plans and waste heat availability forecast data from the power plant control system through corresponding interfaces.

[0050] By deploying multiple types and locations of sensors, a comprehensive data sensing network covering waste heat supply, greenhouse environment, and external meteorological conditions is constructed. High-precision sensors provide reliable real-time status input for the system, offering a comprehensive, accurate, and timely data foundation for subsequent prediction and decision-making, thus solving the problems of single data sources and incomplete information in traditional systems.

[0051] The greenhouse environmental control equipment includes a heat source regulation unit, a ventilation unit, a shading unit, a humidity regulation unit, and a CO2 replenishment unit. The heat source regulation unit regulates the supply of waste heat or auxiliary heat from the power plant to the greenhouse; the ventilation unit regulates the greenhouse ventilation volume; the shading unit regulates the light intensity entering the greenhouse; the humidity regulation unit regulates the air humidity inside the greenhouse; and the CO2 replenishment unit replenishes CO2 gas into the greenhouse. The ventilation unit uses a variable frequency fan, and the shading unit consists of an automatic roller shutter installed outside the greenhouse, driven by a film roller and a geared motor. The humidity regulation unit includes a high-pressure micro-mist system for humidification (composed of a water pump, filter, nozzles, and piping) and a dehumidifier for dehumidification, or regulation via ventilation. The CO2 replenishment unit includes bottled liquid CO2, released via a pressure reducing valve and a solenoid valve.

[0052] The heat source regulation unit includes a heat exchanger connected to the waste heat pipeline of the power plant, a heat storage device, and valves for regulating the flow rate of the pipeline. The heat exchanger is a plate heat exchanger or a shell-and-tube heat exchanger installed in the greenhouse, and is heated by a circulating water pump. The heat storage device is a hot water storage tank or a phase change material heat storage tank. When the weather gets cold and the waste heat supply from the power plant is insufficient, the heat energy can be released through the heat storage device to heat the greenhouse.

[0053] The prediction module utilizes a machine learning model to forecast changes in greenhouse heat load and key environmental parameters over the next 6 to 72 hours. The required input features include: weather forecast data for the next 6-72 hours (temperature, wind speed, cloud cover), historical greenhouse environmental data (temperature and light intensity sequences for the past 24-168 hours), and time features (such as hourly and daily cycles). The prediction module outputs predicted values ​​for key greenhouse environmental parameters over the next period, including indoor temperature, relative humidity, light intensity, and calculated heat load values. The prediction model is periodically retrained or incrementally learned using the latest operational data to maintain prediction accuracy.

[0054] By using machine learning models to quantitatively predict future heat loads and environmental trends, a shift from "sensing-response" to "prediction-preparation" has been achieved. For example, by predicting low nighttime temperatures in advance, the thermal storage device can be instructed to store heat in advance during periods of low electricity prices or when surplus heat is available. This effectively overcomes the control lag problem caused by the large inertia of greenhouses, enabling the system to proactively allocate energy, resist the impact of external weather fluctuations on the greenhouse interior, and improve environmental stability and the economy of energy use.

[0055] The crop model module stores ideal environmental parameters, including daytime target temperature curves varying with light intensity, nighttime target temperature, and corresponding target humidity and CO2 concentration ranges. The crop model module stores data in the form of a database or configuration file. Ideal environmental parameters are set separately for different crops (such as tomatoes, cucumbers, and bell peppers) and their different growth stages (germination, seedling, flowering and fruit setting, and maturity).

[0056] Secondly, this application provides an artificial intelligence-based control method for agricultural greenhouses using waste heat from power plants. This method is implemented using the aforementioned artificial intelligence-based control system for agricultural greenhouses using waste heat from power plants, and includes the following steps: real-time collection of environmental data and waste heat data from the greenhouse, and acquisition of external environmental forecast data; prediction of future heat load and environmental change trends in the greenhouse based on the external environmental forecast data and historical operating data; retrieval of corresponding ideal environmental parameters from a pre-stored crop model based on the currently planted crop type and its growth stage; calculation of coordinated control instructions for the heat source adjustment unit, ventilation unit, shading unit, humidity adjustment unit, and CO2 supplementation unit using an optimization algorithm based on real-time environmental data, predicted future environmental change trends, and ideal environmental parameters; execution of the coordinated control instructions to drive the corresponding environmental control equipment; monitoring of actual environmental data after the environmental control equipment has been running, and comparison with expected targets for optimization of subsequent predictions and decisions.

[0057] This application presents an artificial intelligence-based control method for agricultural greenhouses utilizing waste heat from power plants. This method constructs a complete intelligent closed-loop control process, enabling automatic monitoring, prediction, and execution of greenhouse environmental control. Through high-frequency cyclic execution, the system can continuously and dynamically fine-tune the greenhouse environment. By tightly integrating prediction, crop models, and optimization algorithms into the decision-making process, it ensures that each control command is based on a global consideration of multi-source information, rather than an isolated response to a single variable. Post-execution monitoring and feedback further integrate the actual effects into the next control cycle, forming a continuously improving closed loop. This method systematically solves the shortcomings of traditional methods, such as lag, isolation, and fixation, achieving adaptive, collaborative, and crop-oriented precise control of the greenhouse environment.

[0058] The following is an example of the application scenario of this invention using a specific embodiment. On a winter morning, the system starts operating. The greenhouse-side sensor in the data acquisition module detects an indoor temperature of 10°C and an increase in light intensity. The data interface unit obtains a weather forecast: today is sunny, but a strong cold front will arrive at night. The intelligent decision-making module, an AI-optimized decision engine, and the prediction module begin operation. Based on the weather forecast, the prediction module predicts that the daytime temperature will rise rapidly, requiring appropriate ventilation at noon; the nighttime heat load will be 1.5 times that of a normal day. The crop model module, based on the current "tomato-flowering period" model, outputs today's dynamic environmental targets: with increased light, the target temperature should gradually rise from 20°C in the morning to 26°C at noon; the CO2 concentration should be maintained at 800-1000 ppm. The AI-optimized decision engine initiates optimization calculations. It comprehensively considers: ① the current indoor and outdoor environmental conditions; ② the predicted future heat load and light intensity; ③ the crop dynamic targets; ④ the time-of-use electricity price information. After calculation, it outputs today's optimal control strategy:

[0059] 8:00 AM: Although the current temperature is low, the heat pump will not be started for the time being because the sun is expected to heat up soon. Instead, the low-temperature hot water storage tank of the heat storage device will be used for small-scale heating to save energy.

[0060] 10:00 AM: With ample sunlight, the indoor temperature rises rapidly. The engine instructs the ventilation unit to gradually open the skylights for ventilation and cooling. Simultaneously, to compensate for CO2 loss caused by ventilation, the flue gas purification valve is opened to apply CO2 fertilizer. At this time, both sunlight and CO2 levels are high, and the crop's photosynthetic rate reaches its peak.

[0061] 16:00 in the afternoon: Before the arrival of the off-peak electricity price period, the engine commands the heat pump unit of the heat source regulation unit to run at full capacity, not only to store enough heat for the night, but also to store some heat in the high-temperature hot water storage tank.

[0062] 22:00 at night: Cold air arrives. The engine prioritizes using the cheap heat energy stored during the day for heating, smoothly passing through the peak load period and avoiding starting the high-power heat pump during peak electricity price periods.

[0063] Throughout the process, the system automatically, precisely, and collaboratively completed all the controls, ensuring that crops grew in the optimal environment while minimizing energy costs.

[0064] It is understood that the parts in the above embodiments can be freely combined or deleted to form different combined embodiments. The specific contents of each combined embodiment will not be repeated here. After this description, it can be considered that the present invention specification has recorded each combined embodiment and can support different combined embodiments.

[0065] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An artificial intelligence control system for agricultural greenhouses based on the utilization of waste heat from power plants, characterized in that, include: The greenhouse environment control module includes multiple greenhouse environment control devices, which are used to control the temperature, humidity, ventilation and light intensity inside the greenhouse. The data acquisition module is used to acquire environmental data inside the greenhouse, waste heat data from the power plant, and external environmental forecast data. The prediction module is used to predict the future heat load and environmental change trends of the greenhouse based on the external environment forecast data and historical data. The crop model module stores the ideal environmental parameters for at least one crop at different growth stages. The intelligent decision-making module is communicatively connected to the data acquisition module, the prediction module, and the crop model module, respectively, and is used to formulate a collaborative control strategy for multiple greenhouse environmental control devices based on the real-time data of the data acquisition module, the prediction results of the prediction module, and the current ideal environmental parameters of the crop model module. as well as The control module is connected to the intelligent decision-making module and the greenhouse environment control equipment, and is used to execute the collaborative control strategy.

2. The artificial intelligence control system for agricultural greenhouses based on power plant waste heat utilization according to claim 1, characterized in that, The data acquisition module includes: The greenhouse environment sensor array is used to collect data on air temperature, air humidity, light intensity, and CO2 concentration inside the greenhouse. The waste heat monitoring unit is used to collect temperature and flow data of waste heat from the power plant. The data interface unit is used to access external weather forecast data and power plant production plan data.

3. The artificial intelligence control system for agricultural greenhouses based on power plant waste heat utilization according to claim 1, characterized in that, The various greenhouse environment control devices are as follows: The heat source regulation unit is used to regulate the supply of waste heat from the power plant or auxiliary heat sources to the greenhouse. Ventilation unit, used to regulate the amount of ventilation in the greenhouse; Shading units are used to regulate the intensity of light entering the greenhouse; Humidity control unit, used to regulate the air humidity inside the greenhouse; The CO2 replenishment unit is used to replenish CO2 gas into the greenhouse.

4. The artificial intelligence control system for agricultural greenhouses based on power plant waste heat utilization according to claim 3, characterized in that, The heat source regulation unit includes a heat exchanger connected to the waste heat pipeline of the power plant, a heat storage device, and a valve for regulating the flow rate of the pipeline; the heat storage device is a hot water storage tank or a phase change material heat storage tank.

5. The artificial intelligence control system for agricultural greenhouses based on power plant waste heat utilization according to claim 1, characterized in that, The prediction module uses a machine learning model to predict changes in the greenhouse's heat load and key environmental parameters over the next 6 to 72 hours.

6. The artificial intelligence control system for agricultural greenhouses based on power plant waste heat utilization according to claim 1, characterized in that, The ideal environmental parameters stored in the crop model module include the daytime target temperature curve, the nighttime target temperature, and the corresponding target humidity range and target CO2 concentration range, which vary with light intensity.

7. An artificial intelligence-based control method for agricultural greenhouses based on the utilization of waste heat from power plants, characterized in that, The implementation of an artificial intelligence control system for agricultural greenhouses based on the utilization of waste heat from power plants, as described in any one of claims 1 to 6, includes the following steps: Real-time collection of environmental data inside the greenhouse and waste heat data from the power plant, as well as acquisition of external environmental forecast data; Based on the aforementioned external environment forecast data and historical operating data, predict the future heat load and environmental change trends of the greenhouse; Based on the type of crop currently planted and its growth stage, the corresponding ideal environment parameters are retrieved from the pre-stored crop model; Based on real-time environmental data, predicted future environmental change trends, and the ideal environmental parameters, coordinated control commands for the heat source regulation unit, ventilation unit, shading unit, humidity regulation unit, and CO2 replenishment unit are calculated through an optimization algorithm. The coordinated control commands are executed to drive the corresponding environmental control equipment to operate; Monitor the actual environmental data after the environmental control equipment is in operation, and compare it with the expected target to optimize subsequent forecasting and decision-making.

Images