A smart agricultural control system and method based on the Internet of Things

Abstract

The present application relates to the field of intelligent agricultural control, and more particularly to an intelligent agricultural control system and method based on the Internet of Things. The method comprises: collecting environmental parameters, calculating predicted environmental parameters by a dynamic adaptive trend prediction algorithm; based on the predicted environmental parameters, calculating membership values using a multi-level fuzzy membership environmental adaptability evaluation algorithm; based on the current environmental parameters, the predicted environmental parameters and the membership values, generating control signals using a dynamic control algorithm, and intelligently controlling the equipment. The present application solves the technical problems that the traditional system cannot effectively predict environmental data, but simply responds to the current environmental data; the traditional control method can only determine environmental suitability based on a single numerical value, and cannot achieve fine evaluation of the degree of parameter deviation from the ideal value; and the traditional agricultural control system is difficult to effectively suppress emergencies, which easily causes the system to overrespond or even become unstable.

Description

Technical Field

[0001] This invention relates to the field of smart agricultural control, and more particularly to a smart agricultural control system and method based on the Internet of Things. Background Technology

[0002] With the continuous growth of the global population and the acceleration of urbanization, agriculture is facing unprecedented challenges. Factors such as increased food demand, the impact of climate change, and the growing scarcity of resources make it difficult for traditional agriculture to meet the needs of modern society. Against this backdrop, a smart agricultural control system and method based on the Internet of Things (IoT) has emerged as an important means to improve agricultural production efficiency and achieve sustainable development. In particular, the application of IoT technology has greatly promoted the development of smart agriculture, enabling intelligent and automated data collection, monitoring, and control in the agricultural production process. This not only improves resource utilization efficiency and reduces production costs but also promotes sustainable agricultural development.

[0003] However, existing smart agriculture control methods have the following technical problems: traditional systems cannot effectively predict environmental data, but simply respond to the current environmental data, resulting in untimely regulation and unsatisfactory regulation effects; traditional control methods can only judge environmental suitability based on a single numerical value, and cannot achieve a detailed assessment of the degree to which environmental parameters deviate from the ideal value. Simple numerical judgments can easily lead to frequent and unnecessary regulation actions, which in turn aggravate resource consumption; in actual agricultural production environments, sudden climate change or unpredictable abnormal fluctuations can cause drastic changes in parameters. Traditional agricultural control systems are difficult to effectively suppress sudden events, which can easily cause the system to over-respond or even become unstable. Summary of the Invention

[0004] This invention provides an IoT-based smart agriculture control system and method to address the problems of traditional systems failing to effectively predict environmental data and instead simply responding to current environmental data, resulting in untimely and ineffective regulation. Traditional control methods can only judge environmental suitability based on a single numerical value, failing to achieve a nuanced assessment of the degree to which parameters deviate from ideal values. Simple numerical judgments can easily lead to frequent and unnecessary regulatory actions, which in turn exacerbate resource consumption. In actual agricultural production environments, sudden climate changes or unpredictable abnormal fluctuations can cause drastic changes in parameters, and traditional agricultural control systems are unable to effectively suppress sudden events, easily leading to over-response or even instability.

[0005] The present invention provides a smart agriculture control system and method based on the Internet of Things, specifically including the following technical solutions:

[0006] A smart agriculture control method based on the Internet of Things includes the following steps:

[0007] S1: Collect environmental parameters, calculate the average trend of environmental parameter changes through a dynamic adaptive trend prediction algorithm, and obtain the predicted environmental parameters;

[0008] S2: Based on the predicted environmental parameters, the membership value is calculated using a multi-level fuzzy membership degree environmental adaptability evaluation algorithm;

[0009] S3: Based on current and predicted environmental parameters, a dynamic control algorithm is used to quantify the difference between the predicted state and the current actual state. This is combined with membership values ​​and the upper limit of the equipment's resource usage to generate control signals for intelligent control of the equipment.

[0010] Preferably, S1 specifically includes:

[0011] In the implementation of the dynamic adaptive trend prediction algorithm, historical environmental parameters are extracted from the database, the average trend of historical environmental parameters is analyzed, and the difference of historical environmental parameters between each pair of adjacent time points is calculated. After accumulating the differences of historical environmental parameters, the average trend of the overall environmental parameters is obtained by dividing by the number of time points.

[0012] Preferably, S1 specifically includes:

[0013] Based on the average variation trend of environmental parameters, an inhibition factor is introduced and combined with the tangent function to construct a prediction model and obtain the predicted environmental parameters.

[0014] Preferably, S2 specifically includes:

[0015] In the implementation of the multi-level fuzzy membership degree environmental adaptability evaluation algorithm, a suitable range of predicted environmental parameters is set. When the predicted environmental parameters are between the upper and lower limits of the suitable range, the environmental conditions are considered suitable.

[0016] Preferably, S2 specifically includes:

[0017] In the implementation of the multi-level fuzzy membership degree environmental adaptability evaluation algorithm, a flexible tolerance parameter is set. Based on the appropriate range of predicted environmental parameters, a nonlinear decay is introduced through an exponential function to convert the predicted environmental parameters into membership degree values.

[0018] Preferably, S3 specifically includes:

[0019] The dynamic control algorithm calculates the deviation of environmental parameters by comparing predicted and current environmental parameters; based on the deviation of environmental parameters and in combination with membership values, it introduces the adjustment intensity and the weight of the control influence to generate a control signal.

[0020] Preferably, S3 specifically includes:

[0021] In the implementation of the dynamic control algorithm, an arctangent function is introduced to perform nonlinear smoothing on the deviation values ​​of environmental parameters, and the resource usage of the equipment is constrained by the upper limit of the equipment's resource usage.

[0022] A smart agriculture control system based on the Internet of Things includes the following components:

[0023] Sensor acquisition module, environmental parameter prediction module, environmental adaptability assessment module, control signal generation module, and equipment control module;

[0024] Sensor acquisition module: Collects environmental parameters and outputs them to the environmental parameter prediction module and the control signal generation module;

[0025] Environmental parameter prediction module: Receives environmental parameters from the sensor acquisition module, calculates predicted environmental parameters through a dynamic adaptive trend prediction algorithm, and outputs the predicted environmental parameters to the environmental adaptability assessment module and the control signal generation module;

[0026] Environmental adaptability assessment module: Based on the predicted environmental parameters from the environmental parameter prediction module, the membership degree value is calculated using a multi-level fuzzy membership degree environmental adaptability assessment algorithm, and the membership degree value is output to the control signal generation module;

[0027] Control signal generation module: Receives environmental parameters from sensor acquisition module, predicted environmental parameters from environmental parameter prediction module, and membership values ​​from environmental adaptability assessment module; generates control signals using dynamic control algorithm; and outputs the control signals to equipment control module.

[0028] Equipment control module: performs intelligent control of the equipment based on control signals.

[0029] The beneficial effects of the technical solution of the present invention are:

[0030] 1. By deploying a sensor network and employing a dynamic adaptive trend prediction algorithm, key parameters in the environment, such as temperature, humidity, and light, can be collected and analyzed in real time. Based on historical environmental parameters and the average trend of environmental parameter changes, accurate short-term predictions are provided. In particular, the combination of tangent function and power operation amplifies minute trends, enhances the sensitivity to environmental fluctuations, and significantly improves the ability of IoT-based smart agriculture control systems to predict future environmental conditions. This enables them to respond in advance to keep the environment within a suitable range and reduce the risks brought about by sudden environmental changes.

[0031] 2. Employing a multi-level fuzzy membership degree environmental adaptability assessment algorithm, it can accurately determine the suitability of environmental conditions. By setting suitable range intervals and flexible tolerance parameters for predicted environmental parameters, it can avoid immediately triggering control commands when environmental parameters fluctuate slightly, allowing for a certain adjustment buffer. When environmental parameters exceed the set range, it accurately calculates membership values ​​through a nonlinear exponential decay function, thereby achieving sensitive environmental condition assessment. This not only improves the adaptability and flexibility of the IoT-based smart agriculture control system but also avoids resource waste caused by over-regulation and maintains the relative stability of the agricultural environment.

[0032] 3. Based on current environmental parameters, predicted environmental parameters, and membership values, a dynamic control algorithm is introduced. By analyzing the deviation between predicted and current environmental parameters, control signals are intelligently generated. A nonlinear deviation adjustment factor based on the arctangent function can smoothly adjust the deviation to avoid over-response when environmental parameters fluctuate sharply. The set optimization weights and resource usage limits of the devices ensure a balanced distribution of resources among the devices, preventing any single device from consuming too many resources and ensuring the overall system's high efficiency and energy saving. Through intelligent allocation and dynamic adjustment, the resource needs of each device are accurately met while effectively controlling device energy consumption, ensuring the efficiency and sustainability of the IoT-based smart agriculture control system. Attached Figure Description

[0033] Figure 1 This is a structural diagram of an IoT-based smart agriculture control system according to the present invention.

[0034] Figure 2 This is a flowchart of a smart agriculture control method based on the Internet of Things as described in this invention. Detailed Implementation

[0035] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0036] 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.

[0037] The following description, in conjunction with the accompanying drawings, details a specific solution for an IoT-based smart agriculture control system and method provided by the present invention.

[0038] See attached document Figure 1The diagram illustrates a smart agriculture control system based on the Internet of Things (IoT) according to an embodiment of the present invention. The system includes the following components:

[0039] Sensor acquisition module, environmental parameter prediction module, environmental adaptability assessment module, control signal generation module, and equipment control module;

[0040] Sensor acquisition module: Deploys a sensor network, uses sensors to collect environmental parameters, and outputs the environmental parameters to the environmental parameter prediction module and the control signal generation module;

[0041] Environmental parameter prediction module: Receives environmental parameters from the sensor acquisition module, calculates predicted environmental parameters through a dynamic adaptive trend prediction algorithm, and outputs the predicted environmental parameters to the environmental adaptability assessment module and the control signal generation module;

[0042] Environmental adaptability assessment module: Based on the predicted environmental parameters from the environmental parameter prediction module, the membership degree value is calculated using a multi-level fuzzy membership degree environmental adaptability assessment algorithm, and the membership degree value is output to the control signal generation module;

[0043] Control signal generation module: Receives environmental parameters from sensor acquisition module, predicted environmental parameters from environmental parameter prediction module, and membership values ​​from environmental adaptability assessment module; generates control signals using dynamic control algorithm; and outputs the control signals to equipment control module.

[0044] Equipment control module: Performs intelligent control of the equipment based on the control signals generated by the control signal generation module.

[0045] See attached document Figure 2 The diagram illustrates a flowchart of a smart agriculture control method based on the Internet of Things (IoT) according to an embodiment of the present invention. The method includes the following steps:

[0046] S1. Collect environmental parameters, calculate the average trend of environmental parameter changes through a dynamic adaptive trend prediction algorithm, and obtain the predicted environmental parameters;

[0047] A sensor network is deployed according to the needs of the agricultural environment. Each sensor is responsible for collecting environmental parameters such as temperature, humidity, light intensity, and pH value. These parameters are then standardized to eliminate dimensions. At time t, the environmental parameters collected by sensor i (after standardization) are denoted as... The standardization process described herein is a technical method well known to those skilled in the art and will not be elaborated upon here.

[0048] To accurately predict short-term trends in the agricultural environment and provide reliable support for predicting agricultural environments in IoT-based smart agriculture control systems, a dynamic adaptive trend prediction algorithm is introduced. This algorithm, based on the characteristics of agricultural environmental conditions and combining the features of adaptive learning and dynamic nonlinear adjustment, enables short-term prediction of key environmental parameters (such as temperature, humidity, and light intensity) and calculates the predicted environmental parameters.

[0049] The dynamic adaptive trend prediction algorithm extracts historical environmental parameters for each sensor at different points in the past from the database. After extracting the historical environmental parameters, it analyzes the average trend of each set of historical environmental parameters. Specifically, this is done by analyzing the rate of change of historical environmental parameters, calculating the difference in historical environmental parameters between each pair of adjacent time points, reflecting the magnitude of change in a short period of time. After accumulating the differences in historical environmental parameters, it divides by the number of time points to obtain the average trend of the overall environmental parameters. The average trend of environmental parameters indicates the speed and direction of the overall change of environmental parameters over a period of time, providing a quantitative description of data stability and volatility. The specific calculation formula is as follows:

[0050]

[0051] Where, Δx i This represents the average trend of environmental parameters collected by sensor i within a historical time range, where the historical time range is set based on expert experience. Indicates that sensor i is in time Collected environmental parameters; It represents the amount of data change between two adjacent time points, reflecting the magnitude of change over a short period of time; Indicates to arrive The differences in historical environmental parameters at any given time are summed; m represents the number of time points, which is set according to expert experience and is not limited here.

[0052] Based on the calculated average variation trend of environmental parameters, a prediction model is constructed to predict the environmental state at future moments. The design of the prediction model combines two mathematical processes: on the one hand, the "tangent" operation is applied, which can significantly amplify the average variation trend of small environmental parameters and ensure that the prediction model can identify subtle changes in the environment; on the other hand, the "power" operation is introduced, using a suppression factor to control the response intensity of the prediction model, so as to adjust the amplification effect of the tangent function, enabling the prediction model to adaptively adjust when there are large fluctuations and avoid excessive deviation in prediction.

[0053] The specific formula for calculating predicted environmental parameters is as follows:

[0054]

[0055] Among them, P i,t+1 This represents the predicted environmental parameters of sensor i at the next time step t+1; x i,t γ represents the environmental parameters collected by sensor i at the current time t; i tan(Δx) represents the dynamic learning coefficient, used to adaptively adjust the weights of predicted environmental parameters to adapt to the average changing trend of environmental parameters and improve the accuracy of prediction. It is determined by expert experience and its value ranges from [0,1]. i The tangent function () represents the operation of the tangent function, which amplifies the characteristics of the average trend of environmental parameters and can adapt to rapid changes in environmental parameters; Δx i θ represents the average trend of environmental parameters collected by sensor i over a historical time range; θ represents the inhibition factor, used to control the response intensity of the prediction model and adjust the amplification effect of the tangent function. It is determined by expert experience and its value range is [0,1].

[0056] Using dynamic adaptive trend prediction algorithms can ensure that IoT-based smart agriculture control systems can respond in real time and accurately based on predicted environmental parameters, thereby ensuring that environmental parameters remain within a suitable range and thus guaranteeing the stability of crop growth conditions.

[0057] S2. Based on the predicted environmental parameters, the membership degree value is calculated using a multi-level fuzzy membership degree environmental adaptability evaluation algorithm;

[0058] Based on the predicted environmental parameters, the adaptability of agricultural environmental status is evaluated using a multi-level fuzzy membership degree environmental adaptability assessment algorithm. The membership degree value is calculated to determine whether agricultural production conditions are suitable.

[0059] The design of the multi-level fuzzy membership degree environmental adaptability assessment algorithm aims to compensate for the problems of untimely and inaccurate response of traditional agricultural control systems to complex environments. By setting suitable ranges for the upper and lower limits of predicted environmental parameters, it can determine whether key environmental parameters in the agricultural environment are in a suitable state. Unlike simple numerical judgment methods, the multi-level fuzzy membership degree environmental adaptability assessment algorithm can sensitively assess the degree to which predicted environmental parameters deviate from the ideal state through fuzzy membership degree, thereby achieving delicate control. Even if the predicted environmental parameters fluctuate slightly, they can still remain stable within a suitable range, rather than simply triggering control commands.

[0060] Specifically, a suitable range is set for each predicted environmental parameter. When the predicted environmental parameter is between the upper and lower limits of the suitable range, the environmental conditions are considered suitable. In addition, a flexible tolerance parameter is set for each sensor to control the flexibility of the IoT-based smart agriculture control system. This parameter has a certain tolerance for small parameter fluctuations. When the predicted environmental parameter slightly exceeds the set suitable range, it will not be immediately regarded as an abnormal state, but a certain buffer is allowed. If the predicted environmental parameter exceeds the upper limit of the suitable range, the difference between the predicted environmental parameter and the upper limit will be divided by the flexible tolerance parameter, and then an exponential function will be used to convert the predicted environmental parameter into a membership value using a non-linear decay method. If the predicted environmental parameter is lower than the lower limit of the suitable range, the difference between the lower limit and the predicted environmental parameter will be divided by the flexible tolerance parameter, and then an exponential function will be used to convert the predicted environmental parameter into a membership value using a non-linear decay method.

[0061] The formula for calculating the membership degree is:

[0062]

[0063] Among them, S i,t+1 P represents the degree of matching between the predicted environmental parameters of sensor i and the suitable range at the next time t+1, i.e., the membership value, which ranges from (0,1]. It is used to measure the adaptability of the predicted environmental parameters. The closer the membership value is to 1, the closer the predicted environmental parameters are to the ideal suitable state; the closer the membership value is to 0, the greater the deviation of the predicted environmental parameters from the suitable range. i,t+1 This represents the predicted environmental parameters of sensor i at the next time step t+1; a i and b i These represent the lower and upper limits of the suitable range for the environmental parameters predicted by sensor i, respectively. They can be set according to the specific implementation scenario and are not limited here. The flexible tolerance parameter is used for sensors. The set tolerance range is used to smooth the changes in the membership function. It is determined by expert experience and the value range is (0,1]. exp represents the exponential function with the natural logarithm e as the base. It is used for nonlinear mapping and can enhance the discrimination effect on unsuitable environmental states.

[0064] The multi-level fuzzy membership degree environmental adaptability assessment algorithm has extremely high scalability and can accommodate data from different types of sensors. The calculation of membership degree values ​​based on fuzzy logic is not limited by specific environmental parameters and is suitable for various agricultural environments. Whether it is intelligent greenhouses, field planting, or precision irrigation systems, personalized environmental control can be achieved by adjusting flexible tolerance parameters.

[0065] S3. Based on the current environmental parameters and predicted environmental parameters, a dynamic control algorithm is used to quantify the difference between the predicted state and the current actual state. Combined with the membership value and the upper limit of the equipment's resource usage, a control signal is generated to intelligently control the equipment.

[0066] The dynamic control algorithm calculates the deviation value of each environmental parameter by comparing the predicted environmental parameters with the current environmental parameters. The deviation value reflects the difference between the predicted state and the current actual state and serves as the basis for control. Subsequent control signals are generated by adjusting the intensity, the influence weight, and the membership value. The adjustment intensity is dynamically adjusted according to the characteristics of the equipment, enabling each device to self-adjust based on the current environmental response. The influence weight represents the degree of influence of different sensors on the equipment. Different sensors reflect their effects on the current equipment through the adjustment of the influence weight. The membership value represents the degree of matching between the predicted environmental parameters and the ideal environmental parameters.

[0067] A nonlinear deviation adjustment factor is further introduced to smooth the deviation between the predicted environmental parameters and the current environmental parameters, avoiding excessive adjustment when there are sharp fluctuations. The arctangent function is used to nonlinearly smooth the deviation value, and the smoothing effect is strengthened as the deviation value increases.

[0068] Furthermore, a multi-objective optimization algorithm is introduced to set optimization weights for each device and optimize the resource requirements of each device to prevent a single device from occupying too many resources, ensuring that the needs of each device are reasonably met in resource allocation and achieving a balance of device resources.

[0069] Therefore, the dynamic control algorithm, on the one hand, minimizes the deviation of the environmental state so that the equipment can reach the target environmental state; on the other hand, by setting the upper limit of the equipment's resource usage, it ensures that when the equipment's resource demand exceeds the upper limit, the control signal will be automatically adjusted so that the equipment's resource consumption is reduced to a reasonable range, thereby ensuring energy saving and high efficiency.

[0070] The formula for generating the control signal is:

[0071]

[0072] Among them, u j,t+1 This represents the operation command, i.e., the control signal, generated by device j at the next time t+1; β j This represents the degree to which the adjustment capability of device j contributes to the control signal, i.e., the adjustment strength. It is set according to the expert experience method, and its value range is [0,1]. This represents the summation symbol, where the summation term i ranges from 1 to n, and n represents the number of sensors; f i,jThis represents the weight of sensor i's influence on device j's regulation, reflecting the contribution of each sensor's collected environmental parameters to the device's regulation. It is determined through expert experience and its value ranges from [0,1]. f i,j =1;S i,t+1 P represents the degree of matching between the predicted environmental parameters of sensor i and the suitable range at the next time t+1, i.e., the membership value; i,t+1 This represents the predicted environmental parameters of sensor i at the next time step t+1; x i,t This represents the environmental parameters collected by sensor i at the current time t; This represents the nonlinear deviation adjustment factor, used to smooth the deviation between predicted environmental parameters and current environmental parameters, avoiding excessive adjustment during periods of drastic fluctuations; tan -1 κ represents the arctangent function, used for nonlinear smoothing of the deviation value; the smoothing effect increases with increasing deviation. λ represents the sensitivity factor, used to control the smoothing effect of the arctangent function, determined through expert experience, and its value ranges from [0,1]. j Q represents the optimization weight of device j, used to balance the resource requirements of devices and avoid excessive resource consumption by a single device to achieve energy-saving effects. It is determined by expert experience and its value ranges from [0,1]. j This represents the amount of resources required by device j, used to constrain the resource usage of device j during control signal generation. The resource balance of the device is achieved through a multi-objective optimization algorithm, and the calculation method is as follows;

[0073]

[0074] Where min represents the minimum value operation; R represents the mean absolute difference between the sensor's predicted environmental parameters and the current environmental parameters, reflecting the total resources required by the equipment; j This indicates the maximum resource usage limit for device j, which is set according to the device's design requirements.

[0075] In the field of agricultural intelligent control, dynamic regulation algorithms can generate reasonable control signals under appropriate conditions, without wasting resources or over-regulating. This ensures the rational allocation and use of resources in IoT-based smart agricultural control systems. Even when resources are limited, limited resources can be used for environmental control in areas that urgently require regulation, and equipment can be intelligently controlled based on the generated control signals.

[0076] In summary, a smart agriculture control system and method based on the Internet of Things has been developed.

[0077] The order of the embodiments is for illustrative purposes only and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0078] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0079] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A smart agriculture control method based on the Internet of Things, characterized in that, Includes the following steps: S1: Collect environmental parameters and extract historical environmental parameters from the database. Calculate the average trend of environmental parameters using a dynamic adaptive trend prediction algorithm. The specific calculation formula is as follows: ； Where, Δx i This represents the average trend of environmental parameters collected by sensor i over a historical time period; x i,τ This represents the environmental parameters collected by sensor i at time τ; x i,τ -x i,τ-1 This represents the amount of data change between two adjacent time points; This represents the summation operation on the historical environmental parameter differences from τ=tm to τ=t; m represents the number of time points. Based on the average variation trend of environmental parameters, a suppression factor is introduced, combined with the tangent function, to construct a prediction model and obtain the predicted environmental parameters. The specific calculation formula for the predicted environmental parameters is as follows: ； Among them, P i,t+1 This represents the predicted environmental parameters of sensor i at the next time step t+1; x i,t γ represents the environmental parameters collected by sensor i at the current time t; i Represents the dynamic learning coefficient; tan(Δx) i ) represents the tangent function operation; θ represents the inhibition factor; S2: A multi-level fuzzy membership degree environmental adaptability evaluation algorithm is introduced. A suitable range for the flexible tolerance parameter and the predicted environmental parameters is set. Nonlinear decay is introduced through an exponential function to convert the predicted environmental parameters into membership degree values. The formula for calculating the membership degree value is: ； Among them, S i,t+1 This represents the degree of matching between the environmental parameters predicted by sensor i at the next time t+1 and the appropriate range, i.e., the membership value; a i and b i These represent the lower and upper limits of the suitable range for the environmental parameters predicted by sensor i, respectively; c i represents the flexibility tolerance parameter; exp represents an exponential function with the natural logarithm e as the base. S3: Based on current and predicted environmental parameters, a dynamic control algorithm quantifies the difference between the predicted state and the current actual state to obtain the deviation value of the environmental parameters. Based on the deviation value and membership value of the environmental parameters, combined with the upper limit of equipment resource usage, a control signal is generated to intelligently control the equipment. The formula for generating the control signal is: ； Among them, u j,t+1 This represents the control signal generated by device j at the next time t+1; β j Indicates the adjustment intensity of device j; n represents the number of sensors; f i,j This represents the weight of the influence of sensor i on the regulation of device j; This represents a nonlinear deviation adjustment factor used to smooth the deviation between predicted environmental parameters and current environmental parameters; tan -1 λ represents the arctangent function; λ represents the sensitivity factor; κ represents the arctangent function. j Q represents the optimization weight of device j; j This represents the amount of resources required by device j, used to constrain the resource usage of device j during control signal generation. The calculation method is as follows; ； Where min represents the minimum value operation; R represents the mean absolute difference between the sensor's predicted environmental parameters and the current environmental parameters; j This indicates the upper limit of resource usage for device j.

2. The smart agriculture control method based on the Internet of Things according to claim 1, characterized in that, S2 specifically includes: In the implementation of the multi-level fuzzy membership degree environmental adaptability assessment algorithm, if the predicted environmental parameters are between the upper and lower limits of the appropriate range, the environmental conditions are considered to be suitable.

3. An IoT-based smart agriculture control system, applied to the IoT-based smart agriculture control method described in claim 1, characterized in that, Includes the following parts: Sensor acquisition module, environmental parameter prediction module, environmental adaptability assessment module, control signal generation module, and equipment control module; Sensor acquisition module: Collects environmental parameters and outputs them to the environmental parameter prediction module and the control signal generation module; Environmental parameter prediction module: Receives environmental parameters from the sensor acquisition module, calculates predicted environmental parameters through a dynamic adaptive trend prediction algorithm, and outputs the predicted environmental parameters to the environmental adaptability assessment module and the control signal generation module; Environmental adaptability assessment module: Based on the predicted environmental parameters from the environmental parameter prediction module, the membership degree value is calculated using a multi-level fuzzy membership degree environmental adaptability assessment algorithm, and the membership degree value is output to the control signal generation module; Control signal generation module: Receives environmental parameters from sensor acquisition module, predicted environmental parameters from environmental parameter prediction module, and membership values ​​from environmental adaptability assessment module; generates control signals using dynamic control algorithm; and outputs the control signals to equipment control module. Equipment control module: performs intelligent control of the equipment based on control signals.

Images