Automatic intelligent cultivation system for high-value crops

Abstract

The invention discloses an automatic intelligent cultivation system for high-value crops, and the system comprises an environment monitoring module, a crop detection module, a central controller, a regulation and control decision module, an execution module, a system feedback and optimization module, and an intelligent algorithm control module. The temperature and humidity are adjusted through heat energy heating and refrigerating systems, and the optimal growth environment is created for crops. The AI is controlled through the whale optimization algorithm to adjust the light transmittance and the internal temperature and humidity. Meanwhile, solar energy is converted into electric energy and heat energy through the photovoltaic and photo-thermal dual-energy plate, a better growth environment is provided for agricultural products, and therefore the yield and quality of crops are effectively improved, and energy consumption and cost are reduced.

Description

Technical Field

[0001] The present invention relates to an automated intelligent cultivation system for high-value crops and relates to the field of intelligent agriculture. Background Art

[0002] With the acceleration of agricultural modernization, greenhouse technology plays a significant role in improving crop yield and quality by providing a stable growth environment. However, traditional greenhouses have high energy consumption, low light utilization, and poor environmental control flexibility, making them unable to meet the needs of efficient and energy-saving modern agriculture. The development of photovoltaic technology has provided a new way to power greenhouses, but existing photovoltaic greenhouses face problems such as the contradiction between photovoltaic panels blocking light and crop growth needs, and the inadequate balance between temperature and humidity control and energy efficiency, which limits the overall performance of the system. In recent years, artificial intelligence and bio-inspired optimization algorithms have shown potential in complex system control. However, there is still little research on intelligent control of photothermal and solar-thermal coordinated control in photovoltaic greenhouses, especially in the comprehensive strategies of dynamic light adjustment, integrated thermal energy management, and multi-objective optimization. Therefore, there is an urgent need for a technical solution that integrates photovoltaic power generation, intelligent control, and environmental optimization to overcome the limitations of traditional greenhouses, achieve the dual benefits of crop growth and energy utilization, and support the sustainable development of modern agriculture. Summary of the Invention

[0003] Purpose of the invention: The purpose of the present invention is to provide an automated intelligent cultivation system for high-value crops, improve energy efficiency, reduce greenhouse operating costs, create a suitable growth environment for crops, increase yield and quality, and promote the precision and sustainable development of agricultural production.

[0004] Technical solution: The high-value crop automated intelligent cultivation system described in the present invention includes: an environmental monitoring module, a data processing module, a crop detection module, a central controller, a control and decision-making module, an execution module, and a system feedback and optimization module;

[0005] Environmental monitoring module: uses sensors to monitor environmental data in real time, including light intensity, temperature and humidity, soil moisture, and carbon dioxide concentration;

[0006] Data processing module: pre-process the collected environmental data;

[0007] System feedback and optimization module: fine-tunes control parameters based on the difference between real-time environmental data and preset target values;

[0008] Intelligent algorithm control module: uses the whale optimization algorithm to regulate the temperature and humidity growth environment of crops.

[0009] Preferably, the system also includes a crop detection module, which detects the growth of crops in real time, monitors plant height, leaf area and stem diameter, waits for the plants to mature, and continues to detect their protein and sugar content; uses a high-definition camera to capture crop images, and uses image processing technology to extract leaf area, plant height and stem diameter; uses a near-infrared spectrometer to scan crop samples, and estimates protein and sugar content by analyzing spectral data.

[0010] Preferably, the system also includes a central controller, which adopts microprocessor and embedded system technology, combined with real-time operating system RTOS, to realize the management and control of the automated intelligent cultivation system. The central controller has data processing capabilities and high-speed communication interface, receives data from the environmental monitoring module in real time, and coordinates the actions of the execution module according to the instructions of the control decision module.

[0011] Preferably, the system also includes a control and decision-making module, which analyzes and processes the data collected by the environmental monitoring module based on machine learning and data mining technology, uses prediction models and whale optimization algorithms to predict the growth needs of crops and environmental change trends, and formulates control strategies accordingly.

[0012] Preferably, the system further comprises an execution module, including various actuators directly controlled by a central controller, using a PID control algorithm to ensure that the actuators move accurately and achieve precise control of environmental parameters.

[0013] Preferably, the preprocessing includes noise filtering, outlier removal, and data standardization.

[0014] Preferably, the whale optimization algorithm optimizes and adjusts the temperature and humidity growth environment of crops, and the objective function formula is as follows:

[0015]

[0016] T(t)=T opt +k T ·(F(t)-F target )

[0017] H(t)=H opt +k H ·(F(t)-F target )

[0018]

[0019] Wherein, F(t) is a plant growth index, h(t) is a plant height, A(t) is a leaf area, d1(t) is a stem diameter, P(t) is a protein content, S(t) is a sugar content, a, b, g, d, o are corresponding weight coefficients, representing the contribution degree of different growth indexes to the objective function, l is a decay factor, t is an integral variable, e -λ(t-τ) is an exponential decay term, T(t) is an adjusted temperature, H(t) is an adjusted humidity, T opt is an optimal temperature, H opt is an optimal humidity, k T and k H are adjustment coefficients, F(t) is an objective function of a comprehensive growth state, F target is an optimal objective growth state, the temperature T(t) is adjusted to the optimal temperature T opt , and the difference between the growth state F(t) of the plant and the target growth state F target is adjusted; if F(t) is higher than F target , the temperature is increased; if F(t) is lower than F target , the temperature is decreased, the humidity H(t) is adjusted to the optimal humidity H opt , and the difference between the growth state F(t) of the plant and the target growth state F target is adjusted; if F(t) is higher than F target , the humidity is increased; if F(t) is lower than F target , the humidity is decreased, P0 is an initial protein content, k1 and k2 are coefficients related to soil nutrients and water, N(t) is a change of soil nutrients with time, W(t) is a change of water with time, S0 is an initial sugar content, k3 and k4 are coefficients related to light and temperature, L(t) is a change of light with time, and T(t) is a change of temperature with time.

[0020] Preferably, in the initialization of the whale population stage, the whale optimization algorithm generates a plurality of random solutions and evaluates the fitness value of each solution, and the fitness evaluation formula is:

[0021]

[0022] Wherein, is the position of the i-th whale in the t-th generation, a is a convergence factor, r1 and r2 are random numbers uniformly distributed in the interval [0, 1], corresponding to the plant height and leaf area in the objective function respectively.

[0023] Preferably, in the whale optimization algorithm, the chain foraging position updating formula is:

[0024]

[0025] Wherein, a is a convergence factor.

[0026] Preferably, in the whale optimization algorithm, the movement speed of the whale is adjusted according to the global optimal solution and the individual optimal solution, and the update formula is:

[0027]

[0028] Wherein, w is the inertia weight, is the speed of the i-th whale in the t-th generation, c1 and c2 are acceleration constants, respectively controlling the influence weight of the individual optimal solution and the global optimal solution, r1 and r2 are random numbers, respectively randomly generated in the interval [0, 1], is the individual optimal solution of the i-th whale in the t-th generation, and is the current global optimal solution.

[0029] Beneficial effects: Compared with the prior art, the present application has the following remarkable advantages:

[0030] (1) The present application uses intelligent algorithm control module to give the best scheme between battery energy storage station charging and discharging, light regulation device and temperature and humidity regulation device by using whale optimization algorithm, and the system intelligently optimizes the light, temperature and humidity mode according to the environmental monitoring data, ensuring efficient and stable growth of crops.

[0031] (2) The present application uses light-transmitting photovoltaic panel power supply system to save energy and realize green power supply. The temperature and humidity regulation device operates using photovoltaic power to dynamically maintain a suitable environment, effectively improving crop yield and quality, while reducing dependence on external energy. The sensor group intelligently monitors environmental changes to drive the light and temperature and humidity regulation device to adjust to the best mode in time, improving system operation efficiency.

[0032] (3) The whale optimization algorithm of the present application significantly improves the control accuracy and response speed compared with traditional algorithms, ensuring the optimal adaptability of the greenhouse environmental parameters and providing intelligent support for modern agriculture. BRIEF DESCRIPTION OF DRAWINGS

[0033] Figure 1 The present application is a system structure schematic diagram.

[0034] Figure 2 The present application is a whale optimization algorithm flowchart.

[0035] Figure 3 The present application is a hardware framework schematic diagram. DETAILED DESCRIPTION

[0036] The technical solutions of the present application will be further described below in conjunction with the drawings.

[0037] The application provides an automatic intelligent cultivation system for high-value crops, which comprises an environment monitoring module, a crop detection module, a central controller, a regulation and decision module, an execution module, and a system feedback and optimization module.

[0038] The environment monitoring module uses sensors to monitor environmental data in real time, including but not limited to light intensity, temperature and humidity, soil moisture, and carbon dioxide concentration.

[0039] The data processing module performs data preprocessing on the collected environmental data.

[0040] The system feedback and optimization module adjusts the control parameters based on the difference between real-time environmental data and preset target values.

[0041] The intelligent algorithm control module uses whale optimization algorithm to regulate the temperature and humidity of the crop growth environment.

[0042] The central controller uses advanced microprocessors and embedded system technology, combined with real-time operating system (RTOS), to achieve efficient management and control of the entire automatic intelligent cultivation system. The controller has powerful data processing capabilities and high-speed communication interfaces, can receive data from the environment monitoring module in real time, and coordinate the actions of the execution module according to the instructions of the regulation and decision module. The central controller mainly solves the problem of information integration and coordination between the modules in the system, ensuring that the system can respond quickly to real-time data. It is also responsible for the stability and reliability of the system, through fault detection and self-diagnosis functions, to timely detect and handle abnormal situations in the system.

[0043] The regulation and decision module is based on artificial intelligence algorithms, especially machine learning and data mining techniques, to analyze and process the data collected by the environment monitoring module. The module uses prediction models and whale optimization algorithms to predict the growth needs of crops and environmental trends, and accordingly formulates regulation strategies. The regulation and decision module mainly solves the problem of how to intelligently adjust environmental parameters such as temperature, humidity, and light according to real-time environmental data and the growth state of crops, to optimize the growth environment of crops. It analyzes historical data and current environmental conditions to predict future environmental changes, thereby making regulation decisions in advance and improving the adaptability and efficiency of the system.

[0044] The execution module includes various actuators controlled directly by the central controller. The execution module uses precise control technology and PID control algorithm to ensure the accuracy of the actuator's action, to achieve precise regulation of environmental parameters. The execution module mainly solves the problem of how to convert the strategies formulated by the regulation and decision module into actual physical actions, such as adjusting light transmittance and changing temperature and humidity. It ensures that the regulation measures can be accurately and timely executed, thereby providing the best growth environment for crops.

[0045] The system includes a light-transmitting photovoltaic panel, which is made of an electrochromic material with adjustable light transmittance. The light transmittance of these photovoltaic panels can be changed by applying voltage or current.

[0046] The environmental monitoring module utilizes a high-precision sensor network to monitor real-time environmental variables such as light intensity, temperature and humidity, soil moisture, and carbon dioxide concentration inside and outside the greenhouse. By strategically deploying a variety of sensors inside and outside the greenhouse, the system acquires comprehensive and accurate environmental data, supporting subsequent regulation and decision-making.

[0047] The data processing module performs data preprocessing on the collected environmental data, including noise filtering, outlier removal, data standardization and other steps to ensure data quality and accuracy. The processed data is then transmitted in real time via high-speed wireless transmission technology.

[0048] The crop detection module detects crop growth in real time, monitoring plant height, leaf area, and stem diameter, and then waits for the plants to mature before continuing to detect their protein and sugar content. It uses a high-definition camera to capture crop images and extracts leaf area, plant height, and stem diameter through image processing technology. It uses a near-infrared spectrometer to scan crop samples and estimate protein and sugar content by analyzing spectral data. It adjusts environmental factors inside the greenhouse based on the growth characteristics and environmental conditions of the crops to ensure that the crops grow under the most favorable conditions at each growth stage, thereby increasing yield and ensuring crop quality.

[0049] The system's feedback and optimization module adjusts control measures in real time based on the discrepancies between real-time environmental data and preset target values. By calculating the deviations between different environmental variables, the system can promptly fine-tune control parameters to ensure the optimal crop growth environment. Furthermore, the system continuously accumulates historical data and optimizes control strategies through a data feedback mechanism, gradually improving control precision and enhancing the system's adaptability to changing environmental conditions.

[0050] The Whale Optimization Algorithm (WOA) optimizes and adjusts the temperature and humidity growth environment of crops. The objective function formula is as follows:

[0051]

[0052] T(t)=T opt +k T ·(F(t)-F target )

[0053] H(t)=H opt +k H ·(F(t)-F target )

[0054]

[0055] Among them, F(t) is the plant growth index, h(t) is the plant height, A(t) is the leaf area, stem diameter is d1(t), protein content is P(t), and sugar content is S(t). These indicators change with time t; α, β, γ, δ, ò are the corresponding weight coefficients, indicating the contribution of different growth indicators to the objective function. λ is the decay factor, indicating that the influence of past information on the current state gradually decreases over time. τ is the integral variable, representing each moment from the beginning to time t. e -λ(t-τ) is an exponential decay term, indicating that the influence of past information on the current state decays over time. This reflects the dynamic nature of crop growth, that is, the recent growth state has a greater impact on the current state. T(t) is the adjusted temperature. H(t) is the adjusted humidity. T opt is the optimum temperature. opt Is the optimum humidity. T and k H is the adjustment coefficient, which indicates the sensitivity of temperature and humidity to plant growth status. F(t) is the objective function of comprehensive growth status. target is the optimal target growth state, that is, the growth level we hope the plant will achieve. The temperature T(t) is adjusted to the optimum temperature T opt Based on the plant growth state F(t) and the target growth state F target If F(t) is higher than F target , then increase the temperature; if F(t) is lower than F target , then lower the temperature. Humidity H(t) is adjusted to the optimum humidity H opt Based on the plant growth state F(t) and the target growth state F target If F(t) is higher than F target , then increase the humidity; if F(t) is lower than F target , then reduce the humidity. P0 is the initial protein content. k1 and k2 are coefficients related to soil nutrients and water content. N(t) is the change in soil nutrients over time. W(t) is the change in water content over time. S0 is the initial sugar content. k3 and k4 are coefficients related to light and temperature. L(t) is the change in light over time. T(t) is the change in temperature over time.

[0056] The implementation process of the whale optimization algorithm includes:

[0057] (1) Initialize the whale population, generate multiple random solutions and evaluate the fitness value of each solution as the starting point of the optimization process. These solutions are randomly initialized in the search space, and the fitness of each solution is evaluated by the objective function. The design of the objective function requires the integration of multiple environmental factors and control parameters. The fitness evaluation formula is:

[0058]

[0059] in, is the position of the i-th whale in the t-th generation, a is the convergence factor, r1 and r2 are random numbers uniformly distributed in the interval [0,1], corresponding to the plant height and leaf area in the objective function respectively. By introducing random numbers r1 and r2, the whale position can be prevented from falling into the local optimal solution. is the global optimal position of all whales in the current iteration.

[0060] (2) Using chain foraging behavior, the global optimal solution is used to guide all whales to move towards the solution in each iteration step. In each iteration, each member of the whale group will move according to the current optimal solution. Update your own position. The optimal solution is the optimal target growth state. The position update formula is adjusted according to the behavior patterns simulated by whales, including chain foraging behavior, spiral foraging behavior, and rolling foraging behavior. The general formula for position update is chain foraging position update formula is:

[0061]

[0062] Where a is the convergence factor, which decreases gradually as the iteration proceeds. The chain foraging behavior enables each whale to search near the global optimal solution, gradually approaching the optimal solution.

[0063] (3) When the optimal solution is found, a spiral approach is used to simulate the way whales approach food through rotational motion, further optimizing the quality of the solution. If the optimal solution is not found, a rolling foraging method is used to enhance the diversity of the search and avoid being trapped in a local optimal solution.

[0064]

[0065] Where φ is the convergence factor that decreases with iteration, μ is the dynamic factor, b is the frequency of the spiral, t is the current iteration number, r1 is a random factor that controls the amplitude of the spiral, r2 and r3 are random numbers uniformly distributed on the [0, 1] range, and the sign function represents the tumbling direction.

[0066] (4) In each update, the whale not only updates its position, but also adjusts its movement speed according to the global optimal solution and the personal optimal solution. The update formula is:

[0067]

[0068] where w is the inertia weight, which determines the movement inertia of the whale, and is usually set between [0, 1]; is the speed of the i-th whale in the t-th generation, c1 and c2 are acceleration constants, respectively controlling the influence weight of the individual optimal solution and the global optimal solution, r1 and r2 are random numbers, respectively randomly generated in the interval [0, 1], and are used to introduce randomness, is the individual optimal solution of the i-th whale in the t-th generation, and is the current global optimal solution.

[0069] (5) taking plant height, stem diameter and leaf area as input, and crop temperature and humidity growth environment as output, the optimal sugar content and protein of the plant, i.e. the optimal plant, is obtained, and it is judged whether the stopping condition is met or not, the stopping condition is whether the output three times proportion is the same value or not, if yes, the loop is exited, otherwise, steps (1) to (4) are repeatedly executed until the loop is exited, and finally the optimal plant state is output.

[0070] The application discloses an automatic intelligent cultivation technology for high-value crops, comprising an environment monitoring module, a crop detection module, a central controller, a regulation and decision module, an execution module, a system feedback and optimization module; the photovoltaic greenhouse is covered with light-transmitting photovoltaic panels, and the electric energy provided by photovoltaic power generation is used for sensors and temperature regulation devices of the greenhouse; the growth conditions of crops are detected in real time, the plant height, leaf area and stem diameter are monitored, the plant is waited to mature, and the protein and sugar content of the plant are continuously detected; the intelligent regulation system combines AI technology, monitors and feeds back parameters such as temperature, humidity and light intensity through the above-mentioned several modules, adjusts the temperature and humidity by using a heating and refrigeration system, and creates the best growth environment for crops. The energy storage and energy management system stores the electric energy generated by the photovoltaic panels, and reasonably allocates the electric energy for the operation of the equipment in the greenhouse, and controls the AI to adjust the light transmittance and internal temperature and humidity by using a whale optimization algorithm. At the same time, the system converts solar energy into electric energy and heat energy by using photovoltaic and photothermal dual-energy panels, realizes better provision of a growth environment for agricultural products, and effectively improves the crop yield and quality and reduces energy consumption and cost.

Claims

1. A high-value crop automated intelligent cultivation system, characterized in that: include: Environmental monitoring module, data processing module, crop detection module, central controller, control and decision-making module, execution module, system feedback and optimization module; Environmental monitoring module: uses sensors to monitor environmental data in real time, including light intensity, temperature and humidity, soil moisture, and carbon dioxide concentration; Data processing module: pre-process the collected environmental data; System feedback and optimization module: fine-tunes control parameters based on the difference between real-time environmental data and preset target values; Intelligent algorithm control module: uses the whale optimization algorithm to regulate the temperature and humidity growth environment of crops.

2. The high-value crop automated intelligent cultivation system according to claim 1, characterized in that: The system also includes a crop detection module that detects crop growth in real time, monitors plant height, leaf area, and stem diameter, and waits for the plants to mature before continuing to detect their protein and sugar content. It uses a high-definition camera to capture crop images and uses image processing technology to extract leaf area, plant height, and stem diameter. It uses a near-infrared spectrometer to scan crop samples and estimate protein and sugar content by analyzing spectral data.

3. The high-value crop automated intelligent cultivation system according to claim 1, characterized in that: The system also includes a central controller, which uses microprocessor and embedded system technology, combined with a real-time operating system RTOS, to achieve management and control of the automated intelligent cultivation system. The central controller has data processing capabilities and a high-speed communication interface, receives data from the environmental monitoring module in real time, and coordinates the actions of the execution module according to the instructions of the control decision module.

4. The high-value crop automated intelligent cultivation system according to claim 1, characterized in that: The system also includes a control and decision-making module, which analyzes and processes the data collected by the environmental monitoring module based on machine learning and data mining technologies, and uses prediction models and whale optimization algorithms to predict the growth needs of crops and environmental change trends, and formulates control strategies accordingly.

5. The high-value crop automated intelligent cultivation system according to claim 1, characterized in that: The system also includes an execution module, including various actuators directly controlled by the central controller, using PID control algorithm to ensure the accuracy of the actuator's movements and achieve precise regulation of environmental parameters.

6. The high-value crop automated intelligent cultivation system according to claim 1, characterized in that: The preprocessing includes noise filtering, outlier removal, and data standardization.

7. The high-value crop automated intelligent cultivation system according to claim 1, characterized in that: The Whale Optimization Algorithm optimizes and adjusts the temperature and humidity growth environment of crops. The objective function formula is as follows: T(t)=T opt +k T ·(F(t)-F target ) H(t)=H opt +k H ·(F(t)-F target ) Among them, F(t) is the plant growth index, h(t) is the plant height, A(t) is the leaf area, stem diameter is d1(t), protein content is P(t), and sugar content is S(t); α, β, γ, δ, ò are the corresponding weight coefficients, indicating the contribution of different growth indicators to the objective function; λ is the attenuation factor; τ is the integral variable, e -λ(t-τ) is an exponential decay term, T(t) is the adjusted temperature; H(t) is the adjusted humidity, T opt is the optimum temperature, H opt is the optimum humidity, k T and k H is the adjustment coefficient, F(t) is the objective function of the comprehensive growth state, F target It is the optimal target growth state, and the temperature T(t) is adjusted to the optimum temperature T opt Based on the plant growth state F(t) and the target growth state F target If F(t) is higher than F target , then increase the temperature; if F(t) is lower than F target , then lower the temperature and adjust the humidity H(t) to the optimum humidity H opt Based on the plant growth state F(t) and the target growth state F target If F(t) is higher than F target , then increase the humidity; if F(t) is lower than F target , then reduce the humidity, P0 is the initial protein content, k1 and k2 are coefficients related to soil nutrients and water, N(t) is the change of soil nutrients over time, W(t) is the change of water over time, S0 is the initial sugar content, k3 and k4 are coefficients related to light and temperature, L(t) is the change of light over time, and T(t) is the change of temperature over time.

8. The high-value crop automated intelligent cultivation system according to claim 1, characterized in that: The whale optimization algorithm generates multiple random solutions and evaluates the fitness value of each solution during the whale population initialization phase. The fitness evaluation formula is: in, is the position of the ith whale in the tth generation, a is the convergence factor, r1 and r2 are random numbers uniformly distributed in the interval [0,1], corresponding to the plant height and leaf area in the objective function, respectively.

9. The high-value crop automated intelligent cultivation system according to claim 1, characterized in that: In the whale optimization algorithm, the chain foraging position update formula is: Where a is the convergence factor.

10. The high-value crop automated intelligent cultivation system according to claim 1, characterized in that: In the whale optimization algorithm, the movement speed of the whale is adjusted according to the global optimal solution and the personal optimal solution. The update formula is: Where w is the inertia weight, is the speed of the i-th whale in the t-th generation, c1 and c2 are acceleration constants, which control the influence weights of the personal optimal solution and the global optimal solution respectively, r1 and r2 are random numbers, which are randomly generated in the interval [0,1]. is the personal optimal solution of the i-th whale in the t-th generation and is the current global optimal solution.

Images