Hilly slope irrigation control system based on artificial intelligence

Abstract

The invention discloses a hilly slope irrigation control system based on artificial intelligence, and the system comprises a wind speed and wind direction detection module which is used for obtaining wind speed and wind direction data; the sprinkler head adjusting module is used for adjusting the angle and the spraying distance of a sprinkler head based on the wind speed and wind direction data; the soil humidity detection module is used for being connected with a soil humidity sensor and determining irrigation requirements according to data of the soil humidity sensor; the artificial intelligence control module is used for optimizing the irrigation time and the irrigation amount through an artificial intelligence algorithm; the sprinkling irrigation system control module is used for controlling the sprinkling irrigation system to irrigate according to the optimization result; the hilly slope irrigation control system based on artificial intelligence reduces the phenomenon of non-uniform growth of crops, facilitates healthy and uniform growth of the crops, and ensures that the crops can obtain a proper amount of water supply, so that normal growth and development of the crops are promoted, the yield and quality of the crops are improved, and the agricultural production benefits are further improved.

Description

Technical Field

[0001] The present invention relates to the field of agricultural automation and intelligent irrigation technology, and in particular to an artificial intelligence-based hilly slope irrigation control system. Background Art

[0002] In the existing agricultural irrigation technology, sprinkler irrigation system is widely used due to its water-saving and high efficiency. However, the existing sprinkler irrigation system shows obvious shortcomings under strong wind conditions. Due to the influence of wind speed, the water droplets sprayed by the sprinkler head are easily blown away in the air by the wind, resulting in the water droplets not accurately falling on the target area, resulting in the phenomenon of water droplets drifting. This not only causes a waste of water resources, but also reduces the irrigation effect of sprinkler irrigation, and cannot fully meet the water demand of crops. This problem is particularly prominent in areas where wind speed changes frequently.

[0003] Most existing sprinkler irrigation systems lack an adjustment mechanism for wind speed changes and are unable to effectively control the sprinkler water flow according to the wind speed, further exacerbating the waste of water resources. In addition, the impact of wind on water droplet dispersion also leads to over-irrigation or under-irrigation in local areas, affecting the uniform growth of crops. In order to solve this problem, the existing technology urgently needs an improved solution that can reduce water droplet dispersion in strong wind conditions to improve irrigation accuracy and resource utilization efficiency. Summary of the invention

[0004] The purpose of the present invention is to provide an artificial intelligence-based hilly slope irrigation control system to solve the problem that most of the existing sprinkler irrigation systems lack an adjustment mechanism for wind speed changes and cannot effectively control the sprinkler water flow according to the wind speed, thereby further aggravating the waste of water resources. In addition, the influence of wind on the dispersion of water droplets also leads to over-irrigation or insufficient irrigation in local areas, affecting the uniform growth of crops.

[0005] To achieve the above object, the present invention provides the following technical solution: an artificial intelligence-based hilly slope irrigation control system, the system comprising:

[0006] Wind speed and wind direction detection module, used to obtain wind speed and wind direction data;

[0007] The sprinkler head adjustment module connected to the wind speed and wind direction detection module is used to adjust the angle and spray distance of the sprinkler head based on the wind speed and wind direction data. Specifically, the utility functions of different wind speeds and wind directions are designed to represent the optimal states of spray distance, angle and water flow distribution respectively. The best sprinkler head parameter combination under the current wind speed and wind direction is solved, and the spray angle and distance are automatically adjusted according to the optimal strategy combination. The specific solution process is as follows:

[0008] Among them, u iRepresents the utility function of different wind speeds and directions, s i Indicates the angle or spray distance setting of the sprinkler head. It indicates the optimal angle or spray distance setting of the sprinkler head under the current wind speed and wind direction conditions. si indicates the angle and distance setting of the sprinkler head under other wind speed and wind direction conditions. It indicates the sprinkler head parameter combination when all other wind speed and wind direction conditions adopt their own optimal strategies;

[0009] A soil moisture detection module, used to connect to a soil moisture sensor and determine irrigation needs based on data from the soil moisture sensor;

[0010] The artificial intelligence control module connected to the wind speed and direction detection module and the soil moisture detection module is used to optimize the irrigation time and irrigation amount through the artificial intelligence algorithm. Specifically, the irrigation demand and environmental data are constructed into a small-world network model. Each node in the network represents a different irrigation condition. The edges between the nodes represent the mutual influence between the conditions. The average path length and clustering coefficient of each node are calculated. The calculation formula is:

[0011]

[0012] Among them, N represents the number of network nodes, k represents the average degree of nodes, L represents the average path length of each node, and C represents the clustering coefficient;

[0013] The sprinkler irrigation system control module connected to the artificial intelligence control module is used to control the sprinkler irrigation system for irrigation according to the optimization results.

[0014] Preferably, the wind speed and wind direction detection module acquires wind speed and wind direction data including:

[0015] Collect historical wind speed and direction data, calculate the fluctuation of the data and apply the autoregressive conditional heteroskedasticity model to estimate the conditional variance. The specific formula is:

[0016]

[0017] in, represents the variance at the current moment, ∈ t-1 represents the error at the previous moment, σ t-1 represents the standard deviation of the variance at the previous moment, and α0, α1, β1 represent the parameters of the model.

[0018] Preferably, the soil moisture detection module is connected to a soil moisture sensor and determines the irrigation demand according to the data of the soil moisture sensor, including:

[0019] Collect soil moisture sensor data, analyze its frequency domain characteristics through Fourier transform, identify seasonal or fluctuating frequency components in soil moisture signals, and predict water loss or soil drying trends. The Fourier transform formula is:

[0020]

[0021] Among them, X(q) represents the component of the frequency domain signal, x(n) represents the data point of the time domain signal, M represents the total number of sampling points of the signal, q represents the frequency index, and n represents the time index.

[0022] Preferably, the sprinkler irrigation system control module controls the sprinkler irrigation system to irrigate according to the optimization result, including:

[0023] Irrigation time, irrigation amount, wind speed, and soil moisture are defined as random variables, and irrigation scenarios are simulated. In each simulated scenario, the corresponding irrigation effect is calculated, and the irrigation time and irrigation amount under the combination are generated. All simulation results are expected to be calculated, and the optimal irrigation plan that can perform stably in different environments is selected as the final optimization result. The expected calculation formula is:

[0024]

[0025] Where E[X] is the expected value of variable X, x represents a random variable, N represents the number of simulations, and X i represents the result of the ith simulation.

[0026] Preferably, the sprinkler head adjustment module adjusts the angle and spray distance of the sprinkler head based on the wind speed and wind direction data and further includes:

[0027] Determine wind force level based on wind speed data;

[0028] Adjust the angle of the sprinkler head according to the wind level;

[0029] Adjust the spray distance of the sprinkler head according to the wind level;

[0030] When the wind speed exceeds a preset threshold, the amount of water sprayed by the sprinkler head is reduced.

[0031] Preferably, determining the wind force level based on wind speed data comprises:

[0032] Get real-time wind speed data V;

[0033] Compare wind speed data with a preset wind force scale table;

[0034] Determine the current wind force level L based on the comparison result;

[0035] Determine whether the wind force level L is greater than or equal to 3;

[0036] The specific formula is: L=f(V), where V represents real-time wind speed data and L represents wind force level.

[0037] Preferably, adjusting the angle of the sprinkler head according to the wind force level includes:

[0038] Get the current wind force level L;

[0039] Determine the angle adjustment value θ based on the wind force level L;

[0040] Adjust the angle of the sprinkler head to the current angle plus the adjustment value θ;

[0041] Determine whether the adjusted angle is within a safe range, and if so, perform the adjustment;

[0042] The specific formula is: θ=g(L), where L represents the wind force level and θ represents the angle adjustment value.

[0043] Preferably, the step of adjusting the spray distance of the sprinkler head according to the wind force level includes:

[0044] Get the current wind force level L;

[0045] Determine the spray distance adjustment value D based on the wind force level L;

[0046] Adjust the spray distance of the sprinkler head to the current spray distance minus the adjustment value D;

[0047] Determine whether the adjusted spray distance is within the safe range;

[0048] Formula: D = h (L), where L represents the wind force level and D represents the spray distance adjustment value;

[0049] When the wind speed exceeds a preset threshold, reducing the water spraying amount of the sprinkler head includes:

[0050] Get the current wind speed V;

[0051] Determine the water spray adjustment coefficient K based on the wind speed V;

[0052] Reduce the current water spraying amount multiplied by the adjustment coefficient K;

[0053] Determine whether the reduced water spray volume is within the allowable range;

[0054] Formula: K = i(V), where V represents real-time wind speed data and K represents the water spray adjustment coefficient.

[0055] Preferably, obtaining the current wind speed V includes:

[0056] Collect data from wind speed sensors;

[0057] Smooth the wind speed data to reduce the impact of noise;

[0058] Calculate the average wind speed V based on the smoothed wind speed data;

[0059] Determine whether the average wind speed V exceeds a preset threshold;

[0060] Formula: V = (V1 + V2 + ... + V r ) / r, where V1, V2, ..., V r represents wind speed data measured multiple times, r represents the number of measurements, and V represents the average wind speed after smoothing.

[0061] Preferably, the soil moisture detection module is connected to a soil moisture sensor and determines the irrigation demand according to the data of the soil moisture sensor, and further comprises:

[0062] Get the real-time data S of the soil moisture sensor;

[0063] The real-time data S is compared with the preset soil moisture threshold S min Make comparisons;

[0064] When the soil moisture is lower than the preset threshold S min When the irrigation demand signal is triggered.

[0065] It can be seen from the above technical solution that the present invention has the following beneficial effects:

[0066] The hilly slope irrigation control system based on artificial intelligence obtains wind speed and direction data through the wind speed and wind direction detection module. The sprinkler head adjustment module adjusts the angle and spray distance of the sprinkler head based on the wind speed and wind direction data. The soil moisture detection module is connected to the soil moisture sensor and determines the irrigation demand according to the data of the soil moisture sensor. The artificial intelligence control module optimizes the irrigation time and irrigation amount through the artificial intelligence algorithm. The sprinkler system control module controls the sprinkler system for irrigation according to the optimization result. It can automatically adjust the spray angle and spray distance of the sprinkler head according to the real-time change of wind speed, so that water droplets can fall on the target area more accurately, reduce the deviation and dispersion of water droplets caused by wind, and reduce the phenomenon of sprinkler water drifting and evaporation in the air, thereby effectively reducing the waste of water resources. Especially in areas with water shortages, this water-saving effect is particularly important. It helps to improve agricultural water use efficiency, ensure that irrigation effects are not significantly affected, improve the adaptability of the system in complex environments, avoid over-irrigation or under-irrigation in local areas, reduce uneven crop growth, and is conducive to the healthy and uniform growth of crops. It ensures that crops can obtain an appropriate amount of water supply, thereby promoting the normal growth and development of crops, increasing the yield and quality of crops, and thus improving agricultural production efficiency. It solves the problem that most existing sprinkler irrigation systems lack an adjustment mechanism for wind speed changes and cannot effectively control the sprinkler water flow according to the wind speed, thereby further aggravating the waste of water resources. In addition, the impact of wind on the dispersion of water droplets also leads to over-irrigation or under-irrigation in local areas, affecting the uniform growth of crops. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 It is a schematic diagram of the connection of the system modules of the present invention. DETAILED DESCRIPTION

[0068] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0069] like Figure 1 As shown, the present invention provides a technical solution: an artificial intelligence-based hilly slope irrigation control system, the system comprising:

[0070] Wind speed and wind direction detection module, used to obtain wind speed and wind direction data;

[0071] The sprinkler head adjustment module connected to the wind speed and wind direction detection module is used to adjust the angle and spray distance of the sprinkler head based on the wind speed and wind direction data. Specifically, the utility functions of different wind speeds and wind directions are designed to represent the optimal states of spray distance, angle and water flow distribution respectively. The best sprinkler head parameter combination under the current wind speed and wind direction is solved, and the spray angle and distance are automatically adjusted according to the optimal strategy combination. The specific solution process is as follows:

[0072] Among them, u i Represents the utility function of different wind speeds and directions, s i Indicates the angle or spray distance setting of the sprinkler head. Indicates the optimal angle or spray distance setting of the sprinkler head under the current wind speed and direction conditions, s -i Indicates the angle and distance settings of the sprinkler head under other wind speed and direction conditions. It indicates the sprinkler head parameter combination when all other wind speed and wind direction conditions adopt their own optimal strategies;

[0073] A soil moisture detection module, used to connect to a soil moisture sensor and determine irrigation needs based on data from the soil moisture sensor;

[0074] The artificial intelligence control module connected to the wind speed and direction detection module and the soil moisture detection module is used to optimize the irrigation time and irrigation amount through the artificial intelligence algorithm. Specifically, the irrigation demand and environmental data are constructed into a small-world network model. Each node in the network represents a different irrigation condition. The edges between the nodes represent the mutual influence between the conditions. The average path length and clustering coefficient of each node are calculated. The calculation formula is:

[0075]

[0076] Among them, N represents the number of network nodes, k represents the average degree of nodes, L represents the average path length of each node, and C represents the clustering coefficient;

[0077] The sprinkler irrigation system control module connected to the artificial intelligence control module is used to control the sprinkler irrigation system for irrigation according to the optimization results.

[0078] The system obtains wind speed and direction information through the wind speed and wind direction detection module and transmits it to the sprinkler head adjustment module. The sprinkler head adjustment module automatically adjusts the sprinkler angle and distance according to the current wind speed and wind direction to ensure that the water flow can accurately reach the target area. Subsequently, the soil moisture detection module monitors the soil moisture in real time and feeds back to the artificial intelligence control module. The artificial intelligence control module uses the small world network model based on the wind speed, wind direction and soil moisture data to analyze the mutual influence between nodes, calculate the average path length and clustering coefficient of each node, thereby optimizing the irrigation time and irrigation amount, and finally the sprinkler system control module performs irrigation. The sprinkler angle and distance are dynamically adjusted according to the wind speed and wind direction, so that the water flow can effectively cover the target area and reduce the waste of water resources. The artificial intelligence module optimizes the irrigation time and water volume, improves the irrigation efficiency, meets the real-time demand for soil moisture, reduces the waste of irrigation time and water, and has a significant water resource saving effect. The system can be adaptively adjusted according to the actual wind speed, wind direction and soil moisture conditions, and is suitable for variable hilly slope environments.

[0079] The wind speed and wind direction detection module obtains wind speed and wind direction data including:

[0080] Collect historical wind speed and direction data, calculate the fluctuation of the data and apply the autoregressive conditional heteroskedasticity model to estimate the conditional variance. The specific formula is:

[0081]

[0082] in, represents the variance at the current moment, ∈ t-1 represents the error at the previous moment, σ t-1 represents the standard deviation of the variance at the previous moment, and α0, α1, β1 represent the parameters of the model.

[0083] The system collects current and historical wind speed and wind direction data through the wind speed and wind direction detection module, and uses these data for volatility analysis. The calculation module uses the autoregressive conditional heteroskedasticity model to estimate the conditional variance of wind speed and wind direction data, that is, the volatility of the data. The ARCH model introduces the lag term of the time series so that the current variance is related to the error and variance value of the previous moment, so that the volatility of wind speed and wind direction changes can be captured dynamically. This method can effectively predict the changing trend of wind speed and wind direction in the short term, provide a basis for the precise adjustment of the irrigation system, and help the system better adapt to changes in environmental conditions. By dynamically analyzing the fluctuation of wind speed and wind direction data, the system's prediction accuracy for future wind speed and wind direction changes is improved, which helps to control irrigation parameters more accurately, and can instantly capture the fluctuation trend of wind speed and wind direction, so that the system can quickly adapt to environmental changes in a short period of time and optimize irrigation efficiency. The wind speed and wind direction prediction based on the statistical model makes the irrigation control of the system more scientific, which helps to improve the utilization efficiency of water resources and reduce unnecessary water waste.

[0084] The soil moisture detection module connects to the soil moisture sensor and determines the irrigation demand based on the data of the soil moisture sensor, including:

[0085] Collect soil moisture sensor data, analyze its frequency domain characteristics through Fourier transform, identify seasonal or fluctuating frequency components in soil moisture signals, and predict water loss or soil drying trends. The Fourier transform formula is:

[0086]

[0087] Among them, X(q) represents the component of the frequency domain signal, x(n) represents the data point of the time domain signal, M represents the total number of sampling points of the signal, q represents the frequency index, and n represents the time index.

[0088] The system collects humidity data through the soil moisture detection module, and applies Fourier transform to convert the humidity signal from the time domain to the frequency domain, and analyzes its frequency domain characteristics. By calculating the frequency components of the humidity signal, the system is able to identify the periodicity and fluctuation characteristics of humidity changes. For example, specific frequency components may indicate periodic fluctuations in soil moisture, and this information helps predict the drying trend of the soil or the risk of water loss. In this way, the system can more effectively evaluate the actual irrigation needs of the soil and ensure the rationality and effectiveness of irrigation. By analyzing the frequency components of the humidity signal, it is possible to identify the periodicity of soil moisture changes, accurately predict the future drying trend or water loss of the soil, and identify the fluctuation trend of soil moisture, making the system more scientific in judging irrigation needs, thereby reducing unnecessary irrigation and improving the efficiency of water resource utilization. The system can identify possible drought trends in advance and start irrigation in time, thereby preventing the soil from drying out excessively and ensuring the water supply required for crop growth.

[0089] The sprinkler irrigation system control module controls the sprinkler irrigation system to irrigate according to the optimization results, including:

[0090] Irrigation time, irrigation amount, wind speed, and soil moisture are defined as random variables, and irrigation scenarios are simulated. In each simulated scenario, the corresponding irrigation effect is calculated, and the irrigation time and irrigation amount under the combination are generated. All simulation results are expected to be calculated, and the optimal irrigation plan that can perform stably in different environments is selected as the final optimization result. The expected calculation formula is:

[0091]

[0092] Where E[X] is the expected value of variable X, X represents a random variable, N represents the number of simulations, and X i represents the result of the ith simulation.

[0093] The system constructs multiple different irrigation scenarios by setting parameters such as irrigation time, irrigation amount, wind speed and soil moisture as random variables, and simulates and calculates the irrigation effect of each scenario. Each simulation generates a set of irrigation effects under specific conditions, and a set of irrigation effects under different environmental conditions is obtained through multiple simulations. The system selects a parameter combination that can provide stable irrigation effects under various conditions through expected calculation, and uses it as the optimal configuration of irrigation control to adapt to different hilly slope environments. Multiple simulations generate irrigation results under different conditions, allowing the system to find stable irrigation parameter configurations under different environmental conditions and reduce the impact of environmental fluctuations on irrigation effects. Expected calculations analyze the results of multiple irrigation scenarios through statistical methods, select the best parameter combination, and improve irrigation efficiency and resource utilization. The system can make adaptive adjustments according to different environmental and climatic conditions to ensure that the system can continue to provide the best irrigation effect.

[0094] The sprinkler head adjustment module adjusts the angle and spray distance of the sprinkler head based on the wind speed and wind direction data, and also includes determining the wind force level based on the wind speed data; adjusting the angle of the sprinkler head according to the wind force level; adjusting the spray distance of the sprinkler head according to the wind force level; when the wind speed exceeds a preset threshold, reducing the water spray volume of the sprinkler head.

[0095] The sprinkler head adjustment module first determines the current wind force level based on the wind speed data, and obtains the corresponding level by comparing it with the preset wind force level table. According to the wind force level, the system automatically adjusts the angle and spray distance of the sprinkler head to ensure accurate coverage of the water flow. When the wind speed exceeds the preset threshold of the system, the system reduces the amount of water sprayed by the sprinkler head, thereby reducing the impact of wind on water flow distribution, avoiding waste of water resources and reduced sprinkler irrigation effect. The system dynamically adjusts the angle and spray distance of the sprinkler head according to the wind force level to ensure that the water flow reaches the target area accurately, reduces the amount of water sprayed under strong wind conditions, reduces water loss caused by wind, and improves the efficiency of water resource utilization. The sprinkler system can respond to wind speed changes in real time, adaptively adjust sprinkler parameters under different wind speed conditions, and adapt to changing environmental conditions.

[0096] Determining the wind force level based on wind speed data includes obtaining real-time wind speed data V; comparing the wind speed data with a preset wind force level table; determining the current wind force level L based on the comparison result; and judging whether the wind force level L is greater than or equal to 3; the specific formula is: L=f(V), wherein V represents real-time wind speed data and L represents wind force level.

[0097] The system obtains wind speed data in real time and compares it with the wind force level table to determine the current wind force level. When the wind force level reaches or exceeds level 3, the system automatically adjusts the sprinkler irrigation parameters to ensure that the sprinkler irrigation effect is not affected by high wind speed. The system can adjust the irrigation parameters according to the real-time wind speed to reduce the impact of high wind speed on the irrigation effect. The wind force level discrimination function enables the system to adaptively adjust the sprinkler irrigation parameters under different wind speed conditions to improve the consistency of irrigation effects.

[0098] Adjusting the angle of the sprinkler head according to the wind force level includes obtaining the current wind force level L; determining the angle adjustment value θ based on the wind force level L; adjusting the angle of the sprinkler head to the current angle plus the adjustment value θ; judging whether the adjusted angle is within a safe range, and if so, performing the adjustment; the specific formula is: θ=g(L), wherein L represents the wind force level and θ represents the angle adjustment value.

[0099] The system automatically calculates the angle adjustment value θ according to the current wind force level L, and adjusts the angle of the sprinkler head to adapt to the wind speed change. The adjusted angle must be ensured to be within the safe range. If it is out of the range, the adjustment will not be performed to avoid system failure under extreme conditions. The angle adjustment optimizes the water flow coverage, reduces the impact of wind speed on water flow distribution, ensures that the sprinkler head angle is adjusted within the safe range, and reduces the risk of damage to system components under high wind speeds.

[0100] Adjusting the spray distance of the sprinkler head according to the wind force level includes obtaining the current wind force level L; determining the spray distance adjustment value D based on the wind force level L; adjusting the spray distance of the sprinkler head to the current spray distance minus the adjustment value D; and judging whether the adjusted spray distance is within a safe range; formula: D=h(L), wherein L represents the wind force level and D represents the spray distance adjustment value.

[0101] When the wind speed exceeds a preset threshold, reducing the water spray volume of the sprinkler head includes obtaining the current wind speed V; determining the water spray volume adjustment coefficient K based on the wind speed V; reducing the current water spray volume multiplied by the adjustment coefficient K; and judging whether the reduced water spray volume is within an allowable range; formula: K=i(V), wherein V represents real-time wind speed data, and K represents the water spray volume adjustment coefficient.

[0102] The module adapts to wind speed changes by adjusting the spray distance and automatically reduces the amount of water sprayed when the wind speed exceeds the threshold. The system calculates the spray distance adjustment value D corresponding to the wind force level and performs the adjustment within a safe range. When the wind speed exceeds the threshold, the spray adjustment coefficient K is determined based on the current wind speed V, and the spray amount is reduced proportionally to ensure irrigation uniformity. When the wind speed is high, the amount of water sprayed is reduced to avoid water loss and improve irrigation efficiency. The system can automatically reduce the spray distance according to the wind force level so that the water flow covers the target area more accurately.

[0103] Obtaining the current wind speed V includes collecting data from a wind speed sensor; smoothing the wind speed data to reduce the impact of noise; calculating the average wind speed V based on the smoothed wind speed data; and determining whether the average wind speed V exceeds a preset threshold. Formula: V = (V1 + V2 + ... + V r ) / r, where V1, V2, ..., V r represents wind speed data measured multiple times, r represents the number of measurements, and V represents the average wind speed after smoothing.

[0104] The system collects wind speed sensor data multiple times and smoothes it to reduce the impact of measurement noise on the average wind speed V, thereby obtaining more stable wind speed data. The system compares the calculated average wind speed with the preset threshold to determine whether the sprinkler parameters need to be adjusted. Smoothing reduces noise interference and improves the accuracy of wind speed data. The smoothed average wind speed is used for threshold comparison, making the system more accurate in responding to wind speed changes.

[0105] The soil moisture detection module is connected to the soil moisture sensor and determines the irrigation demand according to the data of the soil moisture sensor, and also includes obtaining the real-time data S of the soil moisture sensor; comparing the real-time data S with the preset soil moisture threshold S min When the soil moisture is lower than the preset threshold S min When the irrigation demand signal is triggered.

[0106] The system collects soil moisture sensor data in real time and compares it with the preset humidity threshold S min When the humidity is lower than this threshold, the system automatically triggers the irrigation demand signal to ensure that the soil moisture meets the needs of crop growth. When the soil moisture is lower than the set threshold, the irrigation demand is automatically triggered to reduce manual intervention. Irrigation is only performed when the soil moisture is insufficient, thereby improving water resource utilization.

[0107] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An artificial intelligence-based hilly slope irrigation control system, characterized in that: The system comprises: Wind speed and wind direction detection module, used to obtain wind speed and wind direction data; The sprinkler head adjustment module connected to the wind speed and wind direction detection module is used to adjust the angle and spray distance of the sprinkler head based on the wind speed and wind direction data. Specifically, the utility functions of different wind speeds and wind directions are designed to represent the optimal states of spray distance, angle and water flow distribution respectively. The best sprinkler head parameter combination under the current wind speed and wind direction is solved, and the spray angle and distance are automatically adjusted according to the optimal strategy combination. The specific solution process is as follows: Among them, u i Represents the utility function of different wind speeds and directions, s i Indicates the angle or spray distance setting of the sprinkler head. Indicates the optimal angle or spray distance setting of the sprinkler head under the current wind speed and direction conditions, s -i Indicates the angle and distance settings of the sprinkler head under other wind speed and direction conditions. It indicates the sprinkler head parameter combination when all other wind speed and wind direction conditions adopt their own optimal strategies; A soil moisture detection module, used to connect to a soil moisture sensor and determine irrigation needs based on data from the soil moisture sensor; The artificial intelligence control module connected to the wind speed and direction detection module and the soil moisture detection module is used to optimize the irrigation time and irrigation amount through the artificial intelligence algorithm. Specifically, the irrigation demand and environmental data are constructed into a small-world network model. Each node in the network represents a different irrigation condition. The edges between the nodes represent the mutual influence between the conditions. The average path length and clustering coefficient of each node are calculated. The calculation formula is: Among them, N represents the number of network nodes, k represents the average degree of nodes, L represents the average path length of each node, and C represents the clustering coefficient; The sprinkler irrigation system control module connected to the artificial intelligence control module is used to control the sprinkler irrigation system for irrigation according to the optimization results.

2. The hilly slope irrigation control system based on artificial intelligence according to claim 1 is characterized by: The wind speed and wind direction detection module acquires wind speed and wind direction data including: Collect historical wind speed and direction data, calculate the fluctuation of the data and apply the autoregressive conditional heteroskedasticity model to estimate the conditional variance. The specific formula is: in, represents the variance at the current moment, ∈ t-1 represents the error at the previous moment, σ t-1 represents the standard deviation of the variance at the previous moment, and α0, α1, β1 represent the parameters of the model.

3. The hilly slope irrigation control system based on artificial intelligence according to claim 1 is characterized by: The soil moisture detection module is connected to the soil moisture sensor and determines the irrigation demand according to the data of the soil moisture sensor, including: Collect soil moisture sensor data, analyze its frequency domain characteristics through Fourier transform, identify seasonal or fluctuating frequency components in soil moisture signals, and predict water loss or soil drying trends. The Fourier transform formula is: Among them, X(q) represents the component of the frequency domain signal, x(n) represents the data point of the time domain signal, M represents the total number of sampling points of the signal, q represents the frequency index, and n represents the time index.

4. The hilly slope irrigation control system based on artificial intelligence according to claim 1 is characterized by: The sprinkler irrigation system control module controls the sprinkler irrigation system to irrigate according to the optimization result, including: Irrigation time, irrigation amount, wind speed, and soil moisture are defined as random variables, and irrigation scenarios are simulated. In each simulated scenario, the corresponding irrigation effect is calculated, and the irrigation time and irrigation amount under the combination are generated. All simulation results are expected to be calculated, and the optimal irrigation plan that can perform stably in different environments is selected as the final optimization result. The expected calculation formula is: Where E[X] is the expected value of variable X, X represents a random variable, N represents the number of simulations, and X i represents the result of the ith simulation.

5. The hilly slope irrigation control system based on artificial intelligence according to claim 1 is characterized by: The sprinkler head adjustment module adjusts the angle and spray distance of the sprinkler head based on wind speed and wind direction data and further includes: Determine wind force level based on wind speed data; Adjust the angle of the sprinkler head according to the wind level; Adjust the spray distance of the sprinkler head according to the wind level; When the wind speed exceeds a preset threshold, the amount of water sprayed by the sprinkler head is reduced.

6. The hilly slope irrigation control system based on artificial intelligence according to claim 5 is characterized by: Determining the wind force level based on wind speed data includes: Get real-time wind speed data V; Compare wind speed data with a preset wind force scale table; Determine the current wind force level L based on the comparison result; Determine whether the wind force level L is greater than or equal to 3; The specific formula is: L=f(V), where V represents real-time wind speed data and L represents wind force level.

7. The hilly slope irrigation control system based on artificial intelligence according to claim 6 is characterized by: The method of adjusting the angle of the sprinkler head according to the wind force level includes: Get the current wind force level L; Determine the angle adjustment value θ based on the wind force level L; Adjust the angle of the sprinkler head to the current angle plus the adjustment value θ; Determine whether the adjusted angle is within a safe range, and if so, perform the adjustment; The specific formula is: θ=g(L), where L represents the wind force level and θ represents the angle adjustment value.

8. The hilly slope irrigation control system based on artificial intelligence according to claim 7 is characterized by: The method of adjusting the spray distance of the sprinkler head according to the wind force level includes: Get the current wind force level L; Determine the spray distance adjustment value D based on the wind force level L; Adjust the spray distance of the sprinkler head to the current spray distance minus the adjustment value D; Determine whether the adjusted spray distance is within the safe range; Formula: D = h (L), where L represents the wind force level and D represents the spray distance adjustment value; When the wind speed exceeds a preset threshold, reducing the water spraying amount of the sprinkler head includes: Get the current wind speed V; Determine the water spray adjustment coefficient K based on the wind speed V; Reduce the current water spraying amount multiplied by the adjustment coefficient K; Determine whether the reduced water spray volume is within the allowable range; Formula: K = i(V), where V represents real-time wind speed data and K represents the water spray adjustment coefficient.

9. The hilly slope irrigation control system based on artificial intelligence according to claim 8 is characterized by: The obtaining of the current wind speed V comprises: Collect data from wind speed sensors; Smooth the wind speed data to reduce the impact of noise; Calculate the average wind speed V based on the smoothed wind speed data; Determine whether the average wind speed V exceeds a preset threshold; Formula: V = (V1 + V2 + ... + V r ) / r, where V1, V2, ..., V r represents wind speed data measured multiple times, r represents the number of measurements, and V represents the average wind speed after smoothing.

10. The hilly slope irrigation control system based on artificial intelligence according to claim 1, characterized in that: The soil moisture detection module is connected to the soil moisture sensor and determines the irrigation demand according to the data of the soil moisture sensor, and further includes: Get the real-time data S of the soil moisture sensor; The real-time data S is compared with the preset soil moisture threshold S min Make comparisons; When the soil moisture is lower than the preset threshold S min When the irrigation demand signal is triggered.

Images