A fully automatic wheat watering optimization control method

Abstract

The present invention relates to a fully automatic wheat watering optimization control method, the method comprising: R1. During the wheat watering process, obtaining the flow data information of wheat, the water content data information of wheat and the data information of water inlet flow; R2. Based on the flow data information of wheat, the water content data information of wheat and the data information of water inlet flow, constructing a diversified wheat watering prediction model, predicting various indicators of wheat, and obtaining the data information of various indicators of wheat after prediction; R3. Based on the data information of various indicators of wheat after prediction. The present invention can not only encapsulate, optimize and detect various indicator data of wheat, so as to obtain accurate wheat watering data information, but also combine big data to topology and update various indicators of wheat watering, so as to further improve the stability and accuracy of watering of medicinal wheat.

Description

Technical Field

[0001] The invention relates to the technical field of wheat watering control, and in particular to a full-automatic wheat watering optimization control method. Background Art

[0002] With the rapid development of information technology, especially the popularity of cloud computing, the Internet of Things and social media, the amount of global data is showing an explosive growth trend. In these fields, people are generating and sharing a large amount of information every minute, including knowledge data information on wheat watering. How to use this information to optimize the control of wheat watering has become an urgent problem to be solved.

[0003] In the prior art, the patent (application number: 201811585126.4) discloses a wheat watering control method and device, which obtains the ambient temperature and ambient humidity within a preset time period, and obtains wheat parameter information; the ambient temperature, ambient humidity and wheat parameter information are input into a pre-trained neural network; based on the pre-trained neural network, the ambient temperature, ambient humidity and wheat parameter information are processed to determine the target watering amount; according to the determined target watering amount, the wheat is watered. After the target watering amount is calibrated in this scheme, the watering amount of wheat cannot be dynamically and adaptively adjusted, resulting in waste of resources and instability of wheat watering. Summary of the invention

[0004] In view of the above deficiencies in the prior art, the present invention provides a fully automatic wheat watering optimization control method, which can not only encapsulate, predict and optimize various indicator data of wheat to obtain accurate wheat watering data information, but also combine big data to topologically update various indicators of wheat watering, thereby further improving the stability and accuracy of wheat watering.

[0005] In order to achieve the above-mentioned purpose and other related purposes, the technical solution provided by the present invention is as follows:

[0006] A fully automatic wheat watering optimization control method, the method comprising:

[0007] R1. During the wheat watering process, obtain the wheat flow data information, wheat moisture content data information and water inflow data information;

[0008] R2. Based on the flow data information of wheat, the moisture content data information of wheat and the water inflow data information, a diversified watering prediction model for wheat is constructed to predict various indicators of wheat to obtain data information of various indicators of wheat after prediction;

[0009] R3. Based on the data information of various indicators of wheat after the prediction, various indicators of wheat are optimized by using a wheat big data optimization algorithm based on hyperparameters to obtain data information of various indicators of wheat after optimization;

[0010] R4. Based on the data information of various indicators of the optimized wheat, a control function F of the fully automatic dampening machine is established to control the flow rate and water inlet flow rate of the wheat, and output the control data information of the flow rate and water inlet flow rate of the wheat.

[0011] Furthermore, in step R2, the construction of a diversified wheat watering prediction model to predict various wheat indicators includes:

[0012] R21. Based on the wheat flow data information, wheat moisture content data information and water inflow data information, construct wheat index encapsulation function G,

[0013]

[0014] Among them, x1 is the flow data information of wheat, x2 is the water content data information of wheat, x3 is the data information of water inflow, α1, α2 and α3 are the encapsulation determining factors of various wheat indicators, and the various indicators of wheat are encapsulated to obtain the encapsulated data information of various indicators of wheat;

[0015] R22. Based on the data information of various indicators of the encapsulated wheat, a multivariate prediction function H of wheat is established.

[0016]

[0017] Among them, a i is the data information of the i-th index of wheat after encapsulation, n is the sample size, β1 and β2 are the prediction factors of wheat, and f is the characteristic function of each index of wheat;

[0018] R23. Based on the multivariate prediction function H of wheat, various indicators of wheat are predicted to obtain data information of various indicators of wheat after prediction.

[0019] Furthermore, the characteristic function f of each wheat index is:

[0020]

[0021] Among them, a i is the i-th indicator data information of the encapsulated wheat, and λ1 and λ2 are constant parameters for extracting the characteristics of various indicators of the encapsulated wheat.

[0022] Furthermore, the constraints of the encapsulation determining factors α1, α2 and α3 of the wheat indicators are:

[0023]

[0024] Furthermore, in step R3, the optimization of various wheat indicators using the wheat big data optimization algorithm based on hyperparameters includes:

[0025] R31. Based on the data information of various indicators of wheat after the prediction, a big data model of wheat watering is constructed, and the hyperparameters of various indicators of wheat are calculated to obtain the hyperparameter data information of various indicators of wheat;

[0026] R32. Based on the hyperparameter data information of various wheat indicators, an optimization function W of various wheat indicators is established.

[0027]

[0028] Among them, J is the hyperparameter sample capacity of each wheat index, b j is the hyperparameter data information of the jth wheat index, θ1 and θ2 are the optimized constant parameters of each wheat index, and the various wheat indexes are optimized to obtain the data information of each optimized wheat index;

[0029] R33. Based on the data information of various indicators of the optimized wheat, a preset threshold is set. If the various indicators of the optimized wheat are greater than the preset threshold, return to step R31; if the various indicators of the optimized wheat are less than the preset threshold, the data information of various indicators of the optimized wheat is output.

[0030] Furthermore, in step R31, the construction of a big data model for wheat watering and the calculation of hyperparameters of various wheat indicators include:

[0031] R311. Input the predicted data information of various wheat indicators into the big data model of wheat watering for training and learning, and determine the hyperparameter function Q of various wheat indicators.

[0032] Among them, y is the data information of various indicators of wheat after prediction, μ1 and μ2 are weight coefficients, and the trained big data model of wheat watering is obtained;

[0033] R312. Based on the trained big data model of wheat hydration, the data information of various indicators of the predicted wheat is input, and the hyperparameters of various indicators of wheat are calculated to obtain the hyperparameter data information of various indicators of wheat.

[0034] Furthermore, the constraints of the optimization constant parameters θ1 and θ2 of the wheat indicators are:

[0035]

[0036] Furthermore, the control function F of the fully automatic dampening machine is:

[0037]

[0038] Among them, z k is the data information of the kth indicator of wheat after optimization, η1, η2 and η3 are the control relationship factors of the automatic dampening machine, and K is the sample capacity of the data of each indicator of wheat after optimization.

[0039] In order to achieve the above-mentioned purpose and other related purposes, the present invention also provides a wheat watering optimization control system based on a fully automatic watering machine, including a computer device, which is programmed or configured to execute the steps of any one of the fully automatic wheat watering optimization control methods.

[0040] In order to achieve the above-mentioned purpose and other related purposes, the present invention also provides a computer-readable storage medium, on which is stored a computer program programmed or configured to execute any one of the fully automatic wheat watering optimization control methods described.

[0041] The present invention has the following positive effects:

[0042] 1. The present invention predicts various indicators of wheat by constructing a diversified wheat watering prediction model. It can not only encapsulate, predict and optimize the data of various indicators of wheat to obtain accurate wheat watering data information, but also in this process, it can adaptively optimize according to different wheat indicators, and has strong robustness.

[0043] 2. The present invention optimizes various indicators of wheat by adopting a wheat big data optimization algorithm based on hyperparameters, and controls the flow rate and water inlet flow rate of wheat by establishing a control function F of a fully automatic watering machine. It can not only perform corresponding precise watering treatment for different wheat indicators, but also combine big data to perform topology and update of wheat watering, thereby further improving the stability and accuracy of wheat watering. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0045] Figure 2 A schematic diagram of the process of constructing a diversified watering prediction model for wheat according to the present invention;

[0046] Figure 3 It is a schematic diagram of the process of the hyperparameter-based wheat big data optimization algorithm of the present invention;

[0047] Figure 4 It is a structural schematic diagram of the fully automatic dampening machine of the present invention (I);

[0048] Figure 5 This is a structural schematic diagram of the fully automatic dampening machine of the present invention (II);

[0049] Figure 6 It is a structural schematic diagram (III) of the fully automatic dampening machine of the present invention.

[0050] Explanation of the numbers in the figure: 1-barrel, 101-feed pipe, 102-discharge pipe, 103-air inlet, 2-spray pipe, 3-water inlet pipe, 4-motor, 5-conveying blades, 6-inlet pipe, 7-inlet diverter pipe, 8-air delivery pipe, 9-air compressor, 10-water mist diverter pipe, 11-mist pipe, 12-industrial atomizer, 13-exhaust port, 14-first flow sensor, 15-display screen, 16-second flow sensor, 17-moisture sensor. DETAILED DESCRIPTION

[0051] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0052] Example 1: Figure 1 or Figure 4 As shown, a fully automatic wheat watering optimization control method comprises:

[0053] R1. During the wheat watering process, obtain the wheat flow data information, wheat moisture content data information and water inflow data information;

[0054] R2. Based on the flow data information of wheat, the moisture content data information of wheat and the water inflow data information, a diversified watering prediction model for wheat is constructed to predict various indicators of wheat to obtain data information of various indicators of wheat after prediction;

[0055] R3. Based on the data information of various indicators of wheat after the prediction, various indicators of wheat are optimized by using a wheat big data optimization algorithm based on hyperparameters to obtain data information of various indicators of wheat after optimization;

[0056] R4. Based on the data information of various indicators of the optimized wheat, a control function F of the fully automatic dampening machine is established to control the flow rate and water inlet flow rate of the wheat, and output the control data information of the flow rate and water inlet flow rate of the wheat.

[0057] In this embodiment, if Figure 2 As shown, in step R2, the construction of a diversified wheat watering prediction model and the prediction of various wheat indicators include:

[0058] R21. Based on the wheat flow data information, wheat moisture content data information and water inflow data information, construct wheat index encapsulation function G,

[0059]

[0060] Among them, x1 is the flow data information of wheat, x2 is the water content data information of wheat, x3 is the data information of water inflow, α1, α2 and α3 are the encapsulation determining factors of various wheat indicators, and the various indicators of wheat are encapsulated to obtain the encapsulated data information of various indicators of wheat;

[0061] R22. Based on the data information of various indicators of the encapsulated wheat, a multivariate prediction function H of wheat is established.

[0062]

[0063] Among them, a i is the data information of the i-th index of wheat after encapsulation, n is the sample size, β1 and β2 are the prediction factors of wheat, and f is the characteristic function of each index of wheat;

[0064] R23. Based on the multivariate prediction function H of wheat, various indicators of wheat are predicted to obtain data information of various indicators of wheat after prediction.

[0065] In this embodiment, the characteristic function f of each wheat index is:

[0066]

[0067] Among them, a i is the i-th indicator data information of the encapsulated wheat, and λ1 and λ2 are constant parameters for extracting the characteristics of various indicators of the encapsulated wheat.

[0068] In this embodiment, the constraints of the packaging determining factors α1, α2 and α3 of the wheat indicators are:

[0069]

[0070] Example 2: Based on the fully automatic wheat watering optimization control method of Example 1, the present invention is further illustrated and described below.

[0071] like Figure 1 or Figure 4 As shown, a fully automatic wheat watering optimization control method comprises:

[0072] R1. During the wheat watering process, obtain the wheat flow data information, wheat moisture content data information and water inflow data information;

[0073] R2. Based on the flow data information of wheat, the moisture content data information of wheat and the water inflow data information, a diversified watering prediction model for wheat is constructed to predict various indicators of wheat to obtain data information of various indicators of wheat after prediction;

[0074] R3. Based on the data information of various indicators of wheat after the prediction, various indicators of wheat are optimized by using a wheat big data optimization algorithm based on hyperparameters to obtain data information of various indicators of wheat after optimization;

[0075] R4. Based on the data information of various indicators of the optimized wheat, a control function F of the fully automatic dampening machine is established to control the flow rate and water inlet flow rate of the wheat, and output the control data information of the flow rate and water inlet flow rate of the wheat.

[0076] In this embodiment, if Figure 3 As shown, in step R3, the optimization of various wheat indicators using the wheat big data optimization algorithm based on hyperparameters includes:

[0077] R31. Based on the data information of various indicators of wheat after the prediction, a big data model of wheat watering is constructed, and the hyperparameters of various indicators of wheat are calculated to obtain the hyperparameter data information of various indicators of wheat;

[0078] R32. Based on the hyperparameter data information of various wheat indicators, an optimization function W of various wheat indicators is established.

[0079]

[0080] Among them, J is the hyperparameter sample capacity of each wheat index, b j is the hyperparameter data information of the jth wheat index, θ1 and θ2 are the optimized constant parameters of each wheat index, and the various wheat indexes are optimized to obtain the data information of each optimized wheat index;

[0081] R33. Based on the data information of various indicators of the optimized wheat, a preset threshold is set. If the various indicators of the optimized wheat are greater than the preset threshold, return to step R31; if the various indicators of the optimized wheat are less than the preset threshold, the data information of various indicators of the optimized wheat is output.

[0082] In this embodiment, in step R31, the construction of a big data model for wheat watering and the calculation of hyperparameters of various wheat indicators include:

[0083] R311. Input the predicted data information of various wheat indicators into the big data model of wheat watering for training and learning, and determine the hyperparameter function Q of various wheat indicators.

[0084] Among them, y is the data information of various indicators of wheat after prediction, μ1 and μ2 are weight coefficients, and the trained big data model of wheat watering is obtained;

[0085] R312. Based on the trained big data model of wheat hydration, the data information of various indicators of the predicted wheat is input, and the hyperparameters of various indicators of wheat are calculated to obtain the hyperparameter data information of various indicators of wheat.

[0086] In this embodiment, the constraints of the optimization constant parameters θ1 and θ2 of the wheat indicators are:

[0087]

[0088] In this embodiment, the control function F of the fully automatic dampener is:

[0089]

[0090] Among them, z k is the data information of the kth indicator of wheat after optimization, η1, η2 and η3 are the control relationship factors of the automatic dampening machine, and K is the sample capacity of the data of each indicator of wheat after optimization.

[0091] In this embodiment, if Figure 4 , Figure 5 or Figure 6As shown, the fully automatic wheat watering equipment comprises a barrel 1, a feed pipe 101 arranged at the top of one end of the barrel 1, a discharge pipe 102 arranged at the bottom of the other end of the barrel 1, a spray pipe 2 installed at the top of the inner wall of the barrel 1, and a water inlet pipe 3 arranged outside the barrel 1 and connected to the spray pipe 2, which is used to transport clean water for watering; a motor 4 is fixedly installed at one end of the barrel 1, and a conveying blade 5 connected to the motor 4 is horizontally installed inside the barrel 1. The conveying blade 5 is a hollow spiral blade. The spiral blade with a hollow structure is used as a propeller to push and turn the wheat. The conveying blades 5, on the one hand, will not block the contact between the water mist of the upper spray pipe 2 and the wheat, and at the same time, the accumulated wheat can also pass through the conveying blades 5 horizontally to improve the turning effect; a plurality of air inlet pipes 6 are fixedly connected to the bottom of the barrel 1 along the axial direction, and at least two groups of air inlet pipes 6 are provided, and the air inlet pipes 6 are symmetrically arranged at the front and back of the bottom of the barrel 1. The air inlet pipes 6 are equidistantly arranged on the barrel 1 along the horizontal axis of the barrel 1 for uniform blowing to improve the turning effect. The air inlet pipes 6 are connected to the inner cavity of the barrel 1 through the air inlet hole 103 provided on the barrel 1, and the inner diameter of the air inlet hole 103 is No more than 2mm, which is larger than the minimum size of wheat to avoid being blocked by wheat; multiple air inlet pipes 6 are connected to the air compressor 9 through the air inlet shunt pipe 7 and the air delivery pipe 8, and a water mist shunt pipe 10 connected to the multiple air inlet pipes 6 is fixedly installed under the barrel 1, and the water mist shunt pipe 10 is connected to the industrial atomizer 12 through the mist pipe 11. An exhaust port 13 is provided on the top of the barrel 1 to balance the internal air pressure; the air inlet pipe 6 is perpendicular to the outer wall of the barrel 1, the air inlet shunt pipe 7 and the water mist shunt pipe 10 are both horizontally arranged, and the branch pipe of the water mist shunt pipe 10 is connected to the air inlet pipe 6. The distance between the air holes 103 is smaller than the distance between the branch pipe of the air intake diverter pipe 7 and the air intake hole 103. The water mist diverter pipe 10 is located above the air intake diverter pipe 7, and the water mist is blown in from bottom to top by pressurized air. A display 15 is provided on the outer shell of the automatic wheat watering equipment for real-time displaying data information on the wheat watering situation. The first flow sensor 14 obtains the flow data information of wheat in real time. The second flow sensor 16 is used to obtain the water intake flow data information in real time. The moisture sensor obtains the moisture content data information of wheat in real time.

[0092] In this embodiment, the present invention provides a wheat watering optimization control system based on a fully automatic watering machine, including a computer device, which is programmed or configured to execute any one of the steps of the fully automatic wheat watering optimization control method.

[0093] In this embodiment, the present invention provides a computer-readable storage medium, on which is stored a computer program programmed or configured to execute any one of the fully-automatic wheat watering optimization control methods.

[0094] Any reference to memory, storage, database or other media used in the embodiments provided in the present application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM) and memory bus dynamic RAM (RDRAM).

[0095] In summary, the present invention can not only encapsulate, optimize and detect various indicator data of wheat to obtain accurate wheat watering data information, but also combine big data to topologically update various indicators of wheat watering, thereby further improving the stability and accuracy of wheat watering.

[0096] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A fully automatic wheat watering optimization control method, characterized in that: The method comprises: R1. During the wheat watering process, obtain the wheat flow data information, wheat moisture content data information and water inflow data information; R2. Based on the flow data information of wheat, the moisture content data information of wheat and the water inflow data information, a diversified watering prediction model for wheat is constructed to predict various indicators of wheat to obtain data information of various indicators of wheat after prediction; R3. Based on the data information of various indicators of wheat after the prediction, various indicators of wheat are optimized by using a wheat big data optimization algorithm based on hyperparameters to obtain data information of various indicators of wheat after optimization; R4. Based on the data information of the optimized wheat indicators, establish the control function F of the fully automatic dampening machine, control the flow rate and water flow rate of wheat, and output the control data information of the flow rate and water flow rate of wheat; In step R2, the construction of a diversified wheat watering prediction model and the prediction of various wheat indicators include: R21. Based on the wheat flow data information, wheat moisture content data information and water inflow data information, construct wheat index encapsulation function G, ， Among them, x1 is the flow data information of wheat, x2 is the water content data information of wheat, x3 is the data information of water inflow, α1, α2 and α3 are the encapsulation determining factors of various wheat indicators, and the various indicators of wheat are encapsulated to obtain the encapsulated data information of various indicators of wheat; R22. Based on the data information of various indicators of the encapsulated wheat, a multivariate prediction function H of wheat is established. ， Among them, a i is the data information of the i-th index of wheat after encapsulation, n is the sample size, β1 and β2 are the prediction factors of wheat, and f is the characteristic function of each index of wheat; R23. Based on the multivariate prediction function H of wheat, various indicators of wheat are predicted to obtain data information of various indicators of wheat after prediction; In step R3, the optimization of various wheat indicators using the wheat big data optimization algorithm based on hyperparameters includes: R31. Based on the data information of various indicators of wheat after the prediction, a big data model of wheat watering is constructed, and the hyperparameters of various indicators of wheat are calculated to obtain the hyperparameter data information of various indicators of wheat; R32. Based on the hyperparameter data information of various wheat indicators, an optimization function W of various wheat indicators is established. ， Among them, J is the hyperparameter sample capacity of each wheat index, b j is the hyperparameter data information of the jth wheat index, θ1 and θ2 are the optimized constant parameters of each wheat index, and the various wheat indexes are optimized to obtain the data information of each optimized wheat index; R33. Based on the data information of the various indicators of the optimized wheat, a preset threshold is set. If the various indicators of the optimized wheat are greater than the preset threshold, the process returns to step R31. If the various indicators of the optimized wheat are less than the preset threshold, the data information of the various indicators of the optimized wheat is output; In step R31, the construction of a big data model for wheat watering and the calculation of hyperparameters of various wheat indicators include: R311. Input the predicted data information of various wheat indicators into the big data model of wheat watering for training and learning, and determine the hyperparameter function Q of various wheat indicators. ， Among them, y is the data information of various indicators of wheat after prediction, µ1 and µ2 are weight coefficients, and the trained big data model of wheat watering is obtained; R312. Based on the trained big data model of wheat hydration, the data information of various indicators of the predicted wheat is input, and the hyperparameters of various indicators of wheat are calculated to obtain the hyperparameter data information of various indicators of wheat.

2. The fully automatic wheat watering optimization control method according to claim 1, characterized in that: The characteristic function f of each wheat index is: ， Among them, a i is the i-th indicator data information of the encapsulated wheat, and λ1 and λ2 are constant parameters for extracting the characteristics of various indicators of the encapsulated wheat.

3. The fully automatic wheat watering optimization control method according to claim 1, characterized in that: The constraints of the packaging determining factors α1, α2 and α3 of the wheat indicators are: 。 4. The fully automatic wheat watering optimization control method according to claim 1, characterized in that: The constraints of the optimization constant parameters θ1 and θ2 of the wheat indicators are: 。 5. The fully automatic wheat watering optimization control method according to claim 1, characterized in that: The control function F of the fully automatic dampening machine is: ， Among them, z k is the data information of the kth indicator of wheat after optimization, η1, η2 and η3 are the control relationship factors of the automatic dampening machine, and K is the sample capacity of the data of each indicator of wheat after optimization.

6. A wheat dampening optimization control system based on a fully automatic dampening machine, comprising a computer device, characterized in that: The computer device is programmed or configured to execute the steps of the fully automatic wheat watering optimization control method as described in any one of claims 1 to 5.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program programmed or configured to execute the fully automatic wheat watering optimization control method according to any one of claims 1 to 5.

Images