Distributor flow control method
The method employs predictive models to monitor and adjust irrigation flow in real-time, addressing pipe blockage issues in agricultural systems by using sensor data to optimize fertilizer delivery and prevent clogging, thus enhancing operational efficiency and reducing maintenance costs.
Patent Information
- Application Number
- CN202411525831.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-30
- Publication Date
- 2025-03-28
AI Technical Summary
Current agricultural systems lack real-time monitoring and predictive capabilities to prevent pipe blockages in irrigation systems due to the complex interactions of factors like flow rate, viscosity, and temperature affecting liquid manure fertilizers, leading to inefficient fertilizer distribution and increased maintenance costs.
A method and system for controlling irrigation flow using a predictive model that calculates pipe blockage risk and adjusts outlet openings based on real-time data from sensors, including density, viscosity, and pressure differences, to optimize fertilizer delivery and prevent pipe clogging.
This approach enables real-time monitoring and prediction of pipe blockages, allowing for proactive adjustments to maintain stable and efficient fertilizer distribution, reducing maintenance costs and ensuring continuous, effective agricultural operations.
Smart Images
Figure CN119717904A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of resource utilization of farmland excrement, and in particular to a distributor flow control method and system. Background Art
[0002] In agricultural production, liquid livestock and poultry manure is an important organic fertilizer and is widely used in field irrigation. However, since liquid fertilizer contains more solid particles and its viscosity fluctuates significantly due to changes in ambient temperature, it is easy for liquid fertilizer to form deposits on the pipe wall during pipeline transportation, which in turn causes pipeline blockage. Once the pipeline is blocked, the transportation efficiency of liquid fertilizer will drop significantly, and problems such as uneven flow or unstable transportation are likely to occur during irrigation, which directly affects the fertilization effect of crops.
[0003] At present, existing technologies mainly rely on post-detection methods, which are unable to achieve real-time monitoring and early warning of pipeline blockage risks, resulting in losses to agricultural production when the problem occurs, and the maintenance cost is high. It is impossible to achieve real-time monitoring and early warning of pipeline blockage, and take regulatory measures before blockage occurs, which in turn leads to pipeline blockage.
[0004] Since the fluidity of liquid fertilizer is affected by many factors, such as flow rate, viscosity and temperature, these factors will affect the flow characteristics of liquid fertilizer and the pressure changes in the pipeline. Under the interaction of these factors, the sediment in the pipeline will gradually increase, resulting in a significant increase in the risk of blockage. It is difficult for existing technologies to simultaneously consider these complex variables and conduct real-time monitoring and comprehensive analysis, so that pipeline blockages are often unable to be predicted in time and flow control measures cannot be accurately adjusted. In addition, with the gradual accumulation of sediments, the pipeline's transportation capacity further decreases, the fluidity of liquid fertilizer deteriorates, and irrigation efficiency decreases, which also affects the nutrient supply of crops. Summary of the invention
[0005] In order to solve the above technical problems, the present invention provides a distributor flow control method.
[0006] A method for controlling flow of a distributor, the method comprising: Get arrive Liquid fertilizer data and in-pipe data of livestock and poultry manure in the distribution pipeline within a time period, and liquid fertilizer flow coefficient is generated according to the liquid fertilizer data and in-pipe data; Collect the temperature data in the distribution pipeline, input the temperature data and the liquid fertilizer flow coefficient into the pre-built blockage coefficient prediction model to obtain arrive The distribution pipeline blockage coefficient within the time period; Collecting water content data of the distribution pipeline, and inputting the water content data of the distribution pipeline and the blockage coefficient of the distribution pipeline into a preset flow control model to generate flow control data; The openings of the multiple outlets of the distributor are adjusted according to the obtained flow control data to control the flow rates of the multiple outlets of the distributor.
[0007] Furthermore, the liquid fertilizer data includes a liquid fertilizer density value, a liquid fertilizer viscosity value and a liquid fertilizer flow value, and the in-pipe data includes a pipeline cross-sectional area and a pressure difference between inside and outside the pipe.
[0008] Furthermore, the logic for generating the liquid fertilizer flow coefficient according to the liquid fertilizer data is: The liquid fertilizer flow coefficient is calculated based on the liquid fertilizer density value, liquid fertilizer viscosity value, liquid fertilizer flow value, pipeline cross-sectional area and the pressure difference between the inside and outside of the pipe. The logical equation of the mathematical model used to calculate the liquid fertilizer flow coefficient is: ; Among them, β is the liquid fertilizer flow coefficient, Q is the liquid fertilizer flow value, △P is the pressure difference between the inside and outside of the pipe, A is the cross-sectional area of the pipe, γ is the viscosity value, and ρ is the liquid fertilizer density value.
[0009] Furthermore, the construction logic of the congestion coefficient prediction model is: Obtaining historical blockage coefficient prediction training data, and dividing the historical blockage coefficient prediction training data into a blockage prediction training set and a blockage prediction test set; the historical blockage coefficient prediction training data includes temperature data, liquid fertilizer flow coefficient and its corresponding estimated distribution pipeline blockage coefficient; Constructing a first regression network, taking the temperature data and the liquid fertilizer flow coefficient in the blockage prediction training set as input data of the first regression network, taking the estimated distribution pipeline blockage coefficient in the blockage prediction training set as output data of the first regression network, training the first regression network, and obtaining an initial first machine learning network; The initial first machine learning network is model verified using the congestion prediction test set, and the initial first machine learning network with a value less than or equal to a preset first test error threshold is output as a pre-constructed congestion coefficient prediction model.
[0010] Furthermore, the generation logic of the distribution pipeline blockage coefficient is: According to the generation time of the historical data of the liquid fertilizer flow coefficient as the starting time, the sediment thickness value and the pipeline friction value of the distribution pipeline after time L are obtained, and the pipeline blockage coefficient is calculated according to the sediment thickness value and the pipeline friction value. The logical equation of the calculation model of the pipeline blockage coefficient is: Among them, K is the pipeline blockage coefficient; S is the thickness of the sediment in the pipeline, Sj is the maximum tolerance value of the thickness of the sediment in the pipeline; M is the pipeline friction value, and Mj is the standard value of the pipeline friction value.
[0011] Furthermore, the construction logic of the traffic control model is: Acquire historical flow control training data, and divide the historical flow control training data into a flow control training set and a flow control test set; the historical flow control training data includes water content data, distribution pipeline blockage coefficient and corresponding estimated flow control data; Constructing a second regression network, taking the water content data and the distribution pipeline blockage coefficient in the flow control training set as input data of the second regression network, taking the estimated flow control data in the flow control training set as output data of the second regression network, training the second regression network, and obtaining an initial second machine learning network; The initial second machine learning network is model verified using the traffic control test set, and the initial second machine learning network with a value less than or equal to a preset second test error threshold is output as the preset traffic control model.
[0012] Furthermore, the generation logic of the flow control data is: Set up d distribution pipes with the same cross-section, collect corresponding real-time flow control reference data according to the water content data and the historical data of the distribution pipe blockage coefficient, so as to obtain d groups of real-time flow control reference data, and divide the distribution pipes whose blockage coefficients are less than or equal to 0.01 into the same comparison group. Among them, in the same comparison group, the opening adjustment amplitude of the distributor outlet is counted, and a total of g adjustment plans are generated. The adjustment plan with the largest proportion of distribution pipes is taken as the ideal plan, and the opening adjustment amplitude of the distributor outlet in the ideal plan is taken as the flow control data.
[0013] A dispenser flow control system, used to execute a dispenser flow control method, the system comprising: Liquid fertilizer analysis module: used to obtain arrive Liquid fertilizer data and in-pipe data of livestock and poultry manure in the distribution pipeline within a time period, and liquid fertilizer flow coefficient is generated according to the liquid fertilizer data and in-pipe data; The first processing module is used to collect temperature data in the distribution pipeline, input the temperature data and the liquid fertilizer flow coefficient into the pre-built blockage coefficient prediction model to obtain arrive The distribution pipeline blockage coefficient within the time period; The second processing module is used to collect the water content data of the distribution pipeline, and input the water content data of the distribution pipeline and the blockage coefficient of the distribution pipeline into a preset flow control model to generate flow control data; Flow control module: used to adjust the opening of multiple outlets of the distributor according to the obtained flow control data, so as to control the flow of multiple outlets of the distributor.
[0014] Compared with the prior art, the present invention has the following beneficial effects: The present invention can monitor and predict the risk of pipeline blockage in future time periods in real time by constructing a blockage coefficient prediction model, and improve the prediction accuracy by predicting the pipeline blockage coefficient, so that effective flow control measures can be taken before blockage occurs; the present invention can also dynamically adjust the opening of the distributor outlet by combining the blockage coefficient prediction model and the flow control model, so as to optimize the transportation and fertilization process of liquid fertilizer, thereby reducing the unstable transportation of liquid fertilizer irrigation when there are many pipe wall deposits, thereby improving the stability and efficiency of fertilization, reducing pipeline blockage and uneven flow, and ensuring the continuous operation and efficient fertilization of the agricultural fertilization system. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.
[0016] Figure 1 A flow chart of a distributor flow control method provided in Example 1 of the present invention; Figure 2 A module diagram of a dispenser flow control system provided in Example 2 of the present invention. DETAILED DESCRIPTION
[0017] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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.
[0018] Example 1 See also Figure 1 As shown, this embodiment discloses a method for controlling flow of a distributor, the method comprising: S110: Get arrive Liquid fertilizer data and in-pipe data of livestock and poultry manure in the distribution pipeline within a time period, and liquid fertilizer flow coefficient is generated according to the liquid fertilizer data and in-pipe data; Specifically, the liquid fertilizer data includes a liquid fertilizer density value, a liquid fertilizer viscosity value, and a liquid fertilizer flow value, and the in-pipe data includes a pipeline cross-sectional area and a pressure difference between the inside and outside of the pipe; It should be understood that: the density value is collected in real time by the liquid fertilizer density sensor in the distribution pipeline, and the liquid fertilizer density value is used to determine the concentration and solid content of the liquid fertilizer; the liquid fertilizer viscosity value is collected by an online viscometer, and the liquid fertilizer viscosity value reflects the fluidity of the liquid fertilizer. The higher the viscosity, the worse the fluidity; the liquid fertilizer flow value is collected by a flow meter to collect the flow in the distribution pipeline, and the liquid fertilizer flow value is used to analyze the real-time transportation of the liquid fertilizer; the cross-sectional area of the pipeline is calculated by measuring the diameter of the pipeline with a measuring tool, and the pressure difference between the inside and outside of the pipe is obtained by a pressure sensor; Specifically, the logic for generating the liquid fertilizer flow coefficient based on the liquid fertilizer data is: The liquid fertilizer flow coefficient is calculated based on the liquid fertilizer density value, liquid fertilizer viscosity value, liquid fertilizer flow value, pipeline cross-sectional area and the pressure difference between the inside and outside of the pipe. The logical equation of the mathematical model used to calculate the liquid fertilizer flow coefficient is: ; Among them, β is the liquid fertilizer flow coefficient, Q is the liquid fertilizer flow value, △P is the pressure difference between the inside and outside of the pipe, A is the cross-sectional area of the pipe, γ is the viscosity value, and ρ is the liquid fertilizer density value; It should be noted that the liquid fertilizer flow coefficient is used to characterize the comprehensive flow resistance of livestock and poultry manure in the pipeline; When the cross-sectional area A of the pipeline is constant, the larger the liquid fertilizer flow rate Q, the faster the liquid flows, so the flow resistance will decrease. Under high flow conditions, the liquid fertilizer in the pipeline is easier to flow; the larger the pressure difference △P inside and outside the pipe, the stronger the force pushing the liquid fertilizer to flow, and the flow resistance will decrease accordingly. If the pressure difference is small, the flow of liquid fertilizer will be restricted and the resistance will increase; the viscosity value γ is proportional to the friction of the liquid fertilizer in the pipe. The higher the viscosity, the more difficult it is for the liquid fertilizer to flow and the greater the flow resistance.
[0019] S120: Collect temperature data in the distribution pipeline, input the temperature data and the liquid fertilizer flow coefficient into a pre-built blockage coefficient prediction model to obtain arrive The blockage coefficient of the distribution pipeline within the time period; Specifically, the construction logic of the congestion coefficient prediction model is: Obtaining historical blockage coefficient prediction training data, and dividing the historical blockage coefficient prediction training data into a blockage prediction training set and a blockage prediction test set; the historical blockage coefficient prediction training data includes temperature data, liquid fertilizer flow coefficient and its corresponding estimated distribution pipeline blockage coefficient; It should be understood that the temperature data is obtained by setting a temperature sensor in the pipe. The temperature data will affect the viscosity and fluidity of the liquid fertilizer. Lower temperature data will lead to higher viscosity, thereby increasing the risk of clogging. Specifically, the generation logic of the distribution pipeline blockage coefficient is: According to the generation time of the historical data of the liquid fertilizer flow coefficient as the starting time, the sediment thickness value and the pipeline friction value of the distribution pipeline after time L are obtained, and the pipeline blockage coefficient is calculated according to the sediment thickness value and the pipeline friction value. The logical equation of the calculation model of the pipeline blockage coefficient is: Among them, K is the pipeline blockage coefficient; S is the thickness of the sediment in the pipeline, Sj is the maximum tolerance value of the thickness of the sediment in the pipeline; M is the pipeline friction value, Mj is the standard value of the pipeline friction value; It is important to understand that each distribution pipeline design has a maximum allowable sediment thickness, i.e., the maximum sediment thickness limit value, which is determined based on design parameters such as the diameter, material properties, and fluid flow capacity of the distribution pipeline. The pipeline friction value is the friction value between the inner wall of the pipeline and the fluid, which is obtained through a sensor installed in the pipeline. Constructing a first regression network, taking the temperature data and the liquid fertilizer flow coefficient in the blockage prediction training set as input data of the first regression network, taking the estimated distribution pipeline blockage coefficient in the blockage prediction training set as output data of the first regression network, training the first regression network, and obtaining an initial first machine learning network; The initial first machine learning network is model verified using the congestion prediction test set, and the initial first machine learning network with a value less than or equal to a preset first test error threshold is output as a pre-constructed congestion coefficient prediction model.
[0020] It should be noted that the first regression network includes but is not limited to a linear regression model, a multilayer perceptron, a decision tree regression or a support vector regression.
[0021] S130: collecting water content data of the distribution pipeline, and inputting the water content data of the distribution pipeline and the blockage coefficient of the distribution pipeline into a preset flow control model to generate flow control data; Specifically, the construction logic of the traffic control model is: Acquire historical flow control training data, and divide the historical flow control training data into a flow control training set and a flow control test set; the historical flow control training data includes water content data, distribution pipeline blockage coefficient and corresponding estimated flow control data; Specifically, the generation logic of the traffic control data is: Set d distribution pipes with the same cross-section, collect corresponding instantaneous flow control reference data according to the water content data and the historical data of the distribution pipe blockage coefficient, so as to obtain d groups of instantaneous flow control reference data, and divide the distribution pipes whose blockage coefficients are less than or equal to 0.01 into the same comparison group, wherein, in the same comparison group, the opening adjustment amplitude of the distributor outlet is counted, and a total of g adjustment plans are generated, and the adjustment plan with the largest proportion of distribution pipes is taken as the ideal plan, and the opening adjustment amplitude of the distributor outlet in the ideal plan is taken as the flow control data; Constructing a second regression network, taking the water content data and the distribution pipeline blockage coefficient in the flow control training set as input data of the second regression network, taking the estimated flow control data in the flow control training set as output data of the second regression network, training the second regression network, and obtaining an initial second machine learning network; Using the flow control test set to perform model verification on the initial second machine learning network, outputting an initial second machine learning network that is less than or equal to a preset second test error threshold as a preset flow control model; It should be noted that the second regression network includes but is not limited to a linear regression model, a multilayer perceptron, a decision tree regression or a support vector regression.
[0022] S140: adjusting the openings of the multiple outlets of the distributor according to the obtained flow control data to control the flow rates of the multiple outlets of the distributor.
[0023] It should be noted that the liquid fertilizer data refers to liquid livestock and poultry manure data; The present invention can monitor and predict the risk of pipeline blockage in future time periods in real time by constructing a blockage coefficient prediction model, and improve the prediction accuracy by predicting the pipeline blockage coefficient, so that effective flow control measures can be taken before blockage occurs; the present invention can also dynamically adjust the opening of the distributor outlet by combining the blockage coefficient prediction model and the flow control model, so as to optimize the transportation and fertilization process of liquid fertilizer, thereby reducing the unstable transportation of liquid fertilizer irrigation when there are many pipe wall deposits, thereby improving the stability and efficiency of fertilization, reducing pipeline blockage and uneven flow, and ensuring the continuous operation and efficient fertilization of the agricultural fertilization system. Example 2 See also Figure 2 As shown, based on the unified inventive concept, this embodiment discloses a dispenser flow control system, the system comprising: Liquid fertilizer analysis module S210: used to obtain arrive Liquid fertilizer data and in-pipe data of livestock and poultry manure in the distribution pipeline within a time period, and liquid fertilizer flow coefficient is generated according to the liquid fertilizer data and in-pipe data; Specifically, the liquid fertilizer data includes a liquid fertilizer density value, a liquid fertilizer viscosity value, and a liquid fertilizer flow value, and the in-pipe data includes a pipeline cross-sectional area and a pressure difference between the inside and outside of the pipe; It should be understood that: the density value is collected in real time by the liquid fertilizer density sensor in the distribution pipeline, and the liquid fertilizer density value is used to determine the concentration and solid content of the liquid fertilizer; the liquid fertilizer viscosity value is collected by an online viscometer, and the liquid fertilizer viscosity value reflects the fluidity of the liquid fertilizer. The higher the viscosity, the worse the fluidity; the liquid fertilizer flow value is collected by a flow meter to collect the flow in the distribution pipeline, and the liquid fertilizer flow value is used to analyze the real-time transportation of the liquid fertilizer; the cross-sectional area of the pipeline is calculated by measuring the diameter of the pipeline with a measuring tool, and the pressure difference between the inside and outside of the pipe is obtained by a pressure sensor; Specifically, the logic for generating the liquid fertilizer flow coefficient based on the liquid fertilizer data is: The liquid fertilizer flow coefficient is calculated based on the liquid fertilizer density value, liquid fertilizer viscosity value, liquid fertilizer flow value, pipeline cross-sectional area and the pressure difference between the inside and outside of the pipe. The logical equation of the mathematical model used to calculate the liquid fertilizer flow coefficient is: ; Among them, β is the liquid fertilizer flow coefficient, Q is the liquid fertilizer flow value, △P is the pressure difference between the inside and outside of the pipe, A is the cross-sectional area of the pipe, γ is the viscosity value, and ρ is the liquid fertilizer density value; It should be noted that the liquid fertilizer flow coefficient is used to characterize the comprehensive flow resistance of livestock and poultry manure in the pipeline; When the cross-sectional area A of the pipeline is constant, the larger the liquid fertilizer flow rate Q, the faster the liquid flows, so the flow resistance will decrease. Under high flow conditions, the liquid fertilizer in the pipeline is easier to flow; the larger the pressure difference △P inside and outside the pipe, the stronger the force pushing the liquid fertilizer to flow, and the flow resistance will decrease accordingly. If the pressure difference is small, the flow of liquid fertilizer will be restricted and the resistance will increase; the viscosity value γ is proportional to the friction of the liquid fertilizer in the pipe. The higher the viscosity, the more difficult it is for the liquid fertilizer to flow and the greater the flow resistance.
[0024] The first processing module S120 is used to collect temperature data in the distribution pipeline, input the temperature data and the liquid fertilizer flow coefficient into the pre-built blockage coefficient prediction model to obtain arrive The distribution pipeline blockage coefficient within the time period; Specifically, the construction logic of the congestion coefficient prediction model is: Obtaining historical blockage coefficient prediction training data, and dividing the historical blockage coefficient prediction training data into a blockage prediction training set and a blockage prediction test set; the historical blockage coefficient prediction training data includes temperature data, liquid fertilizer flow coefficient and its corresponding estimated distribution pipeline blockage coefficient; Specifically, the generation logic of the distribution pipeline blockage coefficient is: According to the generation time of the historical data of the liquid fertilizer flow coefficient as the starting time, the sediment thickness value and the pipeline friction value of the distribution pipeline after time L are obtained, and the pipeline blockage coefficient is calculated according to the sediment thickness value and the pipeline friction value. The logical equation of the calculation model of the pipeline blockage coefficient is: Among them, K is the pipeline blockage coefficient; S is the thickness of the sediment in the pipeline, Sj is the maximum tolerance value of the thickness of the sediment in the pipeline; M is the pipeline friction value, Mj is the standard value of the pipeline friction value; Constructing a first regression network, taking the temperature data and the liquid fertilizer flow coefficient in the blockage prediction training set as input data of the first regression network, taking the estimated distribution pipeline blockage coefficient in the blockage prediction training set as output data of the first regression network, training the first regression network, and obtaining an initial first machine learning network; The initial first machine learning network is model verified using the congestion prediction test set, and the initial first machine learning network with a value less than or equal to a preset first test error threshold is output as a pre-constructed congestion coefficient prediction model.
[0025] The second processing module S130 is used to collect the water content data of the distribution pipeline, and input the water content data of the distribution pipeline and the blockage coefficient of the distribution pipeline into a preset flow control model to generate flow control data; Specifically, the construction logic of the traffic control model is: Acquire historical flow control training data, and divide the historical flow control training data into a flow control training set and a flow control test set; the historical flow control training data includes water content data, distribution pipeline blockage coefficient and corresponding estimated flow control data; Specifically, the generation logic of the traffic control data is: Set d distribution pipes with the same cross-section, collect corresponding instantaneous flow control reference data according to the water content data and the historical data of the distribution pipe blockage coefficient, so as to obtain d groups of instantaneous flow control reference data, and divide the distribution pipes whose blockage coefficients are less than or equal to 0.01 into the same comparison group, wherein, in the same comparison group, the opening adjustment amplitude of the distributor outlet is counted, and a total of g adjustment plans are generated, and the adjustment plan with the largest proportion of distribution pipes is taken as the ideal plan, and the opening adjustment amplitude of the distributor outlet in the ideal plan is taken as the flow control data; Constructing a second regression network, taking the water content data and the distribution pipeline blockage coefficient in the flow control training set as input data of the second regression network, taking the estimated flow control data in the flow control training set as output data of the second regression network, training the second regression network, and obtaining an initial second machine learning network; Using the flow control test set to perform model verification on the initial second machine learning network, outputting an initial second machine learning network that is less than or equal to a preset second test error threshold as a preset flow control model; The flow control module S140 is used to adjust the opening of the multiple outlets of the distributor according to the obtained flow control data, so as to control the flow of the multiple outlets of the distributor.
[0026] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired network or a wireless network. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD) or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.
[0028] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.
[0029] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0030] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a method for controlling the flow of a distributor. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0031] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0032] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0033] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.
[0034] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. A method for controlling the flow rate of a distributor, characterized in that: The method comprises: Get arrive Liquid fertilizer data and in-pipe data of livestock and poultry manure in the distribution pipeline within a time period, and liquid fertilizer flow coefficient is generated according to the liquid fertilizer data and in-pipe data; Collect the temperature data in the distribution pipeline, input the temperature data and the liquid fertilizer flow coefficient into the pre-built blockage coefficient prediction model to obtain arrive The blockage coefficient of the distribution pipeline within the time period; Collecting water content data of the distribution pipeline, and inputting the water content data of the distribution pipeline and the blockage coefficient of the distribution pipeline into a preset flow control model to generate flow control data; The openings of the multiple outlets of the distributor are adjusted according to the obtained flow control data to control the flow rates of the multiple outlets of the distributor.
2. The method for controlling the flow rate of a distributor according to claim 1, characterized in that: The liquid fertilizer data includes a liquid fertilizer density value, a liquid fertilizer viscosity value, and a liquid fertilizer flow value, and the in-pipe data includes a pipeline cross-sectional area and a pressure difference between inside and outside the pipe.
3. The method for controlling the flow rate of a distributor according to claim 2, characterized in that: The logic for generating the liquid fertilizer flow coefficient based on liquid fertilizer data is: The liquid fertilizer flow coefficient is calculated based on the liquid fertilizer density value, liquid fertilizer viscosity value, liquid fertilizer flow value, pipeline cross-sectional area and the pressure difference between the inside and outside of the pipe. The logical equation of the mathematical model used to calculate the liquid fertilizer flow coefficient is: ; Among them, β is the liquid fertilizer flow coefficient, Q is the liquid fertilizer flow value, △P is the pressure difference between the inside and outside of the pipe, A is the cross-sectional area of the pipe, γ is the viscosity value, and ρ is the liquid fertilizer density value.
4. The method for controlling the flow rate of a distributor according to claim 3, characterized in that: The construction logic of the congestion coefficient prediction model is: Obtaining historical blockage coefficient prediction training data, and dividing the historical blockage coefficient prediction training data into a blockage prediction training set and a blockage prediction test set; the historical blockage coefficient prediction training data includes temperature data, liquid fertilizer flow coefficient and its corresponding estimated distribution pipeline blockage coefficient; Constructing a first regression network, taking the temperature data and the liquid fertilizer flow coefficient in the blockage prediction training set as input data of the first regression network, taking the estimated distribution pipeline blockage coefficient in the blockage prediction training set as output data of the first regression network, training the first regression network, and obtaining an initial first machine learning network; The initial first machine learning network is model verified using the congestion prediction test set, and the initial first machine learning network with a value less than or equal to a preset first test error threshold is output as a pre-constructed congestion coefficient prediction model.
5. The method for controlling the flow rate of a distributor according to claim 4, characterized in that: The generation logic of the distribution pipeline blockage coefficient is: According to the generation time of the historical data of the liquid fertilizer flow coefficient as the starting time, the sediment thickness value and the pipeline friction value of the distribution pipeline after time L are obtained, and the pipeline blockage coefficient is calculated according to the sediment thickness value and the pipeline friction value. The logical equation of the calculation model of the pipeline blockage coefficient is: Among them, K is the pipeline blockage coefficient; S is the thickness of the sediment in the pipeline, Sj is the maximum tolerance value of the thickness of the sediment in the pipeline; M is the pipeline friction value, and Mj is the standard value of the pipeline friction value.
6. The method for controlling the flow rate of a distributor according to claim 5, characterized in that: The construction logic of the traffic control model is: Acquire historical flow control training data, and divide the historical flow control training data into a flow control training set and a flow control test set; the historical flow control training data includes water content data, distribution pipeline blockage coefficient and corresponding estimated flow control data; Constructing a second regression network, taking the water content data and the distribution pipeline blockage coefficient in the flow control training set as input data of the second regression network, taking the estimated flow control data in the flow control training set as output data of the second regression network, training the second regression network, and obtaining an initial second machine learning network; The initial second machine learning network is model verified using the traffic control test set, and the initial second machine learning network with a value less than or equal to a preset second test error threshold is output as the preset traffic control model.
7. The method for controlling the flow rate of a distributor according to claim 6, characterized in that: The generation logic of the traffic control data is: Set up d distribution pipes with the same cross-section, collect corresponding real-time flow control reference data according to the water content data and the historical data of the distribution pipe blockage coefficient, so as to obtain d groups of real-time flow control reference data, and divide the distribution pipes whose blockage coefficients are less than or equal to 0.01 into the same comparison group. Among them, in the same comparison group, the opening adjustment amplitude of the distributor outlet is counted, and a total of g adjustment plans are generated. The adjustment plan with the largest proportion of distribution pipes is taken as the ideal plan, and the opening adjustment amplitude of the distributor outlet in the ideal plan is taken as the flow control data.
8. A dispenser flow control system, used to implement the dispenser flow control method of claims 1 to 7, characterized in that: The system comprises: Liquid fertilizer analysis module: used to obtain arrive Liquid fertilizer data and in-pipe data of livestock and poultry manure in the distribution pipeline within a time period, and liquid fertilizer flow coefficient is generated according to the liquid fertilizer data and in-pipe data; The first processing module is used to collect temperature data in the distribution pipeline, input the temperature data and the liquid fertilizer flow coefficient into the pre-built blockage coefficient prediction model to obtain arrive The blockage coefficient of the distribution pipeline within the time period; The second processing module is used to collect the water content data of the distribution pipeline, and input the water content data of the distribution pipeline and the blockage coefficient of the distribution pipeline into a preset flow control model to generate flow control data; Flow control module: used to adjust the opening of multiple outlets of the distributor according to the obtained flow control data, so as to control the flow of multiple outlets of the distributor.