An irrigation pipeline system optimization design method based on data analysis

Abstract

The application discloses an irrigation pipeline system optimization design method based on data analysis and relates to the field of intelligent agriculture. Water level information, environmental information and meteorological data information of an irrigation area are collected in real time; state parameters are determined according to the obtained information data; a water level index is set, a water level dynamic model describing water level change of the irrigation area is constructed by using the state parameters and the water level index; irrigation quantity and drainage quantity are solved; the water level of the irrigation area is kept within the optimal growth water level range, and the water storage quantity does not exceed the maximum water storage quantity, which are taken as irrigation decision targets, a control model for controlling the irrigation quantity and the drainage quantity of the irrigation area is constructed; the control model is used to make irrigation decisions for the irrigation area, the growth water level of crops is ensured to be kept in the optimal state, the number of invalid irrigation times is reduced, and the waste of water resources is avoided, and the method can provide a scientific basis for network irrigation of paddy crops.

Description

Technical Field

[0001] This invention relates to the field of smart agriculture, and in particular to a data analysis-based optimization design method for irrigation pipeline systems. Background Technology

[0002] With the increasing severity of water scarcity, agricultural water use efficiency has become a key factor restricting food security and sustainable development. Traditional rice cultivation often relies on "timed and quantitative" or "experience-based" irrigation, which cannot adjust water volume according to the real-time water requirements of crops and easily leads to water waste or root hypoxia. Therefore, precision irrigation or drainage control systems based on paddy field condition information and meteorological parameters have become an important research direction in modern agriculture.

[0003] Currently, existing irrigation control systems mainly have the following limitations:

[0004] 1) Limited information dimensions: Most systems rely solely on soil moisture sensor thresholds to trigger irrigation, without comprehensively considering the coupling effects of multiple factors such as crop coefficient, farmland infiltration, and effective precipitation coefficient, resulting in low decision-making accuracy.

[0005] 2) Lack of dynamic forecasting capability: Existing technologies mostly adopt an "instant response" strategy, which cannot plan irrigation / drainage in advance based on weather forecasts for the next 3-7 days. This can easily lead to flooding due to failure to drain water in time before heavy rain, or failure to replenish water in advance during periods of no rain.

[0006] (3) Lack of water storage safety constraints: Paddy fields have physiological limits of "maximum water storage θc" and "maximum water storage time ≤ 6 days". Existing control algorithms do not embed these dual constraints into the decision model, which leads to root suffocation caused by long-term deep water layers.

[0007] (4) Low coupling of actuators: Irrigation valves and drainage pumps operate independently in terms of control logic, lacking a “combined irrigation and drainage” coordination strategy, making it difficult to achieve precise closed-loop water level control.

[0008] To address the aforementioned problems, there is an urgent need for a control system that can integrate multi-source paddy field status information (infiltration, effective precipitation coefficient, crop coefficient, water level limits θmax / θmin, maximum water storage θc) and real-time / predicted meteorological parameters (rainfall, evaporation). Furthermore, a mathematical control model should be established that satisfies the dual constraints of "maximum water storage ≤ θc and water storage duration ≤ 6 days" to achieve adaptive and coordinated decision-making for irrigation and drainage, thereby maximizing water conservation and flood control while ensuring optimal rice growth. To this end, a data analysis-based optimization design method for irrigation pipeline systems is proposed. Summary of the Invention

[0009] The main objective of this invention is to provide a data analysis-based optimization design method for irrigation pipeline systems. This method integrates sensor data acquisition technology, embedded system technology, wireless self-organizing network technology, and artificial intelligence theory, incorporating meteorological parameters and precision irrigation schemes to design a smart agricultural networked precision irrigation system. This ensures that the water level for crop growth is maintained at the optimal level, extends equipment lifespan, reduces ineffective irrigation, avoids water waste, and provides a scientific basis for networked irrigation of paddy fields. It effectively solves the problems in the background technology.

[0010] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0011] A data analysis-based optimization design method for irrigation pipeline systems includes the following steps:

[0012] a) Real-time collection of water level information, environmental information, and meteorological data in the irrigation area;

[0013] b) Determine the status parameters based on the acquired information data, including the current water level. farmland infiltration Effective precipitation coefficient Crop coefficient Daily precipitation and daily evaporation ;

[0014] c) Set water level indicators, including the optimal upper limit of water level. Optimal lower limit of water level and maximum water storage capacity ;

[0015] d) Construct a dynamic water level model describing water level changes in the irrigation area using the state parameters and water level indicators;

[0016] e) Solve for irrigation volume using the aforementioned water level dynamic model. and drainage volume ;

[0017] f) Using the goal of maintaining the water level in the irrigation area within the optimal growth range and ensuring that the water storage does not exceed the maximum water storage capacity, an irrigation decision is constructed to control the irrigation amount in the irrigation area. and the drainage volume The control model;

[0018] g) Utilize the control model to formulate irrigation decisions for the irrigation area to meet the irrigation decision objectives.

[0019] Furthermore, the expression for the water level dynamic model is: Where t represents the number of days, and when t=1 it is the current day; This refers to irrigation volume; This refers to the volume of water discharged.

[0020] Furthermore, the control model includes the following irrigation decision rules:

[0021] Rule 1, when At that time, irrigation is carried out in the irrigated area;

[0022] Rule 2, when At that time, drainage should be carried out in the irrigated area;

[0023] Rule 3, when ,and At that time, drainage should be carried out in the irrigated area;

[0024] Rule 4, when ,and At that time, irrigation is carried out in the irrigated area;

[0025] in, Represented as the first The Queen's predicted water level .

[0026] Furthermore, when rule one is met, the irrigation amount The calculation method is as follows: ;in, Represented as taking 0 and The maximum value in.

[0027] Furthermore, when rule two or rule three is satisfied, the drainage volume... The calculation method is as follows: ;

[0028] in, Represented as taking 0 and The maximum value in.

[0029] Furthermore, when rule four is satisfied, the irrigation amount The calculation method is as follows: in, Represented as taking 0 and The maximum value in.

[0030] Furthermore, the first The predicted water level of the Queen The solution is obtained using a discretized model, and the solution process includes the following steps:

[0031] Utilizing the current water level The water level dynamic model is used to calculate the predicted water level for the next day. The calculation formula is: ;

[0032] Using predicted water levels The water level dynamic model is used to calculate the predicted water level for the next day. The calculation formula is: ;

[0033] And so on, using predicted water levels and the solution of the water level dynamic model Predicted water level for the day The calculation formula is: .

[0034] Furthermore, the effective precipitation coefficient It is determined based on the daily rainfall, specifically:

[0035] Rainfall of less than 10 mm on a given day is considered light rain. The effective precipitation coefficient is... Set to 0;

[0036] Rainfall of 10–25 mm is considered moderate rain, and rainfall of 25–50 mm is considered heavy rain. The effective precipitation coefficient for moderate and heavy rain is as described above. Take a value of 0.8 to 1.0;

[0037] Rainfall of 50-100 mm is considered a rainstorm; rainfall of 100-250 mm is considered a heavy rainstorm; rainfall exceeding 250 mm is considered an extremely heavy rainstorm; the effective precipitation coefficient for rainstorms, heavy rainstorms, and extremely heavy rainstorms is as follows. Take a value of 0.7 to 0.8.

[0038] The present invention has the following beneficial effects:

[0039] Compared with existing technologies, this solution integrates multi-source paddy field status information (infiltration, effective precipitation coefficient, crop coefficient, water level limits θmax / θmin, maximum water storage θc) and real-time / predicted meteorological parameters (rainfall, evaporation) into a control system. It also establishes a mathematical control model that meets the dual constraints of "maximum water storage ≤ θc and water storage duration ≤ 6 days" to achieve adaptive and coordinated decision-making for irrigation and drainage. This maximizes water conservation and flood prevention while ensuring optimal rice growth.

[0040] Compared with existing technologies, this solution integrates sensor data acquisition technology, embedded system technology, wireless self-organizing network technology, and artificial intelligence theory, incorporating meteorological parameters and precision irrigation schemes to design a smart agriculture networked precision irrigation system. This ensures that the water level for crop growth is maintained at the optimal level, extends equipment lifespan, reduces ineffective irrigation, avoids water waste, and provides a scientific basis for networked irrigation of paddy fields. Attached Figure Description

[0041] Figure 1 This is a flowchart illustrating an optimization design method for an irrigation pipeline system based on data analysis, according to the present invention.

[0042] Figure 2 This is a schematic diagram of water volume changes in a paddy field area according to an embodiment of the present invention;

[0043] Figure 3 This is a schematic diagram of water level changes in a paddy field area under conditions of no human intervention, as described in an embodiment of the present invention.

[0044] Figure 4 This is a schematic diagram comparing the water level control effects of the control method of the present invention with those of traditional methods;

[0045] Figure 5 This is a schematic diagram illustrating the test control effect of the control method of the present invention. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0047] A data analysis-based optimization design method for irrigation pipeline systems includes the following steps:

[0048] a) Real-time collection of water level information, environmental information, and meteorological data in the irrigation area;

[0049] Water level information can be collected using water level sensors, environmental information can be collected using environmental sensors, and meteorological data can be extracted using web scraping. The specific architecture is as follows:

[0050] (1) Resource layer: The source of data. This layer includes various types of databases such as relational databases, system support libraries (MySQL), and business databases (Oracle).

[0051] (2) Data access layer: Hibernate, JDBC, iBatis and other technologies are used to combine the specific interface parameters of the specific service interface in the database into SQL queries to obtain the corresponding data.

[0052] (3) Logic processing layer: The system utilizes technologies such as Struts and Spring, based on SOA architecture, and processes various types of data in batches.

[0053] (4) Business layer: Based on the SOA protocol, the data provided by the upper layer is analyzed using technologies such as WebService, REST, HTML5, and jQuery.

[0054] (5) User access: Users can complete tasks such as querying meteorological data, registering for meteorological data services, and querying (downloading) meteorological data service application forms.

[0055] First, weather forecasts are captured from web pages. Then, a LabVIEW application is generated that can call the forecasts. Finally, the weather forecasts are converted into meteorological data and uploaded in real time on a daily basis.

[0056] b) Determine the status parameters based on the acquired information data, including the current water level. farmland infiltration Effective precipitation coefficient Crop coefficient Daily precipitation and daily evaporation ;

[0057] In farmland, the infiltration rate is relatively high in dryland areas due to early irrigation, and is highly dependent on soil composition. However, in paddy fields, the soil moisture content is saturated after irrigation, and the infiltration rate remains within a relatively small range. In this embodiment, it is assumed that the test soil moisture content is already saturated, and the infiltration rate (INd) is taken as 0.065 mm / h.

[0058] Effective precipitation coefficient It is determined based on the daily rainfall, specifically:

[0059] Rainfall of less than 10 mm on a given day is considered light rain, with an effective precipitation coefficient of [missing information]. Set to 0;

[0060] Rainfall of 10–25 mm is considered moderate rain, and rainfall of 25–50 mm is considered heavy rain. The effective precipitation coefficient for moderate and heavy rain is given. Take a value of 0.8 to 1.0;

[0061] Rainfall of 50-100 mm is considered a rainstorm; rainfall of 100-250 mm is considered a heavy rainstorm; rainfall exceeding 250 mm is considered an extremely heavy rainstorm; the effective precipitation coefficient for rainstorms, heavy rainstorms, and extremely heavy rainstorms is as follows: Take a value of 0.7 to 0.8.

[0062] The crop coefficient is related to the crop type, geographical location, growth cycle, and current month. The crop coefficients for mid-season rice from May to September are 1.03, 1.35, 1.50, 1.40, and 0.94, respectively.

[0063] c) Set water level indicators, including the optimal upper limit of water level. Optimal lower limit of water level and maximum water storage capacity ;

[0064] d) Construct a dynamic water level model describing water level changes in the irrigation area using state parameters and water level indicators;

[0065] The expression for the water level dynamic model is: Where t represents the number of days, and when t=1 it is the current day; This refers to irrigation volume; This refers to the volume of water discharged.

[0066] e) Solving for irrigation volume using a water level dynamic model and drainage volume ;

[0067] f) Using the goal of maintaining the water level within the optimal growth range and ensuring that the water storage does not exceed the maximum storage capacity as the irrigation decision objective, construct a system for controlling the irrigation volume in the irrigation area. and drainage volume The control model;

[0068] The control model includes the following irrigation decision rules:

[0069] Rule 1, when At that time, irrigation is carried out in the irrigated area;

[0070] Rule 2, when At that time, drainage should be carried out in the irrigated area;

[0071] Rule 3, when ,and At that time, drainage should be carried out in the irrigated area;

[0072] Rule 4, when ,and At that time, irrigation is carried out in the irrigated area;

[0073] in, Represented as the first The Queen's predicted water level Predicted water level The solution is obtained using a discretized model, and the solution process includes the following steps:

[0074] Utilizing the current water level The water level dynamic model is used to calculate the predicted water level for the next day. The calculation formula is: ;

[0075] Using predicted water levels The water level dynamic model is used to calculate the predicted water level for the next day. The calculation formula is: ;

[0076] And so on, using predicted water levels and the solution of the water level dynamic model Predicted water level for the day The calculation formula is: .

[0077] g) Use control models to make irrigation decisions for irrigation areas to meet irrigation decision objectives.

[0078] When rule one is met, the irrigation amount The calculation method is as follows: ;in, Represented as taking 0 and The maximum value in.

[0079] When Rule 2 or Rule 3 is met, the water displacement The calculation method is as follows: ;in, Represented as taking 0 and The maximum value in.

[0080] When rule four is met, irrigation amount The calculation method is as follows: ;in, Represented as taking 0 and The maximum value in.

[0081] Based on the above process steps, in one possible embodiment, this scheme is further illustrated using a paddy field area as an example. Simulation design is performed by collecting weather data from this paddy field area in June. The spatial coordinate system height is set to 2m, meteorological data from days 153 to 183 of 2024 are used, and the initial water level of the paddy field is 25mm. In this embodiment, the rice greening period is selected as the experimental period, and shallow irrigation is chosen as a water-saving method. Under these conditions, and considering the actual situation, 40mm is the upper limit of the optimal water level for crop growth, 20mm is the lower limit, and 60mm is the maximum water storage capacity in the field. Meteorological data is obtained through data capture. The water consumption of crops and effective rainfall are calculated based on the current meteorological data; the results are shown below. Figure 2 Then, starting from June 1, 2024, the water level change of the paddy field under the condition of no human intervention was calculated, and the results are shown in Figure 3.

[0082] from Figure 2It can be seen that the water consumption in this paddy field area changes with the changes in meteorological parameters, especially when the highest temperature reaches the monthly maximum on June 4, the water consumption also reaches the monthly maximum. In addition, considering the changes in the effective precipitation received daily in the paddy field area and the difference between the daily water consumption and inflow of the paddy field, it can be seen that the water volume of the paddy field changes naturally with the difference between precipitation and water consumption. Within 30 days, the natural water level of the paddy field has deviated significantly from the water storage range of the paddy field.

[0083] Generally, irrigation is carried out when the water level is lower than the crop growth level, and drainage is carried out when the water level exceeds a certain threshold. This method is a non-automatic irrigation control method derived from farmers' experience, and the results are shown in [the original text is missing]. Figure 4 As shown. By Figure 4 It can be seen that the non-intelligent irrigation control method adopts a strategy of irrigating when the water level is low and draining when the water level is high. Although this irrigation method controls the water level within a reasonable range, the adjustment is too frequent, resulting in a waste of resources. Further calculations of the number of irrigations / drainages (action dates) and the amount of irrigation / drainage per instance (action amount, unit: mm) for the non-intelligent irrigation control method in June are shown in Table 1.

[0084] Table 1. Comparison of the effectiveness of the proposed control method with traditional control methods.

[0085]

[0086] Furthermore, in this embodiment, an irrigation action is defined as an invalid irrigation action if the water level exceeds the upper limit due to rainfall within 24 hours after irrigation is completed; similarly, an irrigation action is defined as an invalid drainage action if the water level falls below the lower limit due to crop water consumption within 24 hours after drainage is completed. This further yields the number of invalid and valid actions in the non-intelligent irrigation control method.

[0087] In summary, the non-intelligent irrigation control method performed irrigation 7 times and drainage 8 times, for a total of 15 actions, with an effective action rate (number of effective actions divided by the total number of actions) of only 53.33%.

[0088] Under the same parameters, the intelligent irrigation control method designed in this scheme was tested, and the test results are as follows: Figure 5As shown in the figure, under the control of the intelligent irrigation control method, the paddy field water level remained within the safe threshold. For 22 days, the water level was at the optimal level for the rice growth cycle; only 1 day was in a low water level zone; and 7 days were in a high water level zone, with each instance lasting a maximum of 48 hours, thus not harming crop growth. The simulation results were within the system parameter setting thresholds. The intelligent irrigation system operated 11 times within 30 days, including 6 irrigations and 5 drainages, with total irrigation and drainage volumes of 177.41 mm and 184.26 mm, respectively, achieving a 100% effective action rate. It can be seen that compared to the non-intelligent irrigation control method, the intelligent irrigation control method reduced the number of actions by 26.67%, reduced irrigation volume by 40.82%, and reduced drainage volume by 33.89%. (June 1, 2024 is counted as day 0. All values ​​on the vertical axis are converted to water level values ​​for each indicator).

[0089] The feasibility of the precision irrigation control method was verified through physical testing. Meteorological data from June 6th to June 12th were input into the control model for field testing, and the test results are shown in Table 2 below.

[0090] Table 2 Test results of the control method in this scheme

[0091]

[0092] The results above show that, under the regulation of the intelligent irrigation control method, the water level is consistently maintained within the optimal growth range for crops. Table 2 shows that the maximum deviation between the test results and the simulation results is 1 mm for irrigation (June 6th) and 2 mm for drainage (June 12th), which is in line with expectations. The main reasons for this deviation are the interference caused by sensor accuracy in the actual environment and some uncontrollable and inevitable errors. Simulation results show that the control method proposed in this scheme reduces irrigation and drainage by 40.82% and 33.89%, respectively.

[0093] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.

Claims

1. A data analysis-based optimization design method for irrigation pipeline systems, characterized in that, Includes the following steps: a) Real-time collection of water level information, environmental information, and meteorological data in the irrigation area; b) Determine the status parameters based on the acquired information data, including the current water level. farmland infiltration Effective precipitation coefficient Crop coefficient Daily precipitation and daily evaporation ; c) Set water level indicators, including the optimal upper limit of water level. Optimal lower limit of water level and maximum water storage capacity ; d) Construct a dynamic water level model describing water level changes in the irrigation area using the state parameters and water level indicators; e) Solve for irrigation volume using the aforementioned water level dynamic model. and drainage volume ; f) Using the goal of maintaining the water level in the irrigation area within the optimal growth range and ensuring that the water storage does not exceed the maximum water storage capacity, an irrigation decision is constructed to control the irrigation amount in the irrigation area. and the drainage volume The control model; g) Utilize the control model to formulate irrigation decisions for the irrigation area to meet the irrigation decision objectives; The expression for the water level dynamic model is: Where t represents the number of days, when The time is that day; This refers to irrigation volume; For drainage volume; The control model includes the following irrigation decision rules: Rule 1, when At that time, irrigation is carried out in the irrigated area; Rule 2, when At that time, drainage should be carried out in the irrigated area; Rule 3, when ,and At that time, drainage should be carried out in the irrigated area; Rule 4, when ,and At that time, irrigation is carried out in the irrigated area; in, Represented as the first The Queen's predicted water level .

2. The data analysis-based optimization design method for irrigation pipeline systems according to claim 1, characterized in that, When rule one is met, the irrigation amount The calculation method is as follows: ;in, Represented as taking 0 and The maximum value in.

3. The data analysis-based optimization design method for irrigation pipeline systems according to claim 1, characterized in that, When either rule two or rule three is met, the drainage volume The calculation method is as follows: ;in, Represented as taking 0 and The maximum value in.

4. The data analysis-based optimization design method for irrigation pipeline systems according to claim 1, characterized in that, When rule four is met, the irrigation amount The calculation method is as follows: ;in, Represented as taking 0 and The maximum value in.

5. The data analysis-based optimization design method for irrigation pipeline systems according to claim 1, characterized in that, No. The predicted water level of the Queen The solution is obtained using a discretized model, and the solution process includes the following steps: Utilizing the current water level The water level dynamic model is used to calculate the predicted water level for the next day. The calculation formula is: ; Using predicted water levels The water level dynamic model is used to calculate the predicted water level for the next day. The calculation formula is: ; And so on, using predicted water levels and the solution of the water level dynamic model Predicted water level for the day The calculation formula is: .

6. The data analysis-based optimization design method for irrigation pipeline systems according to claim 1, characterized in that, The effective precipitation coefficient It is determined based on the daily rainfall, specifically: Rainfall of less than 10 mm on a given day is considered light rain. The effective precipitation coefficient is... Set to 0; Rainfall of 10–25 mm is considered moderate rain, and rainfall of 25–50 mm is considered heavy rain. The effective precipitation coefficient for moderate and heavy rain is as described above. Take a value of 0.8 to 1.0; Rainfall of 50-100 mm is considered a rainstorm; rainfall of 100-250 mm is considered a heavy rainstorm; rainfall exceeding 250 mm is considered an extremely heavy rainstorm; the effective precipitation coefficient for rainstorms, heavy rainstorms, and extremely heavy rainstorms is as follows. Take a value of 0.7 to 0.8.

Images