Intelligent decision-making method and control system for precise irrigation for agricultural water conservancy project

Abstract

The invention relates to the technical field of agricultural hydraulic engineering, in particular to an intelligent decision-making method and control system for precise irrigation for agricultural hydraulic engineering, and the method comprises the steps: constructing a global simulation model to calculate theoretical operation variables, and carrying out the simulation evaluation and variable optimization processing through the collection of a historical operation sequence of a function module. The operation variables can be adjusted according to the actual performance, the problems of water resource waste, energy consumption increase and equipment service life shortening caused by insufficient data acquisition, uneven resource distribution and high-load equipment operation in the prior art are solved, and precise irrigation and efficient resource utilization are achieved.

Description

Technical Field

[0001] The present invention belongs to the technical field of agricultural water conservancy projects, and specifically relates to an intelligent decision-making method and control system for precision irrigation in agricultural water conservancy projects. Background Art

[0002] Irrigation systems are a crucial component of agricultural water conservancy projects. Their primary function is to deliver the appropriate amount of water to farmland based on crop water requirements and soil moisture conditions. Traditional irrigation methods typically rely on manual experience or simple timed and quantitative control, failing to fully account for regional variations in soil characteristics, meteorological conditions, and crop growth stages. While these methods can meet basic irrigation needs to a certain extent, they can easily lead to water waste or insufficient irrigation, impacting crop yield and quality.

[0003] In practical applications, the efficiency and precision of irrigation systems are closely linked. Precision irrigation requires the integration of multiple data sets, such as soil moisture, meteorological information, and crop growth status. However, existing technologies have limitations in data collection and decision support, often failing to achieve efficient intelligent management. Furthermore, continuously operating irrigation equipment at high loads can lead to increased energy consumption and shortened equipment lifespans, which, to a certain extent, limits the long-term stable operation of irrigation systems. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent decision-making method and control system for precision irrigation in agricultural water conservancy projects, aiming to solve the problems of water resource waste, increased energy consumption and shortened equipment life caused by insufficient data collection, uneven resource allocation and continuous high-load operation of equipment in the existing irrigation system.

[0005] The present invention is implemented as follows. In the first aspect, the present invention provides an intelligent decision-making method for precision irrigation for agricultural water conservancy projects, comprising: obtaining technical parameters of several functional modules in the irrigation system and the interaction relationship between each of the functional modules, constructing module simulation models of each functional module according to the technical parameters of each functional module, and combining the module simulation models into a global simulation model of the irrigation system according to the interaction relationship between each of the functional modules; wherein the module simulation model is used to describe the correlation between the operating variables and the operating effects of the functional modules, and the global simulation model is used to simulate the overall operating effects of each of the functional modules in the irrigation system; continuously collecting the operating variables and operating effects of each of the functional modules at different time points, and chronologically analyzing the collected operating variables and operating effects of each of the functional modules at different time points. Integration and sorting are performed to obtain the historical operation sequence of each functional module; the current irrigation demand of the irrigation system is obtained, and the current irrigation demand is simulated and decomposed by the global simulation model to obtain the theoretical operation variables of each module simulation model for the current irrigation demand; each theoretical operation variable is substituted into the module simulation model of the corresponding functional module, and each module simulation model is made to perform multi-dimensional simulation evaluation processing on each theoretical operation variable according to the corresponding historical operation sequence to obtain the simulation evaluation parameters of each module simulation model; the simulation evaluation parameters of each module simulation model are substituted into the global simulation model, and the global simulation model is made to perform variable optimization processing on each theoretical operation variable to obtain the variable optimization result, and each functional module of the irrigation system is driven according to the variable optimization result.

[0006] Preferably, the steps of obtaining the current irrigation demand of the irrigation system and performing simulation decomposition processing on the current irrigation demand through the global simulation model to obtain theoretical operating variables of each module simulation model for the current irrigation demand include: collecting data from an external monitoring device connected to the irrigation system to obtain monitoring data of the external monitoring device, and analyzing and processing the monitoring data based on crop water demand patterns and soil moisture status to obtain current irrigation recommendations of the external monitoring device, and using the current irrigation recommendations as the current irrigation demand of the irrigation system; decomposing the current irrigation demand through each module simulation model in the global simulation model to obtain sub-item irrigation targets of each module simulation model corresponding to the current irrigation demand; and performing reverse calculation processing on each corresponding sub-item irrigation target according to each module simulation model to obtain theoretical operating variables required for each module simulation model to execute the sub-item irrigation targets.

[0007] Preferably, each of the theoretical operation variables is substituted into the module simulation model of the corresponding functional module, and each of the module simulation models is made to perform multi-dimensional simulation evaluation processing on each of the theoretical operation variables according to the corresponding historical operation sequence to obtain the simulation evaluation parameters of each of the module simulation models. The steps include: substituting each of the theoretical operation variables into the module simulation model of the corresponding functional module, and making the module simulation model perform matching processing on the same data in the corresponding historical operation sequence according to the theoretical operation variables to obtain the operation variables that are the same as the theoretical operation variables in the historical operation sequence, and marking the operation variables and the corresponding operation effects as benchmark data; integrating the continuously recorded benchmark data into a benchmark segment according to the time corresponding to each benchmark data to obtain a plurality of benchmark segments, and performing matching processing on the theoretical operation variables in the historical operation sequence ... benchmark data and the corresponding operation effects as benchmark data; integrating the continuously recorded benchmark data into a benchmark segment according to the time corresponding to each benchmark data to obtain a plurality of benchmark segments, and performing matching processing on the theoretical operation variables in the historical operation sequence to obtain the theoretical operation variables. Each of the benchmark segments is subjected to multi-dimensional analysis to obtain analysis parameters of the benchmark data; taking the theoretical operation variable as the benchmark value, a number of adjacent operation variables adjacent to the theoretical operation variable are obtained, and the module simulation model is made to perform matching processing on the same data in the corresponding historical operation sequence according to the adjacent operation variables to obtain the operation variables identical to the adjacent operation variables in the historical operation sequence, and the operation variables and the corresponding operation effects are marked as comparison data; according to the time corresponding to each of the comparison data, the continuously recorded comparison data are integrated into a comparison segment to obtain a number of comparison segments, and each of the comparison segments is subjected to multi-dimensional analysis to obtain analysis parameters of the comparison data; the analysis parameters of the benchmark data and the analysis parameters of the comparison data are combined to form the simulation evaluation parameters of the module simulation model.

[0008] Preferably, the step of performing multi-dimensional analysis on each of the benchmark segments to obtain analysis parameters of the benchmark data includes: calculating the average value of the benchmark data of each benchmark segment with the same duration, and performing difference calculation between the result of the average value calculation and the operational effect of the corresponding theoretical operational variable under the ideal state, so as to obtain the degree of deviation between the operational effect of the theoretical operational variable produced by the duration and the operational effect under the ideal state, combining each of the deviation degrees with the duration of the corresponding benchmark data, and arranging each combination in chronological order to obtain the first characteristic sequence of the operational variable; performing difference analysis on the benchmark data of each benchmark segment with the same duration to obtain the degree of deviation of the benchmark data of each benchmark segment with the same duration, combining each of the deviation degrees with the duration of the corresponding benchmark data, and arranging each combination in chronological order to obtain the second characteristic sequence of the operational variable; superimposing the first characteristic sequence and the second characteristic sequence to summarize the deviation degrees corresponding to the same duration in the first characteristic sequence and the second characteristic sequence into the same combination as the first analysis parameter of the benchmark data.

[0009] Preferably, the step of performing multi-dimensional analysis on each of the comparison segments to obtain the analysis parameters of the comparison data includes: calculating the average value of the benchmark data of each of the comparison segments with the same duration, and performing difference calculation between the result of the average value calculation and the operational effect of the corresponding theoretical operational variable under the ideal state, so as to obtain the degree of deviation between the operational effect of the theoretical operational variable produced by the duration and the operational effect under the ideal state, combining each of the deviation degrees with the duration of the corresponding benchmark data, and arranging each combination in chronological order to obtain the third characteristic sequence of the operational variable; performing difference analysis on the benchmark data of each of the benchmark segments with the same duration to obtain the degree of deviation of the benchmark data of each of the benchmark segments with the same duration, combining each of the deviation degrees with the duration of the corresponding benchmark data, and arranging each combination in chronological order to obtain the fourth characteristic sequence of the operational variable; superimposing the third characteristic sequence and the fourth characteristic sequence to summarize the deviation degrees corresponding to the same duration in the third characteristic sequence and the fourth characteristic sequence into the same combination, as the second analysis parameter of the benchmark data.

[0010] Preferably, the step of substituting the simulation evaluation parameters of each of the module simulation models into the global simulation model and allowing the global simulation model to perform variable optimization processing on each of the theoretical operating variables includes: substituting the first analysis parameter of the benchmark data of each of the module simulation models into the global simulation model, allowing the global simulation model to perform an overall simulation operation based on the first analysis parameter of the benchmark data of each of the module simulation models to obtain a basic simulation distribution diagram of the global simulation model; taking the basic simulation distribution diagram of the global simulation model as a reference, substituting the second analysis parameter of each of the comparison data of each of the module simulation models into the global simulation model, allowing the global simulation model to perform an overall simulation operation to obtain each adjacent simulation distribution diagram of the global simulation model; performing a comparative analysis on the basic simulation distribution diagram and each of the adjacent simulation distribution diagrams to obtain a result of the comparative analysis, determining the basic simulation distribution diagram or the adjacent simulation distribution diagram with the optimal effect according to the result of the comparative analysis, and adjusting the operating variables corresponding to the basic simulation distribution diagram or the adjacent simulation distribution diagram to the theoretical operating variables to obtain a variable optimization result.

[0011] In a second aspect, the present invention provides an intelligent decision-making system for precision irrigation for agricultural water conservancy projects, comprising: a model construction unit for obtaining technical parameters of several functional modules in an irrigation system and the interaction relationship between each of the functional modules, constructing module simulation models of each functional module according to the technical parameters of each functional module, and combining the module simulation models to construct a global simulation model of the irrigation system according to the interaction relationship between each of the functional modules; wherein the module simulation model is used to describe the correlation between the operating variables and the operating effects of the functional modules, and the global simulation model is used to simulate the overall operating effects of each of the functional modules in the irrigation system; a data acquisition unit for continuously collecting the operating variables and operating effects of each of the functional modules at different time points, and integrating and sorting the collected operating variables and operating effects of each of the functional modules at different time points in chronological order. to obtain the historical operation sequence of each functional module; a preliminary decomposition unit, used to obtain the current irrigation demand of the irrigation system, and perform simulation decomposition processing on the current irrigation demand through the global simulation model, so as to obtain the theoretical operation variables of each module simulation model for the current irrigation demand; a simulation evaluation unit, used to substitute each theoretical operation variable into the module simulation model of the corresponding functional module, and make each module simulation model perform multi-dimensional simulation evaluation processing on each theoretical operation variable according to the corresponding historical operation sequence, so as to obtain the simulation evaluation parameters of each module simulation model; a variable optimization unit, used to substitute the simulation evaluation parameters of each module simulation model into the global simulation model, and make the global simulation model perform variable optimization processing on each theoretical operation variable, so as to obtain the variable optimization result, and drive each functional module of the irrigation system according to the variable optimization result.

[0012] The present invention provides an intelligent decision-making method for precision irrigation for agricultural water conservancy projects, which has the following beneficial effects: the present invention constructs a global simulation model based on each functional module in the irrigation system to calculate the theoretical operating variables that are theoretically most effective in responding to current irrigation needs, and judges the actual performance of the functional modules by collecting the operating variables and operating effects of each functional module in the past operation process, so as to judge what effect the functional modules can actually achieve when actually executing the theoretical operating variables and the adjacent operating variables of the theoretical operating variables, thereby determining the actual optimal operating variables of the irrigation system, solving the problems of water resource waste, increased energy consumption and shortened equipment life caused by insufficient data collection, uneven resource allocation and continuous high-load operation of the equipment in the existing irrigation system. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The present invention will be further described below with reference to the accompanying drawings.

[0014] Figure 1 A flow chart of an intelligent decision-making method for precision irrigation in agricultural water conservancy projects provided by an embodiment of the present invention shows the overall steps from data collection to variable optimization.

[0015] Figure 2 This is a schematic diagram of the construction and interactive relationship of the global simulation model and the module simulation model in an embodiment of the present invention, showing the association between functional modules and their integration in the global simulation model.

[0016] Figure 3 This is a schematic diagram of the generation and processing flow of historical operation sequences in an embodiment of the present invention, illustrating how to collect, integrate and sort the operation variables and operation effects of functional modules.

[0017] Figure 4 The structural block diagram of the intelligent decision-making system for precision irrigation of agricultural water conservancy projects provided by the embodiment of the present invention shows the functional division of each unit of the system and their mutual relationship.

[0018] The accompanying drawings are numbered as follows:

[0019] 1. Model building unit; 2. Data collection unit; 3. Preliminary decomposition unit; 4. Simulation evaluation unit; 5. Variable optimization unit. DETAILED DESCRIPTION

[0020] The present invention provides an intelligent decision-making method and control system for precision irrigation of agricultural water conservancy projects. Figure 1 To the attached Figure 4 In practical application, the system realizes intelligent control of the irrigation system through the collaborative work of multiple functional modules to achieve the purpose of precise irrigation.

[0021] First, refer to the attached Figure 1 and attached Figure 2, the model construction unit 1 is used to obtain the technical parameters of several functional modules in the irrigation system, and construct module simulation models of each functional module according to these technical parameters. The core of the module simulation model is to describe the correlation between the operating variables and the operating effects of the functional modules. For example, the functional modules may include water pumps, valves, sensors and other equipment, and the technical parameters of these equipment include but are not limited to flow, pressure, switch status, etc. When constructing the module simulation model, it is necessary to clarify the specific physical connection relationship and information interaction method of each functional module. For example, the water pump and the pipeline are connected by a flange, and the sensor is connected to the controller through a signal line. This connection relationship ensures that the transmission of water flow and the collection of data can be carried out synchronously. At the same time, the model construction unit 1 also needs to combine the simulation models of each module into a global simulation model according to the interaction relationship between the functional modules. The role of the global simulation model is to simulate the overall operating effects of each functional module in the entire irrigation system. Appendix Figure 2 A schematic diagram of the construction and interaction relationship between the global simulation model and the module simulation model is shown. The global simulation model serves as the core framework, integrating the various module simulation models to form a complete simulation environment.

[0022] Next, refer to the attached Figure 3 The data acquisition unit 2 is used to continuously collect the operating variables and operating effects of each functional module at different time points. The data acquisition process specifically includes obtaining real-time data from sensors, controllers and other monitoring devices, and integrating and sorting these data in chronological order to generate the historical operation sequence of each functional module. The generation process of the historical operation sequence is shown in the attached figure. Figure 3 As shown in the figure, the operational variables and operational effects of each functional module are first collected one by one. This data is then arranged according to timestamps to form an ordered time series. For example, within a certain time period, water pump flow data, valve opening data, and soil moisture sensor readings are all recorded and arranged in chronological order, forming a historical operation sequence for the corresponding functional module. This process not only ensures data integrity but also provides a reliable data foundation for subsequent simulation evaluation.

[0023] The primary task of the initial decomposition unit 3 is to obtain the current irrigation demand of the irrigation system and simulate and decompose it using the global simulation model to obtain the theoretical operational variables for each module simulation model. Specifically, the initial decomposition unit 3 first collects data on crop water requirements and soil moisture status through external monitoring equipment and analyzes and processes this data to generate a current irrigation recommendation. The current irrigation recommendation represents the current irrigation demand of the irrigation system. Subsequently, each module simulation model within the global simulation model decomposes the current irrigation demand to obtain the sub-item irrigation targets corresponding to the current irrigation demand for each module simulation model. For example, the current irrigation demand may require the entire irrigation system to complete a certain amount of irrigation within a specific timeframe, while the sub-item irrigation targets specify the amount of irrigation required for each functional module. Finally, the corresponding sub-item irrigation targets are reverse-calculated based on the simulation models of each module to obtain the theoretical operational variables required for each module simulation model to achieve the sub-item irrigation targets. The key to this process is to ensure the rationality and feasibility of the theoretical operational variables to provide accurate input data for subsequent simulation evaluation.

[0024] The simulation evaluation unit 4 is responsible for substituting each theoretical operational variable into the module simulation model of the corresponding functional module and performing a multi-dimensional simulation evaluation process on each theoretical operational variable based on the corresponding historical operation sequence to obtain simulation evaluation parameters for each module simulation model. In a specific implementation, the simulation evaluation unit 4 first substitutes the theoretical operational variable into the module simulation model and causes the module simulation model to perform a matching process based on the theoretical operational variable in the corresponding historical operation sequence to obtain operational variables identical to the theoretical operational variable in the historical operation sequence and their corresponding operational effects, and marks these data as benchmark data. Next, the simulation evaluation unit 4 integrates the continuously recorded benchmark data into a benchmark segment based on the time corresponding to the benchmark data to obtain several benchmark segments. Subsequently, each benchmark segment is subjected to a multi-dimensional analysis to obtain analysis parameters for the benchmark data. Furthermore, the simulation evaluation unit 4 uses the theoretical operational variable as the benchmark value to obtain several adjacent operational variables adjacent to the theoretical operational variable. The module simulation model then performs a matching process based on the adjacent operational variables in the corresponding historical operation sequence to obtain operational variables identical to the adjacent operational variables in the historical operation sequence and their corresponding operational effects, and marks these data as comparison data. Similarly, continuously recorded comparison data is combined into a comparison segment based on the time corresponding to the comparison data. This results in several comparison segments, each of which is then subjected to multi-dimensional analysis to obtain analysis parameters for the comparison data. Ultimately, the analysis parameters of the baseline data and the analysis parameters of the comparison data are combined to form the simulation evaluation parameters of the module simulation model.

[0025] The variable optimization unit 5 is responsible for substituting the simulation evaluation parameters of each module simulation model into the global simulation model and causing the global simulation model to perform variable optimization on each theoretical operational variable to obtain a variable optimization result. In a specific implementation, the variable optimization unit 5 first substitutes the first analysis parameter of the baseline data of each module simulation model into the global simulation model. The global simulation model then performs an overall simulation operation based on the first analysis parameter of the baseline data of each module simulation model to obtain a basic simulation distribution map for the global simulation model. Subsequently, using the basic simulation distribution map of the global simulation model as a reference, the second analysis parameter of each comparison data of each module simulation model is substituted into the global simulation model. The global simulation model then performs an overall simulation operation to obtain each adjacent simulation distribution map of the global simulation model. Finally, a comparative analysis is performed on the basic simulation distribution map and each adjacent simulation distribution map to obtain a comparative analysis result. Based on the comparative analysis result, the optimal basic simulation distribution map or adjacent simulation distribution map is determined. The operational variables corresponding to the basic simulation distribution map or adjacent simulation distribution map are adjusted against the theoretical operational variables to obtain a variable optimization result. The variable optimization result is directly used to drive each functional module of the irrigation system to achieve the goal of precision irrigation.

[0026] In the above implementation process, the collaborative relationship between the various units is particularly important. The model construction unit 1 provides a basic framework for the construction of the global simulation model. The data acquisition unit 2 provides reliable data support for the subsequent simulation evaluation. The preliminary decomposition unit 3 generates theoretical operating variables by decomposing the current irrigation demand. The simulation evaluation unit 4 generates simulation evaluation parameters through multi-dimensional evaluation of the theoretical operating variables. The variable optimization unit 5 generates the final variable optimization results through analysis and optimization of the simulation evaluation parameters. Figure 4 The structural block diagram of the intelligent decision-making system for precision irrigation in agricultural water conservancy projects is shown, in which the model construction unit 1, data acquisition unit 2, preliminary decomposition unit 3, simulation evaluation unit 4 and variable optimization unit 5 respectively assume different functions and are closely connected through data flow and logical relationships to form a complete intelligent decision-making system.

[0027] In a practical application scenario, suppose an agricultural water conservancy project requires precise irrigation of a field. First, the system collects data on soil moisture, meteorological conditions, and crop growth status through external monitoring equipment. This data is then passed to the preliminary decomposition unit 3 to generate the current irrigation demand. Subsequently, the global simulation model decomposes the current irrigation demand to obtain the theoretical operating variables for each functional module. For example, the theoretical operating variable for a water pump might be 50 cubic meters of water delivered per hour, while the theoretical operating variable for a valve might be 50% opening. Next, the simulation evaluation unit 4 performs a multi-dimensional evaluation of these theoretical operating variables based on historical operation sequences to determine their feasibility and effectiveness in actual operation. Finally, the variable optimization unit 5 analyzes and optimizes the simulation evaluation parameters to generate the final variable optimization results, which are then applied to the actual irrigation system control. In this way, the system can minimize water waste and energy consumption while ensuring irrigation effectiveness, thereby extending the service life of the equipment.

[0028] The above embodiments describe the specific implementation process of the present invention in detail, covering every step from data collection to variable optimization. The connections, positions, and coordination between the various components are fully illustrated with the accompanying figures. Through these embodiments, those skilled in the art will be able to clearly understand and implement the technical solutions of the present invention, thereby achieving the goal of precision irrigation.

[0029] In order to better enable relevant personnel in this technical field to fully understand and implement the present invention, the specific implementation principle of the present invention is further supplemented below with reference to a specific application scenario.

[0030] In a certain agricultural water conservancy project, the system needs to accurately irrigate a piece of farmland. First, the model construction unit 1 obtains the technical parameters of equipment such as water pumps, valves, and sensors in the irrigation system, and constructs module simulation models of these functional modules respectively. For example, the flow and pressure parameters of the water pump are clearly recorded and physically associated with the pipeline through flange connections; the sensor transmits the collected soil moisture data to the controller through signal lines. On this basis, the model construction unit 1 integrates the simulation models of each module into a global simulation model to simulate the overall operation effect of the entire irrigation system. Appendix Figure 2 This process is demonstrated, in which the global simulation model serves as the core framework, tightly connecting the simulation models of each module to form a complete simulation environment.

[0031] Subsequently, the data acquisition unit 2 starts working and continuously collects real-time data from sensors, controllers, and other monitoring devices. For example, within a certain period of time, the flow data of the water pump, the opening data of the valve, and the readings of the soil moisture sensor are all recorded one by one and arranged according to the timestamp, finally generating an orderly historical operation sequence. Figure 3 This process is described in detail, in which the generation of historical operation sequences ensures a complete and reliable data basis for subsequent simulation evaluations.

[0032] Preliminary decomposition unit 3 generates the current irrigation demand based on data collected by external monitoring equipment, including soil moisture, meteorological conditions, and crop growth status. For example, if the current soil moisture in a field is below the minimum threshold required for crop growth, preliminary decomposition unit 3 analyzes and recommends increasing irrigation volume. The global simulation model then decomposes this irrigation demand to derive the theoretical operating variables for each functional module. For example, the theoretical operating variable for a water pump might be set to deliver 50 cubic meters of water per hour, while the theoretical operating variable for a valve might be set to open to 50%.

[0033] Next, the simulation evaluation unit 4 substitutes these theoretical operating variables into the corresponding module simulation model, and performs a multi-dimensional evaluation on the theoretical operating variables in combination with the historical operating sequence. For example, the simulation evaluation unit 4 first finds the operating variables and their corresponding operating effects that are the same as the theoretical operating variables in the historical operating sequence, and marks them as benchmark data. Subsequently, the simulation evaluation unit 4 integrates the continuously recorded benchmark data into several benchmark segments, and performs a multi-dimensional analysis on each benchmark segment. In addition, the simulation evaluation unit 4 also uses the theoretical operating variables as the benchmark value, obtains several neighboring operating variables adjacent to the theoretical operating variables, and finds the operating variables and their corresponding operating effects that are the same as the neighboring operating variables in the historical operating sequence, and marks them as comparative data. Similarly, the comparative data is integrated into several comparative segments, and a multi-dimensional analysis is performed. Appendix Figure 3 The generation and analysis process of benchmark data and comparative data in this process is demonstrated.

[0034] The variable optimization unit 5 substitutes the first analysis parameter of the baseline data and the second analysis parameter of the comparison data into the global simulation model to perform an overall simulation operation. For example, the variable optimization unit 5 first generates a base simulation distribution diagram for the global simulation model based on the first analysis parameter of the baseline data, and then substitutes the second analysis parameter of the comparison data into the global simulation model to generate multiple adjacent simulation distribution diagrams. By comparing and analyzing the base simulation distribution diagram and the adjacent simulation distribution diagrams, the variable optimization unit 5 determines the simulation distribution diagram with the optimal effect and adjusts the theoretical operating variables accordingly to generate variable optimization results. For example, the actual operating variables of a water pump may be adjusted from delivering 50 cubic meters of water per hour to delivering 48 cubic meters of water per hour to better meet actual operating conditions.

[0035] Finally, the variable optimization results are passed to the various functional modules of the irrigation system, driving them to execute the optimized operating variables. For example, the water pump adjusts the flow rate according to the optimized operating variables, and the valve is adjusted according to the optimized opening value, thus achieving the goal of precise irrigation. Figure 4 The structural block diagram of the system is shown, in which the model building unit 1, data acquisition unit 2, preliminary decomposition unit 3, simulation evaluation unit 4 and variable optimization unit 5 work closely together through data flow and logical relationships to form a complete intelligent decision-making system.

[0036] Through these steps, the system ensures irrigation effectiveness while minimizing water waste and energy consumption and extending equipment life. For example, when the system detects that soil moisture in a particular area has reached the optimal range for crop water requirements, it automatically reduces irrigation volume in that area, avoiding water waste caused by over-irrigation. Furthermore, by real-time monitoring and optimizing equipment operating status, the system reduces the amount of time equipment operates at high load, thereby extending its lifespan.

[0037] Any information not described in detail in the specification belongs to the prior art known to those skilled in the art, and the model parameters of each electrical appliance are not specifically limited; conventional equipment can be used. Electrical control components not mentioned in this technical solution are not shown in the figures because they belong to the prior art and will not be described here.

[0038] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included in the scope of protection of the present invention.

Claims

1. An intelligent decision-making method for precision irrigation in agricultural water conservancy projects, characterized in that: include: Obtaining technical parameters of several functional modules in the irrigation system and the interaction relationships between the functional modules, constructing module simulation models for the functional modules based on the technical parameters of the functional modules, and combining the module simulation models to construct a global simulation model of the irrigation system based on the interaction relationships between the functional modules; wherein the module simulation models are used to describe the correlation between the operating variables and the operating effects of the functional modules, and the global simulation model is used to simulate the overall operating effects of the functional modules in the irrigation system; Continuously collecting the operating variables and operating effects of each functional module at different time points, and integrating and sorting the collected operating variables and operating effects of each functional module at different time points in chronological order to obtain a historical operation sequence of each functional module; Acquiring a current irrigation demand of the irrigation system, and performing simulation decomposition processing on the current irrigation demand through the global simulation model to obtain theoretical operating variables of each module simulation model for the current irrigation demand; Substituting each of the theoretical operating variables into the module simulation model of the corresponding functional module, respectively, and causing each of the module simulation models to perform multi-dimensional simulation evaluation processing on each of the theoretical operating variables according to the corresponding historical operation sequence, so as to obtain simulation evaluation parameters of each of the module simulation models; The simulation evaluation parameters of each module simulation model are substituted into the global simulation model, and the global simulation model is made to perform variable optimization processing on each theoretical operation variable to obtain a variable optimization result, and each functional module of the irrigation system is driven according to the variable optimization result.

2. The intelligent decision-making method for precision irrigation of agricultural water conservancy projects according to claim 1, characterized in that: The steps of obtaining the current irrigation demand of the irrigation system and performing simulation decomposition processing on the current irrigation demand through the global simulation model to obtain theoretical operating variables of each module simulation model for the current irrigation demand include: collecting data from an external monitoring device connected to the irrigation system to obtain monitoring data from the external monitoring device, analyzing and processing the monitoring data based on crop water demand patterns and soil moisture status to obtain a current irrigation recommendation from the external monitoring device, and using the current irrigation recommendation as the current irrigation demand of the irrigation system; Decomposing the current irrigation demand through each of the module simulation models in the global simulation model to obtain sub-item irrigation targets of each of the module simulation models corresponding to the current irrigation demand; Reverse calculation processing is performed on the corresponding sub-item irrigation targets according to the respective module simulation models to obtain theoretical operating variables required for the respective module simulation models to execute the sub-item irrigation targets.

3. The intelligent decision-making method for precision irrigation of agricultural water conservancy projects according to claim 1, characterized in that: Substituting each of the theoretical operating variables into the module simulation model of the corresponding functional module, and causing each of the module simulation models to perform multi-dimensional simulation evaluation processing on each of the theoretical operating variables according to the corresponding historical operation sequence to obtain simulation evaluation parameters of each of the module simulation models includes the following steps: Substituting each of the theoretical operation variables into a module simulation model of the corresponding functional module, allowing the module simulation model to perform a matching process on identical data in a corresponding historical operation sequence according to the theoretical operation variables, so as to obtain the operation variables in the historical operation sequence that are identical to the theoretical operation variables, and marking the operation variables and corresponding operation effects as benchmark data; Integrating the continuously recorded benchmark data into a benchmark segment according to the time corresponding to each benchmark data to obtain a plurality of benchmark segments, and performing multi-dimensional analysis on each benchmark segment to obtain analysis parameters of the benchmark data; Taking the theoretical operation variable as a reference value, obtaining several adjacent operation variables adjacent to the theoretical operation variable, causing the module simulation model to perform identical data matching processing in a corresponding historical operation sequence based on the adjacent operation variables, so as to obtain the operation variables identical to the adjacent operation variables in the historical operation sequence, and marking the operation variables and corresponding operation effects as comparison data; Integrating the continuously recorded comparative data into a comparative segment according to the time corresponding to each comparative data to obtain a plurality of comparative segments, and performing multi-dimensional analysis on each comparative segment to obtain analysis parameters of the comparative data; The analysis parameters of the benchmark data and the analysis parameters of the comparison data are combined to form simulation evaluation parameters of the module simulation model.

4. The intelligent decision-making method for precision irrigation of agricultural water conservancy projects according to claim 3, characterized in that: The step of performing multi-dimensional analysis on each of the benchmark segments to obtain analysis parameters of the benchmark data includes: Calculating an average value of the benchmark data of each benchmark segment with the same duration, and performing a difference calculation between the average value calculation result and the operational effect of the corresponding theoretical operational variable under an ideal state to obtain a degree of deviation between the operational effect of the theoretical operational variable produced by the duration and the operational effect under the ideal state, combining each of the deviation degrees with the duration of the corresponding benchmark data, and arranging each combination in chronological order to obtain a first characteristic sequence of the operational variable; performing a difference analysis on the benchmark data of the same duration for each benchmark segment to obtain a degree of deviation of the benchmark data of the same duration for each benchmark segment, combining each degree of deviation with the duration of the corresponding benchmark data, and arranging each combination in chronological order to obtain a second characteristic sequence of the manipulated variable; The first characteristic sequence and the second characteristic sequence are superimposed to summarize the deviation degrees corresponding to the same duration in the first characteristic sequence and the second characteristic sequence into the same combination as the first analysis parameter of the benchmark data.

5. The intelligent decision-making method for precision irrigation of agricultural water conservancy projects according to claim 3, characterized in that: The step of performing multi-dimensional analysis on each of the comparison segments to obtain analysis parameters of the comparison data includes: Calculating an average value of the benchmark data of each comparison segment with the same duration, and performing a difference calculation between the average value calculation result and the operational effect of the corresponding theoretical operational variable under an ideal state to obtain a degree of deviation between the operational effect of the theoretical operational variable produced with the duration and the operational effect under the ideal state, combining each of the deviation degrees with the duration of the corresponding benchmark data, and arranging each combination in chronological order to obtain a third characteristic sequence of the operational variable; performing a difference analysis on the benchmark data of the same duration for each benchmark segment to obtain a degree of deviation of the benchmark data of the same duration for each benchmark segment, combining each degree of deviation with the duration of the corresponding benchmark data, and arranging each combination in chronological order to obtain a fourth characteristic sequence of the manipulated variable; The third characteristic sequence and the fourth characteristic sequence are superimposed to summarize the deviation degrees corresponding to the same duration in the third characteristic sequence and the fourth characteristic sequence into the same combination as the second analysis parameter of the benchmark data.

6. The intelligent decision-making method for precision irrigation of agricultural water conservancy projects according to claim 3, characterized in that: The steps of substituting the simulation evaluation parameters of each module simulation model into the global simulation model and causing the global simulation model to perform variable optimization processing on each theoretical operation variable include: Substituting the first analysis parameter of the benchmark data of each of the module simulation models into the global simulation model, and causing the global simulation model to perform an overall simulation operation according to the first analysis parameter of the benchmark data of each of the module simulation models, so as to obtain a basic simulation distribution diagram of the global simulation model; Taking the basic simulation distribution map of the global simulation model as a reference, the second analysis parameters of each of the comparison data of each of the module simulation models are respectively substituted into the global simulation model, and the global simulation model is made to perform an overall simulation operation to obtain each adjacent simulation distribution map of the global simulation model; A comparative analysis is performed on the basic simulation distribution map and each of the adjacent simulation distribution maps to obtain a comparative analysis result. The basic simulation distribution map or the adjacent simulation distribution map with the optimal effect is determined according to the comparative analysis result, and the operating variables corresponding to the basic simulation distribution map or the adjacent simulation distribution map are adjusted to the theoretical operating variables to obtain a variable optimization result.

7. An intelligent decision-making system for precision irrigation of agricultural water conservancy projects, characterized in that: include: A model construction unit (1) is used to obtain technical parameters of several functional modules in the irrigation system and the interaction relationship between each functional module, respectively construct a module simulation model of each functional module according to the technical parameters of each functional module, and combine each module simulation model to construct a global simulation model of the irrigation system according to the interaction relationship between each functional module; wherein the module simulation model is used to describe the correlation between the operating variables and the operating effects of the functional modules, and the global simulation model is used to simulate the overall operating effects of each functional module in the irrigation system; A data collection unit (2) is used to continuously collect the operation variables and operation effects of each functional module at different time points, and integrate and sort the collected operation variables and operation effects of each functional module at different time points in chronological order to obtain a historical operation sequence of each functional module; A preliminary decomposition unit (3) is used to obtain the current irrigation demand of the irrigation system and simulate and decompose the current irrigation demand through the global simulation model to obtain theoretical operating variables of each module simulation model for the current irrigation demand; A simulation evaluation unit (4) is used to substitute each of the theoretical operation variables into a module simulation model of the corresponding functional module, and to make each of the module simulation models perform multi-dimensional simulation evaluation processing on each of the theoretical operation variables according to the corresponding historical operation sequence, so as to obtain simulation evaluation parameters of each of the module simulation models; A variable optimization unit (5) is used to substitute the simulation evaluation parameters of each module simulation model into the global simulation model, and to make the global simulation model perform variable optimization processing on each theoretical operation variable to obtain a variable optimization result, and to drive each functional module of the irrigation system according to the variable optimization result.

8. The intelligent decision-making system for precision irrigation of agricultural water conservancy projects according to claim 7, characterized in that: The preliminary decomposition unit (3) is also used for: collecting data from an external monitoring device connected to the irrigation system to obtain monitoring data from the external monitoring device, analyzing and processing the monitoring data based on crop water demand patterns and soil moisture status to obtain a current irrigation recommendation from the external monitoring device, and using the current irrigation recommendation as the current irrigation demand of the irrigation system; Decomposing the current irrigation demand through each of the module simulation models in the global simulation model to obtain sub-item irrigation targets of each of the module simulation models corresponding to the current irrigation demand; Reverse calculation processing is performed on the corresponding sub-item irrigation targets according to the respective module simulation models to obtain theoretical operating variables required for the respective module simulation models to execute the sub-item irrigation targets.

9. The intelligent decision-making system for precision irrigation of agricultural water conservancy projects according to claim 7, characterized in that: The simulation evaluation unit (4) is further configured to: Substituting each of the theoretical operation variables into a module simulation model of the corresponding functional module, allowing the module simulation model to perform a matching process on identical data in a corresponding historical operation sequence according to the theoretical operation variables, so as to obtain the operation variables in the historical operation sequence that are identical to the theoretical operation variables, and marking the operation variables and corresponding operation effects as benchmark data; Integrating the continuously recorded benchmark data into a benchmark segment according to the time corresponding to each benchmark data to obtain a plurality of benchmark segments, and performing multi-dimensional analysis on each benchmark segment to obtain analysis parameters of the benchmark data; Taking the theoretical operation variable as a reference value, obtaining several adjacent operation variables adjacent to the theoretical operation variable, causing the module simulation model to perform identical data matching processing in a corresponding historical operation sequence based on the adjacent operation variables, so as to obtain the operation variables identical to the adjacent operation variables in the historical operation sequence, and marking the operation variables and corresponding operation effects as comparison data; Integrating the continuously recorded comparative data into a comparative segment according to the time corresponding to each comparative data to obtain a plurality of comparative segments, and performing multi-dimensional analysis on each comparative segment to obtain analysis parameters of the comparative data; The analysis parameters of the benchmark data and the analysis parameters of the comparison data are combined to form simulation evaluation parameters of the module simulation model.

10. The intelligent decision-making system for precision irrigation of agricultural water conservancy projects according to claim 7, characterized in that: The variable optimization unit (5) is further used for: Substituting the first analysis parameter of the benchmark data of each of the module simulation models into the global simulation model, and causing the global simulation model to perform an overall simulation operation according to the first analysis parameter of the benchmark data of each of the module simulation models, so as to obtain a basic simulation distribution diagram of the global simulation model; Taking the basic simulation distribution map of the global simulation model as a reference, the second analysis parameters of each of the comparison data of each of the module simulation models are respectively substituted into the global simulation model, and the global simulation model is made to perform an overall simulation operation to obtain each adjacent simulation distribution map of the global simulation model; A comparative analysis is performed on the basic simulation distribution map and each of the adjacent simulation distribution maps to obtain a comparative analysis result. The basic simulation distribution map or the adjacent simulation distribution map with the optimal effect is determined according to the comparative analysis result, and the operating variables corresponding to the basic simulation distribution map or the adjacent simulation distribution map are adjusted to the theoretical operating variables to obtain a variable optimization result.

Images