Irrigation and drainage control method and system for saline-alkali land based on cumulative optimization
By performing steady-state feature clustering and chain network construction of saline-alkali land irrigation and drainage areas, and using the cumulative optimization model to optimize irrigation and drainage parameters, the problem of different effects caused by unified control in saline-alkali land irrigation and drainage control is solved, and more efficient irrigation and drainage control is achieved.
Patent Information
- Application Number
- CN202410642120.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-23
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-05-23
AI Technical Summary
The existing saline-alkali land irrigation and drainage control methods lack personalized control for different land characteristics, resulting in poor irrigation and drainage effects, and unified control leads to large differences in improvement effects.
By clustering the steady-state characteristics of the target irrigation and drainage areas, building an irrigation and drainage area chain network, optimizing irrigation parameters using the cumulative optimization model, realizing zoning irrigation control based on regional characteristics, and improving the degree of refinement of irrigation and drainage control.
Through the application of steady-state feature clustering and cumulative optimization model of irrigation and drainage, better adaptation between irrigation and drainage control and actual areas is achieved, and the degree of refinement and effect of irrigation and drainage control is improved.
Smart Images

Figure CN118476462B_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of intelligent control technology, and in particular to a saline-alkali land irrigation and drainage control method and system based on cumulative optimization. Background Art
[0002] Irrigation, leaching and drainage are important measures for improving saline-alkali soil. Land salinization has seriously restricted the development of agricultural economy in special areas. The management of saline-alkali land is a long-term and complex project. Irrigation and drainage engineering measures, including flushing, drainage, and salt removal, have always been important means of improving saline-alkali land. We make full use of the water sources of the main and branch canals and nearby water storage reservoirs, and use water diversion irrigation to wash the field soil. According to the technical plan of alkali pressure replenishment, we test and propose an optimized calculation method for salt washing irrigation quota using concealed pipes and vertical shafts under the condition of sufficient water replenishment in saline-alkali land.
[0003] At present, most of the existing saline-alkali land irrigation and drainage controls are unified controls for a region, but the same region may contain land with different characteristics, which leads to large differences in the saline-alkali land improvement effects in the entire region. In addition, the existing technology lacks control analysis of different control nodes, which leads to poor irrigation and drainage control effects.
[0004] In summary, the existing technology has technical problems such as large differences in the improvement effects of saline-alkali land in the entire area due to the fact that the same area may contain land with different characteristics, and unified control leads to large differences in the control analysis of different control nodes, which in turn leads to poor irrigation and drainage control effects. Summary of the invention
[0005] The purpose of the present invention is to provide a saline-alkali land irrigation and drainage control method and system based on cumulative optimization, so as to solve the technical problems in the prior art that the same area may contain land with different characteristics, and unified control leads to large differences in the improvement effect of saline-alkali land in the entire area, and there is a lack of control analysis for different control nodes, which in turn leads to poor irrigation and drainage control effects.
[0006] In view of the above problems, the present disclosure provides a saline-alkali land irrigation and drainage control method and system based on cumulative optimization.
[0007] In a first aspect, the present disclosure provides a saline-alkali land irrigation and drainage control method based on cumulative optimization, wherein the method is implemented by a saline-alkali land irrigation and drainage control system based on cumulative optimization, wherein the method comprises: collecting target irrigation and drainage area information, clustering irrigation and drainage steady-state characteristics of the target irrigation and drainage area, and constructing an irrigation and drainage area chain network; analyzing irrigation and drainage step parameters according to the target irrigation and drainage area information, determining an irrigation and drainage parameter sequence set, and performing dynamic feature analysis on each parameter in the irrigation and drainage parameter sequence set; determining optimization parameters according to the dynamic feature analysis results, and collecting sample data based on the optimization parameters to train an optimization module; extracting links using the irrigation and drainage area chain network, and embedding links using the optimization module to obtain a cumulative optimization model; collecting irrigation and drainage monitoring data sets, preprocessing the irrigation and drainage monitoring data sets as input, and loading them into the cumulative optimization model to obtain an optimized control parameter chain for irrigation and drainage control.
[0008] In a second aspect, the present disclosure further provides a saline-alkali land irrigation and drainage control system based on cumulative optimization, which is used to execute the saline-alkali land irrigation and drainage control method based on cumulative optimization as described in the first aspect, wherein the system includes: a steady-state feature clustering unit, which is used to collect target irrigation and drainage area information, cluster the irrigation and drainage steady-state features of the target irrigation and drainage area, and construct an irrigation and drainage area chain network; a feature dynamic analysis unit, which is used to analyze irrigation and drainage step parameters according to the target irrigation and drainage area information, determine an irrigation and drainage parameter sequence set, and perform feature dynamic analysis on each parameter in the irrigation and drainage parameter sequence set. dynamic analysis; an optimization training unit, which is used to determine the optimization parameters according to the dynamic analysis results of the features, and to collect sample data based on the optimization parameters to train the optimization module; an optimization model acquisition unit, which is used to extract links based on the irrigation and drainage area chain network, and to embed links using the optimization module to obtain a cumulative optimization model; an irrigation and drainage control unit, which is used to collect irrigation and drainage monitoring data sets, pre-process the irrigation and drainage monitoring data sets as input, load them into the cumulative optimization model, and obtain an optimization control parameter chain for irrigation and drainage control.
[0009] One or more technical solutions provided in this disclosure have at least the following technical effects or advantages:
[0010] Collect the target irrigation and drainage area information, cluster the irrigation and drainage steady-state characteristics of the target irrigation and drainage area, and construct the irrigation and drainage area chain network; analyze the irrigation and drainage step parameters according to the target irrigation and drainage area information, determine the irrigation and drainage parameter sequence set, and perform dynamic feature analysis on each parameter in the irrigation and drainage parameter sequence set; determine the optimization parameters according to the dynamic feature analysis results, and collect sample data based on the optimization parameters to train the optimization module; extract links based on the irrigation and drainage area chain network, use the optimization module to embed links, and obtain the cumulative optimization model; collect irrigation and drainage monitoring data sets, pre-process the irrigation and drainage monitoring data sets as input, load them into the cumulative optimization model, and obtain the optimized control parameter chain for irrigation and drainage control. In this way, by clustering the irrigation and drainage steady-state characteristics of the target irrigation and drainage area, constructing the irrigation and drainage area chain network, and optimizing the irrigation and drainage control parameters based on the irrigation and drainage area chain network through the cumulative optimization model, the regional irrigation control based on the regional characteristics is realized, so as to improve the adaptability of the irrigation and drainage control to the actual area, and then improve the technical effect of the degree of refinement of the irrigation and drainage control.
[0011] The above description is only an overview of the technical solution of the present disclosure. In order to more clearly understand the technical means of the present disclosure, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present disclosure more obvious and easy to understand, the specific implementation methods of the present disclosure are listed below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0012] In order to more clearly illustrate the technical solutions in the present disclosure or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.
[0013] Figure 1 It is a flow chart of the saline-alkali land irrigation and drainage control method based on cumulative optimization disclosed in the present invention;
[0014] Figure 2 This is a schematic diagram of the structure of the saline-alkali land irrigation and drainage control system based on cumulative optimization disclosed in the present invention.
[0015] Explanation of the reference numerals: steady-state feature clustering unit 11 , feature dynamic analysis unit 12 , optimization training unit 13 , optimization model acquisition unit 14 , irrigation and drainage control unit 15 . DETAILED DESCRIPTION
[0016] The present disclosure provides a saline-alkali land irrigation and drainage control method and system based on cumulative optimization, which solves the technical problem in the prior art that the saline-alkali land improvement effect of the entire region is quite different due to the fact that the same region may contain land with different characteristics, and unified control leads to a lack of control analysis for different control nodes, which leads to poor irrigation and drainage control effect. The target irrigation and drainage area is clustered with steady-state irrigation and drainage characteristics, and an irrigation and drainage area chain network is constructed. Based on the irrigation and drainage area chain network, irrigation and drainage control parameters are optimized through a cumulative optimization model, and regional irrigation control based on regional characteristics is realized, so as to achieve the technical effect of improving the adaptability of irrigation and drainage control to the actual region, thereby improving the degree of refinement of irrigation and drainage control.
[0017] Below, the technical solutions in the present disclosure will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments of the present disclosure. It should be understood that the present disclosure is not limited to the example embodiments described herein. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure. It should also be noted that, for the convenience of description, only the parts related to the present disclosure are shown in the accompanying drawings, rather than all of them.
[0018] Example 1
[0019] Please refer to the attached Figure 1 The present disclosure provides a saline-alkali land irrigation and drainage control method based on cumulative optimization, wherein the method is applied to a saline-alkali land irrigation and drainage control system based on cumulative optimization, and the method specifically comprises the following steps:
[0020] Step 1: Collect target irrigation and drainage area information, cluster the irrigation and drainage steady-state characteristics of the target irrigation and drainage areas, and build an irrigation and drainage area chain network;
[0021] Specifically, the target irrigation and drainage area information includes the topography, landform, area, ground flatness, soil quality, location, irrigation and drainage sources, and irrigation and drainage accommodation information of the saline-alkali land to be controlled for irrigation and drainage, among which the irrigation and drainage accommodation information includes the irrigation time, location, water volume of the current irrigation and drainage scheme, as well as the location and time of drainage, as well as information such as irrigation and drainage pipelines and irrigation and drainage equipment; the irrigation and drainage sources include the quality of the water source, such as salt content; the location and soil quality refer to the location and soil texture of the saline-alkali land; the ground flatness refers to the height difference of the field surface; the topography and landform refer to the height of the saline-alkali land, and the corresponding terrain type, such as mountains and hills; the area refers to the numerical representation of the size of the saline-alkali land. It can be understood that the topography, landform, area, ground flatness, soil quality, location, irrigation and drainage sources, and irrigation and drainage accommodation information have an important impact on the irrigation and drainage of saline-alkali land, such as areas with undulating terrain and areas where the ground slopes to one side, and the channel can only irrigate one side. It can be understood that the target irrigation and drainage area information can be collected by the user and uploaded through the client.
[0022] The target irrigation and drainage area is further clustered for irrigation and drainage steady-state characteristics. The target irrigation and drainage area is the saline-alkali land to be controlled for irrigation and drainage. That is to say, the information in the target irrigation and drainage area is difficult to change, such as terrain, drainage pipelines, topography, etc. If you want to improve the irrigation and drainage effect by changing this information, the required human and material resources are huge. Therefore, it is only necessary to cluster the irrigation and drainage steady-state characteristics of the target irrigation and drainage area based on the target irrigation and drainage area information, that is, to divide the target irrigation and drainage area into multiple sub-areas. That is to say, the entire target irrigation and drainage area may contain fields with different terrains, topography, soil qualities, etc. Different fields The irrigation and drainage sources and irrigation and drainage control parameters used in irrigation and drainage are different. However, most of the existing technologies perform unified control, which leads to poor irrigation and drainage effects. The technical solution adopted in the present invention clusters the irrigation and drainage steady-state characteristics of the target irrigation and drainage area, that is, the fields with similar terrain, topography, area, ground flatness, soil quality, location, irrigation and drainage sources, and irrigation and drainage accommodation information are divided into one category, and an irrigation and drainage area chain network is constructed based on the division results. The irrigation and drainage area chain network includes irrigation and drainage links corresponding to each clustering result, that is, links formed by connecting the fields in the clustering results according to the irrigation location and sequence, and the drainage location and sequence.
[0023] Step 2: Analyze irrigation and drainage step parameters according to the target irrigation and drainage area information, determine an irrigation and drainage parameter sequence set, and perform dynamic feature analysis on each parameter in the irrigation and drainage parameter sequence set;
[0024] Specifically, the target irrigation and drainage area information includes the topography, topography, area, ground flatness, soil quality, location, irrigation and drainage sources, and irrigation and drainage accommodation information of the target irrigation and drainage area. According to the target irrigation and drainage area information, the historical irrigation and drainage parameter records of the same type of irrigation and drainage areas are retrieved, and the irrigation and drainage step parameters at different time nodes are extracted, such as the irrigation amount during irrigation, the drainage rate during drainage, etc., thereby determining the irrigation and drainage parameter sequence set, which includes the irrigation amount, drainage rate and other parameters arranged in sequence at different time nodes. Further, the characteristic dynamic analysis of each parameter in the irrigation and drainage parameter sequence set is to analyze the historical irrigation and drainage parameter records, the stability of the changes of the same type of parameters, such as the irrigation amount and drainage rate, which can be specifically calculated by calculating the variance or standard deviation of the same type of parameters under the historical irrigation and drainage parameter records as a stability indicator, and using this as the characteristic dynamic analysis result.
[0025] Step 3: Determine optimization parameters based on the dynamic feature analysis results, collect sample data based on the optimization parameters, and train the optimization module;
[0026] Specifically, the dynamic analysis results of the characteristics include the stability of different irrigation and drainage parameters. If the parameter stability is high, that is, the corresponding variance or standard deviation is low, it means that it has consistently maintained a stable value in the historical irrigation and drainage process. In this case, it will not be changed and optimized, but other parameters with lower stability will be used as optimization parameters. Specifically, a stability index threshold can be set by professional and technical personnel in this field based on actual experience, and parameters with stability indicators greater than the stability index threshold can be extracted as optimization parameters based on the dynamic analysis results of the characteristics. The sample data collection based on the optimization parameters is to collect the parameter value records corresponding to the optimization parameters in the historical irrigation and drainage records, and the irrigation and drainage quality records corresponding to the parameter value records as sample data, and construct an optimization module with the sample data. The optimization module is constructed based on the existing machine learning model, such as a neural network model, with the parameter value records as input, and the corresponding irrigation and drainage quality records are used for output supervision and adjustment, and then the existing optimization algorithm is introduced, such as a particle swarm algorithm, a taboo search algorithm, etc., and the optimization algorithm is used to optimize the direction of quality improvement, thereby training the optimization module to convergence, that is, after the irrigation and drainage data corresponding to the irrigation and drainage steps are input into the optimization module, the optimization module will analyze the output irrigation and drainage quality, and then adjust the irrigation and drainage data through multiple iterations of the optimization algorithm and perform irrigation and drainage quality analysis, and perform optimization in the direction of quality improvement, thereby outputting new irrigation and drainage parameters. Moreover, each irrigation and drainage step will have an impact on the adjacent irrigation and drainage steps behind, so after each step is completed, the parameters are optimized after the impact analysis of the adjacent steps behind is performed based on the completed steps. Different irrigation and drainage steps correspond to an optimization module respectively. At the same time, each time irrigation and drainage is carried out, the salinity of the land in the target irrigation and drainage area is changed once. Subsequently, optimization can be performed again on the basis of the previous optimization. That is, the crops planted in the target irrigation and drainage area at different times may be different, and the irrigation requirements of different crops are also different. For example, some crops have strong salt tolerance, while some crops have weak salt tolerance. For crops at different times, optimization is performed again on the basis of the previous optimization.
[0027] Step 4: extracting links using the irrigation and drainage area chain network, embedding links using the optimization module, and obtaining a cumulative optimization model;
[0028] Specifically, the irrigation and drainage area chain network includes irrigation and drainage links corresponding to each clustering result, and any irrigation and drainage link is extracted, and the optimization module is used to embed the link. That is to say, the aforementioned clustering is performed based on the terrain characteristics of the target irrigation and drainage area, and each clustering result is a segmented field area. Then the terrain between different field areas is different, that is, some areas have high terrain and some areas have low terrain. Then the irrigation and drainage between different areas will have an impact. For example, the water flow in the high-terrain area may flow to the adjacent low-terrain area. Then, when controlling the irrigation and drainage of the next area, it is necessary to consider the terrain influence relationship between adjacent areas to optimize the irrigation and drainage parameters. Based on this, the Markov chain is used to analyze the correlation influence between the terrain of each field area in the irrigation and drainage link, and the optimization module corresponding to the irrigation and drainage link is embedded to obtain a cumulative optimization model. In this way, after optimizing the irrigation and drainage parameters of the irrigation and drainage steps, the cumulative optimization model is used to analyze the terrain correlation influence between fields, and the irrigation and drainage parameters between field areas are optimized and adjusted to improve the refinement of irrigation and drainage control.
[0029] Step 5: Collect irrigation and drainage monitoring data sets, pre-process the irrigation and drainage monitoring data sets as input, load them into the cumulative optimization model, and obtain an optimized control parameter chain for irrigation and drainage control.
[0030] Specifically, an irrigation and drainage monitoring data set is collected, wherein the irrigation and drainage monitoring data set contains the irrigation and drainage data of the control node corresponding to each irrigation and drainage step, including irrigation volume, drainage speed, etc., which can be monitored by setting corresponding sensors at the irrigation and drainage control nodes, and the irrigation and drainage monitoring data set is preprocessed and used as input. The preprocessing is to map and align the irrigation and drainage control nodes of the irrigation and drainage monitoring data set to facilitate control optimization for different nodes, and then load it into the cumulative optimization model to output the optimized control parameter chain corresponding to each node for irrigation and drainage control. The optimized control parameter chain includes control parameters corresponding to different irrigation and drainage control nodes, thereby improving the irrigation and drainage control precision and accuracy.
[0031] Furthermore, step one of the present disclosure also includes:
[0032] Based on the boundary information of the target irrigation and drainage area, the terrain, topography, area, ground flatness, soil quality, location, irrigation and drainage sources, and irrigation and drainage accommodation information of the target irrigation and drainage area are collected as the target irrigation and drainage area information; a constraint analysis is performed on each collected parameter in the target irrigation and drainage area information, and the parameters whose constraint analysis results reach a preset threshold are used as steady-state features; the steady-state features are used to perform parameter clustering on the land in the target irrigation and drainage area, and the land clustering results are segmented according to preset clustering segmentation conditions to obtain the land segmentation results of the target irrigation and drainage area; the irrigation and drainage paths of the land segmentation results are connected based on the irrigation and drainage sources and irrigation and drainage accommodation information to construct the irrigation and drainage area chain network.
[0033] The method of collecting target irrigation and drainage area information, clustering the steady-state characteristics of the target irrigation and drainage area, and constructing the irrigation and drainage area chain network is as follows: First, collect boundary information: First, the boundary information of the target irrigation and drainage area, that is, the starting point, end point, length, width and other information of the target irrigation and drainage area can be obtained through existing map measurement, GPS positioning or on-site investigation. Based on the boundary information, combined with the existing geographic information system or other related tools, the terrain and topographic characteristics are obtained, including altitude, slope, slope direction, landform type and other information. The area of the target irrigation and drainage area is further calculated, and the height difference at different positions in the target irrigation and drainage area is calculated to obtain the ground flatness. By collecting soil samples, the soil pH value, organic matter content, salt content and other indicators are analyzed by existing soil monitoring instruments to obtain the soil quality. Use GPS or other positioning technology to determine the specific location of the target irrigation and drainage area. The irrigation and drainage source and irrigation and drainage accommodation information can be determined by the user in combination with the actual situation and uploaded, and the terrain, topography, area, ground flatness, soil quality, location, irrigation and drainage source, and irrigation and drainage accommodation information of the target irrigation and drainage area are used as the target irrigation and drainage area information.
[0034] Further constraint analysis is performed on each acquisition parameter in the target irrigation and drainage area information, that is, the adjustable performance of the terrain, topography, area, ground flatness, soil quality, location, irrigation and drainage sources, irrigation and drainage accommodation information, etc., that is, the information in the target irrigation and drainage area information is difficult to change, such as the terrain, drainage pipes, topography, etc. If you want to improve the irrigation and drainage effect by changing this information, the required human and material resources are huge. Specifically, historical data can be collected by retrieving each acquisition parameter of the target irrigation and drainage area, and then the stability of the changes of each acquisition parameter in history can be analyzed. For example, the standard deviation or variance of each acquisition parameter can be calculated as the constraint analysis result, and the parameter whose constraint analysis result reaches the preset threshold is used as the steady-state feature. The preset threshold is set by professional and technical personnel in this field based on actual experience.
[0035] Further utilizing the steady-state characteristics to cluster the parameters of the land in the target irrigation and drainage area is to extract the parameters of the steady-state characteristics of the land in the target irrigation and drainage area, and analyze the similarity of the parameters corresponding to different lands, such as the similarity of the land in different locations in terms of topography, topography, area, ground flatness, soil quality, location, irrigation and drainage source, and irrigation and drainage accommodation information. Only the parameters whose parameters corresponding to all the steady-state characteristics have a similarity greater than or equal to the predetermined similarity threshold are clustered into one category to obtain the land clustering result. The predetermined similarity threshold is set by the professional and technical personnel in this field, such as 80%, to classify different lands into one category. It should be noted that similarity analysis is a common technical means used by those skilled in the art. For example, similarity analysis can be performed by analyzing the parameter deviations of different lands. The land clustering results are segmented according to the preset cluster segmentation conditions, that is, the land corresponding to the parameters whose parameter similarities are greater than or equal to the predetermined similarity threshold is divided together, and the land segmentation result of the target irrigation and drainage area can be obtained.
[0036] Finally, the irrigation and drainage paths of the land segmentation results are connected based on the irrigation and drainage sources and the irrigation and drainage containment information. That is, the irrigation and drainage sources are taken as the starting point, and the land segmentation results are connected according to the irrigation and drainage pipes, irrigation and drainage equipment, irrigation time sequence, etc. in the irrigation and drainage containment information. The irrigation and drainage regional chain network composed of irrigation and drainage links corresponding to different land segmentation results is obtained, thereby realizing the segmentation of irrigation and drainage areas and the connection of irrigation and drainage links, providing a basis for subsequent irrigation and drainage control optimization.
[0037] Furthermore, step 4 of the present disclosure also includes:
[0038] Extract links from the irrigation and drainage area chain network with the irrigation and drainage source as the starting point to obtain the irrigation and drainage execution link; take the irrigation and drainage control nodes of the irrigation and drainage execution link as the timing points to construct a timing chain, and use the irrigation and drainage process influence relationship of each irrigation and drainage control node as the node reward to establish a Markov chain model based on the timing chain; obtain the optimization module of each irrigation and drainage control node, embed the optimization module according to the node mapping relationship, and construct the cumulative optimization model.
[0039] The irrigation and drainage area chain network is composed of irrigation and drainage links corresponding to different land segmentation results. The starting point of each link is the irrigation and drainage source. Water is irrigated to the land through irrigation and drainage equipment such as pipes, and the water in the land is discharged through drainage pipes. Therefore, by extracting links from the irrigation and drainage area chain network with the irrigation and drainage source as the starting point, an irrigation and drainage execution link can be obtained. The irrigation and drainage execution link is a link that is connected in the irrigation and drainage execution order for the segmented field areas based on different land segmentation results. Each field area is taken as an irrigation and drainage control node, and the irrigation and drainage control nodes of the irrigation and drainage execution link are sequentially connected as timing points, and the node connection result is used as the timing chain.
[0040] Each irrigation and drainage control node, that is, each field area, will have an impact on the adjacent area behind it, affecting the control parameters of the latter area. Specifically, the historical control data of each irrigation and drainage control node in the irrigation and drainage execution link can be retrieved, and the correlation analysis between adjacent field areas can be performed based on the existing correlation analysis method, such as the grey correlation analysis method, to obtain the corresponding correlation coefficient as the irrigation and drainage process influence relationship of each irrigation and drainage control node, and each irrigation and drainage control node in the timing chain can be used as the state node in the Markov chain model, and the irrigation and drainage process influence relationship of each irrigation and drainage control node can be used as the node reward to optimize the control of each state node. That is to say, the optimization module of each irrigation and drainage control node is obtained, and the optimization module is embedded in the Markov chain model according to the node mapping relationship between each irrigation and drainage control node and the optimization module, so as to obtain the cumulative optimization model. In this way, after the control parameters of each irrigation and drainage control node are optimized by the optimization module in the cumulative optimization model, the optimized control parameters are compensated and corrected according to the irrigation and drainage process influence relationship of each irrigation and drainage control node, that is, the optimized control parameters are adjusted accordingly according to the correlation coefficient in the irrigation and drainage process influence relationship of each irrigation and drainage control node, thereby improving the refinement of irrigation and drainage control.
[0041] Furthermore, step five of the present disclosure also includes:
[0042] The irrigation and drainage monitoring data set is node-aligned with the optimization link to determine the mapping relationship between the irrigation and drainage monitoring data set and the node; based on the mapping relationship, the irrigation and drainage monitoring data set is entered into the corresponding optimization module to perform node control parameter optimization; the node control data is obtained by iterative optimization through the optimization module of each node; the control target of the full-cycle node is optimized based on the cumulative optimization model, and the optimized control parameters that meet the full-cycle target requirements are determined and output.
[0043] Furthermore, the present disclosure also includes the following steps:
[0044] Obtain the time series information of water supply of irrigation and drainage sources, weather forecast information, and irrigation and drainage quotas; construct an optimization space using the time series information of water supply of irrigation and drainage sources as constraints, the weather forecast information as adjustment data, and the irrigation and drainage quotas as control optimization targets; based on the optimization space, use the cumulative optimization model to perform node and full-cycle optimization to obtain optimized control parameters that satisfy each node and the full cycle.
[0045] Furthermore, the present disclosure also includes the following steps:
[0046] According to the formula: M = m 1 + m 2 + E – P, calculate the irrigation and drainage quota, M is the flushing quota m 3 / hm 2、m 1 The amount of water required to increase the natural water content of the desalinated soil layer to the maximum water holding capacity of the field for the planned flushing is m 3 / hm 2 、m 2 The amount of water required to achieve the planned desalination layer desalination standard m 3 / hm 2 , E is the cumulative evaporation during flushing m 3 / hm 2 , P is the precipitation during the flushing period m 3 / hm 2 ;
[0047] Among them, m 1 = 666.7 Hγd(θ f -θ i ), H is the planned flushing desalination layer thickness m, γ d Dry density of the planned flushing desalination soil layer kg / m 3 ,θ f is the maximum field water holding capacity of the planned flushing desalination soil layer, θ i The natural water content of the desalination soil layer planned for flushing (%); , S 0 is the salt content of the planned desalination soil layer before flushing, S c is the desalination standard of the planned flushing desalination soil layer, K is the average salt removal coefficient that reaches the desalination standard, kg / m 3 Specifically, the irrigation and drainage monitoring data set is preprocessed as input and loaded into the cumulative optimization model to obtain an optimized control parameter chain for irrigation and drainage control, which includes:
[0048] The irrigation and drainage monitoring data set is node-aligned with the optimization link, wherein the optimization link generally refers to the irrigation and drainage execution link obtained after link extraction with the irrigation and drainage regional chain network, that is, the irrigation and drainage regional chain network includes multiple links, and the irrigation and drainage monitoring data set refers to the data set obtained by monitoring each irrigation and drainage control node in the optimization link, that is, the optimization link contains multiple irrigation and drainage control nodes. Therefore, it is necessary to map and associate the node data of each irrigation and drainage control node in the optimization link with the irrigation and drainage monitoring data set to prevent data confusion from causing the optimization process and the node from not matching, thereby obtaining the corresponding relationship between the node and the irrigation and drainage monitoring data set, which is used as the node mapping relationship. Based on the mapping relationship, the irrigation and drainage monitoring data set is entered into the optimization module corresponding to each irrigation and drainage control node to perform node control parameter optimization, that is, after the irrigation and drainage quality analysis of the irrigation and drainage monitoring data set in the optimization module, the node control parameters are adjusted iteratively for multiple times until the irrigation and drainage quality reaches the preset irrigation and drainage quality. The preset irrigation and drainage quality is set by professional and technical personnel in this field in combination with actual conditions, such as the preset irrigation and drainage quality based on the salinity requirements of the crops actually planted. The optimized node control parameters output by the optimization module are obtained as node control data.
[0049] Further, based on the cumulative optimization model, the control objectives of the full-cycle nodes are optimized, that is, after optimizing each irrigation and drainage control node respectively, the optimized control parameters that meet the full-cycle target requirements are determined and output. The specific method is: obtaining the water supply time series information, weather forecast information, and irrigation and drainage quota of the irrigation and drainage sources. The water supply time series information can be extracted based on the historical water supply of the irrigation and drainage sources; the weather forecast information can be obtained by connecting to the existing weather forecast platform, including weather information such as light and precipitation.
[0050] The method for obtaining the irrigation and drainage quota is as follows: According to the formula: M = m 1 + m 2 + E – P, calculate the irrigation and drainage quota, M is the flushing quota m 3 / hm 2 、m 1 The amount of water required to increase the natural water content of the desalinated soil layer to the maximum water holding capacity of the field for the planned flushing is m 3 / hm 2 、m 2 The amount of water required to achieve the planned desalination layer desalination standard m 3 / hm 2 , E is the cumulative evaporation during flushing m 3 / hm 2 , P is the precipitation during the flushing period m 3 / hm 2, This formula is a semi-empirical formula used in the existing saline-alkali land improvement and flushing quota.
[0051] Among them, m 1 It can be determined based on soil physical property test data, m 1 = 666.7 Hγd(θ f -θ i ), H is the planned flushing desalination layer thickness m, γ d Dry density of the planned flushing desalination soil layer kg / m 3 ,θ f is the maximum field water holding capacity of the planned flushing desalination soil layer, θ i The natural water content of the desalination soil layer planned for flushing (%); , S 0 The salt content of the planned desalination soil layer before flushing can be obtained based on existing technical tests, S c is the desalination standard of the planned flushing desalination soil layer, K is the average salt removal coefficient that reaches the desalination standard, kg / m 3, That is, the amount of salt discharged by a unit of flushing water. During the salt washing process, the soil salt content is always in a gradually decreasing state. Therefore, the total amount of water used for salt washing to meet the desalination standard is actually the cumulative value of the amount of water used for salt washing under different salt contents, which needs to be calculated using the integral method.
[0052] Furthermore, the water supply time series information of the irrigation and drainage source is used as a constraint condition, that is, when optimizing the control target of the full-cycle node based on the cumulative optimization model, it is necessary to ensure that the water supply corresponding to the obtained optimized control parameters is within the range of the water supply time series information, otherwise the optimized control parameters cannot achieve the corresponding optimization effect. At the same time, the weather forecast information is used as adjustment data and the irrigation and drainage quota is used as the control optimization target to construct an optimization space. That is to say, different weather will cause different evaporation of water from the land, and even increase the water supply during rainfall. Therefore, by retrieving the water supply impact records under different historical weather forecast information, the corresponding water supply impact degree is matched based on the weather forecast information as adjustment data, and the irrigation and drainage quota is used as the control optimization target to obtain the optimization space. It can be understood that in the process of using the cumulative optimization model to perform node and full-cycle optimization, it is necessary to ensure that the water supply corresponding to the optimized control parameters meets the water supply time series information, and at the same time, it is adjusted based on the degree of influence of the water supply corresponding to the weather forecast information. For example, rainy weather will increase the amount of water in the field. The optimized control parameters are adjusted according to the proportion of rainfall to the irrigation and drainage quota, so that the water supply corresponding to the optimized control parameters meets the irrigation and drainage quota. In this way, by using the cumulative optimization model to perform node and full-cycle optimization, that is, after optimizing each irrigation and drainage control node, it is necessary to analyze the corresponding water supply under each irrigation and drainage control node to meet the constraints and control optimization objectives, thereby obtaining the optimized control parameters that meet each node and the entire cycle, realizing the optimization of the nodes of the entire process of irrigation and drainage, and improving the refinement of irrigation and drainage optimization and the global optimization performance.
[0053] Furthermore, the present disclosure also includes the following steps:
[0054] Node decomposition is performed according to the optimization control parameter chain to generate optimization evaluation nodes, wherein the optimization evaluation nodes include node time and node weight; evaluation monitoring is performed based on the optimization evaluation nodes through monitoring equipment, and evaluation data of the evaluation nodes is determined based on the node weight and evaluation monitoring data; irrigation and drainage prediction is performed based on the optimization control parameter chain and the evaluation node evaluation data, and the irrigation and drainage control parameters are adjusted and reset using the predicted irrigation and drainage results.
[0055] Specifically, the nodes are decomposed according to the optimization control parameter chain according to each irrigation and drainage control node, and each irrigation and drainage control node is an optimization evaluation node. The optimization evaluation node includes node time and node weight. The node time is the irrigation and drainage execution time of the optimization evaluation node. The node weight can be set based on the importance of the optimization evaluation node to the irrigation and drainage process. The greater the importance, the greater the node weight. It can be set by professional and technical personnel in this field based on actual experience, or it can be set by analyzing the correlation between the optimization evaluation node and the irrigation and drainage quality through existing correlation analysis methods. The greater the correlation, the greater the weight. This is a common technical means used by professional and technical personnel in this field and will not be expanded here.
[0056] Further, based on the optimization evaluation node, the monitoring device is used for evaluation and monitoring. The monitoring device refers to the existing equipment for monitoring the node irrigation and drainage data of the optimization evaluation node, such as a water volume monitoring instrument, which monitors the irrigation and drainage volume of the optimization evaluation node. Then, the evaluation monitoring data is weightedly calculated based on the node weight, and the calculation result is used as the evaluation data of the evaluation node. Finally, the irrigation and drainage prediction is performed based on the optimization control parameter chain and the evaluation data of the evaluation node, that is, whether the final irrigation and drainage effect can meet the expectations. Specifically, the node optimization control parameters corresponding to the evaluation data of the evaluation node and the irrigation and drainage volume corresponding to the node optimization control parameters can be retrieved based on the optimization control parameter chain, and it is judged whether the deviation between the irrigation water volume corresponding to the node optimization control parameters and the evaluation data of the evaluation node is within the predetermined deviation threshold. The predetermined deviation threshold is the actual allowable irrigation and drainage volume deviation, which is set based on actual experience. If the deviation is within the predetermined deviation threshold, the predicted irrigation and drainage result is qualified, otherwise, it is unqualified, then the nodes behind the optimization evaluation node in the optimization control parameter chain are compensated according to the degree of deviation, so as to adjust and reset the irrigation and drainage control parameters and improve the accuracy of irrigation and drainage control.
[0057] In summary, the saline-alkali land irrigation and drainage control method based on cumulative optimization provided by the present disclosure has the following technical effects:
[0058] Collect the target irrigation and drainage area information, cluster the irrigation and drainage steady-state characteristics of the target irrigation and drainage area, and construct the irrigation and drainage area chain network; analyze the irrigation and drainage step parameters according to the target irrigation and drainage area information, determine the irrigation and drainage parameter sequence set, and perform dynamic feature analysis on each parameter in the irrigation and drainage parameter sequence set; determine the optimization parameters according to the dynamic feature analysis results, and collect sample data based on the optimization parameters to train the optimization module; extract links based on the irrigation and drainage area chain network, use the optimization module to embed links, and obtain the cumulative optimization model; collect irrigation and drainage monitoring data sets, pre-process the irrigation and drainage monitoring data sets as input, load them into the cumulative optimization model, and obtain the optimized control parameter chain for irrigation and drainage control. In this way, by clustering the irrigation and drainage steady-state characteristics of the target irrigation and drainage area, constructing the irrigation and drainage area chain network, and optimizing the irrigation and drainage control parameters based on the irrigation and drainage area chain network through the cumulative optimization model, the regional irrigation control based on the regional characteristics is realized, so as to improve the adaptability of the irrigation and drainage control to the actual area, and then improve the technical effect of the degree of refinement of the irrigation and drainage control.
[0059] Example 2
[0060] Based on the same inventive concept as the saline-alkali land irrigation and drainage control method based on cumulative optimization in the aforementioned embodiment, the present disclosure also provides a saline-alkali land irrigation and drainage control system based on cumulative optimization, please refer to the attached Figure 2 , the system comprising:
[0061] A steady-state feature clustering unit 11, which is used to collect target irrigation and drainage area information, cluster the target irrigation and drainage areas with steady-state features, and construct an irrigation and drainage area chain network;
[0062] A dynamic feature analysis unit 12, the dynamic feature analysis unit 12 is used to perform irrigation and drainage step parameter analysis according to the target irrigation and drainage area information, determine an irrigation and drainage parameter sequence set, and perform dynamic feature analysis on each parameter in the irrigation and drainage parameter sequence set;
[0063] The optimization training unit 13 is used to determine the optimization parameters according to the dynamic feature analysis results, and to collect sample data based on the optimization parameters to train the optimization module;
[0064] An optimization model acquisition unit 14, the optimization model acquisition unit 14 is used to extract links using the irrigation and drainage area chain network, embed links using the optimization module, and obtain a cumulative optimization model;
[0065] The irrigation and drainage control unit 15 is used to collect irrigation and drainage monitoring data sets, pre-process the irrigation and drainage monitoring data sets as input, load them into the cumulative optimization model, and obtain an optimized control parameter chain for irrigation and drainage control.
[0066] Furthermore, the system further comprises an adjustment and reset unit, wherein the adjustment and reset unit is used for:
[0067] Decomposing nodes according to the optimization control parameter chain to generate optimization evaluation nodes, wherein the optimization evaluation nodes include node time and node weight;
[0068] Based on the optimization evaluation node, evaluation monitoring is performed through a monitoring device, and based on the node weight and evaluation monitoring data, evaluation data of the evaluation node is determined;
[0069] Based on the optimization control parameter chain and the evaluation data of the evaluation node, irrigation and drainage prediction is performed, and the irrigation and drainage control parameters are adjusted and reset using the predicted irrigation and drainage results.
[0070] Furthermore, the steady-state feature clustering unit 11 in the system is also used for:
[0071] Based on the boundary information of the target irrigation and drainage area, the terrain, topography, area, ground flatness, soil quality, location, irrigation and drainage sources, and irrigation and drainage accommodation information of the target irrigation and drainage area are collected as the target irrigation and drainage area information;
[0072] Performing constraint analysis on each collected parameter in the target irrigation and drainage area information, and taking the parameter whose constraint analysis result reaches a preset threshold as a steady-state feature;
[0073] The steady-state characteristics are used to perform parameter clustering on the land in the target irrigation and drainage area, and the land clustering results are segmented according to the preset cluster segmentation conditions to obtain the land segmentation results of the target irrigation and drainage area;
[0074] Based on the irrigation and drainage sources and irrigation and drainage containment information, the irrigation and drainage paths of the land segmentation results are connected to construct the irrigation and drainage area chain network.
[0075] Furthermore, the optimization model acquisition unit 14 in the system is also used for:
[0076] Extracting links from the irrigation and drainage regional chain network with the irrigation and drainage source as the starting point to obtain irrigation and drainage execution links;
[0077] The irrigation and drainage control nodes of the irrigation and drainage execution link are taken as timing points to construct a timing chain, and the irrigation and drainage process influence relationship of each irrigation and drainage control node is taken as a node reward, and a Markov chain model is established based on the timing chain;
[0078] The optimization module of each irrigation and drainage control node is obtained, and the optimization module is embedded according to the node mapping relationship to construct the cumulative optimization model.
[0079] Furthermore, the irrigation and drainage control unit 15 in the system is also used for:
[0080] Perform node alignment on the irrigation and drainage monitoring data set and the optimization link, determine the mapping relationship between the irrigation and drainage monitoring data set and the node, and based on the mapping relationship, enter the irrigation and drainage monitoring data set into the corresponding optimization module to perform node control parameter optimization;
[0081] The node control data is obtained by iteratively searching for the optimal solution through the optimization module of each node;
[0082] Based on the cumulative optimization model, the control objectives of the full-cycle nodes are optimized, and the optimized control parameters that meet the full-cycle objective requirements are determined and output.
[0083] Furthermore, the irrigation and drainage control unit 15 in the system is also used for:
[0084] Obtain water supply time series information, weather forecast information, and irrigation and drainage quotas from irrigation and drainage sources;
[0085] Taking the water supply time series information of the irrigation and drainage source as the constraint condition, taking the weather forecast information as the adjustment data, and taking the irrigation and drainage quota as the control optimization target, an optimization space is constructed;
[0086] Based on the optimization space, the cumulative optimization model is used to perform node and full-cycle optimization to obtain optimized control parameters that meet the requirements of each node and the full cycle.
[0087] Furthermore, the irrigation and drainage control unit 15 in the system is also used for:
[0088] According to the formula: M = m 1 + m 2 + E – P, calculate the irrigation and drainage quota, M is the flushing quota m 3 / hm 2 、m 1 The amount of water required to increase the natural water content of the desalinated soil layer to the maximum water holding capacity of the field for the planned flushing is m 3 / hm 2 、m 2 The amount of water required to achieve the planned desalination layer desalination standard m 3 / hm 2 , E is the cumulative evaporation during flushing m 3 / hm 2 , P is the precipitation during the flushing period m 3 / hm 2 ;
[0089] Where, m1 = 666.7 Hγd (θf- θi), H is the thickness of the planned flushing desalination layer m, γd is the dry bulk density of the planned flushing desalination soil layer kg / m 3, θf is the maximum field water holding capacity of the planned flushing desalination soil layer %, θi is the natural water content of the planned flushing desalination soil layer %; , S0 is the salt content of the planned desalination soil layer before flushing, Sc is the desalination standard of the planned desalination soil layer, and K is the average salt removal coefficient that reaches the desalination standard kg / m 3 .
[0090] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. Figure 1 The saline-alkali land irrigation and drainage control method based on cumulative optimization and the specific examples in Example 1 are also applicable to the saline-alkali land irrigation and drainage control system based on cumulative optimization in this embodiment. Through the above detailed description of the saline-alkali land irrigation and drainage control method based on cumulative optimization, those skilled in the art can clearly know the saline-alkali land irrigation and drainage control system based on cumulative optimization in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.
[0091] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
[0092] Obviously, those skilled in the art can make various changes and modifications to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, if these modifications and variations of the present disclosure belong to the scope of the present disclosure and its equivalent technology, the present disclosure is also intended to include these modifications and variations.
Claims
1. Saline-alkali land irrigation and drainage control method based on cumulative optimization, It is characterized in that include: Collect information on target irrigation and drainage areas, cluster the irrigation and drainage steady-state characteristics of target irrigation and drainage areas, and build an irrigation and drainage area chain network; Perform irrigation and drainage step parameter analysis according to the target irrigation and drainage area information, determine an irrigation and drainage parameter sequence set, and perform dynamic feature analysis on each parameter in the irrigation and drainage parameter sequence set; According to the dynamic feature analysis results, the optimization parameters are determined, and sample data is collected based on the optimization parameters to train the optimization module; Extracting links using the irrigation and drainage area chain network, embedding links using the optimization module, and obtaining a cumulative optimization model; Collecting irrigation and drainage monitoring data sets, pre-processing the irrigation and drainage monitoring data sets as input, loading the data sets into the cumulative optimization model, and obtaining an optimized control parameter chain for irrigation and drainage control; The link extraction is performed using the irrigation and drainage area chain network, and the link embedding is performed using the optimization module to obtain a cumulative optimization model, including: Extracting links from the irrigation and drainage regional chain network with the irrigation and drainage source as the starting point to obtain irrigation and drainage execution links; Taking the irrigation and drainage control nodes of the irrigation and drainage execution link as timing points, constructing a timing chain, and taking the irrigation and drainage process influence relationship of each irrigation and drainage control node as a node reward, a Markov chain model is established based on the timing chain; The optimization module of each irrigation and drainage control node is obtained, and the optimization module is embedded according to the node mapping relationship to construct the cumulative optimization model.
2. The method according to claim 1, It is characterized in that Also includes: Decomposing nodes according to the optimization control parameter chain to generate optimization evaluation nodes, wherein the optimization evaluation nodes include node time and node weight; Based on the optimization evaluation node, evaluation monitoring is performed through a monitoring device, and based on the node weight and evaluation monitoring data, evaluation data of the evaluation node is determined; Based on the optimization control parameter chain and the evaluation data of the evaluation node, irrigation and drainage prediction is performed, and the irrigation and drainage control parameters are adjusted and reset using the predicted irrigation and drainage results.
3. The method according to claim 1, It is characterized in that The collecting of target irrigation and drainage area information, clustering of irrigation and drainage steady-state characteristics of the target irrigation and drainage area, and construction of an irrigation and drainage area chain network include: Based on the boundary information of the target irrigation and drainage area, the terrain, topography, area, ground flatness, soil quality, location, irrigation and drainage sources, and irrigation and drainage accommodation information of the target irrigation and drainage area are collected as the target irrigation and drainage area information; Performing constraint analysis on each collected parameter in the target irrigation and drainage area information, and taking the parameter whose constraint analysis result reaches a preset threshold as a steady-state feature; The steady-state characteristics are used to perform parameter clustering on the land in the target irrigation and drainage area, and the land clustering results are segmented according to the preset cluster segmentation conditions to obtain the land segmentation results of the target irrigation and drainage area; Based on the irrigation and drainage sources and irrigation and drainage containment information, the irrigation and drainage paths of the land segmentation results are connected to construct the irrigation and drainage area chain network.
4. The method according to claim 1, It is characterized in that The irrigation and drainage monitoring data set is preprocessed as input and loaded into the cumulative optimization model to obtain an optimized control parameter chain for irrigation and drainage control, including: Perform node alignment on the irrigation and drainage monitoring data set and the optimization link, determine the mapping relationship between the irrigation and drainage monitoring data set and the node, and based on the mapping relationship, enter the irrigation and drainage monitoring data set into the corresponding optimization module to perform node control parameter optimization; The node control data is obtained by iteratively searching for the optimal solution through the optimization module of each node; Based on the cumulative optimization model, the control objectives of the full-cycle nodes are optimized, and the optimized control parameters that meet the full-cycle objective requirements are determined and output.
5. The method according to claim 4, It is characterized in that The control target of the full-cycle node is optimized based on the cumulative optimization model, including: Obtain water supply time series information, weather forecast information, and irrigation and drainage quotas from irrigation and drainage sources; Taking the water supply time series information of the irrigation and drainage source as the constraint condition, taking the weather forecast information as the adjustment data, and taking the irrigation and drainage quota as the control optimization target, an optimization space is constructed; Based on the optimization space, the cumulative optimization model is used to perform node and full-cycle optimization to obtain optimized control parameters that meet the requirements of each node and the full cycle.
6. The method according to claim 5, It is characterized in that Obtain irrigation and drainage quotas, including: According to the formula: M = m1+ m2+ E – P, the irrigation and drainage quota is calculated, where M is the flushing quota m3 / hm2, m1 is the amount of water required to increase the natural water content of the planned flushing desalination soil layer to the maximum field water holding capacity m3 / hm2, m2 is the amount of water required to reach the desalination standard of the planned desalination layer m3 / hm2, E is the cumulative evaporation during the flushing period m3 / hm2, and P is the precipitation during the flushing period m3 / hm2; Among them, m1= 666.7 Hγd(θf- θi), H is the thickness of the planned flushing desalination layer m, γd is the dry bulk density of the planned flushing desalination soil layer kg / m3, θf is the maximum field water holding capacity of the planned flushing desalination soil layer %, θi is the natural water content of the planned flushing desalination soil layer %; , S0 is the salt content of the planned desalination soil layer before flushing, Sc is the desalination standard of the planned desalination soil layer, and K is the average salt discharge coefficient kg / m3 that meets the desalination standard.
7. Saline-alkali land irrigation and drainage control system based on cumulative optimization, It is characterized in that For implementing the steps of the method according to any one of claims 1 to 6, the system comprises: A steady-state feature clustering unit, which is used to collect target irrigation and drainage area information, cluster the target irrigation and drainage areas with steady-state features, and construct an irrigation and drainage area chain network; A dynamic feature analysis unit, the dynamic feature analysis unit is used to perform irrigation and drainage step parameter analysis according to the target irrigation and drainage area information, determine an irrigation and drainage parameter sequence set, and perform dynamic feature analysis on each parameter in the irrigation and drainage parameter sequence set; An optimization training unit, which is used to determine optimization parameters according to the dynamic feature analysis results, and to collect sample data and train the optimization module based on the optimization parameters; An optimization model acquisition unit, the optimization model acquisition unit is used to extract links using the irrigation and drainage area chain network, embed links using the optimization module, and obtain a cumulative optimization model; The irrigation and drainage control unit is used to collect irrigation and drainage monitoring data sets, pre-process the irrigation and drainage monitoring data sets as input, load them into the cumulative optimization model, and obtain an optimized control parameter chain for irrigation and drainage control.
Citation Information
Patent Citations
Automatic farmland irrigation system
CN103210817A
Intelligent water-saving irrigation method and intelligent water-saving irrigation system
CN105794605A
Irrigation decision method, device, computer device and storage medium
CN110999766A
Water-saving irrigation system and accurate irrigation method
CN112602563A
Soil remediation humidity adjusting system and method
CN114342786A
