System for constructing highland stereoclimate irrigation district information database

Abstract

The application discloses a highland stereoscopic climate irrigated area information big database construction system and relates to the technical field of irrigation data management.The highland irrigated area environment data and historical environment data are collected in real time through the construction of a sensor network mode, and the collected highland irrigated area environment data and historical environment data are processed through a data processing mode; after the processing, the processed historical environment data are analyzed and trained through a data analysis mode, and a plurality of irrigation decision target models are constructed; meanwhile, the processed historical environment data and the trained historical environment data are summarized, and the plurality of irrigation decision target models are optimized through a model optimization algorithm; finally, the control point coordinates, the historical environment data and the optimized plurality of irrigation decision target models are summarized to construct an information big database, and the highland irrigated area is controlled based on the information big database, thereby improving the accuracy of the irrigated area irrigation control.

Description

Technical Field

[0001] This invention relates to the field of irrigation data management technology, specifically to a system for constructing a large database of information on irrigation districts with plateau three-dimensional climate. Background Technology

[0002] Currently, the overall level of digitalization in irrigation districts is not high. The construction of data, algorithms, and computing power for intelligent irrigation decision-making is basically in its initial stage. Therefore, there is an urgent need for a large information database to enhance the data, algorithms, and computing power for intelligent irrigation decision-making.

[0003] The prior art, such as the invention patent application with publication number CN116245375A, discloses a water resource irrigation area management method and system based on the Internet of Things. The method includes: a map monitoring system, an intelligent irrigation management system, a data analysis module, and an information query system. The map monitoring system is used to monitor the various channels, gate chambers, and gates in the irrigation area online. The intelligent irrigation management system is used to control various irrigation valves and realize on-site control of the entire irrigation process by setting irrigation parameters and irrigation strategies. The data analysis module is used to perform statistical analysis on the actual situation and historical data of the entire irrigation area.

[0004] As can be seen from the above solutions, the current intelligent irrigation management system mainly relies on IoT valve control, lacking intelligent irrigation regulation and overall analysis, and thus has certain limitations. Summary of the Invention

[0005] The purpose of this invention is to provide a system for constructing a large database of information on irrigation areas with plateau three-dimensional climate, which solves the problems existing in the background technology.

[0006] To solve the above-mentioned technical problems, the present invention adopts the following technical solution: The present invention provides a system for constructing a large database of information on irrigation areas with plateau three-dimensional climate, specifically including the following steps:

[0007] S1. Set up q control points in the plateau irrigation area and install data monitoring sensors and control gateways at each control point. At the same time, construct a sensor network based on the installed data monitoring sensors and control gateways.

[0008] S2. Based on the constructed sensor network, real-time environmental data and historical environmental data of the plateau irrigation area are collected. At the same time, the real-time collected environmental data and historical environmental data of the plateau irrigation area are processed through data processing methods to obtain processed real-time environmental data and historical environmental data.

[0009] The collected environmental data of the plateau irrigation area includes: temperature, humidity, rainfall data and crop image data; S21, the real-time collected historical environmental data is processed by data processing methods to obtain processed historical environmental data;

[0010] S22. The real-time collected environmental data of the plateau irrigation area is processed by data processing methods to obtain processed real-time environmental data.

[0011] S3. Train and analyze the processed historical environmental data through data analysis to obtain trained and analyzed historical environmental data.

[0012] S4. Construct multiple irrigation decision target models based on historical environmental data after training and analysis;

[0013] S5. Summarize the processed historical environmental data and the trained and analyzed historical environmental data. Based on the summarized data, optimize the constructed multiple sets of irrigation decision target models through model optimization algorithms to obtain optimized multiple sets of irrigation decision target models.

[0014] S6. Summarize the coordinates of control points, historical environmental data, and optimized multiple sets of irrigation decision target models to construct a large information database. At the same time, irrigation control in the plateau irrigation area is carried out based on the constructed large information database.

[0015] Preferably, the step of setting up q control points in the plateau irrigation area and installing data monitoring sensors and control gateways at each control point, and constructing a sensor network based on the installed data monitoring sensors and control gateways, includes the following steps:

[0016] S11. Based on setting up q control points in the plateau irrigation area, each control point is directly connected to the control gateway;

[0017] Number the q control points and control gateways. Set number To control the gateway, Number the q control points;

[0018] S12, Configure the control gateway The coordinates are taken as the origin, according to Establish a three-dimensional control coordinate system based on control points. Update and determine the coordinates of all other control points;

[0019] S13. Save the coordinates of each control point and build a sensor network based on the connection status of the monitoring sensors and the control gateway.

[0020] Preferably, the process of processing the real-time collected historical environmental data to obtain processed historical environmental data includes the following steps:

[0021] S211. Filter the temperature, humidity and rainfall data in the real-time collected historical environmental data to obtain filtered historical environmental data.

[0022] Establish a standard set of environmental data, including: temperature, humidity, and rainfall data;

[0023] The collected historical environmental data is traversed to locate historical environmental data with missing content.

[0024] After locating the environmental data with missing content, the historical environmental data with missing content is deleted:

[0025] The processed historical environment data is obtained by summarizing the historical environment data after the deletion process is completed.

[0026] S212. Extract features from crop image data in real-time collected historical environmental data.

[0027] Preferably, the extraction of features from crop image data in real-time collected historical environmental data includes the following steps:

[0028] The crop image data in the historical environmental data collected in real time is divided into m image data blocks of the same size.

[0029] The m image data blocks after division are used for feature extraction by independent component analysis.

[0030] The formula for independent component analysis is shown below:

[0031] ;

[0032] in, Represents the independent components of the i-th image data block. Represents the i-th image data block point The observed images, Represents the midpoint of crop image data in historical environmental data. Characteristic components;

[0033] The features of crop image data in historical environmental data are obtained by summarizing the feature components of all points in the crop image data in historical environmental data.

[0034] The features of the aggregated crop image data are classified using data classification methods to obtain the features of the classified crop image data.

[0035] Preferably, the process of processing the real-time collected environmental data of the plateau irrigation area to obtain processed real-time environmental data includes the following steps:

[0036] S221. Standardize the temperature, humidity, and rainfall data in the real-time collected environmental data of the plateau irrigation area through data standardization.

[0037] The data standardization formula is as follows:

[0038] ;

[0039] in, This represents environmental data of the plateau irrigation area before standardization. This represents standardized environmental data for the plateau irrigation area. This represents the maximum value in the environmental data of the plateau irrigation area. This represents the minimum value in the environmental data of the plateau irrigation area;

[0040] S222. The crop image data in the real-time collected plateau irrigation area environmental data are extracted using the independent component analysis method. The extracted features are then compared with the features of various crop image data in the historical environmental data to determine the crop type.

[0041] The formula for feature comparison calculation is as follows:

[0042] ;

[0043] in, This indicates a comparison calculation function. This represents the characteristics of various crop image data in historical environmental data. This represents the characteristics of crop image data in real-time collected environmental data of plateau irrigation areas;

[0044] Set a similarity threshold. If the calculation result is greater than or equal to the set threshold, the two sets of crop images are determined to belong to the same type.

[0045] If the calculation result is less than the set threshold, it is determined that the two sets of crop images do not belong to the same type.

[0046] Preferably, the step of training and analyzing the processed historical environmental data through data analysis to obtain the trained and analyzed historical environmental data includes the following steps:

[0047] Summarize rainfall data from historical environmental data and record changes in temperature and humidity before and after rainfall;

[0048] The changes in temperature and humidity before and after rainfall are quantified by averaging the data.

[0049] The quantification formula is shown below:

[0050] ;

[0051] in, This indicates the changes in temperature and humidity before and after rainfall. This represents the temperature and humidity data after the j-th rainfall. The data shows the temperature and humidity before the j-th rainfall, where n represents the number of rainfalls.

[0052] Simultaneously predict the probability of rainfall;

[0053] The rainfall probability model is shown below:

[0054] ;

[0055] in, Let e ​​represent the probability of rainfall, and e represent the natural logarithm. This represents the average of historical rainfall data. The standard deviation of historical rainfall data This indicates the amount of rainfall.

[0056] Preferably, the construction of multiple irrigation decision target models based on historical environmental data after training and analysis includes the following steps:

[0057] The formulas for decision variables are shown below:

[0058] ;

[0059] in, This indicates whether the area corresponding to the k-th monitoring sensor requires irrigation control. =1 indicates that the area corresponding to the k-th monitoring sensor needs irrigation. =0 indicates that the area corresponding to the kth monitoring sensor does not need irrigation;

[0060] Multiple irrigation decision-making objective models were constructed based on historical environmental data after training and analysis.

[0061] The optimal decision-making model for the growth environment is shown below:

[0062] ;

[0063] ;

[0064] in, This represents a decision-making model for optimizing the growth environment. This represents a high-standard model of the current crop growing environment. This represents the maximum value within the current standard range for crop growth environment. These represent temperature and humidity, respectively.

[0065] The production cost minimization decision model is shown below:

[0066] ;

[0067] ;

[0068] in, This represents a decision-making model for optimizing the growth environment. This represents a low-standard model of the current crop growing environment. This represents the minimum value within the current standard range for crop growth environment.

[0069] Preferably, the process of aggregating and processing historical environmental data and training and analyzing historical environmental data, and then optimizing the constructed multiple sets of irrigation decision target models based on the aggregated data using a model optimization algorithm to obtain the optimized multiple sets of irrigation decision target models, includes the following steps:

[0070] S51. Chromosome encoding is performed on the processed historical environment data and the historical environment data after training analysis.

[0071] S52. Perform population initialization;

[0072] Each chromosome group is defined to represent a set of processed historical environmental data and a set of trained and analyzed historical environmental data. The population size and the maximum number of iterations are also defined. ;

[0073] S53. Establish a fitness function based on the constructed multi-set irrigation decision objective model;

[0074] The fitness function is set as follows:

[0075] ;

[0076] in, This represents the fitness of the irrigation decision target model corresponding to the historical environmental data of group Q in the initial population after treatment and the historical environmental data after training and analysis.

[0077] S54. Select genetic operators based on the established fitness function;

[0078] S55. Perform chromosome crossover on the selected genetic operators;

[0079] Randomly select crossover points from the chosen genetic operators, and perform pairwise crossovers in a sequential manner to generate a new pair of chromosome codes;

[0080] The newly generated chromosome codes will be used as a new population to participate in the iteration;

[0081] S56. Iterate through steps S52-S55 until the maximum number of iterations is reached. The optimized irrigation decision target models are output.

[0082] Preferably, the process of constructing a large information database using the aggregated control point coordinates, historical environmental data, and optimized multiple sets of irrigation decision target models, and then controlling irrigation in the plateau irrigation area based on this database, includes the following steps:

[0083] The collected historical environmental data, control point coordinates, and optimized multiple irrigation decision target models will be used as the basis for constructing a large information database.

[0084] Simultaneously, the processed real-time environmental data is input into a large information database, and the processed real-time environmental data is matched and analyzed through the large information database to obtain corresponding irrigation control decisions. Based on the obtained irrigation control decisions and the coordinates of each control point in the large information database, irrigation control is carried out on each control point.

[0085] This invention also discloses a system for constructing a large database of information on irrigation areas with plateau three-dimensional climate. The system includes: a data acquisition module, a data processing module, a data analysis module, a decision construction module, a decision optimization module, and an irrigation control module.

[0086] The data acquisition module is used to collect environmental data in the plateau irrigation area in real time.

[0087] The data processing module is used to process the real-time collected environmental data of the plateau irrigation area to obtain processed environmental data.

[0088] The data analysis module is used to analyze the processed environmental data to obtain the analyzed environmental data.

[0089] The decision-making construction module is used to construct multiple sets of irrigation decision target models based on the analyzed environmental data.

[0090] The decision optimization module is used to optimize the constructed multiple sets of irrigation decision target models;

[0091] The irrigation control module is used to control irrigation based on multiple optimized irrigation decision target models.

[0092] The beneficial effects of this invention are as follows:

[0093] (1) This invention collects real-time environmental data and historical environmental data of the plateau irrigation area by constructing a sensor network. At the same time, it processes the real-time collected environmental data and historical environmental data of the plateau irrigation area through data processing. After processing, it trains and analyzes the processed historical environmental data and constructs multiple sets of irrigation decision target models through data analysis. At the same time, it summarizes the processed historical environmental data and the trained and analyzed historical environmental data and optimizes the constructed multiple sets of irrigation decision target models through model optimization algorithms. Finally, it summarizes the control point coordinates, historical environmental data and the optimized multiple sets of irrigation decision target models to construct a large information database. At the same time, it conducts irrigation control of the plateau irrigation area based on the constructed large information database, which improves the accuracy of irrigation control in the irrigation area.

[0094] (2) This invention improves the rationality of processing historical and real-time environmental data by processing and analyzing the collected historical and real-time environmental data separately, and by using data filtering, data feature extraction and identification, and data standardization methods.

[0095] (3) This invention summarizes rainfall data from historical environmental data and records the changes in temperature and humidity before and after rainfall. At the same time, it provides a standard for irrigation control through rainfall probability prediction, thus ensuring the accuracy of irrigation control.

[0096] (4) This invention constructs multiple irrigation decision target models based on historical environmental data after training and analysis, and provides a variety of irrigation control decisions by constructing multiple irrigation decision target models, thereby optimizing irrigation control targets.

[0097] (5) This invention provides sample templates and control standards for irrigation control by summarizing and constructing a large information database, thereby improving the efficiency of irrigation control. Attached Figure Description

[0098] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0099] Figure 1 This is a schematic diagram of the process for constructing a large database of information on plateau three-dimensional climate irrigation areas according to the present invention. Detailed Implementation

[0100] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0101] In a specific embodiment of the present invention,

[0102] Reference Figure 1 As shown, this invention provides a system for constructing a large database of information on irrigation areas with a plateau three-dimensional climate, including the following steps:

[0103] S1. Set up q control points in the plateau irrigation area and install data monitoring sensors and control gateways at each control point. At the same time, construct a sensor network based on the installed data monitoring sensors and control gateways.

[0104] S2. Based on the constructed sensor network, real-time environmental data and historical environmental data of the plateau irrigation area are collected. At the same time, the real-time collected environmental data and historical environmental data of the plateau irrigation area are processed through data processing methods to obtain processed real-time environmental data and historical environmental data.

[0105] The collected environmental data of the plateau irrigation area includes: temperature, humidity, rainfall data and crop image data; S21, the real-time collected historical environmental data is processed by data processing methods to obtain processed historical environmental data;

[0106] S22. The real-time collected environmental data of the plateau irrigation area is processed by data processing methods to obtain processed real-time environmental data.

[0107] S3. Train and analyze the processed historical environmental data through data analysis to obtain trained and analyzed historical environmental data.

[0108] S4. Construct multiple irrigation decision target models based on historical environmental data after training and analysis;

[0109] S5. Summarize the processed historical environmental data and the trained and analyzed historical environmental data. Based on the summarized data, optimize the constructed multiple sets of irrigation decision target models through model optimization algorithms to obtain optimized multiple sets of irrigation decision target models.

[0110] S6. Summarize the coordinates of control points, historical environmental data, and optimized multiple sets of irrigation decision target models to build a large information database. At the same time, irrigation control is carried out in the plateau irrigation area based on the constructed information database.

[0111] Furthermore, referring to Figure 1As shown, q control points are set up in the plateau irrigation area, and data monitoring sensors and control gateways are installed at each control point. The sensor network is constructed based on the installed data monitoring sensors and control gateways, including the following steps:

[0112] S11. Based on setting up q control points in the plateau irrigation area, each control point is directly connected to the control gateway;

[0113] Furthermore, the q control points and control gateways are numbered. Set number To control the gateway, Number the q control points;

[0114] S12, Configure the control gateway The coordinates are taken as the origin, according to Establish a three-dimensional control coordinate system based on control points. Update and determine the coordinates of all other control points;

[0115] S13. Save the coordinates of each control point and build a sensor network based on the connection status of the monitoring sensors and the control gateway.

[0116] Furthermore, referring to Figure 1 As shown, the real-time collected historical environmental data is processed using data processing methods to obtain the processed historical environmental data, including the following steps:

[0117] S211. Filter the temperature, humidity and rainfall data in the real-time collected historical environmental data to obtain filtered historical environmental data.

[0118] Establish a standard set of environmental data, including: temperature, humidity, and rainfall data;

[0119] The collected historical environmental data is traversed to locate historical environmental data with missing content.

[0120] After locating the environmental data with missing content, the historical environmental data with missing content is deleted:

[0121] The processed historical environment data is obtained by summarizing the historical environment data after the deletion process is completed.

[0122] S212. Extract features from crop image data in real-time collected historical environmental data;

[0123] The crop image data in the historical environmental data collected in real time is divided into m image data blocks of the same size.

[0124] Furthermore, the m image data blocks after division are used for feature extraction using independent component analysis.

[0125] The formula for independent component analysis is shown below:

[0126] ;

[0127] in, Represents the independent components of the i-th image data block. Represents the i-th image data block point The observed images, Represents the midpoint of crop image data in historical environmental data. Characteristic components;

[0128] The features of crop image data in historical environmental data are obtained by summarizing the feature components of all points in the crop image data in historical environmental data.

[0129] Furthermore, the features of the aggregated crop image data are classified using data classification methods to obtain the features of the classified crop image data;

[0130] Furthermore, referring to Figure 1 As shown, the real-time environmental data collected in the plateau irrigation area is processed using data processing methods to obtain the processed real-time environmental data, including the following steps:

[0131] S221. Standardize the temperature, humidity, and rainfall data in the real-time collected environmental data of the plateau irrigation area through data standardization.

[0132] The data standardization formula is as follows:

[0133] ;

[0134] in, This represents environmental data of the plateau irrigation area before standardization. This represents standardized environmental data for the plateau irrigation area. This represents the maximum value in the environmental data of the plateau irrigation area. This represents the minimum value in the environmental data of the plateau irrigation area;

[0135] S222. The crop image data in the real-time collected plateau irrigation area environmental data are extracted using the independent component analysis method. The extracted features are then compared with the features of various crop image data in the historical environmental data to determine the crop type.

[0136] The formula for feature comparison calculation is as follows:

[0137] ;

[0138] in, This indicates a comparison calculation function. This represents the characteristics of various crop image data in historical environmental data. This represents the characteristics of crop image data in real-time collected environmental data of plateau irrigation areas;

[0139] Set a similarity threshold. If the calculation result is greater than or equal to the set threshold, the two sets of crop images are determined to belong to the same type.

[0140] If the calculation result is less than the set threshold, it is determined that the two sets of crop images do not belong to the same type.

[0141] Furthermore, referring to Figure 1 As shown, the process of training and analyzing the processed historical environmental data to obtain the trained and analyzed historical environmental data includes the following steps;

[0142] Summarize rainfall data from historical environmental data and record changes in temperature and humidity before and after rainfall;

[0143] Furthermore, the changes in temperature and humidity before and after rainfall are quantified by averaging the data;

[0144] The quantification formula is shown below:

[0145] ;

[0146] in, This indicates the changes in temperature and humidity before and after rainfall. This represents the temperature and humidity data after the j-th rainfall. The data shows the temperature and humidity before the j-th rainfall, where n represents the number of rainfalls.

[0147] Simultaneously predict the probability of rainfall;

[0148] The rainfall probability model is shown below:

[0149] ;

[0150] in, Let e ​​represent the probability of rainfall, and e represent the natural logarithm. This represents the average of historical rainfall data. The standard deviation of historical rainfall data Indicates rainfall amount;

[0151] Furthermore, referring to Figure 1 As shown, constructing multiple irrigation decision target models based on historical environmental data after training and analysis includes the following steps:

[0152] The formulas for decision variables are shown below:

[0153] ;

[0154] in, This indicates whether the area corresponding to the k-th monitoring sensor requires irrigation control. =1 indicates that the area corresponding to the k-th monitoring sensor needs irrigation. =0 indicates that the area corresponding to the kth monitoring sensor does not need irrigation;

[0155] Multiple irrigation decision-making objective models were constructed based on historical environmental data after training and analysis.

[0156] The optimal decision-making model for the growth environment is shown below:

[0157] ;

[0158] ;

[0159] in, This represents a decision-making model for optimizing the growth environment. This represents a high-standard model of the current crop growing environment. This represents the maximum value within the current standard range for crop growth environment. These represent temperature and humidity, respectively.

[0160] The production cost minimization decision model is shown below:

[0161] ;

[0162] ;

[0163] in, This represents a decision-making model for optimizing the growth environment. This represents a low-standard model of the current crop growing environment. This represents the minimum value within the current standard range for crop growth environment.

[0164] Furthermore, referring to Figure 1 As shown, the historical environmental data after aggregation and processing, and the historical environmental data after training and analysis are aggregated. Based on the aggregated data, the multiple sets of irrigation decision target models are optimized using a model optimization algorithm to obtain the optimized multiple sets of irrigation decision target models. The process includes the following steps:

[0165] S51. Chromosome encoding is performed on the processed historical environment data and the historical environment data after training analysis.

[0166] S52. Perform population initialization;

[0167] Each chromosome group is defined to represent a set of processed historical environmental data and a set of trained and analyzed historical environmental data. The population size and the maximum number of iterations are also defined. ;

[0168] S53. Establish a fitness function based on the constructed multi-set irrigation decision objective model;

[0169] The fitness function is set as follows:

[0170] ;

[0171] in, This represents the fitness of the irrigation decision target model corresponding to the historical environmental data of group Q in the initial population after treatment and the historical environmental data after training and analysis.

[0172] S54. Select genetic operators based on the established fitness function;

[0173] The genetic operators are randomly selected by using a roulette wheel method. The probability of selecting the irrigation decision target model corresponding to each group of processed historical environmental data and trained and analyzed historical environmental data is proportional to the fitness. The irrigation decision target model corresponding to the group of processed historical environmental data and trained and analyzed historical environmental data with high fitness is selected.

[0174] The probability formula for the selection of a genetic operator is shown below:

[0175] ,

[0176] in, Indicates population size, This represents the probability that the irrigation decision target model is selected based on the historical environmental data of the Qth group in the initial population after processing and the historical environmental data after training and analysis.

[0177] S55. Perform chromosome crossover on the selected genetic operators;

[0178] Randomly select crossover points from the chosen genetic operators, and perform pairwise crossovers in a sequential manner to generate a new pair of chromosome codes;

[0179] The newly generated chromosome codes will be used as a new population to participate in the iteration;

[0180] S56. Iterate through steps S52-S55 until the maximum number of iterations is reached. Output optimized sets of irrigation decision target models;

[0181] Furthermore, referring to Figure 1 As shown, a large information database is constructed by summarizing control point coordinates, historical environmental data, and optimized multiple sets of irrigation decision target models. Based on this database, irrigation control in the plateau irrigation area includes the following steps:

[0182] The collected historical environmental data, control point coordinates, and optimized multiple irrigation decision target models will be used as the basis for constructing a large information database.

[0183] Simultaneously, the processed real-time environmental data is input into the constructed information big data database, and the processed real-time environmental data is matched and analyzed through the information big data database to obtain the corresponding irrigation control decisions. Based on the obtained irrigation control decisions and the coordinates of each control point in the information big data database, irrigation control is carried out on each control point.

[0184] In one specific embodiment, the system for constructing a large database of information on irrigation areas based on plateau three-dimensional climate includes: a data acquisition module, a data processing module, a data analysis module, a decision-making construction module, a decision optimization module, and an irrigation control module;

[0185] The data acquisition module is used to collect environmental data in the plateau irrigation area in real time.

[0186] The data processing module is used to process the real-time collected environmental data of the plateau irrigation area to obtain processed environmental data.

[0187] The data analysis module is used to analyze the processed environmental data to obtain the analyzed environmental data.

[0188] The decision-making construction module is used to construct multiple sets of irrigation decision target models based on the analyzed environmental data.

[0189] The decision optimization module is used to optimize the constructed multiple sets of irrigation decision target models;

[0190] The irrigation control module is used to control irrigation based on multiple optimized irrigation decision target models.

[0191] It should be noted that,

[0192] The above content is merely an example and illustration of the concept of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described, or use similar methods to replace them, as long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, and all such modifications and additions should fall within the protection scope of the present invention.

Claims

1. A system for constructing a large database of information on irrigation areas with a three-dimensional climate in plateau regions, characterized in that: Includes the following steps: S1. Set up q control points in the plateau irrigation area and install data monitoring sensors and control gateways at each control point. At the same time, construct a sensor network based on the installed data monitoring sensors and control gateways. S2. Based on the constructed sensor network, real-time environmental data and historical environmental data of the plateau irrigation area are collected. At the same time, the real-time collected environmental data and historical environmental data of the plateau irrigation area are processed through data processing methods to obtain processed real-time environmental data and historical environmental data. The collected environmental data for the plateau irrigation area includes: temperature, humidity, rainfall data, and crop image data; S21. The historical environmental data collected in real time is processed by data processing methods to obtain the processed historical environmental data; S22. The real-time collected environmental data of the plateau irrigation area is processed by data processing methods to obtain processed real-time environmental data. S3. Train and analyze the processed historical environmental data through data analysis to obtain trained and analyzed historical environmental data. Summarize rainfall data from historical environmental data and record changes in temperature and humidity before and after rainfall; The changes in temperature and humidity before and after rainfall are quantified by averaging the data. The quantification formula is shown below: ； in, This indicates the changes in temperature and humidity before and after rainfall. This represents the temperature and humidity data after the j-th rainfall. The data shows the temperature and humidity before the j-th rainfall, where n represents the number of rainfalls. Simultaneously predict the probability of rainfall; The rainfall probability model is shown below: ； in, Let e ​​represent the probability of rainfall, and e represent the natural logarithm. This represents the average of historical rainfall data. The standard deviation of historical rainfall data Indicates rainfall amount; S4. Construct multiple irrigation decision target models based on historical environmental data after training and analysis; The formulas for decision variables are shown below: ； in, This indicates whether the area corresponding to the k-th monitoring sensor requires irrigation control. =1 indicates that the area corresponding to the k-th monitoring sensor needs irrigation. =0 indicates that the area corresponding to the kth monitoring sensor does not need irrigation; Multiple irrigation decision-making objective models were constructed based on historical environmental data after training and analysis. The optimal decision-making model for the growth environment is shown below: ； ； in, This represents a decision-making model for optimizing the growth environment. This represents a high-standard model of the current crop growing environment. This represents the maximum value within the current standard range for crop growth environment. These represent temperature and humidity, respectively. The production cost minimization decision model is shown below: ； ； in, This represents a decision-making model for optimizing the growth environment. This represents a low-standard model of the current crop growth environment. This represents the minimum value within the current standard range for crop growth environment. S5. Summarize the processed historical environmental data and the trained and analyzed historical environmental data. Based on the summarized data, optimize the constructed multiple irrigation decision target models through model optimization algorithms to obtain the optimized multiple irrigation decision target models. S6. Summarize the coordinates of control points, historical environmental data, and optimized multiple sets of irrigation decision target models to construct a large information database. At the same time, irrigation control in the plateau irrigation area is carried out based on the constructed large information database.

2. The system for constructing a large database of information on irrigation areas based on a plateau three-dimensional climate, as described in claim 1, is characterized in that... The process of setting up q control points in the plateau irrigation area and installing data monitoring sensors and control gateways at each control point, and constructing a sensor network based on the installed data monitoring sensors and control gateways, includes the following steps: S11. Based on setting up q control points in the plateau irrigation area, each control point is directly connected to the control gateway; Number the q control points and control gateways. Set number To control the gateway, Number the q control points; S12, Configure the control gateway The coordinates are taken as the origin, according to Establish a three-dimensional control coordinate system based on control points. Update and determine the coordinates of all other control points; S13. Save the coordinates of each control point and build a sensor network based on the connection status of the monitoring sensors and the control gateway.

3. The system for constructing a large database of information on irrigation areas based on plateau three-dimensional climate, as described in claim 1, is characterized in that... The process of processing the real-time collected historical environmental data to obtain the processed historical environmental data includes the following steps: S211. Filter the temperature, humidity and rainfall data in the real-time collected historical environmental data to obtain filtered historical environmental data. Establish a standard set of environmental data, including: temperature, humidity, and rainfall data; The collected historical environmental data is traversed to locate historical environmental data with missing content. After locating the environmental data with missing content, the historical environmental data with missing content is deleted: The processed historical environment data is obtained by summarizing the historical environment data after the deletion process is completed. S212. Extract features from crop image data in real-time collected historical environmental data.

4. The system for constructing a large database of information on irrigation areas based on plateau three-dimensional climate, as described in claim 3, is characterized in that... The process of extracting features from crop image data in real-time collected historical environmental data includes the following steps: The crop image data in the historical environmental data collected in real time is divided into m image data blocks of the same size. The m image data blocks after division are used for feature extraction by independent component analysis. The formula for independent component analysis is shown below: ； in, Represents the independent components of the i-th image data block. Represents the i-th image data block point The observed images, Represents the midpoint of crop image data in historical environmental data. Characteristic components; The features of crop image data in historical environmental data are obtained by summarizing the feature components of all points in the crop image data in historical environmental data. The features of the aggregated crop image data are classified using data classification methods to obtain the features of the classified crop image data.

5. The system for constructing a large database of information on irrigation areas based on plateau three-dimensional climate, as described in claim 1, is characterized in that... The process of processing the real-time collected environmental data of the plateau irrigation area to obtain the processed real-time environmental data includes the following steps: S221. Standardize the temperature, humidity, and rainfall data in the real-time collected environmental data of the plateau irrigation area through data standardization. The data standardization formula is as follows: ； in, This represents environmental data of the plateau irrigation area before standardization. This represents standardized environmental data for the plateau irrigation area. This represents the maximum value in the environmental data of the plateau irrigation area. This represents the minimum value in the environmental data of the plateau irrigation area; S222. The crop image data in the real-time collected plateau irrigation area environmental data is extracted by independent component analysis. The extracted features are compared with the features of various crop image data in historical environmental data to determine the crop type. The formula for feature comparison calculation is as follows: ； in, This indicates a comparison calculation function. This represents the characteristics of various crop image data in historical environmental data. This represents the characteristics of crop image data in real-time collected environmental data of plateau irrigation areas; Set a similarity threshold. If the calculation result is greater than or equal to the set threshold, the two sets of crop images are determined to belong to the same type. If the calculation result is less than the set threshold, it is determined that the two sets of crop images do not belong to the same type.

6. The system for constructing a large database of information on irrigation areas based on plateau three-dimensional climate, as described in claim 1, is characterized in that... The aggregated historical environmental data and the trained historical environmental data are used to optimize the constructed multiple sets of irrigation decision target models based on the aggregated data using a model optimization algorithm. The optimized multiple sets of irrigation decision target models include the following steps: S51. Chromosome encoding is performed on the processed historical environment data and the historical environment data after training analysis. S52. Perform population initialization; Each chromosome group is defined to represent a set of processed historical environmental data and a set of trained and analyzed historical environmental data. The population size and the maximum number of iterations are also defined. ; S53. Establish a fitness function based on the constructed multi-set irrigation decision objective model; The fitness function is set as follows: ； in, This represents the fitness of the irrigation decision target model corresponding to the historical environmental data of group Q in the initial population after treatment and the historical environmental data after training and analysis. S54. Select genetic operators based on the established fitness function; S55. Perform chromosome crossover on the selected genetic operators; Randomly select crossover points from the chosen genetic operators, and perform pairwise crossovers in a sequential manner to generate a new pair of chromosome codes; The newly generated chromosome codes will be used as a new population to participate in the iteration; S56. Iterate through steps S52-S55 until the maximum number of iterations is reached. The optimized irrigation decision target models are output.

7. The system for constructing a large database of information on irrigation areas based on plateau three-dimensional climate, as described in claim 1, is characterized in that... The collection of control point coordinates, historical environmental data, and optimized multiple sets of irrigation decision target models are used to construct a large information database. The irrigation control in the plateau irrigation area based on this database includes the following steps: The collected historical environmental data, control point coordinates, and optimized multiple irrigation decision target models will be used as the basis for constructing a large information database. Simultaneously, the processed real-time environmental data is input into a large information database, and the processed real-time environmental data is matched and analyzed through the large information database to obtain corresponding irrigation control decisions. Based on the obtained irrigation control decisions and the coordinates of each control point in the large information database, irrigation control is carried out on each control point.

8. An apparatus for implementing the system for constructing a large database of information on irrigation districts based on plateau three-dimensional climate as described in any one of claims 1-7, characterized in that, include: The system includes a data acquisition module, a data processing module, a data analysis module, a decision building module, a decision optimization module, and an irrigation control module. The data acquisition module is used to collect environmental data in the plateau irrigation area in real time. The data processing module is used to process the real-time collected environmental data of the plateau irrigation area to obtain processed environmental data. The data analysis module is used to analyze the processed environmental data to obtain the analyzed environmental data. The decision-making construction module is used to construct multiple sets of irrigation decision target models based on the analyzed environmental data. The decision optimization module is used to optimize the constructed multiple sets of irrigation decision target models; The irrigation control module is used to control irrigation based on multiple optimized irrigation decision target models.

Images