Search

CN-121986704-A - Automatic irrigation method and device based on artificial intelligence

CN121986704ACN 121986704 ACN121986704 ACN 121986704ACN-121986704-A

Abstract

The application relates to the technical field of irrigation, in particular to an automatic irrigation method and device based on artificial intelligence, wherein the method comprises the steps of collecting crop physiological signals, microclimate data, soil parameters, root system distribution data, crop canopy structure parameters and sprinkler angle adjustment range data of a planting area in real time; the method comprises the steps of identifying abnormal types of crop physiological signals and matching growth stress factors if the crop physiological signals exceed a health threshold, simulating an irrigation intervention effect and evaluating irrigation priority based on an area ecological model, extracting target irrigation working condition characteristics from a historical irrigation database if the crop physiological signals are high in priority, acquiring irrigation requirement parameters by combining real-time data, comparing adaptation degree, generating a dynamic irrigation scheme according to root system distribution data, soil parameters and sprinkling angle adjustment range data if the adaptation degree is insufficient, and irrigating a planting area based on the dynamic irrigation scheme. The application is beneficial to realizing the dynamic and accurate irrigation of crops in a planting area.

Inventors

  • TAN WEIYONG

Assignees

  • 湖南达美策略信息技术服务有限公司

Dates

Publication Date
20260508
Application Date
20260303

Claims (9)

  1. 1. An artificial intelligence based automatic irrigation method, comprising: Collecting target data of a planting area in real time, wherein the target data comprise crop physiological signals, microclimate data, soil parameters, root system distribution data, crop canopy structure parameters and sprinkling angle adjusting range data of an irrigation device; If the crop physiological signal exceeds the health threshold, identifying the abnormal type of the signal; based on the abnormal signal type, matching corresponding crop growth stress factors; Based on the abnormal type and the stress factors, a regional ecological model is called, and based on the regional ecological model, the irrigation intervention effect is simulated and the irrigation priority is evaluated; if the evaluation result is high priority, extracting target irrigation working condition characteristics from a historical irrigation database based on the current microclimate, soil parameters, crop canopy structure parameters and a preset similarity threshold; acquiring current irrigation demand parameters based on crop physiological signals, microclimate data, soil parameters and crop canopy structure parameters; comparing the adaptation degree of the current irrigation demand parameter and the target irrigation working condition characteristic; If the adaptation degree is smaller than the critical value, generating a dynamic irrigation scheme based on root system distribution data, soil parameters and sprinkler angle adjustment range data; Irrigation is performed on the planting area based on a dynamic irrigation scheme.
  2. 2. The artificial intelligence based automatic irrigation method of claim 1, wherein the matching corresponding crop growth stress factors based on signal anomaly type comprises: Acquiring characteristic dimensions of signal anomaly types; constructing an abnormal feature vector based on the feature dimension; Vector matching is carried out on the abnormal feature vector and a preset stress factor feature library; Calculating cosine similarity of the abnormal feature vector and each stress factor feature vector; screening stress factors with cosine similarity higher than a matching threshold value as candidate stress factors; Carrying out relevance verification on the candidate stress factors, and verifying suitability of the candidate stress factors and environmental conditions of the planting area; Rejecting candidate stress factors with suitability to environmental conditions lower than an adaptation threshold; and sequencing the remaining candidate stress factors from high to low according to the similarity, and selecting the stress factor at the first sequence as the crop growth stress factor.
  3. 3. An artificial intelligence based automatic irrigation method according to claim 1, wherein the simulating irrigation intervention effect and evaluating irrigation priority based on the regional ecological model comprises: Dividing a planting area into a plurality of subareas, and acquiring target data distribution characteristics of each subarea; inputting target data of each subarea into an area ecological model, and simulating crop physiological signal recovery trends under different irrigation water amounts and irrigation durations; calculating irrigation effect scores of all subareas based on the recovery trend; Counting irrigation effect scores of all subareas in the planting area, and calculating area comprehensive scores; comparing the comprehensive scores of the areas with preset priority level standards to determine the primary irrigation priority level; If a plurality of planting areas exist, applying for irrigation resources at the same time, and acquiring the importance coefficient and the growth stage weight of the crop variety in each area; and (5) adjusting the preliminary irrigation priority by combining the comprehensive scores of the areas, the variety importance coefficients and the growth stage weights to obtain the final irrigation priority.
  4. 4. The automatic irrigation method based on artificial intelligence according to claim 1, wherein if the adaptation degree is smaller than a critical value, generating a dynamic irrigation scheme based on root distribution data, soil parameters, and sprinkler angle adjustment range data comprises: If the adaptation degree is smaller than the critical value, determining position coordinates of a root system dense region and a root system sparse region in the planting region based on the root system distribution data; According to soil parameters, analyzing soil water holding capacity and water permeability coefficients of different positions; Calculating the sprinkling coverage range of the irrigation device under different angles by combining the sprinkling angle adjusting range data; Performing space matching on the position coordinates of the root system dense region and the sparse region and the water spraying coverage; according to the water holding capacity and the water permeability coefficient of the soil, different irrigation water quantities are distributed to different areas; setting a sprinkling angle combination of the irrigation device based on the water distribution result and the sprinkling coverage area; according to the water sprinkling angle combination and water distribution, making an irrigation execution plan for time intervals; And integrating the position coordinates, water distribution, water sprinkling angle combination and an irrigation execution plan to generate a dynamic irrigation scheme.
  5. 5. The method of claim 1, wherein the irrigating the planting area based on the dynamic irrigation scheme comprises: Disassembling the dynamic irrigation scheme into a plurality of irrigation subtasks, wherein each subtask corresponds to one sub-area of the planting area; Distributing a corresponding irrigation device and an execution time window for each irrigation subtask; in the execution time window, controlling the irrigation device to start irrigation according to a preset watering angle combination; Collecting soil humidity data and crop physiological signal feedback data in the irrigation process in real time; comparing the collected soil humidity data and crop physiological signal feedback data with corresponding preset indexes in a dynamic irrigation scheme respectively; If the soil humidity data or crop physiological signal feedback data deviate from the preset index, calculating a deviation value; adjusting the sprinkling angle and the water yield of the irrigation device according to the deviation value; continuously monitoring the adjusted irrigation effect until the subareas complete irrigation and the data reach the standard; all the irrigation subtasks are completed in sequence, and the whole irrigation of the planting area is realized.
  6. 6. The method of claim 5, wherein adjusting the watering angle and the water output of the irrigation device based on the deviation value comprises: Obtaining a deviation type corresponding to the deviation value, wherein the deviation type is divided into soil humidity deviation and crop physiological signal deviation; if the deviation type is the deviation of the soil humidity, the soil water holding capacity and the soil water permeability coefficient of the target subarea are obtained; Determining a target amount of soil humidity to be supplemented or reduced based on the soil water holding capacity and the soil water permeability coefficient; calculating the sprinkling angle adjustment amplitude which can enable the soil humidity to reach a target amount by combining sprinkling angle adjustment range data of an irrigation device; determining the adjustment proportion of the water yield based on the soil permeability coefficient; if the deviation type is the deviation of the crop physiological signals, acquiring the growth requirement corresponding to the current physiological signals of the crops; Comparing the growth requirement with a preset physiological signal index, and determining an irrigation condition adjustment direction required by signal recovery; according to the adjustment direction, the sprinkling angle is adjusted to optimize the water coverage range by combining with the crop canopy structure parameters, and the water yield is adjusted to match the growth requirement.
  7. 7. The method of claim 6, wherein determining the target amount of soil moisture to be replenished or reduced based on the soil water holding capacity and the soil permeability coefficient comprises: acquiring historical soil humidity standard reaching data of a target subarea, and determining a proper soil humidity range of crops corresponding to the target subarea in a current growth stage; Acquiring the current soil humidity of the target subarea, and comparing the current soil humidity data with a proper soil humidity range; if the current soil humidity is lower than the suitable soil humidity range, analyzing the evaporation rate of soil moisture by combining the soil water holding capacity; calculating the total amount of water to be supplemented in order to maintain the soil humidity in a proper range during the irrigation interval according to the evaporation rate, and taking the total amount of water to be supplemented as a target amount to be supplemented; if the current humidity is higher than the proper soil humidity range, determining the infiltration rate of the soil moisture based on the soil permeability coefficient; based on microclimate data within a preset time, the total amount of water to be reduced for bringing the soil humidity down to a proper range is calculated as a target amount to be reduced.
  8. 8. The method of claim 7, wherein determining the infiltration rate of soil moisture based on the soil permeability coefficient if the current humidity is above the suitable soil humidity range comprises: Obtaining soil layering samples of different depths of a target subarea, and detecting soil texture and porosity data of each soil layering sample; calculating the initial infiltration rate of each soil layering sample by combining the soil permeability coefficient; Collecting soil moisture infiltration history data of a target subregion after irrigation for a plurality of times, and calculating an average infiltration attenuation coefficient; Based on the initial infiltration rate and the average infiltration attenuation coefficient, establishing a dynamic model of the soil moisture infiltration rate changing with time; And determining the infiltration rate of the soil moisture in the current period through a dynamic model based on the current soil moisture and the proper moisture range.
  9. 9. An artificial intelligence based automatic irrigation device comprising: The data acquisition module is used for acquiring target data of a planting area in real time, wherein the target data comprise crop physiological signals, microclimate data, soil parameters, root system distribution data, crop canopy structure parameters and sprinkling angle adjustment range data of an irrigation device; The abnormality identification module is used for identifying the abnormal type of the signal if the physiological signal of the crop exceeds the health threshold; the factor matching module is used for matching corresponding crop growth stress factors based on the signal anomaly type; the simulated irrigation module is used for calling a regional ecological model based on the abnormal type and the stress factors, simulating irrigation intervention effect based on the regional ecological model and evaluating irrigation priority; The characteristic extraction module is used for extracting target irrigation working condition characteristics from the historical irrigation database based on the current microclimate, the soil parameters, the crop canopy structure parameters and a preset similarity threshold value if the evaluation result is high priority; the parameter acquisition module is used for acquiring current irrigation demand parameters based on crop physiological signals, microclimate data, soil parameters and crop canopy structure parameters; the adaptation degree comparison module is used for comparing the adaptation degree of the current irrigation demand parameters and the target irrigation working condition characteristics; The scheme generation module is used for generating a dynamic irrigation scheme based on root system distribution data, soil parameters and sprinkler angle adjustment range data if the adaptation degree is smaller than a critical value; And the irrigation module is used for irrigating the planting area based on a dynamic irrigation scheme.

Description

Automatic irrigation method and device based on artificial intelligence Technical Field The application relates to the technical field of irrigation, in particular to an automatic irrigation method and device based on artificial intelligence. Background Agricultural irrigation is a key link of agricultural production, and is directly related to the growth state of crops, the final yield quality and the utilization efficiency of agricultural water resources. At present, the problem of global water resource shortage is increasingly severe, along with the continuous promotion of the modern agricultural process, the limitation of the traditional irrigation mode is increasingly remarkable, and the intelligent and accurate irrigation technology has become an important direction of the development of the agricultural field. Traditional irrigation adopts modes such as flood irrigation and furrow irrigation, and is completely dependent on manual experience operation of a grower, and accurate perception of actual growth requirements of crops and environments of planting areas is lacking. The growers irrigate according to a fixed period, and the situation that the irrigation is excessive or insufficient often occurs, namely, excessive irrigation can lead to soil ponding, root system anoxic decay, possibly cause soil salinization and serious waste of water resources, and insufficient irrigation can lead crops to sink into water stress, influence photosynthesis and nutrient absorption, and lead to slow growth, yield reduction and even death. Meanwhile, the traditional mode can not realize differential irrigation according to different crop varieties, different growth stages and the difference of microenvironments in a planting area, so that irrigation effectiveness is greatly reduced. To solve the defects of traditional irrigation, intelligent irrigation technology has been developed. The existing intelligent irrigation system generally collects environmental parameters such as soil humidity and temperature, and combines a preset irrigation threshold value to perform automatic irrigation control. Part of the technology also introduces a crop water demand model, and the irrigation quantity is estimated according to the growth period of crops. However, the sensing dimension of the existing irrigation system is single, and most of the sensing dimension is only concerned with partial parameters of soil or weather, and key information such as physiological signals, root system distribution characteristics and crop canopy structures of crops are ignored, so that a precise irrigation scheme cannot be formulated according to the essential requirement of crop growth, and finally, dynamic precise irrigation of crops in a planting area cannot be realized. Disclosure of Invention In order to facilitate dynamic and accurate irrigation of crops in a planting area, the application provides an automatic irrigation method and equipment based on artificial intelligence. In a first aspect, the application provides an artificial intelligence based automatic irrigation method, which adopts the following technical scheme: an artificial intelligence based automatic irrigation method comprising: climate data, soil parameters and crop canopy structure parameters, and acquiring current irrigation demand parameters; comparing the adaptation degree of the current irrigation demand parameter and the target irrigation working condition characteristic; If the adaptation degree is smaller than the critical value, generating a dynamic irrigation scheme based on root system distribution data, soil parameters and sprinkler angle adjustment range data; Irrigation is performed on the planting area based on a dynamic irrigation scheme. Optionally, the matching the corresponding crop growth stress factor based on the signal anomaly type includes: Acquiring characteristic dimensions of signal anomaly types; constructing an abnormal feature vector based on the feature dimension; Vector matching is carried out on the abnormal feature vector and a preset stress factor feature library; Calculating cosine similarity of the abnormal feature vector and each stress factor feature vector; screening stress factors with cosine similarity higher than a matching threshold value as candidate stress factors; Carrying out relevance verification on the candidate stress factors, and verifying suitability of the candidate stress factors and environmental conditions of the planting area; Rejecting candidate stress factors with suitability to environmental conditions lower than an adaptation threshold; and sequencing the remaining candidate stress factors from high to low according to the similarity, and selecting the stress factor at the first sequence as the crop growth stress factor. Optionally, simulating the irrigation intervention effect and evaluating the irrigation priority based on the regional ecological model includes: Dividing a planting area into a plurality of subar