CN-121986638-A - Automatic planning method for intelligent agriculture Internet of things equipment

CN121986638ACN 121986638 ACN121986638 ACN 121986638ACN-121986638-A

Abstract

The invention belongs to the technical field of equipment planning, and discloses an automatic planning method of intelligent agriculture Internet of things equipment, which comprises the steps of dividing a target area into grid units, collecting soil moisture parameters and nutrient parameters of each grid, and establishing an area digital twin model; the method comprises the steps of obtaining target crops of grids, obtaining growth information from a crop knowledge base, executing time sequence simulation to generate a water and fertilizer demand table of each grid, executing a water and fertilizer balancing strategy based on the water and fertilizer demand table to generate a water and fertilizer supply plan of each grid, analyzing spatial distribution characteristics of the supply plan, clustering adjacent grids with similar plans into irrigation management partitions, and generating a pipe network topological structure and an equipment planning scheme based on partition layout. According to the method, the traditional uniformly distributed areas are scientifically divided into the management partitions with consistent internal requirements, unified management of the same partition is achieved, and the problem of supply and demand mismatch caused by neglecting spatial heterogeneity in the traditional method is solved.

Inventors

ZHAO JUAN
RONG XIONG
LUO CHEN

Assignees

内蒙古中孚明丰农业科技有限公司

Dates

Publication Date: 20260508
Application Date: 20251224

Claims (8)

1. An automatic planning method for intelligent agriculture internet of things equipment is characterized by comprising the following steps: dividing a target area into a plurality of grid cells, collecting soil moisture parameters and soil nutrient parameters of each grid cell, and establishing an area digital twin model; Acquiring target crops of all grid units, acquiring growth information of the target crops from a pre-constructed crop knowledge base, and loading the growth information into a regional digital twin model; Executing time sequence simulation in the regional digital twin model to generate a water and fertilizer requirement table of each grid unit; executing a water and fertilizer balancing strategy in the regional digital twin model based on the water and fertilizer demand table, generating a water and fertilizer supply plan, and mapping the water and fertilizer supply plan to each grid unit of the model; Analyzing spatial distribution characteristics of a water and fertilizer supply plan in a regional digital twin model, and clustering grid units into irrigation management partitions; And generating a pipe network topological structure based on the spatial layout of the irrigation management partition, and generating an equipment planning scheme based on the pipe network topological structure.
2. The method for automatically planning intelligent agriculture internet of things equipment according to claim 1, wherein the step of collecting the soil moisture parameter and the soil nutrient parameter of each grid cell comprises the steps of: collecting soil samples at farmland positions corresponding to each grid unit; measuring the soil effective water content as soil moisture parameters and the quick-acting nitrogen, quick-acting phosphorus and quick-acting potassium contents as soil nutrient parameters based on the collected soil samples; The establishing of the regional digital twin model comprises the steps of setting a unique identifier and a space coordinate for each grid unit, and establishing the regional digital twin model based on the unique identifier, the space coordinate, the soil moisture parameter and the soil nutrient parameter.
3. The automatic planning method for intelligent agriculture internet of things equipment according to claim 2, wherein the construction process of the crop knowledge base comprises the following steps: For each crop, collecting daily water demand data and nutrient absorption data of the whole growth period, and combining continuous time periods, in which the water demand data and the nutrient absorption data are both within a preset difference range, into a growth stage; for each growth stage, recording start-stop time, daily water demand, daily nitrogen, phosphorus and potassium demand and nitrogen, phosphorus and potassium utilization rate as stage information, and combining all the stage information into growth information; A crop knowledge base is constructed using all crops and their corresponding growth information.
4. The automatic planning method of intelligent agriculture internet of things equipment according to claim 3, wherein the performing time sequence simulation in the regional digital twin model, generating the water and fertilizer requirement table of each grid unit comprises: creating a moisture account and a nitrogen, phosphorus and potassium nutrient account for each grid cell in the regional digital twin model; initializing the water account capacity as a soil water parameter value, and the nutrient account initial value as a soil nutrient parameter value; The method comprises the steps of carrying out demand simulation on each growth stage in a model, obtaining expected precipitation data of each stage, updating a water account according to the expected precipitation data, updating the water account according to the daily water demand corresponding to each stage, and recording a water gap of each stage; and (3) merging the water gaps and the nitrogen, phosphorus and potassium nutrient gaps generated by simulation at each stage into a water and fertilizer requirement table after sequencing according to time sequence.
5. The method for automatically planning intelligent agriculture internet of things equipment according to claim 4, wherein the step of executing a water and fertilizer balance strategy in an area digital twin model based on a water and fertilizer demand table, and the step of generating a water and fertilizer supply plan comprises the steps of: Extracting a water gap value and a nitrogen, phosphorus and potassium nutrient gap value of each growth stage from a water and fertilizer requirement table, and constructing a gap sequence; marking a stage with a moisture gap value greater than zero as an irrigatable stage; Calculating the nutrient carrying capacity of each irrigatable stage based on the moisture gap value and the preset concentration upper limit; The method comprises the steps of performing a nutrient balance distribution algorithm, namely traversing a gap sequence forwards from a last growth stage, and for a stage with a nutrient gap, if the stage is an irrigatable stage, preferentially distributing the nutrient gap to the stage until reaching a bearing capacity, if the stage is not irrigatable or the bearing capacity is insufficient, searching the rest nutrient gap forwards for the latest irrigatable stage to distribute, recording the accumulated nutrient distribution amount of each irrigatable stage, and if the bearing capacity of all the irrigatable stages is used up but still has unassigned nutrient gaps, uniformly distributing the rest gap to all the irrigatable stages; Generating a water and fertilizer supply plan, wherein the water and fertilizer supply plan comprises irrigation quantity and nitrogen, phosphorus and potassium fertilization quantity of each stage, the irrigation quantity is equal to the original moisture gap value, and the nitrogen, phosphorus and potassium fertilization quantity is equal to the accumulated nutrient allocation quantity of each stage capable of irrigating.
6. The method for automatically planning intelligent agriculture internet of things equipment according to claim 5, wherein analyzing spatial distribution characteristics of a water and fertilizer supply plan in a regional digital twin model, clustering grid cells into irrigation management zones comprises: reading a water and fertilizer supply plan of each grid unit from the regional digital twin model; Extracting an irrigation amount sequence, a nitrogen fertilization amount sequence, a phosphorus fertilization amount sequence and a potassium fertilization amount sequence; Initializing each grid unit into an independent partition, iterating and combining grid units with feature distances smaller than a threshold value and adjacent to each other in space, and updating the central features of the combined partitions until grid pairs meeting combining conditions are not available, wherein the feature distances are obtained by calculation based on an irrigation quantity sequence, a nitrogen fertilization quantity sequence, a phosphorus fertilization quantity sequence and a potassium fertilization quantity sequence; updating the partition identification in the regional digital twin model, taking the combined units as irrigation management partitions, and recording the area, the grid number, the boundary coordinates and the partition center position of each irrigation management partition.
7. The method for automatically planning intelligent agriculture internet of things equipment according to claim 6, wherein the generating a pipe network topology based on the spatial layout of the irrigation management partition comprises: extracting boundary coordinates and contained grid cell coordinates of each irrigation management partition from the regional digital twin model; Establishing orthogonal grid lines along the row direction and the column direction of the target area to form a basic pipeline grid; identifying, within each irrigation management partition, intersections of the partition boundaries with the underlying piping grid as candidate entry points; selecting, for each partition, a point closest to the partition geometric center from the candidate entry points as a partition entry point; Generating a main pipe path along the outermost boundary of the base pipe grid; traversing all grid cells in the partition along the basic grid lines from the partition entry point inside each partition, and marking the grid lines passing through the boundaries of the grid cells as end pipeline paths; And recording the coordinate sequences and the hierarchical relations of the main pipeline, the branch pipeline and the tail end pipeline to form a pipeline network topological structure.
8. The automatic planning method for intelligent agriculture internet of things equipment according to claim 7, wherein the generating the equipment planning scheme based on the pipe network topology comprises: The method comprises the steps of configuring a control valve at the position of each subarea inlet point of a pipe network topological structure, configuring water and fertilizer mixing equipment at the connection position of a main pipeline and an external supply system, configuring a connector at a pipeline junction, configuring a plurality of water outlets in grid units in each subarea, configuring pressure monitoring points at pipeline nodes at the subarea boundary, configuring a soil monitoring sensor at the geometric center of each subarea, and outputting an equipment type, quantity and coordinate position list to form an equipment planning scheme.

Description

Automatic planning method for intelligent agriculture Internet of things equipment Technical Field The invention relates to equipment planning technology, in particular to an automatic planning method for intelligent agriculture Internet of things equipment. Background With the rapid development of the Internet of things, big data and artificial intelligence technology, intelligent agriculture has become an important direction of modern agriculture transformation and upgrading. The agricultural Internet of things equipment comprises an environment monitoring sensor, an automatic irrigation system, intelligent fertilization equipment, a weather station, a soil monitor and the like, and the equipment is connected with each other through a network to realize real-time sensing and accurate regulation and control of farmland environment. The intelligent agriculture Internet of things system has the advantages of scientific planning and reasonable layout, and has important significance for improving the agricultural production efficiency, saving resources and increasing the yield. In the aspect of water and fertilizer management, the water and fertilizer integrated system is an important technical means for improving the water and fertilizer utilization efficiency by dissolving fertilizer in irrigation water and simultaneously completing irrigation and fertilizer application operation by utilizing a pipeline system. The traditional water and fertilizer integrated equipment planning method mainly adopts a uniform layout strategy, namely, gridding arrangement is carried out according to fixed intervals, irrigation and fertilizer equipment with the same specification is configured on each grid, and a unified management system is adopted. This uniform layout approach has significant limitations. The farmland has obvious spatial heterogeneity, the soil water retention capacity of different positions is very different, the water retention capacity of a sandy soil area is poor, the water retention capacity of a clay area is strong, the initial fertility of the soil is unevenly distributed, some areas are rich in nutrients, some areas are relatively barren, different grids can be used for planting different crops, and the water and fertilizer requirement rules of the different grids are completely different. By adopting the unified equipment configuration and management mode, the differences are ignored, so that in actual operation, the water and fertilizer supply surplus occurs at the positions in the same management area, the resource waste and the environmental pollution risk are caused, and the supply shortage occurs at other positions, so that the normal growth of crops is influenced. Disclosure of Invention In order to overcome the problems in the prior art, the invention provides an automatic planning method of intelligent agriculture Internet of things equipment, which is used for solving the problems. The invention provides the following technical scheme: an automatic planning method for intelligent agriculture internet of things equipment, comprising: dividing a target area into a plurality of grid cells, collecting soil moisture parameters and soil nutrient parameters of each grid cell, and establishing an area digital twin model; Acquiring target crops of all grid units, acquiring growth information of the target crops from a pre-constructed crop knowledge base, and loading the growth information into a regional digital twin model; Executing time sequence simulation in the regional digital twin model to generate a water and fertilizer requirement table of each grid unit; executing a water and fertilizer balancing strategy in the regional digital twin model based on the water and fertilizer demand table, generating a water and fertilizer supply plan, and mapping the water and fertilizer supply plan to each grid unit of the model; Analyzing spatial distribution characteristics of a water and fertilizer supply plan in a regional digital twin model, and clustering grid units into irrigation management partitions; And generating a pipe network topological structure based on the spatial layout of the irrigation management partition, and generating an equipment planning scheme based on the pipe network topological structure. Preferably, the collecting the soil moisture parameter and the soil nutrient parameter of each grid cell includes: collecting soil samples at farmland positions corresponding to each grid unit; measuring the soil effective water content as soil moisture parameters and the quick-acting nitrogen, quick-acting phosphorus and quick-acting potassium contents as soil nutrient parameters based on the collected soil samples; The establishing of the regional digital twin model comprises the steps of setting a unique identifier and a space coordinate for each grid unit, and establishing the regional digital twin model based on the unique identifier, the space coordinate, the soil moisture parameter and th