CN-122004108-A - Planting park spray irrigation management method and system based on intelligent Internet of things

CN122004108ACN 122004108 ACN122004108 ACN 122004108ACN-122004108-A

Abstract

The invention is applicable to the technical field of agricultural intelligent irrigation control and environmental perception data processing, and provides a planting park sprinkling irrigation management method and system based on intelligent Internet of things, wherein the method comprises the following steps: and obtaining a plurality of reference data samples with consistent sprinkling background information in the target planting area, wherein the reference data samples comprise original particle composition data in the air before sprinkling and corresponding humidity lifting rate value of unit water quantity after sprinkling. The invention provides a quantifiable input intensity factor generation mechanism by constructing a time evolution trend mapping relation between the non-moisture source particle component proportion and the unit water quantity humidity lifting rate. Compared with the processing mode in the prior art that potential influences can be omitted by directly eliminating the particle components, the method and the device calculate the retention proportion by utilizing the slope deviation quantity, and realize dynamic weakening processing of the non-moisture source particle components in the original data.

Inventors

DONG AIHONG
MA YANLI
CHEN WENXU
HAN HONGLIANG
Zha Shuting

Assignees

陕西农林职业技术大学
杨凌惠远农业技术开发有限公司

Dates

Publication Date: 20260512
Application Date: 20251208

Claims (10)

1. The planting park sprinkling irrigation management method based on the intelligent Internet of things is characterized by comprising the following steps of: Obtaining a plurality of reference data samples with consistent sprinkling background information in a target planting area, wherein the reference data samples comprise original particle composition data in air before sprinkling and corresponding humidity increasing rate value of unit water quantity after sprinkling; determining the proportion of non-moisture source particle components in original particle composition data in each reference data sample based on a preset recognition mechanism, and constructing a first change trend of the proportion and a second change trend of a unit water volume humidity lifting rate value according to time sequence; respectively performing linear fitting on the first change trend and the second change trend to obtain a corresponding first trend slope and a corresponding second trend slope, and if the first change trend is in linear rising and the second change trend is in linear falling, and the absolute value of the second trend slope is smaller than that of the first trend slope, generating a delivery retention ratio according to the difference between the first trend slope and the second trend slope; In the subsequent sprinkling irrigation management, the delivery retention proportion is applied to corresponding non-moisture source particle components in future original particle composition data to be delivered to a sprinkling irrigation demand analysis model, and corrected particle composition data are input into the model to obtain a corrected demand intensity value for subsequent sprinkling irrigation regulation.
2. The intelligent internet of things-based planting park sprinkling management method according to claim 1, wherein the sprinkling background information is identical, namely that crop types corresponding to reference data samples are identical, growth phases are identical, acquisition time is in the same natural period, and the variation ranges of sprinkling water quantity, ambient temperature and ambient humidity are all in a set tolerance range.
3. The intelligent internet of things-based plantation spray management method of claim 1, wherein the step of determining the proportion of the non-moisture source particle components in the original particle composition data in each reference data sample based on a preset recognition mechanism, and constructing a first change trend of the proportion and a second change trend of the unit water amount humidity increase rate value according to the time sequence comprises the following steps: Acquiring original particle composition data in air of a target planting area before sprinkling irrigation according to each reference data sample, classifying and identifying particle components in unit volume based on particle size structural characteristics, component identification parameters or a preset analysis device, determining a part belonging to non-moisture source particle components, calculating the proportion of the part in the whole particle composition data, and marking the proportion as the proportion of the non-moisture source particle components; The proportion of the corresponding non-moisture source particle components in all the reference data samples is arranged in time sequence to form a first change trend, and the air humidity lifting speed values caused by the unit water quantity in each reference data sample are arranged in the same time sequence to form a second change trend.
4. The intelligent internet of things-based plantation spray management method of claim 3, wherein the step of linearly fitting the first trend and the second trend to obtain the corresponding first trend slope and second trend slope, and if the first trend is linearly rising and the second trend is linearly falling, and the absolute value of the second trend slope is smaller than the absolute value of the first trend slope, generating the delivery retention ratio according to the difference between the first trend slope and the second trend slope comprises: Respectively performing linear fitting on the first change trend and the second change trend based on a least square fitting technology, and calculating a corresponding first trend slope and a corresponding second trend slope; If the first trend slope is positive and the second trend slope is negative and the absolute value of the second trend slope is smaller than that of the first trend slope, calculating the relative deviation ratio between the absolute values of the two slopes; And based on the relative deviation ratio, combining a preset adjusting amplitude factor to generate a delivery retention ratio for adjusting the input intensity of the non-moisture source particle component in the spray irrigation demand analysis model.
5. The intelligent Internet of things-based plantation sprinkling management method of claim 4, wherein in subsequent sprinkling management, after the original particle composition data for calculating the required intensity value is obtained, the non-moisture source particle component subset is identified, intensity adjustment is carried out on the non-moisture source particle component subset by adopting the delivery retention proportion instead of direct elimination, and the adjusted non-moisture source particle component data and the rest particle data are input into a sprinkling demand analysis model together to generate a corrected required intensity value for subsequent sprinkling regulation.
6. Plantation sprinkling management system based on wisdom thing networking, its characterized in that, the system includes: the sample acquisition module is used for acquiring a plurality of reference data samples with consistent sprinkling background information in a target planting area, wherein the reference data samples comprise original particle composition data in the air before sprinkling and corresponding unit water volume humidity lifting rate values after sprinkling; The relevance recognition module is used for determining the proportion of non-moisture source particle components in original particle composition data in each reference data sample based on a preset recognition mechanism, and constructing a first change trend of the proportion and a second change trend of a unit water volume humidity lifting rate value according to time sequence; The delivery retention ratio generation module is used for respectively carrying out linear fitting on the first change trend and the second change trend to obtain a corresponding first trend slope and a corresponding second trend slope, and if the first change trend is linearly ascending, the second change trend is linearly descending, and the absolute value of the second trend slope is smaller than that of the first trend slope, the delivery retention ratio is generated according to the difference between the first trend slope and the second trend slope; and the model input adjusting module is used for applying the delivery retention proportion to corresponding non-moisture source particle components in future original particle composition data to be delivered to the spray irrigation demand analysis model in the follow-up spray irrigation management, and inputting the corrected particle composition data into the model to obtain a corrected demand intensity value for follow-up spray irrigation regulation.
7. The intelligent internet of things-based plantation sprinkling management system of claim 6, wherein the sprinkling background information is identical, the crop types corresponding to the reference data samples are identical, the growth phases are identical, the collection time is in the same natural period, and the variation ranges of sprinkling water quantity, ambient temperature and ambient humidity are all in the set tolerance range.
8. The intelligent internet of things-based plantation spray management system of claim 7, wherein said relevance identification module specifically comprises: the component identification unit is used for acquiring original particle composition data in the air of a target planting area before sprinkling irrigation according to each reference data sample, classifying and identifying particle components in unit volume based on particle size structural characteristics, component identification parameters or a preset analysis device, determining a part belonging to the non-moisture source particle components, calculating the proportion of the part in the whole particle composition data, and marking the proportion as the proportion of the non-moisture source particle components; The trend construction unit is used for arranging the proportion of the corresponding non-moisture source particle components in all the reference data samples in time sequence to form a first change trend, and arranging the air humidity lifting speed values caused by the unit water quantity in each reference data sample in the same time sequence to form a second change trend.
9. The intelligent internet of things-based plantation spray management system of claim 8, wherein said delivery reservation ratio generation module specifically comprises: the trend fitting unit is used for respectively carrying out linear fitting on the first change trend and the second change trend based on a least square fitting technology, and calculating a corresponding first trend slope and a corresponding second trend slope; The condition judging unit is used for calculating the relative deviation ratio between the absolute values of the first trend slope and the second trend slope if the first trend slope is a positive value and the second trend slope is a negative value and the absolute value of the second trend slope is smaller than the absolute value of the first trend slope; And the factor generation unit is used for generating a delivery retention ratio for adjusting the input intensity of the non-moisture source particle component in the spray irrigation demand analysis model based on the relative deviation ratio and combining a preset adjustment amplitude factor.
10. The intelligent internet of things-based plantation sprinkling management system of claim 9, wherein in subsequent sprinkling management, after the primary particle composition data for calculating the required intensity value is obtained, the non-moisture source particle component subset is identified, intensity adjustment is performed on the non-moisture source particle component subset by adopting the delivery retention ratio instead of direct elimination, and the adjusted non-moisture source particle component data and the rest particle data are input into a sprinkling demand analysis model together to generate a corrected required intensity value for subsequent sprinkling regulation.

Description

Planting park spray irrigation management method and system based on intelligent Internet of things Technical Field The invention belongs to the technical field of agricultural intelligent irrigation control and environmental perception data processing, and particularly relates to a planting park sprinkling irrigation management method and system based on an intelligent Internet of things. Background In the existing agricultural irrigation management system, the identification and control of the irrigation demand generally depend on various monitoring parameters such as environmental temperature and humidity, soil water content, meteorological data and the like. Some of the more advanced demand analysis models also introduce air particle composition as a reference variable, and it is considered that the specific particle concentration change can reflect the indirect change trend of the evapotranspiration intensity, the plant physiological activity or the moisture state to a certain extent. Therefore, in the intelligent Internet of things planting park with the environment monitoring capability, the particle composition data in the air is gradually brought into the input parameter system for sprinkling irrigation regulation and control, and is used for assisting in judging whether actual sprinkling irrigation demands exist currently. However, in practical applications, some systems directly pre-process the original particle composition data, that is, identify and reject particle components (such as soil loosening, manual inspection disturbance, or border dust of a planting area) that are not directly related to moisture changes, and only a subset of the determined moisture correlation is reserved for inputting the analysis model. While this approach simplifies the data structure and improves model computational efficiency, it too relies on regularized classifications, ignoring the effect that some "non-moisture derived particles" may indirectly affect humidity changes during certain phases or in certain crop environments. For example, such particles may affect evaporation rate due to physical shielding, reflection, carry-over of biological particles, etc., but these potential effects are often ignored by existing rules, resulting in larger deviations in the judgment of the analytical model from the actual humidity response. Disclosure of Invention The invention aims to provide a planting park spray irrigation management method and system based on an intelligent Internet of things, and aims to solve the problems in the background technology. The invention discloses a planting park spray irrigation management method based on intelligent Internet of things, which comprises the following steps: Obtaining a plurality of reference data samples with consistent sprinkling background information in a target planting area, wherein the reference data samples comprise original particle composition data in air before sprinkling and corresponding humidity increasing rate value of unit water quantity after sprinkling; determining the proportion of non-moisture source particle components in original particle composition data in each reference data sample based on a preset recognition mechanism, and constructing a first change trend of the proportion and a second change trend of a unit water volume humidity lifting rate value according to time sequence; respectively performing linear fitting on the first change trend and the second change trend to obtain a corresponding first trend slope and a corresponding second trend slope, and if the first change trend is in linear rising and the second change trend is in linear falling, and the absolute value of the second trend slope is smaller than that of the first trend slope, generating a delivery retention ratio according to the difference between the first trend slope and the second trend slope; In the subsequent sprinkling irrigation management, the delivery retention proportion is applied to corresponding non-moisture source particle components in future original particle composition data to be delivered to a sprinkling irrigation demand analysis model, and corrected particle composition data are input into the model to obtain a corrected demand intensity value for subsequent sprinkling irrigation regulation. As a further limitation of the technical scheme of the embodiment of the invention, the consistency of the sprinkling background information refers to the consistency of crop types, the consistency of growth stages and the acquisition time corresponding to the reference data samples in the same natural period, and the variation ranges of sprinkling water quantity, ambient temperature and ambient humidity are all in the set tolerance interval. As a further limitation of the technical solution of the embodiment of the present invention, the step of determining the proportion of the non-moisture source particle components in the original particle composition data in each refe