CN-122018338-A - Environment control method based on Internet of things and meteorological soil moisture content monitoring

CN122018338ACN 122018338 ACN122018338 ACN 122018338ACN-122018338-A

Abstract

The invention discloses an environment control method based on the Internet of things and meteorological soil moisture content monitoring, and belongs to the technical field of intelligent environment control. The method comprises the steps of collecting meteorological element data, soil moisture content time sequence data and environment execution equipment state data of a target area through a monitoring node of the Internet of things, completing data time sequence alignment and preliminary noise reduction processing, calculating soil moisture content time sequence disturbance entropy values and dividing environment disturbance grades by adopting an arrangement entropy algorithm, constructing a multi-objective fitness function containing multi-dimensional constraint, completing environment control parameter optimization based on an improved sparrow search algorithm, issuing a control instruction to an execution terminal, and completing disturbance entropy value updating and closed-loop regulation of data after synchronous collection regulation. According to the invention, dynamic sensing and accurate regulation of the environmental state are realized, the scene suitability of a control strategy is improved, the multi-dimensional regulation and control requirement is considered, and the comprehensive operation efficiency of environmental control is improved.

Inventors

LI WENXUE
TANG YAN
JIANG YUNKE
ZHANG ZHIXING
YANG XUE
HE LONG
DU QIN
LIU WEI
HE CHANGLIANG
LUO HAO
WU GUOSHENG
WANG LINLU
QING XUEGANG
ZHOU YUE
CHEN XIAOPING
LIU GANG
HUANG GAIQUN
YIN HONG
AN JU

Assignees

四川省农业科学院蚕业研究所(四川省农业科学院特种经济动植物研究所)
四川省南充市桃园生物化学研究开发有限公司
四川实有智能科技有限公司

Dates

Publication Date: 20260512
Application Date: 20260413

Claims (10)

1. An environment control method based on the internet of things and meteorological soil moisture content monitoring is characterized by comprising the following steps: S1, acquiring meteorological element data, soil moisture content time sequence data and environment execution equipment state data of a target area through an Internet of things monitoring node, performing time sequence alignment processing on the meteorological element data, the soil moisture content time sequence data and the environment execution equipment state data, and performing preliminary noise reduction processing on the time sequence aligned data; s2, performing permutation entropy calculation on the meteorological element data and the soil moisture content time sequence data after the preliminary noise reduction treatment to obtain a soil moisture content time sequence disturbance entropy value, and dividing the environmental disturbance level according to the soil moisture content time sequence disturbance entropy value; S3, constructing a multi-target fitness function, wherein the multi-target fitness function comprises regulation and control precision constraint, energy consumption constraint and response speed constraint, processing the multi-target fitness function based on an improved sparrow search algorithm, and executing chaotic initialization operation, self-adaptive weight adjustment operation and boundary constraint correction operation by the improved sparrow search algorithm; S4, taking the environmental disturbance level as input constraint of an improved sparrow search algorithm, determining an environmental control parameter combination through the improved sparrow search algorithm, converting the environmental control parameter combination into a control instruction, issuing the control instruction to an environmental regulation and control execution terminal through an Internet of things communication link, collecting regulated soil moisture content time sequence data and updating a soil moisture content time sequence disturbance entropy value.
2. The method according to claim 1, wherein in step S1, step S1.1. The abnormal value identification process is performed on the original meteorological element data, the original soil moisture content time series data, and the original environment execution device state data collected by the monitoring node of the internet of things, the abnormal data deviating from the normal data interval is identified, and the rejection process is performed; s1.2, performing time axis matching processing on meteorological element data, soil moisture content time sequence data and environment execution equipment state data after abnormal data are removed, completing time sequence alignment processing, performing smooth filtering processing on the data after time sequence alignment, completing preliminary noise reduction processing, removing interference information generated in a data transmission process, sequentially performing abnormal value identification processing, time axis matching processing and smooth filtering processing, directly taking the data after the former step as input data of the latter step, and directly entering the processing flow of permutation entropy calculation on the processed meteorological element data, soil moisture content time sequence data and environment execution equipment state data.
3. The method according to claim 1, wherein in step S2, step S2.1. The soil moisture content time sequence data after the preliminary noise reduction processing is selected to construct a time sequence, phase space reconstruction processing is performed on the time sequence, and symbolized sorting processing is performed on the data after the phase space reconstruction according to the numerical value size to form a corresponding sorting feature sequence; S2.2, performing probability statistics processing on the sequencing feature sequences, performing permutation entropy calculation according to probability statistics processing results, comparing soil moisture content time sequence disturbance entropy values with preset dividing conditions, dividing environment disturbance levels of target areas according to comparison results, sequentially connecting phase space reconstruction processing, symbolizing sequencing processing and probability statistics processing, directly using the processed data for environment disturbance level division, and directly inputting the environment disturbance levels after division into an improved sparrow search algorithm as constraint conditions.
4. The method according to claim 1, wherein in step S3, step S3.1. Selecting a chaotic mapping sequence to generate initial population data, and performing a population chaotic initialization operation for improving a sparrow search algorithm by using the chaotic mapping sequence, so that the initial population is in a uniform distribution state in a search space; S3.2, performing self-adaptive inertia weight adjustment operation in the iterative optimization process of the improved sparrow search algorithm, dynamically adjusting the search step length of the improved sparrow search algorithm, performing boundary constraint correction operation on parameters exceeding a preset parameter interval in the iterative calculation process of the improved sparrow search algorithm, correcting out-of-range parameters into the preset parameter interval, and sequentially performing chaotic initialization operation, self-adaptive inertia weight adjustment operation and boundary constraint correction operation, wherein an operation result is directly applied to the solving process of the multi-target fitness function.
5. The method according to claim 1, wherein in step S4, step S4.1. The classified environmental disturbance level is input into an improved sparrow search algorithm, the improved sparrow search algorithm matches the corresponding iteration pattern according to the environmental disturbance level, and an environmental control parameter combination is determined by iterative optimization calculation; S4.2, converting the determined environment control parameter combination into a standardized control instruction according to an Internet of things communication protocol format, transmitting the standardized control instruction to an environment regulation and control execution terminal through an Internet of things communication link, executing environment regulation and control actions by the environment regulation and control execution terminal according to the standardized control instruction, collecting regulated soil moisture content time sequence data and transmitting the regulated soil moisture content time sequence data back to a data processing terminal, and sequentially executing iterative optimizing calculation, instruction format conversion and instruction transmission operation, wherein the returned soil moisture content time sequence data is directly used for updating calculation of soil moisture content time sequence disturbance entropy values.
6. The method according to claim 2, wherein in step S1, data synchronization processing is performed on meteorological element data, soil moisture content time sequence data and environment execution device state data collected by the monitoring node of the internet of things, collection time stamps and transmission frequencies of the meteorological element data, the soil moisture content time sequence data and the environment execution device state data are unified, different types of monitoring data are summarized under the same time dimension, data synchronization processing and abnormal data eliminating operation and time sequence alignment processing are synchronously performed, the synchronized meteorological element data, soil moisture content time sequence data and environment execution device state data are unified into a smooth filtering processing flow, and the data after the data synchronization processing directly participate in subsequent time sequence alignment operation and preliminary noise reduction operation.
7. A method according to claim 3, wherein in step S2, a time series trend feature extraction operation is performed on the weather element data and the soil moisture content time series data after the preliminary noise reduction processing, the weather element variation trend feature and the soil moisture content time series fluctuation feature are extracted, the extracted time series trend feature is incorporated into an arrangement entropy calculation process, a feature data screening operation and a feature data integration operation are performed before the arrangement entropy calculation, redundant feature data irrelevant to the time series disturbance is removed, the arrangement entropy calculation is completed according to the feature data after the screening integration, the time series trend feature extraction operation is performed after the preliminary noise reduction processing, and the feature data after the extraction and integration are directly used as input data for the arrangement entropy calculation.
8. The method according to claim 4, wherein in step S3, after finishing a single iteration by the improved sparrow search algorithm, a neighborhood disturbance update operation is performed on position data corresponding to the bird in the improved sparrow search algorithm, new position data is generated in a preset interval around the bird-capturing position, the original bird-capturing position data is replaced by the newly generated position data, the neighborhood disturbance update operation is performed after finishing the single iteration, the updated bird-capturing position data directly participates in the next iteration calculation of the improved sparrow search algorithm, and the neighborhood disturbance update operation is performed in cooperation with a chaotic initialization operation and an adaptive inertia weight adjustment operation to jointly finish the solving of the multi-objective fitness function.
9. The method according to claim 8, wherein in step S3, the number ratio of the finder individuals and the follower individuals in the improved sparrow search algorithm is adjusted according to the classified environmental disturbance level, the allocation rule of the finder and the follower is updated synchronously when the environmental disturbance level changes, the population roles are allocated according to the adjusted ratio in the iteration process of the improved sparrow search algorithm, the finder performs the global scope search operation, the follower performs the local scope search operation, the population role ratio adjustment operation is performed after the bird collar position data is updated, and the adjusted role allocation rule is directly applied to the search operation in the subsequent iteration process of the improved sparrow search algorithm.
10. The method according to claim 9, wherein in step S4, soil moisture content time series data after the operation of the environment control execution terminal is collected, permutation entropy calculation is performed again according to the soil moisture content time series data, an updated soil moisture content time series disturbance entropy value is obtained, environment disturbance levels are divided again according to the updated soil moisture content time series disturbance entropy value, the divided environment disturbance levels are input into an improved sparrow search algorithm for completing population role proportion adjustment, the iteration number and search range of the improved sparrow search algorithm are adjusted, an iteration strategy corresponding to the current environment state is matched, and the divided environment disturbance levels are directly used for adjusting operation parameters of the improved sparrow search algorithm.

Description

Environment control method based on Internet of things and meteorological soil moisture content monitoring Technical Field The invention relates to the technical field of intelligent environmental control, in particular to an environmental control method based on the Internet of things and meteorological soil moisture monitoring. Background With the deep fusion of the sensing technology of the Internet of things, the intelligent data processing technology and the modern agriculture environment management and control technology, the environment intelligent control based on meteorological soil moisture content monitoring has become the core technology application direction in the fields of intelligent agriculture, facility planting, ecological vegetation management and protection and the like. In the current industry, deployment and application of the monitoring nodes of the Internet of things are popularized in a large scale, real-time acquisition and transmission of multidimensional environmental data such as meteorological elements, soil moisture content, equipment running state and the like can be completed, and coverage area, transmission efficiency and acquisition dimension of data acquisition are remarkably improved. Meanwhile, the technical means such as a time sequence data analysis method and a group intelligent optimization algorithm are gradually applied to decision links of environmental control, analysis processing of collected data and optimization solving of environmental control parameters can be achieved, a traditional manual control and fixed threshold control mode is replaced, the continuous development of an environmental control technology from automation to intelligent is promoted, the application scene of the related technology is continuously expanded, and a technical system is also continuously perfected in practical application. In the practical application process of the prior art, the multisource heterogeneous monitoring data lacks of standardized time sequence alignment and preprocessing flow after acquisition, the consistency of time dimensions of different types of data is insufficient, data dislocation and noise interference are easy to occur, and high-quality basic data support cannot be provided for subsequent control decisions. Meanwhile, the prior method cannot effectively quantify the time sequence disturbance influence caused by the change of meteorological elements on soil moisture content, and is difficult to accurately grade the actual fluctuation state of the environment, so that the environment control decision lacks constraint conditions for attaching to the real-time environment state, and the suitability of the control strategy and the actual environment requirement is insufficient. In addition, the multi-dimensional requirements of regulation and control precision, energy consumption loss and response speed are difficult to be considered in the optimizing process of the existing environment control parameters, the conventional optimizing algorithm has limitations in the multi-objective solving process, the real-time data feedback after regulation and control execution and the dynamic update of the control strategy cannot be realized, the problems of regulation and control lag, excessive regulation and the like are easy to occur, and the closed-loop dynamic accurate management and control of the environment state is difficult to realize. Disclosure of Invention The invention aims to overcome the defects of the prior art and provides an environment control method based on the Internet of things and meteorological soil moisture monitoring. The aim of the invention is realized by the following technical scheme: the environment control method based on the Internet of things and the meteorological soil moisture monitoring comprises the following steps: S1, acquiring meteorological element data, soil moisture content time sequence data and environment execution equipment state data of a target area through an Internet of things monitoring node, performing time sequence alignment processing on the meteorological element data, the soil moisture content time sequence data and the environment execution equipment state data, and performing preliminary noise reduction processing on the time sequence aligned data; s2, performing permutation entropy calculation on the meteorological element data and the soil moisture content time sequence data after the preliminary noise reduction treatment to obtain a soil moisture content time sequence disturbance entropy value, and dividing the environmental disturbance level according to the soil moisture content time sequence disturbance entropy value; S3, constructing a multi-target fitness function, wherein the multi-target fitness function comprises regulation and control precision constraint, energy consumption constraint and response speed constraint, processing the multi-target fitness function based on an improved sparrow search al