Intelligent remote environment monitoring method and system for farm

Abstract

The application discloses a kind of intelligent remote environment monitoring method and system for farm, it is related to remote environment monitoring technical field.By dividing farm into multiple basic space units, and combining physical shelter, maintenance interference and environmental disturbance, etc. Constraint condition, determine the space range of the monitoring node that can be arranged and cannot be arranged. Subsequently, through the sampling period node, the wind speed, temperature and humidity data of adjacent arrangeable unit are collected, the environmental state of unarrangeable unit is indirectly estimated, and the state estimation vector and state change estimation vector are constructed. Further introduce spatial similarity factor, consistency bias vector and estimation error offset vector, calculate the comprehensive environmental state confidence factor, and set threshold to warn environment anomaly.The method realizes the continuity of unarrangeable area environmental monitoring and dynamic risk identification, improves the spatial coverage, estimation accuracy and early warning response capability of monitoring system, and is suitable for large-scale farm intelligent environmental management.

Description

Technical Field

[0001] This invention relates to the field of remote environmental monitoring technology, and in particular to a smart remote environmental monitoring method and system for livestock farms. Background Technology

[0002] In recent years, with the continuous development of smart agriculture and IoT technologies, environmental monitoring has become increasingly prevalent in livestock farm management. Traditional livestock environmental monitoring methods rely heavily on manual inspections and point-based sensor deployment. While these methods can monitor key parameters such as temperature, humidity, and wind speed, the continuity, completeness, and representativeness of the monitoring data are often difficult to guarantee when dealing with large-scale spaces, complex equipment layouts, and dynamic climate disturbances. To address this issue, the industry has gradually introduced wireless sensor networks, edge computing, and remote data acquisition technologies, driving the development of livestock environmental monitoring methods towards remote, automated, and intelligent approaches. Recent research has also proposed using distributed sensors and spatial model fusion to achieve dynamic analysis of the environmental status of local areas within a livestock farm, coupled with early warning mechanisms to identify and respond to abnormal situations. These trends indicate that the livestock industry is gradually moving towards digital and intelligent transformation.

[0003] However, existing smart environmental monitoring technologies still face several limitations in practical deployment. Firstly, the complex spatial structure and high density of equipment in farms, coupled with physical obstructions or severe environmental disturbances in some areas, prevent the comprehensive deployment of monitoring nodes, creating numerous "blind spots" and hindering the acquisition of complete data. Secondly, traditional systems often employ static interpolation or simple inference methods when dealing with environmental conditions in areas where deployment is impossible, lacking dynamic response and spatial collaborative estimation capabilities. This can easily lead to large estimation biases and distorted early warning judgments. Furthermore, current environmental data fusion and early warning mechanisms are largely based on direct sampling data, neglecting the structural similarities between spatial neighborhoods and climate evolution patterns. This makes it difficult to effectively support indirect estimation and credibility assessment of unmonitored areas, thus affecting the overall reliability and stability of the monitoring system. Summary of the Invention

[0004] Given that existing environmental monitoring technologies for livestock farms suffer from insufficient accuracy, weak spatial inference mechanisms, and a lack of state reliability evaluation in estimating environmental information in areas where sensors cannot be deployed, this invention proposes a smart remote environmental monitoring method and system for livestock farms.

[0005] Therefore, the problem to be solved by this invention is how to accurately estimate the changes in the environmental status of areas where monitoring nodes cannot be set up due to physical obstruction, equipment interference or personnel access restrictions in the process of environmental monitoring in aquaculture farms, and how to effectively identify and warn of potential anomalies.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, embodiments of the present invention provide a smart remote environmental monitoring method for a farm, comprising the following steps: S1: dividing the overall spatial area of ​​the farm into several basic spatial units; setting constraints on the basic spatial units; and deploying monitoring nodes within the basic spatial units that satisfy the constraints.

[0008] Step S2: Construct a set of basic spatial units where monitoring nodes cannot be deployed; construct sampling time period nodes in hours;

[0009] Step S3: Construct the set of adjacent deployable units of the basic spatial unit that cannot be equipped with monitoring nodes; calculate the indirect wind speed estimate, indirect temperature estimate, and indirect humidity estimate of the basic spatial unit that cannot be equipped with monitoring nodes within a single sampling period node, and construct the state estimation vector.

[0010] Step S4: Based on the state estimation vector, calculate the state change estimation vector of the basic spatial unit where monitoring nodes cannot be deployed between two adjacent sampling period nodes;

[0011] Step S5: Calculate the spatial similarity factor between the basic spatial unit where monitoring nodes cannot be deployed and the adjacent deployable unit. Combine the state change estimation vector to calculate the average state change vector and the estimation error offset vector.

[0012] Step S6: Construct a consistency deviation vector; based on the estimated error offset vector and the consistency deviation vector, calculate the comprehensive environmental state confidence factor of the basic spatial unit where monitoring nodes cannot be deployed between two adjacent sampling period nodes; preset a threshold, analyze and issue an early warning.

[0013] As a preferred embodiment of the intelligent remote environmental monitoring method for aquaculture farms described in this invention, the specific implementation process of step S1 includes:

[0014] Obtain the site structure and equipment layout diagram of the breeding farm; based on the equipment layout diagram, identify areas with dense equipment; and define the overall spatial area of ​​the breeding farm according to the site structure. Then, use grid partitioning technology to divide the overall spatial area of ​​the breeding farm into several basic spatial units.

[0015] Set basic spatial unit constraints, and based on these constraints, filter the basic spatial units and set monitoring nodes, as follows:

[0016] The basic spatial unit constraints include physical occlusion constraints. Maintaining interference constraints and environmental disturbance high interference area constraints ;

[0017] If a fixed device exists within the basic spatial unit, preventing the sensor from being installed, then set... Otherwise set ;

[0018] If the basic space unit is located on the main passageway for animal keepers and the regular washing path, then set Otherwise set ;

[0019] If the basic space unit contains high-power devices, then set Otherwise set ;

[0020] like Monitoring nodes are then deployed within the basic spatial unit, and wind speed sensors and temperature and humidity sensors are deployed at the monitoring nodes. One basic spatial unit corresponds to one monitoring node, and one monitoring node corresponds to one wind speed sensor and one temperature and humidity sensor.

[0021] As a preferred embodiment of the intelligent remote environmental monitoring method for aquaculture farms described in this invention, the specific implementation process of step S2 includes:

[0022] Based on the aforementioned basic spatial unit constraints, a set of basic spatial units to which monitoring nodes cannot be deployed is constructed, as follows:

[0023] Construct a set of basic spatial units where monitoring nodes cannot be deployed, if If a basic spatial unit is determined to be a basic spatial unit where monitoring nodes cannot be deployed, it is added to the set of basic spatial units where monitoring nodes cannot be deployed, and this set is denoted as . ,in, Let A represent the basic spatial unit where the a-th monitoring node cannot be deployed, and let A represent the total number of basic spatial units where monitoring nodes cannot be deployed. , and These represent the physical occlusion constraints, maintenance interference constraints, and environmental disturbance high-interference area constraints corresponding to the basic spatial unit where the a-th monitoring node cannot be deployed.

[0024] Let the basic spatial unit where the b-th monitoring node can be deployed be denoted as . Using hours as the unit, construct sampling time period nodes, and collect the basic spatial units within the i-th sampling period node respectively. The wind speed, temperature, and humidity data from the monitoring nodes within the area are normalized and recorded as follows: , and .

[0025] As a preferred embodiment of the intelligent remote environmental monitoring method for aquaculture farms described in this invention, the specific implementation process of step S3 further includes:

[0026] Basic spatial units where monitoring nodes cannot be deployed Basic spatial unit with deployable monitoring nodes If a shared physical boundary exists, then the basic spatial unit where monitoring nodes can be deployed will be available. The basic spatial unit that cannot be used to deploy monitoring nodes is denoted as [the basic spatial unit]. Adjacent deployable units are used to construct basic spatial units where monitoring nodes cannot be deployed. The set of adjacent deployable units;

[0027] Basic spatial unit based on non-deployable monitoring nodes The set of adjacent deployable cells is used to obtain wind speed, temperature, and humidity data for all adjacent deployable cells, and then a weighted summation and average is performed.

[0028] Calculate the basic spatial unit where monitoring nodes cannot be deployed. Indirect wind speed estimate, indirect temperature estimate, and indirect humidity estimate within the node of the i-th sampling period;

[0029] Basic spatial unit based on non-deployable monitoring nodes Based on the indirect wind speed estimate, indirect temperature estimate, and indirect humidity estimate within the node of the i-th sampling period, a basic spatial unit for which monitoring nodes cannot be deployed is constructed. The state estimation vector within the node of the i-th sampling period is denoted as... ,in, This represents the indirect wind speed estimate. This represents an indirect temperature estimate. This represents an indirect humidity estimate.

[0030] As a preferred embodiment of the intelligent remote environmental monitoring method for aquaculture farms described in this invention, the specific implementation process of step S4 includes:

[0031] Basic spatial unit based on non-deployable monitoring nodes State estimation vector within the node of the i-th sampling period Calculate the basic spatial unit where monitoring nodes cannot be deployed. The estimated vector of state changes between the node in the i-th sampling period and the node in the (i+1)-th sampling period is calculated using the following formula: ,in, This represents the state change estimation vector. Basic spatial unit representing the location where monitoring nodes cannot be deployed The state estimation vector within the (i+1)th sampling period node.

[0032] As a preferred embodiment of the intelligent remote environmental monitoring method for aquaculture farms described in this invention, the specific implementation process of step S5 includes:

[0033] Basic spatial unit based on non-deployable monitoring nodes The set of adjacent deployable units, and the basic spatial units where monitoring nodes cannot be deployed are preset. Adjacent deployable units Physical structural similarity between Similarity to environmental function And calculate the basic spatial unit where monitoring nodes cannot be deployed. Adjacent deployable units The spatial similarity factor between them is calculated using the following formula:

[0034] ;

[0035] in, Basic spatial unit representing the location where monitoring nodes cannot be deployed Adjacent deployable units Spatial similarity factor between them and These represent the weights of the influencing indicators for physical structure similarity and environmental functional similarity, respectively.

[0036] Obtain the basic spatial unit where monitoring nodes cannot be deployed. Spatial similarity factors with all adjacent deployable units, combined with state change estimation vectors. Calculate the average vector of state changes of all adjacent deployable units, denoted as . ;

[0037] Estimated vector of state change Average vector of state changes of all adjacent deployable units Subtracting them, we construct the estimation error offset vector, denoted as... .

[0038] As a preferred embodiment of the intelligent remote environmental monitoring method for aquaculture farms described in this invention, the specific implementation process of step S6 includes:

[0039] Obtain the average change in wind speed data for all adjacent deployable cells between the i-th sampling period node and the (i+1)-th sampling period node. Average change in temperature data and average change in humidity data And construct a reference vector for actual meteorological changes, denoted as ;

[0040] Estimated vector of state change Reference vector of actual meteorological changes Subtracting them, we construct a consistency deviation vector, denoted as... ;

[0041] Based on the estimation error offset vector Consistency Deviation Vector Calculate the basic spatial unit where monitoring nodes cannot be deployed. The comprehensive environmental state confidence factor between the i-th sampling period node and the (i+1)-th sampling period node is calculated using the following formula:

[0042] ;

[0043] in, Basic spatial unit representing the location where monitoring nodes cannot be deployed The comprehensive environmental state confidence factor between the i-th sampling period node and the (i+1)-th sampling period node. and This represents the influence factor between the preset estimation error offset vector and the consistency deviation vector. Denotes the Euclidean norm;

[0044] The preset comprehensive environmental state confidence factor threshold is used as the basic spatial unit for which monitoring nodes cannot be deployed. The comprehensive environmental state confidence factor between the i-th sampling period node and the (i+1)-th sampling period node If the confidence factor threshold of the comprehensive environmental state is greater than or equal to the threshold value, then the basic spatial unit is determined to be unsuitable for deploying monitoring nodes. If there is an environmental deviation between the i-th sampling period node and the (i+1)-th sampling period node, an early warning will be issued to the relevant staff.

[0045] Secondly, embodiments of the present invention provide a smart remote environmental monitoring system for aquaculture farms, comprising a unit division and node deployment module for dividing the overall spatial area of ​​the aquaculture farm into several basic spatial units; setting constraints on the basic spatial units and deploying monitoring nodes within the basic spatial units that meet the constraints; a set and period construction module for constructing a set of basic spatial units where monitoring nodes cannot be deployed; constructing sampling time period nodes in hours; and an estimation value and estimation vector calculation module for constructing a set of adjacent deployable units of the basic spatial units where monitoring nodes cannot be deployed; calculating the indirect wind speed estimate, indirect temperature estimate, and indirect humidity estimate of the basic spatial units where monitoring nodes cannot be deployed within a single sampling period node, and constructing a state. The system includes: an estimation vector calculation module for state change estimation vectors; a state change estimation vector calculation module for calculating the state change estimation vector of a basic spatial unit without deployable monitoring nodes between two adjacent sampling period nodes; a state change estimation vector and estimation error offset vector calculation module for calculating the spatial similarity factor between the basic spatial unit without deployable monitoring nodes and adjacent deployable units, and calculating the average state change vector and estimation error offset vector by combining the state change estimation vector; a confidence factor calculation, analysis, and early warning module for constructing a consistency deviation vector; calculating the comprehensive environmental state confidence factor of the basic spatial unit without deployable monitoring nodes between two adjacent sampling period nodes based on the estimation error offset vector and the consistency deviation vector; and setting a preset threshold for analysis and early warning.

[0046] Thirdly, embodiments of the present invention provide a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, they implement the steps of a smart remote environmental monitoring method for a livestock farm as described in the first aspect of the present invention.

[0047] Fourthly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, they implement the steps of a smart remote environmental monitoring method for a farm as described in the first aspect of the present invention.

[0048] The beneficial effects of this invention are as follows: By dividing the farm into multiple basic spatial units and setting constraints such as physical shielding, maintenance interference, and environmental disturbance, the deployment area of ​​monitoring nodes is rationally planned, achieving the construction of a highly reliable and low-interference data acquisition network; further, a spatial set of non-deployable monitoring nodes is constructed and sampling time period nodes are introduced to standardize the temporal and spatial structure of monitoring data, providing basic support for the state estimation of non-deployable areas; based on this, wind speed, temperature, and humidity data from adjacent deployable units are used to indirectly estimate the environmental state of non-deployable areas, and state estimation vectors and state change estimation vectors are constructed, realizing dynamic environmental modeling of inaccessible areas; subsequently, physical structure similarity and environmental function similarity are introduced to calculate spatial similarity factors, and combined with the average state change vector, estimation error offset vector is further calculated to correct the spatial rationality of the indirect estimation results; finally, by introducing actual meteorological change reference vectors, a consistency deviation vector is constructed, and estimation error offset and consistency deviation are fused to calculate a comprehensive environmental state confidence factor, judge environmental anomalies, and issue early warnings, achieving high-precision and continuous assessment and intelligent early warning of the environmental state of non-deployable areas, thereby improving the spatial coverage, monitoring accuracy, and risk response efficiency of the entire farm environmental monitoring system. Attached Figure Description

[0049] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying 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.

[0050] Figure 1 This is a schematic diagram illustrating the steps of a smart remote environmental monitoring method for livestock farms.

[0051] Figure 2 This is a schematic diagram of a smart remote environmental monitoring system for aquaculture farms. Detailed Implementation

[0052] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0053] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0054] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0055] Reference Figures 1-2 This is one embodiment of the present invention, which provides a smart remote environmental monitoring method for aquaculture farms, including:

[0056] Step S1: Divide the overall space of the farm into several basic spatial units; set constraints for the basic spatial units, and deploy monitoring nodes within the basic spatial units that meet the constraints.

[0057] Specifically, the site structure and equipment layout of the farm are obtained; based on the equipment layout, densely populated equipment areas are identified; and the overall spatial area of ​​the farm is defined according to the site structure. Using grid partitioning technology, the overall spatial area of ​​the farm is divided into several basic spatial units.

[0058] Set basic spatial unit constraints, and based on these constraints, filter the basic spatial units and set monitoring nodes, as follows:

[0059] The basic spatial unit constraints include physical occlusion constraints. Maintaining interference constraints and environmental disturbance high interference area constraints ;

[0060] If a fixed device exists within the basic spatial unit, preventing the sensor from being installed, then set... Otherwise set ;

[0061] If the basic space unit is located on the main passageway for animal keepers and the regular washing path, then set Otherwise set ;

[0062] If the basic space unit contains high-power devices, then set Otherwise set ;

[0063] like Monitoring nodes are then deployed within the basic spatial unit, and wind speed sensors and temperature and humidity sensors are deployed at the monitoring nodes. One basic spatial unit corresponds to one monitoring node, and one monitoring node corresponds to one wind speed sensor and one temperature and humidity sensor.

[0064] In this invention, step S1 finely divides the overall space of the aquaculture farm into several basic spatial units, and sets constraints including physical obstruction, maintenance interference, and environmental disturbance. The deployability of each basic unit is then assessed, enabling the scientific selection and optimization of sensor deployment areas in complex aquaculture environments. This mechanism ensures that monitoring nodes avoid interference sources and physical obstacles, improving the stability and reliability of data acquisition from the source, avoiding monitoring errors or equipment damage caused by improper location selection, and ultimately achieving a high-efficiency, low-interference sensing network deployment effect.

[0065] Step S2: Construct a set of basic spatial units where monitoring nodes cannot be deployed; construct sampling time period nodes in hours.

[0066] Specifically, based on the aforementioned basic spatial unit constraints, a set of basic spatial units to which monitoring nodes cannot be deployed is constructed, as follows:

[0067] Construct a set of basic spatial units where monitoring nodes cannot be deployed, if If a basic spatial unit is determined to be a basic spatial unit where monitoring nodes cannot be deployed, it is added to the set of basic spatial units where monitoring nodes cannot be deployed, and this set is denoted as . ,in, Let A represent the basic spatial unit where the a-th monitoring node cannot be deployed, and let A represent the total number of basic spatial units where monitoring nodes cannot be deployed. , and These represent the physical occlusion constraints, maintenance interference constraints, and environmental disturbance high-interference area constraints corresponding to the basic spatial unit where the a-th monitoring node cannot be deployed.

[0068] Let the basic spatial unit where the b-th monitoring node can be deployed be denoted as . Using hours as the unit, construct sampling time period nodes, and collect the basic spatial units within the i-th sampling period node respectively. The wind speed, temperature, and humidity data from the monitoring nodes within the area are normalized and recorded as follows: , and .

[0069] In this invention, a spatial set of monitoring nodes that cannot be deployed is constructed, and sampling time period nodes are introduced, enabling the standardization of the time series of environmental monitoring data collection and the identification of spatial distribution differences. While ensuring deployment safety and operational convenience, this lays a unified foundation for the data structure and time axis of subsequent state estimation of non-deployable areas, thereby effectively improving the adaptability and timeliness of the environmental estimation model.

[0070] Step S3: Construct the set of adjacent deployable units of the basic spatial unit that cannot be equipped with monitoring nodes; calculate the indirect wind speed estimate, indirect temperature estimate, and indirect humidity estimate of the basic spatial unit that cannot be equipped with monitoring nodes within a single sampling period node, and construct the state estimation vector.

[0071] Specifically, if it is not possible to deploy monitoring nodes in the basic spatial unit Basic spatial unit with deployable monitoring nodes If a shared physical boundary exists, then the basic spatial unit where monitoring nodes can be deployed will be available. The basic spatial unit that cannot be used to deploy monitoring nodes is denoted as [the basic spatial unit]. Adjacent deployable units are used to construct basic spatial units where monitoring nodes cannot be deployed. The set of adjacent deployable units;

[0072] Basic spatial unit based on non-deployable monitoring nodes The set of adjacent deployable units is used to obtain wind speed, temperature, and humidity data for all adjacent deployable units. These data are then weighted, summed, and averaged to calculate the basic spatial unit from which monitoring nodes cannot be deployed. Indirect wind speed estimate, indirect temperature estimate, and indirect humidity estimate within the node of the i-th sampling period;

[0073] Basic spatial unit based on non-deployable monitoring nodes Based on the indirect wind speed estimate, indirect temperature estimate, and indirect humidity estimate within the node of the i-th sampling period, a basic spatial unit for which monitoring nodes cannot be deployed is constructed. The state estimation vector within the node of the i-th sampling period is denoted as... ,in, This represents the indirect wind speed estimate. This represents an indirect temperature estimate. This represents an indirect humidity estimate.

[0074] In this invention, a weighted average of wind speed, temperature, and humidity data between non-deployable monitoring nodes and their adjacent deployable units sharing a physical boundary is used to achieve indirect environmental state estimation for non-deployable areas. This method establishes a virtual sensing mechanism for inaccessible areas without introducing additional hardware costs, significantly enhancing the system's perception coverage and completeness of environmental changes across the entire space, making it particularly suitable for complex and variable environments such as aquaculture farms.

[0075] Step S4: Based on the state estimation vector, calculate the state change estimation vector of the basic spatial unit where monitoring nodes cannot be deployed between two adjacent sampling period nodes.

[0076] Specifically, based on the basic spatial unit where monitoring nodes cannot be deployed. State estimation vector within the node of the i-th sampling period Calculate the basic spatial unit where monitoring nodes cannot be deployed. The estimated vector of state changes between the node in the i-th sampling period and the node in the (i+1)-th sampling period is calculated using the following formula: ,in, This represents the state change estimation vector. Basic spatial unit representing the location where monitoring nodes cannot be deployed The state estimation vector within the (i+1)th sampling period node.

[0077] In this invention, by constructing the difference in changes of state estimation vectors at different time points, a state change estimation vector is formed, thereby realizing dynamic evolution modeling of the environmental state of undeployable areas. Compared with static estimation methods, this step improves the system's response capability to sudden environmental fluctuations (such as sudden ventilation changes, local temperature rises, etc.), providing crucial time dimension support for subsequent deviation identification and early warning decisions.

[0078] Step S5: Calculate the spatial similarity factor between the basic spatial unit where monitoring nodes cannot be deployed and the adjacent deployable unit. Combine the state change estimation vector to calculate the average state change vector and the estimation error offset vector.

[0079] Specifically, based on the basic spatial unit where monitoring nodes cannot be deployed. The set of adjacent deployable units, and the basic spatial units where monitoring nodes cannot be deployed are preset. Adjacent deployable units Physical structural similarity between Similarity to environmental function And calculate the basic spatial unit where monitoring nodes cannot be deployed. Adjacent deployable units The spatial similarity factor between them is calculated using the following formula:

[0080] ;

[0081] in, Basic spatial unit representing the location where monitoring nodes cannot be deployed Adjacent deployable units Spatial similarity factor between them and These represent the weights of the influencing indicators for physical structure similarity and environmental functional similarity, respectively.

[0082] It should be noted that this formula incorporates physical structure similarity ( Such as wall material, space size) and similarity of environmental function ( (e.g., whether they belong to the same brooding area), by weight. and Weighted calculation of basic spatial units where monitoring nodes cannot be deployed Adjacent deployable units The similarity quantifies the degree of similarity between "unmeasurable areas" and "measurable areas," avoiding errors caused by simply taking the average (e.g., adjacent areas with different functions have large environmental differences, so the weight should be lower); the formula takes into account the characteristic that "physical structure and function determine environmental similarity" in the actual scenario of a farm (e.g., adjacent units in the same brooding area have similar temperature and humidity), and improves the accuracy of similarity assessment through weighted logic, providing a reasonable basis for the correction of subsequent estimates.

[0083] Among them, physical structure similarity Based on spatial structural attributes such as building materials, wall thickness, and shading and ventilation methods, structural labels are matched. The matching formula is for basic spatial units where monitoring nodes cannot be deployed. Adjacent deployable units The number of matching features between them divided by the number of basic spatial units where monitoring nodes cannot be deployed Total number of features, environmental functional similarity This is used to indicate the compatibility of spatial functions, such as whether they are both brooding areas or both exit passages. It is scored through expert evaluation; if the functions are the same, then... If the functions are similar, then record 1. The value is 0.5. If the functional differences are large, then it is recorded as 0.5. It is 0.

[0084] Obtain the basic spatial unit where monitoring nodes cannot be deployed. Spatial similarity factors with all adjacent deployable units, combined with state change estimation vectors. Calculate the average vector of state changes of all adjacent deployable units, denoted as . , where the average vector of state changes The calculation formula is as follows:

[0085] ;

[0086] in, Basic spatial unit representing the location where monitoring nodes cannot be deployed The set of adjacent deployable units, Represents the weight of the preset spatial similarity factor;

[0087] It should be noted that this formula uses spatial similarity factors. As weights, for basic spatial units where monitoring nodes cannot be deployed. The state change vector of all adjacent deployable units A weighted average is performed to obtain a reasonable reference change vector, which provides a benchmark for the state changes of non-deployable units based on the actual changes in similar areas, and is used to determine whether its estimated value deviates from the normal trend.

[0088] Estimated vector of state change Average vector of state changes of all adjacent deployable units Subtracting them, we construct the estimation error offset vector, denoted as... .

[0089] In this invention, by introducing physical structure similarity and environmental function similarity indices and calculating a spatial similarity factor, combined with the state change vector, the average state change vector and the estimation error offset vector are obtained, thereby achieving spatial rationality correction and error trend quantification of the indirect estimation results. This step not only improves the credibility of the estimated data but also enhances the model's understanding of local spatial distribution characteristics, effectively suppressing estimation offsets caused by non-uniform structures or differences in environmental function.

[0090] Step S6: Construct a consistency deviation vector; based on the estimated error offset vector and the consistency deviation vector, calculate the comprehensive environmental state confidence factor of the basic spatial unit where monitoring nodes cannot be deployed between two adjacent sampling period nodes; preset a threshold, analyze and issue an early warning.

[0091] Specifically, obtain the average change in wind speed data for all adjacent deployable units between the i-th sampling period node and the (i+1)-th sampling period node. Average change in temperature data and average change in humidity data And construct a reference vector for actual meteorological changes, denoted as ;

[0092] Estimated vector of state change Reference vector of actual meteorological changes Subtracting them, we construct a consistency deviation vector, denoted as... ;

[0093] Based on the estimation error offset vector Consistency Deviation Vector Calculate the basic spatial unit where monitoring nodes cannot be deployed. The comprehensive environmental state confidence factor between the i-th sampling period node and the (i+1)-th sampling period node is calculated using the following formula:

[0094] ;

[0095] in, Basic spatial unit representing the location where monitoring nodes cannot be deployed The comprehensive environmental state confidence factor between the i-th sampling period node and the (i+1)-th sampling period node. and This represents the influence factor between the preset estimation error offset vector and the consistency deviation vector. Denotes the Euclidean norm;

[0096] It should be noted that the estimation error offset vector is shifted using the Euclidean norm (quantization vector size). Consistency Deviation Vector Convert to a scalar, then use weights and Weighted summation yields the comprehensive confidence factor. This formula is used to determine whether the environment is abnormal. It integrates local similarity area deviation and global trend deviation to avoid the limitations of single-dimensional judgment. By using norm to transform the three-dimensional vector into a comparable scalar, it simplifies the threshold judgment logic and meets the actual needs of rapid early warning in farms.

[0097] The preset comprehensive environmental state confidence factor threshold is used as the basic spatial unit for which monitoring nodes cannot be deployed. The comprehensive environmental state confidence factor between the i-th sampling period node and the (i+1)-th sampling period node If the confidence factor threshold of the comprehensive environmental state is greater than or equal to the threshold value, then the basic spatial unit is determined to be unsuitable for deploying monitoring nodes. If there is an environmental deviation between the i-th sampling period node and the (i+1)-th sampling period node, an early warning will be issued to the relevant staff.

[0098] In this invention, the estimated error offset vector is fused with a consistency deviation vector constructed based on actual meteorological changes to calculate a comprehensive environmental state confidence factor. This factor, combined with a preset threshold, determines whether to issue an early warning, thus realizing a joint credibility assessment and intelligent early warning mechanism under multi-dimensional environmental factors. This strategy takes into account the deviation matching relationship between error trends and actual changes, avoiding false alarms or missed alarms caused by short-term fluctuations. This achieves a leap from data-driven to knowledge-driven monitoring of aquaculture environments, improving the system's overall effectiveness in intelligent risk identification and proactive intervention.

[0099] Furthermore, this embodiment also provides a smart remote environmental monitoring system for aquaculture farms, including: a unit division and node deployment module for dividing the overall spatial area of ​​the aquaculture farm into several basic spatial units; setting constraints on the basic spatial units and deploying monitoring nodes within the basic spatial units that meet the constraints; a set and period construction module for constructing a set of basic spatial units where monitoring nodes cannot be deployed; constructing sampling time period nodes in hours; and an estimation value and estimation vector calculation module for constructing a set of adjacent deployable units of the basic spatial units where monitoring nodes cannot be deployed; calculating the indirect wind speed estimate, indirect temperature estimate, and indirect humidity estimate of the basic spatial units where monitoring nodes cannot be deployed within a single sampling period node, and constructing a state estimate. The system includes: a state change estimation vector calculation module, used to calculate the state change estimation vector of the basic spatial unit of the non-monitoring node between two adjacent sampling period nodes based on the state estimation vector; a state change estimation vector and estimation error offset vector calculation module, used to calculate the spatial similarity factor between the basic spatial unit of the non-monitoring node and the adjacent deployable unit, and to calculate the average state change vector and estimation error offset vector by combining the state change estimation vector; a confidence factor calculation, analysis and early warning module, used to construct a consistency deviation vector; to calculate the comprehensive environmental state confidence factor of the basic spatial unit of the non-monitoring node between two adjacent sampling period nodes based on the estimation error offset vector and the consistency deviation vector; and to set a threshold, analyze and issue an early warning.

[0100] Referring to Table 1, there are two embodiments of the present invention. In this second embodiment, a smart remote environmental monitoring method for aquaculture farms is provided. To verify the beneficial effects of the present invention, a simulation experiment is conducted for scientific demonstration.

[0101] Suppose a broiler chicken farm is divided into basic spatial units of 10×10 (side length 2 meters), where... This is a unit that cannot be installed (due to the presence of high-power ventilation equipment). ,satisfy Then it is added to the set of basic spatial units where monitoring nodes cannot be deployed.

[0102] Basic spatial unit where monitoring nodes cannot be deployed The adjacent deployable units are and (There is a shared physical boundary), and the sampling period is 1 hour (from i= to i=2).

[0103] Table 1 Parameter Data

[0104]

[0105] Assuming physical structural similarity , ;

[0106] Environmental functional similarity , ;

[0107] , , , , ;

[0108] ;

[0109] ;

[0110] ;

[0111] ;

[0112] ;

[0113] ;

[0114] ;

[0115] ;

[0116] ;

[0117] ;

[0118] Assuming the confidence factor threshold for the overall environmental state is 0.25, then Then, the basic spatial unit that cannot be used to deploy monitoring nodes is determined. If there is an environmental deviation between the first and second sampling cycle nodes, an early warning will be issued to the relevant staff.

[0119] This embodiment also provides a computer device applicable to a smart remote environmental monitoring method for aquaculture farms, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize the smart remote environmental monitoring method for aquaculture farms as proposed in the above embodiment.

[0120] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0121] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements a smart remote environmental monitoring method for aquaculture farms as proposed in the above embodiments.

[0122] In summary, this invention divides the farm into multiple basic spatial units and sets constraints such as physical shielding, maintenance interference, and environmental disturbance, rationally planning the deployment area of ​​monitoring nodes to achieve the construction of a highly reliable and low-interference data acquisition network. Furthermore, it constructs a spatial set of undeployable monitoring nodes and introduces sampling time period nodes to standardize the temporal and spatial structure of monitoring data, providing fundamental support for state estimation of undeployable areas. Based on this, it indirectly estimates the environmental state of undeployable areas using wind speed, temperature, and humidity data from adjacent deployable units, and constructs state estimation vectors and state change estimation vectors, realizing dynamic environmental modeling of inaccessible areas. Subsequently, it introduces physical structure similarity and environmental function similarity to calculate spatial similarity factors, and combines this with the average state change vector to further calculate the estimation error offset vector, performing spatial rationality correction on the indirect estimation results. Finally, by introducing an actual meteorological change reference vector, it constructs a consistency deviation vector, integrates the estimation error offset and consistency deviation, calculates a comprehensive environmental state confidence factor, judges environmental anomalies, and issues early warnings. This achieves high-precision, continuous assessment and intelligent early warning of the environmental state of undeployable areas, thereby improving the spatial coverage, monitoring accuracy, and risk response efficiency of the entire farm environmental monitoring system.

[0123] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A smart remote environmental monitoring method for livestock farms, characterized in that: include: Step S1: Divide the overall space of the farm into several basic spatial units; Set basic spatial unit constraints, and deploy monitoring nodes within the basic spatial units that meet the constraints; Step S2: Construct a set of basic spatial units where monitoring nodes cannot be deployed; construct sampling time period nodes in hours; Step S3: Construct the set of adjacent deployable units of the basic spatial unit that cannot be equipped with monitoring nodes; calculate the indirect wind speed estimate, indirect temperature estimate, and indirect humidity estimate of the basic spatial unit that cannot be equipped with monitoring nodes within a single sampling period node, and construct the state estimation vector. Step S4: Based on the state estimation vector, calculate the state change estimation vector of the basic spatial unit where monitoring nodes cannot be deployed between two adjacent sampling period nodes; Step S5: Calculate the spatial similarity factor between the basic spatial unit where monitoring nodes cannot be deployed and the adjacent deployable unit. Combine the state change estimation vector to calculate the average state change vector and the estimation error offset vector. Step S6: Construct the consistency deviation vector; Based on the estimated error offset vector and the consistency deviation vector, calculate the comprehensive environmental state confidence factor of the basic spatial unit where monitoring nodes cannot be deployed between two adjacent sampling period nodes; Set preset thresholds, analyze data, and issue early warnings; Step S5 includes: Basic spatial unit based on non-deployable monitoring nodes The set of adjacent deployable units, and the basic spatial units where monitoring nodes cannot be deployed are preset. Adjacent deployable units Physical structural similarity between Similarity to environmental function And calculate the basic spatial unit where monitoring nodes cannot be deployed. Adjacent deployable units The spatial similarity factor between them is calculated using the following formula: ； in, Basic spatial unit representing the location where monitoring nodes cannot be deployed Adjacent deployable units Spatial similarity factor between them and These represent the weights of the influencing indicators for physical structure similarity and environmental functional similarity, respectively. Obtain the basic spatial unit where monitoring nodes cannot be deployed. Spatial similarity factors with all adjacent deployable units, combined with state change estimation vectors. Calculate the average vector of state changes of all adjacent deployable units, denoted as . ; Estimated vector of state change Average vector of state changes of all adjacent deployable units Subtracting them, we construct the estimation error offset vector, denoted as... .

2. The intelligent remote environmental monitoring method for aquaculture farms according to claim 1, characterized in that, Step S1 includes: Obtain the site structure and equipment layout diagram of the breeding farm; based on the equipment layout diagram, identify areas with dense equipment; and define the overall spatial area of ​​the breeding farm according to the site structure. Then, use grid partitioning technology to divide the overall spatial area of ​​the breeding farm into several basic spatial units. Set basic spatial unit constraints, and based on these constraints, filter the basic spatial units and set monitoring nodes, as follows: The basic spatial unit constraints include physical occlusion constraints. Maintaining interference constraints and environmental disturbance high interference area constraints ; If a fixed device exists within the basic spatial unit, preventing the sensor from being installed, then set... Otherwise set ; If the basic space unit is located on the main passageway for animal keepers and the regular washing path, then set Otherwise set ; If the basic space unit contains high-power devices, then set Otherwise set ; like Monitoring nodes are then deployed within the basic spatial unit, and wind speed sensors and temperature and humidity sensors are deployed at the monitoring nodes. One basic spatial unit corresponds to one monitoring node, and one monitoring node corresponds to one wind speed sensor and one temperature and humidity sensor.

3. The intelligent remote environmental monitoring method for aquaculture farms according to claim 2, characterized in that, Step S2 includes: Based on the aforementioned basic spatial unit constraints, a set of basic spatial units to which monitoring nodes cannot be deployed is constructed, as follows: Construct a set of basic spatial units where monitoring nodes cannot be deployed, if If a basic spatial unit is determined to be a basic spatial unit where monitoring nodes cannot be deployed, it is added to the set of basic spatial units where monitoring nodes cannot be deployed, and this set is denoted as . ,in, Let A represent the basic spatial unit where the a-th monitoring node cannot be deployed, and let A represent the total number of basic spatial units where monitoring nodes cannot be deployed. , and These represent the physical occlusion constraints, maintenance interference constraints, and environmental disturbance high-interference area constraints corresponding to the basic spatial unit where the a-th monitoring node cannot be deployed. Let the basic spatial unit where the b-th monitoring node can be deployed be denoted as . Using hours as the unit, construct sampling time period nodes, and collect the basic spatial units within the i-th sampling period node respectively. The wind speed, temperature, and humidity data from the monitoring nodes within the area are normalized and recorded as follows: , and .

4. The intelligent remote environmental monitoring method for aquaculture farms according to claim 3, characterized in that, Step S3 includes: Basic spatial units where monitoring nodes cannot be deployed Basic spatial unit with deployable monitoring nodes If a shared physical boundary exists, then the basic spatial unit where monitoring nodes can be deployed will be available. The basic spatial unit that cannot be used to deploy monitoring nodes is denoted as [the basic spatial unit]. Adjacent deployable units are used to construct basic spatial units where monitoring nodes cannot be deployed. The set of adjacent deployable units; Basic spatial unit based on non-deployable monitoring nodes The set of adjacent deployable units is used to obtain wind speed, temperature, and humidity data for all adjacent deployable units. These data are then weighted, summed, and averaged to calculate the basic spatial unit from which monitoring nodes cannot be deployed. Indirect wind speed estimate, indirect temperature estimate, and indirect humidity estimate within the node of the i-th sampling period; Basic spatial unit based on non-deployable monitoring nodes Based on the indirect wind speed estimate, indirect temperature estimate, and indirect humidity estimate within the node of the i-th sampling period, a basic spatial unit for which monitoring nodes cannot be deployed is constructed. The state estimation vector within the node of the i-th sampling period is denoted as... ,in, This represents the indirect wind speed estimate. This represents an indirect temperature estimate. This represents an indirect humidity estimate.

5. A smart remote environmental monitoring method for aquaculture farms according to claim 4, characterized in that, Step S4 includes: Basic spatial unit based on non-deployable monitoring nodes State estimation vector within the node of the i-th sampling period Calculate the basic spatial unit where monitoring nodes cannot be deployed. The estimated vector of state changes between the node in the i-th sampling period and the node in the (i+1)-th sampling period is calculated using the following formula: ,in, This represents the state change estimation vector. Basic spatial unit representing the location where monitoring nodes cannot be deployed The state estimation vector within the (i+1)th sampling period node.

6. The intelligent remote environmental monitoring method for aquaculture farms according to claim 5, characterized in that, Step S6 includes: Obtain the average change in wind speed data for all adjacent deployable cells between the i-th sampling period node and the (i+1)-th sampling period node. Average change in temperature data and average change in humidity data And construct a reference vector for actual meteorological changes, denoted as ; Estimated vector of state change Reference vector of actual meteorological changes Subtracting them, we construct a consistency deviation vector, denoted as... ; Based on the estimation error offset vector Consistency Deviation Vector Calculate the basic spatial unit where monitoring nodes cannot be deployed. The comprehensive environmental state confidence factor between the i-th sampling period node and the (i+1)-th sampling period node is calculated using the following formula: ； in, Basic spatial unit representing the location where monitoring nodes cannot be deployed The comprehensive environmental state confidence factor between the i-th sampling period node and the (i+1)-th sampling period node. and This represents the influence factor between the preset estimation error offset vector and the consistency deviation vector. Denotes the Euclidean norm; The preset comprehensive environmental state confidence factor threshold is used as the basic spatial unit for which monitoring nodes cannot be deployed. The comprehensive environmental state confidence factor between the i-th sampling period node and the (i+1)-th sampling period node If the confidence factor threshold of the comprehensive environmental state is greater than or equal to the threshold value, then the basic spatial unit is determined to be unsuitable for deploying monitoring nodes. If there is an environmental deviation between the i-th sampling period node and the (i+1)-th sampling period node, an early warning will be issued to the relevant staff.

7. A smart remote environmental monitoring system for aquaculture farms, based on the smart remote environmental monitoring method for aquaculture farms as described in any one of claims 1 to 6, characterized in that: Also includes: The unit division and node layout module is used to divide the overall spatial area of ​​the farm into several basic spatial units; Set basic spatial unit constraints, and deploy monitoring nodes within the basic spatial units that meet the constraints; The set and period construction module is used to construct a set of basic spatial units where monitoring nodes cannot be deployed; and to construct sampling time period nodes in hours. The estimation value and estimation vector calculation module is used to construct the set of adjacent deployable units of the basic spatial unit of the non-deployable monitoring node; calculate the indirect wind speed estimate, indirect temperature estimate, and indirect humidity estimate of the basic spatial unit of the non-deployable monitoring node within a single sampling period node, and construct the state estimation vector. The state change estimation vector calculation module is used to calculate the state change estimation vector of the basic spatial unit where monitoring nodes cannot be deployed between two adjacent sampling period nodes based on the state estimation vector. The module for calculating the state change estimation vector and the estimation error offset vector is used to calculate the spatial similarity factor between the basic spatial unit where monitoring nodes cannot be deployed and the adjacent deployable unit. Combined with the state change estimation vector, it calculates the average state change vector and the estimation error offset vector. The confidence factor calculation and analysis early warning module is used to construct the consistency deviation vector; based on the estimation error offset vector and the consistency deviation vector, it calculates the comprehensive environmental state confidence factor of the basic spatial unit where monitoring nodes cannot be deployed between two adjacent sampling period nodes. Set preset thresholds, analyze data, and issue early warnings; The module for calculating the state change estimation vector and estimation error offset vector includes: Basic spatial unit based on non-deployable monitoring nodes The set of adjacent deployable units, and the basic spatial units where monitoring nodes cannot be deployed are preset. Adjacent deployable units Physical structural similarity between Similarity to environmental function And calculate the basic spatial unit where monitoring nodes cannot be deployed. Adjacent deployable units The spatial similarity factor between them is calculated using the following formula: ； in, Basic spatial unit representing the location where monitoring nodes cannot be deployed Adjacent deployable units Spatial similarity factor between them and These represent the weights of the influencing indicators for physical structure similarity and environmental functional similarity, respectively. Obtain the basic spatial unit where monitoring nodes cannot be deployed. Spatial similarity factors with all adjacent deployable units, combined with state change estimation vectors. Calculate the average vector of state changes of all adjacent deployable units, denoted as . ; Estimated vector of state change Average vector of state changes of all adjacent deployable units Subtracting them, we construct the estimation error offset vector, denoted as... .

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the intelligent remote environmental monitoring method for aquaculture farms as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the intelligent remote environmental monitoring method for aquaculture farms as described in any one of claims 1 to 6.

Images