Online detection system and method for water content of rice based on Internet of Things

Abstract

The invention relates to the technical field of rice moisture content detection, in particular to a rice moisture content online detection system and method based on the Internet of Things, and the method comprises the steps: real-time detection of soil moisture content of different levels of a rice field is realized through deployment of a three-dimensional layered sensor network, and rice growth data is acquired through infrared thermal imaging; data fusion is carried out based on the water content of the rice field, and online detection of the water content of the rice is carried out according to the fused three-dimensional space-time matrix. The depth of the sensor is dynamically adjusted through the three-dimensional layered sensor network and the root growth cycle, it is ensured that water monitoring can cover all growth layers of rice, and more accurate water state data are provided; and on the basis of a water flow and absorption equation model, absorption and dynamic change of rice water can be accurately simulated, so that real-time monitoring of the rice water content is realized, and reduction of water resource waste is facilitated.

Description

Technical Field

[0001] The present invention relates to the technical field of rice moisture content detection, and in particular to an Internet of Things-based rice moisture content online detection system and method. Background Art

[0002] With the increasing population, rice has become the main food source. Therefore, monitoring the growth of rice is becoming increasingly important, especially monitoring the moisture content of rice during its growth. However, at present, the detection of rice moisture content faces the following difficulties:

[0003] Focusing only on the surface soil or rice stems and leaves, it is impossible to obtain real-time moisture gradient data in the root zone and deep soil, resulting in incomplete analysis of water absorption paths;

[0004] The fixed deployment of the sensor network cannot adapt to the dynamic expansion of the rice root system during the growth cycle (such as the tillering stage to the booting stage), resulting in monitoring blind spots;

[0005] Relying on a single type of sensor (such as a dielectric constant sensor), it lacks the integration of multi-source data such as transpiration rate and temperature gradient, and the detection accuracy is greatly affected by environmental interference;

[0006] Traditional methods require manual intervention or offline analysis, making it difficult to provide immediate decision support for precision irrigation. Summary of the Invention

[0007] In view of the above-mentioned problems, the present invention is proposed.

[0008] In order to solve the above technical problems, the present invention provides the following technical solutions: an online detection method for rice moisture content based on the Internet of Things, comprising the following steps:

[0009] By deploying a three-dimensional layered sensor network, we can achieve real-time detection of soil moisture content at different levels of the rice field. Specifically:

[0010] Multiple sensors are deployed in rice fields to build a three-dimensional sensor network. The sensor distribution density is dynamically adjusted based on the density of the rice root system. A hierarchical network topology optimization is performed based on a dynamic ad hoc network protocol. The moisture content of the paddy soil is calculated based on the data collected by the sensors and constructed into a three-dimensional spatiotemporal matrix. The sensor monitoring depth is dynamically adjusted based on the depth of the rice root system.

[0011] Rice growth data is collected through infrared thermal imaging and fused based on the moisture content of the rice fields. Specifically:

[0012] The transpiration rate and evaporation rate of rice are calculated based on the data collected by the infrared sensor. Then, the spatiotemporal weights are calculated using the weight factors regulated by environmental changes and the spatiotemporal weighting factors. The data are fused based on the calculated spatiotemporal weights.

[0013] By constructing the water transfer equation and water absorption equation in rice, and setting the water transfer loss coefficient to make a positive correction to the water transfer equation, real-time online detection of rice moisture content can be achieved based on the data ratio between the constructed equation and the paddy field soil.

[0014] As a preferred solution of the online rice moisture content detection method based on the Internet of Things of the present invention, the three-dimensional sensor network is specifically as follows:

[0015] Set the deployment coordinates of the 3D sensor network (x i ,y i ,z i ), and satisfy the formula:

[0016] S={(x i ,y i ,z k )|x i ∈[0,L x ],y i ∈[0,L y ],z i ∈{20,50,80}}

[0017] Where S represents a three-dimensional sensor network, (x i ,y i ,z i ) represents the sensor coordinates in the sensor network, L x 、L y Respectively represent the maximum length and width of the rice field, z i Indicates the vertical depth, which is the divided sensing layer, (x i ,y i ) represents the positioning coordinate information carried by the sensor;

[0018] For the divided sensor layers, the sensor density of each sensor layer is dynamically regulated by the rice root density, specifically:

[0019]

[0020] Where N0 represents the number of initial sensor deployments, α and β represent the fitting parameters of rice root distribution, and ρ(z) represents the sensor density at level z.

[0021] As a preferred solution of the online rice moisture content detection method based on the Internet of Things of the present invention, the hierarchical network topology optimization based on the dynamic self-organizing network protocol is specifically as follows:

[0022] Set the sensor node set N = {n1,n2,...,n k}, where n k represents the sensor of the kth node;

[0023] At the same time, set node n i With node n j The distance d ij , and the distance between nodes satisfies the formula d ij <d max , where d max Indicates the maximum communication distance between nodes, which is set based on historical nodes;

[0024] The topological structure of IoT communication is reflected by the adjacency matrix, and the adjacency matrix A[i][j]=1 is used to represent node n i With node n j They can communicate directly, using the adjacency matrix A[i][j]=0 to represent node n i With node n j There is no direct communication between them, and the communication relationship between nodes is represented by the adjacency matrix in turn until the adjacency relationship between all nodes in the sensor node set is terminated. At this time, the communication relationship between all nodes is a hierarchical topology structure between each sensor node in the hierarchical network.

[0025] As a preferred embodiment of the online detection method of rice moisture content based on the Internet of Things of the present invention, the calculation of the moisture content of paddy soil based on the data collected by the sensor is as follows:

[0026] The input variables are the dielectric constant ε(z i ,t) and temperature gradient data Calculate the real-time soil moisture content of the paddy field based on the input variables, then:

[0027]

[0028] Among them, a, b, c represent paddy field calibration parameters, ε(z i ,t) represents level z i The dielectric constant at time t is, Indicates level z i Temperature gradient data at time t, Δz i represents the difference step size, θ(z i ,t) represents level z i Soil moisture content at time t;

[0029] According to the calculated moisture content of paddy soil, a three-dimensional space-time matrix is ​​constructed, and then,

[0030]

[0031] Among them, θ(zi ,t) represents level z i The soil moisture content at time t, (x i ,y i ) represents the positioning coordinate information carried by the sensor, d represents the distance between sensor nodes, σ represents the spatial correlation radius, and M(x, y, z, t) represents the constructed three-dimensional space-time matrix, which is used to monitor the soil moisture content of the paddy field corresponding to the current sensor position based on the data collected by sensors at different positions at time t.

[0032] As a preferred solution of the online rice moisture content detection method based on the Internet of Things of the present invention, the dynamic adjustment of the sensor monitoring depth according to the rice root depth is specifically as follows:

[0033] Based on the root distribution characteristics of the rice growth cycle, a root depth-time function is constructed. The rice growth cycle includes the tillering stage and the booting stage. The specific function is as follows:

[0034]

[0035] Among them, l(T GS ) represents the depth of the dominant root layer of rice, which is used to control the monitoring depth of the sensor array. l0 represents the initial root depth of rice in the tillering stage. l1 represents the initial root depth of rice in the booting stage. k1 and k2 represent the root growth rates of rice in the tillering stage and the booting stage, respectively. T1 and T2 represent the end time of the tillering stage and the end time of the booting stage, respectively. T GS Indicates rice production stage;

[0036] According to the constructed function, the monitoring depth of the sensor is dynamically adjusted, specifically:

[0037] For the sensor's monitoring depth z i ,When monitoring the water absorption dynamics of rice roots in the root ,zone, the monitoring depth is dynamically adjusted according to the ,growth cycle of the root system, so that the monitoring depth of the sensor does not exceed the ,depth of the root system.

[0038] As a preferred solution of the online rice moisture content detection method based on the Internet of Things of the present invention, the data fusion is realized according to the calculated spatiotemporal weights as follows:

[0039] For transpiration rate and evaporation rate, set the weight factor as well as The set weight factors are dynamically adjusted by the implementer based on environmental changes and the stability of the sensor signal. Specifically:

[0040] If the meteorological data changes abnormally, the weight factor is increased, otherwise the weight factor is reduced;

[0041] For the rice growth levels in space, the weight coefficient is adaptively adjusted according to the influencing factors of each level;

[0042] According to the set weight coefficient and combined with the spatiotemporal weighting factor, the spatiotemporal weight after fusion is calculated, then,

[0043]

[0044] Among them, w f(x,y,z,t) represents the fused spatiotemporal weight, represents the weight factor of transpiration rate, Represents the weight factor of evaporation rate, w M(x,y,z,t) represents the weight coefficient of the three-dimensional space-time matrix, and γ represents the space-time weighting factor;

[0045] Based on the calculated fusion spatiotemporal weights, the three-dimensional fusion of the spatiotemporal matrix constructed by rice transpiration rate and evaporation rate is realized, then,

[0046] M f(x,y,z,t) =w f(x,y,z,t) E(x,y,t)

[0047] Among them, M f(x,y,z,t) represents the fused three-dimensional spatiotemporal matrix, which includes rice transpiration rate, evaporation rate and paddy field moisture content data, w f(x,y,z,t) represents the fused spatiotemporal weight, and E(x, y, t) represents the spatiotemporal matrix constructed by rice transpiration rate and evaporation rate.

[0048] As a preferred embodiment of the method for online detection of rice moisture content based on the Internet of Things of the present invention, the real-time online detection of rice moisture content is specifically as follows:

[0049] Based on the constructed water transfer equation and water absorption equation, online detection of rice moisture content is achieved, specifically:

[0050]

[0051] Among them, f1 represents the rice water transfer equation, f2 represents the overall rice water absorption equation, δ represents the water loss coefficient during the transfer process, M(x, y, z, t) represents the paddy field soil moisture data, and W represents the calculated rice moisture content, which is used to realize real-time online detection of rice moisture content.

[0052] An Internet of Things-based online rice moisture detection system includes a data acquisition module, a data fusion module, and a moisture detection module. The data acquisition module collects data related to the rice growth environment and moisture from multiple sensors. The data fusion module reduces the error of a single data source by combining a physical model with measured soil data. The moisture detection module achieves efficient detection of rice moisture through precise data modeling and real-time prediction.

[0053] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of an online rice moisture content detection method based on the Internet of Things when executing the computer program.

[0054] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of an online rice moisture content detection method based on the Internet of Things.

[0055] Beneficial effects of the present invention:

[0056] The present invention uses a three-dimensional layered sensor network and dynamically adjusts the sensor depth according to the root growth cycle to ensure that moisture monitoring can cover all growth layers of rice and provide more accurate moisture status data;

[0057] Based on dynamic adjustment of sensor depth and adaptive IoT protocol, it can adapt to different growth stages and environmental changes, improve the flexibility and stability of the system, and ensure the real-time and reliability of data;

[0058] By integrating multimodal data and factors such as transpiration and evaporation rates, a more comprehensive analysis of rice water status can be provided, providing strong support for precision irrigation and agricultural decision-making.

[0059] Based on the model of water flow and absorption equations, the absorption and dynamic changes of rice water can be accurately simulated, thereby realizing real-time monitoring of rice moisture content, helping to reduce water waste and optimize irrigation and management measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort. Among them:

[0061] Figure 1 This is a schematic diagram of the overall method steps of an online rice moisture content detection method based on the Internet of Things of the present invention. DETAILED DESCRIPTION

[0062] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0063] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0064] Secondly, the term "one embodiment" or "embodiment" 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 various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0065] The present invention is described in detail with reference to schematic diagrams. For ease of illustration, cross-sectional views of device structures may be partially enlarged and not to scale when describing embodiments of the present invention. Furthermore, the schematic diagrams are merely illustrative and should not limit the scope of the present invention. Furthermore, in actual production, the three-dimensional dimensions of length, width, and depth should be included.

[0066] At the same time, in the description of the present invention, it should be noted that the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0067] In this disclosure, unless otherwise specified or limited, the terms "mounted," "connected," and "connected" should be interpreted broadly. For example, they may refer to fixed, removable, or integral connections. They may also refer to mechanical, electrical, or direct connections, indirect connections through an intermediary, or internal communication between two components. Those skilled in the art will understand the specific meanings of these terms in this disclosure.

[0068] Example 1

[0069] Reference Figure 1 , as an embodiment of the present invention, provides an online detection method for rice moisture content based on the Internet of Things, comprising the following steps:

[0070] S1: Through the deployment of a three-dimensional hierarchical sensor network, real-time detection of soil moisture content at different levels of the rice field is achieved.

[0071] Specifically, the deployment of the three-dimensional hierarchical sensor network is based on a vertical hierarchical detection architecture, dividing the rice field into three sensing layers: the canopy layer for monitoring the moisture content of rice stems and leaves, the root zone for monitoring the dynamics of water absorption by the rice main root system, and the deep layer for monitoring the soil water potential gradient. In addition, sensors with positioning functions are deployed in each sensing layer to collect rice data at each layer. At the same time, data between sensors at different layers is transmitted through autonomous communication of the Internet of Things. The specific implementation is as follows:

[0072] Set the deployment coordinates of the 3D sensor network (x i ,y i ,z i ), and satisfy the formula:

[0073] S={(x i ,y i ,z k )|x i ∈[0,L x ],y i ∈[0,L y ],z i ∈{20,50,80}}

[0074] Where S represents a three-dimensional sensor network, (x i ,y i ,z i ) represents the sensor coordinates in the sensor network, L x 、L y Respectively represent the maximum length and width of the rice field, z i Indicates the vertical depth, which is the divided sensing layer, (x i ,y i ) represents the positioning coordinate information carried by the sensor;

[0075] For the divided sensor layers, the sensor density of each sensor layer is dynamically regulated by the rice root density, specifically:

[0076]

[0077] Where N0 represents the number of initial sensor deployments, α and β represent the fitting parameters of rice root distribution. In this embodiment, α = 0.1 cm -1 Taking β = 40 cm as an example, ρ(z) represents the sensor density at level z.

[0078] Furthermore, the autonomous communication of the Internet of Things is based on the dynamic self-organizing network protocol to achieve hierarchical network topology optimization, as follows:

[0079] Set the sensor node set N = {n1,n2,...,n k}, where n k represents the sensor of the kth node;

[0080] At the same time, set node n i With node n j The distance d ij , and the distance between nodes satisfies the formula d ij <d max , where d max Indicates the maximum communication distance between nodes, which is set based on historical nodes;

[0081] The topological structure of IoT communication is reflected by the adjacency matrix, and the adjacency matrix A[i][j]=1 is used to represent node n i With node n j They can communicate directly, using the adjacency matrix A[i][j]=0 to represent node n i With node n j There is no direct communication between them, and the communication relationship between nodes is represented by the adjacency matrix in turn until the adjacency relationship between all nodes in the sensor node set is terminated. At this time, the communication relationship between all nodes is a hierarchical topology structure between each sensor node in the hierarchical network.

[0082] Furthermore, the real-time detection of soil moisture content at different levels of the paddy field is to construct a three-dimensional moisture content matrix based on the data collected in real time by the sensor, as follows:

[0083] Sensors at different levels collect dielectric constant and temperature gradient data at each level, and use the collected data as input variables to calculate the real-time soil moisture content at each location in the paddy field. Based on the calculation results, a three-dimensional spatiotemporal matrix is ​​generated to realize the changing trend of soil moisture in the paddy field. Specifically:

[0084] The input variables are the dielectric constant ε(z i ,t) and temperature gradient data Calculate the real-time soil moisture content of the paddy field based on the input variables, then:

[0085]

[0086] Among them, a, b, c represent paddy field calibration parameters, ε(z i ,t) represents level z i The dielectric constant at time t is, Indicates level z i Temperature gradient data at time t, Δz irepresents the differential step size, which is set by the implementer according to the actual application scenario. i ,t) represents level z i Soil moisture content at time t;

[0087] According to the calculated moisture content of paddy soil, a three-dimensional space-time matrix is ​​constructed, and then,

[0088]

[0089] Among them, θ(z i ,t) represents level z i The soil moisture content at time t, (x i ,y i ) represents the positioning coordinate information carried by the sensor, d represents the distance between sensor nodes, σ represents the spatial correlation radius, which is set by the implementer according to the actual application scenario, and M(x, y, z, t) represents the constructed three-dimensional space-time matrix, which is used to monitor the soil moisture content of the paddy field corresponding to the current sensor position based on the data collected by sensors at different positions at time t.

[0090] It should be noted that through the three-dimensional hierarchical architecture and the generation of a three-dimensional space-time matrix, comprehensive monitoring and analysis of the water absorption path and changes in soil moisture status during rice growth can be achieved; through the self-organizing network protocol to support real-time adjustment of network topology, reliable transmission and processing of real-time data related to different environments can be achieved; through the mathematical model, soil moisture data and temperature data are combined to achieve all-round monitoring of rice field soil from the surface to the deep root zone.

[0091] It should be noted that for sensors deployed in the root system to monitor the water absorption dynamics of the rice main root, the deployment depth of the sensor array at the current level is dynamically adjusted according to the root depth of the rice growth cycle. The specific dynamic adjustment is as follows:

[0092] Based on the root distribution characteristics of the rice growth cycle, a root depth-time function is constructed. The rice growth cycle includes the tillering stage and the booting stage. The specific function is as follows:

[0093]

[0094] Among them, l(T GS) represents the depth of the dominant root layer of the rice, which is used to control the monitoring depth of the sensor array. l0 represents the initial root depth of the rice in the tillering stage. In this embodiment, the initial root depth of the rice in the tillering stage satisfies the formula 0≤l0≤15. l1 represents the initial root depth of the rice in the booting stage. In this embodiment, the initial root depth of the rice in the tillering stage satisfies the formula 15<l1≤30. k1 and k2 represent the root growth rates of the rice in the tillering stage and the booting stage, respectively. In this example, the root growth rates of the rice satisfy the formulas k1=0.5cm / day and k2=1.2cm / day. T1 and T2 represent the end time of the tillering stage and the end time of the booting stage, respectively. In this embodiment, the number of days from the end of the tillering stage and the end of the booting stage satisfy the formulas T1=30 and T2=60. GS Indicates the rice production stage, measured by direct observation;

[0095] According to the constructed function, the monitoring depth of the sensor is dynamically adjusted, specifically:

[0096] For the sensor's monitoring depth z i ,When monitoring the water absorption dynamics of rice roots in the root ,zone, the monitoring depth is dynamically adjusted according to the ,growth cycle of the root system, so that the monitoring depth of the sensor does not exceed the ,depth of the root system.

[0097] It should be noted that by dynamically adjusting the monitoring depth and flexibly adjusting the monitoring depth as the rice root system grows, it is ensured that the water absorption of rice can be accurately monitored, thereby improving the accuracy and adaptability of monitoring.

[0098] S2: Collect rice growth data through infrared thermal imaging and perform data fusion based on the moisture content of the rice field.

[0099] Specifically, the rice growth data collected by infrared thermal imaging is collected by infrared sensors deployed in the canopy, and the moisture status of the rice is calculated based on the collected data. The specific calculation is as follows:

[0100] Based on the collected temperature data, the transpiration rate of rice leaves is calculated as follows:

[0101] The canopy temperature T at each location is obtained by infrared sensors canopy (x, y, t), and ambient temperature data T e , and calculate the temperature difference between the two ΔT=T(x,y,t)-T e ;

[0102] According to the calculated temperature difference, the transpiration rate and evaporation rate of rice are calculated, then,

[0103]

[0104] According to the calculated temperature difference, the evaporation rate of rice is calculated, then,

[0105]

[0106] Among them, R represents the net radiation, G represents the earth's heat flux density, ρ e represents the air density, r e represents air resistance, c e represents the specific heat capacity of air, r s represents the stomatal resistance of rice, E t represents the calculated rice transpiration rate, η represents the dry gas constant, E v represents the calculated rice transpiration rate;

[0107] The calculated rice transpiration rate and evaporation rate are constructed into the corresponding space-time matrix, then,

[0108] E(x,y,t)={E t (x,y,t),E v (x,y,t)}

[0109] Among them, E(x,y,t) represents the spatiotemporal matrix constructed by rice transpiration rate and evaporation rate, E t (x,y,t),E v (x, y, t) represents the transpiration rate and evaporation rate of the canopy position (x, y) at time t, respectively.

[0110] Furthermore, the data fusion based on the moisture content of the paddy field is to perform multimodal fusion of the spatiotemporal matrix constructed by the transpiration rate and evaporation rate of the rice with the spatiotemporal matrix of the paddy field soil moisture content corresponding to the current sensor position. The specific fusion is as follows:

[0111] For transpiration rate and evaporation rate, set the weight factor as well as The set weight factors are dynamically adjusted by the implementer based on environmental changes and the stability of the sensor signal. Specifically:

[0112] If the meteorological data changes abnormally, the weight factor is increased, otherwise the weight factor is reduced;

[0113] For the rice growth levels in space, the weight coefficient is adaptively adjusted according to the influencing factors of each level;

[0114] According to the set de-weighting coefficient and combined with the spatiotemporal weighting factor, the spatiotemporal weight after fusion is calculated, then,

[0115]

[0116] Among them, wf(x,y,z,t) represents the fused spatiotemporal weight, represents the weight coefficient of transpiration rate, Represents the weight coefficient of evaporation rate, w M(x,y,z,t) represents the weight coefficient of the three-dimensional space-time matrix, and γ represents the space-time weighting factor, which is set by the implementer according to the actual application scenario;

[0117] Based on the calculated fusion spatiotemporal weights, the three-dimensional fusion of the spatiotemporal matrix constructed by rice transpiration rate and evaporation rate is realized, then,

[0118] M f(x,y,z,t) =w f(x,y,z,t) E(x,y,t)

[0119] Among them, M f(x,y,z,t) represents the fused three-dimensional spatiotemporal matrix, which includes rice transpiration rate, evaporation rate and paddy field moisture content data, w f(x,y,z,t) represents the fused spatiotemporal weight, and E(x, y, t) represents the spatiotemporal matrix constructed by rice transpiration rate and evaporation rate.

[0120] It should be noted that by weighted fusion of data from different sensors and combining it with information such as rice transpiration and evaporation rates for comprehensive analysis, this multimodal data fusion improves the accuracy and reliability of moisture monitoring compared to traditional single data source monitoring methods.

[0121] S3: Based on the fused three-dimensional spatiotemporal matrix, online detection of rice moisture content is performed.

[0122] Specifically, the online detection of rice moisture content is achieved by constructing a water transfer equation and a water absorption equation in rice. At the same time, a water transfer loss coefficient is set to perform a positive correction on the water transfer equation. Based on the data ratio between the constructed equation and the paddy soil, the real-time online detection of rice moisture content is achieved. The specific detection is as follows:

[0123] The rice water movement equation is constructed based on the water movement mechanics mechanism, and we have:

[0124]

[0125] Where f1 represents the rice water transfer equation, represents the water content data of the paddy field, E(x,y,t) represents the transpiration data of the rice, represents the amount of water absorbed by rice roots from the paddy field, z represents the divided level, and l represents the depth of the main root of rice;

[0126] The overall water absorption equation of rice is constructed based on the fused three-dimensional time matrix, then,

[0127]

[0128] Among them, f2 represents the overall water absorption equation of rice, It indicates the water content of the rice field after transpiration. represents the amount of water absorbed by rice roots from the paddy field, z represents the divided level, and l represents the depth of the main root of rice;

[0129] Based on the constructed water transfer equation and water absorption equation, online detection of rice moisture content is achieved, specifically:

[0130]

[0131] Among them, f1 represents the rice water transfer equation, f2 represents the overall rice water absorption equation, δ represents the water loss coefficient during the transfer process, and the specific value is set by the implementer according to the actual application scenario. M(x, y, z, t) represents the paddy field soil moisture data, and W represents the calculated rice moisture content, which is used to realize real-time online detection of rice moisture content.

[0132] It should be noted that this technical solution constructs the rice water flow equation and absorption equation, combines the soil moisture content and the transpiration rate of rice, calculates the rice moisture content in real time, and accurately calculates the rice moisture content through the dynamic moisture model combined with spatiotemporal data. It also takes into account the flow and absorption of water at different levels, solves the shortcomings of the existing technology in water dynamic analysis, and improves the accuracy of the monitoring system.

[0133] Example 2

[0134] A second embodiment of the present invention provides an online rice moisture content detection system based on the Internet of Things, comprising a data acquisition module, a data fusion module, and a moisture content detection module;

[0135] Specifically, the data acquisition module is responsible for collecting data related to the rice growth environment and moisture from a variety of sensors, including soil moisture, canopy temperature, ambient temperature, humidity, and transpiration and evaporation rates. Specifically:

[0136] Constructing a three-dimensional layered sensor network for data collection, we have:

[0137] Used to monitor the moisture content of rice stems and leaves in the canopy, deploy infrared sensors to collect real-time rice canopy temperature data for calculating transpiration and evaporation rates;

[0138] The root zone is used to monitor the water absorption dynamics of the main root of rice. Dielectric constant sensors and temperature sensors are installed to dynamically monitor the soil function rate and temperature gradient in the root zone, supporting the analysis of the root water absorption path;

[0139] Also, for monitoring the deep layer of soil water potential gradient, high-precision soil water potential sensors are deployed to detect the deep soil moisture status and prevent irrigation waste caused by water infiltration;

[0140] At the same time, the sensor deployment depth and density are automatically adjusted according to the rice root growth function to ensure synchronization with the root distribution. Through the dynamic self-organizing network protocol, the node communication path is optimized to ensure the stability of data transmission.

[0141] The data fusion module reduces the error of a single data source by combining the physical model with the measured soil data. Specifically:

[0142] Receive the spatiotemporal matrix of transpiration rate and evaporation rate from the canopy, and the spatiotemporal matrix of soil moisture content in the deep root zone;

[0143] Dynamically adjust the weighting factor based on environmental anomalies to enhance data reliability, then use the Gaussian kernel function to construct a three-dimensional space-time matrix to achieve spatial interpolation and data smoothing;

[0144] The moisture content detection module achieves efficient detection of rice moisture content through accurate data modeling and real-time prediction, specifically:

[0145] By constructing the moisture transfer equation and the absorption equation, and combining the loss coefficient to make a positive correction to the moisture transfer equation, and based on the paddy field moisture data, real-time detection of rice moisture content can be achieved.

[0146] Furthermore, if the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0147] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0148] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0149] Additionally, in order to provide a concise description of exemplary embodiments, all features of an actual embodiment (ie, those features that are not relevant to the best mode presently contemplated for carrying out the invention or those that are not relevant to implementing the invention) may not be described.

[0150] It will be appreciated that in the development of any actual embodiment, as in any engineering or design project, numerous implementation-specific decisions may be made. Such a development effort may be complex and time-consuming, but will, for those of ordinary skill having the benefit of this disclosure, be a routine undertaking of design, fabrication, and production without undue experimentation.

[0151] 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 the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An online detection method for rice moisture content based on the Internet of Things, characterized by: The following steps are included: By deploying a three-dimensional layered sensor network, we can achieve real-time detection of soil moisture content at different levels of the rice field. Specifically: Multiple sensors are deployed in rice fields to build a three-dimensional sensor network. The sensor distribution density is dynamically adjusted based on the density of the rice root system. A hierarchical network topology optimization is performed based on a dynamic ad hoc network protocol. The moisture content of the paddy soil is calculated based on the data collected by the sensors and constructed into a three-dimensional spatiotemporal matrix. The sensor monitoring depth is dynamically adjusted based on the depth of the rice root system. Rice growth data is collected through infrared thermal imaging and fused based on the moisture content of the rice fields. Specifically: The transpiration rate and evaporation rate of rice are calculated based on the data collected by the infrared sensor. Then, the spatiotemporal weights are calculated using the weight factors regulated by environmental changes and the spatiotemporal weighting factors. The data are fused based on the calculated spatiotemporal weights. By constructing the water transfer equation and water absorption equation in rice, and setting the water transfer loss coefficient to make a positive correction to the water transfer equation, real-time online detection of rice moisture content can be achieved based on the data ratio between the constructed equation and the paddy field soil.

2. The online detection method for rice moisture content based on the Internet of Things according to claim 1, characterized in that: The three-dimensional sensor network is specifically as follows: Set the deployment coordinates of the 3D sensor network (x i ,y i ,z i ), and satisfy the formula: S={(x i ,y i ,z k )|x i ∈[0,L x ],y i ∈[0,L y ],z i ∈{20,50,80}} Where S represents a three-dimensional sensor network, (x i ,y i ,z i ) represents the sensor coordinates in the sensor network, L x , L y Respectively represent the maximum length and width of the rice field, z i Indicates the vertical depth, which is the divided sensing layer, (x i ,y i ) represents the positioning coordinate information carried by the sensor; For the divided sensor levels, the sensor density of each sensor layer is dynamically regulated by the rice root density, specifically: Where N0 represents the number of initial sensor deployments, α and β represent the fitting parameters of rice root distribution, and ρ(z) represents the sensor density at level z.

3. The online detection method for rice moisture content based on the Internet of Things according to claim 2, characterized in that: The hierarchical network topology optimization based on the dynamic self-organizing network protocol is specifically as follows: Set the sensor node set N = {n1,n2,...,n k }, where n k represents the sensor of the kth node; At the same time, set node n i With node n j The distance d ij , and the distance between nodes satisfies the formula d ij <d max , where d max Indicates the maximum communication distance between nodes, which is set based on historical nodes; The topological structure of IoT communication is reflected by the adjacency matrix, and the adjacency matrix A[i][j]=1 is used to represent node n i With node n j They can communicate directly, using the adjacency matrix A[i][j]=0 to represent node n i With node n j There is no direct communication between them, and the communication relationship between nodes is represented by the adjacency matrix in turn until the adjacency relationship between all nodes in the sensor node set is terminated. At this time, the communication relationship between all nodes is a hierarchical topology structure between each sensor node in the hierarchical network.

4. The online detection method for rice moisture content based on the Internet of Things according to claim 3, characterized in that: The specific method for calculating the moisture content of paddy soil based on the data collected by the sensor is as follows: The input variables are the dielectric constant ε(z i ,t) and temperature gradient data ▽T(z i ,t), calculate the real-time soil moisture content of the paddy field according to the input variables, then we have, Among them, a, b, c represent paddy field calibration parameters, ε(z i ,t) represents level z i The dielectric constant at time t is, Indicates level z i Temperature gradient data at time t, Δz i represents the difference step size, θ(z i ,t) represents level z i Soil moisture content at time t; According to the calculated moisture content of paddy soil, a three-dimensional space-time matrix is ​​constructed, and then, Among them, θ(z i ,t) represents level z i The soil moisture content at time t, (x i ,y i ) represents the positioning coordinate information carried by the sensor, d represents the distance between sensor nodes, σ represents the spatial correlation radius, and M(x, y, z, t) represents the constructed three-dimensional space-time matrix, which is used to monitor the soil moisture content of the paddy field corresponding to the current sensor position based on the data collected by sensors at different positions at time t.

5. The online detection method for rice moisture content based on the Internet of Things according to claim 4, characterized in that: The dynamic adjustment of the sensor monitoring depth according to the rice root depth is specifically as follows: Based on the root distribution characteristics of the rice growth cycle, a root depth-time function is constructed. The rice growth cycle includes the tillering stage and the booting stage. The specific function is as follows: Among them, l(T GS ) represents the depth of the dominant root layer of rice, which is used to control the monitoring depth of the sensor array. l0 represents the initial root depth of rice in the tillering stage. l1 represents the initial root depth of rice in the booting stage. k1 and k2 represent the root growth rates of rice in the tillering stage and the booting stage, respectively. T1 and T2 represent the end time of the tillering stage and the end time of the booting stage, respectively. T GS Indicates rice production stage; According to the constructed function, the monitoring depth of the sensor is dynamically adjusted, specifically: For the sensor's monitoring depth z i ,When monitoring the water absorption dynamics of rice roots in the root ,zone, the monitoring depth is dynamically adjusted according to the ,growth cycle of the root system, so that the monitoring depth of the sensor does not exceed the ,depth of the root system.

6. The method for online detection of rice moisture content based on the Internet of Things according to claim 5, characterized in that: The data fusion is realized according to the calculated spatiotemporal weights as follows: For transpiration rate and evaporation rate, set the weight factor as well as The set weight factors are dynamically adjusted by the implementer based on environmental changes and the stability of the sensor signal. Specifically: If the meteorological data changes abnormally, the weight factor is increased, otherwise the weight factor is reduced; For the rice growth levels in space, the weight coefficient is adaptively adjusted according to the influencing factors of each level; According to the set weight coefficient and combined with the spatiotemporal weighting factor, the spatiotemporal weight after fusion is calculated, then, Among them, w f(x,y,z,t) represents the spatiotemporal weight after fusion, represents the weight factor of transpiration rate, Represents the weight factor of evaporation rate, w M( x, y, z, t) represents the weight coefficient of the three-dimensional space-time matrix, and γ represents the space-time weighting factor; Based on the calculated fusion spatiotemporal weights, the three-dimensional fusion of the spatiotemporal matrix constructed by rice transpiration rate and evaporation rate is realized, then, M f(x,y,z,t) =w f(x,y,z,t) ·E(x,y,t) Among them, M f(x,y,z,t) represents the fused three-dimensional spatiotemporal matrix, which includes rice transpiration rate, evaporation rate and paddy field moisture content data, w f(x,y,z,t) represents the fused spatiotemporal weight, and E(x, y, t) represents the spatiotemporal matrix constructed by rice transpiration rate and evaporation rate.

7. The online detection method for rice moisture content based on the Internet of Things according to claim 6, characterized in that: The real-time online detection of rice moisture content is as follows: Based on the constructed water transfer equation and water absorption equation, online detection of rice moisture content is achieved, specifically: Among them, f1 represents the rice water transfer equation, f2 represents the overall rice water absorption equation, δ represents the water loss coefficient during the transfer process, M(x, y, z, t) represents the paddy field soil moisture data, and W represents the calculated rice moisture content, which is used to realize real-time online detection of rice moisture content.

8. An online rice moisture content detection system based on the Internet of Things, applied to the online rice moisture content detection method based on the Internet of Things according to any one of claims 1 to 7, characterized in that: Including data acquisition module, data fusion module and moisture content detection module; The data acquisition module collects data related to the rice growth environment and moisture from a variety of sensors; The data fusion module reduces the error of a single data source by combining the physical model with the measured soil data; The moisture content detection module realizes efficient detection of rice moisture content through accurate data modeling and real-time prediction.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images