Rice planting and aquaculture integrated comprehensive intelligent monitoring system

By using multi-sensor and mathematical model combined with multi-objective particle swarm optimization algorithm in the comprehensive rice fishing system, the problem of low environmental parameter regulation efficiency in traditional rice fishing breeding is solved, and rice and water are realized The efficient growth environment management of the product improves output and profit.

CN119004025APending Publication Date: 2024-11-22SUZHOU ACAD OF AGRI SCI (JIANGSU TAIHU REGIONAL AGRI SCI INST)
View PDF 0 Cites 6 Cited by

Patent Information

Application Number
CN202411061395.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-05
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

The traditional comprehensive rice and fish farming model lacks an intelligent multi-parameter comprehensive monitoring and regulation system, resulting in low environmental parameter regulation efficiency, making it difficult to meet the growth needs of rice and aquatic products at the same time, affecting yield and profit.

Method used

A comprehensive intelligent monitoring system for integrated rice cultivation and aquaculture was designed, using multiple sensors to collect environmental data, transmit and process data through wireless communication, establish a mathematical model for environmental parameter analysis and adjustment, and combine it with a multi-objective particle swarm optimization algorithm. Generate a comprehensive control and adjustment plan to adjust temperature, humidity, light intensity and water quality parameters in real time.

Benefits of technology

It has achieved accurate adjustment of the growth environment of rice and aquatic products, improved growth efficiency and yield, ensured that environmental parameters are within a reasonable range, met the growth needs of both, and improved overall yield and benefits.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119004025A_ABST
    Figure CN119004025A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of planting control and adjustment, in particular to a rice planting and aquaculture integrated comprehensive intelligent monitoring system, which comprises a data acquisition module used for acquiring various environmental data, rice growth parameters and aquatic product growth parameters in a planting and breeding environment; the data processing module is used for processing and analyzing the received data and generating a comprehensive control and regulation scheme, and specifically comprises a data preprocessing unit, a first mathematical model unit, a second mathematical model unit and a comprehensive regulation unit; and the control execution module is connected with the data processing module and is used for adjusting the planting and breeding environment according to the final comprehensive control adjustment scheme. According to the invention, through a closed-loop control mechanism, the regulation effect is continuously monitored and fed back, and the optimal growth state of rice and aquatic products is ensured.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of planting control and regulation, and in particular to an integrated intelligent monitoring system for rice planting and aquaculture. Background Art

[0002] With the growth of global population and the increasing demand for resources, agriculture and aquaculture are facing the dual challenges of increasing production and resource utilization efficiency. As an efficient ecological agricultural model, rice-fish integrated farming can not only improve the utilization efficiency of land and water resources, but also improve the ecological environment and increase farmers' income by combining rice planting and aquaculture. However, the traditional rice-fish integrated farming model still has some technical bottlenecks and challenges, which are mainly manifested in the following aspects:

[0003] In the traditional integrated rice-fish farming model, the monitoring methods for environmental parameters (such as temperature, humidity, light intensity and water quality parameters) are relatively simple, and it is impossible to achieve comprehensive and real-time monitoring of the farming environment. The lack of accurate monitoring of key environmental parameters leads to low efficiency in regulating the farming environment and makes it difficult to promptly detect and respond to the impact of environmental changes on the growth of rice and aquatic products.

[0004] In the traditional model, the regulation of environmental parameters mainly relies on manual experience and simple adjustment methods, which makes it difficult to achieve precise control. Since rice and aquatic products have different requirements for environmental parameters, it is difficult to meet the growth needs of both at the same time, which often leads to poor growth of rice or aquatic products, affecting overall yield and income.

[0005] At present, there is a lack of integrated intelligent monitoring and control systems on the market that can comprehensively consider the growth needs of rice and aquatic products and optimize and adjust environmental parameters. It is impossible to achieve comprehensive monitoring and adjustment of multiple parameters, the level of intelligence is low, and the potential of integrated rice-fish farming cannot be fully tapped.

[0006] In response to the above problems, there is an urgent need for a system that can realize comprehensive multi-parameter monitoring, intelligent analysis and precise adjustment, so as to optimize the integrated rice-fish farming environment and improve the growth efficiency and yield of rice and aquatic products. Summary of the invention

[0007] Based on the above objectives, the present invention provides an integrated intelligent monitoring system for rice planting and aquaculture.

[0008] An integrated intelligent monitoring system for rice planting and aquaculture, comprising:

[0009] Data acquisition module: used to collect various environmental data in the breeding environment, including temperature, humidity, light intensity, water quality parameters (pH value, dissolved oxygen, ammonia nitrogen), rice growth parameters and aquatic product growth parameters. The data acquisition module includes multiple sensors, including water temperature sensors, humidity sensors, water quality sensors, and light sensors, which are arranged in different positions of the rice field to ensure the comprehensiveness and accuracy of data collection;

[0010] Data transmission module: connected to the data acquisition module, used to transmit the collected data to the data processing module. The data transmission module adopts wireless communication to ensure the real-time transmission and stability of the data;

[0011] Data processing module: connected to the data transmission module, used to process and analyze the received data and generate a comprehensive control and adjustment plan, specifically including:

[0012] Data preprocessing unit: performs preprocessing operations on the collected raw data to remove noise and fill in missing values;

[0013] The first mathematical model unit: based on the correlation analysis between environmental data and rice growth parameters, establish a first mathematical model between environmental parameters and rice growth parameters, input the real-time monitored rice growth parameter data into the first mathematical model, and generate preliminary environmental parameter control instructions, the preliminary environmental control instructions include specific control values ​​of temperature, humidity, light intensity, and water quality parameters;

[0014] Second mathematical model unit: based on the correlation analysis between environmental parameters and aquatic product growth parameters, establish a second mathematical model between environmental parameters and aquatic product growth parameters, import the preliminary environmental parameter control instructions into the second mathematical model, and predict the impact of the preliminary environmental parameters on the growth of aquatic products;

[0015] Comprehensive adjustment unit: According to the prediction results of the second mathematical model combined with the constraints, the preliminary environmental parameter control instructions are adjusted to generate the final comprehensive control adjustment plan to meet the environmental requirements of rice planting and aquaculture at the same time;

[0016] Control execution module: connected to the data processing module, used to adjust the breeding environment according to the final comprehensive control and adjustment plan.

[0017] Optionally, the water temperature sensors are arranged at different depths of the water layer in the rice field to monitor the surface, middle and bottom temperatures of the water body respectively, and obtain temperature data of different water layers in the rice field to optimize the growth environment of rice and aquatic products;

[0018] The humidity sensor comprises:

[0019] Air humidity sensor: installed above the rice field to monitor air humidity and capture humidity data of the rice field environment;

[0020] Soil moisture sensors: installed in the soil of rice fields at different depths to monitor soil moisture changes and ensure that the humidity of rice roots is appropriate;

[0021] The water quality sensors are arranged at different positions and depths of the water layer in the rice field, including:

[0022] pH sensor: installed on the surface, middle and bottom layers of the rice field to monitor the pH value of the water and ensure that the water quality is suitable for the growth of rice and aquatic products;

[0023] Dissolved oxygen sensor: installed at different depths in the rice field to monitor the dissolved oxygen content of the water to ensure that the growth environment of aquatic products has sufficient oxygen supply;

[0024] Ammonia nitrogen sensor: installed at different depths in the rice fields to monitor the ammonia nitrogen content in the water to ensure that the water quality meets the healthy growth requirements of aquatic products;

[0025] The light sensor is arranged directly above the rice field to monitor the light intensity and ensure that the light conditions are suitable for the growth of rice and aquatic products;

[0026] The rice growth parameters include plant height, number of leaves, chlorophyll content, and stem diameter;

[0027] The aquatic product growth parameters include body length and body weight.

[0028] Optionally, the correlation analysis between the environmental data and the rice growth parameters and the correlation analysis between the environmental parameters and the aquatic product growth parameters are both performed by Pearson correlation coefficient;

[0029] The Pearson correlation coefficient was used to analyze the relationship between environmental data and rice growth parameters, and the environmental parameters that had a significant impact on rice growth were determined. The Pearson correlation coefficient was used to analyze the relationship between environmental data and aquatic product growth parameters, and the environmental parameters that had a significant impact on aquatic product growth were determined. The environmental parameters that had a significant impact on rice growth and aquatic product growth included temperature T, humidity H, light intensity L, and water quality parameter W.

[0030] Optionally, the use of the Pearson correlation coefficient to analyze the relationship between environmental data and rice growth parameters to determine the environmental parameters that have a significant impact on rice growth specifically includes:

[0031] Collect various environmental data (temperature, humidity, light intensity, water quality parameters) and rice growth parameters (plant height, number of leaves, chlorophyll content, stem diameter);

[0032] The relationship between environmental data and rice growth parameters was analyzed using the Pearson correlation coefficient, expressed as:

[0033] Among them, r xy is the correlation coefficient between environmental parameter x and rice growth parameter y, x i and i are the data points of environmental parameters and water chestnut growth parameters, and is its mean value.

[0034] Optionally, the first mathematical model and the second mathematical model both adopt a multiple linear regression model, and the first mathematical model established between the environmental parameters and the rice growth parameters specifically includes:

[0035] Use historical data and experimental data to train a multivariate linear regression model and determine the model parameters: y = β0 + β1T + β2H + β3L + β4W, where y is the growth parameter of water chestnut, including plant height, number of leaves, chlorophyll content, and stem diameter; β0 is a constant term; β1, β2, β3, and β4 are regression coefficients; T is temperature, H is humidity, L is light intensity, and W is a water quality parameter;

[0036] The real-time environmental parameter data is input into the first mathematical model, and the environmental parameters are adjusted according to the model prediction of the impact of the current environmental conditions on the future rice growth. Based on the model prediction results, preliminary environmental parameter control instructions are generated to adjust the temperature, humidity, light intensity and water quality parameters to optimize the rice growth conditions:

[0037] T control =f temp (T real , H real , L real , W real ,y real );

[0038] Hc ontrol =f humid (T real , H real , L real , W real ,y real );

[0039] L control =f light (T real , H real , L real , W real ,y real );

[0040] W control =fwater (T real , H real , L real , W real ,y real );

[0041] Among them, f temp , f humid , f light , f water is the control function calculated by the model, which is used to generate the specific control value of each environmental parameter, T control is the temperature control value of the preliminary environmental control instruction; H control is the humidity control value of the preliminary environmental control instruction; L control is the light intensity control value of the preliminary environment control instruction; W control The water quality parameter control values ​​for the preliminary environmental control directive.

[0042] The scheme for establishing the second mathematical model between environmental parameters and aquatic product growth parameters is the same as described above.

[0043] Optionally, the regression coefficients β0, β1, β2, β3, and β4 are determined based on a gradient descent method, and the loss function is minimized through iterative optimization, which is expressed as:

[0044] Among them, yi is the rice growth parameter of the i-th sample, T i , H i , L i , W i are the temperature, humidity, light intensity and water quality parameters of the i-th sample, respectively, and n is the total number of samples;

[0045] Update the regression coefficients using the gradient descent algorithm:

[0046] Among them, α is the learning rate.

[0047] Optionally, the second mathematical model is expressed as: z=γ0+γ1T+γ2H+γ3L+γ4W,

[0048] Among them, z is the growth parameter of aquatic products, including body length and weight, γ0 is the constant term, and γ1, γ2, γ3, and γ4 are regression coefficients;

[0049] The step of importing the preliminary environmental parameter control instruction into the second mathematical model to predict the effect of the preliminary environmental parameter on the growth of aquatic products specifically includes:

[0050] The generated preliminary environmental parameter control instructions (specific control values ​​of temperature, humidity, light intensity, and water quality parameters) are input into the second mathematical model. According to the second mathematical model, the effect of the preliminary environmental parameter control instructions on the growth of aquatic products is predicted, and the changes in the length or weight of aquatic products under the control instructions are predicted:

[0051] Predicted_Fish_Length = γ 0L +γ 1L T control +γ 2L H control +γ 3L L control +γ 4L W control ;

[0052] Predicted_Fish_Weight = γ 0W +γ 1W T control +γ 2W H control +γ 3W L control +γ 4W W controi ;

[0053] Among them, T control , H control , L control , W control The specific control values ​​of temperature, humidity, light intensity and water quality parameters in the preliminary environmental parameter control instructions;

[0054] γ 0L , γ 1L , γ 2L , γ 3L , γ 4L and γ 0W , γ 1W , γ 2W , γ 3W , γ 4W is the regression coefficient determined by gradient descent, γ 0L , γ 1L , γ 2L , γ 3L , γ 4L is the regression coefficient used to predict the body length of aquatic products; 0W , γ 1W , γ 2W ,γ3W,γ 4W is the regression coefficient used to predict the weight of aquatic products.

[0055] Optionally, the comprehensive adjustment unit specifically includes:

[0056] Obtain preliminary environmental parameter control instructions on the impact of aquatic product growth;

[0057] Define constraints: including the growth requirements of rice and aquatic products, and the reasonable range of environmental parameters:

[0058] T min ≤T≤T max ;

[0059] H min ≤H≤H max ;

[0060] L min ≤L≤L max ;

[0061] W min ≤W≤W max ;

[0062] Multi-objective optimization: Through the multi-objective particle swarm optimization algorithm, various environmental parameters are optimized under constraints to simultaneously meet the growth requirements of rice and aquatic products. The optimization objectives include:

[0063] Rice growth optimization: maximizing rice growth parameters (such as plant height, number of leaves, chlorophyll content, stem diameter);

[0064] Aquatic product growth optimization: Maximizing aquatic product growth parameters (such as body length and weight).

[0065] Optionally, the multi-objective particle swarm optimization algorithm specifically includes:

[0066] Initialize the particle swarm, each particle represents an environmental parameter combination x = (T, H, L, W), initialize the speed v of each particle, set the initial position and speed of each particle to random values, and generate them within the parameter range;

[0067] Fitness evaluation: Calculate the fitness value of each particle, evaluate the rice growth parameters and aquatic product growth parameters respectively, let f1 represent the optimization target of rice growth, f2 represent the optimization target of aquatic product growth, the goal of multi-objective optimization is to optimize f1 and f2 at the same time, to find a compromise solution, so that both rice and aquatic products can grow in the best environment:

[0068] f1(x)=α1(β0+β1T+β2H+β3L+β4W);

[0069] f2(x)=α2(γ0+γ1T+γ2H+γ3L+γ4W); where α1 and α2 are weight coefficients of rice and aquatic product growth parameters, respectively. f1(x) is used to evaluate the effect of environmental parameter combination x on rice growth, and f2(x) is used to evaluate the effect of environmental parameter combination x on aquatic product growth.

[0070] Update the individual optimal solution p of each particle i and the global optimal solution g, maintaining the Pareto frontier solution set;

[0071] Update the particle's velocity and position:

[0072] v i (t+1)=ωv i (t)+c1r1(p i -x i (t))+c2r2(gx i (t));

[0073] x i (t+1)=x i (t)+v i (t+1);

[0074] Among them, v i (t+1) is the speed of the ith particle at the t+1th iteration, ω is the inertia weight, which controls the inertia of the particle movement, c1 and c2 are acceleration coefficients, which control the acceleration of the particle to the individual optimal solution and the global optimal solution respectively, r1 and r2 are random numbers between 0 and 1, which increase the randomness of the particle, and p i is the individual optimal position of the i-th particle, g is the global optimal position, x i (t) is the position of the ith particle at the tth iteration, x i (t+1) is the position of the i-th particle at the t+1th iteration;

[0075] Check and correct the current position of the particle to make it meet the constraints of the environmental parameters;

[0076] Repeat fitness evaluation, update of individual and global optimal solutions, speed and position update, and constraint condition check until the predetermined number of iterations or convergence conditions are reached; select the optimal solution from the Pareto front solution set as the final environmental parameter combination T final , H final , L final , W final .

[0077] Optionally, the control execution module specifically includes:

[0078] Irrigation control unit: adjusts the water supply in the rice planting environment according to the control instructions to ensure the normal growth of rice;

[0079] Water quality treatment control unit: adjusts the water quality treatment system according to control instructions, maintains appropriate water quality parameters in the water body, and ensures the healthy growth of aquatic products;

[0080] Lighting control unit: adjusts the lighting system according to control instructions, provides suitable lighting conditions, and promotes the growth of rice and aquatic products;

[0081] Temperature control unit: adjusts the water temperature regulation system according to control instructions to provide suitable temperature conditions to ensure the normal growth of rice and aquatic products.

[0082] Beneficial effects of the present invention:

[0083] The present invention adopts a first mathematical model and a second mathematical model to respectively describe the relationship between environmental parameters and rice growth parameters and aquatic product growth parameters, and determines the influence of each environmental parameter on the growth parameters through correlation analysis and multiple linear regression methods. The real-time monitoring data is input into the first mathematical model to generate preliminary environmental parameter control instructions, and the preliminary control instructions are then input into the second mathematical model to predict the influence on the growth of aquatic products. The dual model structure ensures that the generated control instructions not only meet the growth requirements of rice, but also take into account the growth environment of aquatic products.

[0084] The present invention introduces a multi-objective particle swarm optimization algorithm, and optimizes the growth environment of rice and aquatic products at the same time under defined constraints. The fitness function evaluates the influence of environmental parameters on rice and aquatic products respectively, and solves the optimal combination of environmental parameters through the multi-objective optimization algorithm. The final generated comprehensive control and adjustment scheme combines the optimization results and balance adjustment to ensure that the temperature, humidity, light intensity and water quality parameters are within a reasonable range. The control execution module adjusts the breeding environment in real time according to the comprehensive adjustment scheme, and continuously monitors and feedbacks the adjustment effect through a closed-loop control mechanism to ensure the optimal growth state of rice and aquatic products. BRIEF DESCRIPTION OF THE DRAWINGS

[0085] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0086] Figure 1 A schematic diagram of system function modules according to an embodiment of the present invention;

[0087] Figure 2 Schematic diagram of the logic of the data processing module of the embodiment of the present invention. DETAILED DESCRIPTION

[0088] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0089] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0090] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0091] like Figure 1-Figure 2 As shown, a rice planting and aquaculture integrated intelligent monitoring system includes:

[0092] Data acquisition module: used to collect various environmental data in the breeding environment, including temperature, humidity, light intensity, water quality parameters (pH value, dissolved oxygen, ammonia nitrogen), rice growth parameters and aquatic product growth parameters. The data acquisition module includes multiple sensors, including water temperature sensors, humidity sensors, water quality sensors, and light sensors, which are arranged in different positions of the rice field to ensure the comprehensiveness and accuracy of data collection;

[0093] Data transmission module: connected with the data acquisition module, used to transmit the collected data to the data processing module. The data transmission module adopts wireless communication to ensure the real-time transmission and stability of data;

[0094] Data processing module: connected to the data transmission module, used to process and analyze the received data and generate a comprehensive control and adjustment plan, including:

[0095] Data preprocessing unit: performs preprocessing operations on the collected raw data to remove noise and fill in missing values ​​to ensure data quality;

[0096] Data denoising specifically includes:

[0097] The sliding window filtering method is used to smooth the data to reduce the impact of random noise. The window size n is set according to the actual situation and is expressed as:

[0098] in, is the smoothed data, x j is the original data;

[0099] Apply a Gaussian filter to smooth the data to reduce the effect of noise:

[0100] Among them, G(i, j) is the Gaussian kernel function, k is the size of the filter window;

[0101] Missing value completion specifically includes:

[0102] Linear interpolation: For missing data points, use adjacent data points for linear interpolation: Where t1 and t2 are the time points on both sides of the missing value, and x(t1) and x(t2) are the corresponding data values;

[0103] When there are many missing values, multiple interpolation is used to predict and fill in the missing values ​​based on the correlation between variables, expressed as: missing =f(x1, x2, ..., x n ), where f is a function of other variables x1, x2, ..., x n Function to calculate missing values.

[0104] The first mathematical model unit: based on the correlation analysis between environmental data and rice growth parameters, establish a first mathematical model between environmental parameters and rice growth parameters, input the real-time monitored rice growth parameter data into the first mathematical model, and generate preliminary environmental parameter control instructions, the preliminary environmental control instructions include specific control values ​​of temperature, humidity, light intensity, and water quality parameters;

[0105] Second mathematical model unit: based on the correlation analysis between environmental parameters and aquatic product growth parameters, establish a second mathematical model between environmental parameters and aquatic product growth parameters, import the preliminary environmental parameter control instructions into the second mathematical model, and predict the impact of the preliminary environmental parameters on the growth of aquatic products;

[0106] Comprehensive adjustment unit: According to the prediction results of the second mathematical model combined with the constraints, the preliminary environmental parameter control instructions are adjusted to generate the final comprehensive control adjustment plan to meet the environmental requirements of rice planting and aquaculture at the same time;

[0107] Control execution module: connected to the data processing module, used to adjust the breeding environment according to the final comprehensive control and adjustment plan;

[0108] It also includes a human-computer interaction module, which is connected to the data processing module and the control execution module to enable users to monitor and manually control the system in real time and provide a data display and operation interface. The human-computer interaction module includes a display screen, control buttons and a communication interface for information interaction between the user and the system.

[0109] Water temperature sensors are placed at different depths in the water layer of the rice field to monitor the surface, middle and bottom temperatures of the water body, and obtain temperature data of different water layers in the rice field to optimize the growth environment of rice and aquatic products.

[0110] Humidity sensors include:

[0111] Air humidity sensor: installed above the rice field to monitor air humidity and capture humidity data of the rice field environment;

[0112] Soil moisture sensors: installed in the soil of rice fields at different depths to monitor soil moisture changes and ensure that the humidity of rice roots is appropriate;

[0113] Water quality sensors are placed at different locations and depths in the water layer of the rice fields, including:

[0114] pH sensor: installed on the surface, middle and bottom layers of the rice field to monitor the pH value of the water and ensure that the water quality is suitable for the growth of rice and aquatic products;

[0115] Dissolved oxygen sensor: installed at different depths in the rice field to monitor the dissolved oxygen content of the water to ensure that the growth environment of aquatic products has sufficient oxygen supply;

[0116] Ammonia nitrogen sensor: installed at different depths in the rice fields to monitor the ammonia nitrogen content in the water to ensure that the water quality meets the healthy growth requirements of aquatic products;

[0117] Light sensors are placed directly above the rice fields to monitor light intensity and ensure that light conditions are suitable for the growth of rice and aquatic products;

[0118] Rice growth parameters include plant height, number of leaves, chlorophyll content, and stem diameter. The specific monitoring methods are as follows:

[0119] Plant height: The height of rice plants was measured regularly using a laser rangefinder.

[0120] Leaf Count: Rice plant images are captured by a high-resolution camera and leaf counts are performed using image processing algorithms.

[0121] Chlorophyll content: The chlorophyll content of leaves was measured using a portable chlorophyll meter (SPAD).

[0122] Stem diameter: The thickness of the rice stem was measured using a radial measuring instrument.

[0123] The growth parameters of aquatic products include body length and weight. The specific monitoring methods are as follows:

[0124] Body length and weight: Regularly capture some sample aquatic products, weigh them and measure their body length, and estimate the average weight and average body length. Sample capture: Regularly capture a certain number of aquatic product samples randomly from rice fields.

[0125] Weighing and measuring body length:

[0126] Weighing: Use a precision electronic scale to weigh the body weight of each caught sample and record the data.

[0127] Measuring body length: Use a measuring board or ruler to measure the body length of each caught sample and record the data.

[0128] Data recording: Record the weight and length data of all samples. Assuming that N fish are caught, the recorded data is Where L i is the body length of the ith fish, W i is the weight of the ith fish.

[0129] Calculate average weight and length:

[0130] Calculate the average weight of the catch:

[0131] Calculate the average body length of the catch:

[0132] The leaf count is as follows:

[0133] 1. Image acquisition: Use a high-resolution camera to capture images of rice plants, ensuring that the image clarity and resolution are high enough for subsequent processing.

[0134] 2. Image preprocessing:

[0135] Convert a color image to a grayscale image, removing the color information and retaining only the brightness information;

[0136] Use Gaussian filtering or median filtering to remove noise from the image.

[0137] 3. Edge detection: Use the Canny edge detection algorithm to extract the edge of the leaf, including:

[0138] Gradient calculation: Calculate the gradient strength and direction of the image:

[0139] Gx (x, y) = I smooth (x+1,y)-I smooth (x-1, y);

[0140] G y (x, y) = I smooth (x, y+1)-I smooth (x, y-1);

[0141]

[0142] Non-maximum suppression: refine edges and suppress non-maximum gradients.

[0143] Edge pixels are determined through dual threshold detection and hysteresis threshold.

[0144] 4. Use dilation and erosion morphological operations to connect broken edges and fill small holes;

[0145] Expansion: I dilate (x, y) = max (i,j)∈kernel I edge (x+i, y+j);

[0146] Corrosion: I erode (x, y) = min (i,j)∈kernel I dilate (x+i, y+j);

[0147] 5. Contour detection and extraction: Use the contour detection algorithm (findContours function in OpenCV) to extract the leaf contour in the image, expressed as:

[0148] Contours = findContours(I morph ,textCHAIN A PPROX S IMPLE);

[0149] Leaf counting: Count the number of leaves by analyzing the number and characteristics of their contours.

[0150] leaf count = len(contours);

[0151] Remove non-leaf contours: Remove non-leaf contours based on the area characteristics of the contours, area filtering:

[0152] filtered_contours=[c for c∈contours if contourArea(c)>thres hold];

[0153] Final leaf counting result: final_leaf_count=len(filtered_contours).

[0154] The correlation analysis between environmental data and rice growth parameters and between environmental parameters and aquatic product growth parameters were performed using Pearson correlation coefficient;

[0155] The Pearson correlation coefficient was used to analyze the relationship between environmental data and rice growth parameters, and the environmental parameters that had a significant impact on rice growth were determined. The Pearson correlation coefficient was used to analyze the relationship between environmental data and aquatic product growth parameters, and the environmental parameters that had a significant impact on aquatic product growth were determined. The environmental parameters that had a significant impact on rice growth and aquatic product growth included temperature T, humidity H, light intensity L, and water quality parameter W.

[0156] The Pearson correlation coefficient was used to analyze the relationship between environmental data and rice growth parameters, and the environmental parameters that had a significant impact on rice growth were determined to be:

[0157] Collect various environmental data (temperature, humidity, light intensity, water quality parameters) and rice growth parameters (plant height, number of leaves, chlorophyll content, stem diameter);

[0158] The relationship between environmental data and rice growth parameters was analyzed using the Pearson correlation coefficient, expressed as:

[0159] Among them, r xy is the correlation coefficient between environmental parameter x and rice growth parameter y, x i and i are the data points of environmental parameters and rice growth parameters, and The correlation coefficients between multiple environmental parameters and rice growth parameters were calculated as their mean values, and the environmental parameters with significant correlation were screened out.

[0160] The Pearson correlation coefficient was used to analyze the relationship between environmental data and aquatic product growth parameters, and the environmental parameters that had a significant impact on the growth of aquatic products were determined to be the same as the above scheme, expressed as:

[0161] Among them, r xz is the correlation coefficient between environmental parameter x and aquatic product growth parameter z, x i and z i are the data points of environmental parameters and aquatic product growth parameters, and The correlation coefficients between multiple environmental parameters and aquatic product growth parameters were calculated as their mean values, and the environmental parameters with significant correlation were screened out.

[0162] The first mathematical model and the second mathematical model both adopt a multiple linear regression model, and the first mathematical model between the environmental parameters and the rice growth parameters is established specifically including:

[0163] The multivariate linear regression model was trained using historical data and experimental data to determine the model parameters: y = β0 + β1T + β2H + β3L + β4W, where y is the rice growth parameter, including plant height, number of leaves, chlorophyll content, and stem diameter; β0 is a constant term; β1, β2, β3, and β4 are regression coefficients; T is temperature, H is humidity, L is light intensity, and W is a water quality parameter;

[0164] The real-time environmental parameter data is input into the first mathematical model, and the environmental parameters are adjusted according to the model prediction of the impact of the current environmental conditions on the future rice growth. Based on the model prediction results, preliminary environmental parameter control instructions are generated to adjust the temperature, humidity, light intensity and water quality parameters to optimize the rice growth conditions:

[0165] T control =f temp (T real , H real , L real , W real ,y real );

[0166] H control =f humid (T real , H real , L real , W real ,y real );

[0167] L control =f light (T real , H real , L real , W real ,y real );

[0168] W control =f water (T real , H real , L real , W real ,y real );

[0169] Among them, f temp , f humid , f light , f wateris the control function calculated by the model, which is used to generate the specific control value of each environmental parameter, T control is the temperature control value of the preliminary environmental control instruction; H control is the humidity control value of the preliminary environmental control instruction; L control is the light intensity control value of the preliminary environment control instruction; W control The water quality parameter control values ​​for the preliminary environmental control directive.

[0170] The scheme for establishing the second mathematical model between environmental parameters and aquatic product growth parameters is the same as described above.

[0171] The regression coefficients β0, β1, β2, β3, and β4 are determined based on the gradient descent method, and the loss function is minimized through iterative optimization, which is expressed as:

[0172] Among them, yi is the rice growth parameter of the i-th sample, T i , H i , L i , W i are the temperature, humidity, light intensity and water quality parameters of the i-th sample, respectively, and n is the total number of samples;

[0173] Update the regression coefficients using the gradient descent algorithm:

[0174] Among them, α is the learning rate.

[0175] The specific expansion of each control function is as follows:

[0176] Control_Temperature=β 0T +β 1T T real +β 2T H real +β 3T L real +β 4T W real ;

[0177] Control_Humidity=β 0H +β 1H T real +β 2H H real +β 3H L real +β 4H W real ;

[0178] Control_Light=β 0L +β 1L T real +β2L H real +β 3L L real +β 4L W real ;

[0179] Control_Water_Quality = β 0W +β 1W T real +β 2W H real +β 3W L real +β 4W W real ;

[0180] Among them, β 0T , β 1T , β 2T , β 3T , β 4T are the regression coefficients determined by the gradient descent method.

[0181] The second mathematical model is expressed as: z = γ0 + γ1T + γ2H + γ3L + γ4W,

[0182] Among them, z is the growth parameter of aquatic products, including body length and weight, γ0 is the constant term, and γ1, γ2, γ3, and γ4 are regression coefficients;

[0183] The preliminary environmental parameter control instructions are introduced into the second mathematical model to predict the impact of the preliminary environmental parameters on the growth of aquatic products, including:

[0184] The generated preliminary environmental parameter control instructions (specific control values ​​of temperature, humidity, light intensity, and water quality parameters) are input into the second mathematical model. According to the second mathematical model, the effect of the preliminary environmental parameter control instructions on the growth of aquatic products is predicted, and the changes in the length or weight of aquatic products under the control instructions are predicted:

[0185] Predicted_Fish_Length = γ 0L +γ 1L T control +γ 2L H control +γ 3L L control +γ 4L W control ;

[0186] Predicted_Fish_Weight = γ 0W +γ 1W T control +γ 2W H control+γ 3W L control +γ 4W W controi ;

[0187] Among them, T control , H control , L control , W control The specific control values ​​of temperature, humidity, light intensity and water quality parameters in the preliminary environmental parameter control instructions;

[0188] γ 0L , γ 1L , γ 2L , γ 3L , γ 4L and γ 0W , γ 1W ,γ2W,γ 3W , γ 4W is the regression coefficient determined by gradient descent, γ 0L , γ 1L , γ 2L , γ 3L , γ 4L is the regression coefficient used to predict the body length of aquatic products; 0W , γ 1W , γ 2W ,γ3W,γ 4W is the regression coefficient used to predict the weight of aquatic products.

[0189] The comprehensive regulation unit specifically includes:

[0190] Obtain preliminary environmental parameter control instructions on the impact of aquatic product growth;

[0191] Define constraints: including the growth requirements of rice and aquatic products, and the reasonable range of environmental parameters:

[0192] T min ≤T≤T max ;

[0193] H min ≤H≤H max ;

[0194] L min ≤L≤L max ;

[0195] W min ≤W≤W max ;

[0196] Multi-objective optimization: Through the multi-objective particle swarm optimization algorithm, various environmental parameters are optimized under constraints to simultaneously meet the growth requirements of rice and aquatic products. The optimization objectives include:

[0197] Rice growth optimization: maximizing rice growth parameters (such as plant height, number of leaves, chlorophyll content, stem diameter);

[0198] Aquatic product growth optimization: Maximizing aquatic product growth parameters (such as body length and weight).

[0199] The multi-objective particle swarm optimization algorithm specifically includes:

[0200] Initialize the particle swarm, each particle represents an environmental parameter combination x = (T, H, L, W), initialize the speed v of each particle, set the initial position and speed of each particle to random values, and generate them within the parameter range;

[0201] Fitness evaluation: Calculate the fitness value of each particle, evaluate the rice growth parameters and aquatic product growth parameters respectively, let f1 represent the optimization target of rice growth, f2 represent the optimization target of aquatic product growth, the goal of multi-objective optimization is to optimize f1 and f2 at the same time, to find a compromise solution, so that both rice and aquatic products can grow in the best environment:

[0202] f1(x)=α1(β0+β1T+β2H+β3L+β4W);

[0203] f2(x)=α2(γ0+γ1T+γ2H+γ3L+γ4W); where α1 and α2 are weight coefficients of rice and aquatic product growth parameters, respectively. f1(x) is used to evaluate the effect of environmental parameter combination x on rice growth, and f2(x) is used to evaluate the effect of environmental parameter combination x on aquatic product growth.

[0204] Update the individual optimal solution p of each particle i and the global optimal solution g, maintaining the Pareto frontier solution set;

[0205] Update the particle's velocity and position:

[0206] v i (t+1)=ωv i (t)+c1r1(p i -x i (t))+c2r2(gx i (t));

[0207] x i (t+1)=x i (t)+v i (t+1);

[0208] Among them, v i(t+1) is the speed of the ith particle at the t+1th iteration, ω is the inertia weight, which controls the inertia of the particle movement, c1 and c2 are acceleration coefficients, which control the acceleration of the particle to the individual optimal solution and the global optimal solution respectively, r1 and r2 are random numbers between 0 and 1, which increase the randomness of the particle, and p i is the individual optimal position of the i-th particle, g is the global optimal position, x i (t) is the position of the ith particle at the tth iteration, x i (t+1) is the position of the i-th particle at the t+1th iteration;

[0209] Check and correct the current position of the particle to make it meet the constraints of the environmental parameters;

[0210] Repeat fitness evaluation, update of individual and global optimal solutions, speed and position update, and constraint condition check until the predetermined number of iterations or convergence conditions are reached; select the optimal solution from the Pareto front solution set as the final environmental parameter combination T final , H final , L final , W final .

[0211] Balance and adjust the optimization results according to the actual situation to ensure the feasibility of actual operation and system stability. Consider the response speed and adjustment accuracy of the system and smooth the optimization results appropriately.

[0212] The final generated comprehensive control and adjustment plan is passed to the control execution module to implement adjustments to the breeding environment, including adjustments to temperature, humidity, light intensity and water quality parameters.

[0213] The control execution module specifically includes:

[0214] Irrigation control unit: adjusts the water supply in the rice planting environment according to the control instructions to ensure the normal growth of rice;

[0215] Water quality treatment control unit: adjusts the water quality treatment system according to control instructions, maintains appropriate water quality parameters in the water body, and ensures the healthy growth of aquatic products;

[0216] Lighting control unit: adjusts the lighting system according to control instructions, provides suitable lighting conditions, and promotes the growth of rice and aquatic products;

[0217] Temperature control unit: adjusts the water temperature regulation system according to control instructions to provide suitable temperature conditions to ensure the normal growth of rice and aquatic products.

[0218] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0219] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An integrated intelligent monitoring system for rice planting and aquaculture, It is characterized in that include: Data acquisition module: used to collect various environmental data in the breeding environment, including temperature, humidity, light intensity, water quality parameters, rice growth parameters and aquatic product growth parameters. The data acquisition module includes multiple sensors, including water temperature sensors, humidity sensors, water quality sensors, and light sensors, which are arranged in different positions of the rice field; Data transmission module: connected to the data acquisition module, used to transmit the collected data to the data processing module, the data transmission module adopts wireless communication; Data processing module: connected to the data transmission module, used to process and analyze the received data and generate a comprehensive control and adjustment plan, specifically including: Data preprocessing unit: performs preprocessing operations on the collected raw data to remove noise and fill in missing values; The first mathematical model unit: based on the correlation analysis between environmental data and rice growth parameters, establish a first mathematical model between environmental parameters and rice growth parameters, input the real-time monitored rice growth parameter data into the first mathematical model, and generate preliminary environmental parameter control instructions, the preliminary environmental control instructions include specific control values ​​of temperature, humidity, light intensity, and water quality parameters; Second mathematical model unit: based on the correlation analysis between environmental parameters and aquatic product growth parameters, establish a second mathematical model between environmental parameters and aquatic product growth parameters, import the preliminary environmental parameter control instructions into the second mathematical model, and predict the impact of the preliminary environmental parameters on the growth of aquatic products; Comprehensive adjustment unit: According to the prediction results of the second mathematical model combined with the constraints, the preliminary environmental parameter control instructions are adjusted to generate the final comprehensive control adjustment plan to meet the environmental requirements of rice planting and aquaculture at the same time; Control execution module: connected to the data processing module, used to adjust the breeding environment according to the final comprehensive control and adjustment plan.

2. The rice planting and aquaculture integrated intelligent monitoring system according to claim 1, It is characterized in that The water temperature sensors are arranged at different depths of the water layer in the rice field to monitor the surface, middle and bottom temperatures of the water body and obtain temperature data of different water layers in the rice field; The humidity sensor comprises: Air humidity sensor: installed above the rice field to monitor air humidity and capture humidity data of the rice field environment; Soil moisture sensors: installed in the soil of rice fields at different depths to monitor soil moisture changes and ensure that the humidity of rice roots is appropriate; The water quality sensors are arranged at different positions and depths of the water layer in the rice field, including: pH sensor: installed on the surface, middle and bottom layers of the rice field to monitor the pH value of the water and ensure that the water quality is suitable for the growth of rice and aquatic products; Dissolved oxygen sensor: installed at different depths in the rice field to monitor the dissolved oxygen content of the water to ensure that the growth environment of aquatic products has sufficient oxygen supply; Ammonia nitrogen sensor: installed at different depths in the rice fields to monitor the ammonia nitrogen content in the water to ensure that the water quality meets the healthy growth requirements of aquatic products; The light sensor is arranged directly above the rice field to monitor the light intensity and ensure that the light conditions are suitable for the growth of rice and aquatic products; The rice growth parameters include plant height, number of leaves, chlorophyll content, and stem diameter; The aquatic product growth parameters include body length and body weight.

3. The rice planting and aquaculture integrated intelligent monitoring system according to claim 1, It is characterized in that The correlation analysis between the environmental data and rice growth parameters and the correlation analysis between the environmental parameters and aquatic product growth parameters are both performed using the Pearson correlation coefficient; The Pearson correlation coefficient was used to analyze the relationship between environmental data and rice growth parameters to determine the environmental parameters that affect rice growth. The Pearson correlation coefficient was used to analyze the relationship between environmental data and aquatic product growth parameters to determine the environmental parameters that affect aquatic product growth. The environmental parameters that affect rice growth and aquatic product growth include temperature T, humidity H, light intensity L, and water quality parameter W.

4. The integrated intelligent monitoring system for rice planting and aquaculture according to claim 3, It is characterized in that The use of the Pearson correlation coefficient to analyze the relationship between environmental data and rice growth parameters to determine the environmental parameters that have an impact on rice growth specifically includes: Collect various environmental data and rice growth parameters; The relationship between environmental data and rice growth parameters was analyzed using the Pearson correlation coefficient, expressed as: Among them, r xy is the correlation coefficient between environmental parameter x and rice growth parameter y, x i and i are the data points of environmental parameters and rice growth parameters, and is its mean value.

5. The integrated intelligent monitoring system for rice planting and aquaculture according to claim 4, It is characterized in that The first mathematical model and the second mathematical model both adopt a multiple linear regression model, and the first mathematical model established between the environmental parameters and the rice growth parameters specifically includes: Use historical data and experimental data to train the multivariate linear regression model and determine the model parameters: y = β 0 +β 1 T+β 2 H+β 3 L+β 4 W, where y is the rice growth parameter, including plant height, number of leaves, chlorophyll content, stem diameter, β 0 is a constant term, β 1 , β 2 , β 3 , β 4 is the regression coefficient; T is temperature, H is humidity, L is light intensity, and W is water quality parameter; The real-time environmental parameter data is input into the first mathematical model, and the environmental parameters are adjusted according to the model prediction of the impact of the current environmental conditions on the future rice growth. Based on the model prediction results, preliminary environmental parameter control instructions are generated to adjust the temperature, humidity, light intensity and water quality parameters to optimize the rice growth conditions: T control =f temp (T real ,H real ,L real ,W real ,y real ); H control =f humid (T real ,H real ,L real ,W real ,y real ); L control =f light (T real ,H real ,L real ,W real ,y real ); W control =f water (r real ,H real ,L real ,W real ,y real ); Among them, f temp , f humid , f light , f water is the control function calculated by the model, which is used to generate the specific control value of each environmental parameter, T control is the temperature control value of the preliminary environmental control instruction; H control is the humidity control value of the preliminary environmental control instruction; L control is the light intensity control value of the preliminary environment control instruction; W control The water quality parameter control values ​​for the preliminary environmental control directive.

6. The integrated intelligent monitoring system for rice planting and aquaculture according to claim 5, It is characterized in that The regression coefficient β 0 , β 1 , β 2 , β 3 , β 4 Based on the gradient descent method, the loss function is minimized through iterative optimization, which is expressed as: Among them, y i is the rice growth parameter of the ith sample, T i , H i , L i , W i are the temperature, humidity, light intensity and water quality parameters of the i-th sample, respectively, and n is the total number of samples; Update the regression coefficients using the gradient descent algorithm: Among them, α is the learning rate.

7. The integrated intelligent monitoring system for rice planting and aquaculture according to claim 5, It is characterized in that The second mathematical model is expressed as: z = γ 0 +γ 1 T+γ 2 H+γ 3 L+γ 4 W, Among them, z is the growth parameter of aquatic products, including body length and weight, γ 0 is a constant term, γ 1 , γ 2 , γ 3 , γ 4 is the regression coefficient; The step of importing the preliminary environmental parameter control instruction into the second mathematical model to predict the effect of the preliminary environmental parameter on the growth of aquatic products specifically includes: The generated preliminary environmental parameter control instructions are input into the second mathematical model, and the effect of the preliminary environmental parameter control instructions on the growth of aquatic products is predicted according to the second mathematical model, and the changes in the length or weight of the aquatic products under the control instructions are predicted: Predicted_Fish_Length=γ 0L +g 1L T control +g 2L H control +g 3L L control +g 4L W control ; Predicted_Fish_Weight=γ 0W +g 1W T control +g 2W H control +g 3W L control +g 4W W control ; Among them, T control , H control , L control, W control The specific control values ​​of temperature, humidity, light intensity and water quality parameters in the preliminary environmental parameter control instructions; γ 0L , γ 1L , γ 2L , γ 3L , γ 4L and γ 0W , γ 1W , γ 2 W, γ 3W , γ 4W is the regression coefficient determined by gradient descent, γ 0L , γ 1L , γ 2L , γ 3L , γ 4L is the regression coefficient used to predict the body length of aquatic products; 0W , γ 1W , γ 2W , γ 3 W, γ 4W is the regression coefficient used to predict the weight of aquatic products.

8. The integrated intelligent monitoring system for rice planting and aquaculture according to claim 7, It is characterized in that The comprehensive adjustment unit specifically includes: Obtain preliminary environmental parameter control instructions on the impact of aquatic product growth; Define constraints: including the growth requirements of rice and aquatic products, and the reasonable range of environmental parameters: T min ≤T≤T max ; H min ≤H≤H max ; L min ≤L≤L max ; IN min ≤W≤W max ; Multi-objective optimization: Through the multi-objective particle swarm optimization algorithm, various environmental parameters are optimized under constraints to simultaneously meet the growth requirements of rice and aquatic products. The optimization objectives include: Rice growth optimization: maximizing rice growth parameters; Aquaculture Growth Optimization: Maximizing aquaculture growth parameters.

9. The rice planting and aquaculture integrated intelligent monitoring system according to claim 8, It is characterized in that The multi-objective particle swarm optimization algorithm specifically includes: Initialize the particle swarm, each particle represents an environmental parameter combination x = (T, H, L, W), initialize the speed v of each particle, set the initial position and speed of each particle to random values, and generate them within the parameter range; Fitness evaluation: Calculate the fitness value of each particle, evaluate the rice growth parameters and aquatic product growth parameters respectively, let f1 represent the optimization target of rice growth, f2 represent the optimization target of aquatic product growth, the goal of multi-objective optimization is to optimize f1 and f2 at the same time, to find a compromise solution, so that both rice and aquatic products can grow in the best environment: f 1 (x)=a 1 (b 0 +b 1 T+β 2 H+β 3 L+β 4 W); f 2 (x) = α 2 (γ 0 +γ 1 T+γ 2 H+γ 3 L+γ 4 W); where α 1 and α 2 are the weight coefficients of rice and aquatic product growth parameters, respectively; Update the individual optimal solution p of each particle i and the global optimal solution g, maintaining the Pareto frontier solution set; Update the particle's velocity and position: v i (t+1)=ωv i (t)+c 1 r 1 (p i -x i (t))+C 2 r 2 (g-x i (t)); x i (t+1)=x i (t)+v i (t+1); Among them, v i (t+1) is the velocity of the ith particle at the t+1th iteration, ω is the inertia weight, which controls the inertia of the particle movement, and c 1 , c 2 is the acceleration coefficient, which controls the acceleration of particles to the individual optimal solution and the global optimal solution respectively, r 1 , r 2 is a random number between 0 and 1, increasing the randomness of the particles, p i is the individual optimal position of the ith particle, g is the global optimal position, x i (t) is the position of the ith particle at the tth iteration, x i (t+1) is the position of the i-th particle at the t+1th iteration; Check and correct the current position of the particle to make it meet the constraints of the environmental parameters; Repeat fitness evaluation, update of individual and global optimal solutions, speed and position update, and constraint condition check until the predetermined number of iterations or convergence conditions are reached; select the optimal solution from the Pareto front solution set as the final environmental parameter combination T final , H final , L final , W final .

10. The integrated intelligent monitoring system for rice planting and aquaculture according to claim 1, It is characterized in that The control execution module specifically includes: Irrigation control unit: adjusts the water supply in the rice planting environment according to the control instructions to ensure the normal growth of rice; Water quality treatment control unit: adjusts the water quality treatment system according to control instructions, maintains appropriate water quality parameters in the water body, and ensures the healthy growth of aquatic products; Lighting control unit: adjusts the lighting system according to control instructions to provide required lighting conditions; Temperature control unit: adjusts the water temperature control system according to the control instructions to provide the required temperature conditions.

Citation Information

Cited By

  • Paddy field aquaculture intelligent management system based on Internet of Things

    CN119937693A

  • Method and system for monitoring collaborative ecological breeding environment of freshwater shrimps and hydroponic Chinese chives

    CN120226631A

  • Remote mining area image processing method and system

    CN120374441A

  • Remote mine site image processing method and system

    CN120374441B

  • Wireless multi-sensing data monitoring terminal system for smart rice and fish

    CN120800473A