Accurate irrigation control system and method for substrate cultivation

Abstract

The invention belongs to the technical field of agricultural cultivation, and particularly relates to a precise irrigation control system and method for substrate cultivation. The method specifically comprises the following steps: monitoring multi-parameter data, namely a soil humidity index, a plant physiological index and an environmental factor index, in real time through a multi-parameter sensor, and transmitting the data in a wired or wireless manner; the collected multi-parameter data are preprocessed, and then predicted plant water demand is obtained by using an intelligent decision algorithm and is displayed through a visual platform; the on-off state and the flow of the irrigation equipment are automatically adjusted through the control circuit according to the predicted water demand of the plants, the actual water demand of the plants can be accurately matched through multi-parameter monitoring and an intelligent decision algorithm, the situation of excessive or insufficient irrigation is reduced, the irrigation efficiency and the water resource utilization rate are improved, and accurate irrigation is achieved.

Description

Technical Field

[0001] The invention belongs to the technical field of agricultural cultivation, and specifically relates to a substrate cultivation precision irrigation control system and method. Background Art

[0002] As an efficient and environmentally friendly planting method, substrate cultivation is highly favored because it can precisely control the plant growth environment. Currently, there are many substrate cultivation irrigation systems on the market, which mainly control the irrigation amount through preset time intervals or soil moisture thresholds to meet the basic water needs of plant growth.

[0003] However, these existing technical solutions have the following significant disadvantages: (1) Insufficient irrigation accuracy: Traditional irrigation systems often use a unified time or humidity standard for irrigation, ignoring the differences in water demand of plants at different growth stages and under different weather conditions, resulting in excessive or insufficient irrigation, which affects the quality of plant growth. (2) Waste of resources: Imprecise irrigation strategies can easily lead to waste of water resources and nutrients, especially in areas with tight water resources. (3) Lack of intelligent management: Most existing systems lack intelligent monitoring and dynamic adjustment mechanisms, and are unable to flexibly adjust irrigation strategies in real time according to the actual growth conditions of plants and changes in the external environment. Therefore, a substrate cultivation precision irrigation control system and method are proposed to solve the above problems. Summary of the invention

[0004] The present invention provides a substrate cultivation precision irrigation control system and method, which are used to solve the technical problems of low precision, waste of resources and lack of intelligent management of existing irrigation systems.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0006] A method for controlling precise irrigation of substrate cultivation, comprising:

[0007] (1) Multi-parameter data monitoring and transmission: Multi-parameter sensors are used to monitor multi-parameter data in real time, namely soil moisture index, plant physiological index and environmental factor index. The plant physiological index includes leaf water potential x yp , stomatal conductance x qd , transpiration rate x zt The environmental factor index includes the ambient temperature x ht , humidity x sd , light intensity x gq ,The data collected by multi-parameter sensors are transmitted in real time via wireless or wired means;

[0008] (2) Data processing and analysis: preprocessing the collected multi-parameter data, including data cleaning, data standardization and data normalization, and then using an intelligent decision-making algorithm to obtain the predicted plant water requirement, which is displayed on a visualization platform;

[0009] (3) Precise control of irrigation equipment: By predicting the water demand of plants, the switch status and flow rate of irrigation equipment are automatically adjusted through the control circuit.

[0010] Furthermore, the intelligent decision-making algorithm uses an RNN-CNN ensemble model, takes soil moisture indicators, plant physiological indicators, and environmental factor indicators as input layers, performs feature learning and nonlinear transformation through multiple hidden layers, and finally outputs the predicted plant water requirement.

[0011] Furthermore, the specific process of the RNN-CNN ensemble model is as follows: Assume that the network input x is M-dimensional: x = [x1, x2, ..., x M ] T The hidden layer has a total of K nodes, the output y is L-dimensional, the length of the input and output sample pairs is N, and the function of the hidden layer node of the radial basis network is

[0012] The hidden layer of the RBF network realizes the linear mapping of the conversion dimension to the output layer, and outputs it to the workspace as an important control variable according to different backgrounds; the above is the input x i The preprocessed multi-parameter data, the output y is the amount of water required by the plant.

[0013] Furthermore, the RNN-CNN ensemble model is trained and optimized by dividing the preprocessed data into a training set and a test set, using the training set data to train the model, and optimizing the model parameters by back propagation algorithm or gradient descent method.

[0014] A substrate cultivation precision irrigation control system comprises a multi-parameter monitoring module, a data processing module, a data analysis module, a data display module and a control center. The multi-parameter monitoring module transmits the collected data to the data processing module in real time by wireless or wired means. The data processing module pre-processes the collected data. The data analysis module calculates the pre-processed data using an intelligent decision-making algorithm. The calculated results are displayed by the data display module.

[0015] Furthermore, the control center also includes a control circuit that can automatically adjust the switch state and flow rate of the irrigation equipment.

[0016] Furthermore, the data display module presents the growth status of the plant and the calculation results of the data analysis module in real time.

[0017] Compared with the prior art, the present invention has the following beneficial effects:

[0018] (1) High irrigation accuracy: Through multi-parameter monitoring and intelligent decision-making algorithms, it can accurately match the actual water demand of plants, reduce over-irrigation or under-irrigation, and improve irrigation efficiency and water resource utilization.

[0019] (2) Resource conservation: Precision irrigation can effectively avoid the waste of water resources and nutrients, especially in areas with water shortages, and has a significant water-saving effect.

[0020] (3) High level of intelligent management: The system has the ability to automatically learn and dynamically adjust, and can automatically optimize irrigation strategies as the plant growth cycle and external environment changes, reducing the cost of manual intervention and improving management efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a structural diagram of the substrate cultivation precision irrigation control system of the present invention;

[0022] Figure 2 To invent a precise irrigation control circuit for substrate cultivation. DETAILED DESCRIPTION

[0023] The present invention is described in detail below in conjunction with specific embodiments. The following embodiments will help those skilled in the art to further understand the present invention, but are not intended to limit the present invention in any form. It should be noted that, for those of ordinary skill in the art, several changes and improvements can also be made without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

[0024] A method for controlling precise irrigation of substrate cultivation, comprising:

[0025] (1) Multi-parameter data monitoring and transmission: Multi-parameter sensors are used to monitor multi-parameter data in real time, namely soil moisture index, plant physiological index and environmental factor index. The plant physiological index includes leaf water potential x yp , stomatal conductance x qd , transpiration rate x zt The environmental factor index includes the ambient temperature x ht , humidity x sd , light intensity x gq ,The data collected by multi-parameter sensors are transmitted in real time via wireless or wired means;

[0026] Soil moisture monitoring: Soil moisture is one of the important factors affecting plant growth. Soil moisture sensors use advanced capacitive or resistive measurement principles to accurately measure soil moisture content at different depths. These sensors are distributed at different levels of the cultivation matrix to obtain more comprehensive soil moisture information and provide more refined data support for irrigation decisions.

[0027] Plant physiological indicator monitoring: Plant physiological indicators are direct indicators that reflect the internal physiological state and water demand of plants. Among them, leaf water potential is a key parameter for measuring the water status of plants. Through non-contact or minimally invasive leaf water potential sensors, it is possible to monitor the water potential changes of plant leaves in real time and then evaluate the water demand of plants. In addition, other physiological indicator sensors, such as stomatal conductance, transpiration rate, etc., can be integrated according to needs to further improve the comprehensiveness and accuracy of monitoring.

[0028] Environmental factor monitoring: In addition to soil moisture and plant physiological indicators, environmental factors such as ambient temperature, humidity, and light intensity also have an important impact on plant growth and water requirements. Temperature sensors, humidity sensors, and light intensity sensors can collect and transmit these environmental parameters to the control center in real time.

[0029] (2) Data processing and analysis: preprocessing the collected multi-parameter data, including data cleaning, data standardization and data normalization, and then using an intelligent decision-making algorithm to obtain the predicted plant water requirement, which is displayed on a visualization platform;

[0030] The collected soil moisture, plant physiological indicators (leaf water potential x yp , stomatal conductance x qd , transpiration rate x zt ), environmental factors (ambient temperature x ht , humidity x sd , light intensity x gq ) for preprocessing and in-depth analysis. The specific process is as follows:

[0031] Data cleaning: By setting reasonable thresholds and filtering algorithms, noise and outliers are removed to ensure data accuracy and reliability. The standard deviation method is used to identify and process outliers. For each data point x i (Soil moisture, plant physiological indicators, environmental factors x i =ω yp ·x ypi +ω qd ·x qdi +ω zt ·x zti +ω ht ·x hti +ω sd ·x sdi +ω gq ·x gqi , i∈{1,2,3...,N},), where ω xx is the normalized weight value. Calculate its average value The difference χ i =x i-u, and with standard deviation If the difference χ i If the value of -s exceeds the threshold m=3s (3 times the standard deviation), the data point is considered an outlier and is removed or replaced.

[0032] Data standardization: Standardize data from different sources and units so that they can be compared and analyzed on the same scale, using improved Z-score standardization. Among them, x is the multi-parameter data after data cleaning, μ is the mean of the data, and σ is the standard deviation of the data. After standardization, the mean of the data is 0 and the standard deviation is 1.

[0033] Data normalization: Through the normalization algorithm, the data is converted into a dimensionless value between 0 and 1, which is convenient for subsequent algorithm processing and analysis. Minimum-maximum normalization formula: Among them, x is the exercise tolerance data after data cleaning and standardization, x min and x max are the minimum and maximum values ​​in the data respectively. After normalization, the value range of the data is between 0 and 1.

[0034] Intelligent decision-making algorithm to select RNN-CNN ensemble model:

[0035] Assume that the network input x is M-dimensional: x = [x1, x2, ..., x M ] T The hidden layer has a total of K nodes, the output y is L-dimensional, the length of the input and output sample pairs is N, and the action function of the radial basis network hidden layer nodes is the Gaussian basis function:

[0036]

[0037] The input data vector is mapped to the hidden layer, and the output of the hidden layer node j is:

[0038]

[0039] Where: δ is the standardization constant of the hidden layer nodes, c is the center vector of the Gaussian function of the hidden layer nodes, c j =[c j1 ,c j2 ,...,c jM ] T ,

[0040] The hidden layer to output layer of the RBF network realizes a linear mapping of the conversion dimension, that is, the output of the output layer node k is:

[0041]

[0042] Where:jk is the adjustment weight from the hidden layer to the output layer; θ k is the bias of the output layer node k. k As a response to the corresponding input signal, it is output to the workspace as an important regulatory variable according to different backgrounds.

[0043] The input x is the feature data, that is,

[0044] x i =ω yp ·x ypi +ω qd ·x qdi +ω zt ·x zti +ω ht ·x hti +ω sd ·x sdi +ω gq ·x gqi , i∈{1,2,3...,N}, the output y is the amount of water required by the plant.

[0045] Neural network model: soil moisture, plant physiological indicators, and environmental factors are used as input layers, and feature learning and nonlinear transformation are performed through multiple hidden layers to ultimately output the predicted plant water requirement.

[0046] Utilize multiple network layers for ensemble learning to improve prediction accuracy through voting or averaging.

[0047] Model training and optimization:

[0048] Training data: Divide the preprocessed data into training set and test set.

[0049] Training process: Use the training set data to train the model and optimize the model parameters through the back propagation algorithm or gradient descent method.

[0050] Hyperparameter tuning: Adjust model hyperparameters such as learning rate, number of iterations, number of hidden layer nodes, etc. through cross-validation, grid search and other methods to improve model performance.

[0051] Real-time data display: The visualization platform can display key information such as plant growth status, irrigation records and environmental parameters in real time. Users can intuitively understand the growth of plants and irrigation effects through charts, curves, etc. At the same time, the platform also supports historical data query and comparative analysis functions to help users better understand the laws and trends of plant growth.

[0052] (3) Precise control of irrigation equipment: By predicting the water demand of plants, the switch status and flow rate of irrigation equipment are automatically adjusted through the control circuit.

[0053] like Figure 2 The control circuit shown: firstly, the water requirement y of the plant is encoded through the encoder and connected to relay1. When the Realay1 interface inputs a low level, the transistor is in the off state and the relay does not work, so the irrigation equipment is automatically adjusted to not work. When a high level is connected, the transistor is in the on state after the voltage is divided by the current limiting resistor R14. At this time, the induction coil in the relay passes the current, generates a magnetic field, and Vout outputs a 12V voltage, which stimulates the irrigation equipment to work, thereby controlling the flow rate.

[0054] A substrate cultivation precision irrigation control system includes a multi-parameter monitoring module, a data processing module, a data analysis module, a data display module and a control center. The multi-parameter monitoring module transmits the collected data to the data processing module in real time by wireless or wired means. The data processing module pre-processes the collected data. The data analysis module calculates the pre-processed data using an intelligent decision-making algorithm, and the calculated results are displayed by the data display module. The control center also includes a control circuit that can automatically adjust the switch state and flow size of the irrigation equipment.

[0055] The data display module presents the growth status of the plant and the calculation results of the data analysis module in real time.

[0056] The above describes the specific embodiments of the present invention. It should be understood that the present invention is not limited to the above specific embodiments, and those skilled in the art can make various changes or modifications within the scope of the claims, which does not affect the essence of the present invention. In the absence of conflict, the embodiments of the present application and the features in the embodiments can be combined with each other arbitrarily.

Claims

1. A method for precise irrigation control of substrate cultivation, characterized in that: The method comprises: (1) Multi-parameter data monitoring and transmission: Multi-parameter sensors are used to monitor multi-parameter data in real time, namely soil moisture index, plant physiological index and environmental factor index. The plant physiological index includes leaf water potential x yp , stomatal conductance x qd , transpiration rate x zt The environmental factor index includes the ambient temperature x ht , humidity x sd , light intensity x gq ,The data collected by multi-parameter sensors are transmitted in real time via wireless or wired means; (2) Data processing and analysis: preprocessing the collected multi-parameter data, including data cleaning, data standardization and data normalization, and then using an intelligent decision-making algorithm to obtain the predicted plant water requirement, which is displayed on a visualization platform; (3) Precise control of irrigation equipment: By predicting the water demand of plants, the switch status and flow rate of irrigation equipment are automatically adjusted through the control circuit.

2. A substrate cultivation precision irrigation control method according to claim 1, characterized in that: The intelligent decision-making algorithm uses the RNN-CNN ensemble model, takes soil moisture indicators, plant physiological indicators, and environmental factor indicators as input layers, performs feature learning and nonlinear transformation through multiple hidden layers, and finally outputs the predicted plant water requirement.

3. A substrate cultivation precision irrigation control method according to claim 2, characterized in that: The specific process of the RNN-CNN ensemble model is as follows: Assume that the network input x is M-dimensional: x = [x1, x2, ..., x M ] T The hidden layer has a total of K nodes, the output y is L-dimensional, the length of the input and output sample pairs is N, and the action function of the hidden layer nodes of the radial basis network.

4. A substrate cultivation precision irrigation control method according to claim 3, characterized in that: The hidden layer of the RBF network realizes the linear mapping of the conversion dimension to the output layer, and outputs it to the workspace as an important control variable according to different backgrounds; the above is the input x i is the preprocessed multi-parameter data, and the output y is the amount of water required by the plant.

5. A substrate cultivation precision irrigation control method according to claim 4, characterized in that: The RNN-CNN ensemble model is trained and optimized by dividing the preprocessed data into a training set and a test set, using the training set data to train the model, and optimizing the model parameters by a back propagation algorithm or a gradient descent method.

6. A substrate cultivation precision irrigation control system, characterized in that: A method for controlling substrate cultivation precision irrigation according to any one of claims 1 to 5, comprising: It includes a multi-parameter monitoring module, a data processing module, a data analysis module, a data display module and a control center. The multi-parameter monitoring module transmits the collected data to the data processing module in real time via wireless or wired means. The data processing module pre-processes the collected data. The data analysis module uses an intelligent decision-making algorithm to calculate the pre-processed data, and the calculated results are displayed through the data display module.

7. A substrate cultivation precision irrigation control system according to claim 6, characterized in that: The control center also includes a control circuit that can automatically adjust the switch status and flow rate of the irrigation equipment.

8. A substrate cultivation precision irrigation control system according to claim 6, characterized in that: The data display module presents the growth status of the plant and the calculation results of the data analysis module in real time.

Images