Intelligent root temperature regulation and control system for hydroponic crops and implementation method of intelligent root temperature regulation and control system

Abstract

The invention relates to the technical field of temperature regulation, in particular to an intelligent root temperature regulation system for hydroponic crops and an implementation method thereof, and the system comprises a root system oxygen consumption monitoring module, an osmotic pressure state monitoring module, a root system metabolism state analysis module, a root temperature parameter reconstruction module and a nutrient solution circulation linkage module. According to the method, the metabolic rhythm state of the root system is judged through oxygen consumption rate gradient difference calculation and trend analysis, the cell injury risk is recognized through two-parameter logic judgment by combining the osmotic pressure change amplitude and the oxygen consumption trend, and the target root temperature is selected through gray correlation analysis according to the abnormal triggering temperature and the stable state temperature; a regulation and control instruction is generated, a PID algorithm is called in combination with real-time circulation flow velocity data to adjust the pump speed, closed-loop dynamic matching of a root temperature set value and a flow velocity behavior is achieved, the adaptability of root temperature response is enhanced, the real-time regulation and control capacity for metabolic imbalance is improved, and the stability and the moisture and nutrient absorption efficiency of a water culture environment root system are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature regulation, and particularly to an intelligent root temperature control system for hydroponic crops and a method for realizing the same. Background Art

[0002] The technical field of temperature regulation includes precise management technologies for key parameters of plant growth in agricultural environment control. Its core content focuses on real-time monitoring of environmental variables through a sensor network and dynamically adjusting the operating state of devices based on a feedback mechanism. This field systematically integrates a technical system of temperature acquisition devices, control units, and actuators, and mainly solves the impact of environmental parameter fluctuations on crop physiological activities in protected agriculture. Especially in hydroponic systems, the stable control of root temperature directly affects the nutrient solution absorption efficiency and plant metabolism rate. Existing technologies mostly use fixed threshold control or manual intervention methods to adjust water temperature, lacking the ability to adaptively regulate to the dynamic changes of the root microenvironment.

[0003] Among them, an intelligent root temperature control system for hydroponic crops refers to real-time collecting rhizosphere water temperature data through distributed temperature probes, constructing a multi-node temperature field model in combination with the structural characteristics of the cultivation container, and triggering a gradient temperature control strategy based on a preset threshold range. This system specifically includes a flow rate adjustment device for the circulating water path, a heat exchanger power control unit, and a redundant temperature compensation mechanism, uses a temperature difference prediction method based on time series analysis to drive the linkage of actuators, realizes the uniform distribution of the root temperature field through hydrodynamic optimization design, and separates the logical processing processes of the data acquisition layer and the device drive layer using a hierarchical control architecture.

[0004] Existing technologies mostly rely on temperature field models and time series prediction methods to execute control instructions. Although multi-node regulation of root temperature is achieved, there are lag problems in identifying abnormal root metabolism. The fundamental reason is that the regulation mechanism usually only triggers based on the change trend of water temperature itself, without introducing a real-time feedback path for the physiological state of the crop. As a result, at the initial stage of temperature fluctuation, the system is difficult to capture the signal of functional changes in the roots in a timely manner, resulting in response delays. For example, in the high-temperature stage, although the root temperature does not exceed the set upper limit, the roots have already experienced metabolic imbalance, and the system still maintains a slow adjustment state, further aggravating root damage. And in existing technologies, static thresholds are mostly used to set the temperature range, which cannot adapt to the dynamic changes of the roots, and it is easy to have frequent misadjustments or control idling due to inaccurate set values, reducing the sensitivity and regulation efficiency of the control system. Summary of the Invention

[0005] In order to solve the technical problems existing in the prior art, an embodiment of the present invention provides an intelligent root temperature control system for hydroponic crops and a method for realizing the same. The technical solution is as follows: On the one hand, an intelligent root temperature control system for hydroponic crops is provided, and the system includes: The root oxygen consumption monitoring module collects root oxygen concentration data in real time, calculates the root oxygen consumption rate gradient, judges the trend state of the oxygen consumption gradient based on a multivariable nonlinear coupling model, and transmits it to the osmotic pressure state monitoring module; The osmotic pressure state monitoring module obtains the cell osmotic pressure change data, performs a difference calculation in combination with the oxygen consumption gradient trend state to obtain the dynamic offset of the osmotic pressure change, and transmits it to the root metabolism state analysis module; The root metabolism state analysis module, based on the oxygen consumption gradient trend state and the dynamic offset of the osmotic pressure change, and by weighting the pore connectivity and root depth, inputs a multi-condition state machine model to judge the damage risk level, obtains the determination result of the metabolic abnormal state, and transmits it to the root temperature parameter reconstruction module; The root temperature parameter reconstruction module compares the metabolic abnormal trigger temperature with the root temperature before the occurrence of the abnormal state in the determination result of the metabolic abnormal state, generates a root temperature regulation instruction, and transmits it to the nutrient solution circulation linkage module; The nutrient solution circulation linkage module receives the root temperature regulation instruction, obtains the circulation flow rate data in real time, and calls the PID control algorithm to adjust the rotation speed of the circulation pump.

[0006] As a further solution of the present invention, the oxygen consumption gradient trend state includes a gradient direction vector, a change frequency feature, and an amplitude fluctuation range. The dynamic offset of the osmotic pressure change is the maximum positive deviation value, the maximum negative deviation value, and the offset duration. The determination result of the metabolic abnormal state includes the abnormal condition category, the cell risk rating, and the root temperature at the corresponding moment. The root temperature regulation instruction is the target temperature range, the regulation mode code, and the instruction effective time. The regulation result of adjusting the rotation speed of the circulation pump includes the set rotation speed value, the expected flow rate target, and the PID output parameter.

[0007] As a further solution of the present invention, the root oxygen consumption monitoring module includes: The oxygen concentration acquisition sub-module: monitors the original signal of the oxygen concentration in the root area of the dissolved oxygen through a dissolved oxygen sensor, performs smoothing processing on the original oxygen concentration signal by using low-pass filtering, and automatically adjusts the filtering window length according to the pore connectivity. The lower the porosity, the larger the window length. At the same time, by constraining the boundary value of the filtering window length, a Gaussian white noise characteristic map is superimposed to perform differential noise reduction, and the data points are position-calibrated according to the three-dimensional Cartesian coordinate system to generate an oxygen concentration time series set; The pore connectivity index is obtained by performing a CT scan on the soil sample and analyzing the geometric shape, size, distribution, and connection mode of the pores through Avizo to obtain the connectivity index; Gradient calculation sub-module: Invoke the oxygen concentration time series set, calculate the concentration difference between adjacent points within a continuous time window, perform specified time normalization processing on the concentration difference, construct a spatial gradient field using piecewise interpolation method, introduce radial basis function to compensate for missing boundary data, and generate a gradient distribution rate; Trend judgment sub-module: Analyze the gradient distribution rate through a multi-variable non-linear coupling model, obtain root depth data through the root profile sampling method, measure the total porosity by the cutting ring method, obtain soil porosity parameters in combination with the mercury intrusion method, integrate the root depth data and soil porosity parameters, calculate the diffusion rate of the root oxygen consumption rate gradient field in the direction of the pore connectivity index, adjust the diffusion resistance coefficient inside the non-linear coupling model by the volumetric water content measured in-situ by the time domain reflectometer, generate an oxygen consumption gradient trend state, and transfer it to the osmotic pressure state monitoring module.

[0008] As a further solution of the present invention, smooth the original oxygen concentration signal, using the formula: ; wherein, CLPF(m) is the output after filtering, which is the smoothing result of taking the mean value of the data within the window near index m in the original signal, N represents the window length, which is the total number of data points included in the filtering window participating in the average calculation, and is dynamically adjusted according to the pore connectivity index, represents the original data sequence, which is the input signal sequence without filtering processing, m represents the current index, which is the target data position where the filtered value needs to be calculated, represents the currently processed signal point, j is the offset for the current index m, used to traverse all data points within the window, represents the mean coefficient, represents the unilateral offset, which is the number of data points on both sides of the window center point, N - 1 represents the window symmetric offset, which is the window total width minus 1.

[0009] As a further solution of the present invention, the osmotic pressure state monitoring module includes: Osmotic pressure acquisition sub-module: Configure a digital temperature sensor to monitor the root temperature, deploy sensor nodes at depth intervals, synchronously collect temperature data, record the osmotic pressure at fixed time intervals, and generate an osmotic pressure time series set including temperature compensation parameters; Gradient difference sub-module: Invoke the osmotic pressure time series set, combine the root temperature data collected by the digital temperature sensor, calculate the temperature-compensated osmotic pressure, extract the osmotic pressure difference within adjacent time windows, and superimpose the oxygen consumption gradient trend state to generate an osmotic pressure gradient difference; Change amplitude sub-module: Invoke the peak-valley extreme values in the osmotic pressure gradient difference, calculate the moving window mean of the absolute value of the peak-valley difference, with a window length of 5 minutes. Adjust the moving window mean through the temperature compensation parameter, where the temperature compensation coefficient = 0.1 × real-time temperature change rate, generate the dynamic offset of osmotic pressure change, and transfer it to the root metabolic state analysis module.

[0010] As a further aspect of the present invention, the root metabolic state analysis module includes: Damage risk sub-module: Invoke the dynamic offset of osmotic pressure change and the oxygen consumption gradient trend state, calculate the covariance between the two within a continuous time window, extract the main diagonal elements of the covariance, and compare them item by item with a preset damage risk threshold to generate a damage risk coefficient; the damage risk threshold is determined by the covariance extreme value when the cell damage probability > 90% in past data; State integration sub-module: Invoke the damage risk coefficient, superimpose the real-time temperature data, and perform linear interpolation on the damage risk coefficient according to the temperature segmented interval to generate a metabolic state vector; Model analysis sub-module: Input the metabolic state vector into a multi-condition state machine model, define the damage risk coefficient and temperature value as state transition conditions, and allocate weights through pore connectivity and root depth. Input the multi-condition state machine model to judge the damage risk level, calculate the Manhattan distance between the current state and the metabolic abnormal mode, generate a metabolic abnormal state determination result, and transfer it to the root temperature parameter reconstruction module; The weight factor of the Manhattan distance is dynamically adjusted according to the cell risk rating; the multi-condition state machine model is constructed based on the discrete metabolic states in root physiology, setting based on the damage risk coefficient and logical rules, and determining the target metabolic abnormal mode.

[0011] As a further aspect of the present invention, the root temperature parameter reconstruction module includes: Temperature data sub-module: Obtain the stable state root temperature data in the metabolic abnormal state determination result for standardization processing, and generate a temperature data set including time stamps and temperature feature markers; Correlation analysis sub-module: Invoke the temperature data set, traverse the corresponding data points of the metabolic abnormal trigger temperature sequence and the stable state temperature sequence, calculate the absolute difference of each data point, extract the minimum and maximum values of all differences, and based on the grey correlation analysis algorithm, call the resolution coefficient ρ = 0.5 to calculate the correlation coefficient of each data point, and take the arithmetic mean of all correlation coefficients to generate the correlation degree coefficient within the time window; Regulation instruction sub-module: Invoke the correlation coefficient, compare the coefficient sequence with the correlation threshold item by item, screen out the nodes with coefficients lower than the correlation threshold, extract the temperature adjustment amplitude and direction data corresponding to the time stamps of the nodes, and generate root temperature regulation instructions; the correlation threshold determines the optimal classification performance value through the point corresponding to the maximum Youden index on the ROC curve.

[0012] As a further solution of the present invention, the nutrient solution circulation linkage module includes: Instruction parsing sub-module: Receive the root temperature regulation instruction, parse the temperature adjustment amplitude and time stamp parameters in the instruction, screen out the timeout instructions based on the time stamp alignment rule, and generate the aging regulation parameters matching the current clock. Flow rate dynamic sub-module: Invoke the time window of the aging regulation parameters, collect the original flow rate data of the electromagnetic flowmeter, set the number of samples for moving average filtering according to the time window length, eliminate the noise interference, and generate the flow rate dynamic baseline synchronized with the temperature regulation time sequence. Rotation speed decision sub-module: Invoke the temperature adjustment amplitude in the aging regulation parameters and the flow rate dynamic baseline, based on the PID control algorithm, map the temperature amplitude to the target flow rate increment, calculate the deviation value between the current flow rate baseline and the target increment, superimpose the proportional term, integral term, and differential term, and adjust the rotation speed of the circulation pump; the parameter tuning method of the PID control algorithm Kp, Ki, Kd adopts the Ziegler-Nichols critical ratio method, the Kp range is the parameter range optimized through 50 flow rate step response experiments, and the obtained Kp range is 0.5 - 5.0, Ki 0.01 - 0.5, Kd 0.1 - 2.0. For every 10 L / min increase in the flow rate, Kp is increased by 10% - 30%, and Ki is decreased by 5% - 15%. The adjustment range is self-matched and adjusted following the fluctuation amplitude of the flow rate.

[0013] As a further solution of the present invention, the deviation between the current flow rate baseline and the target increment is calculated using the formula: ; where u(t) is the real-time control signal output by the PID control algorithm, is the proportional gain, e(t) is the current error, represents the integral gain, which eliminates the steady-state error according to the cumulative value of the error, represents the differential gain, represents the error change rate, t represents the current time, represents the integral time variable.

[0014] On the other hand, a method for realizing intelligent regulation of the root temperature of hydroponic crops is provided. This method is applied to the intelligent root temperature regulation system of hydroponic crops, and this method includes: S1: Collect root oxygen concentration data in real time, calculate the root oxygen consumption rate gradient, and judge the trend state of the oxygen consumption gradient based on the multivariable nonlinear coupling model; S2: Obtain the real-time data of the cell osmotic pressure in the hydroponic nutrient solution through dissolved oxygen sensing, obtain the data of the change in cell osmotic pressure, and perform difference calculation in combination with the trend state of the oxygen consumption gradient to generate a dynamic offset of the osmotic pressure change; S3: Based on the dynamic offset of the osmotic pressure change, combine the trend state of the oxygen consumption rate gradient to judge the damage risk of root cells and the real-time root temperature of the risk state, and obtain the determination result of the metabolic abnormal state through the multi-condition state machine model; S4: Compare the metabolic abnormal trigger temperature with the root temperature in the stable state before the occurrence of the abnormal state in the determination result of the metabolic abnormal state through the grey relational analysis algorithm, and generate a root temperature regulation instruction; S5: Invoke the root temperature regulation instruction, obtain the real-time data of the circulation flow rate, apply the PID control algorithm, and adjust the rotation speed of the circulation pump through the combined operation of proportional, integral, and differential.

[0015] The beneficial effects brought by the technical solution provided by the embodiment of the present invention at least include: obtaining the root oxygen consumption rate gradient through the periodic difference operation of the dissolved oxygen concentration, and judging the trend state with a unary linear regression model to realize the dynamic quantification of the rhythm of root metabolic activities. Then, taking this trend as a prerequisite for judging the abnormality of cell osmotic pressure enhances the response accuracy of damage recognition; combining the change amplitude of cell osmotic pressure and the dual-parameter linkage of the oxygen consumption gradient trend to judge the root damage risk and improve the collaborative recognition ability of cell function abnormalities; through the relative comparison of the abnormal state determination temperature and the monitored historical stable state temperature, using the grey relational analysis algorithm to dynamically select the target temperature setting value to break through the limitations of the fixed threshold control method; after generating the root temperature regulation instruction, combining the real-time data of the circulation rate, invoking the PID control algorithm to adjust the pump speed, and realizing the dynamic closed-loop matching between the root temperature setting value and the flow rate behavior. In this processing logic, the single-parameter threshold trigger method is replaced by the coupling judgment mechanism of metabolic trend and cell state, so that the root temperature response has the characteristics of event-driven, and can automatically generate the target setting value with the smallest difference according to the risk time point data, effectively enhancing the pertinence and real-time of root temperature regulation, and further improving the root stability and metabolic coordination in the hydroponic environment. Description of the Drawings

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained according to these drawings.

[0017] Figure 1 is a system flow chart of the present invention; Figure 2 is a system block diagram of the present invention; Figure 3 It is a schematic diagram of the steps of the method of the present invention. DETAILED DESCRIPTION

[0018] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0019] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0020] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0021] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0022] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0023] The embodiment of the present invention provides a root temperature intelligent control system for hydroponic crops, please refer to Figures 1 to 2 The present invention provides a technical solution, a root temperature intelligent control system for hydroponic crops, comprising: The root oxygen consumption monitoring module collects root oxygen concentration data in real time, calculates the root oxygen consumption rate gradient, determines the trend state of the oxygen consumption gradient based on a multivariable nonlinear coupling model, and transmits it to the osmotic pressure state monitoring module; The osmotic pressure status monitoring module obtains the cell osmotic pressure change data, performs difference calculation based on the oxygen consumption gradient trend status, obtains the dynamic offset of the osmotic pressure change, and transmits it to the root metabolism status analysis module; The root system metabolism status analysis module, based on the oxygen consumption gradient trend status and the dynamic offset of osmotic pressure change, and through the pore connectivity and root depth to allocate weights, inputs into the multi-condition state machine model to judge the damage risk level, obtains the determination result of the metabolic abnormal state, and transmits it to the root temperature parameter reconstruction module; The root temperature parameter reconstruction module compares the proximity between the temperature triggering metabolic abnormality and the root temperature before the occurrence of the abnormal state in the determination result of the metabolic abnormal state, generates a root temperature regulation instruction, and transmits it to the nutrient solution circulation linkage module; The nutrient solution circulation linkage module receives the root temperature regulation instruction, obtains the circulating flow rate data in real time, and calls the PID control algorithm to adjust the rotation speed of the circulation pump; The oxygen consumption gradient trend status includes the gradient direction vector, the change frequency characteristic, and the amplitude fluctuation range. The dynamic offset of the osmotic pressure change specifically refers to the maximum positive deviation value, the maximum negative deviation value, and the offset duration. The determination result of the metabolic abnormal state includes the abnormal condition category, the cell risk rating, and the root temperature at the corresponding moment. The root temperature regulation instruction specifically is the target temperature range, the regulation mode code number, and the instruction effective moment. The regulation result of adjusting the rotation speed of the circulation pump includes the set rotation speed value, the expected flow rate target, and the PID output parameter.

[0024] Please refer to Figure 2 , the root oxygen consumption monitoring module includes: Oxygen concentration acquisition sub-module: monitors the original signal of the oxygen concentration in the root area of the dissolved oxygen through a dissolved oxygen sensor, performs smoothing processing on the original oxygen concentration signal using low-pass filtering, and automatically adjusts the filtering window length according to the pore connectivity. The lower the porosity, the larger the window length. At the same time, by constraining the boundary value of the filtering window length, a differential noise reduction is performed by superimposing the Gaussian white noise characteristic map, and the data points are positionally calibrated according to the three-dimensional Cartesian coordinate system to generate an oxygen concentration time series set; The pore connectivity index is obtained by performing a CT scan on the soil sample and analyzing the geometric shape, size, distribution, and connection method of the pores through Avizo to obtain the connectivity index; The dissolved oxygen sensor collects the original oxygen concentration signal at a period of 0.5 seconds , where k is the discrete time sequence number, and the original oxygen concentration signal is smoothed through the moving average low-pass filtering formula , where CLPF(m) is the output after filtering, the filtering result at index m, representing the smoothed data value, N represents the total number of data points included in the filtering window participating in the average calculation during filtering, and is dynamically adjusted according to the pore connectivity index. represents the original data sequence, which is the unprocessed input signal and usually contains noise. m represents the current index, and j represents the offset relative to the current index m, used to traverse the adjacent data points within the window. represents the mean coefficient, and N - 1 represents the window symmetric offset. Here, N is dynamically adjusted according to the pore connectivity index CI (reflecting pore connectivity). When the pore connectivity is low (CI < 0.4), N is increased (e.g., N = 7) to enhance noise reduction. When the pore connectivity is high (CI > 0.6), N is decreased to retain high-frequency details. At the same time, the range of N is restricted to avoid filtering distortion caused by extreme values. During execution, N = 5 (window time span 2.5 seconds) is set. When k = 3, the filtering result is calculated by to the average value. If the original signal sequence is [8.4, 8.5, 8.3, 8.6, 8.2] mg / L, then The setting basis of the window length N is as follows: According to the sampling period of 0.5 seconds and the upper limit of the temperature fluctuation frequency of 0.1 Hz (period 10 seconds), at least 5 temperature fluctuation periods need to be covered to fully suppress high-frequency noise. Therefore, N = 5 corresponds to a 2.5-second time window, which can filter out noise with a frequency higher than and retain the temperature component below 0.1 Hz. After filtering, Gaussian white noise with a mean of 0 and a variance of 0.05 is superimposed. The noise value of -0.1 mg / L is superimposed on the filtered value of 8.4 mg / L to generate a characteristic spectrum value of 8.3 mg / L. When performing differential noise reduction, the variance difference of adjacent period spectra is calculated to be 0.02, and it is corrected to 8.35 mg / L after triggering the noise reduction threshold. Combining with the three-dimensional coordinates (2.3 m, 5.1 m, -1.2 m) generates an oxygen concentration time series set.

[0025] Table 1 Oxygen Concentration Time Series Data Table

[0026] As shown in Table 1, the filtering process performs signal smoothing through the arithmetic mean of the data within the window, and the window moving step size is 1 sampling point (0.5 seconds) to generate an oxygen concentration time series set.

[0027] Gradient calculation sub-module: Call the oxygen concentration time series set, calculate the concentration difference between adjacent points within a continuous time window, perform specified time normalization processing on the concentration difference, construct a spatial gradient field using the piecewise interpolation method, introduce a radial basis function to compensate for missing boundary data, and generate a gradient distribution rate; Call the oxygen concentration data of 5 adjacent monitoring points in the time period from 10:00 to 10:05 in Table 1, calculate the concentration difference between adjacent points. When the difference ΔC between point A (8.4 mg / L) and point B (8.1 mg / L) is 0.3 mg / L, perform normalization on ΔC with a 1-minute time window. Divide the 0.3 mg / L difference by the time window length of 60 seconds to obtain a change rate of 0.005 mg / (L·s). Use linear interpolation to construct a spatial gradient field. When the gradient values of four adjacent points are [0.005, 0.004, 0.006, 0.003] mg / (L·s) respectively, introduce a radial basis function with ε = 0.5 to compensate for the missing boundary points. When the theoretical gradient of the boundary point is 0.004 mg / (L·s), the compensated gradient distribution rate is corrected to 0.004×(1 + 0.5) = 0.006 mg / (L·s).

[0028] Trend judgment sub-module: Analyze the gradient distribution rate through a multi-variable non-linear coupling model, obtain root depth data through the root profile sampling method, and measure the total porosity by the core cutter method. Combine with the mercury intrusion method to obtain soil porosity parameters. Integrate the root depth data and soil porosity parameters, calculate the diffusion rate of the root oxygen consumption rate gradient field in the direction of the pore connectivity index, adjust the diffusion resistance coefficient inside the non-linear coupling model by the volumetric water content measured in-situ by the time domain reflectometer, generate the oxygen consumption gradient trend state, and transmit it to the osmotic pressure state monitoring module; Input the gradient distribution rate into the multi-variable model. When the depth measured by root profile sampling is 0.8 m, obtain the wet weight of the soil sample as 125 g and the dry weight as 110 g by the core cutter method, calculate the total porosity (125 - 110) / 125×100% = 12%. The proportion of pores with a pore diameter > 50 μm measured by the mercury intrusion method is 35%. Set the pore connectivity index = 12%×35% = 4.2%. When the diffusion rate of the oxygen consumption rate gradient field in the X direction is 0.008 mg / (L·s), substitute the volumetric water content of 28% measured by the time domain reflectometer into the model. If the water content exceeds 25%, adjust the diffusion resistance coefficient by a ratio of 0.8. The original coefficient of 1.2 is adjusted to 1.2×0.8 = 0.96, and the oxygen consumption gradient trend state is generated.

[0029] Please refer to Figure 2 , the osmotic pressure state monitoring module includes: Osmotic pressure acquisition sub-module: Configure a digital temperature sensor to monitor the root temperature, deploy sensor nodes at depth intervals, synchronously collect temperature data, record the osmotic pressure at fixed time intervals, and generate an osmotic pressure time series set including temperature compensation parameters; DS18B20 digital temperature sensors are deployed at 0.1 m, 0.3 m, and 0.5 m depth intervals in the root profile. The sampling frequency of the sensors is 1 Hz. When synchronously collecting temperature data, the original osmotic pressure value is recorded every 5 seconds. When the temperature measured by the sensor at a depth of 0.3 m is 25.6 °C, the original osmotic pressure value is 1.2 MPa. According to the temperature compensation parameter correct the osmotic pressure. The calculation formula is , where is the corrected osmotic pressure calculated through the compensation formula by combining the temperature measurement value and the original osmotic pressure value, represents the original measured value of osmotic pressure, and the reference temperature . When , the compensated osmotic pressure is . After continuously recording 10 groups of data, an osmotic pressure time series set is generated.

[0030] Table 2 Osmotic pressure data table

[0031] As shown in Table 2, the temperature compensation parameter is set according to the laboratory calibration data. The calibration method is: control the temperature in the thermostat to rise from 20 °C to 30 °C, measure the change in osmotic pressure for each 1 °C increase, and obtain by fitting the slope of the linear regression curve. The storage format of the time series set is (timestamp, depth, compensated osmotic pressure).

[0032] Gradient difference sub-module: Call the osmotic pressure time series set, combine the root temperature data collected by the DS18B20 digital temperature sensor, calculate the osmotic pressure after temperature compensation, extract the osmotic pressure difference within adjacent time windows, and superimpose the oxygen consumption gradient trend state to generate the osmotic pressure gradient difference; Call the compensated osmotic pressure data in the time period from 11:00 to 11:10 in Table 2, calculate the difference in adjacent time windows (5-minute interval). When = 11:00 = 1.212 MPa, = 11:05 = 1.228 MPa, the difference = 1.228 - 1.212 = 0.016 MPa. When superimposing the oxygen consumption gradient trend state parameter , calculate with w = 0.5 to generate the osmotic pressure gradient difference = 0.016 + 0.5 × 0.008 = 0.020 MPa. The weight w is set according to the correlation coefficient between osmotic pressure and oxygen consumption rate. When the correlation coefficient calculated from the data is 0.6, it is mapped to w = 0.6 / 1.2 = 0.5.

[0033] Change amplitude sub-module: Call the peak-valley extreme values in the osmotic pressure gradient difference, calculate the moving window mean of the absolute value of the peak-valley difference, with the window length of 5 minutes. Adjust the moving window mean through the temperature compensation parameter, where the temperature compensation coefficient = 0.1 × real-time temperature change rate, generate the dynamic offset of osmotic pressure change, and transfer it to the root metabolic state analysis module; Extract the peak-valley extreme values of the osmotic pressure gradient difference during the period from 11:00 to 11:30 in Table 2. When the peak value sequence is [0.020, 0.018, 0.022] MPa and the valley value sequence is [0.015, 0.012, 0.014] MPa, calculate the moving window (window length 3 groups) mean of the absolute value of the peak-valley difference. The peak-valley difference of window 1 is 、 、 , and the mean value is (0.005 + 0.006 + 0.008) / 3 = 0.0063 MPa. According to the temperature compensation parameter Adjust the mean value. When the temperature fluctuation range = 0.5 °C, the adjustment coefficient , where represents the temperature fluctuation range, α represents the temperature compensation coefficient, and the dynamic offset of osmotic pressure change = 0.0063 x 1.01 = 0.00636 MPa.

[0034] Please refer to Figure 2 , the root metabolic state analysis module includes: Damage risk sub-module: Call the dynamic offset of osmotic pressure change and the trend state of oxygen consumption gradient, calculate the covariance between the two within a continuous time window, extract the main diagonal elements of the covariance, and compare them item by item with the preset damage risk threshold to generate a damage risk coefficient; The damage risk threshold is determined by the covariance extreme value when the cell damage probability > 90% in the past data; Call the dynamic offset of osmotic pressure change and the trend state of oxygen consumption gradient of the time series data, intercept the data sequences of three consecutive time windows (window 1 to window 3), calculate the covariance matrix , extract the main diagonal elements , for the data of window 1, calculate the mean value , calculate the squared deviation value of each data point from the mean value, sum them up and divide by the degrees of freedom n - 1 = 2 to get , call the preset damage risk threshold , compare item by item with . When the of window 1 = 0. Similarly, calculate those of Window 2 and Window 3 are 0.00000003 and 0.00000002 respectively, both of which are less than the threshold value, generating a risk coefficient sequence , and the basis for setting the threshold value is: Through the laboratory cell damage experiment, 100 groups of samples are statistically analyzed. For the damaged group mean value , and the mean value of the non-damaged group , take the median value as the demarcation point.

[0035] Status integration sub-module: Call the damage risk coefficient, superimpose the real-time temperature data, perform linear interpolation on the damage risk coefficient according to the temperature segmentation interval, and generate a metabolic status vector; Call the damage risk coefficient and the real-time temperature data , divide the temperature interval: low temperature segment T < 25 °C, medium temperature segment 25 ≤ T < 28 °C, high temperature segment T ≥ 28 °C. When the temperature of Window 2 belongs to the medium temperature segment, according to the interpolation rule , is the parameter value after temperature adjustment, calculate , where is the parameter value after temperature adjustment in Window 2. When the temperature of Window 3 , it also belongs to the medium temperature segment, calculate = 0 × 1.2667 = 0. The basis for temperature segmentation is the experimental data of plant root metabolic rate: The metabolic activity decreases by 50% below 25 °C, and the enzyme activity decays by 30% above 28 °C. The interpolation coefficient is determined by linearly fitting the slope of the experimental data to generate a metabolic status vector .

[0036] Model analysis sub-module: Input the metabolic status vector into the multi-condition state machine model, define the damage risk coefficient and temperature value as state transition conditions, and allocate weights through pore connectivity and root depth. Input the multi-condition state machine model to judge the damage risk level, calculate the Manhattan distance between the current state and the metabolic abnormal pattern, generate a metabolic abnormal state determination result, and transfer it to the root temperature parameter reconstruction module; The weight factor of the Manhattan distance is dynamically adjusted according to the cell risk rating; The multi-condition state machine model is constructed through the discrete metabolic states in root physiology, setting based on the damage risk coefficient and logical rules, and defining the target metabolic abnormal pattern; Input the metabolic status vector into the multi-condition state machine model, define four discrete states: normal (S0), mild abnormality (S1), moderate abnormality (S2), severe abnormality (S3). According to the acquired real-time data, construct a vector , oxygen consumption gradient , based on porosity , connectivity CI = 0.5, depth 0.8 m, calculate the oxygen consumption rate ; osmotic pressure offset (expected value output by the dynamic prediction model ); root temperature , calculate the Manhattan distance , comparison threshold , meet , calculate the damage risk coefficient , where represents the intensity of the oxygen consumption trend, represents the osmotic pressure offset weight, represents porosity, represents the normalized root depth value, PCI represents the soil pore connectivity index, state machine determination: d = 1.949 ≤ 2.4, but r = 0.8 > 0.5 (severe anomaly threshold); determined as severe anomaly (S3), generate the determination result of the metabolic anomaly state.

[0037] Table 3 Data table for metabolic state determination

[0038] Please refer to Figure 2 , the root temperature parameter reconstruction module includes: Temperature data sub-module: Obtain the stable state root temperature data in the metabolic anomaly state determination result for normalization processing, generate a temperature data set including time stamps and temperature feature markers; The temperature data sub-module extracts the stable state root temperature data from the metabolic anomaly state determination result, obtains the time stamp sequence corresponding temperature data , the normalization method is used for normalization processing, and the formula is: , where , , is the maximum temperature within the current time window 1, is the minimum temperature within the current time window 1, calculate the normalized temperature of window 1: , generate the temperature feature marker field is-anomaly, assign values according to the metabolic anomaly state determination result (if window 2 is determined as abnormal, then mark as 1), and the format of the temperature data set is: data set .

[0039] Table 4 Example representation of the temperature data set

[0040] As shown in Table 4, the normalized temperature is calculated by normalization, and the anomaly marker field is bound to the metabolic determination result.

[0041] Association analysis sub-module: Call the temperature dataset, traverse the corresponding data points of the metabolic abnormality trigger temperature sequence and the steady-state temperature sequence, calculate the absolute difference of each data point, extract the minimum and maximum values among all the differences, call the resolution coefficient ρ = 0.5 based on the grey relational analysis algorithm, calculate the relational coefficient of each data point, and take the arithmetic mean of all the relational coefficients to generate the relational degree coefficient within the time window; The association analysis sub-module calls the abnormal trigger sequence in the temperature dataset and the steady-state sequence , traverse the data points to calculate the absolute difference, the difference of window 2: , where is the temperature value corresponding to the first trigger event, is the temperature reference value under the second steady state, extract the minimum value and the maximum value of all the differences, call the grey relational analysis formula to calculate the relational coefficient: , where the resolution coefficient = 0.5, the relational coefficient of window 2 is calculated as: , take the arithmetic mean of the relational coefficients of all the data points, the of the three windows, then the relational degree coefficient is: , Regulation instruction sub-module: Call the relational degree coefficient, compare the coefficient sequence item by item with the relational degree threshold, screen the nodes with coefficients lower than the relational degree threshold, extract the temperature adjustment amplitude and direction data corresponding to the time stamps of the nodes, and generate the root temperature regulation instruction; The relational degree threshold determines the optimal classification performance value through the point corresponding to the maximum Youden index on the ROC curve; The regulation instruction sub-module calls the relational degree coefficient sequence , the relational degree threshold is determined by the Youden index of the ROC curve, the true positive rate , the false positive rate in the experimental data, calculate the Youden index: , get , the maximum value corresponds to the threshold = 0.4, screen the nodes with coefficients lower than 0.4 (including 0.572 > 0.4 in window 3 which is not screened), extract the time stamps of the qualified nodes (including 0.623 > 0.4 in window 1 which is not screened), if no node meets the condition, output "No regulation required", otherwise generate the root temperature regulation instruction according to the temperature adjustment rule.

[0042] Please refer to Figure 2 , the nutrient solution circulation linkage module includes: Instruction parsing sub-module: Receive the root temperature regulation instruction, parse the temperature adjustment range and timestamp parameters in the instruction, screen out the timeout instructions based on the timestamp alignment rule, and generate the time-effective regulation parameters that match the current clock; The instruction parsing sub-module receives the root temperature regulation instruction from the regulation instruction sub-module. For example, the instruction format is [timestamp: 10:25, adjustment range: +2.5°C]. Obtain the current system clock as 10:30, call the timestamp alignment rule, define the timeout threshold as 5 minutes, and calculate the difference between the instruction timestamp and the current time: = 10:30 - 10:25 = 5 minutes, determine ≤ 5 minutes is a valid instruction, retain this instruction. If > 5 minutes, then screen it out, and generate the time-effective regulation parameter [valid time window: 10:25 - 10:30, adjustment range: +2.5°C]. In the example, the current time difference is 5 minutes, just meeting the threshold, and the instruction is retained.

[0043] Table 5 Timeout determination rule table

[0044] As shown in Table 5, the time difference is calculated through the clock difference, and the timeout threshold is set according to the system response delay experiment.

[0045] Flow rate dynamic sub-module: Call the time window of the time-effective regulation parameter, collect the original flow rate data of the electromagnetic flowmeter, set the number of sample points for moving average filtering according to the time window length, eliminate noise interference, and generate a flow rate dynamic baseline synchronized with the temperature regulation time sequence; The flow rate dynamic sub-module calls the time window 10:25 - 10:30 of the time-effective regulation parameter to collect the original flow rate data from the electromagnetic flowmeter. For example, the original data is a sequence sampled once per second: , according to the time window length of 5 minutes (300 seconds), set the number of sample points for moving average filtering to 300, and the calculation formula is , where The Q value of the physical quantity after filtering processing, is the i-th original data point, is the normalization coefficient for mean calculation, and the first 5 sample points are taken for calculation: , generate the flow rate dynamic baseline [102.48], synchronized with the temperature regulation time sequence.

[0046] Rotation speed decision sub-module: Call the temperature adjustment range and flow rate dynamic baseline in the aging control parameters. Based on the PID control algorithm, map the temperature range to the target flow rate increment, calculate the deviation value between the current flow rate baseline and the target increment, and adjust the rotation speed of the circulation pump by superimposing the proportional term, integral term, and differential term; The tuning method of the PID control algorithm's Kp proportional gain, Ki integral gain, and Kd differential gain parameters adopts the Ziegler-Nichols critical ratio method. The range of Kp is 0.5 - 5.0, Ki is 0.01 - 0.5, and Kd is 0.1 - 2.0. For every 10 L / min increase in the flow rate, Kp is increased by 10% - 30%, and Ki is decreased by 5% - 15%. The adjustment range is self-matched and adjusted following the fluctuation amplitude of the flow rate; The rotation speed decision sub-module calls the temperature adjustment range in the aging control parameters = +2.5 °C, and maps it to the target flow rate increment. The mapping rule is: , represents the value of the physical quantity Q after filtering processing, the current flow rate baseline , the target flow rate , collect the real-time flow rate , calculate the deviation: , e(t) represents the deviation that changes with time, that is, the instantaneous difference between the target value and the current actual value. Based on the Ziegler-Nichols critical ratio method, the initial PID parameters are = 2.0, = 0.1, = 0.5. According to the dynamic adjustment rule of the flow rate increment: for every 10 L / min increase in the flow rate, is increased by 20%, is decreased by 10%, remains unchanged. The current flow rate baseline is 102.48 L / min (reference value 100 L / min), and the increment , which does not reach the 10 L / min threshold, and the parameters remain at the initial values. Calculate the error signal: , where u(t) is the real-time control signal output by the PID control algorithm, is the proportional gain, e(t) is the current error, represents the integral gain, and eliminates the steady-state error according to the cumulative value of the error, represents the differential gain, represents the error change rate, t represents the current time, represents the integral time variable. Assume that the integral term accumulates the error , the differential term , and introduce the porosity ( , that is, the ratio of the pore volume to the total volume of the soil) and the oxygen consumption rate , where k represents the intrinsic oxygen consumption rate constant, represents the porosity attenuation coefficient, represents the connectivity gain coefficient, CI represents the pore connectivity index, represents the real-time oxygen concentration, dynamically corrects the target flow rate increment and adjusts the PID parameters, based on the oxygen consumption rate the reference increment for temperature control such as +5 L / min) for feedforward compensation, and the formula is: , where is the oxygen consumption flow rate coupling coefficient, is the reference oxygen consumption rate. In the example, when the porosity , the connectivity CI = 0.6, and the oxygen concentration , the target increment is corrected from +5 L / min to +5.38 L / min. PID parameter adaptation: low porosity ( = 0.3) triggers the proportional gain (initial value = 3.0) is increased to 3.36 according to the formula to enhance the response speed; when the flow rate increment threshold (10 L / min) is not reached, the initial integral gain = 0.1 and the derivative gain = 0.5 are retained. The real-time flow rate deviation e(t) = 2.9 L / min is calculated by PID to output the rotational speed adjustment amount u(t) = 0.785 RPM, realizing the dynamic coordination between the soil pore structure characteristics and fluid control, improving the accuracy, and adjusting the rotational speed of the circulation pump according to u(t) = 0.785.

[0047] Please refer to Figure 3 , and the method includes: S1: Real-time collect the root oxygen concentration data, calculate the root oxygen consumption rate gradient, and judge the trend state of the oxygen consumption gradient based on the multivariable nonlinear coupling model; S2: Obtain the real-time data of the cell osmotic pressure in the hydroponic nutrient solution through dissolved oxygen sensing, obtain the cell osmotic pressure change data, and perform difference calculation in combination with the oxygen consumption gradient trend state to generate the dynamic offset of the osmotic pressure change; S3: Based on the dynamic offset of the osmotic pressure change, combine the oxygen consumption rate gradient trend state to judge the damage risk of the root cells and the real-time root temperature of the risk state, and obtain the metabolic abnormality state determination result through the multi-condition state machine model; S4: Compare the metabolic abnormality triggering temperature with the root temperature in the stable state before the occurrence of the abnormal state in the metabolic abnormality state determination result through the grey relational analysis algorithm to generate the root temperature regulation instruction; S5: Call the root temperature regulation instruction, real-time obtain the circulation flow rate data, apply the PID control algorithm, and adjust the rotational speed of the circulation pump through the combined operation of proportional, integral, and derivative.

[0048] It should be understood that the term "and / or" in this text is merely a description of the association relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. Additionally, the character " / " in this text generally represents an "or" relationship between the preceding and following associated objects, but it may also represent an "and / or" relationship, which can be specifically understood by referring to the context before and after.

[0049] In the present invention, "at least one" means one or more, and "a plurality" means two or more. "At least one of the following items" or similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0050] It should be understood that in various embodiments of the present invention, the magnitude of the serial numbers of the above processes does not imply the sequence of execution. The execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0051] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0052] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the devices, apparatuses, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0053] In several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces, and the indirect coupling or communication connection of devices or units can be in electrical, mechanical, or other forms.

[0054] The unit described as a separated component may or may not be physically separated, and the component displayed as a unit may or may not be a physical unit, that is, it may be located in one place or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0055] In addition, each functional unit in various embodiments of the present invention may be integrated in a processing unit, may exist separately physically for each unit, or two or more units may be integrated in one unit.

[0056] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical discs that can store program codes.

[0057] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. An intelligent root temperature control system for hydroponic crops, characterized in that, The system includes: A root oxygen consumption monitoring module that collects root oxygen concentration data in real time, calculates the root oxygen consumption rate gradient, judges the trend state of the oxygen consumption gradient based on a multivariable nonlinear coupling model, and transmits it to the osmotic pressure state monitoring module; An osmotic pressure state monitoring module that obtains cell osmotic pressure change data, performs a difference calculation in combination with the oxygen consumption gradient trend state to obtain the dynamic offset of the osmotic pressure change, and transmits it to the root metabolism state analysis module; A root metabolism state analysis module that, based on the oxygen consumption gradient trend state and the dynamic offset of the osmotic pressure change, and by allocating weights through pore connectivity and root depth, inputs a multi-condition state machine model to judge the damage risk level, obtains the determination result of the metabolic abnormal state, and transmits it to the root temperature parameter reconstruction module; A root temperature parameter reconstruction module that compares the metabolic abnormal triggering temperature with the root temperature before the occurrence of the abnormal state in the determination result of the metabolic abnormal state, generates a root temperature regulation instruction, and transmits it to the nutrient solution circulation linkage module; A nutrient solution circulation linkage module that receives the root temperature regulation instruction, obtains the circulation flow rate data in real time, and calls the PID control algorithm to adjust the rotation speed of the circulation pump.

2. The intelligent root temperature control system for hydroponic crops according to claim 1, wherein The oxygen consumption gradient trend state includes a gradient direction vector, a change frequency feature, and an amplitude fluctuation range. The dynamic offset of the osmotic pressure change is the maximum positive deviation value, the maximum negative deviation value, and the offset duration. The determination result of the metabolic abnormal state includes the abnormal condition category, the cell risk rating, and the root temperature at the corresponding moment. The root temperature regulation instruction is the target temperature range, the regulation mode code, and the instruction effective moment. The regulation result of adjusting the rotation speed of the circulation pump includes the set rotation speed value, the expected flow rate target, and the PID output parameter.

3. The intelligent root temperature control system for hydroponic crops according to claim 1, characterized in that, The root oxygen consumption monitoring module includes: An oxygen concentration acquisition sub-module: monitors the original signal of the oxygen concentration in the root area of dissolved oxygen through a dissolved oxygen sensor, performs smoothing processing on the original oxygen concentration signal using low-pass filtering, and automatically adjusts the filtering window length according to the pore connectivity. The lower the porosity, the larger the window length. At the same time, by constraining the boundary values of the filtering window length, a Gaussian white noise characteristic map is superimposed to perform differential noise reduction, and the data points are position-calibrated according to the three-dimensional Cartesian coordinate system to generate an oxygen concentration time series set; The pore connectivity index is obtained by performing a CT scan on a soil sample and analyzing the geometric shape, size, distribution, and connection mode of the pores through Avizo to obtain a connectivity index; A gradient calculation sub-module: calls the oxygen concentration time series set, calculates the concentration difference between adjacent points within a continuous time window, performs specified time normalization processing on the concentration difference, constructs a spatial gradient field using piecewise interpolation, and introduces a radial basis function to compensate for missing boundary data to generate a gradient distribution rate; Trend judgment sub-module: Analyze the gradient distribution rate through a multi-variable non-linear coupling model, obtain root depth data through the root profile sampling method, measure the total porosity by the cutting ring method, combine with the mercury intrusion method to obtain soil porosity parameters, integrate the root depth data and soil porosity parameters, calculate the diffusion rate of the root oxygen consumption rate gradient field in the direction of the pore connectivity index, adjust the diffusion resistance coefficient inside the non-linear coupling model by the volumetric water content measured in-situ by the time domain reflectometer, generate the oxygen consumption gradient trend state, and transmit it to the osmotic pressure state monitoring module.

4. The intelligent root temperature control system for hydroponic crops according to claim 3, characterized in that, Smooth the original oxygen concentration signal, using the formula: ； Among them, CLPF(m) is the output after filtering, which is the smoothed result of taking the mean of the data within the window near index m in the original signal. N represents the window length, which is the total number of data points included in the filtering window involved in the average calculation during filtering, and is dynamically adjusted according to the pore connectivity index. represents the original data sequence, which is the input signal sequence without filtering. m represents the current index, which is the target data position where the filtered value needs to be calculated, indicating the currently processed signal point. j is the offset for the current index m, used to traverse all data points within the window. represents the mean coefficient. represents the unilateral offset, which is the number of data points on both sides of the center point of the window. N - 1 represents the window symmetric offset, which is the window total width minus 1.

5. The intelligent root temperature control system for hydroponic crops according to claim 1, wherein The osmotic pressure state monitoring module includes: Osmotic pressure acquisition sub-module: Configure a digital temperature sensor to monitor the root temperature, deploy sensor nodes at depth intervals, synchronously collect temperature data, record the osmotic pressure at fixed time intervals, and generate an osmotic pressure time series set including temperature compensation parameters; Gradient difference sub-module: Call the osmotic pressure time series set, combine with the root temperature data collected by the digital temperature sensor, calculate the temperature-compensated osmotic pressure, extract the osmotic pressure difference within adjacent time windows, and superimpose the oxygen consumption gradient trend state to generate an osmotic pressure gradient difference; Change amplitude sub-module: Call the peak and valley extreme values in the osmotic pressure gradient difference, calculate the moving window mean of the absolute value of the peak and valley difference, the window length is 5 minutes, adjust the moving window mean through the temperature compensation parameters, and the temperature compensation coefficient = 0.1 × the real-time temperature change rate, generate the dynamic offset of the osmotic pressure change, and transmit it to the root metabolism state analysis module.

6. The intelligent root temperature control system for hydroponic crops according to claim 1, characterized in that The root metabolism state analysis module includes: Damage risk sub-module: Call the dynamic offset of the osmotic pressure change and the oxygen consumption gradient trend state, calculate the covariance between the two within a continuous time window, extract the main diagonal elements of the covariance, and compare them item by item with the preset damage risk threshold to generate a damage risk coefficient; the damage risk threshold is determined by the covariance extreme value when the cell damage probability > 90% in the past data; State integration sub-module: Call the damage risk coefficient, superimpose the real-time temperature data, and perform linear interpolation on the damage risk coefficient according to the temperature segmentation interval to generate a metabolism state vector; Model analysis sub-module: Input the metabolism state vector into a multi-condition state machine model, define the damage risk coefficient and temperature value as state transition conditions, and allocate weights through the pore connectivity and root depth, input the multi-condition state machine model to judge the damage risk level, calculate the Manhattan distance between the current state and the metabolic abnormal mode, generate a metabolic abnormal state determination result, and transmit it to the root temperature parameter reconstruction module; The weight factor of the Manhattan distance is dynamically adjusted according to the cell risk rating; the multi-condition state machine model is constructed based on the discrete metabolic states in root physiology, setting logical rules based on the damage risk coefficient, and determining the target metabolic abnormal mode.

7. The intelligent root temperature control system for hydroponic crops according to claim 1, wherein The root temperature parameter reconstruction module includes: Temperature data sub-module: Obtain the stable state root temperature data in the metabolic abnormal state determination result for standardization processing, and generate a temperature data set including timestamps and temperature feature markers; Association analysis sub-module: Call the temperature data set, traverse the corresponding data points of the metabolic abnormality trigger temperature sequence and the steady-state temperature sequence, calculate the absolute difference of each data point, extract the minimum and maximum values among all the differences, call the resolution coefficient ρ = 0.5 based on the grey relational analysis algorithm, calculate the relational coefficient of each data point, and take the arithmetic mean of all the relational coefficients to generate the correlation coefficient within the time window; Regulation instruction sub-module: Call the correlation coefficient, compare the coefficient sequence with the correlation threshold item by item, screen the nodes with coefficients lower than the correlation threshold, extract the temperature adjustment amplitude and direction data corresponding to the time stamps of the nodes, and generate the root temperature regulation instruction; The correlation threshold determines the optimal classification performance value through the point corresponding to the maximum Youden index on the ROC curve.

8. The intelligent root temperature control system for hydroponic crops according to claim 1, wherein The nutrient solution circulation linkage module includes: Instruction parsing sub-module: Receive the root temperature regulation instruction, parse the temperature adjustment amplitude and time stamp parameters in the instruction, and screen out the timeout instructions based on the time stamp alignment rule to generate the aging regulation parameters matching the current clock; Flow rate dynamic sub-module: Call the time window of the aging regulation parameters, collect the original flow rate data of the electromagnetic flowmeter, set the number of sample points for moving average filtering according to the time window length, eliminate the noise interference, and generate the flow rate dynamic baseline synchronized with the temperature regulation time sequence; Rotation speed decision sub-module: Call the temperature adjustment amplitude in the aging regulation parameters and the flow rate dynamic baseline, based on the PID control algorithm, map the temperature amplitude to the target flow rate increment, calculate the deviation value between the current flow rate baseline and the target increment, and superimpose the proportional term, integral term, and differential term to adjust the rotation speed of the circulation pump; The parameter tuning method of the PID control algorithm Kp, Ki, and Kd adopts the Ziegler-Nichols critical ratio method. The Kp range is the parameter range optimized through 50 flow rate step response experiments. The obtained Kp range is 0.5 - 5.0, Ki 0.01 - 0.5, Kd 0.1 - 2.

0. For every 10 L / min increase in the flow rate, Kp is increased by 10% - 30% and Ki is decreased by 5% - 15%. The adjustment range self-matches and adjusts according to the fluctuation amplitude of the flow rate.

9. The intelligent root temperature control system for hydroponic crops according to claim 8, characterized in that, Calculate the deviation between the current flow rate baseline and the target increment using the formula: ； where, u(t) is the real-time control signal output by the PID control algorithm, is the proportional gain, e(t) is the current error, represents the integral gain, which eliminates the steady-state error according to the cumulative value of the error, represents the derivative gain, represents the error change rate, t represents the current time, represents the integral time variable.

10. A method for realizing intelligent regulation of the root temperature of hydroponic crops, characterized in that, The method is used to implement the intelligent root temperature regulation system for hydroponic crops described in any one of claims 1 - 9. The method includes: S1: Real-time collect the root oxygen concentration data, calculate the root oxygen consumption rate gradient, and judge the trend state of the oxygen consumption gradient based on the multi-variable non-linear coupling model; S2: Obtain the real-time data of the cell osmotic pressure in the hydroponic nutrient solution through the dissolved oxygen sensor, obtain the cell osmotic pressure change data, and perform difference calculation in combination with the oxygen consumption gradient trend state to generate the osmotic pressure change dynamic offset; S3: Based on the osmotic pressure change dynamic offset, combine the oxygen consumption rate gradient trend state to judge the damage risk of the root cells and the real-time root temperature of the risk state, and obtain the metabolic abnormality state determination result through the multi-condition state machine model; S4: Compare the metabolic disorder triggering temperature with the root temperature in the stable state before the occurrence of the abnormal state in the metabolic disorder state determination result through the grey relational analysis algorithm, and generate a root temperature regulation instruction; S5: Invoke the root temperature regulation instruction, obtain the circulating flow rate data in real time, apply the PID control algorithm, and adjust the rotational speed of the circulation pump through the combined operation of proportional, integral, and differential.

Images