Disclosure of Invention
In order to solve the technical problems in the prior art, the embodiment of the invention provides an intelligent root temperature regulation and control system for hydroponic crops and an implementation method thereof. The technical scheme is as follows:
in one aspect, an intelligent root temperature regulation and control system for hydroponic crops is provided, the system comprises:
the root system oxygen consumption monitoring module is used for collecting root system oxygen concentration data in real time, calculating the root system oxygen consumption rate gradient, judging the trend state of the oxygen consumption gradient based on the multivariable nonlinear coupling model, and transmitting the trend state to the osmotic pressure state monitoring module;
The osmotic pressure state monitoring module is used for acquiring cell osmotic pressure change data, carrying out difference value calculation by combining the oxygen consumption gradient trend state, acquiring osmotic pressure change dynamic offset and transmitting the osmotic pressure change dynamic offset to the root system metabolic state analysis module;
The root system metabolism state analysis module is used for distributing weight through pore connectivity and root system depth based on the oxygen consumption gradient trend state and the osmotic pressure change dynamic offset, inputting a multi-condition state machine model to judge the damage risk level, obtaining a metabolism abnormal state judgment result, and transmitting the judgment result to the root temperature parameter reconstruction module;
the root temperature parameter reconstruction module compares the metabolic abnormality triggering temperature with the approach degree of the root system temperature before the abnormal state occurs in the metabolic abnormal state judging result, generates a root system temperature regulation and control instruction and transmits the root system temperature regulation and control instruction to the nutrient solution circulation linkage module;
And the nutrient solution circulation linkage module receives the root system temperature regulation and control instruction, acquires circulation flow rate data in real time, and calls a PID control algorithm to adjust the rotation speed of the circulation pump.
As a further scheme of the invention, the oxygen consumption gradient trend state comprises a gradient direction vector, a change frequency characteristic and an amplitude fluctuation interval, the osmotic pressure change dynamic offset is a maximum positive offset value, a maximum negative offset value and an offset duration, the metabolic abnormal state judgment result comprises an abnormal condition type, a cell risk rating and a root temperature at a corresponding moment, the root temperature regulation instruction is a target temperature range, a regulation mode code number and an instruction effective moment, and the regulation result for regulating the rotation speed of the circulating pump comprises a set rotation speed value, an expected flow speed target and a PID output parameter.
As a further aspect of the present invention, the root oxygen consumption monitoring module includes:
The oxygen concentration acquisition submodule monitors an original oxygen concentration signal of a dissolved oxygen root system area through dissolved oxygen sensing, performs smoothing treatment on the original oxygen concentration signal through low-pass filtering, automatically adjusts the length of a filtering window according to the connectivity of pores, wherein the lower the porosity is, the larger the window length is, and simultaneously performs differential noise reduction by restraining the boundary value of the filtering window length, overlapping a Gaussian white noise characteristic map, performing position calibration on data points according to a three-dimensional Cartesian coordinate system, and generating an oxygen concentration time sequence set;
the pore connectivity index is obtained by CT scanning of a soil sample and analyzing the geometric shape, size, distribution and connection mode of pores through Avizo;
the gradient calculation sub-module is used for calling the oxygen concentration time sequence set, calculating concentration differences of adjacent points in a continuous time window, executing specified time normalization processing on the concentration differences, constructing a spatial gradient field by adopting a piecewise interpolation method, introducing a radial basis function to compensate boundary data loss, and generating gradient distribution rate;
Analyzing gradient distribution rate through a multivariable nonlinear coupling model, acquiring root depth data through a root profile sampling method, measuring total porosity through a ring cutting method, acquiring soil porosity parameters through a mercury compression method, integrating the root depth data and the soil porosity parameters, calculating the diffusion rate of a root system oxygen consumption rate gradient field in the pore connectivity index direction, performing in-situ measurement of volume water content through a time domain reflectometer, performing adjustment on diffusion resistance coefficient in the nonlinear coupling model, generating an oxygen consumption gradient trend state, and transmitting to an osmotic pressure state monitoring module.
As a further aspect of the present invention, the raw oxygen concentration signal is smoothed using the formula:
;
wherein CLPF (m) is output after filtering, is a smoothing result obtained by averaging data in a window near an index m in an original signal, N represents window length, is total number of data points involved in average calculation filtering window during filtering, is dynamically adjusted according to a pore connectivity index,Representing the original data sequence, being an unfiltered input signal sequence, m representing the current index, being the target data location where the filtered value needs to be calculated, representing the current processed signal point, j being the offset to the current index m for traversing all data points within the window,Represents the mean value coefficient of the average value,Representing the single-side offset, which is the number of data points on both sides of the window center point, and N-1 represents the window symmetrical offset, which is the window total width minus 1.
As a further aspect of the present invention, the osmotic pressure state monitoring module includes:
The osmotic pressure acquisition submodule is used for configuring a digital temperature sensor to monitor the temperature of a root system, deploying sensor nodes according to depth intervals, synchronously acquiring temperature data, recording osmotic pressure at fixed time intervals and generating an osmotic pressure time sequence set comprising temperature compensation parameters;
the gradient difference value submodule is used for calling the osmotic pressure time sequence set, combining root system temperature data acquired by a digital temperature sensor, calculating osmotic pressure after temperature compensation, extracting osmotic pressure difference values in adjacent time windows, superposing the oxygen consumption gradient trend state and generating an osmotic pressure gradient difference value;
And the change amplitude submodule is used for calling a peak Gu Jizhi in the osmotic pressure gradient difference value, calculating a sliding window mean value of the absolute value of the peak-valley difference value, adjusting the sliding window mean value through the temperature compensation parameter, generating an osmotic pressure change dynamic offset, and transmitting the osmotic pressure change dynamic offset to the root system metabolic state analysis module, wherein the window length is 5 minutes.
As a further aspect of the present invention, the root metabolism state analysis module includes:
The damage risk sub-module is used for calling the dynamic offset of osmotic pressure change and the oxygen consumption gradient trend state, calculating covariance of the dynamic offset of osmotic pressure change and the oxygen consumption gradient trend state in a continuous time window, extracting covariance main diagonal elements, and performing item-by-item comparison with a preset damage risk threshold value to generate a damage risk coefficient;
The model analysis submodule inputs the metabolism state vector into a multi-condition state machine model, defines damage risk coefficient and temperature value as state transition conditions, distributes weight through pore connectivity and root depth, inputs the multi-condition state machine model to judge damage risk level, calculates Manhattan distance between the current state and the metabolism abnormality mode, generates a metabolism abnormality state judgment result, and transmits the judgment result to the root temperature parameter reconstruction module;
The multi-condition state machine model is constructed by setting a discrete metabolic state based on root physiology, setting a damage risk coefficient and a logic rule and determining a target metabolic abnormality mode.
As a further aspect of the present invention, the root temperature parameter reconstruction module includes:
The temperature data sub-module is used for obtaining the steady-state root system temperature data in the metabolic abnormal state judgment result to carry out standardized processing and generating a temperature data set comprising a time stamp and a temperature characteristic mark;
The correlation analysis sub-module is used for calling the temperature dataset, traversing the corresponding data points of the generation Xie Yichang trigger temperature sequence and the steady state temperature sequence, calculating absolute difference values of each data point, extracting minimum values and maximum values in all the difference values, calling a resolution coefficient rho=0.5 based on a gray correlation analysis algorithm, calculating the correlation coefficient of each data point, taking arithmetic average value of all the correlation coefficients, and generating the correlation coefficient in a time window;
And the regulation and control instruction submodule is used for calling the relevance coefficient, comparing the coefficient sequence with a relevance threshold item by item, screening nodes with coefficients lower than the relevance threshold, extracting temperature regulation amplitude and direction data of a timestamp corresponding to the nodes, and generating a root system temperature regulation and control instruction, wherein the relevance threshold determines a classification performance optimal value through a point corresponding to the maximum value of the Johnson index on the ROC curve.
As a further aspect of the present invention, the nutrient solution circulation linkage module includes:
The instruction analysis submodule is used for receiving the root system temperature regulation instruction, analyzing the temperature regulation amplitude and the time stamp parameter in the instruction, screening out the overtime instruction based on the time stamp alignment rule, and generating an aging regulation parameter matched with the current clock;
the flow velocity dynamic submodule invokes a time window of the aging regulation parameter, acquires the original flow velocity data of the electromagnetic flowmeter, sets the number of sample points of the moving average filter according to the length of the time window, eliminates noise interference and generates a flow velocity dynamic base line synchronous with the temperature regulation time sequence;
The rotating speed decision sub-module is used for calling the temperature adjustment amplitude in the aging regulation parameters and the flow speed dynamic base line, mapping the temperature amplitude into a target flow speed increment based on a PID control algorithm, calculating the deviation value of the current flow speed base line and the target increment, superposing a proportional term, an integral term and a differential term, and adjusting the rotating speed of the circulating pump, wherein the PID control algorithm adopts a Ziegler-Nichols critical proportion method through Kp, ki and Kd parameter setting methods, the Kp range is a parameter range obtained by optimizing 50 flow speed step response experiments, the obtained Kp range is 0.5-5.0, ki0.01-0.5 and Kd0.1-2.0, the flow speed is increased by 10L/min each time, the Kp is adjusted by 10% -30%, the Ki is adjusted by 5% -15%, and the adjusting range is adjusted in a self-matching way along with the fluctuation amplitude of the flow speed.
As a further aspect of the present invention, the deviation of the current flow rate baseline from the target increment is calculated using the formula:
;
wherein u (t) is a real-time control signal output by the PID control algorithm,Is the proportional gain, e (t) is the current error,Representing the integral gain, eliminating steady-state error based on the cumulative value of the error,Representing the differential gain of the signal,Representing the rate of change of the error, t representing the current time,Representing the integration time variable.
On the other hand, a method for realizing the intelligent regulation and control of the root temperature of the hydroponic crop is provided, and the method is applied to an intelligent regulation and control system of the root temperature of the hydroponic crop, and comprises the following steps:
S1, collecting root system oxygen concentration data in real time, calculating root system oxygen consumption rate gradient, and judging oxygen consumption gradient trend state based on a multivariable nonlinear coupling model;
S2, obtaining real-time data of cell osmotic pressure in the hydroponic nutrient solution through dissolved oxygen sensing, obtaining cell osmotic pressure change data, and carrying out difference calculation by combining the oxygen consumption gradient trend state to generate osmotic pressure change dynamic offset;
S3, judging the damage risk of root system cells and the real-time root system temperature of the risk state based on the dynamic offset of osmotic pressure variation and in combination with the oxygen consumption rate gradient trend state, and obtaining a metabolic abnormal state judgment result through a multi-condition state machine model;
s4, comparing the metabolism abnormality triggering temperature with the approach degree of the steady-state root system temperature before the abnormal state occurs in the metabolism abnormality state judging result through a gray correlation analysis algorithm, and generating a root system temperature regulating instruction;
and S5, calling the root system temperature regulation instruction, acquiring circulating flow rate data in real time, applying a PID control algorithm, and regulating the rotating speed of the circulating pump through proportional, integral and differential combined operation.
The technical scheme provided by the embodiment of the invention has the advantages that at least, the root system oxygen consumption rate gradient is obtained through periodical difference operation of dissolved oxygen concentration, the trend state is judged by a unitary linear regression model, dynamic quantification of the metabolic activity rhythm of the root system is realized, the trend is used as a precondition for judging the abnormal osmotic pressure of cells, the response accuracy of damage identification is enhanced, the root system damage risk is judged by combining the dual-parameter linkage of the change amplitude of the osmotic pressure of the cells and the trend of the oxygen consumption gradient, the cooperative identification capability of abnormal cell functions is improved, the target temperature set value is dynamically selected by utilizing a gray correlation analysis algorithm through the relative comparison of the abnormal state judgment temperature and the monitoring historical steady state temperature, the limitation of a fixed threshold control mode is broken through, and after a root temperature regulation instruction is generated, the PID control algorithm is called for pump speed adjustment by combining the real-time data of the circulation rate, so that the dynamic closed-loop matching between the root temperature set value and the flow speed behavior is realized. In the processing logic, a single parameter threshold triggering mode is replaced by a coupling judgment mechanism of the metabolic trend and the cell state, so that the root temperature response has event driving characteristics, a target set value with the smallest difference can be automatically generated according to the risk time point data, the pertinence and the instantaneity of root temperature regulation are effectively enhanced, and the root system stability and the metabolic coordination in the hydroponic environment are further improved.
Detailed Description
The technical scheme of the invention is described below with reference to the accompanying drawings.
In embodiments of the invention, words such as "exemplary," "such as" and the like are used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, the term use of an example is intended to present concepts in a concrete fashion. Furthermore, in embodiments of the present invention, the meaning of "and/or" may be that of both, or may be that of either, optionally one of both.
In the embodiments of the present invention, "image" and "picture" may be sometimes used in combination, and it should be noted that the meaning of the expression is consistent when the distinction is not emphasized. "of", "corresponding (corresponding, relevant)" and "corresponding (corresponding)" are sometimes used in combination, and it should be noted that the meaning of the expression is consistent when the distinction is not emphasized.
In embodiments of the present invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1, and the meaning of the expression is consistent when de-emphasizing the distinction.
In order to make the technical problems, technical solutions and advantages to be solved more apparent, the following detailed description will be given with reference to the accompanying drawings and specific embodiments.
The embodiment of the invention provides an intelligent root temperature control system for hydroponic crops, referring to fig. 1 to 2, the invention provides a technical scheme, and the intelligent root temperature control system for hydroponic crops comprises:
the root system oxygen consumption monitoring module is used for collecting root system oxygen concentration data in real time, calculating the root system oxygen consumption rate gradient, judging the trend state of the oxygen consumption gradient based on the multivariable nonlinear coupling model, and transmitting the trend state to the osmotic pressure state monitoring module;
The osmotic pressure state monitoring module is used for acquiring cell osmotic pressure change data, carrying out difference value calculation by combining with the oxygen consumption gradient trend state, acquiring osmotic pressure change dynamic offset, and transmitting the dynamic offset to the root system metabolic state analysis module;
The root system metabolic state analysis module is used for distributing weights based on the oxygen consumption gradient trend state and the osmotic pressure change dynamic offset, inputting a multi-condition state machine model to judge the damage risk level, obtaining a metabolic abnormal state judgment result and transmitting the judgment result to the root temperature parameter reconstruction module;
The root temperature parameter reconstruction module compares the abnormal metabolism trigger temperature with the approach degree of the root system temperature before the abnormal state occurs in the abnormal metabolism state judgment result, generates a root system temperature regulation instruction and transmits the root system temperature regulation instruction to the nutrient solution circulation linkage module;
the nutrient solution circulation linkage module receives a root system temperature regulation instruction, acquires circulation flow rate data in real time, and calls a PID control algorithm to adjust the rotation speed of the circulation pump;
The oxygen consumption gradient trend state comprises a gradient direction vector, a change frequency characteristic and an amplitude fluctuation interval, the osmotic pressure change dynamic offset specifically refers to a maximum positive deviation value, a maximum negative deviation value and an offset duration, the metabolic abnormal state judgment result comprises an abnormal state type, a cell risk rating, a corresponding moment root temperature, the root system temperature regulation instruction specifically comprises a target temperature range, a regulation mode code number and an instruction effective moment, and the regulation result for regulating the rotation speed of the circulating pump comprises a set rotation speed value, an expected flow speed target and a PID output parameter.
Referring to fig. 2, the root oxygen consumption monitoring module includes:
The oxygen concentration acquisition submodule monitors an original oxygen concentration signal of a dissolved oxygen root system area through dissolved oxygen sensing, performs smoothing treatment on the original oxygen concentration signal through low-pass filtering, automatically adjusts the length of a filtering window according to the connectivity of pores, wherein the lower the porosity is, the larger the window length is, and simultaneously performs differential noise reduction by restraining the boundary value of the filtering window length, overlapping a Gaussian white noise characteristic map, performing position calibration on data points according to a three-dimensional Cartesian coordinate system, and generating an oxygen concentration time sequence set;
The pore connectivity index is obtained by CT scanning of a soil sample and analyzing the geometric shape, size, distribution and connection mode of pores through Avizo;
the dissolved oxygen sensor collects the original oxygen concentration signal with the period of 0.5 seconds as the periodWhere k is the discrete time number, by the moving average low pass filter formulaSmoothing the original oxygen concentration signal, wherein CLPF (m) is a filtered output, a filtered result at an index m represents a smoothed data value, N represents the total number of data points involved in the average calculation filter window during filtering, and is dynamically adjusted according to the pore connectivity index,Representing the original data sequence, being an unprocessed input signal, typically containing noise, m represents the current index, j represents the offset from the current index m, for traversing adjacent data points within the window,Representing the mean coefficient, N-1 represents the window symmetry offset, where N dynamically adjusts N according to the pore connectivity index CI (reflecting pore connectivity), increases N (e.g., n=7) to enhance noise reduction when pore connectivity is low (CI < 0.4), decreases N to preserve high frequency detail when pore connectivity is high (CI > 0.6), while constraining the N range from extreme values resulting in filtering distortion, when executed, sets n=5 (window time span 2.5 seconds), when k=3, the filtering results are calculated byTo the point ofIf the original signal sequence is [8.4,8.5,8.3,8.6,8.2] mg/LThe window length N is set according to the sampling period of 0.5 second and the upper limit of the temperature fluctuation frequency of 0.1Hz (period of 10 seconds), at least 5 temperature fluctuation periods are required to be covered to fully inhibit high-frequency noise, so N=5 corresponds to a time window of 2.5 seconds, and the frequency can be filtered to be higher thanNoise of 0.4Hz is reserved, meanwhile, temperature components lower than 0.1Hz are reserved, gaussian white noise with the average value of 0 and the variance of 0.05 is superimposed after filtering, the noise value of-0.1 mg/L is superimposed on the filtering value of 8.4mg/L, the characteristic map value of 8.3mg/L is generated, when differential noise reduction is carried out, the difference value of adjacent periodic map variances is calculated to be 0.02, the noise reduction threshold value is triggered and corrected to be 8.35mg/L, and the oxygen concentration time sequence set is generated by combining three-dimensional coordinates (2.3 m,5.1m and-1.2 m).
TABLE 1 oxygen concentration time series data sheet
As shown in table 1, the filtering process performs signal smoothing by arithmetic averaging of the data in the window, the window moving step is 1 sampling point (0.5 seconds), and the oxygen concentration time series set is generated.
The gradient calculation sub-module is used for calling an oxygen concentration time sequence set, calculating concentration differences of adjacent points in a continuous time window, executing specified time normalization processing on the concentration differences, constructing a spatial gradient field by adopting a piecewise interpolation method, introducing radial basis functions to compensate boundary data loss, and generating gradient distribution rate;
Invoking oxygen concentration data of 5 adjacent monitoring points in a period of 10:00 to 10:05 in table 1, calculating the concentration difference of the adjacent points, when the difference delta C=0.3 mg/L between the point A (8.4 mg/L) and the point B (8.1 mg/L), normalizing delta C by taking 1 minute as a time window, dividing the 0.3mg/L difference by the length of the time window for 60 seconds to obtain a change rate of 0.005 mg/(L.s), constructing a spatial gradient field by adopting a linear interpolation method, and when gradient values of four adjacent points are [0.005,0.004,0.006,0.003] mg/(L.s), respectively, introducing a radial basis function of epsilon=0.5 to the missing boundary point to compensate, and when the theoretical gradient of the boundary point is 0.004 mg/(L.s), correcting the gradient distribution rate after compensation to be 0.004× (1+0.5) 0.006 mg/(L.s).
Analyzing gradient distribution rate through a multivariable nonlinear coupling model, acquiring root depth data through a root profile sampling method, measuring total porosity through a ring cutting method, acquiring soil porosity parameters through a mercury compression method, integrating the root depth data and the soil porosity parameters, calculating the diffusion rate of a root oxygen consumption rate gradient field in the pore connectivity index direction, performing adjustment on the diffusion resistance coefficient in the nonlinear coupling model through the volume water content in-situ measured by a time domain reflectometer, generating an oxygen consumption gradient trend state, and transmitting the oxygen consumption gradient trend state to an osmotic pressure state monitoring module;
inputting gradient distribution ratio into a multivariable model, when the depth measured by sampling a root system profile is 0.8m, obtaining 125g of soil sample wet weight and 110g of dry weight by adopting a ring cutter method, calculating the aperture ratio of total porosity (125-110)/125X 100% = 12%, measuring aperture ratio of aperture >50 μm by using a mercury porosimetry method to be 35%, setting aperture connectivity index = 12% x35% = 4.2%, when the diffusion rate of an oxygen consumption rate gradient field in the X direction is 0.008 mg/(L.s), substituting 28% of volume water content measured by a time domain reflectometer into the model, and adjusting diffusion resistance coefficient according to a proportion of 0.8 if the water content exceeds 25%, and adjusting original coefficient 1.2 to be 1.2X 0.8 = 0.96, thereby generating an oxygen consumption gradient trend state.
Referring to fig. 2, the osmotic pressure status monitoring module includes:
The osmotic pressure acquisition submodule is used for configuring a digital temperature sensor to monitor the temperature of a root system, deploying sensor nodes according to depth intervals, synchronously acquiring temperature data, recording osmotic pressure at fixed time intervals and generating an osmotic pressure time sequence set comprising temperature compensation parameters;
DS18B20 digital temperature sensor is deployed on root system section at depth intervals of 0.1 meter, 0.3 meter and 0.5 meter, sampling frequency of sensor is 1Hz, when temperature data are synchronously collected, osmotic pressure original value is recorded every 5 seconds, when temperature measured by the sensor at depth of 0.3 meter is 25.6 ℃, osmotic pressure original value is 1.2MPa, and according to temperature compensation parametersOsmotic pressure is corrected, and the calculation formula is as follows, wherein,Is the corrected osmotic pressure obtained by combining the temperature measured value and the osmotic pressure original value and calculating through a compensation formula,Representing the original measurement of osmotic pressure, reference temperatureWhen t=25.6 ℃, the osmotic pressure after compensation was 1.2+0.02× (25.6-25) =1.212 MPa, and 10 sets of data were recorded consecutively to generate an osmotic pressure time series set.
Table 2 osmotic pressure data table
As shown in table 2, the temperature compensation parameter α is set according to laboratory calibration data, and the calibration method is to control the temperature to rise from 20 ℃ to 30 ℃ in an incubator, measure the osmotic pressure variation every 1 ℃ rise, and fit the linear regression curve slope to obtain α=0.02 MPa/° C, and the time sequence set storage format is (time stamp, depth, osmotic pressure after compensation).
The gradient difference value submodule is used for calling a osmotic pressure time sequence set, combining root system temperature data acquired by a DS18B20 digital temperature sensor, calculating osmotic pressure after temperature compensation, extracting osmotic pressure difference values in adjacent time windows, and superposing oxygen consumption gradient trend states to generate an osmotic pressure gradient difference value;
the compensated osmolarity data in the 11:00 to 11:10 time period of Table 2 were recalled, and the difference between adjacent time windows (5 minute intervals) was calculated asWhen=11:00=1.212MPa,When=11:05=1.228 MPa, differenceWhen the oxygen consumption gradient trend state parameter G=0.008 mg/(L.s) is superimposed, w=0.5 is calculated to generate an osmotic pressure gradient difference valueWhen the correlation coefficient is calculated as 0.6 by data, the weight w is mapped as w=0.6/1.2=0.5.
The change amplitude submodule is used for calling a peak Gu Jizhi in the osmotic pressure gradient difference value, calculating a sliding window mean value of the absolute value of the peak-valley difference value, adjusting the sliding window mean value through temperature compensation parameters to generate an osmotic pressure change dynamic offset, and transmitting the osmotic pressure change dynamic offset to the root system metabolic state analysis module, wherein the window length is 5 minutes;
Extracting peak Gu Jizhi of osmotic gradient difference in 11:00 to 11:30 period in table 2, when the peak value sequence is [0.020,0.018,0.022] MPa, the valley value sequence is [0.015,0.012,0.014] MPa, calculating sliding window (window length 3 group) mean value of absolute value of peak-valley difference, and the peak-valley difference of window 1 is、、The average value is (0.005+0.006+0.008)/3=0.0063 MPa, and the average value is adjusted according to the temperature compensation parameter alpha, when the temperature fluctuation range isWhen=0.5 ℃, the adjustment coefficientWhereinRepresenting the temperature fluctuation amplitude, alpha represents the temperature compensation coefficient, and the osmotic pressure change dynamic offset=0.0063×1.01=0.00636MPa。
Referring to fig. 2, the root metabolism analysis module includes:
the damage risk submodule is used for calling dynamic offset of osmotic pressure change and oxygen consumption gradient trend states, calculating covariance of the dynamic offset and the oxygen consumption gradient trend states in a continuous time window, extracting covariance main diagonal elements, and performing item-by-item comparison with a preset damage risk threshold value to generate a damage risk coefficient, wherein the damage risk threshold value is determined by a covariance extremum when the probability of cell damage in forward data is more than 90%;
invoking osmotic pressure change dynamic offsetTrend of oxygen consumption gradientIntercepting the data sequence of three consecutive time windows (window 1 to window 3), calculating the covariance matrixExtracting main diagonal elementsFor data of window 1, calculate the meanCalculating the deviation square value of each data point and the mean value, and dividing the deviation square value by the degree of freedom n-1=2 after summing to obtainCalling a preset damage risk threshold valueItem-by-item comparisonAnd (3) withWhen the window 1Marking risk factors=0, Similarly to calculate window 2 and window 30.00000003 And 0.00000002, respectively, which are both less than a threshold value, a risk coefficient sequence is generatedThe threshold value is set according to the method that 100 groups of samples are counted through a laboratory cell damage experiment, and the damage group is obtainedMean value ofNon-invasive group meanTake the intermediate valueAs a demarcation point.
The state integration sub-module is used for calling the damage risk coefficient, superposing real-time temperature data, and performing linear interpolation on the damage risk coefficient according to the temperature segmentation interval to generate a metabolic state vector;
calling damage risk coefficientAnd real-time temperature dataDividing the temperature interval into a low temperature section T <25 ℃, a medium temperature section T <28 ℃, and a high temperature section T <28 ℃ when the temperature of the window 2 is equal to or less than 25 DEG CWhen the temperature of the mixture is 26.1 ℃ and belongs to the middle temperature range, the interpolation rule is adopted,Is the parameter value after temperature adjustment, calculatesWhereinIs the parameter value after temperature adjustment in window 2, when the temperature of window 3When the temperature is=25.8 ℃, the method also belongs to a middle temperature section, and calculatesThe temperature segmentation is based on plant root metabolism rate experimental data, wherein the metabolic activity is reduced by 50% below 25 ℃ and the enzyme activity is attenuated by 30% above 28 ℃, and the interpolation coefficient is obtained by linear fitting of the slope of the experimental dataDetermining, generating a metabolic state vector。
The model analysis submodule inputs the metabolism state vector into a multi-condition state machine model, defines damage risk coefficient and temperature value as state transition conditions, distributes weight through pore connectivity and root depth, inputs the multi-condition state machine model to judge damage risk level, calculates Manhattan distance between the current state and the metabolism abnormality mode, generates a metabolism abnormality state judgment result, and transmits the metabolism abnormality state judgment result to the root temperature parameter reconstruction module;
The multi-condition state machine model is constructed by setting a discrete metabolic state based on root physiology, a damage risk coefficient and a logic rule and defining a target metabolic abnormality mode;
Inputting the metabolism state vector into a multi-condition state machine model, defining four discrete states, namely normal (S0), mild abnormality (S1), moderate abnormality (S2) and severe abnormality (S3), and constructing the vector according to the acquired real-time dataOxygen consumption gradient= -28%, Based on porosityCalculate oxygen consumption rate with 0.3, connectivity ci=0.5, depth 0.8mOsmotic pressure offset(Dynamic predictive model outputs expected values)Bar), root system temperature=26.5 ℃, Manhattan distance was calculatedContrast thresholdSatisfies d less than or equal to 2.4, calculates damage risk coefficientWhereinRepresents the intensity of the trend of oxygen consumption,Representing the weight of the osmotic pressure shift,Representing the degree of porosity of the material,And (3) representing a root depth standardized value, wherein PCI represents a soil pore connectivity index, a state machine judges that d= 1.949 is less than or equal to 2.4, r=0.8 >0.5 (severe anomaly threshold), and a metabolic anomaly state judgment result is generated.
TABLE 3 Metabolic status determination data sheet
Referring to fig. 2, the root temperature parameter reconstruction module includes:
The temperature data sub-module is used for obtaining the steady-state root system temperature data in the metabolic abnormal state judgment result to carry out standardized processing and generating a temperature data set comprising a time stamp and a temperature characteristic mark;
the temperature data submodule extracts the temperature data of the root system in the steady state from the metabolic abnormal state judging result and acquires a time stamp sequenceCorresponding temperature dataThe normalization process adopts a normalization method, and the formula is: Wherein,,Is the maximum value of the temperature within the current time window 1,Is the minimum value of the temperature in the current time window 1, and calculates the normalized temperature of the window 1: Generating a temperature characteristic mark field is-anomaly, assigning a value according to the metabolic abnormal state judgment result (the window 2 is judged to be abnormal, and the mark is 1), and the temperature data set format is as follows:。
Table 4 temperature dataset representative examples
As shown in table 4, the normalized temperature was calculated by normalization, and the abnormality flag field was bound to the metabolic determination result.
The correlation analysis sub-module is used for calling a temperature dataset, traversing the corresponding data points of the temperature sequence and the steady state temperature sequence triggered by the generation Xie Yichang, calculating the absolute difference value of each data point, extracting the minimum value and the maximum value in all the difference values, calling a resolution coefficient rho=0.5 based on a gray correlation analysis algorithm, calculating the correlation coefficient of each data point, taking the arithmetic average value of all the correlation coefficients, and generating the correlation coefficient in a time window;
the correlation analysis sub-module invokes an exception trigger sequence in the temperature datasetAnd steady state sequencesThe absolute difference is calculated across the data points, the difference for window 2: , wherein,The temperature value corresponding to the 1 st trigger event,Is the 2 nd temperature reference value in steady state, and the minimum value of all the difference values is extractedAnd maximum valueAnd (5) calling a gray correlation analysis formula to calculate a correlation coefficient: where the resolution coefficient ρ=0.5, the correlation coefficient for window 2 is calculated as: arithmetic mean is taken for the association coefficients of all data points, three windowsThe association coefficient is:,
The regulation and control instruction submodule is used for calling a relevance coefficient, comparing the coefficient sequence with a relevance threshold value item by item, screening nodes with coefficients lower than the relevance threshold value, extracting temperature regulation amplitude and direction data of a timestamp corresponding to the nodes, and generating a root system temperature regulation and control instruction;
regulation instruction submodule calls relevance coefficient sequenceThe correlation threshold is determined by ROC curve about log index, and the true positive rate in experimental dataFalse positive rateCalculating about step index: ObtainingMaximum value corresponds to threshold valueAnd (3) extracting the time stamp of the node meeting the condition (including 0.572>0.4 of window 1 without screening) from the node with the screening coefficient lower than 0.4 (including 0.572>0.4 of window 3 without screening), outputting 'no regulation and control' if no node meets the condition, and otherwise, generating a root system temperature regulation and control instruction according to a temperature regulation rule.
Referring to fig. 2, the nutrient solution circulation linkage module includes:
The instruction analysis submodule is used for receiving a root system temperature regulation instruction, analyzing temperature regulation amplitude and time stamp parameters in the instruction, screening out a timeout instruction based on a time stamp alignment rule, and generating an aging regulation parameter matched with a current clock;
The instruction analysis submodule receives a root system temperature regulation instruction from the regulation instruction submodule, for example, the instruction format is [ timestamp: 10:25, the regulation amplitude is +2.5 ℃, the current system clock is 10:30, the timestamp alignment rule is called, the overtime threshold is defined as 5 minutes, and the difference value between the instruction timestamp and the current time is calculated: determination of =10:30-10:25=5 minThe instruction is kept for less than or equal to 5 minutes as an effective instruction, ifScreening out for 5 minutes to generate an aging regulation parameter [ effective time window: 10:25-10:30, adjusting amplitude: +2.5 ℃), wherein the current time difference is 5 minutes in the example, the threshold is just met, and the instruction is reserved.
Table 5 time-out decision rule table
As shown in table 5, the time difference was calculated by the clock difference value and the timeout threshold was set according to the system response delay experiment.
The flow velocity dynamic submodule is used for calling a time window of the aging regulation parameter, collecting the original flow velocity data of the electromagnetic flowmeter, setting the number of sample points of the moving average filter according to the length of the time window, eliminating noise interference and generating a flow velocity dynamic base line synchronous with the temperature regulation time sequence;
The flow rate dynamic submodule invokes a time window 10:25-10:30 of the aging regulation parameter to collect raw flow rate data from the electromagnetic flowmeter, for example, the raw data is a sequence of samples per second:
according to the length of the time window of 5 minutes (300 seconds), the number of sample points of the moving average filtering is set to be 300, and a calculation formula is thatWhereinThe Q value of the physical quantity after the filtering process,Is the i-th raw data point,Is a normalized coefficient of mean value calculation, and the first 5 sample points are taken for calculation: a flow velocity dynamic base line [102.48] is generated and is synchronous with the temperature regulation time sequence.
The rotating speed decision sub-module is used for calling a temperature adjustment amplitude and a flow speed dynamic baseline in the aging regulation parameters, mapping the temperature amplitude into a target flow speed increment based on a PID control algorithm, calculating the deviation value of the current flow speed baseline and the target increment, superposing a proportional term, an integral term and a differential term, and adjusting the rotating speed of the circulating pump, wherein the PID control algorithm adopts a Ziegler-Nichols critical proportional method through a Kp proportional gain, a Ki integral gain and a Kd differential gain parameter setting method, the Kp range is 0.5-5.0, ki0.01-0.5 and Kd0.1-2.0, the Kp is adjusted upwards by 10% -30% and the Ki is adjusted downwards by 5% -15% when the flow speed is increased by 10L/min, and the adjusting range is adjusted in a self-matching way along with the flow speed fluctuation amplitude;
the rotation speed decision sub-module calls the temperature adjustment amplitude in the aging regulation parameters= +2.5 ℃, Mapped to target flow rate increment, mapping rule is:, Representing the value of the filtered physical quantity Q, the current flow rate baselineTarget flow rateCollecting real-time flow velocityCalculating deviation: = 103.48-103.1=0.38L/min, e (t) represents the time-dependent deviation, i.e. the instantaneous difference of the target value from the current actual value, based on Ziegler-Nichols critical scale method, the initial PID parameters are、、According to the flow rate increment dynamic regulation rule, every 10L/min of flow rate increase,Up-regulating by 20%,Down-regulating by 10%,Is unchanged. The current flow rate baseline is 102.48L/min (reference value 100L/min), incrementThe parameter remains at the initial value below the 10L/min threshold. Calculating an error signalWherein u (t) is a real-time control signal output by the PID control algorithm,Is the proportional gain, e (t) is the current error,Representing the integral gain, eliminating steady-state error based on the cumulative value of the error,Representing the differential gain of the signal,Representing the rate of change of the error, t representing the current time,Representing the integral time variable, assuming the integral term accumulates errorDifferential termU (t) =2.0×0.38+0.1×0.15+0.5×0.02=0.76+0.015+0.01=0.785, and porosity is introduced [ (]I.e., the ratio of pore volume to total soil volume) and the oxygen consumption rate [ ]Wherein k represents an intrinsic oxygen consumption rate constant,Representing the coefficient of attenuation of the porosity of the porous body,Represents the connectivity gain factor, CI represents the pore connectivity index,Representing real-time oxygen concentration, dynamically correcting target flow speed increment and adjusting PID parameters based on oxygen consumption rateReference increment for temperature regulationAnd (e.g., +5L/min) performing feedforward compensation, wherein the formula is as follows: WhereinIs the coupling coefficient of the oxygen consumption flow velocity,Is the reference oxygen consumption rate. In the example, when the porosity is=0.3, Connectivity ci=0.6, oxygen concentrationAt this time, the target increment was corrected from +5L/min to +5.38L/min. PID parameter self-adaption, low porosity%=0.3) Trigger proportional gain(Initial value)) According to the formulaIncreasing to 3.36, increasing response speed, and retaining initial integral gain when the flow speed increment threshold (10L/min) is not reachedDifferential gainReal-time flow rate deviationOutput rotation speed adjustment quantity calculated by PIDThe dynamic coordination of soil pore structure characteristics and fluid control is realized, the accuracy is improved, and the rotating speed of the circulating pump is adjusted according to u (t) =0.785.
Referring to fig. 3, the method includes:
S1, collecting root system oxygen concentration data in real time, calculating root system oxygen consumption rate gradient, and judging oxygen consumption gradient trend state based on a multivariable nonlinear coupling model;
S2, obtaining real-time data of cell osmotic pressure in the hydroponic nutrient solution through dissolved oxygen sensing, obtaining data of cell osmotic pressure change, and carrying out difference calculation by combining with the oxygen consumption gradient trend state to generate dynamic offset of osmotic pressure change;
S3, judging the damage risk of root system cells and the real-time root system temperature of the risk state based on the dynamic offset of osmotic pressure change and in combination with the oxygen consumption rate gradient trend state, and obtaining a metabolic abnormal state judgment result through a multi-condition state machine model;
S4, comparing the metabolism abnormality triggering temperature with the approach degree of the steady-state root system temperature before the abnormal state occurs in the metabolism abnormal state judging result through a gray correlation analysis algorithm, and generating a root system temperature regulation instruction;
And S5, calling a root system temperature regulation instruction, acquiring circulating flow rate data in real time, applying a PID control algorithm, and regulating the rotating speed of the circulating pump through proportional, integral and differential combined operation.
It should be understood that the term "and/or" is merely an association relationship describing the associated object, and means that three relationships may exist, for example, a and/or B, and may mean that a exists alone, while a and B exist alone, and B exists alone, wherein a and B may be singular or plural. In addition, the character "/" herein generally indicates that the associated object is an "or" relationship, but may also indicate an "and/or" relationship, and may be understood by referring to the context.
In the present invention, "at least one" means one or more, and "a plurality" means two or more. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (a, b, or c) of a, b, c, a-b, a-c, b-c, or a-b-c may be represented, wherein a, b, c may be single or plural.
It should be understood that, in various embodiments of the present invention, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, specific working procedures of the apparatus, device and unit described above may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus, device and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of elements is merely a logical function division, and there may be additional divisions of actual implementation, e.g., multiple elements or components may be combined or integrated into another device, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method of the embodiments of the present invention. The storage medium includes a U disk, a removable hard disk, a read-only memory (ROM), a random access memory (randomaccess memory, RAM), a magnetic disk or an optical disk, etc. which can store the program code.
The foregoing is merely illustrative embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily think about variations or substitutions within the technical scope of the present invention, and the invention should be covered. Therefore, the protection scope of the invention is subject to the protection scope of the claims.