CN117369550A - Intelligent humidity adjustment method, medium and system for greenhouse - Google Patents
Intelligent humidity adjustment method, medium and system for greenhouse Download PDFInfo
- Publication number
- CN117369550A CN117369550A CN202311540908.7A CN202311540908A CN117369550A CN 117369550 A CN117369550 A CN 117369550A CN 202311540908 A CN202311540908 A CN 202311540908A CN 117369550 A CN117369550 A CN 117369550A
- Authority
- CN
- China
- Prior art keywords
- humidity
- greenhouse
- growth
- growth index
- optimal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 230000012010 growth Effects 0.000 claims abstract description 126
- 230000007613 environmental effect Effects 0.000 claims abstract description 50
- 238000012417 linear regression Methods 0.000 claims abstract description 33
- 238000005286 illumination Methods 0.000 claims abstract description 28
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 10
- 239000003337 fertilizer Substances 0.000 claims abstract description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 22
- 238000012549 training Methods 0.000 claims description 22
- 230000000694 effects Effects 0.000 claims description 20
- 239000002689 soil Substances 0.000 claims description 14
- 238000013507 mapping Methods 0.000 claims description 9
- 238000012544 monitoring process Methods 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 230000003203 everyday effect Effects 0.000 claims description 3
- 230000003750 conditioning effect Effects 0.000 claims description 2
- 238000012795 verification Methods 0.000 claims description 2
- 230000008635 plant growth Effects 0.000 abstract description 3
- 230000001276 controlling effect Effects 0.000 description 5
- 238000013459 approach Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000007791 dehumidification Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000001035 drying Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 238000009736 wetting Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000007363 regulatory process Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000007921 spray Substances 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D22/00—Control of humidity
- G05D22/02—Control of humidity characterised by the use of electric means
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Greenhouses (AREA)
Abstract
The invention provides a greenhouse intelligent humidity adjusting method, medium and system, belonging to the technical field of greenhouse planting, comprising the following steps: acquiring environmental parameter sets of multiple groups of greenhouse crop growing periods; calculating a growth index increment corresponding to each environmental parameter; establishing a linear regression model for representing the relationship among temperature, humidity, water and fertilizer supply, illumination and growth index increment; fitting the linear regression model to obtain a crop growth environment model; acquiring an optimal humidity range of crop growth by using a crop growth environment model; acquiring the humidity of a greenhouse to be controlled to obtain a first humidity; and comparing the first humidity with the optimal humidity range, and sending the first humidity to a humidifying and dehumidifying system for humidity adjustment in the greenhouse. The method solves the technical problems that the prior art often adopts manual experience to control the humidity adjustment of the greenhouse and fails to consider the adjustment of the optimal humidity threshold value in the greenhouse for plant growth.
Description
Technical Field
The invention belongs to the technical field of greenhouse planting, and particularly relates to an intelligent greenhouse humidity adjusting method, medium and system.
Background
The traditional greenhouse humidity control is mainly regulated by experience, and has the problems of extensive monitoring and control, lag regulation, incapability of real-time optimization and the like. In recent years, with the development of sensing technology and computer technology, a method for optimally controlling greenhouse humidity by adopting environmental parameter modeling is proposed. Traditionally, greenhouse humidity is regulated and controlled mainly by means of manual experience of workers. According to the method, a temperature and humidity target range is preset according to the types and growth stages of crops; the greenhouse humidity is then maintained by turning on or off the humidification and dehumidification devices at regular intervals. The method is simple to realize, but has the problem of extensive monitoring and control. Because accurate environmental parameters cannot be obtained in real time, the experience target range is difficult to adapt to environmental changes and actual demands of crops, and excessive wetting or excessive drying is easy to cause. With the popularization of various environmental sensors, a temperature and humidity sensor can be installed in a greenhouse to monitor the current environmental state in real time, and a humidifying and dehumidifying system is controlled in a feedback manner to enable humidity to approach a set target. This is more accurate than empirical control, but the control system is relatively passive, and the target humidity range is still determined empirically by the person and cannot be actively adjusted according to crop demands.
Disclosure of Invention
In view of the above, the invention provides a greenhouse intelligent humidity adjustment method, medium and system, which can solve the technical problems that the prior art often adopts manual experience to control the greenhouse humidity adjustment and cannot consider the adjustment of the optimal humidity threshold in the greenhouse for plant growth.
The invention is realized in the following way:
the first aspect of the invention provides a greenhouse intelligent humidity adjustment method, which comprises the following steps:
s10, acquiring environment parameter sets of a plurality of groups of greenhouse crop growing periods, wherein the environment parameter sets comprise greenhouse environment parameters acquired per hour, including temperature, humidity, water and fertilizer supply degree, illumination and growth indexes; the growth index is the average area of orthographic projections of a plurality of vertical surfaces of the crops;
s20, calculating a growth index increment corresponding to each environmental parameter;
s30, establishing a linear regression model for representing the relationship among temperature, humidity, water and fertilizer supply, illumination and growth index increment;
s40, fitting the linear regression model to obtain a crop growth environment model;
s50, acquiring an optimal humidity range of crop growth by using a crop growth environment model;
s60, collecting the humidity of a greenhouse to be controlled to obtain a first humidity;
s70, comparing the first humidity with an optimal humidity range, and if the first humidity is lower than the minimum value of the optimal humidity range, sending a control instruction to the humidifying system to increase the humidity; otherwise, a control instruction is sent to the dehumidifying equipment to reduce the humidity.
On the basis of the technical scheme, the intelligent humidity adjusting method for the greenhouse can be further improved as follows:
the step of acquiring the environmental parameter sets of the growth period of the greenhouse crops comprises the following steps:
a temperature and humidity sensor, a soil humidity sensor, an illumination sensor and an image acquisition device are arranged in the greenhouse and are used for monitoring and acquiring greenhouse environment parameters in real time;
setting a timer, and collecting data collected by various sensors according to the frequency of each hour;
shooting the growth condition of crops in a greenhouse by using image acquisition equipment according to preset time every day;
identifying crops in each image by using an image processing algorithm, and extracting crop outlines;
calculating the orthographic projection areas of a plurality of views of each crop sample, and taking the average value as the growth index of the sample;
repeating the steps, and continuously tracking and recording the growth index of crops;
and acquiring a temperature, humidity, soil humidity and illumination data set of the complete growth cycle of the crops and a corresponding growth index data set.
The step of calculating the growth index increment corresponding to each environmental parameter comprises the following steps:
arranging the environmental parameter data set and the growth index data set acquired in the step S10 into a plurality of groups of data pairs according to time sequence;
traversing the data set, and pairing two adjacent groups of data, namely pairing the current group of environment parameters and the growth index with the previous group;
calculating an increment of the growth index for each paired set of data;
recording the corresponding relation between each environmental parameter and the increment of the growth index in each group of data;
and traversing all the data pairs to obtain a mapping relation data set of each environmental parameter and the growth index increment.
Wherein, the step of establishing a linear regression model includes:
establishing a linear regression model by using the environmental parameter and growth index increment mapping relation data set obtained in the step S20;
taking the environmental parameter as an independent variable and the growth index increment as an independent variable;
and testing a plurality of linear regression algorithms, and selecting the linear regression algorithm with the strongest linear relation and the best fitting effect to obtain a final environment parameter and growth index increment prediction model.
The step of fitting the linear regression model comprises the following steps:
training the data set obtained in the step S30 by using a training algorithm of a linear regression model;
the algorithm super-parameters are adjusted, so that the fitting effect of the model obtained through training on the training set is optimal;
verifying the prediction effect of the model on the verification set;
repeating the steps until a crop growth environment model with optimized fitting degree and generalization capability of the training set is obtained.
The method of claim 1, wherein the step of obtaining an optimal humidity range for crop growth using a crop growth environmental model comprises:
in a crop growth environment model, fixing temperature, soil humidity and illumination parameters, and only changing humidity parameters;
predicting by the running model for multiple times to obtain predicted growth indexes under different humidity conditions;
analyzing the functional relation between the growth index and the humidity, and determining the humidity range in which the growth index reaches the maximum;
all possible combinations of temperature and illumination are traversed to determine the optimum humidity range in all directions.
The method for acquiring the humidity of the greenhouse to be controlled to obtain the first humidity comprises the following steps of:
a humidity sensor is arranged in the greenhouse to be controlled and used for monitoring the air humidity of the greenhouse in real time;
a data acquisition device is arranged and connected with the humidity sensor;
periodically reading the output of the humidity sensor and recording the acquired humidity reading;
at the beginning of the control interval, the collected humidity value is taken as the first humidity.
Wherein the step of comparing the first humidity with the optimal humidity range comprises:
acquiring a first humidity value acquired in the step S60;
acquiring the optimal humidity range determined in the step S50;
judging the magnitude relation between the first humidity value and the optimal humidity range;
if the first humidity is lower than the minimum value of the optimal humidity range, calculating the humidity amount to be increased;
if the first humidity is higher than the maximum value of the optimal humidity range, the amount of humidity that needs to be reduced is calculated.
A second aspect of the present invention provides a computer readable storage medium, wherein the computer readable storage medium stores program instructions, and the program instructions are used to execute the intelligent humidity control method for a greenhouse when the program instructions are executed.
A third aspect of the present invention provides a greenhouse intelligent humidity conditioning system, comprising the computer readable storage medium described above.
Compared with the prior art, the intelligent humidity adjusting method, medium and system for the greenhouse provided by the invention have the beneficial effects that: the invention can actively simulate and predict the optimal humidity range by constructing an accurate crop growth environment model, rather than passively presetting an experience target. The control system takes the optimal range as a reference to realize the active optimal adjustment of humidity. The model comprehensively considers the temperature, illumination, soil humidity and other multi-environment parameters, and combines the parameters with the real-time growth index of crops to determine the dynamic humidity target. The method ensures that the change of humidity in the regulating process is always matched with the real-time growth condition of crops, thereby effectively preventing over-wetting or over-drying, and the whole process is accurately controlled according to specific data and threshold values. The method solves the technical problems that the prior art often adopts manual experience to control the humidity adjustment of the greenhouse and fails to consider the adjustment of the optimal humidity threshold value in the greenhouse for plant growth.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments of the present invention will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method provided by the present invention;
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, based on the embodiments of the invention, which are apparent to those of ordinary skill in the art without inventive faculty, are intended to be within the scope of the invention.
Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, based on the embodiments of the invention, which are apparent to those of ordinary skill in the art without inventive faculty, are intended to be within the scope of the invention.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.
In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings are merely for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the apparatus or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present invention.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
As shown in fig. 1, the first aspect of the present invention provides a flowchart of a method for intelligent humidity adjustment of a greenhouse, which includes the following steps:
s10, acquiring environment parameter sets of a plurality of groups of greenhouse crop growing periods, wherein the environment parameter sets comprise greenhouse environment parameters acquired per hour, including temperature, humidity, water and fertilizer supply degree, illumination and growth indexes; the growth index is the average area of orthographic projections of a plurality of vertical surfaces of the crops;
s20, calculating a growth index increment corresponding to each environmental parameter;
s30, establishing a linear regression model for representing the relationship among temperature, humidity, water and fertilizer supply, illumination and growth index increment;
s40, fitting the linear regression model to obtain a crop growth environment model;
s50, acquiring an optimal humidity range of crop growth by using a crop growth environment model;
s60, collecting the humidity of a greenhouse to be controlled to obtain a first humidity;
s70, comparing the first humidity with an optimal humidity range, and if the first humidity is lower than the minimum value of the optimal humidity range, sending a control instruction to the humidifying system to increase the humidity; otherwise, a control instruction is sent to the dehumidifying equipment to reduce the humidity.
The following describes in detail the specific embodiments of the above steps:
s10, acquiring environment parameter sets of a plurality of groups of greenhouse crop growing periods, wherein the environment parameter sets comprise greenhouse environment parameters acquired per hour, including temperature, humidity, water and fertilizer supply degree, illumination and growth indexes; the growth index is the average area of orthographic projections of a plurality of vertical surfaces of the crops;
the specific implementation mode is as follows:
(1) Temperature and humidity sensors, soil humidity sensors, illumination sensors and image acquisition equipment are arranged in the greenhouse and used for monitoring and acquiring greenhouse environment parameters including temperature, humidity, soil humidity and illumination intensity in real time.
(2) A timer is set to collect data collected by various sensors according to the frequency of each hour. The collected data is stored in a data server.
(3) The image acquisition equipment is used for shooting the growth condition of crops in the greenhouse every day according to the preset time. The multi-view shooting can be adopted, so that the whole crop is ensured to be shot.
(4) Using an image processing algorithm, the crop in each image is identified, and the crop profile is extracted.
(5) The forward projected areas of multiple views of each crop sample were calculated and the average taken as the growth index for that sample.
(6) Repeating the steps (3) - (5), and continuously tracking and recording the growth index of the crops.
(7) And acquiring a temperature, humidity, soil humidity and illumination data set of the complete growth cycle of the crops and a corresponding growth index data set.
S20, calculating a growth index increment corresponding to each environmental parameter;
the specific implementation mode is as follows:
(1) The environmental parameter data set and the growth index data set acquired in step S10 are arranged in time series into a plurality of sets of data pairs.
(2) Traversing the data set, and pairing two adjacent groups of data, namely pairing the current group of environment parameters and the growth index with the previous group.
(3) For each paired set of data, an increment of growth index was calculated.
(4) And recording the corresponding relation between each environmental parameter and the increment of the growth index in each group of data.
(5) And traversing all the data pairs to obtain a mapping relation data set of each environmental parameter and the growth index increment.
S30, establishing a linear regression model for representing the relationship among temperature, humidity, water and fertilizer supply, illumination and growth index increment;
the specific implementation mode is as follows:
(1) And (3) establishing a linear regression model by using the environmental parameter and growth index increment mapping relation data set obtained in the step (S20).
(2) The environmental parameter is taken as an independent variable, and the growth index increment is taken as an independent variable.
(3) And testing various linear regression algorithms including common linear regression, ridge regression, LASSO regression and the like, and evaluating and comparing the performances of the models.
(4) And selecting a linear regression algorithm with the strongest linear relation and the best fitting effect to obtain a final prediction model of the environmental parameters and the growth index increment.
S40, fitting the linear regression model to obtain a crop growth environment model;
the specific implementation mode is as follows:
(1) And training the environmental parameter data set and the growth index increment data set obtained in the step S30 by using a training algorithm of a linear regression model.
(2) And (3) adjusting the algorithm super-parameters to ensure that the fitting effect of the model obtained by training on the training set is optimal.
(3) The performance index of the statistical model, such as the decision coefficient R square, the mean square error, etc., ensures that it reaches the set target.
(4) The predictive effect of the model on the validation set is validated.
(5) Repeating the steps (1) - (4) until a crop growth environment model with optimized training set fitting degree and generalization capability is obtained.
S50, acquiring an optimal humidity range of crop growth by using a crop growth environment model;
the specific implementation mode is as follows:
(1) In a crop growth environment model, the temperature, soil humidity and illumination parameters are fixed, and only the humidity parameter is changed.
(2) And (5) carrying out model prediction for multiple times to obtain predicted growth indexes under different humidity conditions.
(3) And analyzing the function relation of the growth index and the humidity, and determining the humidity range in which the growth index reaches the maximum.
(4) Repeating the steps (1) - (3) to obtain the optimal humidity range under the temperature and illumination conditions.
(5) All possible combinations of temperature and illumination are traversed to determine the optimum humidity range in all directions.
S60, collecting the humidity of a greenhouse to be controlled to obtain a first humidity;
the specific implementation mode is as follows:
(1) And a humidity sensor is arranged in the greenhouse to be controlled and used for monitoring the air humidity of the greenhouse in real time.
(2) And a data acquisition device is arranged and connected with the humidity sensor.
(3) The output of the humidity sensor is periodically read and the collected humidity readings are recorded.
(4) And filtering and smoothing the acquired humidity data.
(5) At the beginning of the control interval, the collected humidity value is taken as the first humidity.
S70, comparing the first humidity with an optimal humidity range, and if the first humidity is lower than the minimum value of the optimal humidity range, sending a control instruction to the humidifying system to increase the humidity; otherwise, a control instruction is sent to the dehumidifying equipment to reduce the humidity.
The specific implementation mode is as follows:
(1) The first humidity value acquired in step S60 is acquired.
(2) The optimal humidity range determined in step S50 is acquired.
(3) And judging the magnitude relation between the first humidity value and the optimal humidity range.
(4) If the first humidity is below the minimum of the optimal humidity range, then the amount of humidity that needs to be increased is calculated.
(5) And controlling a humidifying system to spray and supplement water into the greenhouse according to the humidifying amount.
(6) If the first humidity is higher than the maximum value of the optimal humidity range, the amount of humidity that needs to be reduced is calculated.
(7) And controlling the moisture removal system to remove redundant moisture according to the moisture reduction amount.
(8) And (5) sequentially adjusting and controlling to gradually approach the humidity of the greenhouse to the optimal range.
The following adopts a specific embodiment to describe the technical scheme of the invention in detail:
s10 detailed description of the invention
1. Environmental parameter acquisition
The following sensors and devices are set up in the greenhouse to collect environmental parameters:
temperature sensor T s Measuring the temperature T (T), in degrees Celsius
Humidity sensor H s Relative humidity RH (t) in% was measured
Soil humidity sensor SM s Soil moisture SM (t), unit%
Illumination sensor L s The light intensity PAR (t) in [ mu ] mol/m2/s was measured
Camera C for shooting crop image
2. Data acquisition and storage
And setting a data acquisition card DAQ and a Timer, and acquiring data of each sensor according to the frequency of once per hour.
The collected data is converted into digital signals through DAQ and transmitted to a data Server for storage. The stored data format is:
Data＝{T(t)，RH(t)，SM(t)，PAR(t)，Img(t)}
where Img (t) represents a crop image taken at time t.
3. Growth index calculation
Extracting each crop sample S from Img (t) using an image processing algorithm i Contour region R of (t) i (t) pair R i (t) performing principal component analysis to obtain vectors consisting of multi-view orthographic projection areas of the crop samples:
A i (t)＝[A i1 (t)，A i2 (t)，...，A in (t)] T
calculating the growth index GI of the sample i (t)：
GI i (t)＝mean(A i (t))
For all n samples, a growth index set is constructed:
GI(t)＝[GI 1 (t)，GI 2 (t)，...，GI n (t)] T
4. effects of
Through the steps, the environment parameter combination Data set { Data (t) } and the corresponding crop growth index Data set { GI (t) } in the greenhouse can be obtained periodically, and training Data can be generated for subsequent modeling analysis.
S20 detailed description of the invention
1. Data pairing
Sorting the environmental parameter dataset { Data (t) } and the growth index dataset { GI (t) } in chronological order
Traversing the dataset, and pairing two groups of data adjacent in time:
(Data (t), GI (t)) and (Data (t+1), GI (t+1))
2. Differential calculation
For the paired two sets of data, the increment of growth index was calculated:
ΔGI(t)＝GI(t+1)-GI(t)
3. construction of mapping relation data set
In each pairing, the environmental parameters Data (t) and the growth index increment Δgi (t) are extracted, constituting a new dataset:
DataSet＝{(Data(t)，ΔGI(t))}
the dataset presents a mapping between environmental parameters and growth index increases.
4. Effects of
By means of time-aligned differential calculation, the time integral effect of the environmental parameters on the growth index can be eliminated, and only the incremental effect of the environmental parameters is modeled, so that the model is more accurate.
S30 detailed description
1. Establishing a linear regression model
For a DataSet, a linear regression model is built:
where W is the weight vector of the environmental parameter to the growth exponent increment and b is the bias term.
2. Algorithm selection
Testing different linear regression algorithms, e.g. linear regression, ridge regression, LASSO regression, etc
Evaluation of the performance of each algorithm using a k-fold cross validation method
Selecting an algorithm with strong linear relation and good fitting effect to obtain a final weight W * And bias b *
3. Effects of
And obtaining a linear regression model with a predictable relation between the environmental parameters and the growth index increment, and providing a basis for subsequent model fitting and growth condition optimization.
S40 detailed description of the invention
1. Model training
Training the prediction model of the environmental parameter and the growth index increment by using a selected linear regression algorithm and taking the DataSet as a training set to obtain a final model parameter { W } * ，b * }。
2. Model evaluation
Testing model predictive performance on independent validation sets
Calculating performance metrics, e.g. mean square error, R 2 Etc
The algorithm super-parameters are adjusted, and training and testing are repeated, so that the performance index reaches the preset target
3. Effects of
And obtaining a crop growth environment model which is well fit to the relationship between the environment parameters and the growth index increment. The model can accurately predict the growth indexes under different environmental conditions.
S50 detailed description of the invention
1. Simulating environmental scenes
Setting different temperatures T and illumination PAR conditions in an environment model obtained by training
Changing humidity parameter RH only to generate various environment scenes
2. Growth prediction
For each humidity scene, the growth index is predicted using an environmental model
Obtaining the prediction function relation of the growth index and the humidity
3. Humidity optimization
AnalysisFinding the humidity range [ RH ] with maximum growth index min ，RH max ]
Repeating the above process, traversing different temperatures and illumination conditions, and determining optimal humidity range under each condition
4. Effects of
And the optimal humidity range of crop growth under the light temperature condition is obtained through model prediction simulation, so that reference is provided for subsequent environmental control.
S60 detailed description
1. Humidity acquisition
In the greenhouse to be controlled, a humidity sensor H is provided s
The data acquisition card DAQ acquires humidity RH (t) at a certain frequency
2 data processing
Filtering and smoothing the collected humidity data to remove noise
At control start time t 0 The obtained smoothed humidity is the first humidity RH 0
3. Effects of
Obtaining the actual humidity RH of the greenhouse at the beginning of control 0 Feedback is provided for subsequent control.
S70 detailed description
1. Comparative humidity
Acquiring a first humidity RH 0
Acquisition ofOptimal humidity range [ RH ] min ，RH max ]
Comparison of RH 0 Magnitude relation to optimal humidity range
2. Control strategy
If RH 0 ＜RH min Calculating the humidification quantity and sending a control instruction to a humidification system
If RH 0 ＞RH max Calculating the dehumidification amount and sending a control instruction to a dehumidification system
Controlling humidity to gradually approach the optimal range
3. Effects of
By comparison with the optimal humidity range and closed-loop control, the greenhouse humidity can be stabilized in a state most favorable for crop growth.
Specifically, the principle of the invention is as follows: the method comprises the steps of setting temperature and humidity, illumination, soil humidity sensors and camera equipment, collecting greenhouse environment parameters in real time, calculating crop growth indexes, and obtaining a data set pair of the environment parameters and the growth indexes as model training data. To eliminate the time integral effect of the environmental parameters on the growth index, an increment mapping model, namely a quantitative relation model between the environmental parameters and the growth index increment, is constructed. The model can accurately describe the influence of the environment parameter increment on the growth.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (10)
1. The intelligent humidity adjusting method for the greenhouse is characterized by comprising the following steps of:
s10, acquiring environment parameter sets of a plurality of groups of greenhouse crop growing periods, wherein the environment parameter sets comprise greenhouse environment parameters acquired per hour, including temperature, humidity, water and fertilizer supply degree, illumination and growth indexes; the growth index is the average area of orthographic projections of a plurality of vertical surfaces of the crops;
s20, calculating a growth index increment corresponding to each environmental parameter;
s30, establishing a linear regression model for representing the relationship among temperature, humidity, water and fertilizer supply, illumination and growth index increment;
s40, fitting the linear regression model to obtain a crop growth environment model;
s50, acquiring an optimal humidity range of crop growth by using a crop growth environment model;
s60, collecting the humidity of a greenhouse to be controlled to obtain a first humidity;
s70, comparing the first humidity with an optimal humidity range, and if the first humidity is lower than the minimum value of the optimal humidity range, sending a control instruction to the humidifying system to increase the humidity; otherwise, a control instruction is sent to the dehumidifying equipment to reduce the humidity.
2. The intelligent humidity control method of claim 1, wherein the step of obtaining a plurality of sets of environmental parameters for a growing period of greenhouse crops comprises:
a temperature and humidity sensor, a soil humidity sensor, an illumination sensor and an image acquisition device are arranged in the greenhouse and are used for monitoring and acquiring greenhouse environment parameters in real time;
setting a timer, and collecting data collected by various sensors according to the frequency of each hour;
shooting the growth condition of crops in a greenhouse by using image acquisition equipment according to preset time every day;
identifying crops in each image by using an image processing algorithm, and extracting crop outlines;
calculating the orthographic projection areas of a plurality of views of each crop sample, and taking the average value as the growth index of the sample;
repeating the steps, and continuously tracking and recording the growth index of crops;
and acquiring a temperature, humidity, soil humidity and illumination data set of the complete growth cycle of the crops and a corresponding growth index data set.
3. The intelligent humidity control method of claim 1, wherein the step of calculating a growth index increment corresponding to each environmental parameter comprises:
arranging the environmental parameter data set and the growth index data set acquired in the step S10 into a plurality of groups of data pairs according to time sequence;
traversing the data set, and pairing two adjacent groups of data, namely pairing the current group of environment parameters and the growth index with the previous group;
calculating an increment of the growth index for each paired set of data;
recording the corresponding relation between each environmental parameter and the increment of the growth index in each group of data;
and traversing all the data pairs to obtain a mapping relation data set of each environmental parameter and the growth index increment.
4. The intelligent humidity control method of claim 1, wherein the step of establishing a linear regression model comprises:
establishing a linear regression model by using the environmental parameter and growth index increment mapping relation data set obtained in the step S20;
taking the environmental parameter as an independent variable and the growth index increment as an independent variable;
and testing a plurality of linear regression algorithms, and selecting the linear regression algorithm with the strongest linear relation and the best fitting effect to obtain a final environment parameter and growth index increment prediction model.
5. The intelligent humidity control method of claim 1, wherein the step of fitting the linear regression model comprises:
training the data set obtained in the step S30 by using a training algorithm of a linear regression model;
the algorithm super-parameters are adjusted, so that the fitting effect of the model obtained through training on the training set is optimal;
verifying the prediction effect of the model on the verification set;
repeating the steps until a crop growth environment model with optimized fitting degree and generalization capability of the training set is obtained.
6. The intelligent humidity control method of claim 1, wherein the step of obtaining an optimal humidity range for crop growth using a crop growth environmental model comprises:
in a crop growth environment model, fixing temperature, soil humidity and illumination parameters, and only changing humidity parameters;
predicting by the running model for multiple times to obtain predicted growth indexes under different humidity conditions;
analyzing the functional relation between the growth index and the humidity, and determining the humidity range in which the growth index reaches the maximum;
all possible combinations of temperature and illumination are traversed to determine the optimum humidity range in all directions.
7. The intelligent humidity control method for a greenhouse according to claim 1, wherein the step of acquiring the humidity of the greenhouse to be controlled to obtain the first humidity comprises the steps of:
a humidity sensor is arranged in the greenhouse to be controlled and used for monitoring the air humidity of the greenhouse in real time;
a data acquisition device is arranged and connected with the humidity sensor;
periodically reading the output of the humidity sensor and recording the acquired humidity reading;
at the beginning of the control interval, the collected humidity value is taken as the first humidity.
8. The intelligent humidity control method of claim 1, wherein the step of comparing the first humidity to the optimal humidity range comprises:
acquiring a first humidity value acquired in the step S60;
acquiring the optimal humidity range determined in the step S50;
judging the magnitude relation between the first humidity value and the optimal humidity range;
if the first humidity is lower than the minimum value of the optimal humidity range, calculating the humidity amount to be increased;
if the first humidity is higher than the maximum value of the optimal humidity range, the amount of humidity that needs to be reduced is calculated.
9. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein program instructions, which when run, are adapted to perform a greenhouse intelligent humidity adjustment method according to any one of claims 1-8.
10. A greenhouse intelligent humidity conditioning system comprising the computer readable storage medium of claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311540908.7A CN117369550A (en) | 2023-11-17 | 2023-11-17 | Intelligent humidity adjustment method, medium and system for greenhouse |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311540908.7A CN117369550A (en) | 2023-11-17 | 2023-11-17 | Intelligent humidity adjustment method, medium and system for greenhouse |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117369550A true CN117369550A (en) | 2024-01-09 |
Family
ID=89391087
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311540908.7A Pending CN117369550A (en) | 2023-11-17 | 2023-11-17 | Intelligent humidity adjustment method, medium and system for greenhouse |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117369550A (en) |
-
2023
- 2023-11-17 CN CN202311540908.7A patent/CN117369550A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3179319B1 (en) | Method for irrigation planning and system for its implementation | |
| CN107219759B (en) | Greenhouse environment control method and device | |
| CN111080173B (en) | Estimation method of carbon flux of forest system | |
| CN112418498B (en) | Temperature prediction method and system for intelligent greenhouse | |
| CN110999766A (en) | Irrigation decision method, device, computer equipment and storage medium | |
| CN113723757A (en) | Decision generation model training method, decision generation method and device | |
| CN117296538B (en) | Green plant maintenance method, device and system based on vegetation soil component detection | |
| WO2021039465A1 (en) | Disease prediction system, disease prediction method, and program | |
| KR20180029381A (en) | Appratus for controlling environment in the protected horticulture and method for using the same | |
| CN114092776A (en) | Multi-sensor data fusion method applied to intelligent agriculture | |
| CN116863410B (en) | Data acquisition and processing method and system based on pest control | |
| CN117873238A (en) | Plant growth control method and system, computer equipment and storage medium | |
| CN113642249A (en) | Gyroscope zero-bias error compensation method | |
| CN117369550A (en) | Intelligent humidity adjustment method, medium and system for greenhouse | |
| KR102387765B1 (en) | Method and apparatus for estimating crop growth quantity | |
| CN116452358B (en) | Intelligent agriculture management system based on Internet of things | |
| KR101959886B1 (en) | Server and method for determining actuator parameter of greenhouse | |
| CN111625030A (en) | Greenhouse environment control method, device, equipment, system and storage medium | |
| KR20230060815A (en) | Edge computing device for smart farm and smart farm including same | |
| CN113221452A (en) | Office space temperature prediction system based on distributed optical fiber | |
| CN116224870B (en) | Intelligent planting environment control system and method based on multi-network fusion and plant photosynthesis feedback | |
| CN117389357B (en) | Agricultural greenhouse temperature self-adaptive adjusting method and system based on Internet of things | |
| CN112365103B (en) | Method, device, equipment and medium for predicting short-term load of building in operation stage | |
| CN117333321B (en) | Agricultural irrigation water consumption estimation method, system and medium based on machine learning | |
| CN117575174B (en) | Intelligent agricultural monitoring and management system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |