CN117354988A - Greenhouse LED illumination closed-loop control method and system based on ambient light sensing - Google Patents
Greenhouse LED illumination closed-loop control method and system based on ambient light sensing Download PDFInfo
- Publication number
- CN117354988A CN117354988A CN202311449610.5A CN202311449610A CN117354988A CN 117354988 A CN117354988 A CN 117354988A CN 202311449610 A CN202311449610 A CN 202311449610A CN 117354988 A CN117354988 A CN 117354988A
- Authority
- CN
- China
- Prior art keywords
- illumination intensity
- illumination
- crop
- crops
- planting
- 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
- 238000005286 illumination Methods 0.000 title claims abstract description 478
- 238000000034 method Methods 0.000 title claims abstract description 49
- 230000005855 radiation Effects 0.000 claims abstract description 94
- 238000012549 training Methods 0.000 claims abstract description 68
- 230000006978 adaptation Effects 0.000 claims abstract description 42
- 230000008859 change Effects 0.000 claims description 28
- 238000012216 screening Methods 0.000 claims description 27
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000007405 data analysis Methods 0.000 claims description 4
- 238000007477 logistic regression Methods 0.000 claims description 4
- 238000003062 neural network model Methods 0.000 claims description 4
- 238000012706 support-vector machine Methods 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 238000003703 image analysis method Methods 0.000 claims 1
- 241000894007 species Species 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 5
- 230000001276 controlling effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 4
- 235000000832 Ayote Nutrition 0.000 description 3
- 235000009854 Cucurbita moschata Nutrition 0.000 description 3
- 240000001980 Cucurbita pepo Species 0.000 description 3
- 235000009804 Cucurbita pepo subsp pepo Nutrition 0.000 description 3
- 235000015136 pumpkin Nutrition 0.000 description 3
- 239000002699 waste material Substances 0.000 description 3
- 229910002092 carbon dioxide Inorganic materials 0.000 description 2
- 239000001569 carbon dioxide Substances 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 229930192334 Auxin Natural products 0.000 description 1
- 238000012271 agricultural production Methods 0.000 description 1
- 239000002363 auxin Substances 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 235000011089 carbon dioxide Nutrition 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- SEOVTRFCIGRIMH-UHFFFAOYSA-N indole-3-acetic acid Chemical compound C1=CC=C2C(CC(=O)O)=CNC2=C1 SEOVTRFCIGRIMH-UHFFFAOYSA-N 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000017260 vegetative to reproductive phase transition of meristem Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
- H05B—ELECTRIC HEATING; ELECTRIC LIGHT SOURCES NOT OTHERWISE PROVIDED FOR; CIRCUIT ARRANGEMENTS FOR ELECTRIC LIGHT SOURCES, IN GENERAL
- H05B45/00—Circuit arrangements for operating light-emitting diodes [LED]
- H05B45/10—Controlling the intensity of the light
- H05B45/12—Controlling the intensity of the light using optical feedback
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01G—HORTICULTURE; CULTIVATION OF VEGETABLES, FLOWERS, RICE, FRUIT, VINES, HOPS OR SEAWEED; FORESTRY; WATERING
- A01G7/00—Botany in general
- A01G7/04—Electric or magnetic or acoustic treatment of plants for promoting growth
- A01G7/045—Electric or magnetic or acoustic treatment of plants for promoting growth with electric lighting
-
- H—ELECTRICITY
- H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
- H05B—ELECTRIC HEATING; ELECTRIC LIGHT SOURCES NOT OTHERWISE PROVIDED FOR; CIRCUIT ARRANGEMENTS FOR ELECTRIC LIGHT SOURCES, IN GENERAL
- H05B47/00—Circuit arrangements for operating light sources in general, i.e. where the type of light source is not relevant
- H05B47/10—Controlling the light source
- H05B47/105—Controlling the light source in response to determined parameters
- H05B47/115—Controlling the light source in response to determined parameters by determining the presence or movement of objects or living beings
- H05B47/125—Controlling the light source in response to determined parameters by determining the presence or movement of objects or living beings by using cameras
-
- H—ELECTRICITY
- H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
- H05B—ELECTRIC HEATING; ELECTRIC LIGHT SOURCES NOT OTHERWISE PROVIDED FOR; CIRCUIT ARRANGEMENTS FOR ELECTRIC LIGHT SOURCES, IN GENERAL
- H05B47/00—Circuit arrangements for operating light sources in general, i.e. where the type of light source is not relevant
- H05B47/10—Controlling the light source
- H05B47/165—Controlling the light source following a pre-assigned programmed sequence; Logic control [LC]
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Botany (AREA)
- Ecology (AREA)
- Forests & Forestry (AREA)
- Environmental Sciences (AREA)
- Circuit Arrangement For Electric Light Sources In General (AREA)
Abstract
The invention belongs to the technical field of greenhouse illumination closed-loop control, and discloses a greenhouse LED illumination closed-loop control method and system based on ambient light sensing; dividing a greenhouse into m planting areas according to planting areas of crops, and dividing each planting area into n radiation unit areas according to radiation ranges of photosensitive sensors in the planting areas; collecting crop images of m planting areas; analyzing the crop image to obtain the current growth stage of the crop; collecting historical crop state data; training an illumination adaptation model for predicting illumination intensity based on historical crop state data; inputting crop characteristic data acquired in real time into an illumination adaptation model, and taking the predicted illumination intensity as the illumination intensity of the current stage of crops in an mth planting area; effectively improves the growth efficiency of crops, shortens the growth period and increases the yield of crops.
Description
Technical Field
The invention relates to the technical field of greenhouse illumination closed-loop control, in particular to a greenhouse LED illumination closed-loop control method and system based on ambient light sensing.
Background
With the development of society, the development of agriculture is continuously advanced, and the traditional agriculture production mode cannot adapt to the requirements of modern agriculture development; greenhouse cultivation is used as an efficient cultivation mode for protecting crops, plays an increasingly important role in current agricultural production, the growth and development of the crops are directly influenced by illumination conditions in the greenhouse, and reasonable illumination is very necessary for promoting the yield increase and the quality improvement of the crops.
At present, the illumination control of the greenhouse mainly adopts a manual experience mode, and a planter manually sets the illumination intensity in the greenhouse according to the characteristics and growth cycle of crops; the control mode depends on experience of a planter, cannot monitor illumination changes in real time and adjust the illumination changes, and cannot realize optimal illumination for crops in different growth stages; in addition, in a greenhouse with a large planting area, the requirement of crops in different areas is difficult to meet by single illumination setting; there are, of course, also partly intelligent greenhouse illumination control methods or systems, for example, the patent with application publication No. CN109375682a discloses a control system for greenhouse illumination and carbon dioxide concentration and a control method thereof; the control system comprises a control module, an LED illuminating lamp, a light equalizing plate, a timer, a ventilating fan, a dry ice releasing module, a motor driving module, a photosensitive sensor, a power module, a carbon dioxide concentration detector, a display screen, an illumination driving module and an alarm device; although the method can realize the closed-loop control of illumination, the inventor researches and practical application of the method and the prior art find that the method and the prior art have at least the following partial defects:
(1) The illumination intensity needs to be manually set by a planter in the greenhouse planting process, cannot be automatically changed according to the types and the growth stages of crops, has high requirements on the professional level of the planter, needs to consume more manpower resources for the greenhouse with multiple areas, has weak self-adaptability, and can cause energy waste if the illumination intensity is improperly set;
(2) The illumination closed-loop control is completed only by setting the illumination intensity threshold value for comparison analysis, the illumination intensity of the determined numerical control cannot be calculated, and the precision of the closed-loop control is poor.
In view of the above, the present invention proposes a greenhouse LED lighting closed-loop control method and system based on ambient light sensing to solve the above-mentioned problems.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides the following technical scheme for achieving the purposes: the greenhouse LED illumination closed-loop control method based on ambient light sensing comprises the following steps:
dividing a greenhouse into m planting areas according to planting areas of crops, dividing each planting area into n radiation unit areas according to radiation ranges of photosensitive sensors in the planting areas, wherein n and m are integers larger than 1;
collecting crop images of m planting areas;
analyzing crop images of m planting areas to obtain the current growth stage of crops;
Collecting historical crop state data, wherein the historical crop state data comprises crop characteristic data and illumination intensity corresponding to the crop characteristic data, and the crop characteristic data comprises crop types and crop growth stages;
training an illumination adaptation model for predicting illumination intensity based on historical crop state data;
inputting crop characteristic data acquired in real time into an illumination adaptation model, taking the predicted illumination intensity as target illumination intensity, and taking the target illumination intensity as illumination intensity of the current stage of crops in an mth planting area; controlling an LED illuminating lamp to adjust the illumination intensity of an mth planting area in the greenhouse to a target illumination intensity;
during crop planting, collecting real-time illumination intensities of Q radiation unit areas at the same moment, wherein Q=m×n;
comparing and analyzing the real-time illumination intensities of the Q radiation unit areas with the target illumination intensities of the Q radiation unit areas, calculating an illumination intensity error, and calculating an illumination intensity adjustment quantity through a PID control algorithm;
the LED driver controls the LED illuminating lamp according to the illumination intensity adjusting quantity, and adjusts the current real-time illumination intensity to the target illumination intensity.
Further, the analysis method of the crop image comprises the following steps:
Sequentially identifying m crop images by using a trained growth stage judging model, and outputting an identification result, wherein the identification result is a growth stage corresponding to the current crop image;
further, the training method of the growth stage judgment model comprises the following steps:
collecting images of different types of crops in different growth stages, marking the images as training images, marking each training image in the growth stage, and converting the growth stage into digital marking; dividing the marked training image into a training set and a testing set, training the growth stage judging model by using the training set, testing the growth stage judging model by using the testing set, and outputting the growth stage judging model meeting the preset accuracy, wherein the calculation formula of the prediction accuracy is z c ＝(α c -μ c ) 2 Wherein z is c For prediction accuracy, c is the number of the training image, α c For the prediction label corresponding to the training image of the c group, mu c The actual labels corresponding to the training images of the c group; the growth stepThe segment judgment model is one of a logistic regression model, a naive Bayesian model or a support vector machine model.
Further, the specific training mode of the illumination adaptation model comprises the following steps:
the method comprises the steps that crop characteristic data are used as input of an illumination adaptation model, the illumination adaptation model takes predicted illumination intensity of each group of crop characteristic data as output, actual illumination intensity corresponding to the group of crop characteristic data as a prediction target, and the sum of prediction errors of all crop characteristic data is minimized as a training target; training the illumination adaptation model until the sum of the prediction errors reaches convergence, and stopping training; the illumination adaptation model is any one of a deep neural network model or a deep belief network model.
Further, the target illumination intensities of the n radiation units correspond to the target illumination intensity of one planting area, and the target illumination intensities of the m planting areas are the target illumination intensities of the Q radiation unit areas; the illumination intensity error is the difference value of the target illumination intensity minus the real-time illumination intensity;
further, the illumination intensity adjustment amount is calculated as follows:
in GZ (t) i For adjusting the illumination intensity, WC (t) i For illumination intensity error, BZ is proportional gain, JZ is integral gain, WZ is differential gain, i is the ith radiation unit area, i e Q, t is acquisition frequency.
Further, if the illumination intensity errors exist in two adjacent radiation unit areas at the same moment, and the difference value of the illumination intensity error absolute values is larger than a difference value threshold value, comparing the illumination intensity error absolute values of the two radiation unit areas, marking the radiation unit area with the large illumination intensity error absolute value as a large error area, marking the radiation unit area with the small illumination intensity error absolute value as a small error area, calculating the illumination intensity change amount of the small error area when the illumination intensity of the large error area is regulated, and calculating the new illumination intensity regulation amount of the small error area;
The amount of change in the illumination intensity was calculated as follows:
GB in i SS as the amount of change in illumination intensity i Real-time illumination intensity for small error region, SS j For large error area real-time illumination intensity, MB j For the target illumination intensity of the large error area, MJ is the radiation range of the photosensitive sensor, lambda 1 、λ 2 For a predetermined scaling factor, j+.i and j ε Q.
Further, the calculation of the new light intensity adjustment amount for the small error region is as follows:
if the illumination intensity errors of the large error area and the small error area are both larger than 0 or smaller than 0, adding the illumination intensity adjustment quantity of the small error area and the illumination intensity change quantity to be used as a new illumination intensity adjustment quantity of the small error area;
if the illumination intensity error of the large error area is larger than 0 and the illumination intensity error of the small error area is smaller than 0, or if the illumination intensity error of the large error area is smaller than 0 and the illumination intensity error of the small error area is larger than 0, subtracting the illumination intensity change amount from the illumination intensity adjustment amount of the small error area to obtain a new illumination intensity adjustment amount of the small error area.
Further, screening U crops to be planted, and selecting m crops with the closest target illumination intensity in each growth stage, wherein U is an integer greater than 1 and is more than m; the screening steps of m crops comprise:
S1: before crop planting, inputting crop characteristic data of U crops into an illumination adaptation model to obtain target illumination intensity of each growth stage of the U crops;
s2: selecting one of the crops and marking the crop as a target crop;
s3: sequentially subtracting the target illumination intensities of all growth stages of the target crops from the target illumination intensities of all growth stages of the U-1 crops to obtain difference values, sequentially comparing the difference values with screening threshold range values corresponding to all growth stages of the target crops, and marking the crops as the crops capable of being planted if a plurality of difference values of one crop are within the screening threshold range values; if at least one difference value in a plurality of difference values of one crop is outside a screening threshold value range, marking the crop as non-plantable crop;
s4: counting the number of the types of the crops which can be planted, and if the number of the types of the crops which can be planted is smaller than m, replacing target crops and repeating the steps S2-S4; if the number of the crop species capable of being planted is equal to m crops, planting the m crops; if the number of the crop species is larger than m crops, accumulating the difference values of the crop species, sorting the accumulated values from small to large, and selecting m crops according to the positive sequence.
The greenhouse LED illumination closed-loop control system based on the ambient light sensing implements the greenhouse LED illumination closed-loop control method based on the ambient light sensing, and comprises the following steps:
the region dividing module divides the greenhouse into m planting regions according to the planting regions of crops, and divides each planting region into n radiation unit regions according to the radiation range of the photosensitive sensor in the planting region, wherein n and m are integers larger than 1;
the first data acquisition module acquires crop images of m planting areas;
the data analysis module is used for analyzing crop images of m planting areas to acquire the current growth stage of crops;
the second data acquisition module acquires historical crop state data, wherein the historical crop state data comprises crop characteristic data and illumination intensity corresponding to the crop characteristic data, and the crop characteristic data comprises crop types and crop growth stages;
the model training module is used for training an illumination adaptation model for predicting illumination intensity based on historical crop state data;
the illumination intensity adaptation module inputs the crop characteristic data acquired in real time into an illumination adaptation model, the predicted illumination intensity is used as target illumination intensity, and the target illumination intensity is used as illumination intensity of the current stage of crops in the mth planting area; controlling an LED illuminating lamp to adjust the illumination intensity of an mth planting area in the greenhouse to a target illumination intensity;
The third data acquisition module acquires the real-time illumination intensity of Q radiation unit areas at the same moment during crop planting, wherein Q=m×n;
the feedback control module is used for comparing and analyzing the real-time illumination intensities of the Q radiation unit areas with the target illumination intensities of the Q radiation unit areas, calculating an illumination intensity error and calculating an illumination intensity adjustment quantity through a PID control algorithm;
and the adjusting module is used for controlling the LED illuminating lamp according to the illumination intensity adjusting quantity and adjusting the current real-time illumination intensity to the target illumination intensity.
The greenhouse LED illumination closed-loop control method and system based on ambient light sensing have the technical effects and advantages that:
1. determining the current crop growth stage by analyzing the crop image; the illumination intensity suitable for the growth stage of crops is obtained by using a machine learning model, the illumination intensity can be adaptively adjusted to ensure that the crops grow under the suitable illumination intensity, and the illumination energy consumption is saved; the illumination intensity in the greenhouse is monitored and fed back in real time in the growth process of crops, and the area with illumination intensity errors is adjusted in real time through a PID control algorithm, so that closed-loop control of greenhouse LED illumination is realized, energy-saving illumination is realized, and energy waste caused by too strong illumination intensity is avoided; effectively improves the growth efficiency of crops, shortens the growth period and increases the yield of crops.
2. By calculating the change amount of the illumination intensity, the problem that the illumination intensity of the area with smaller illumination intensity errors still has larger illumination intensity errors after the real-time illumination intensity is adjusted because the illumination intensity of the area with smaller illumination intensity errors can be influenced when the area with larger illumination intensity errors adjusts the real-time illumination intensity is avoided; the influence on the illumination intensity in the area with smaller illumination intensity error is reduced.
3. The crop variety is screened before crops are planted, the condition that the illumination intensity of adjacent radiation unit areas is mutually influenced and cannot be adjusted to the target illumination intensity is avoided, and the crops are ensured to grow under the proper illumination intensity in each growth stage.
Drawings
FIG. 1 is a schematic diagram of a closed loop control system for greenhouse LED illumination based on ambient light sensing according to embodiment 1 of the present invention;
FIG. 2 is a schematic view of the division of greenhouse areas according to example 1 of the present invention;
FIG. 3 is a schematic diagram of a closed loop control system for greenhouse LED illumination based on ambient light sensing according to embodiment 2 of the present invention;
FIG. 4 is a schematic view of two adjacent irradiation unit areas according to embodiment 2 of the present invention;
FIG. 5 is a schematic diagram of a closed loop control system for greenhouse LED illumination based on ambient light sensing according to embodiment 3 of the present invention;
FIG. 6 is a schematic diagram of a closed loop control method of greenhouse LED illumination based on ambient light sensing according to embodiment 4 of the present invention;
fig. 7 is a schematic diagram of an electronic device according to embodiment 5 of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
Referring to fig. 1, the greenhouse LED lighting closed-loop control system based on ambient light sensing according to the present embodiment includes a region dividing module, a first data acquisition module, a data analysis module, a second data acquisition module, a model training module, an illumination intensity adaptation module, a third data acquisition module, a feedback control module and an adjustment module, where each module is connected by a wired and/or wireless manner, so as to realize data transmission between the modules;
the region dividing module divides the greenhouse into m planting regions according to the planting regions of crops, and divides each planting region into n radiation unit regions according to the radiation range of the photosensitive sensor in the planting region, wherein n and m are integers larger than 1, as shown in fig. 2; a photosensitive sensor and an LED illuminating lamp are arranged in each radiation unit area; the radiation range of the photosensitive sensor is determined according to the product specification of the photosensitive sensor; the planting area of the crops is an area corresponding to each crop planted in the greenhouse;
The reason for the regional division according to the planting areas of crops is that various crops can be planted in a greenhouse, and the illumination intensities required in the growth process of different types of crops are different, so that different photosensitive sensors are required to be used for collecting the illumination intensities in the growth process of different types of crops for real-time feedback;
the reason why the area division is performed according to the radiation range of the photosensitive sensors is that if one planting area is large, one photosensitive sensor is arranged and cannot acquire the illumination intensity of the whole area, so that a plurality of photosensitive sensors are required to be arranged according to the radiation range of the photosensitive sensors, and the illumination intensity can be ensured to be detected at any position in each planting area;
the first data acquisition module acquires crop images of m planting areas, and the crop images are acquired by CCD image sensors arranged in the m planting areas;
the data analysis module is used for analyzing crop images of m planting areas to acquire the current crop growth stage;
the analysis method of the crop image comprises the following steps:
sequentially identifying m crop images by using a trained growth stage judging model, and outputting an identification result, wherein the identification result is a growth stage corresponding to the current crop image;
The training method of the growth stage judgment model comprises the following steps:
collecting images of different types of crops in different growth stages, marking the images as training images, marking each training image with the growth stage, and converting the growth stage into digital marking, which is exemplary: the pumpkin sprouting stage is converted into 1, the pumpkin flowering stage is converted into 2, and the pumpkin fruiting stage is converted into 3; dividing the marked training image into a training set and a testing set, training the growth stage judging model by using the training set, testing the growth stage judging model by using the testing set, and outputting the growth stage judging model meeting the preset accuracy, wherein the calculation formula of the prediction accuracy is z c ＝(α c -μ c ) 2 Wherein z is c For prediction accuracy, c is the number of the training image, α c For the prediction label corresponding to the training image of the c group, mu c The actual labels corresponding to the training images of the c group; the growth stage judging model is specifically one of a logistic regression model, a naive Bayesian model or a support vector machine model;
the second data acquisition module acquires Y groups of historical crop state data, wherein Y is an integer greater than 1; the historical crop state data comprises crop characteristic data and illumination intensity corresponding to the crop characteristic data, and the crop characteristic data comprises crop types and crop growth stages; the crop types are set by a manual input control system of a planter, different crop types are different from illumination intensities required in a crop growth stage, the illumination intensities are acquired through a photosensitive sensor, the illumination intensities are key factors for crop growth, and the proper illumination intensities can improve the crop growth efficiency, shorten the growth period and increase the yield;
The model training module is used for training an illumination adaptation model for predicting illumination intensity based on historical crop state data;
the specific training mode of the illumination adaptation model comprises the following steps:
under an experimental environment, crops with different crop characteristic data are cultivated according to preset various illumination intensities in sequence, the growth condition of the crops is recorded in sequence, and the illumination intensity of the crops capable of growing in an auxin manner is used as the illumination intensity corresponding to the crop characteristic data;
the method comprises the steps that crop characteristic data are used as input of an illumination adaptation model, the illumination adaptation model takes predicted illumination intensity of each group of crop characteristic data as output, actual illumination intensity corresponding to the group of crop characteristic data as a prediction target, and the sum of prediction errors of all crop characteristic data is minimized as a training target; wherein, the calculation formula of the prediction error is z k ＝(α k -μ k ) 2 Wherein z is k For prediction error, k is the number of crop characteristic data, α k Predicted illumination intensity, μ for the k-th set of crop signature data k The actual illumination intensity corresponding to the k group of crop characteristic data; training the illumination adaptation model until the sum of the prediction errors reaches convergence, and stopping training;
The illumination adaptation model is any one of a deep neural network model or a deep belief network model;
the illumination intensity adaptation module inputs the crop characteristic data acquired in real time into an illumination adaptation model, the predicted illumination intensity is used as target illumination intensity, and the target illumination intensity is used as illumination intensity of the current stage of crops in the mth planting area; controlling an LED illuminating lamp to adjust the illumination intensity of an mth planting area in the greenhouse to a target illumination intensity for crop planting; namely, the illumination intensity of m planting areas in the greenhouse is controlled within a range suitable for the growth of crops in the present stage;
the third data acquisition module acquires the real-time illumination intensity of Q radiation unit areas at the same moment during crop planting, wherein Q=m×n; the acquisition frequency is t seconds;
the feedback control module is used for comparing and analyzing the real-time illumination intensities of the Q radiation unit areas with the target illumination intensities of the Q radiation unit areas, calculating an illumination intensity error and calculating an illumination intensity adjustment quantity through a PID control algorithm;
the n radiation unit area areas are obtained by dividing one planting area again according to the radiation range of the photosensitive sensor, so that the target illumination intensities of the n radiation units correspond to the target illumination intensity of one planting area, and the target illumination intensities of the m planting areas are the target illumination intensities of the Q radiation unit areas; the illumination intensity error is the difference value of the target illumination intensity minus the real-time illumination intensity;
The amount of illumination intensity adjustment was calculated as follows:
in GZ (t) i For adjusting the illumination intensity, WC (t) i BZ is proportional gain, JZ is integral gain, WZ is differential gain, i is the ith area, i is E Q;
wherein the preset gain coefficient is obtained by a person skilled in the art, the preset gain coefficient is the proportional gain, integral gain and differential gain in the formula, the corresponding gain coefficient is set for each group of the comprehensive parameters, the preset gain coefficient and the obtained comprehensive parameters are substituted into the formula, any three formulas form a ternary one-time equation set, the calculated gain coefficient is screened and averaged, and the values of BZ, JZ and WZ are obtained;
the LED driver controls the LED illuminating lamp according to the illumination intensity adjusting quantity, and adjusts the current real-time illumination intensity to the target illumination intensity;
in the embodiment, the current crop growth stage is determined by analyzing the crop image; the illumination intensity suitable for the growth stage of the crops is obtained by using a machine learning model, the illumination intensity can be adaptively adjusted to ensure that the crops grow under the suitable illumination intensity, and the illumination energy consumption is saved; the illumination intensity in the greenhouse is monitored and fed back in real time in the growth process of crops, and the area with illumination intensity errors is adjusted in real time through a PID control algorithm, so that closed-loop control of greenhouse LED illumination is realized, energy-saving illumination is realized, and energy waste caused by too strong illumination intensity is avoided; effectively improves the growth efficiency of crops, shortens the growth period and increases the yield of crops.
Example 2
Referring to fig. 3, in this embodiment, in the closed loop control process of LED illumination, if two adjacent radiation unit areas have illumination intensity errors at the same time, and the illumination intensity errors differ greatly, when adjusting the real-time illumination intensity of the radiation unit area with the larger illumination intensity error, the illumination intensity of the radiation unit area with the smaller illumination intensity error will be affected, so that the radiation unit area with the smaller illumination intensity error still has a larger illumination intensity error after adjusting the real-time illumination intensity; therefore, the embodiment provides a greenhouse LED illumination closed-loop control system based on ambient light sensing, which further comprises a control calculation module, wherein the control calculation module is used for calculating the illumination intensity influence degree of the radiation unit area with smaller illumination intensity error when the illumination intensity of the radiation unit area with larger illumination intensity error is adjusted, so that the influence on the illumination intensity of the radiation unit area with smaller illumination intensity error is reduced;
the control calculation module is used for comparing the absolute values of the illumination intensity errors of the two adjacent radiation unit areas when the illumination intensity errors exist in the two adjacent radiation unit areas at the same moment and the difference value of the absolute values of the illumination intensity errors is larger than a difference value threshold, marking the radiation unit area with the larger absolute value of the illumination intensity errors as a large error area, marking the radiation unit area with the smaller absolute value of the illumination intensity errors as a small error area, calculating new illumination intensity adjustment quantity of the small error area for the illumination intensity change quantity of the small error area when the illumination intensity adjustment is carried out on the large error area, and referring to the figure 4;
The difference threshold is the illumination intensity of one of the two adjacent radiation unit areas under the experimental environment, and when the illumination intensity of the other radiation unit area is changed, the illumination intensity adjustment quantity of the radiation unit area for adjusting the illumination intensity is collected at the moment; setting a radiation unit area for adjusting the illumination intensity as a plurality of different illumination intensities according to the method, collecting a plurality of illumination intensity adjustment amounts, and taking an average value of the illumination intensity adjustment amounts as a difference threshold value;
the amount of change in the illumination intensity was calculated as follows:
GB in i SS as the amount of change in illumination intensity i Real-time illumination intensity for small error region, SS j For large error area real-time illumination intensity, MB j For the target illumination intensity of the large error area, MJ is the radiation range of the photosensitive sensor, lambda 1 、λ 2 J is equal to i and j is equal to Q for a preset proportionality coefficient;
wherein the preset proportionality coefficient is obtained by the person skilled in the art, a plurality of groups of comprehensive parameters are collected, the corresponding proportionality coefficient is set for each group of comprehensive parameters, the preset proportionality coefficient and the collected comprehensive parameters are substituted into a formula, any two formulas form a binary once equation set, the calculated proportionality coefficient is screened and averaged to obtain lambda 1 、λ 2 Is a value of (2);
the absolute value of the difference value between the real-time illumination intensity of the small-error area and the real-time illumination intensity of the large-error area can influence the illumination intensity change amount, and the larger the absolute value of the difference value is, the larger the difference between the real-time illumination intensities of the two areas is, and the influence degree of the small-error area is larger at the moment, and the illumination intensity change amount is larger; the illumination intensity adjustment quantity of the large error area is the difference value of the target illumination intensity of the large error area minus the real-time illumination intensity of the large error area, and the larger the illumination intensity adjustment quantity of the large error area is, the larger the influence degree of the small error area is, and the larger the illumination intensity change quantity is; the radiation range of the photosensitive sensor determines the areas of n areas, the larger the area is, the farther the LED illuminating lamp of the large-error area is from the small-error area, the smaller the influence degree of the small-error area is, and the smaller the illumination intensity change amount is;
the calculation of the new light intensity adjustment amount for the small error region is as follows:
if the illumination intensity errors of the large error area and the small error area are both larger than 0 or smaller than 0, adding the illumination intensity adjustment quantity of the small error area and the illumination intensity change quantity to be used as a new illumination intensity adjustment quantity of the small error area;
If the illumination intensity error of the large error area is larger than 0 and the illumination intensity error of the small error area is smaller than 0, or if the illumination intensity error of the large error area is smaller than 0 and the illumination intensity error of the small error area is larger than 0, subtracting the illumination intensity change amount of the small error area from the illumination intensity change amount of the small error area to obtain a new illumination intensity adjustment amount of the small error area;
when the condition that two adjacent areas have illumination intensity errors at the same time occurs, the illumination intensity of the large error area needs to be adjusted, the illumination intensity change amount of the small error area and the new illumination intensity adjustment amount of the small error area are calculated, and then the illumination intensity of the small error area is adjusted; because the illumination intensity of the small error area is adjusted, the illumination intensity adjustment amount of the illumination intensity is smaller, and the influence degree of the large error area is smaller, if the illumination intensity of the small error area is adjusted first, after the illumination intensity of the large error area is adjusted, the illumination intensity of the small error area is changed due to the influence, and larger illumination intensity error can be generated, so that the illumination intensity of the large error area needs to be adjusted first;
According to the embodiment, the change amount of the illumination intensity is calculated, so that the problem that the illumination intensity of the area with smaller illumination intensity errors still has larger illumination intensity errors after the real-time illumination intensity is adjusted due to the fact that the illumination intensity of the area with smaller illumination intensity errors is influenced when the real-time illumination intensity is adjusted by the area with larger illumination intensity errors is avoided; the influence on the illumination intensity in the area with smaller illumination intensity error is reduced.
Example 3
Referring to fig. 5, in this embodiment, the design is further improved based on embodiment 2, if the difference between the target illumination intensities of two adjacent planting areas is too large, the illumination intensities of the adjacent radiation unit areas in the two planting areas are all affected, the extent of the influence of the radiation unit area with small target illumination intensity on the radiation unit area with large target illumination intensity is far greater than the extent of the influence of the radiation unit area with large target illumination intensity on the radiation unit area with small target illumination intensity, at this time, the situation described in embodiment 2 exists, that is, the illumination intensity errors exist in both adjacent radiation unit areas at the same time, and the illumination intensity errors differ greatly; the new illumination intensity adjustment quantity of the small-error area is calculated to be too large, if the real-time illumination intensity of the small-error area is adjusted, the real-time illumination intensity of the large-error area is influenced, and the real-time illumination intensities of the two radiation unit areas cannot be adjusted to the target illumination intensity; therefore, the embodiment provides a greenhouse LED illumination closed-loop control system based on ambient light sensing, which further comprises a screening module, wherein the screening module is used for screening crops which are suitable for being planted together in the same batch, so that the condition that the illumination intensities of adjacent radiation unit areas are mutually influenced and cannot be regulated to target illumination intensity is avoided;
The screening module is used for screening U crops to be planted, selecting m crops with the closest target illumination intensity in each growth stage, wherein U is an integer greater than 1 and is more than m; ensuring that the target illumination intensities of the m crops in each growth stage are not mutually influenced;
the screening steps of m crops comprise:
s1: before crop planting, inputting crop characteristic data of U crops into an illumination adaptation model to obtain target illumination intensity of each growth stage of the U crops;
s2: selecting one of the crops and marking the crop as a target crop;
s3: sequentially subtracting the target illumination intensities of all growth stages of the target crops from the target illumination intensities of all growth stages of the U-1 crops to obtain difference values, sequentially comparing the difference values with screening threshold range values corresponding to all growth stages of the target crops, and marking the crops as the crops capable of being planted if a plurality of difference values of one crop are within the screening threshold range values; if at least one difference value in a plurality of difference values of one crop is outside a screening threshold value range, marking the crop as non-plantable crop;
s4: counting the number of the types of the crops which can be planted, and if the number of the types of the crops which can be planted is smaller than m, replacing target crops and repeating the steps S2-S4; if the number of the crop species capable of being planted is equal to m crops, planting the m crops; if the number of the types of the crops capable of being planted is greater than m crops, accumulating a plurality of differences of the crops capable of being planted, sequencing the accumulated values from small to large, and selecting m crops according to a positive sequence;
The screening threshold value range value is obtained by adjusting the illumination intensity of one of two adjacent radiation unit areas under an experimental environment by a planter, marking the radiation unit area as a first area, and collecting the illumination intensity adjustment quantity of the first area when the illumination intensity of the other radiation unit area is changed, wherein the range between the positive value and the negative value of the illumination intensity adjustment quantity is used as the screening threshold value range value; setting the initial illumination intensity of the first area to a plurality of different illumination intensities according to the method, and collecting a plurality of illumination intensity adjustment amounts, wherein the illumination intensity adjustment amounts are in one-to-one correspondence with the initial illumination intensity of the first area, namely the screening threshold range values are in one-to-one correspondence with the initial illumination intensity of the first area, so that the screening threshold range values are in one-to-one correspondence with the target illumination intensities of the target crops in each growth stage;
according to the embodiment, the crop types are screened before the crops are planted, the condition that the illumination intensities of the adjacent radiation unit areas are mutually influenced and cannot be adjusted to the target illumination intensity is avoided, and the crops are ensured to grow under the proper illumination intensity at each growth stage.
Example 4
Referring to fig. 6, this embodiment, which is not described in detail in embodiments 1, 2 and 3, provides a greenhouse LED lighting closed-loop control method based on ambient light sensing, comprising:
dividing a greenhouse into m planting areas according to planting areas of crops, dividing each planting area into n radiation unit areas according to radiation ranges of photosensitive sensors in the planting areas, wherein n and m are integers larger than 1;
collecting crop images of m planting areas;
analyzing crop images of m planting areas to obtain the current growth stage of crops;
collecting historical crop state data, wherein the historical crop state data comprises crop characteristic data and illumination intensity corresponding to the crop characteristic data, and the crop characteristic data comprises crop types and crop growth stages;
training an illumination adaptation model for predicting illumination intensity based on historical crop state data;
inputting crop characteristic data acquired in real time into an illumination adaptation model, taking the predicted illumination intensity as target illumination intensity, and taking the target illumination intensity as illumination intensity of the current stage of crops in an mth planting area; controlling an LED illuminating lamp to adjust the illumination intensity of an mth planting area in the greenhouse to a target illumination intensity;
During crop planting, collecting real-time illumination intensities of Q radiation unit areas at the same moment, wherein Q=m×n;
comparing and analyzing the real-time illumination intensities of the Q radiation unit areas with the target illumination intensities of the Q radiation unit areas, calculating an illumination intensity error, and calculating an illumination intensity adjustment quantity through a PID control algorithm;
the LED driver controls the LED illuminating lamp according to the illumination intensity adjusting quantity, and adjusts the current real-time illumination intensity to the target illumination intensity.
Further, the analysis method of the crop image comprises the following steps:
sequentially identifying m crop images by using a trained growth stage judging model, and outputting an identification result, wherein the identification result is a growth stage corresponding to the current crop image;
further, the training method of the growth stage judgment model comprises the following steps:
collecting images of different types of crops in different growth stages, marking the images as training images, marking each training image in the growth stage, and converting the growth stage into digital marking; dividing the marked training image into a training set and a testing set, training the growth stage judging model by using the training set, and training the growth stage judging model by using the testing setTesting the growth stage judgment model, and outputting the growth stage judgment model meeting the preset accuracy, wherein the calculation formula of the prediction accuracy is z c ＝(α c -μ c ) 2 Wherein z is c For prediction accuracy, c is the number of the training image, α c For the prediction label corresponding to the training image of the c group, mu c The actual labels corresponding to the training images of the c group; the growth stage judging model is one of a logistic regression model, a naive Bayesian model and a support vector machine model.
Further, the specific training mode of the illumination adaptation model comprises the following steps:
the method comprises the steps that crop characteristic data are used as input of an illumination adaptation model, the illumination adaptation model takes predicted illumination intensity of each group of crop characteristic data as output, actual illumination intensity corresponding to the group of crop characteristic data as a prediction target, and the sum of prediction errors of all crop characteristic data is minimized as a training target; training the illumination adaptation model until the sum of the prediction errors reaches convergence, and stopping training; the illumination adaptation model is any one of a deep neural network model or a deep belief network model.
Further, the target illumination intensities of the n radiation units correspond to the target illumination intensity of one planting area, and the target illumination intensities of the m planting areas are the target illumination intensities of the Q radiation unit areas; the illumination intensity error is the difference value of the target illumination intensity minus the real-time illumination intensity;
Further, the illumination intensity adjustment amount is calculated as follows:
wherein GZ (t) i is the illumination intensity adjustment quantity, WC (t) i is the illumination intensity error, BZ is the proportional gain, JZ is the integral gain, WZ is the differential gain, i is the ith radiation unit area, i epsilon Q, and t is the acquisition frequency.
Further, if illumination intensity errors exist in two adjacent radiation unit areas at the same moment, and the difference value of the illumination intensity error absolute values is larger than a difference value threshold value, comparing the illumination intensity error absolute values of the two radiation unit areas, marking the radiation unit area with the large illumination intensity error absolute value as a large error area, marking the radiation unit area with the small illumination intensity error absolute value as a small error area, and calculating a new illumination intensity adjustment quantity of the small error area for the illumination intensity change quantity of the small error area when the illumination intensity adjustment is carried out in the large error area;
the amount of change in the illumination intensity was calculated as follows:
GB in i SS as the amount of change in illumination intensity i Real-time illumination intensity for small error region, SS j For large error area real-time illumination intensity, MB j For the target illumination intensity of the large error area, MJ is the radiation range of the photosensitive sensor, lambda 1 、λ 2 For a predetermined scaling factor, j+.i and j ε Q.
Further, the calculation of the new light intensity adjustment amount for the small error region is as follows:
if the illumination intensity errors of the large error area and the small error area are both larger than 0 or smaller than 0, adding the illumination intensity adjustment quantity of the small error area and the illumination intensity change quantity to be used as a new illumination intensity adjustment quantity of the small error area;
if the illumination intensity error of the large error area is larger than 0 and the illumination intensity error of the small error area is smaller than 0, or if the illumination intensity error of the large error area is smaller than 0 and the illumination intensity error of the small error area is larger than 0, subtracting the illumination intensity change amount from the illumination intensity adjustment amount of the small error area to obtain a new illumination intensity adjustment amount of the small error area.
Further, screening U crops to be planted, and selecting m crops with the closest target illumination intensity in each growth stage, wherein U is an integer greater than 1 and is more than m; the screening steps of m crops comprise:
s1: before crop planting, inputting crop characteristic data of U crops into an illumination adaptation model to obtain target illumination intensity of each growth stage of the U crops;
S2: selecting one of the crops and marking the crop as a target crop;
s3: sequentially subtracting the target illumination intensities of all growth stages of the target crops from the target illumination intensities of all growth stages of the U-1 crops to obtain difference values, sequentially comparing the difference values with screening threshold range values corresponding to all growth stages of the target crops, and marking the crops as the crops capable of being planted if a plurality of difference values of one crop are within the screening threshold range values; if at least one difference value in a plurality of difference values of one crop is outside a screening threshold value range, marking the crop as non-plantable crop;
s4: counting the number of the types of the crops which can be planted, and if the number of the types of the crops which can be planted is smaller than m, replacing target crops and repeating the steps S2-S4; if the number of the crop species capable of being planted is equal to m crops, planting the m crops; if the number of the crop species is larger than m crops, accumulating the difference values of the crop species, sorting the accumulated values from small to large, and selecting m crops according to the positive sequence.
Example 5
Referring to fig. 7, the disclosure provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor implements any one of the methods for closed loop control of greenhouse LED lighting based on ambient light sensing provided by the above methods when executing the computer program.
Since the electronic device described in this embodiment is an electronic device used to implement the greenhouse LED lighting closed-loop control method based on ambient light sensing in this embodiment, based on the greenhouse LED lighting closed-loop control method based on ambient light sensing described in this embodiment, those skilled in the art can understand the specific implementation of the electronic device and various modifications thereof, so how to implement the method in this embodiment of the present application for this electronic device will not be described in detail herein. As long as the person skilled in the art implements the electronic device adopted by the greenhouse LED illumination closed-loop control method based on ambient light sensing in the embodiment of the application, the electronic device belongs to the scope of protection intended by the application.
Example 6
The embodiment discloses a computer readable storage medium, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the greenhouse LED illumination closed-loop control method based on the ambient light sensing provided by any one of the methods when executing the computer program.
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 present invention shall be subject to the protection scope of the claims.
Finally: the foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (10)
1. The greenhouse LED illumination closed-loop control method based on ambient light sensing is characterized by comprising the following steps of:
dividing a greenhouse into m planting areas according to planting areas of crops, dividing each planting area into n radiation unit areas according to radiation ranges of photosensitive sensors in the planting areas, wherein n and m are integers larger than 1;
collecting crop images of m planting areas;
analyzing crop images of m planting areas to obtain the current growth stage of crops;
collecting historical crop state data, wherein the historical crop state data comprises crop characteristic data and illumination intensity corresponding to the crop characteristic data, and the crop characteristic data comprises crop types and crop growth stages;
training an illumination adaptation model for predicting illumination intensity based on historical crop state data;
inputting crop characteristic data acquired in real time into an illumination adaptation model, taking the predicted illumination intensity as target illumination intensity, and taking the target illumination intensity as illumination intensity of the current stage of crops in an mth planting area; controlling an LED illuminating lamp to adjust the illumination intensity of an mth planting area in the greenhouse to a target illumination intensity;
During crop planting, collecting real-time illumination intensities of Q radiation unit areas at the same moment, wherein Q=m×n;
comparing and analyzing the real-time illumination intensities of the Q radiation unit areas with the target illumination intensities of the Q radiation unit areas, calculating an illumination intensity error, and calculating an illumination intensity adjustment quantity through a PID control algorithm;
the LED driver controls the LED illuminating lamp according to the illumination intensity adjusting quantity, and adjusts the current real-time illumination intensity to the target illumination intensity.
2. The greenhouse LED lighting closed-loop control method based on ambient light sensing according to claim 1, wherein the crop image analysis method comprises:
and sequentially identifying m crop images by using the trained growth stage judging model, and outputting an identification result, wherein the identification result is the growth stage corresponding to the current crop image.
3. The greenhouse LED lighting closed-loop control method based on ambient light sensing according to claim 2, wherein the training method of the growth stage judgment model comprises:
collecting images of different types of crops in different growth stages, marking the images as training images, marking each training image with the growth stage, and converting the growth stage into a plurality of images Marking words; dividing the marked training image into a training set and a testing set, training the growth stage judging model by using the training set, testing the growth stage judging model by using the testing set, and outputting the growth stage judging model meeting the preset accuracy, wherein the calculation formula of the prediction accuracy is z c ＝(α c -μ c ) 2 Wherein z is c For prediction accuracy, c is the number of the training image, α c For the prediction label corresponding to the training image of the c group, mu c The actual labels corresponding to the training images of the c group; the growth stage judging model is one of a logistic regression model, a naive Bayesian model and a support vector machine model.
4. The greenhouse LED illumination closed-loop control method based on ambient light sensing according to claim 3, wherein the specific training mode of the illumination adaptation model comprises the following steps:
the method comprises the steps that crop characteristic data are used as input of an illumination adaptation model, the illumination adaptation model takes predicted illumination intensity of each group of crop characteristic data as output, actual illumination intensity corresponding to the group of crop characteristic data as a prediction target, and the sum of prediction errors of all crop characteristic data is minimized as a training target; training the illumination adaptation model until the sum of the prediction errors reaches convergence, and stopping training; the illumination adaptation model is any one of a deep neural network model or a deep belief network model.
5. The greenhouse LED lighting closed-loop control method based on ambient light sensing according to claim 4, wherein,
the target illumination intensities of the n radiation units correspond to the target illumination intensity of one planting area, and the target illumination intensities of the m planting areas are the target illumination intensities of the Q radiation unit areas; the illumination intensity error is the difference of the target illumination intensity minus the real-time illumination intensity.
6. The greenhouse LED lighting closed-loop control method based on ambient light sensing according to claim 5, wherein the illumination intensity adjustment amount is calculated as follows:
wherein GZ (t) i is the illumination intensity adjustment quantity, WC (t) i is the illumination intensity error, BZ is the proportional gain, JZ is the integral gain, WZ is the differential gain, i is the ith radiation unit area, i epsilon Q, and t is the acquisition frequency.
7. The greenhouse LED illumination closed-loop control method based on ambient light sensing according to claim 6, wherein if illumination intensity errors exist in two adjacent radiation unit areas at the same time, and the difference value of the illumination intensity error absolute values is larger than a difference threshold value, comparing the illumination intensity error absolute values of the two radiation unit areas, marking the radiation unit area with the large illumination intensity error absolute value as a large error area, marking the radiation unit area with the small illumination intensity error absolute value as a small error area, and calculating a new illumination intensity adjustment quantity of the small error area for the illumination intensity change quantity of the small error area when the illumination intensity adjustment is carried out in the large error area;
The amount of illumination intensity change is calculated as follows:
GB in i SS as the amount of change in illumination intensity i Real-time illumination intensity for small error region, SS j For large error area real-time illumination intensity, MB j For the target illumination intensity of the large error area, MJ is the radiation range of the photosensitive sensor, lambda 1 、λ 2 For a predetermined scaling factor, j+.i and j ε Q.
8. The greenhouse LED illumination closed-loop control method based on ambient light sensing according to claim 7, wherein the calculation of the new illumination intensity adjustment amount in the small error area is as follows:
if the illumination intensity errors of the large error area and the small error area are both larger than 0 or smaller than 0, adding the illumination intensity adjustment quantity of the small error area and the illumination intensity change quantity to be used as a new illumination intensity adjustment quantity of the small error area;
if the illumination intensity error of the large error area is larger than 0 and the illumination intensity error of the small error area is smaller than 0, or if the illumination intensity error of the large error area is smaller than 0 and the illumination intensity error of the small error area is larger than 0, subtracting the illumination intensity change amount from the illumination intensity adjustment amount of the small error area to obtain a new illumination intensity adjustment amount of the small error area.
9. The greenhouse LED illumination closed-loop control method based on ambient light sensing according to claim 8, wherein U crops to be planted are screened, m crops with the closest target illumination intensity in each growth stage are selected, U is an integer greater than 1 and U is greater than m; the screening steps of m crops comprise:
S1: before crop planting, inputting crop characteristic data of U crops into an illumination adaptation model to obtain target illumination intensity of each growth stage of the U crops;
s2: selecting one of the crops and marking the crop as a target crop;
s3: sequentially subtracting the target illumination intensities of all growth stages of the target crops from the target illumination intensities of all growth stages of the U-1 crops to obtain difference values, sequentially comparing the difference values with screening threshold range values corresponding to all growth stages of the target crops, and marking the crops as the crops capable of being planted if a plurality of difference values of one crop are within the screening threshold range values; if at least one difference value in a plurality of difference values of one crop is outside a screening threshold value range, marking the crop as non-plantable crop;
s4: counting the number of the types of the crops which can be planted, and if the number of the types of the crops which can be planted is smaller than m, replacing target crops and repeating the steps S2-S4; if the number of the crop species capable of being planted is equal to m crops, planting the m crops; if the number of the types of the crops capable of being planted is larger than m crops, accumulating a plurality of differences of the crops capable of being planted, sequencing the accumulated values from small to large, and selecting m crops according to a positive sequence.
10. The greenhouse LED illumination closed-loop control system based on ambient light sensing, which implements the greenhouse LED illumination closed-loop control method based on ambient light sensing as claimed in any one of claims 1 to 9, and is characterized by comprising:
the region dividing module divides the greenhouse into m planting regions according to the planting regions of crops, and divides each planting region into n radiation unit regions according to the radiation range of the photosensitive sensor in the planting region, wherein n and m are integers larger than 1;
the first data acquisition module acquires crop images of m planting areas;
the data analysis module is used for analyzing crop images of m planting areas to acquire the current growth stage of crops;
the second data acquisition module acquires historical crop state data, wherein the historical crop state data comprises crop characteristic data and illumination intensity corresponding to the crop characteristic data, and the crop characteristic data comprises crop types and crop growth stages;
the model training module is used for training an illumination adaptation model for predicting illumination intensity based on historical crop state data;
the illumination intensity adaptation module inputs the crop characteristic data acquired in real time into an illumination adaptation model, the predicted illumination intensity is used as target illumination intensity, and the target illumination intensity is used as illumination intensity of the current stage of crops in the mth planting area; controlling an LED illuminating lamp to adjust the illumination intensity of an mth planting area in the greenhouse to a target illumination intensity;
The third data acquisition module acquires the real-time illumination intensity of Q radiation unit areas at the same moment during crop planting, wherein Q=m×n;
the feedback control module is used for comparing and analyzing the real-time illumination intensities of the Q radiation unit areas with the target illumination intensities of the Q radiation unit areas, calculating an illumination intensity error and calculating an illumination intensity adjustment quantity through a PID control algorithm;
and the adjusting module is used for controlling the LED illuminating lamp according to the illumination intensity adjusting quantity and adjusting the current real-time illumination intensity to the target illumination intensity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311449610.5A CN117354988A (en) | 2023-11-02 | 2023-11-02 | Greenhouse LED illumination closed-loop control method and system based on ambient light sensing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311449610.5A CN117354988A (en) | 2023-11-02 | 2023-11-02 | Greenhouse LED illumination closed-loop control method and system based on ambient light sensing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117354988A true CN117354988A (en) | 2024-01-05 |
Family
ID=89355795
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311449610.5A Pending CN117354988A (en) | 2023-11-02 | 2023-11-02 | Greenhouse LED illumination closed-loop control method and system based on ambient light sensing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117354988A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117854012A (en) * | 2024-03-07 | 2024-04-09 | 成都智慧城市信息技术有限公司 | Crop environment monitoring method and system based on big data |
-
2023
- 2023-11-02 CN CN202311449610.5A patent/CN117354988A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117854012A (en) * | 2024-03-07 | 2024-04-09 | 成都智慧城市信息技术有限公司 | Crop environment monitoring method and system based on big data |
| CN117854012B (en) * | 2024-03-07 | 2024-05-14 | 成都智慧城市信息技术有限公司 | Crop environment monitoring method and system based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220075344A1 (en) | A method of finding a target environment suitable for growth of a plant variety | |
| CN117354988A (en) | Greenhouse LED illumination closed-loop control method and system based on ambient light sensing | |
| CN113126490B (en) | Intelligent frequency conversion oxygenation control method and device | |
| CN111096130B (en) | Unmanned intervention planting system using AI spectrum and control method thereof | |
| KR20180022159A (en) | Nutrient solution control apparatus and methods using maching learning | |
| CN114269041A (en) | Intelligent control method and system for plant light supplement based on LED | |
| CN106900418A (en) | A kind of integrated warmhouse booth control system | |
| CN113711798B (en) | Plant growth control method, control equipment, plant growth lamp and control system | |
| CN108983849A (en) | It is a kind of to utilize compound extreme learning machine ANN Control greenhouse method | |
| CN116954291A (en) | Quick adjustment integration method for environmental control equipment | |
| CN117148902B (en) | Intelligent fungus stick growth environment self-adaptive control system and method | |
| CN115530066A (en) | Automatic light adjusting system based on soilless culture | |
| CN118095633A (en) | Greenhouse crop growth monitoring and management system and method based on data analysis | |
| CN115793756A (en) | A plant cabinet environmental control system for adjusting vegetation cycle | |
| CN115292753A (en) | Agricultural greenhouse data tracing and management method based on block chain | |
| CN117852912A (en) | Crop planting income measuring and calculating method and system | |
| KR20230063976A (en) | Method for providing an indicator of temperature stress in watermelon, and system for detecting an abnormality in watermelon temperature based thereon | |
| US20230309464A1 (en) | Method and apparatus for automated crop recipe optimization | |
| CN117521520A (en) | Multi-factor coupled plant factory light environment regulation and control method and system | |
| CN116755485A (en) | Greenhouse regulation and control method, device, system, equipment and storage medium | |
| CN116452358B (en) | Intelligent agriculture management system based on Internet of things | |
| KR20240012288A (en) | Smart farm system with learning algorithm function | |
| KR102039744B1 (en) | Control Method for Collecting and Analyzing Feed-back Control Data for Producing Control Conditions of Plant Growth Environment Conditions for Plant Factory | |
| KR20240012287A (en) | Machine learning-based crop growth optimization system using RGB LED light sources and environmental data | |
| CN110377082A (en) | A kind of automatic control system in greenhouse |
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 |