CN111096130B - Unmanned intervention planting system using AI spectrum and control method thereof - Google Patents

Unmanned intervention planting system using AI spectrum and control method thereof Download PDF

Info

Publication number
CN111096130B
CN111096130B CN201911393053.3A CN201911393053A CN111096130B CN 111096130 B CN111096130 B CN 111096130B CN 201911393053 A CN201911393053 A CN 201911393053A CN 111096130 B CN111096130 B CN 111096130B
Authority
CN
China
Prior art keywords
information
control
regulation
greenhouse
crops
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.)
Active
Application number
CN201911393053.3A
Other languages
Chinese (zh)
Other versions
CN111096130A (en
Inventor
胡炳樑
李海巍
陈军宇
陈铁桥
周安安
高晓惠
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
XiAn Institute of Optics and Precision Mechanics of CAS
Original Assignee
XiAn Institute of Optics and Precision Mechanics of CAS
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by XiAn Institute of Optics and Precision Mechanics of CAS filed Critical XiAn Institute of Optics and Precision Mechanics of CAS
Priority to CN201911393053.3A priority Critical patent/CN111096130B/en
Publication of CN111096130A publication Critical patent/CN111096130A/en
Application granted granted Critical
Publication of CN111096130B publication Critical patent/CN111096130B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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
    • A01G9/00—Cultivation in receptacles, forcing-frames or greenhouses; Edging for beds, lawn or the like
    • A01G9/14—Greenhouses
    • A—HUMAN NECESSITIES
    • A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01C—PLANTING; SOWING; FERTILISING
    • A01C23/00—Distributing devices specially adapted for liquid manure or other fertilising liquid, including ammonia, e.g. transport tanks or sprinkling wagons
    • 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
    • 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
    • A01G9/00—Cultivation in receptacles, forcing-frames or greenhouses; Edging for beds, lawn or the like
    • A01G9/24—Devices or systems for heating, ventilating, regulating temperature, illuminating, or watering, in greenhouses, forcing-frames, or the like
    • A01G9/246—Air-conditioning systems
    • 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
    • A01G9/00—Cultivation in receptacles, forcing-frames or greenhouses; Edging for beds, lawn or the like
    • A01G9/24—Devices or systems for heating, ventilating, regulating temperature, illuminating, or watering, in greenhouses, forcing-frames, or the like
    • A01G9/247—Watering arrangements
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D27/00—Simultaneous control of variables covered by two or more of main groups G05D1/00 - G05D25/00
    • G05D27/02—Simultaneous control of variables covered by two or more of main groups G05D1/00 - G05D25/00 characterised by the use of electric means
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
    • Y02A40/10—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture
    • Y02A40/25—Greenhouse technology, e.g. cooling systems therefor

Landscapes

  • Life Sciences & Earth Sciences (AREA)
  • Environmental Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Physics & Mathematics (AREA)
  • Botany (AREA)
  • Ecology (AREA)
  • Forests & Forestry (AREA)
  • Water Supply & Treatment (AREA)
  • Soil Sciences (AREA)
  • Cultivation Of Plants (AREA)
  • Greenhouses (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention belongs to an intelligent planting control system and method, and provides an unmanned intervention planting system using AI spectrum and a control method thereof for solving the technical problem that the existing greenhouse lacks a targeted matching control system, wherein the planting system comprises a monitoring unit, a transmission unit, a control analysis unit and a regulation and control unit; the spectral information of plants and soil in the greenhouse is collected in real time through the monitoring unit, the environmental information and the illumination condition in the greenhouse are monitored, the environmental information and the illumination condition are transmitted to the control and analysis unit through the transmission unit, the control and analysis unit carries out contrastive analysis on the information of original-place crops stored in the control and analysis unit and sends corresponding regulation and control instructions to the regulation and control unit, and the environment, the crops and the like in the greenhouse are regulated. The control method comprises the steps of monitoring the indoor condition of the greenhouse in real time, calling corresponding information of the original-place crops in the control analysis unit, generating corresponding regulation and control instructions after comparison and analysis, and regulating the greenhouse according to the content of the instructions after the regulation and control unit receives the regulation and control instructions.

Description

Unmanned intervention planting system using AI spectrum and control method thereof
Technical Field
The invention belongs to an intelligent planting control system and method, and particularly relates to an unmanned intervention planting system using an AI spectrum and a control method thereof.
Background
In some remote and high-cold regions, the natural environment is severe and the transportation is inconvenient, the fruits and vegetables which are used as the necessities for life are easy to have the phenomenon of wilting in the transportation process in case of high-temperature weather, and are difficult to supply in time in case of cold days, so that the fruits and vegetables can be frozen in the transportation process even if the fruits and vegetables can be transported. Therefore, fruits and vegetables are difficult to obtain in the areas, and the quality of life of the areas is seriously affected. Some regions adopt greenhouses to solve the problems, but the existing greenhouses often lack a targeted control system and a corresponding control method, so that the control of the greenhouses is not accurate enough, and a large amount of manpower intervention is needed.
Disclosure of Invention
The invention mainly aims to solve the technical problems that fruits and vegetables are difficult to obtain in remote and high-cold regions, the life quality is seriously influenced, and a targeted matching control system is lacked even by means of a greenhouse in the prior art, and provides an unmanned intervention planting system using an AI spectrum and a control method thereof.
In order to achieve the purpose, the invention provides the following technical scheme:
an unmanned intervention planting system using AI spectrum is used for controlling a crop greenhouse and is characterized by comprising a monitoring unit, a transmission unit, a control analysis unit and a regulation and control unit;
the monitoring unit comprises a hyperspectral monitoring module, an environment monitoring module and an illumination monitoring module, wherein the hyperspectral monitoring module is used for collecting the spectrums of crops and soil; the environment monitoring module is used for acquiring environment information consisting of temperature, humidity, air flow and air in the greenhouse; the illumination monitoring module is used for acquiring spectral information and illumination intensity information of a light source in the greenhouse;
the transmission unit transmits the information collected by the monitoring unit to the control unit through a wireless sensor network;
the control analysis unit is used for storing hyperspectral information, water and fertilizer ratio information, solar radiation brightness information, environment information and soil hyperspectral information of various crops in the origin place at each growth stage, receiving corresponding information in the greenhouse, collected by the monitoring unit and transmitted by the storage and transmission unit, comparing and analyzing the information collected by the monitoring unit with the stored information of the corresponding crops in the origin place at each growth stage, and sending a regulation and control instruction or a harvesting instruction to the regulation and control unit according to the comparison and analysis result;
the control unit judges whether the control instruction or the harvesting instruction is received by the control analysis unit, if the control instruction is received by the control analysis unit, whether the temperature, the humidity, the air flow, the air composition, the illumination and the soil nutrients in the greenhouse need to be adjusted is judged according to the control instruction sent by the control analysis unit, if the control instruction is received by the control analysis unit, the adjustment is carried out according to the control instruction, and if the control instruction is not received by the control analysis unit, the existing state is controlled and maintained; and if the command is a harvesting command, sending a harvesting prompt.
Further, the control analysis unit comprises a workstation and a terminal device;
the workstation comprises a data storage unit and a data analysis unit; the data storage unit is used for storing hyperspectral information, water and fertilizer ratio information, solar radiation brightness information, environment information and soil hyperspectral information of various crops in a native place at each growth stage, constructing a corresponding database and receiving corresponding information in the greenhouse, which is collected by the monitoring unit and transmitted by the transmission unit; the data analysis unit is used for comparing and analyzing the information acquired by the monitoring unit with the stored information of each growth stage of the original-place crops;
the terminal equipment is used for receiving and displaying the storage information in the data storage unit and the corresponding information in the greenhouse collected by the detection unit; meanwhile, an auxiliary regulation and control instruction can be input in a man-machine interaction mode and sent to a regulation and control unit, and the regulation and control unit regulates the greenhouse according to the received auxiliary regulation and control instruction.
Furthermore, the hyperspectral information, the water and fertilizer ratio information, the solar radiation brightness information, the environment information and the soil hyperspectral information of various crops in the origin place at each growth stage are obtained by the following method,
the hyperspectral information and soil hyperspectral information of crops in the origin place at each growth stage are that in the origin place of the crops, a hyperspectral imager is adopted to obtain the spectral curves of the soil and the crops in three growth stages of seedling stage, growth stage and maturation stage of various crops, normalization processing is carried out to obtain the spectral characteristic absorption parameters of the soil in different stages and corresponding stages of the crops, and a hyperspectral database C of the crops is establishedj,hAnd a hyperspectral database S of soilj,hWherein j ∈ [1,2,3 ]]Representative of cropsThree growth stages; h is E [0,1,2, 3.]Category label information representing different crops;
the solar light radiation brightness information of crops in the origin place at each growth stage is obtained by reflecting sunlight with the help of a high-reflectivity standard plate and then obtaining a solar light radiation brightness information database I through a hyperspectral imagerj,h；
The environmental information of the crops in the origin place at each growth stage comprises temperature, humidity, air flow and air composition, and is acquired through a thermometer, a humidity sensor, a wind speed and direction sensor and a carbon dioxide sensor respectively.
A control method using the unmanned intervention planting system using AI spectra as described above, characterized by comprising the steps of:
s1, monitoring information in the greenhouse by the monitoring unit
The hyperspectral monitoring module is used for acquiring the spectrums of crops and soil and acquiring the nutrient information of the crops and the soil according to the spectrums of the crops and the soil; the environmental information of temperature, humidity, air flow and air composition in the greenhouse is collected through an environmental monitoring module; collecting spectral information and illumination intensity information of a light source in the greenhouse through an illumination monitoring module;
s2, comparing and analyzing with the origin information
S2.1, transmitting the information collected by the monitoring unit in the step S1 to a control analysis unit through a transmission unit;
s2.2, the control analysis unit receives and stores the information collected by the monitoring unit, compares the information with the stored information of each growth stage of the original-place crops, and generates a regulation instruction or a harvesting instruction according to the comparison analysis result;
s2.3, sending a regulation and control instruction or a harvesting prompt to a regulation and control unit;
s3, adjusting the inside of the greenhouse
Judging whether the instruction received in the step S2.3 is a regulation instruction or a harvesting instruction; if the regulation instruction is the regulation instruction, judging whether the temperature, the humidity, the air flow, the air composition, the illumination and the soil nutrients in the greenhouse need to be regulated or not according to the regulation instruction sent by the control analysis unit, if so, regulating according to the regulation instruction, otherwise, controlling and maintaining the existing state; if the command is a harvesting command, a harvesting prompt is sent to carry out manual picking.
Further, the step S2.2 specifically includes:
s2.2.1 comparative analysis of crop and soil nutrient information
The method comprises the following steps of acquiring the spectrum of soil and crop leaf canopies in real time through a hyperspectral detector arranged in a greenhouse, and calculating a model through inversion:
y＝a1x1+a2x2+…+anxn
wherein: y is the content of the element inverted by the spectrum, a1,a2…,anIs the weight parameter, x, of each band in the spectrum1,x2…,xnRespectively calculating the organic matter element content and the water content of the greenhouse crops and the soil at the collected spectrum positions for each wave band of the spectrum, then calculating the organic matter element content and the water content of the corresponding original-place crops and the soil, and if the difference value of the organic matter element content and the water content is larger than a preset content threshold value, generating a fertilization regulation and control instruction;
s2.2.2 comparative analysis of environmental information
Comparing the environmental information in the greenhouse with the environmental information of crops in the corresponding origin, calculating the difference between the greenhouse and the corresponding origin by using a deep neural network model, performing repeated iteration, adaptively solving the corresponding weight, setting a difference threshold gamma, and if the difference threshold gamma is larger than the gamma, sending an environmental regulation and control instruction to a regulation and control unit until the difference threshold gamma is smaller than or equal to the gamma and stopping sending the environmental regulation and control instruction;
s2.2.3 comparative analysis of light intensity information
Collecting an illumination signal n by an illumination sensor arranged in a greenhouse1Combining temperature sensor signal n collected by temperature sensor in greenhouse2Obtaining the control parameter m ═ b of the artificial light source1*n1+b2*n2Comparing the illumination intensity information with the illumination intensity information of the corresponding origin crops, and sending an illumination regulation and control instruction to a regulation and control unit according to the comparison difference;
s2.2.4, generating harvesting instructions
Crop spectrum curve C collected by hyperspectral monitoring module in greenhouseugWith a crop hyperspectral database C obtained by harvesting at the place of originj,hThe corresponding spectrum in (1) is analyzed for the difference degree, and the angular difference value of the spectrum is calculated
Figure BDA0002345526140000041
And if the calculation result is smaller than the set threshold, judging maturity and sending a harvesting instruction to the regulation and control unit.
Further, the step S2.3 is specifically,
if the received regulation and control instruction is a fertilization regulation and control instruction, performing fixed-point fertilization on the collected spectrum until the difference value between the content of the organic matter element and the moisture content is less than or equal to a preset content threshold value, and stopping fertilization;
if the received regulation and control instruction is an environment regulation and control instruction, draining and exhausting water in the greenhouse until the difference value of the environment information is less than or equal to the difference threshold gamma;
if the received regulation and control instruction is an illumination regulation and control instruction, adjusting an artificial light source in the greenhouse until the contrast difference with the illumination intensity information of the corresponding origin crops is less than or equal to a preset value;
if receiving a harvesting instruction, controlling a harvesting device in the greenhouse to complete harvesting at the position of collecting the spectrum, or prompting manual harvesting.
Compared with the prior art, the invention has the beneficial effects that:
1. the invention uses an AI spectrum unmanned intervention planting system, collects hyperspectral information of plants and soil in a greenhouse in real time through a monitoring unit, monitors environmental information and illumination condition in the greenhouse, transmits the hyperspectral information to a control analysis unit through a transmission unit, the control analysis unit carries out contrastive analysis with the information of crops in the origin place stored in the control analysis unit, sends corresponding regulation and control instructions to the regulation and control unit, regulates the environment, the crops and the like in the greenhouse, realizes full-automatic planting control through the planting system of the invention, constructs an automatic system aiming at the greenhouse, fully releases labor force, regulates the planting environment of the crops in the greenhouse more accurately and pertinently, leads the crops in the greenhouse to grow in the growing environment matched with the origin place all the time, keeps the water and fertilizer conditions in the best state, effectively ensures the growth quality of the crops, and can accurately regulate the plants and the environment in the greenhouse according to the monitoring and analysis results, the utilization rate of water and fertilizer is improved, and the best planting effect is achieved while the minimum investment is achieved. Can acquire the all-round information in greenhouse at any time, be convenient for read the vegetation condition in real time.
2. The control analysis unit not only can store the relevant growth information of various stages of crops in the origin and construct a corresponding database, but also comprises terminal equipment which is convenient for checking the real-time information in the greenhouse, and inputs an auxiliary regulation and control instruction in a man-machine interaction mode to assist in regulating the greenhouse.
3. The invention establishes the information of various growth stages of various crops in the origin place in a normalization processing mode, establishes a hyperspectral database of the crops and the soil respectively, and stores the related information of the seedling stage, the growth stage and the mature stage in the growth of the crops in the database, thereby facilitating the control and analysis unit to be called at any time. In addition, when the solar radiation brightness information is obtained, the light loss is avoided by means of the high-reflectivity standard plate, and the obtained spectrum is more accurate.
4. The control method of the unmanned intervention planting system using the AI spectrum is based on the planting system, firstly, the indoor condition of the temperature measurement is monitored in real time, then, the corresponding information of the original-place crops in the control and analysis unit is called, the corresponding regulation and control instructions are generated after the comparison and analysis, and the regulation and control unit regulates the greenhouse according to the content of the instructions after receiving the regulation and control instructions.
5. The control analysis unit of the invention respectively calculates and analyzes the crop and soil nutrient information, the environment information, the illumination intensity information and the crop spectrum curve through corresponding models and algorithms, and sends corresponding regulation and control instructions to the regulation and control unit according to respective conditions, thereby achieving the effect of accurate control.
6. The regulating and controlling unit can accurately apply water and fertilizer to crops in the greenhouse, regulate the environment through water drainage and air exhaust, regulate the illumination condition, and control automatic harvesting or manual harvesting if the mature fruits are detected.
Drawings
FIG. 1 is a schematic structural diagram of an embodiment of an unmanned intervention planting system using AI spectra according to the present invention;
fig. 2 is a schematic flow chart of an embodiment of the unmanned intervention planting control method using AI spectra according to the invention.
Detailed Description
The technical solution of the present invention will be clearly and completely described below with reference to the embodiments of the present invention and the accompanying drawings, and it is obvious that the described embodiments do not limit the present invention.
Aiming at a crop greenhouse, an intelligent control system, such as an unmanned intervention planting system using AI spectrum shown in the attached figures 1 and 2, is constructed, and comprises a monitoring unit, a transmission unit, a control and analysis unit and a regulation and control unit.
The monitoring unit comprises a hyperspectral monitoring module, an environment monitoring module and an illumination monitoring module, the hyperspectral monitoring module is used for acquiring the spectrum of crops and soil, and the nutrient conditions of the soil and the crops can be monitored by inverting the content of elements such as nitrogen, phosphorus and potassium; the environment monitoring module monitors the temperature, the humidity, the air flow and the air composition in the temperature measuring room in real time by using intelligent environment monitoring equipment comprising a temperature and humidity sensor, a wind speed and direction sensor and a carbon dioxide concentration sensor; and the illumination monitoring module monitors the spectrum information and the illumination intensity information of the artificial crop light source arranged in the greenhouse by using the intelligent spectrometer and the illumination sensor.
The transmission unit transmits information acquired by the monitoring unit to the control analysis unit for data processing and analysis by using a wireless sensor network, such as GPRS, 5G, 4G, 3G and the like, so as to obtain a regulation instruction or a harvesting instruction, in addition, the regulation unit judges whether the regulation instruction or the harvesting instruction is received by the control analysis unit after receiving the regulation instruction or the harvesting instruction, if the regulation instruction is received, whether the temperature, the humidity, the air flow, the air composition, the illumination and the soil nutrient in the greenhouse need to be regulated or not is judged according to the regulation instruction sent by the control analysis unit, if the regulation instruction is required, the regulation is carried out according to the regulation instruction, otherwise, the control is maintained in the existing state; and if the command is a harvesting command, sending a harvesting prompt.
The control analysis unit may include a workstation and a terminal device, and the terminal device may be a computer, a mobile phone or other forms of upper computers. The conditions of the environment, soil and crops in the greenhouse can be observed in real time through the terminal equipment, remote regulation and control can be carried out according to related parameters under the condition that no human intervention is needed, and an auxiliary regulation and control instruction is input, so that the regulation and control unit regulates the greenhouse according to the auxiliary regulation and control instruction.
The workstation comprises a data storage unit and a data analysis unit. The data storage unit stores pre-collected hyperspectral information, water and fertilizer proportioning information, sunlight spectrum radiance information, temperature, humidity, wind direction and wind speed of the original place and air component content information of the original place soil and various crops at different growth stages, and corresponding databases are respectively constructed by the information; the temperature, humidity, air flow, illumination and hyperspectral information of soil and crops and real-time water and fertilizer ratio information collected in the greenhouse in real time are also used for constructing a corresponding database.
The specific content of the information related to the origin place is collected by adopting a hyperspectral imager to obtain standard spectral curves of soil and a plurality of crops to be detected in the seedling stage, the growth stage and the maturation stage, normalization processing is carried out to obtain different periods of each crop including the seedling stage, the growth stage and the maturation stage of the crop and spectral characteristic absorption parameters of corresponding soil, and a crop hyperspectral database C is establishedj,hAnd soil hyperspectral database Sj,hWhere j ∈ [1,2,3 ]]Represents three growth stages of the crop; h is E [0,1,2, 3.]Category label information representing different crops. Then obtaining the water-fertilizer ratio W of different crops in different stages of the originj,h. Meanwhile, the solar spectral irradiance information I at different stages is collected and stored by means of a high-reflectivity standard platej,h. Measuring the environmental temperature, humidity, air component content and wind speed and direction of the origin by a thermometerThe sensor, the carbon dioxide sensor and the wind speed and direction sensor.
In the data analysis unit, the hyperspectral data and the environmental parameter data of the acquired soil crops are processed and analyzed, the control instruction of the processing result is sent to the control unit through the transmission unit, the maturity of the crops can be monitored when the crops are mature, the corresponding harvest instruction is sent out through the processing of the crop spectrum, the crop yield information can be combined in the transmission process, the optimal control threshold value is continuously updated, the spectrum in the database is iteratively optimized, different intelligent greenhouse special databases and control threshold values are adaptively established according to different conditions, and the method mainly comprises the comparative analysis of the following four aspects:
(1) spectral treatment of soil and crops in greenhouses. Respectively processing the spectra of soil and crops, acquiring the organic matter content, nitrogen, phosphorus, potassium, moisture content information and the like of soil and crop leaf canopies in real time through a hyperspectral detector in a greenhouse, and establishing an inversion calculation model of each channel of an intelligent spectrometer and the content of soil and crop elements:
y＝a1x1+a2x2+…+anxn
in the formula: y is the content of the element inverted by the spectrum, a1,a2…,anIs the weight information of each wave band of the sensor, x1,x2…,xnFor each wavelength band of the sensor, a1,a2…,anIs the weight parameter, x, of each band in the spectrum1,x2…,xnIn each band of the spectrum. For example, the total nitrogen content of the blade can be jointly inverted through the absorption depths of the absorption characteristic spectra 585-.
Comparing the greenhouse hyperspectral curve with a standard spectrum library curve, determining the elements lacking in crops and soil according to the difference by combining the models in the formula aiming at the difference region, and outputting a corresponding fertilization regulation and control instruction if the difference is greater than a preset content threshold. During fertilization, the deficient elements can be automatically added through the intelligent fertigation control system, and fertilization can be stopped until the monitored spectrum in the greenhouse is close to the spectrum in the standard spectrum library according to the change condition of the corresponding spectrum curve in the greenhouse.
(2) And comparing and analyzing the environmental information, namely comparing the temperature, the humidity, the wind speed and the wind direction and the illumination in the environmental information with the temperature, the humidity, the wind speed and the wind direction of the original place in the database respectively, calculating the difference between the greenhouse and the original place by using a deep neural network model, repeating iteration, adaptively solving the corresponding weight, setting a difference threshold gamma, and sending an environmental regulation and control instruction to a regulation and control unit until the difference is less than or equal to the gamma, wherein the difference threshold gamma is set to be more than the corresponding weight. Wherein the analysis and comparison of the illumination intensity is that an illumination signal n is collected by an illumination sensor arranged in the greenhouse1Combining temperature sensor signal n collected by temperature sensor in greenhouse2Obtaining the control parameter m ═ b of the artificial light source1*n1+b2*n2Comparing the illumination intensity information with the illumination intensity information of the corresponding origin crops, and sending an illumination regulation and control instruction to a regulation and control unit according to the comparison difference;
(3) judging the maturity, and collecting the crop spectrum curve C collected by the hyperspectral monitoring module in the greenhouseugWith a crop hyperspectral database C obtained by harvesting at the place of originj,hThe corresponding spectrum in (1) is analyzed for the difference degree, and the angular difference value of the spectrum is calculated
Figure BDA0002345526140000081
If the calculation result is smaller than the set threshold value, the maturity is judged, a harvesting instruction is sent to the regulating and controlling unit, and the regulating and controlling unit can control the intelligent harvesting equipment to carry out automatic picking or manual picking.
An optimization processing module can be added, the nutrition proportion is continuously updated and optimized according to hyperspectral information recorded in the growth process of crops in the greenhouse and by combining yield information and quality detection information after the crops are mature, a standard spectrum database is iteratively evolved, and different intelligent special spectrum databases and regulation and control threshold values for the underground greenhouse are adaptively established according to different conditions.
The regulation and control unit mainly realizes the following four aspects of control:
(1) and (3) intelligent control of the precision drip irrigation fertilization, namely allocating water and fertilizer in a corresponding proportion to the soil and the crops in the spectrum acquisition area by receiving a fertilization regulation and control instruction sent by the control and analysis unit, regulating the nutrient content and the moisture content of the soil and the crops until the difference value of the environmental information is less than or equal to the difference threshold gamma, and stopping water and fertilizer regulation and control on the area.
(2) The illumination control is realized by adjusting the radiance of the artificial light source and controlling the regulation and control instruction sent by the analysis unit to depend on the illumination signal n collected by the illumination sensor1Temperature sensor signal n collected by temperature sensor2As a result of the co-action, different weighting parameters b are selected according to different scenes1And b2Obtaining the control parameter m ═ b of the artificial light source1*n1+b2*n2(ii) a And when m is larger than the set threshold range, sending a regulation and control instruction to the artificial light source control system to regulate the radiance condition of the light source.
(3) The environment control comprises the steps that an environment regulation and control instruction is sent out through a control analysis unit, air exhaust and water drainage regulation is carried out on the greenhouse, the environment regulation and control instruction depends on information of a temperature sensor and a humidity sensor received by the control analysis unit, air exhaust and water drainage results are output by setting different weights, corresponding difference threshold values are set, when the difference threshold value ranges are exceeded, the regulation and control unit carries out air exhaust and water drainage control of different levels, and the regulation and control are stopped until the temperature and the humidity reach the set difference threshold values.
If the regulation and control unit receives a harvesting instruction, a corresponding automatic harvesting device can be carried in the greenhouse, the automatic harvesting device can automatically search for mature crops, and automatic harvesting is completed after the corresponding crops are found.
The control method is summarized as follows:
s1, monitoring information in the greenhouse by the monitoring unit
The hyperspectral monitoring module is used for acquiring the spectrums of crops and soil and acquiring the nutrient information of the crops and the soil according to the spectrums of the crops and the soil; the environmental information of temperature, humidity, air flow and air composition in the greenhouse is collected through an environmental monitoring module; collecting spectral information and illumination intensity information of a light source in the greenhouse through an illumination monitoring module;
s2, comparing and analyzing with the origin information
S2.1, transmitting the information collected by the monitoring unit in the step S1 to a control analysis unit through a transmission unit;
s2.2, the control analysis unit receives and stores the information collected by the monitoring unit, compares the information with the stored information of each growth stage of the original-place crops, and generates a regulation instruction or a harvesting instruction according to the comparison analysis result;
s2.3, sending a regulation and control instruction or a harvesting prompt to a regulation and control unit;
s3, adjusting the inside of the greenhouse
Judging whether the instruction received in the step S2.3 is a regulation instruction or a harvesting instruction; if the regulation instruction is the regulation instruction, judging whether the temperature, the humidity, the air flow, the air composition, the illumination and the soil nutrients in the greenhouse need to be regulated or not according to the regulation instruction sent by the control analysis unit, if so, regulating according to the regulation instruction, otherwise, controlling and maintaining the existing state; if the command is a harvesting command, a harvesting prompt is sent to carry out manual picking.
Based on the planting system, under the control method, unmanned intervention planting can be realized, crops can be managed accurately, and the planting efficiency is effectively improved.
The above description is only an embodiment of the present invention, and is not intended to limit the scope of the present invention, and all equivalent structural changes made by using the contents of the present specification and the drawings, or applied directly or indirectly to other related technical fields, are included in the scope of the present invention.

Claims (4)

1. A control method of an unmanned intervention planting system using AI spectrum is used for controlling a crop greenhouse and comprises a monitoring unit, a transmission unit, a control analysis unit and a regulation and control unit;
the monitoring unit comprises a hyperspectral monitoring module, an environment monitoring module and an illumination monitoring module, and the hyperspectral monitoring module is used for acquiring hyperspectral information of crops and soil; the environment monitoring module is used for acquiring environment information consisting of temperature, humidity, air flow and air in the greenhouse; the illumination monitoring module is used for acquiring spectral information and illumination intensity information of a light source in the greenhouse;
the transmission unit transmits the information collected by the monitoring unit to the control unit through a wireless sensor network;
the control analysis unit is used for storing hyperspectral information, water and fertilizer ratio information, solar radiation brightness information, environment information and soil hyperspectral information of various crops in the origin place at each growth stage, receiving corresponding information in the greenhouse, collected by the monitoring unit and transmitted by the storage and transmission unit, comparing and analyzing the information collected by the monitoring unit with the stored information of the corresponding crops in the origin place at each growth stage, and sending a regulation and control instruction or a harvesting instruction to the regulation and control unit according to the comparison and analysis result;
the control unit judges whether the control instruction or the harvesting instruction is received by the control analysis unit, if the control instruction is received by the control analysis unit, whether the temperature, the humidity, the air flow, the air composition, the illumination and the soil nutrients in the greenhouse need to be adjusted is judged according to the control instruction sent by the control analysis unit, if the control instruction is received by the control analysis unit, the adjustment is carried out according to the control instruction, and if the control instruction is not received by the control analysis unit, the existing state is controlled and maintained; if the command is a harvesting command, a harvesting prompt is sent;
the method is characterized by comprising the following steps:
s1, monitoring information in the greenhouse by the monitoring unit
The hyperspectral monitoring module is used for acquiring the spectrums of crops and soil and acquiring the nutrient information of the crops and the soil according to the spectrums of the crops and the soil; the environmental information of temperature, humidity, air flow and air composition in the greenhouse is collected through an environmental monitoring module; collecting spectral information and illumination intensity information of a light source in the greenhouse through an illumination monitoring module;
s2, comparing and analyzing with the origin information
S2.1, transmitting the information collected by the monitoring unit in the step S1 to a control analysis unit through a transmission unit;
s2.2.1 comparative analysis of crop and soil nutrient information
The method comprises the following steps of acquiring the spectrum of soil and crop leaf canopies in real time through a hyperspectral detector arranged in a greenhouse, and calculating a model through inversion:
y＝a1x1+a2x2+…+anxn
wherein: y is the content of the element inverted by the spectrum, a1,a2...,anIs the weight parameter, x, of each band in the spectrum1,x2...,xnRespectively calculating the organic matter element content and the water content of the greenhouse crops and the soil at the collected spectrum positions for each wave band of the spectrum, then calculating the organic matter element content and the water content of the corresponding original-place crops and the soil, and if the difference value of the organic matter element content and the water content is larger than a preset content threshold value, generating a fertilization regulation and control instruction;
s2.2.2 comparative analysis of environmental information
Comparing the environmental information in the greenhouse with the environmental information of crops in the corresponding origin, calculating the difference between the greenhouse and the corresponding origin by using a deep neural network model, performing repeated iteration, adaptively solving the corresponding weight, setting a difference threshold gamma, and if the difference threshold gamma is larger than the gamma, sending an environmental regulation and control instruction to a regulation and control unit until the difference threshold gamma is smaller than or equal to the gamma and stopping sending the environmental regulation and control instruction;
s2.2.3 comparative analysis of light intensity information
Collecting an illumination signal n by an illumination sensor arranged in a greenhouse1Combining temperature sensor signal n collected by temperature sensor in greenhouse2Obtaining the control parameter m ═ b of the artificial light source1*n1+b2*n2Wherein b is1And b2Are each n1And n2The weight parameters are compared with the illumination intensity information of the corresponding origin crops, and an illumination regulation and control instruction is sent to a regulation and control unit according to the comparison difference;
s2.2.4, generating harvesting instructions
Crop spectrum curve C collected by hyperspectral monitoring module in greenhouseugWith a crop hyperspectral database C obtained by harvesting at the place of originj,hThe corresponding spectrum in (1) is analyzed for the difference degree, and the angular difference value of the spectrum is calculated
Figure FDA0003022660730000021
If the calculation result is smaller than the set threshold, judging maturity, and sending a harvesting instruction to the regulation and control unit;
s2.3, sending a regulation and control instruction or a harvesting prompt to a regulation and control unit;
s3, adjusting the inside of the greenhouse
Judging whether the instruction received in the step S2.3 is a regulation instruction or a harvesting instruction; if the regulation instruction is the regulation instruction, judging whether the temperature, the humidity, the air flow, the air composition, the illumination and the soil nutrients in the greenhouse need to be regulated or not according to the regulation instruction sent by the control analysis unit, if so, regulating according to the regulation instruction, otherwise, controlling and maintaining the existing state; if the command is a harvesting command, a harvesting prompt is sent to carry out manual picking.
2. The control method according to claim 1, characterized in that: the step S2.3 is specifically that,
if the received regulation and control instruction is a fertilization regulation and control instruction, performing fixed-point fertilization on the collected spectrum until the difference value between the content of the organic matter element and the moisture content is less than or equal to a preset content threshold value, and stopping fertilization;
if the received regulation and control instruction is an environment regulation and control instruction, draining and exhausting water in the greenhouse until the difference value of the environment information is less than or equal to the difference threshold gamma;
if the received regulation and control instruction is an illumination regulation and control instruction, adjusting an artificial light source in the greenhouse until the contrast difference with the illumination intensity information of the corresponding origin crops is less than or equal to a preset value;
and if a harvesting instruction is received, controlling a harvesting device in the greenhouse to complete harvesting at the position of collecting the spectrum, or prompting manual harvesting.
3. The control method according to claim 1, characterized in that: the control analysis unit comprises a workstation and terminal equipment;
the workstation comprises a data storage unit and a data analysis unit; the data storage unit is used for storing hyperspectral information, water and fertilizer ratio information, solar radiation brightness information, environment information and soil hyperspectral information of various crops in a native place at each growth stage, constructing a corresponding database and receiving corresponding information in the greenhouse, which is collected by the monitoring unit and transmitted by the transmission unit; the data analysis unit is used for comparing and analyzing the information acquired by the monitoring unit with the stored information of each growth stage of the original-place crops;
the terminal equipment is used for receiving and displaying the storage information in the data storage unit and the corresponding information in the greenhouse collected by the detection unit; meanwhile, an auxiliary regulation and control instruction can be input in a man-machine interaction mode and sent to a regulation and control unit, and the regulation and control unit regulates the greenhouse according to the received auxiliary regulation and control instruction.
4. The control method according to claim 3, characterized in that: the hyperspectral information, the water and fertilizer ratio information, the solar radiation brightness information, the environment information and the soil hyperspectral information of various crops in the origin place at each growth stage are obtained by the following method,
the hyperspectral information and soil hyperspectral information of crops in the origin place at each growth stage are that in the origin place of the crops, a hyperspectral imager is adopted to obtain the spectral curves of the soil and the crops in three growth stages of seedling stage, growth stage and maturation stage of various crops, normalization processing is carried out to obtain the spectral characteristic absorption parameters of the soil in different stages and corresponding stages of the crops, and a hyperspectral database C of the crops is establishedj,hAnd a hyperspectral database S of soilj,hWherein j ∈ [1,2,3 ]]Represents three growth stages of the crop; h is E [0,1,2, 3.]Category label information representing different crops;
the solar light radiation brightness information of crops in the origin place at each growth stage is obtained by reflecting sunlight with the help of a high-reflectivity standard plate and then obtaining a solar light radiation brightness information database I through a hyperspectral imagerj,h；
The environmental information of the crops in the origin place at each growth stage comprises temperature, humidity, air flow and air composition, and is acquired through a thermometer, a humidity sensor, a wind speed and direction sensor and a carbon dioxide sensor respectively.
CN201911393053.3A 2019-12-30 2019-12-30 Unmanned intervention planting system using AI spectrum and control method thereof Active CN111096130B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911393053.3A CN111096130B (en) 2019-12-30 2019-12-30 Unmanned intervention planting system using AI spectrum and control method thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911393053.3A CN111096130B (en) 2019-12-30 2019-12-30 Unmanned intervention planting system using AI spectrum and control method thereof

Publications (2)

Publication Number Publication Date
CN111096130A CN111096130A (en) 2020-05-05
CN111096130B true CN111096130B (en) 2021-07-27

Family

ID=70424299

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911393053.3A Active CN111096130B (en) 2019-12-30 2019-12-30 Unmanned intervention planting system using AI spectrum and control method thereof

Country Status (1)

Country Link
CN (1) CN111096130B (en)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111624165A (en) * 2020-05-20 2020-09-04 农芯科技（北京）有限责任公司 Synchronous measurement system and method for meteorological environment parameters and spectrums
CN111781331A (en) * 2020-06-30 2020-10-16 中日友好环境保护中心(生态环境部环境发展中心) Physicochemical data acquisition and analysis processing system for chemical fertilizer stress contaminated soil
CN113029984A (en) * 2021-03-13 2021-06-25 深圳市威视佰科科技有限公司 Soil monitoring method and device based on multi-channel spectral sensor
CN114616999A (en) * 2022-04-08 2022-06-14 宁波云笈科技有限公司 Planting equipment for adjusting water and fertilizer supply according to illuminance parameters
CN115428637A (en) * 2022-09-05 2022-12-06 浙江大学 Illumination-water-fertilizer comprehensive planting system and planting method thereof
CN117295210B (en) * 2023-11-24 2024-02-23 深圳市金威源科技股份有限公司 Intelligent power supply control method, system and storage medium based on agricultural illumination

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106069144A (en) * 2016-07-08 2016-11-09 湖南普斯赛特光电科技有限公司 A kind of method planting Herba Spinaciae in artificial light type plant factor
CN107589729A (en) * 2017-09-12 2018-01-16 合肥师范学院 A kind of wisdom agricultural management system and method based on Internet of Things and expert system

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106069144A (en) * 2016-07-08 2016-11-09 湖南普斯赛特光电科技有限公司 A kind of method planting Herba Spinaciae in artificial light type plant factor
CN107589729A (en) * 2017-09-12 2018-01-16 合肥师范学院 A kind of wisdom agricultural management system and method based on Internet of Things and expert system

Also Published As

Publication number Publication date
CN111096130A (en) 2020-05-05

Similar Documents

Publication Publication Date Title
CN111096130B (en) Unmanned intervention planting system using AI spectrum and control method thereof
RU2688234C1 (en) Smart growing control method and smart device for growing
CN105045321A (en) Internet-of-things application design-based cloud platform integrated management method
CN111066535A (en) Planting greenhouse using AI spectrum and planting method
CN113439520A (en) Intelligent decision-making method and system for crop irrigation and fertilization
CN112042353A (en) Water and fertilizer accurate decision method and system suitable for sunlight greenhouse
CN114723113A (en) Agricultural automated production management system
Jo et al. Development of a transpiration model for precise tomato (Solanum lycopersicum L.) irrigation control under various environmental conditions in greenhouse
CN111084030A (en) Container AI spectrum planting system simulating mars microgravity and control method thereof
CN116362578A (en) Determination method and device of irrigation strategy
CN115439402A (en) Sugar cane yield-per-unit remote sensing estimation method and device based on SAFY-Sugar model
Choi et al. Development of a transpiration model for precise irrigation control in tomato cultivation
CN114066033A (en) Intelligent agriculture optimization method and system
CN111176238B (en) AIPA intelligent decision-making type precise agricultural system
Atmadja et al. Indoor Hydroponic System Using IoT-Based LED
CN110751322B (en) Litchi shoot control and flower promotion management method based on big data analysis and prediction
Black et al. The effects of conditioning strawberry plug plants under altered red/far-red light environments
CN113597941A (en) Greenhouse intelligent environment regulation and control system and device
KR102134397B1 (en) An environmental condition control system based on plant activity index for controlled horticulture and method thereof
Nederhoff et al. Measurement and simulation of crop photosynthesis of cucumber (Cucumis sativus L.) in greenhouses.
Kizer et al. Continuous, proximal leaf monitoring system to assist with precision irrigation implementation using a wireless mesh network of sensors and controllers in almonds
Ko et al. CWSI-based Smart Irrigation System Design
CN116578047B (en) Fine intelligent control method and system for chilli production
Shelford et al. Comparison of a new plant-based irrigation control method with light-based irrigation control for greenhouse tomato production
CN214708748U (en) Management and control system for accurate nutrition irrigation of crops

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
GR01 Patent grant
GR01 Patent grant