CN114902854B - Accurate water and fertilizer management method and system for field based on computer deep learning - Google Patents
Accurate water and fertilizer management method and system for field based on computer deep learning Download PDFInfo
- Publication number
- CN114902854B CN114902854B CN202210772568.XA CN202210772568A CN114902854B CN 114902854 B CN114902854 B CN 114902854B CN 202210772568 A CN202210772568 A CN 202210772568A CN 114902854 B CN114902854 B CN 114902854B
- Authority
- CN
- China
- Prior art keywords
- data
- fertilizer
- water
- field
- control
- 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
Links
- 239000003337 fertilizer Substances 0.000 title claims abstract description 172
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 153
- 238000007726 management method Methods 0.000 title claims abstract description 57
- 238000013135 deep learning Methods 0.000 title claims abstract description 38
- 238000004364 calculation method Methods 0.000 claims abstract description 12
- 239000002689 soil Substances 0.000 claims description 60
- 238000004891 communication Methods 0.000 claims description 53
- 239000007788 liquid Substances 0.000 claims description 41
- 238000003973 irrigation Methods 0.000 claims description 27
- 230000002262 irrigation Effects 0.000 claims description 27
- 238000010248 power generation Methods 0.000 claims description 16
- 238000001556 precipitation Methods 0.000 claims description 16
- 238000013507 mapping Methods 0.000 claims description 15
- 230000005855 radiation Effects 0.000 claims description 15
- 238000003756 stirring Methods 0.000 claims description 14
- 238000002156 mixing Methods 0.000 claims description 13
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 claims description 12
- 238000005286 illumination Methods 0.000 claims description 12
- 235000021049 nutrient content Nutrition 0.000 claims description 12
- 239000004744 fabric Substances 0.000 claims description 10
- 238000003860 storage Methods 0.000 claims description 10
- 230000003993 interaction Effects 0.000 claims description 9
- 238000000034 method Methods 0.000 claims description 8
- 230000001960 triggered effect Effects 0.000 claims description 7
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 claims description 6
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical compound [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 claims description 6
- 210000003608 fece Anatomy 0.000 claims description 6
- 239000010871 livestock manure Substances 0.000 claims description 6
- 229910052757 nitrogen Inorganic materials 0.000 claims description 6
- 229910052698 phosphorus Inorganic materials 0.000 claims description 6
- 239000011574 phosphorus Substances 0.000 claims description 6
- 239000011591 potassium Substances 0.000 claims description 6
- 229910052700 potassium Inorganic materials 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 244000037666 field crops Species 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 230000001502 supplementing effect Effects 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 3
- 244000061456 Solanum tuberosum Species 0.000 description 6
- 235000002595 Solanum tuberosum Nutrition 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 241000209140 Triticum Species 0.000 description 2
- 235000021307 Triticum Nutrition 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 2
- 238000004090 dissolution Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 239000003621 irrigation water Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000007665 sagging Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- 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
- A01C23/007—Metering or regulating systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- 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
- Y02A40/22—Improving land use; Improving water use or availability; Controlling erosion
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Agronomy & Crop Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Environmental Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Soil Sciences (AREA)
- Biophysics (AREA)
- Animal Husbandry (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Water Supply & Treatment (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Hydroponics (AREA)
Abstract
The invention provides a field accurate water and fertilizer management method and system based on computer deep learning, and belongs to the technical field of field water and fertilizer management. According to the invention, through collecting weather and climate data, apparent state data of crops and data capable of being manually controlled through water and fertilizer management, all conditions required by crop growth are basically contained, modeling analysis is carried out on the data by utilizing a computer deep learning mode, the water and fertilizer in a field can be managed more accurately, and as the data are accumulated, the water and fertilizer management becomes more and more accurate, meanwhile, a control model is generated and optimized by utilizing the strong calculation force of the central server of the cloud server, and the data calculation and control instruction generation are carried out by utilizing the edge node server by utilizing the control model, so that the data feedback time can be greatly shortened, and the water and fertilizer can be controlled more accurately; and the cloud server is utilized to easily realize remote control, so that the water and fertilizer management of a field is facilitated.
Description
Technical Field
The invention belongs to the technical field of field water and fertilizer management, and particularly relates to a field accurate water and fertilizer management method and system based on computer deep learning.
Background
Wheat is commonly planted in China and China, but most of wheat fields are in a traditional manual work state, water and fertilizer management is rough, and water resource waste and fertilizer abuse are easy to cause.
The intelligent water and fertilizer integrated management system for field potato planting comprises a field data acquisition device for acquiring data and uploading the data, a soil moisture content identification device for data analysis, an automatic control device for controlling irrigation equipment and a field irrigation device for potato irrigation, wherein the soil moisture content identification device and the automatic control device are arranged in a remote upper computer; the field data acquisition device comprises a soil moisture sensor, an information acquisition terminal and a solar storage battery. Through the same position, the multiple depth, stability, the continuous monitoring to soil for the soil moisture data of survey has practical value, can instruct actual production, can realize planting automatic monitoring and irrigation in the field, makes potato crop can be in good time moderate irrigation under various meteorological factors, the water economy resource for soil moisture content can be more suitable for the growth of potato, improves potato output. However, this management system has the following problems: only be used for the potato, and only adjust irrigation water, still can not carry out long-range management and control, regulate and control can not adjust according to weather and climate change for the accuracy ratio of liquid manure management is lower.
Disclosure of Invention
The invention aims to provide a field accurate water and fertilizer management method and system based on computer deep learning, which are used for solving the technical problems in the prior art.
In order to achieve the above purpose, the invention adopts the following technical scheme: the field accurate water and fertilizer management method based on computer deep learning comprises the following steps:
s1, acquiring field data in a period T1 by using a sensor, wherein the field data comprise natural climate data, apparent contrast data and adjustable data, the natural climate data are weather and climate data, the apparent contrast data are apparent state data of crops, and the adjustable data are data which can be manually controlled through water and fertilizer management;
s2, selecting an edge node server with the fastest response from the cloud servers as a first edge node server by using the controller;
s3, transmitting field data of the period T1 to a first edge node server, and enabling the first edge node server to give a control instruction of the period T1 according to the field data and transmit the control instruction to a field water and fertilizer control device so as to control water and fertilizer applied to a field;
s4, the first edge node server transmits field data of the period T1 and control instructions of the period T1 to a central server of the cloud server, the central server adopts a deep learning method, and carries out training learning by combining historical data of the field data to obtain a T1 control model for controlling water and fertilizer of crops, wherein the historical data is all historical statistical data before the field data of the period T1;
s5, the T1 control model is returned to the first edge node server;
s6, collecting field data of a T2 period, transmitting the field data to a first edge node server, giving a control instruction of the T2 period according to calculation of a T1 control model, and transmitting the control instruction to a field water and fertilizer control device to control water and fertilizer applied to a field;
s7, repeating the steps S4-S6 until the field water and fertilizer management work is finished.
In one possible implementation, in S1, the natural climate data includes air temperature and humidity data, precipitation data, light radiation data, wind direction data, the apparent control data includes crop image information data, and the adjustable data includes soil moisture content data, soil temperature data, soil EC conductivity data, soil PH data, soil quick-acting nitrogen, phosphorus, potassium nutrient content data, and leaf temperature and humidity data.
In one possible implementation, in S4, the step of generating the T1 control model includes:
selecting apparent contrast data corresponding to the optimal growth state of crops in historical data of field data, and combining the apparent contrast data with corresponding natural climate data and adjustable data to generate climate-apparent-adjustable relation mapping; selecting apparent control data corresponding to different growth states of crops in historical data of field data, and combining the apparent control data with corresponding adjustable data to generate apparent-adjustable relation mapping;
after the field data of the period T1 are acquired, natural climate data closest to natural climate data in the field data of the period T1 are found in the climate-apparent-regulation relation mapping, and apparent control data and regulatable data corresponding to the natural climate data are found;
respectively finding apparent control data closest to apparent control data in field data of a T1 period in an apparent-regulation relation map by using a neural network method, continuously finding corresponding regulatable data, and supplementing the field data of the T1 period into the apparent-regulation relation map;
according to the difference value between the adjustable data found in the climate-apparent-regulation relation mapping and the adjustable data found in the apparent-regulation relation mapping, the control instruction of the field water and fertilizer control device is given by combining the area parameter of the land block;
and generating a control model in the control step to obtain the T1 control model.
In order to achieve the above purpose, the invention adopts the following technical scheme: the field accurate water and fertilizer management system based on computer deep learning comprises a field data acquisition device, a crop image acquisition module, a climate data acquisition device, a water source pipeline, a fertilizer liquid supply device, a water and fertilizer control device, a cloud server and a communication device, wherein the field data acquisition device is used for acquiring field data; the crop image acquisition module is used for acquiring images of field crops; the climate data acquisition device is used for acquiring climate data; the water source pipeline is provided with a water flow control valve for supplying water to the field; the fertilizer liquid supply device comprises a fertilizer dissolving stirring barrel, a fertilizer liquid supply pipeline connected with the fertilizer dissolving stirring barrel and a fertilizer liquid flow control valve arranged on the fertilizer liquid supply pipeline so as to supply fertilizer liquid into the field; the water and fertilizer control device is respectively and electrically connected with the water flow control valve and the fertilizer flow control valve to control the actions of the water flow control valve and the fertilizer flow control valve; the cloud server is used for carrying out data processing; the communication device is respectively in communication connection with the water and fertilizer control device and the cloud server, is in communication connection with the field data acquisition device through the wireless communication module, and is used for receiving signals transmitted by the field data acquisition device and then transmitting the signals to the cloud server, and receiving data signals of the cloud server and then transmitting the data signals to the water and fertilizer control device.
In one possible implementation mode, the field data acquisition device comprises a soil moisture content sensor for detecting soil moisture content, a soil EC conductivity acquisition module for detecting soil EC conductivity, a soil PH value acquisition module for detecting soil PH value, a soil temperature acquisition module for detecting soil temperature, a nutrient content acquisition module for detecting the nutrient content of quick-acting nitrogen, phosphorus and potassium of soil, a blade temperature and humidity acquisition module for detecting blade temperature and humidity, a data processor for processing data and a field power supply module for supplying power, wherein the data processor is respectively and electrically connected with the soil moisture content sensor, the soil EC conductivity acquisition module, the soil PH value acquisition module, the soil temperature acquisition module, the nutrient content acquisition module and the blade temperature and humidity acquisition module and is in communication connection with the communication device through a wireless communication module so as to transmit acquired data signals to the communication device; the field power module is electrically connected with the data processor to supply power.
In one possible implementation mode, the field precise water and fertilizer management system based on computer deep learning further comprises a blending pump and a drip irrigation pipeline, wherein the water inlet end of the blending pump is connected with the fertilizer liquid supply pipeline and the water source pipeline, the water outlet end of the blending pump is connected with the drip irrigation pipeline, the blending pump is electrically connected with the water and fertilizer control device so as to be opened and closed under the control of the water and fertilizer control device, and the drip irrigation pipeline extends to the field so as to perform drip irrigation; the drip irrigation pipeline is provided with a water pressure sensor and a plurality of branch pipes, the branch pipes extend to different plots respectively, each branch pipe is provided with a check valve, and the check valves and the water pressure sensor are in communication connection with the water and fertilizer control device through a wireless communication module so as to adjust the flow of the corresponding branch pipe under the control of the water and fertilizer control device; the power module comprises a solar power generation module, a hydroelectric power generation assembly and a power storage module, wherein the hydroelectric power generation assembly is arranged on a drip irrigation pipeline to generate power by utilizing water flow in the drip irrigation pipeline, the power generation module and the hydroelectric power generation assembly are electrically connected with the power storage module, and the power storage module is electrically connected with the data processor, the throttle valve and the water pressure sensor respectively to supply power.
In one possible implementation manner, the climate data acquisition device comprises an air temperature and humidity acquisition module, a precipitation acquisition module, an illumination radiation acquisition module and a wind power wind direction acquisition module, wherein the air temperature and humidity acquisition module, the precipitation acquisition module, the illumination radiation acquisition module and the wind power wind direction acquisition module are all in communication connection with the communication device so as to transmit acquired air temperature and humidity data, precipitation data, illumination radiation data and wind power wind direction data to the cloud server; the fertilizer liquid supply device is also provided with at least one fertilizer dissolution stirring barrel, and the fertilizer dissolution stirring barrels are arranged in one-to-one correspondence with the fertilizer liquid supply pipelines and are used for conveying out the fertilizer after the fertilizer is prepared into fertilizer liquid through the fertilizer liquid supply pipelines; the field accurate liquid manure management system based on computer deep learning still includes well accuse operation panel, and air temperature humidity collection module, precipitation collection module, illumination radiation collection module, wind-force wind direction collection module, fertilizer dissolve agitator and liquid manure controlling means all establish on well accuse operation panel, still are equipped with the display on the well accuse operation panel, and crop image collection module and display all are connected with communication device communication in order to carry out data interaction.
In one possible implementation manner, the central control console is further provided with a screen bracket, the display is arranged on the screen bracket, the crop image acquisition module and the wind power and wind direction acquisition module are arranged at the top of the screen bracket, a desk plate is arranged at the position, below the display, of the middle part of the screen bracket, a sunshade net is arranged at the position, below one side of the display, of the screen bracket, and a right-angle space for placing a computer is formed by the display, the sunshade net and the desk plate; the desk plate and the sunshade net are both of folding structures; the outer end contact of the table plate and the sunshade net are connected with each other to form a support.
In one possible implementation manner, the edge of one side of the desk plate is rotationally connected with the screen bracket, a jack is arranged at the joint of the desk plate and the sunshade net, a clamping groove is arranged on the side wall of the jack, a power socket is arranged on the desk plate, a contact switch is arranged at the upward position of the side wall of the clamping groove, the contact switch is connected with the power socket, the power socket is powered on after the contact switch is triggered, and the power socket is not powered on when the contact switch is not triggered; sunshade net includes articulated pole and screen cloth, and articulated pole upper end is articulated with the screen support, and the net is laid between articulated pole and screen support, and with articulated pole and screen support connection respectively, articulated pole lower extreme be equipped with jack complex inserted bar, be equipped with on the inserted bar be used for triggering contact switch's joint arch, wherein, articulated pole drives the screen cloth and expandes the back, in the inserted bar inserts the jack, makes the joint arch get into the joint groove to trigger contact switch and with the inserted bar card in the jack simultaneously.
In one possible implementation, the cloud server includes a central server and an edge node server, the edge node server is connected to the central server for data interaction, and the communication device is connected to the edge node server for data interaction.
The field accurate water and fertilizer management method based on computer deep learning provided by the invention has the beneficial effects that: compared with the prior art, the method has the advantages that the weather and climate data, the apparent state data of crops and the data capable of being manually controlled through water and fertilizer management are collected, all conditions required by crop growth are basically contained, the data are modeled and analyzed through a computer deep learning mode, the water and fertilizer in the field can be accurately managed through a water and fertilizer control device in the field, the water and fertilizer management is more and more accurate along with the accumulation of the data, meanwhile, the generation and the use of a control model are separated, the control model is generated and optimized through the strong calculation force of the central server of the cloud server, the data calculation and the generation of control instructions are performed through the edge node server by using the control model, the feedback time of the data can be greatly shortened, the water and fertilizer control delay caused by network delay is avoided, and the water and fertilizer can be more or less applied, so that the water and fertilizer can be more accurately controlled; and the cloud server is utilized to easily realize remote control, so that the water and fertilizer management of a field is facilitated.
The field accurate water and fertilizer management system based on computer deep learning provided by the invention has the beneficial effects that: compared with the prior art, the system has the advantages that the field data acquisition device, the crop image acquisition module and the climate data acquisition device are used for acquiring weather and climate data, apparent state data of crops and data which can be manually controlled through water and fertilizer management, the data are transmitted to the cloud server through the communication device to be calculated, remote control is facilitated, the calculation force of the cloud server can be relied on, modeling analysis can be better performed on the data by utilizing a computer deep learning mode, so that a more accurate control command is obtained, and the control command is executed by utilizing the water flow control valve of a water source pipeline and the fertilizer flow control valve of a fertilizer and liquid supply device, so that accurate water and fertilizer management of a field is realized; meanwhile, the data of the field data acquisition device 10 are acquired through the wireless communication module, so that a large number of data wires can be saved, the overall wiring quantity is improved, the simplicity and the stability of the wires are improved, and the use safety is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a field accurate water and fertilizer management method based on computer deep learning according to an embodiment of the invention;
fig. 2 is a schematic layout structure diagram of a field precise water and fertilizer management system based on computer deep learning according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a connection state of a control part of a field precise water and fertilizer management system based on computer deep learning according to an embodiment of the present invention, wherein a dotted line represents wireless communication connection;
fig. 4 is a schematic diagram of a front view structure of a table board part of a field accurate water and fertilizer management system based on computer deep learning according to an embodiment of the present invention;
fig. 5 is a partial enlarged view of fig. 4.
Wherein, each reference sign is as follows in the figure:
10. a field data acquisition device;
20. a water source pipeline; 21. a water flow control valve;
31. a fertilizer flow control valve; 32. a fertilizer liquid supply pipe; 33. a fertilizer dissolving and stirring barrel;
40. a water and fertilizer control device; 50. a communication device; 60. a blending pump;
70. a drip irrigation pipeline; 71. a throttle valve; 72. a water pressure sensor; 73. a hydro-power generation assembly;
80. a central control console; 81. the crop image acquisition module; 82. a display;
83. the wind power and wind direction acquisition module; 84. a precipitation amount acquisition module; 85. a screen bracket;
86. a table plate; 861. a jack; 862. a clamping groove; 863. a power socket; 864. a contact switch;
87. sunshade net; 871. a hinge rod; 872. a mesh cloth; 873. a rod; 874. the clamping bulge;
91. a central server; 92. edge node servers.
Detailed Description
In order to make the technical problems, technical schemes and beneficial effects to be solved more clear, the invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The field accurate water and fertilizer management method and system based on computer deep learning provided by the invention are now described.
Referring to fig. 1, the field accurate water and fertilizer management method based on computer deep learning provided by the first embodiment of the invention comprises the following steps:
s1, acquiring field data in a period T1 by using a sensor, wherein the field data comprise natural climate data, apparent contrast data and adjustable data, the natural climate data are weather and climate data, the apparent contrast data are apparent state data of crops, and the adjustable data are data which can be manually controlled through water and fertilizer management;
s2, selecting an edge node server with the fastest response from the cloud servers as a first edge node server by using the controller;
s3, transmitting field data of the period T1 to a first edge node server, and enabling the first edge node server to give a control instruction of the period T1 according to the field data and transmit the control instruction to a field water and fertilizer control device so as to control water and fertilizer applied to a field;
s4, the first edge node server transmits field data of the period T1 and control instructions of the period T1 to a central server of the cloud server, the central server adopts a deep learning method, and carries out training learning by combining historical data of the field data to obtain a T1 control model for controlling water and fertilizer of crops, wherein the historical data is all historical statistical data before the field data of the period T1;
s5, the T1 control model is returned to the first edge node server;
s6, collecting field data of a T2 period, transmitting the field data to a first edge node server, giving a control instruction of the T2 period according to calculation of a T1 control model, and transmitting the control instruction to a field water and fertilizer control device to control water and fertilizer applied to a field;
s7, repeating the steps S4-S6 until the field water and fertilizer management work is finished.
Compared with the prior art, the accurate water and fertilizer management method for the field based on the computer deep learning basically comprises all conditions required by the growth of crops by collecting weather and climate data, apparent state data of the crops and data capable of being manually controlled through water and fertilizer management, and then the data are modeled and analyzed in a computer deep learning mode, the water and fertilizer in the field can be accurately managed through a water and fertilizer control device for the field, and the water and fertilizer management becomes more and more accurate along with the accumulation of the data, meanwhile, the generation and the use of a control model are separated, the control model is generated and optimized by utilizing the strong calculation force of the central server of the cloud server, the data calculation and the control instruction generation are performed by utilizing the edge node server, the data feedback time can be greatly shortened, the water and fertilizer control delay caused by network delay is avoided, and the water and fertilizer can be more accurately controlled; and the cloud server is utilized to easily realize remote control, so that the water and fertilizer management of a field is facilitated.
The invention further provides a specific embodiment based on the first embodiment, which is as follows:
in S1, natural climate data comprise air temperature and humidity data, precipitation data, light radiation data and wind direction data, apparent control data comprise crop image information data, and adjustable data comprise soil moisture content data, soil temperature data, soil EC conductivity data, soil PH value data, soil quick-acting nitrogen, phosphorus and potassium nutrient content data and blade temperature and humidity data.
In S4, the control step of generating the T1 control model includes:
selecting apparent contrast data corresponding to the optimal growth state of crops in historical data of field data, and combining the apparent contrast data with corresponding natural climate data and adjustable data to generate climate-apparent-adjustable relation mapping; selecting apparent control data corresponding to different growth states of crops in historical data of field data, and combining the apparent control data with corresponding adjustable data to generate apparent-adjustable relation mapping;
after the field data of the period T1 are acquired, natural climate data closest to natural climate data in the field data of the period T1 are found in the climate-apparent-regulation relation mapping, and apparent control data and regulatable data corresponding to the natural climate data are found;
respectively finding apparent control data closest to apparent control data in field data of a T1 period in an apparent-regulation relation map by using a neural network method, continuously finding corresponding regulatable data, and supplementing the field data of the T1 period into the apparent-regulation relation map;
according to the difference value between the adjustable data found in the climate-apparent-regulation relation mapping and the adjustable data found in the apparent-regulation relation mapping, the control instruction of the field water and fertilizer control device is given by combining the area parameter of the land block;
and generating a control model in the control step to obtain the T1 control model.
Referring to fig. 2 and fig. 3 together, the field precise water and fertilizer management system based on computer deep learning provided in the second embodiment of the present invention is configured to apply the above field precise water and fertilizer management method based on computer deep learning, and includes a field data acquisition device 10, a crop image acquisition module 81, a climate data acquisition device, a water source pipeline 20, a fertilizer liquid supply device, a water and fertilizer control device 40, a cloud server and a communication device 50, where the field data acquisition device 10 is configured to acquire field data; the crop image acquisition module 81 is used for acquiring images of field crops; the climate data acquisition device is used for acquiring climate data; the water source pipeline 20 is provided with a water flow control valve 21 for supplying water to the field; the fertilizer liquid supply device comprises a fertilizer dissolving stirring barrel 33, a fertilizer liquid supply pipeline 32 connected with the fertilizer dissolving stirring barrel 33 and a fertilizer liquid flow control valve 31 arranged on the fertilizer liquid supply pipeline 32 so as to supply fertilizer liquid into the field; the water and fertilizer control device 40 is electrically connected with the water flow control valve 21 and the fertilizer flow control valve 31 respectively so as to control the actions of the water flow control valve 21 and the fertilizer flow control valve 31; the cloud server is used for carrying out data processing; the communication device 50 is respectively in communication connection with the water and fertilizer control device 40 and the cloud server, and is in communication connection with the field data acquisition device 10 through a wireless communication module, and is used for receiving signals transmitted by the field data acquisition device 10 and then transmitting the signals to the cloud server, and receiving data signals of the cloud server and then transmitting the data signals to the water and fertilizer control device 40.
Compared with the prior art, the field precise water and fertilizer management method based on computer deep learning is characterized in that the field data acquisition device 10, the crop image acquisition module 81 and the climate data acquisition device acquire weather and climate data, apparent state data of crops and data which can be manually controlled through water and fertilizer management, the communication device 50 transmits the data to the cloud server for calculation, remote control is facilitated, the calculation force of the cloud server can be relied on, modeling analysis can be better performed on the data in a computer deep learning mode, so that a more precise control command is obtained, and the water flow control valve 21 of the water source pipeline 20 and the fertilizer flow control valve 31 of the fertilizer and liquid supply device are utilized for executing the control command, so that the field precise water and fertilizer management is realized; meanwhile, the data of the field data acquisition device 10 are acquired through the wireless communication module, so that a large number of data wires can be saved, the overall wiring quantity is improved, the simplicity and the stability of the wires are improved, and the use safety is improved.
Referring to fig. 2 and 3, an embodiment of the present invention based on the first embodiment is as follows:
the field data acquisition device 10 comprises a soil moisture content sensor for detecting soil moisture content, a soil EC conductivity acquisition module for detecting soil EC conductivity, a soil PH value acquisition module for detecting soil PH value, a soil temperature acquisition module for detecting soil temperature, a nutrient content acquisition module for detecting quick-acting nitrogen, phosphorus and potassium nutrient content of soil, a blade temperature and humidity acquisition module for detecting blade temperature and humidity, a data processor for processing data and a field power supply module for supplying power, wherein the data processor is respectively and electrically connected with the soil moisture content sensor, the soil EC conductivity acquisition module, the soil PH value acquisition module, the soil temperature acquisition module, the nutrient content acquisition module and the blade temperature and humidity acquisition module and is in communication connection with the communication device 50 through a wireless communication module so as to transmit acquired data signals to the communication device 50; the field power module is electrically connected with the data processor to supply power.
The accurate water and fertilizer management system of the field based on the computer deep learning further comprises a blending pump 60 and a drip irrigation pipeline 70, wherein the water inlet end of the blending pump 60 is connected with the fertilizer liquid supply pipeline 32 and the water source pipeline 20, the water outlet end of the blending pump 60 is connected with the drip irrigation pipeline 70, and the blending pump 60 is electrically connected with the water and fertilizer control device 40 so as to be opened and closed under the control of the water and fertilizer control device 40, and the drip irrigation pipeline 70 extends to the field so as to perform drip irrigation; the drip irrigation pipeline 70 is provided with a water pressure sensor 72 and a plurality of branch pipes, the branch pipes extend to different plots respectively, each branch pipe is provided with a check valve 71, and the check valves 71 and the water pressure sensor 72 are in communication connection with the water and fertilizer control device 40 through a wireless communication module so as to adjust the flow of the corresponding branch pipe under the control of the water and fertilizer control device 40; the power module comprises a solar power generation module, a hydroelectric power generation assembly 73 and a power storage module, wherein the hydroelectric power generation assembly 73 is arranged on the drip irrigation pipeline 70 to generate power by utilizing water flow in the drip irrigation pipeline 70, the power generation module and the hydroelectric power generation assembly 73 are electrically connected with the power storage module, and the power storage module is electrically connected with the data processor, the throttle valve 71 and the water pressure sensor 72 respectively to supply power.
The climate data acquisition device comprises an air temperature and humidity acquisition module, a precipitation acquisition module 84, an illumination radiation acquisition module and a wind power wind direction acquisition module 83, wherein the air temperature and humidity acquisition module, the precipitation acquisition module 84, the illumination radiation acquisition module and the wind power wind direction acquisition module 83 are all in communication connection with the communication device 50 so as to transmit acquired air temperature and humidity data, precipitation data, illumination radiation data and wind power wind direction data to the cloud server; the fertilizer liquid supply device is also provided with at least one fertilizer dissolving stirring barrel 33, and the fertilizer dissolving stirring barrels 33 are arranged in one-to-one correspondence with the fertilizer liquid supply pipelines 32 and are used for conveying out fertilizer through the fertilizer liquid supply pipelines 32 after fertilizer is prepared into fertilizer liquid; the field accurate liquid manure management system based on computer deep learning still includes well accuse operation panel 80, and air temperature humidity collection module, precipitation collection module 84, illumination radiation collection module, wind-force wind direction collection module 83, fertilizer dissolve agitator 33 and liquid manure controlling means 40 all establish on well accuse operation panel 80, still are equipped with display 82 on the well accuse operation panel 80, and crop image collection module 81 and display 82 all are connected with communication device 50 communication in order to carry out data interaction.
The cloud server includes a central server 91 and an edge node server 92, the edge node server 92 is connected to the central server 91 for data interaction, and the communication device 50 is connected to the edge node server 92 for data interaction.
Referring to fig. 2 to 5, an embodiment of the present invention based on the first embodiment is as follows:
the center control console 80 is also provided with a screen bracket 85, the display 82 is arranged on the screen bracket 85, and the crop image acquisition module 81 and the wind direction acquisition module 83 are arranged on the top of the screen bracket 85.
Because the field has no position for office use, in order to facilitate the use of equipment such as computers and the like by scientific researchers, a desk plate 86 is arranged at the position of the middle part of the screen support 85 below the display 82, a sunshade net 87 is arranged at the position of the screen support 85 at one side of the display 82, and the display 82, the sunshade net 87 and the desk plate 86 form a right-angle space for placing the computers; the table 86 and the sunshade net 87 are both folded; the outer end contact of the table 86 and the sunshade screen 87 are connected to each other to form a support so that a researcher can acquire a position for operating a computer to regulate and control the whole equipment and prevent strong light from affecting the display of a computer screen in the daytime.
The edge of one side of the table plate 86 is rotationally connected with the screen bracket 85, a jack 861 is arranged at the joint of the table plate 86 and the sunshade net 87, a clamping groove 862 is arranged on the side wall of the jack 861, a power socket 863 is arranged on the table plate 86, a contact switch 864 is arranged at the upward side wall of the clamping groove 862, the contact switch 864 is connected with the power socket 863, the power socket 863 is powered on after the contact switch 864 is triggered, and the power socket 863 is not powered on when the contact switch 864 is not triggered; sunshade screen 87 includes articulated pole 871 and screen cloth 872, articulated pole 871 upper end and screen support 85 are articulated, screen cloth 872 establishes between articulated pole 871 and screen support 85, and be connected with articulated pole 871 and screen support 85 respectively, articulated pole 871 lower extreme is equipped with the inserted bar 873 with jack 861 complex, be equipped with the joint protruding 874 that is used for triggering contact switch 864 on the inserted bar 873, wherein, after articulated pole 871 drove screen cloth 872 and expand, inserted bar 873 inserts in jack 861, makes joint protruding 874 get into joint groove 862, and trigger contact switch 864 and block inserted bar 873 in jack 861 simultaneously.
When the computer desk is used, after the desk plate 86 and the hinging rod 871 are connected, the screen cloth 872 of the display 82 and the sunshade net 87 and the desk plate 86 form a right-angle space for placing a computer, strong sunlight can be shielded, the strong light is prevented from influencing the operation of the computer, meanwhile, the hinging rod 871 is pressed down by the gravity of the computer, the clamping protrusion 874 can be clamped in the clamping groove 862, the inserting rod 873 on the hinging rod 871 can be prevented from being separated, the contact switch 864 can be kept in a trigger state all the time, and the power socket 863 can supply power for the computer; and after the table 86 and the hinge rod 871 are retracted, the power socket is automatically powered off, so that the danger caused by rainwater entering the power socket is avoided.
Further, a screen safety switch is further provided at the connection between the hinge rod 871 and the screen support 85, and the screen safety switch is connected with the display 82, and is triggered to be turned on when the hinge rod 871 is in a natural sagging state, so that the display 82 is turned on, and is turned off when the hinge rod 871 is opened, so that the risk of the display 82 being electrically connected when a scientific research person works on the desk plate 86 is avoided.
In order to avoid rainwater entering the contact switch 864 to cause connection, the jack 861 can be obliquely arranged in the table 86, so that the inside of the jack 861 is higher than the outer end after the table 86 is not used and naturally sags, rainwater is prevented from flowing in, and water entering the jack is also conveniently discharged.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (5)
1. Accurate liquid manure management system in field based on computer degree of depth study, its characterized in that includes:
the field data acquisition device (10) is used for acquiring field data;
the crop image acquisition module (81) is used for acquiring images of field crops;
the climate data acquisition device is used for acquiring climate data;
a water source pipeline (20) provided with a water flow control valve (21) for supplying water to the field;
a fertilizer liquid supply device comprising a fertilizer dissolving stirring barrel (33), a fertilizer liquid supply pipeline (32) connected with the fertilizer dissolving stirring barrel (33) and a fertilizer liquid flow control valve (31) arranged on the fertilizer liquid supply pipeline (32) so as to supply fertilizer liquid into a field;
a water and fertilizer control device (40) which is electrically connected with the water flow control valve (21) and the fertilizer flow control valve (31) respectively so as to control the actions of the water flow control valve (21) and the fertilizer flow control valve (31);
the cloud server is used for carrying out data processing;
the communication device (50) is respectively in communication connection with the water and fertilizer control device (40) and the cloud server, is in communication connection with the field data acquisition device (10) through a wireless communication module, and is used for receiving signals transmitted by the field data acquisition device (10) and then transmitting the signals to the cloud server, and receiving data signals of the cloud server and then transmitting the data signals to the water and fertilizer control device (40);
the field data acquisition device (10) comprises a soil moisture content sensor for detecting soil moisture content, a soil EC conductivity acquisition module for detecting soil EC conductivity, a soil PH value acquisition module for detecting soil PH value, a soil temperature acquisition module for detecting soil temperature, a nutrient content acquisition module for detecting quick-acting nitrogen, phosphorus and potassium nutrient content of soil, a blade temperature and humidity acquisition module for detecting blade temperature and humidity, a data processor for processing data and a field power supply module for supplying power, wherein the data processor is respectively connected with the soil moisture content sensor, the soil EC conductivity acquisition module, the soil PH value acquisition module, the soil temperature acquisition module, the nutrient content acquisition module and the blade temperature and humidity acquisition module and is in communication connection with the communication device (50) through a wireless communication module so as to transmit acquired data signals to the communication device (50); the field power supply module is electrically connected with the data processor to supply power;
the field accurate water and fertilizer management system based on computer deep learning further comprises a blending pump (60) and a drip irrigation pipeline (70), wherein the water inlet end of the blending pump (60) is connected with the fertilizer liquid supply pipeline (32) and the water source pipeline (20), the water outlet end of the blending pump is connected with the drip irrigation pipeline (70), the blending pump (60) is electrically connected with the water and fertilizer control device (40) so as to be opened and closed under the control of the water and fertilizer control device (40), and the drip irrigation pipeline (70) extends to the field to perform drip irrigation; the drip irrigation pipeline (70) is provided with a water pressure sensor (72) and a plurality of branch pipes, the branch pipes extend to different plots respectively, each branch pipe is provided with a throttle valve (71), and the throttle valves (71) and the water pressure sensor (72) are in communication connection with the water and fertilizer control device (40) through a wireless communication module so as to regulate the flow of the corresponding branch pipe under the control of the water and fertilizer control device (40); the power supply module comprises a solar power generation module, a hydroelectric power generation assembly (73) and a power storage module, wherein the hydroelectric power generation assembly (73) is arranged on the drip irrigation pipeline (70) to generate power by utilizing water flow in the drip irrigation pipeline (70), the power generation module and the hydroelectric power generation assembly (73) are electrically connected with the power storage module, and the power storage module is electrically connected with the data processor, the throttle valve (71) and the water pressure sensor (72) respectively to supply power;
the climate data acquisition device comprises an air temperature and humidity acquisition module, a precipitation acquisition module (84), an illumination radiation acquisition module and a wind power wind direction acquisition module (83), wherein the air temperature and humidity acquisition module, the precipitation acquisition module (84), the illumination radiation acquisition module and the wind power wind direction acquisition module (83) are all in communication connection with the communication device (50) so as to transmit acquired air temperature and humidity data, precipitation data, illumination radiation data and wind power wind direction data to a cloud server; the fertilizer liquid supply device is also provided with at least one fertilizer dissolving stirring barrel (33), and the fertilizer dissolving stirring barrels (33) are arranged in one-to-one correspondence with the fertilizer liquid supply pipelines (32) and are used for conveying out fertilizer through the fertilizer liquid supply pipelines (32) after fertilizer is prepared into fertilizer liquid; the field accurate water and fertilizer management system based on computer deep learning further comprises a central control operation table (80), wherein the air temperature and humidity acquisition module, the precipitation amount acquisition module (84), the illumination radiation acquisition module, the wind power and wind direction acquisition module (83), the fertilizer dissolving and stirring barrel (33) and the water and fertilizer control device (40) are all arranged on the central control operation table (80), a display (82) is further arranged on the central control operation table (80), and the crop image acquisition module (81) and the display (82) are all in communication connection with the communication device (50) for data interaction;
the central control operation table (80) is further provided with a screen support (85), the display (82) is arranged on the screen support (85), the crop image acquisition module (81) and the wind power and wind direction acquisition module (83) are arranged at the top of the screen support (85), a table plate (86) is arranged at the position, below the display (82), of the middle part of the screen support (85), a sunshade net (87) is arranged at the position, below the display (82), of the screen support (85), and the display (82), the sunshade net (87) and the table plate (86) form a right-angle space for placing a computer; the table plate (86) and the sunshade net (87) are of folding structures; the outer end contact of the table plate (86) and the sunshade net (87) are connected with each other to form a support;
the edge of one side of the table plate (86) is rotationally connected with the screen bracket (85), a jack (861) is arranged at the joint of the table plate (86) and the sunshade net (87), a clamping groove (862) is formed in the side wall of the jack (861), a power socket (863) is arranged on the table plate (86), a contact switch (864) is arranged at the upward side wall of the clamping groove (862), the contact switch (864) is connected with the power socket (863), the power socket (863) is powered on after the contact switch (864) is triggered, and the power socket (863) is not powered on when the contact switch (864) is not triggered; sunshade net (87) include articulated pole (871) and screen cloth (872), articulated pole (871) upper end with screen support (85) are articulated, screen cloth (872) are established articulated pole (871) with between screen support (85), and respectively with articulated pole (871) with screen support (85) are connected, articulated pole (871) lower extreme be equipped with jack (861) complex inserted bar (873), be equipped with on inserted bar (873) and be used for triggering joint protruding (874) of contact switch (864), wherein, articulated pole (871) drive after screen cloth (872) are expanded, inserted bar (873) inserts in jack (861), make joint protruding (874) get into joint groove (862), and trigger contact switch (864) will simultaneously inserted bar (873) card in jack (861).
2. The field-accurate water and fertilizer management system based on computer deep learning of claim 1, wherein: the cloud server comprises a central server (91) and an edge node server (92), the edge node server (92) is connected with the central server (91) for data interaction, and the communication device (50) is connected with the edge node server (92) for data interaction.
3. The field accurate water and fertilizer management method based on computer deep learning is characterized in that the field accurate water and fertilizer management system based on computer deep learning as claimed in claim 1 or 2 is adopted, and the method comprises the following steps:
s1, acquiring field data in a period T1 by using a sensor, wherein the field data comprise natural climate data, apparent control data and adjustable data, the natural climate data are weather and climate data, the apparent control data are apparent state data of crops, and the adjustable data are data which can be manually controlled through water and fertilizer management;
s2, selecting an edge node server with the fastest response from the cloud servers as a first edge node server by using the controller;
s3, transmitting field data of the period T1 to a first edge node server, giving a control instruction of the period T1 according to the field data by the first edge node server, and transmitting the control instruction to a field water and fertilizer control device so as to control water and fertilizer applied to a field;
s4, the first edge node server transmits field data of the period T1 and control instructions of the period T1 to a central server of the cloud server, the central server adopts a deep learning method, and carries out training learning by combining historical data of the field data to obtain a T1 control model for controlling water and fertilizer of crops, wherein the historical data is all historical statistical data before the field data of the period T1;
s5, the T1 control model is returned to the first edge node server;
s6, collecting field data of a T2 period, transmitting the field data to the first edge node server, giving a control instruction of the T2 period according to calculation of a T1 control model, and transmitting the control instruction to a field water and fertilizer control device to control water and fertilizer applied to a field;
s7, repeating the steps S4-S6 until the field water and fertilizer management work is finished.
4. The field accurate water and fertilizer management method based on computer deep learning as set forth in claim 3, wherein: in S1, natural climate data comprise air temperature and humidity data, precipitation data, light radiation data and wind direction data, apparent control data comprise crop image information data, and adjustable data comprise soil moisture content data, soil temperature data, soil EC conductivity data, soil PH value data, soil quick-acting nitrogen, phosphorus and potassium nutrient content data and blade temperature and humidity data.
5. The field-accurate water and fertilizer management method based on computer deep learning of claim 4, wherein in S4, the control step of generating the T1 control model includes:
selecting apparent contrast data corresponding to the optimal growth state of crops in historical data of field data, and combining the apparent contrast data with corresponding natural climate data and adjustable data to generate climate-apparent-adjustable relation mapping; selecting apparent control data corresponding to different growth states of crops in historical data of field data, and combining the apparent control data with corresponding adjustable data to generate apparent-adjustable relation mapping;
after the field data of the period T1 are acquired, natural climate data closest to natural climate data in the field data of the period T1 are found in the climate-apparent-regulation relation mapping, and apparent control data and regulatable data corresponding to the natural climate data are found;
respectively finding apparent control data closest to apparent control data in field data of a T1 period in an apparent-regulation relation map by using a neural network method, continuously finding corresponding regulatable data, and supplementing the field data of the T1 period into the apparent-regulation relation map;
according to the difference value between the adjustable data found in the climate-apparent-regulation relation mapping and the adjustable data found in the apparent-regulation relation mapping, the control instruction of the field water and fertilizer control device is given by combining the area parameter of the land block;
and generating a control model in the control step to obtain the T1 control model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210772568.XA CN114902854B (en) | 2022-06-30 | 2022-06-30 | Accurate water and fertilizer management method and system for field based on computer deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210772568.XA CN114902854B (en) | 2022-06-30 | 2022-06-30 | Accurate water and fertilizer management method and system for field based on computer deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114902854A CN114902854A (en) | 2022-08-16 |
| CN114902854B true CN114902854B (en) | 2023-08-29 |
Family
ID=82772490
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210772568.XA Active CN114902854B (en) | 2022-06-30 | 2022-06-30 | Accurate water and fertilizer management method and system for field based on computer deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114902854B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109168535A (en) * | 2018-09-21 | 2019-01-11 | 山东省农业机械科学研究院 | A kind of accurate administration system of water-fertilizer-pesticide based on Internet of Things and method |
| CN109392676A (en) * | 2018-12-13 | 2019-03-01 | 黑龙江大学 | A kind of system of the cloud algorithm platform control fertigation based on block chain structure |
| CN109673480A (en) * | 2019-02-22 | 2019-04-26 | 福州阿里他巴信息科技有限公司 | Intelligent water and fertilizer integrated sprinkling irrigation system and control method |
| CN209299722U (en) * | 2018-11-14 | 2019-08-27 | 山东省农业机械科学研究院 | A kind of intelligent and high-efficiency water-fertilizer-pesticide integral system |
| CN112450056A (en) * | 2019-09-09 | 2021-03-09 | 云南天质弘耕科技有限公司 | Water, fertilizer and pesticide integrated intelligent irrigation system based on machine learning algorithm |
| CN113439520A (en) * | 2021-07-21 | 2021-09-28 | 中国农业科学院农业环境与可持续发展研究所 | Intelligent decision-making method and system for crop irrigation and fertilization |
| CN114287220A (en) * | 2021-12-14 | 2022-04-08 | 中天水土治理科技(山东)股份有限公司 | Intelligent irrigation system and method based on water and fertilizer integration |
| CN114647192A (en) * | 2022-04-08 | 2022-06-21 | 河北省农林科学院农业资源环境研究所 | Intelligent field water and fertilizer control method and system based on convolutional neural network |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10716269B2 (en) * | 2008-08-12 | 2020-07-21 | Rain Bird Corporation | Methods and systems for irrigation control |
| WO2018222875A1 (en) * | 2017-06-01 | 2018-12-06 | Valmont Industries, Inc. | System and method for irrigation management using machine learning workflows |
| US11833313B2 (en) * | 2018-08-17 | 2023-12-05 | Hortau Inc. | Systems and methods for monitoring and regulating plant productivity |
| WO2022020367A1 (en) * | 2020-07-20 | 2022-01-27 | Psimos, Inc | Smart fertilizer delivery system |
-
2022
- 2022-06-30 CN CN202210772568.XA patent/CN114902854B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109168535A (en) * | 2018-09-21 | 2019-01-11 | 山东省农业机械科学研究院 | A kind of accurate administration system of water-fertilizer-pesticide based on Internet of Things and method |
| CN209299722U (en) * | 2018-11-14 | 2019-08-27 | 山东省农业机械科学研究院 | A kind of intelligent and high-efficiency water-fertilizer-pesticide integral system |
| CN109392676A (en) * | 2018-12-13 | 2019-03-01 | 黑龙江大学 | A kind of system of the cloud algorithm platform control fertigation based on block chain structure |
| CN109673480A (en) * | 2019-02-22 | 2019-04-26 | 福州阿里他巴信息科技有限公司 | Intelligent water and fertilizer integrated sprinkling irrigation system and control method |
| CN112450056A (en) * | 2019-09-09 | 2021-03-09 | 云南天质弘耕科技有限公司 | Water, fertilizer and pesticide integrated intelligent irrigation system based on machine learning algorithm |
| CN113439520A (en) * | 2021-07-21 | 2021-09-28 | 中国农业科学院农业环境与可持续发展研究所 | Intelligent decision-making method and system for crop irrigation and fertilization |
| CN114287220A (en) * | 2021-12-14 | 2022-04-08 | 中天水土治理科技(山东)股份有限公司 | Intelligent irrigation system and method based on water and fertilizer integration |
| CN114647192A (en) * | 2022-04-08 | 2022-06-21 | 河北省农林科学院农业资源环境研究所 | Intelligent field water and fertilizer control method and system based on convolutional neural network |
Non-Patent Citations (1)
| Title |
|---|
| 基于ＰＳＯ－ＢＰ优化ＰＩＤ模型的水肥控制系统研究;宋卓研等;中国农机化学报;第42卷(第9期);第83-89页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114902854A (en) | 2022-08-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108156918B (en) | Large-scale farmland wireless Internet of things intelligent drip irrigation system and method | |
| CN109168535B (en) | Water and fertilizer accurate application system and method based on Internet of things | |
| CN205584783U (en) | All -weather wireless Intelligence irrigation and fertilization system | |
| CN103548621B (en) | Greenhouse by solar heat close type cultivation system and method | |
| CN107317937A (en) | A kind of three-dimensional agriculture planting shed long-distance management system based on mobile phone A PP | |
| CN109392676A (en) | A kind of system of the cloud algorithm platform control fertigation based on block chain structure | |
| CN110122024A (en) | A kind of intelligent integral fertilization system for applying biogas slurry | |
| CN104267699A (en) | Agricultural greenhouse intelligent control device based on Internet of things technology and working method thereof | |
| CN110488891A (en) | A kind of solar energy accurate remote irrigation system of Internet of Things | |
| CN109601334A (en) | Liquid manure drip irrigation system based on Internet of Things | |
| CN207885191U (en) | A kind of field irrigation system | |
| CN101430552A (en) | Automatic control system for greenhouse culture environment | |
| CN207053612U (en) | A kind of three-dimensional agriculture planting shed long-distance management system based on cell phone application | |
| CN103461077A (en) | Method for determining theoretical water irrigation quantity of flue-cured tobacco irrigation and tobacco field irrigation guide device | |
| CN214339200U (en) | Agricultural liquid manure integration intelligent integrated operation and maintenance system | |
| CN213044174U (en) | Intelligent water and fertilizer integrated machine | |
| CN108668865A (en) | A kind of Internet of Things intelligent irrigation total management system | |
| CN211745617U (en) | Intelligent maintenance device for vegetation of green building | |
| CN107396676A (en) | A kind of intelligent greenhouse for planting vegetable | |
| CN111427404A (en) | Agricultural greenhouse environment control system based on 5G network | |
| CN114902854B (en) | Accurate water and fertilizer management method and system for field based on computer deep learning | |
| CN208490387U (en) | A kind of sweet osmanthus height of seedling survival rate cuttage and seedling culture device | |
| CN204613723U (en) | Novel intelligent irrigation system | |
| CN210008361U (en) | Intelligent irrigation management and control system based on Internet of things | |
| CN109379961A (en) | A kind of solar energy radio automatic irrigation system and its method |
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 |