CN113273449A - Digital twin body construction method for precise monitoring of sunlight greenhouse - Google Patents

Digital twin body construction method for precise monitoring of sunlight greenhouse Download PDF

Info

Publication number
CN113273449A
CN113273449A CN202110523825.1A CN202110523825A CN113273449A CN 113273449 A CN113273449 A CN 113273449A CN 202110523825 A CN202110523825 A CN 202110523825A CN 113273449 A CN113273449 A CN 113273449A
Authority
CN
China
Prior art keywords
sunlight greenhouse
digital twin
greenhouse
monitoring
sunlight
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110523825.1A
Other languages
Chinese (zh)
Inventor
乐章燕
耿雪莹
任武
石茗化
周鹏
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.)
Langfang Meteorological Bureau
Original Assignee
Langfang Meteorological Bureau
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 Langfang Meteorological Bureau filed Critical Langfang Meteorological Bureau
Priority to CN202110523825.1A priority Critical patent/CN113273449A/en
Publication of CN113273449A publication Critical patent/CN113273449A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • AHUMAN NECESSITIES
    • A01AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01GHORTICULTURE; CULTIVATION OF VEGETABLES, FLOWERS, RICE, FRUIT, VINES, HOPS OR SEAWEED; FORESTRY; WATERING
    • A01G22/00Cultivation of specific crops or plants not otherwise provided for
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01DMEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
    • G01D21/00Measuring or testing not otherwise provided for
    • G01D21/02Measuring two or more variables by means not covered by a single other subclass

Abstract

A digital twin body construction method for precise monitoring of a sunlight greenhouse comprises the following three steps: the method comprises the following steps of firstly, preparing, carrying out early-stage information acquisition and making a digital twinning sunlight greenhouse scheme; secondly, constructing a digital twin sunlight greenhouse, wherein the digital twin sunlight greenhouse comprises a digitization process, a standardization process and an intellectualization process; and thirdly, operation and maintenance are carried out, and expansion, feedback and optimization are carried out on the constructed digital twin body. The invention can realize the automatic real-time acquisition, display and modeling analysis of multi-environment element data, and support the automatic linkage regulation and control according to the early warning rule, thereby achieving the effects of improving the crop yield, reducing the operation and management cost, improving the disaster risk resistance, optimizing the management mode and enhancing the automatic management and control capability of the greenhouse.

Description

Digital twin body construction method for precise monitoring of sunlight greenhouse
Technical Field
The invention relates to the technical field of automatic environment monitoring, in particular to a digital twin body construction method for precise monitoring of a sunlight greenhouse.
Background
China is the world with the largest greenhouse area, and has become the most popular in villages in recent years. However, the sunlight greenhouse planting in China is still in the traditional agricultural stage at present, and the sunlight greenhouse planting method has the limitations of insufficient modernization degree and insufficient cost and investment. There are mainly the following problems:
1. most greenhouse planting farmers still take manual management as the main part, depend on the planting experience and actual feeling of the farmers, pay attention to the use of water and fertilizer, and lack attention to elements such as sunlight greenhouse, crops and planting related weather. Diseases and pests and adverse environmental conditions of stressed crop growth factors caused by insufficient temperature and humidity management occur occasionally, and losses are caused to growers.
2. Digital acquisition equipment is expensive, and the automation investment is insufficient. Automatic monitoring and control equipment are less in the greenhouse, even there is observation equipment, also because the automation is with high costs, only has carried out single-point observation, and monitoring greenhouse environment precision is low.
3. The problems of low resource utilization rate and labor force increase always limit the economic benefit of the greenhouse sunlight greenhouse. Although the investment on intelligent agriculture in China is continuously increased, intelligent control strategies are also increased. But more, the system is optimized and adjusted manually according to production experience, or the whole system is monitored and controlled by adopting a single algorithm. The scientificity is insufficient in the production process, and the sensitivity and accuracy of the system are still not high.
4. A standardized planting management concept is lacking. Most growers can adjust the planting method based on experience and technology of other places blindly, and the planting method has certain randomness and non-replicability. Accurate digital analysis modeling, analysis and empirical models cannot be established. The quality and economic benefit cannot be improved permanently.
In recent years, the technology development of the internet of things and the internet is very rapid, artificial intelligence and machine learning are also gradually applied to agricultural production, an intelligent algorithm can bring faster development to an intelligent greenhouse system, the accuracy and the sensitivity of the system can be greatly improved, and the future greenhouse agricultural production development direction is intelligentized, networked and precise.
Disclosure of Invention
The invention provides a digital twin body construction method for precise monitoring of a sunlight greenhouse, which aims to solve the technical problems in the background technology.
The invention provides a construction method for sunlight greenhouse digital twin bodies, which can be used for dynamically, real-timely and continuously digitally acquiring and monitoring sunlight greenhouse, crops and planting processes, further digitally modeling the sunlight greenhouse, the crops and the planting processes, constructing time, space and element digital twin bodies, and constructing standardized sunlight greenhouse design construction, standardized crop growth processes and standardized planting management schemes through analysis and experiments. And the intelligent identification, positioning, tracking, monitoring and management of the sunlight greenhouse, crops and planting process are finally realized. The invention can be customized according to local conditions, provides a digital foundation for reasonable planting under different environmental conditions, and promotes the development of facility agriculture to intelligent agriculture.
The invention discloses a digital twin body construction method for precise monitoring of a sunlight greenhouse, which is characterized by comprising the following steps of:
collecting information related to a sunlight greenhouse, and pre-generating a digital twin sunlight greenhouse scheme based on the collected information;
constructing a digital twinning sunlight greenhouse based on a pre-generated digital twinning sunlight greenhouse scheme; and
and expanding, feeding back and optimizing the constructed digital twin sunlight greenhouse.
Wherein constructing the digital twin sunlight greenhouse based on the pre-generated digital twin sunlight greenhouse scheme comprises:
and establishing a comprehensive situation perception monitoring system based on a pre-generated digital twin sunlight greenhouse scheme, and digitalizing the sunlight greenhouse, crops and a planting process.
The method comprises the following steps of establishing a comprehensive situation perception monitoring system based on a pre-generated digital twin sunlight greenhouse scheme, and digitalizing sunlight greenhouses, crops and planting processes, wherein the method comprises the following steps:
based on a pre-generated digital twin sunlight greenhouse scheme, according to planted crops, a plurality of observation elements and cost budget of a sunlight greenhouse, a plurality of modules are utilized to form a single-point monitoring device, and a stationing, control linkage and networking scheme is determined;
deploying the single-point monitoring device according to the stationing and networking scheme, and performing data acquisition and test by using the single-point monitoring device;
performing linkage debugging on the functions of the single-point monitoring device to ensure that real-time situation perception and effective control are correctly performed, thereby forming the comprehensive situation perception monitoring system; and
and accessing the comprehensive situation awareness monitoring system to multi-source data and establishing an expert knowledge base.
Wherein constructing the digital twin sunlight greenhouse based on the pre-generated digital twin sunlight greenhouse scheme comprises:
and constructing a data cube based on the pre-generated digital twin sunlight greenhouse scheme, and performing modeling analysis and experiments to refine the standardized sunlight greenhouse, crop and planting process model.
The method comprises the following steps of constructing a data cube based on a pre-generated digital twin sunlight greenhouse scheme, and carrying out modeling analysis and experiments to refine standardized sunlight greenhouses, crops and planting process models, wherein the method comprises the following steps:
determining the change rule of environmental elements in the sunlight greenhouse based on the continuous monitoring data of the sunlight greenhouse body so as to construct an accurate sunlight greenhouse model;
determining the growth rule of crops based on the accumulated monitoring data of the whole growth cycle of the crops, and constructing models of the development and the yield of the crops under different environmental parameters and special models about crop diseases and insect pests;
establishing a planting scene model based on water, fertilizer and pesticide and personnel management conditions in the planting process;
establishing a peripheral environment data model, wherein the peripheral environment data model comprises a regional accurate climate and disaster model and/or an agricultural product market channel model; and
and constructing a comprehensive data analysis model aiming at the sunlight greenhouse body, the crops and the environmental elements based on the sunlight greenhouse accurate model, the models of the crop development and yield under different environmental parameters, the special models, the planting scene models and the surrounding environment data models so as to form a greenhouse multidimensional data cube, generate a mathematical statistics report and an analysis report, and provide suggested measures and linkage schemes under different parameters.
The method comprises the following steps of constructing a data cube based on a pre-generated digital twin sunlight greenhouse scheme, carrying out modeling analysis and experiments, and further comprising the following steps of:
integrating mathematical analysis and artificial intelligence algorithm; and
and constructing a multi-path integrated visual monitoring platform for the greenhouse, the internal crops and the surrounding environment.
Wherein constructing the digital twin sunlight greenhouse based on the pre-generated digital twin sunlight greenhouse scheme comprises:
the intelligent sunlight greenhouse, crop and planting process is established through an automatic scheme and a model of early warning, maintenance and scheduling in the pre-generated digital twin sunlight greenhouse scheme.
The method comprises the following steps of establishing an intelligent sunlight greenhouse, crops and a planting process through an automatic scheme and a model of early warning, maintenance and scheduling in a pre-generated digital twin sunlight greenhouse scheme:
according to environmental element indexes required by a specific growth cycle of crops, in combination with external regional weather forecast data and data monitored in real time in a greenhouse, a crop predictive alarm and predictive maintenance scheme is established;
alarming local crop index abnormity, and establishing an automatic linkage scheme with the predictive maintenance to realize an automatic linkage control mechanism of a greenhouse internal monitoring and control module;
when an alarm occurs, a one-key start-stop remote control signal of a related control function of the greenhouse is received to protect the safety of the greenhouse; and
deduction is carried out on specific disasters or risks, loss is calculated, and preventive exercises are carried out simultaneously to establish a loss stopping plan.
The invention achieves the following beneficial technical effects:
1. the cost is controllable, and the customization is flexible.
Firstly, the intelligent nodes are used as edge terminals, and can be deployed according to the actual requirements and cost budget of the development stage of the sunlight greenhouse and the requirements of planting monitoring elements in a planned step. If the facility sunlight greenhouse just begins to contact with the automation equipment, only basic environment element sensors can be integrated, the requirement for meeting the basic meteorological monitoring requirement is met, and meanwhile, the cost of the collection node is practically reduced. Along with the upgrading of the sunlight greenhouse of facility farmers, the investment on automation equipment is increased, the configuration of an upgrading part of intelligent nodes can be considered, three-dimensional detection is carried out, the environmental element data in the sunlight greenhouse is accurately acquired, and modules such as storage, a power supply and intelligent control are expanded. When the facility farmers manage the whole facility agriculture garden area, the management cost is increased and the complexity is increased sharply, more cost can be invested to further consider customizing intelligent nodes of different levels according to different planting functional areas, networking is carried out in the garden area, large-screen display and control are provided, and intelligent linkage is further realized.
And secondly, flexibly customizing an intelligent node comprehensive three-dimensional monitoring point arrangement scheme according to the point location area where the intelligent node is located, the type of the sunlight greenhouse, the planted crops and the observation factors. For example, the intelligent node observation elements of the distribution position close to the ground crop horizontal plane comprise soil moisture content, illumination temperature and humidity, crop growth state images and the like; the point location intelligent nodes hung in the air do not need to pay attention to soil moisture content, but need more attention to facility linkage; the intelligent nodes of the distribution positions of the areas inside and outside the boundary of the sunlight greenhouse pay more attention to the internal and external environment parameters of the sunlight greenhouse and the state image of the sunlight greenhouse body; in addition, different crops, such as strawberries and mushrooms, have different environmental monitoring element types which need to be focused, and different intelligent nodes can be set according to actual crop requirements.
In a word, the invention can well support the customized planting according to the planting type, scale and development stage of facility farmers according to local conditions, thereby minimizing the cost and maximizing the benefit.
2. Easy to expand and upgrade online.
First, the smart nodes support good upgrade extensions for the sensors and control modules. The core computing unit of the intelligent node is provided with an operating system, can be quickly compatible with a new version of sensor through programming and installing a driver, and realizes function improvement. Therefore, along with the development of sensor technology, the function and the precision of the sensor are improved, and a facility farmer can select a proper time to replace and upgrade the sensor. When a new sensor type appears, the sensor type can be rapidly integrated on the original intelligent node, so that the monitoring control function is expanded while the repeated investment is saved.
Secondly, the intelligent nodes support online upgrade and maintenance of algorithms and models. Along with the aging of the sunlight greenhouse, the replacement of crop varieties, the change of various model parameters such as the climate change of the external environment and the like, the output of the model also generates difference. The method supports online upgrading and adjusting of the model parameters through real-time monitoring, and real-time and accurate model optimization and replacement are obtained. In addition, through intelligent node networking and platform integration, cloud remote patrol and maintenance, fault online maintenance, remote diagnosis and online debugging of equipment and nodes are realized for the intelligent nodes and various automatic equipment in the sunlight greenhouse.
3. Accurate service, quality improvement and efficiency improvement.
The invention starts from an intelligent node for digitalizing in the real world, automatically collects, monitors and links equipment for a real sunlight greenhouse, crops and planting management mode through the intelligent node, and obtains real-time and historical data of the digital sunlight greenhouse, the digital crops and the digital planting management. The data can accurately reflect the state of the solar greenhouse, crops and planting management on high time and spatial resolution. And a foundation is laid for accurate service.
According to the invention, based on a cloud statistics and modeling analysis method, after a large amount of real data are collected to the cloud, through data-driven modeling and analysis of various different methods, a standardized sunlight greenhouse design mode, a crop growth standard model and a standardized management system can be obtained. Support is provided for subsequent better scale enlargement and quality improvement.
Furthermore, on the basis of digitization and standardization, by expanding an artificial intelligence algorithm and an automatic linkage module of an intelligent node, intelligent management can be constructed to construct an intelligent sunlight greenhouse, crops and planting, so that accurate management and control are realized, planting personnel are liberated from heavy and low-efficiency work and are converted into intelligent planting experts, and the aims of cost reduction, efficiency improvement and high-quality development of facility agriculture are better realized.
Drawings
FIG. 1 is a schematic flow chart of a sunlight greenhouse precise monitoring digital twin construction method of the present invention;
fig. 2 is a schematic view of a stereoscopic monitoring stationing scheme.
Detailed Description
So that the manner in which the above recited features of the present invention can be understood in detail, a more particular description of the invention, briefly summarized above, may be had by reference to embodiments, some of which are illustrated in the appended drawings.
As shown in the flow chart of fig. 1, the method of the present invention comprises three steps, namely preparation, digital twin sunlight greenhouse construction and operational maintenance.
The method comprises the following steps of firstly, preparing, and mainly comprising two preparation contents:
firstly, information acquisition in earlier stage is carried out, and background data is acquired. The method is deeply applied to a sunlight greenhouse of a planting farmer for comprehensive research and analysis, and the production stage, the cost investment budget, the existing problems and the expected effect to be achieved of the planting farmer object are known. On the basis, early experiments and data acquisition are carried out.
And secondly, establishing a digital twinning sunlight greenhouse scheme. On the basis of research, comprehensive analysis is carried out after comprehensively considering the development stage of facility agriculture of an implementation object, the actual situation of a sunlight greenhouse and main planted crops, a digital twin sunlight greenhouse construction scheme is specified to be made, for example, the size, the input cost and the type of the planted crops of the greenhouse are considered, observation factors, the planting process, the observation stage and the like are determined, and a preliminary scheme is confirmed according to the factors.
Secondly, constructing a digital twin sunlight greenhouse, wherein the specific process comprises the following three steps:
1. and (3) a digitalizing process: and establishing a comprehensive situation perception monitoring system, and digitalizing the sunlight greenhouse, crops and a planting process.
By successfully deploying the schemes of body distribution monitoring, control linkage, networking storage and the like covering the whole area of the greenhouse and combining external multi-source auxiliary data and an expert knowledge base, the solar greenhouse situation perception monitoring system is established. Specifically, the digitization process includes the following steps:
1.1 layout and networking scheme design
And setting a composition module, a point distribution scheme, a control linkage scheme and a networking scheme of the single-point monitoring device according to the size, the problem current situation, the crop type, the observation factors and other factors of the sunlight greenhouse and the related cost budget.
The distribution scheme is as shown in figure 2, and the distribution directions in the horizontal and vertical directions are reasonably selected according to the size of the sunlight greenhouse. The distribution range is customized according to the actual conditions of the sunlight greenhouse, control nodes are properly distributed inside and outside the boundary of the sunlight greenhouse, and meanwhile, the comprehensive consideration is given by combining the position of automation equipment in the greenhouse. The method aims to perform grid-meshing cutting and numbering on the three-dimensional space of the sunlight greenhouse, each point position is responsible for data acquisition and monitoring of a grid where the point position is located, and accurate data of each point on the three-dimensional space of the sunlight greenhouse can be finally obtained.
For a newly-built solar greenhouse, the design can be combined and carried out in the design and construction period.
For the sunlight greenhouse in operation, the problems commonly existing in the greenhouse can be combined, the design with emphasis can be carried out, and the optimization can be gradually expanded and promoted.
1.2 data acquisition and Joint control device deployment
And designing deployment, data acquisition, joint debugging and testing of devices such as a single-point monitoring device, a linkage control device, a networking device and the like according to a stationing and networking scheme. The three-dimensional grid area of the sunlight greenhouse is uniformly and comprehensively covered without dead angles, and the whole growth process of crop planting is free of shielding. The joint debugging comprises the testing between the nodes such as monitoring and linkage control in the greenhouse.
1.3, data transmission and linkage debugging
The data acquisition function of the monitoring device, the data transmission and storage function of the networking and data storage module, the linkage control function of the control device and the functions of all nodes on the cloud edge end cooperative link are jointly adjusted, and real-time situation sensing and effective control are guaranteed to be correctly carried out.
1.4 accessing multi-source data and establishing expert knowledge base
Besides greenhouse body data, the data of GIS layers of geographical and topographic environments of areas where the greenhouse is located, weather forecast data (gridding), disaster weather early warning data, early modeling and analysis experiment data, market price, agricultural condition service data and other multi-source support data can be widely accessed. And establishing a knowledge base of service experts such as greenhouses, crops and the like and updating in time.
2. And (3) a standardization process: and modeling analysis and experiments are carried out on the basis of constructing a data cube, and standardized sunlight greenhouse, crop and planting process models are extracted.
The method comprises the steps of carrying out comprehensive modeling and analysis through data collected by a comprehensive situation awareness monitoring system, constructing digital twin bodies of a sunlight greenhouse, crops and the environment, carrying out data statistics and analysis, intelligent algorithm integration, an automatic model, a networking and control module combined with the situation awareness monitoring system, and constructing a greenhouse visual monitoring platform.
After the points are distributed in a three-dimensional mode, the sunlight greenhouse is divided into accurate three-dimensional grids in a three-dimensional space, and each node can acquire element data of the point position where the node is located. In order to obtain the overall statistics and analysis results in the whole sunlight greenhouse more quickly and accurately, cloud-side linkage should be performed. The normalization process comprises the following steps:
2.1 sunlight greenhouse ontology data analysis modeling
On the basis of continuous monitoring data such as operation and control of a sunlight greenhouse body, the change rule of each environmental element of the sunlight greenhouse is analyzed, accurate models such as day-night difference, internal and external difference and regional difference of the sunlight greenhouse are constructed, and drawing of a three-dimensional interpolation physical quantity field in the greenhouse is supported. And decision support is provided for further improving and optimizing the design, layout, management and control and the like of the sunlight greenhouse.
2.2 crop full Life cycle modeling
Based on the accumulation of monitoring data of the whole growth period of crops, the growth rule of the crops is analyzed, models of the development and the yield of the crops under different environmental parameters and special models of crop diseases and insect pests and the like are constructed, and an auxiliary decision is provided for identifying and judging the stages and abnormal states of the crops.
2.3 plant process data modeling analysis
And analyzing the water, fertilizer and pesticide and personnel management conditions in the planting process, and modeling the planting scene. For example, a precision model is provided for planting in a water-fertilizer-pesticide key stage, and a standardized support is constructed for precision management.
2.4 modeling of ambient environmental data
Based on the integrated analysis of internal and external multi-source data, models such as regional environment disasters and accurate input-output prediction can be established. For example, based on data of surrounding weather, environment and the like, a regional accurate climate and disaster model is established; and establishing an agricultural product market channel model through data such as geographic GIS, market price, transportation and the like.
2.5 statistical analysis of data
Establishing a multi-dimensional data cube of greenhouse observed quantity, space, time, crops and the like, combining expert theoretical knowledge, constructing a comprehensive data analysis model aiming at sunlight greenhouse bodies, crops and environmental elements, and providing a mathematical statistics report and an analysis report under the decision of the expert knowledge. And providing suggested measures and linkage schemes under different parameters.
2.6 Intelligent Algorithm integration
Various traditional mathematical analysis and artificial intelligence algorithms are integrated, and a foundation is laid for automatic control. For example, a crop fruit image recognition algorithm can be integrated to estimate crop yield and the like at regular time, and a greenhouse inspection log and the like are automatically established through face recognition.
2.7, constructing a visual monitoring platform
And constructing a multi-path integrated visual monitoring platform for the greenhouse, the internal crops and the surrounding environment. Besides visual display data, thematic data drilling can be performed, overall process visual demonstration is performed on the monitoring, control and feedback processes, and convenience of greenhouse management and control is effectively improved.
3. An intelligent process: and establishing an intelligent sunlight greenhouse, crop and planting process through an automatic scheme and a model of early warning, maintenance and scheduling.
On the basis of comprehensive situation perception monitoring and a modeling analysis and visual monitoring platform, various analysis and discrimination models are applied, intelligent and convenient functions such as greenhouse predictive maintenance, automatic alarm joint control, one-key start-stop and the like are established, preventive exercises can be further provided, and loss estimation and loss stopping scheme recommendation under extreme conditions are established. The intelligent process comprises the following steps:
3.1 predictive maintenance (disaster weather risk prevention)
And according to the environmental element indexes required by the specific growth cycle of the crops, combining the weather forecast data of the external area and the real-time monitoring data in the greenhouse, and establishing a crop predictive alarm and predictive maintenance scheme. And fine management and maintenance are realized.
3.2, automatic linkage of alarm
The automatic linkage control system realizes an automatic linkage control mechanism of a monitoring and control module in the greenhouse, alarms local crop index abnormity, establishes an automatic linkage scheme with predictive maintenance, can automatically recognize and alarm when corresponding conditions occur, recommends the scheme correspondingly, and sets automatic processing according to the preset linkage scheme.
3.3 starting and stopping by one key
When taking place to report an emergency and ask for help or increased vigilance, support long-range to the relevant processing control function key of greenhouse and open and stop the operation, be convenient for protect greenhouse body safety.
3.4 preventive exercises
The method comprises the steps of constructing process deduction on of specific disasters or risks of situations such as crop plant diseases and insect pests, disastrous weather and the like, calculating loss, performing preventive exercise, and establishing an effective loss stopping plan.
And thirdly, operation and maintenance are carried out, and expansion, feedback and optimization are mainly carried out on the constructed digital twin body.
Starting from the actual application effect and the model, simplifying or expanding the device module and improving the model parameters and the algorithm according to the characteristics of the greenhouse, the crops and the geographic region, the law of meteorological observation elements and the cost-to-output ratio of the device; meanwhile, new technologies are combined to optimize distribution, networking, modeling analysis algorithms and the like, device modules are updated, and the new expansion requirements and the access, integration and implementation of the devices are supported. Such as extended sensors or functional modules: the access of security and protection requirements is realized by expanding boundary precaution and the like, the function of video logs is realized by an intelligent access control and a camera, a thermal infrared module is expanded, an automatic identification module is expanded and the like; or expanding the advanced technology to realize the functions: such as artificial intelligence auto-recognition algorithms. The optimization mode can be, for example, an online upgrade algorithm, and the model is corrected according to data in the implementation process, so that the accuracy is improved; or the replacement sensor is upgraded, and along with the change of the technology and the cost, the replacement sensor is upgraded in the equipment with the new version, so that the cost is reduced and the efficiency is improved.
Example 1: certain strawberry planting farmer
Take a certain strawberry planting farmer in Hebei as an example. The process of constructing the digital twinning sunlight greenhouse is as follows:
firstly, in the research and data acquisition stage, the actual development condition of the grower is obtained through field visit, information collection and the like. The sunlight greenhouse planted by the peasant household is in the early development stage, and the sunlight greenhouse is still built in the traditional plastic sunlight greenhouse mode. The main crop is strawberry, and mushroom planting is tried. And measuring and analyzing the strawberry sunlight greenhouse in the early stage, and designing a preliminary construction scheme by combining the expectation of lower cost of planting farmers.
The second stage is the construction stage of the digital twin sunlight greenhouse.
The first link is a digitization stage, and the experiment of the intelligent node making and the three-dimensional stationing monitoring scheme is carried out on the strawberry sunlight greenhouse in the park.
For cost control and growth characteristics of strawberry crops, the selected edge intelligent nodes are formed as follows: the sensors comprise a DTH22 sensor, a GY30 light sensor, a DS1280 soil temperature sensor and a capacitance soil humidity sensor, the core computing unit is constructed by adopting a raspberry zero development board, and the total cost of a single node is not more than 200 yuan.
The sizes of the strawberry sunlight greenhouse are 80 meters long, 8 meters wide and 6 meters high, and the number of the set intelligent nodes is 22. The stereoscopic monitoring stationing scheme is described as follows:
in the horizontal plane 30cm away from the ground in the sunlight greenhouse, 8 points are arranged, 4 points at two ends are 5 m away from the edge of the sunlight greenhouse, and the middle 4 points are uniformly distributed according to the distance. And 6 points are arranged on a horizontal plane 2.5 meters away from the ground in the sunlight greenhouse. And 4 points are arranged on a horizontal plane 50cm away from the top of the sunlight greenhouse in the sunlight greenhouse. In addition, 1 node is respectively arranged in each direction at the position, 1 meter away from the ground, 1 meter away from the boundary of the sunlight greenhouse and near the central point of the length and the width, of the outer side of the sunlight greenhouse, and 4 points are arranged in total.
And preliminarily setting observation factors including air temperature and humidity, soil temperature and humidity and illumination intensity at a node 30cm away from the ground. The observation elements of the other nodes are only air temperature and humidity.
The data for each node is stored on the tf memory card on the intelligent node. A set of gateway switch for data networking based on an Internet of things card is deployed in a sunlight greenhouse and used for transmitting data to a cloud. And simultaneously 1 public cloud server is rented to provide data storage and analysis functions. And real-time data query is provided for the grower through the applet and the app.
The second step is the normalization phase. Through data acquisition of 22 nodes in the digital stage, after the data are collected into a cloud server database, a cube of time, space and elements of the temperature in the sunlight greenhouse can be constructed, and the cube can be rolled up, drilled down and sliced and diced for analysis. Taking the internal and external temperature elements of the sunlight greenhouse as an example, the temperature is interpolated on a three-dimensional space, a dynamic change model with the precision of minute level is generated within 24 hours of the whole day, and the design defects of the sunlight greenhouse are accurately positioned for farmers and repaired. Meanwhile, by combining the growth states and yield conditions of strawberries at different area positions in the sunlight greenhouse, a relevant model is established, the optimal relation between the temperature and the humidity and the yield is obtained, and empirical reference is provided for standardized planting.
The third link is the intelligence stage. After the data modeling analysis of the stages, the shutter rolling machine, the ventilation device and the experiment in the sunlight greenhouse can be carried out, the warning information is intelligently pushed for the planting farmers through the small programs and the apps, the processing suggestions are provided, and the planting farmers are helped to take corresponding measures and planting suggestions according to the warning. By actually improving the yield, the method further promotes the growers to generate the expected expectations of expanding investment, carrying out subsequent automatic linkage and transformation.
In the operation maintenance stage of the third stage, the on-line diagnosis and remote upgrading maintenance functions are provided for the growers through the communication function of the applet and the app platform, and the field round-trip time and the labor cost are reduced. Meanwhile, after the yield is practically improved by a grower through the scheme, the expectation that the growth of crops can be seen in real time and linkage of a roller shutter machine is expected is provided, and a camera module with 500 ten thousand pixels is expanded for each intelligent node close to the ground level, so that the function of displaying images on line can be provided. Further support is provided for modeling and analyzing the full growth cycle image of the crop. Meanwhile, an infrared remote control transmitting module is arranged at a node near the automatic curtain rolling machine, so that the curtain rolling machine can be automatically linked to be switched on and off, and heavy labor of personnel is reduced.
Example 2: modernized facility park peasant household
Take a modern plantation in Hebei as an example. The process of constructing the digital twinning sunlight greenhouse is as follows:
firstly, in the research and data acquisition stage, the actual development condition of the park is acquired through field visit, information collection and the like. The garden is in the middle stage of development, has good planting and selling channels and has perfect modernized facilities in a sunlight greenhouse. The main planting crops are strawberries, mushrooms, tomatoes and the like. Through the communication with the planting peasant household, it is big to know artifical intensity of labour in the garden, and intelligent degree is not enough, and the higher problem of operation maintenance cost, selects to carry out whole digital twin to whole garden and constructs, and the planting peasant household has the ability to carry out the expectation that higher input promotes intelligent degree, designs preliminary construction scheme.
The second stage is the construction stage of the digital twin sunlight greenhouse.
The first link is a digital stage, different types of sunlight greenhouses in the park are measured on the spot, and targeted intelligent node design and manufacture and a three-dimensional stationing monitoring scheme experiment are carried out.
The intelligent edge nodes aiming at different crops in different sunlight greenhouses are designed in a customized manner by combining the space size of the sunlight greenhouse, the characteristics of internal facilities and the growth characteristics of different planted crops. Except for conventional air temperature and humidity, illumination, carbon dioxide, image acquisition and soil moisture content sensor modules, an infrared remote control module is also deployed to link a light supplement device in a sunlight greenhouse, a wireless remote control module is linked with modules such as a roller shutter machine, and an irrigation facility module is controlled through a stepping motor module. In addition, a Lora gateway and an LTE gateway are also deployed in each shed and used for networking and data transmission in the campus. The core computing unit is constructed by adopting a raspberry pi 4B development board.
And setting a three-dimensional monitoring point distribution scheme according to the size of the sunlight greenhouse. And performing grid division and numbering in each sunlight greenhouse according to the size, the facility position, the planting observation factors and the crop growth characteristics. And a customized intelligent node is deployed in each three-dimensional grid. The data for each node is stored on the tf memory card on the intelligent node.
And a video monitoring camera and an artificial intelligent node are arranged at a main trunk road and an entrance of the park and are used for personnel monitoring and access control management control.
And grid numbering is also carried out on the whole park, and regional gateways are also arranged in different regional grids to carry out data summarization and instruction issuing linkage.
And 3 public cloud servers are rented at the same time, and the functions of data storage, analysis and statistics and web service release are respectively provided. Real-time data query and control are provided for growers by constructing a park digital twin intelligent comprehensive monitoring control platform.
The second step is the normalization phase. A plurality of sets of intelligent monitoring nodes, monitoring nodes and network nodes are deployed in a park in a digital stage for data acquisition and transmission, and after the data are collected into a cloud server database, cubes of time, space and elements for observing the elements of each sunlight greenhouse in the park can be constructed, and the cubes of the elements are rolled up, drilled down and sliced and analyzed. For example, drilling and scrolling analysis can be performed on a plurality of scales of a garden, a planting functional area and a sunlight greenhouse, a distribution map on a three-dimensional space can be drawn by selecting a specific observation element, a dynamic change model with the precision of minute level is generated within 24 hours all day, an area abnormity is accurately positioned for farmers, and notification and alarm are performed. The grower can accurately position the live situation of an abnormal area through the video module and the camera data of the intelligent node, inquire and display the live situation on a large monitoring screen of the garden, and simultaneously perform related linkage operation on line by combining a linkage module in a sunlight greenhouse. The experimental reference is provided for standardized planting by modeling and analyzing park monitoring, sunlight greenhouse facility control, crop growth data and the like.
The third link is the intelligence stage. After the data modeling analysis in the above stage, an intelligent plan can be constructed, and when the specific area is found to be abnormal, the processing can be automatically carried out through a standardized flow. The loss caused by mistakes and untimely operation caused by confusion of people is avoided. And disaster deduction and evaluation can be performed on line, and data and schemes are established for optimizing layout, accurately controlling and promoting benefits and the like in the park. Through little program, app, intelligent operation monitoring platform in garden and big screen show control platform, provide decision support for planting the user, propelling movement and coordinated control plan are reported an emergency and asked for help to plant the peasant household and set up intelligent planting scheme, according to planting the plan, when starting this plan in the region automatic trigger and notice planting the user. And automatically adjusting planting measures and planting suggestions at different growth stages of crops. The planting farmers become industrial workers and planting scientists.
In the operation maintenance stage of the third stage, a communication and expert support function is further built through an online platform, a service group is established for the grower, business, technology and expert support is provided, the grower can perform online live display with the experts in various fields, abnormal online consultation, online experiment and remote upgrade maintenance are performed, and the time and labor cost for the expert to come and go on site are reduced. When a sensor with higher precision is arranged or control facilities in the sunlight greenhouse are updated, the online expansion can be flexibly carried out. Furthermore, the intelligent nodes of the automatic picking robot and the advanced customization function nodes such as the round unmanned aerial vehicle inspection node can be customized according to needs, and the idea is developed for future agriculture.
The foregoing description of the invention is illustrative and not restrictive, and it will be understood by those skilled in the art that many changes, variations or equivalents may be made therein without departing from the spirit and scope of the invention as defined in the appended claims.

Claims (8)

1. A digital twin construction method for precise sunlight greenhouse monitoring is characterized by comprising the following steps:
collecting information related to a sunlight greenhouse, and pre-generating a digital twin sunlight greenhouse scheme based on the collected information;
constructing a digital twinning sunlight greenhouse based on a pre-generated digital twinning sunlight greenhouse scheme; and
and expanding, feeding back and optimizing the constructed digital twin sunlight greenhouse.
2. The digital twin construction method for precise sunlight greenhouse monitoring of claim 1, wherein constructing the digital twin sunlight greenhouse based on the pre-generated digital twin sunlight greenhouse solution comprises:
and establishing a comprehensive situation perception monitoring system based on a pre-generated digital twin sunlight greenhouse scheme, and digitalizing the sunlight greenhouse, crops and a planting process.
3. The digital twin construction method for precise sunlight greenhouse monitoring as claimed in claim 2, wherein building a comprehensive situational awareness monitoring system based on pre-generated digital twin sunlight greenhouse solutions, and digitizing sunlight greenhouses, crops and planting processes comprises:
based on a pre-generated digital twin sunlight greenhouse scheme, according to planted crops, a plurality of observation elements and cost budget of a sunlight greenhouse, a plurality of modules are utilized to form a single-point monitoring device, and a stationing, control linkage and networking scheme is determined;
deploying the single-point monitoring device according to the stationing and networking scheme, and performing data acquisition and test by using the single-point monitoring device;
performing linkage debugging on the functions of the single-point monitoring device to ensure that real-time situation perception and effective control are correctly performed, thereby forming the comprehensive situation perception monitoring system; and
and accessing the comprehensive situation awareness monitoring system to multi-source data and establishing an expert knowledge base.
4. The digital twin construction method for precise sunlight greenhouse monitoring of claim 1, wherein constructing the digital twin sunlight greenhouse based on the pre-generated digital twin sunlight greenhouse solution comprises:
and constructing a data cube based on the pre-generated digital twin sunlight greenhouse scheme, and performing modeling analysis and experiments to refine the standardized sunlight greenhouse, crop and planting process model.
5. The digital twin construction method for sunlight greenhouse accurate monitoring as claimed in claim 4, wherein constructing a data cube based on a pre-generated digital twin sunlight greenhouse solution and performing modeling analysis and experiments to refine a standardized sunlight greenhouse, crop and planting process model comprises:
determining the change rule of environmental elements in the sunlight greenhouse based on the continuous monitoring data of the sunlight greenhouse body so as to construct an accurate sunlight greenhouse model;
determining the growth rule of crops based on the accumulated monitoring data of the whole growth cycle of the crops, and constructing models of the development and the yield of the crops under different environmental parameters and special models about crop diseases and insect pests;
establishing a planting scene model based on water, fertilizer and pesticide and personnel management conditions in the planting process;
establishing a peripheral environment data model, wherein the peripheral environment data model comprises a regional accurate climate and disaster model and/or an agricultural product market channel model; and
and constructing a comprehensive data analysis model aiming at the sunlight greenhouse body, the crops and the environmental elements based on the sunlight greenhouse accurate model, the models of the crop development and yield under different environmental parameters, the special models, the planting scene models and the surrounding environment data models so as to form a greenhouse multidimensional data cube, generate a mathematical statistics report and an analysis report, and provide suggested measures and linkage schemes under different parameters.
6. The digital twin construction method for sunlight greenhouse accurate monitoring as claimed in claim 5, wherein constructing a data cube based on a pre-generated digital twin sunlight greenhouse solution and performing modeling analysis and experiments to refine a standardized sunlight greenhouse, crop and planting process model further comprises:
integrating mathematical analysis and artificial intelligence algorithm; and
and constructing a multi-path integrated visual monitoring platform for the greenhouse, the internal crops and the surrounding environment.
7. The digital twin construction method for precise sunlight greenhouse monitoring of claim 1, wherein constructing the digital twin sunlight greenhouse based on the pre-generated digital twin sunlight greenhouse solution comprises:
the intelligent sunlight greenhouse, crop and planting process is established through an automatic scheme and a model of early warning, maintenance and scheduling in the pre-generated digital twin sunlight greenhouse scheme.
8. The digital twin construction method for precise sunlight greenhouse monitoring as claimed in claim 7, wherein building intelligent sunlight greenhouse, crop and planting process through automated schemes and models of early warning, maintenance and scheduling in pre-generated digital twin sunlight greenhouse schemes comprises:
according to environmental element indexes required by a specific growth cycle of crops, in combination with external regional weather forecast data and data monitored in real time in a greenhouse, a crop predictive alarm and predictive maintenance scheme is established;
alarming local crop index abnormity, and establishing an automatic linkage scheme with the predictive maintenance to realize an automatic linkage control mechanism of a greenhouse internal monitoring and control module;
when an alarm occurs, a one-key start-stop remote control signal of a related control function of the greenhouse is received to protect the safety of the greenhouse; and
deduction is carried out on specific disasters or risks, loss is calculated, and preventive exercises are carried out simultaneously to establish a loss stopping plan.
CN202110523825.1A 2021-05-13 2021-05-13 Digital twin body construction method for precise monitoring of sunlight greenhouse Pending CN113273449A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110523825.1A CN113273449A (en) 2021-05-13 2021-05-13 Digital twin body construction method for precise monitoring of sunlight greenhouse

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110523825.1A CN113273449A (en) 2021-05-13 2021-05-13 Digital twin body construction method for precise monitoring of sunlight greenhouse

Publications (1)

Publication Number Publication Date
CN113273449A true CN113273449A (en) 2021-08-20

Family

ID=77278797

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110523825.1A Pending CN113273449A (en) 2021-05-13 2021-05-13 Digital twin body construction method for precise monitoring of sunlight greenhouse

Country Status (1)

Country Link
CN (1) CN113273449A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113796228A (en) * 2021-09-26 2021-12-17 南京邮电大学 Plant cultivation system and method based on digital twinning
CN113849022A (en) * 2021-09-23 2021-12-28 上海孪数科技有限公司 Photovoltaic greenhouse environment management system based on digital twinning and spatial calculation
CN114080905A (en) * 2021-11-25 2022-02-25 杭州乔戈里科技有限公司 Picking method based on digital twins and cloud picking robot system
CN116429180A (en) * 2023-04-19 2023-07-14 江苏中翰食用菌有限公司 Edible fungus growth environment detection equipment and method
CN116738766A (en) * 2023-08-11 2023-09-12 安徽金海迪尔信息技术有限责任公司 Intelligent agriculture online industrialization service system based on digital twinning

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102035876A (en) * 2010-10-15 2011-04-27 江苏鸿信系统集成有限公司 Remote monitoring and intelligent control system and method of agricultural greenhouse based on M2M framework
CN105425755A (en) * 2015-12-22 2016-03-23 天津宏宝派农业科技发展有限公司 Smart agricultural planting system based on internet of things
CN209517198U (en) * 2019-04-15 2019-10-18 广州鑫博软件技术有限公司 A kind of wisdom agricultural standardization management system
CN110704974A (en) * 2019-09-30 2020-01-17 江苏科技大学 Modeling and using method of process model based on digital twin drive

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102035876A (en) * 2010-10-15 2011-04-27 江苏鸿信系统集成有限公司 Remote monitoring and intelligent control system and method of agricultural greenhouse based on M2M framework
CN105425755A (en) * 2015-12-22 2016-03-23 天津宏宝派农业科技发展有限公司 Smart agricultural planting system based on internet of things
CN209517198U (en) * 2019-04-15 2019-10-18 广州鑫博软件技术有限公司 A kind of wisdom agricultural standardization management system
CN110704974A (en) * 2019-09-30 2020-01-17 江苏科技大学 Modeling and using method of process model based on digital twin drive

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
毛雨晗: "《温室自动化多层栽培装备数字孪生监控方法》", 《中国优秀博硕士学位论文全文数据库(硕士) 农业科技辑》 *
郑大玮,李茂松,霍治国, 中国农业大学出版社 *

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113849022A (en) * 2021-09-23 2021-12-28 上海孪数科技有限公司 Photovoltaic greenhouse environment management system based on digital twinning and spatial calculation
CN113796228A (en) * 2021-09-26 2021-12-17 南京邮电大学 Plant cultivation system and method based on digital twinning
CN113796228B (en) * 2021-09-26 2022-08-23 南京邮电大学 Plant cultivation system and method based on digital twinning
CN114080905A (en) * 2021-11-25 2022-02-25 杭州乔戈里科技有限公司 Picking method based on digital twins and cloud picking robot system
CN116429180A (en) * 2023-04-19 2023-07-14 江苏中翰食用菌有限公司 Edible fungus growth environment detection equipment and method
CN116429180B (en) * 2023-04-19 2023-09-12 江苏中翰食用菌有限公司 Edible fungus growth environment detection equipment and method
CN116738766A (en) * 2023-08-11 2023-09-12 安徽金海迪尔信息技术有限责任公司 Intelligent agriculture online industrialization service system based on digital twinning
CN116738766B (en) * 2023-08-11 2023-10-13 安徽金海迪尔信息技术有限责任公司 Intelligent agriculture online industrialization service system based on digital twinning

Similar Documents

Publication Publication Date Title
CN113273449A (en) Digital twin body construction method for precise monitoring of sunlight greenhouse
CN209517198U (en) A kind of wisdom agricultural standardization management system
CN110347127A (en) Crop planting mandatory system and method based on cloud service
CN110545531A (en) Crop growth monitoring method and system based on big data and cloud computing
CN109781963A (en) A kind of field planting environmental monitoring system
CN108829165A (en) A kind of reading intelligent agriculture Internet of things system
CN106254476A (en) Agroecological environment information management based on Internet of Things, big data and cloud computing and monitoring method and system
CN113409023A (en) Wisdom gardens integrated service management platform
CN104635694A (en) Intelligent agricultural early warning system
CN103701845A (en) Cloud computing based monitoring and early warning control cloud service system and method for greenhouse cluster internet of things
CN113191914A (en) Digital twin body construction system for precise monitoring of sunlight greenhouse
CN104991459A (en) Organic vegetable greenhouse monitoring system and method
CN114743100B (en) Agricultural product growth condition monitoring method and system
CN112465109A (en) Green house controlling means based on cloud limit is in coordination
KR20220071405A (en) Agricultural support system and method using big data of smart farm
CN113406899A (en) Intelligent agricultural monitoring system based on Internet of things
CN108234558A (en) A kind of agricultural greenhouse intelligent control method based on LoRa technologies
CN112883230A (en) Potato production management system
CN113867243A (en) Digital and intelligent landscaping and maintenance integrated management system
CN111223003A (en) Production area-oriented planting decision service system and method
CN114578881B (en) Intelligent maintenance management system
Mittal et al. IoT-based precision monitoring of horticultural crops—A case-study on cabbage and capsicum
CN211908856U (en) Plant data acquisition system based on Internet of things
Wang et al. Image detection system based on smart sensor network and ecological economy in the context of fine agriculture
CN114895616A (en) Intelligent remote monitoring diagnostic system for agricultural greenhouse

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20210820