WO2023061483A1

WO2023061483A1 - Care device for plant factory

Info

Publication number: WO2023061483A1
Application number: PCT/CN2022/125378
Authority: WO
Inventors: 许亚良; 杨其长; 李清明; 郑胤建; 郑毅; 车元朋
Original assignee: 中国农业科学院都市农业研究所; 沈阳新松机器人自动化股份有限公司
Priority date: 2021-10-15
Filing date: 2022-10-14
Publication date: 2023-04-20
Also published as: GB202405363D0

Abstract

A plant care device for a plant factory, at least comprising a shuttle trolley (1) capable of moving around a cultivation rack (8) in a planting space and a care and acquisition unit (2) disposed on the shuttle trolley (1) and capable of performing image acquisition of a plant planted on the cultivation rack (8), the care and acquisition unit (2) completing image acquisition of the plant placed on the cultivation rack (8) while following the movement of the shuttle trolley (1) around the cultivation rack (8) along a preset path; and a processing module (3) for marking the plants having abnormal growth states by comparing a plurality of plant images acquired by the care and acquisition unit (2) with each other, so that the shuttle trolley (1) can perform a secondary target point inspection operation according to the marking result, and acquire dual heterogeneous verification data for secondary verification of the marked plants by means of the care and acquisition unit (2) and a monitoring module (4) which are mounted on the shuttle trolley (1). By means of the configurations, the quality of the plants harvested in each batch can be counted and analyzed, traceability analysis is performed on quality detection information so as to find and summarize a more reasonable planting scheme of the plants, thereby improving the quality of the plant products produced by the plant factory.

Description

A care device for a plant factory

technical field

The invention relates to the technical field of indoor care devices, in particular to a plant care device and method for plant factories.

Background technique

In the modern agricultural production and planting industry, factory agriculture is a highly specialized and modern facility agriculture that integrates automation control and artificial intelligence. At present, factory agriculture mainly realizes efficient and modern plant production through soilless cultivation technology, nutrient control technology, CO ₂ fertilization technology, environmental monitoring and control technology, water-saving irrigation technology, etc., supplemented by intelligent control system. In the process of plant cultivation and production by means of industrial agriculture, intelligent control by computer equipment, and cultivation based on pre-established relevant nutrient control models and existing industrial cultivation technology and experience are effective and conducive to production of industrial plants. production methods.

Plant factory is a highly specialized and modern facility agriculture developed after greenhouse cultivation. It is different from greenhouse production in that it completely gets rid of the constraints of natural conditions and climate under field production conditions, uses modern advanced equipment, completely controls environmental conditions manually, and provides a balanced supply of agricultural products throughout the year. At present, high-efficiency plant factories are developing rapidly in developed countries, and factory production of vegetables, edible fungi and precious flowers and trees has been initially realized. The United States is studying the use of "plant factories" to grow wheat, rice, plant tissue culture, rapid propagation, and detoxification. Since the crop production environment in the plant factory is not affected by external climate and other conditions, for example, lettuce seedlings can be harvested after 2 weeks of transplanting, and more than 20 crops of products can be harvested throughout the year, and the annual vegetable output is dozens of times that of open field cultivation. It is more than 10 times that of greenhouse cultivation. In addition, plant factories can achieve soilless cultivation, without pesticides, and can produce pollution-free vegetables. At present, there are only dozens of large-scale plant factories in the world. Due to the large investment in equipment and high power consumption (accounting for more than half of the production cost), high cost investment has become one of the biggest constraints in the process of plant factory construction around the world.

Chinese patent CN102147127A discloses an air-conditioning system for a closed artificial light plant factory, including: an artificial light source and an artificial light source heat dissipation recovery device, a timing controller, and a heat recovery air-conditioning unit; the timing controller controls the opening of the artificial light source Turn off the artificial light source during the day as the dark period of plant growth, and turn on the artificial light source at night as the light period of plant growth; the artificial light heat recovery device absorbs the heat of the artificial light source and absorbs it through the heat recovery air conditioning unit The air-handling unit distributes heat to the plant factory; the heat recovery air-conditioning unit and the air-handling unit are jointly controlled by a controller. The timing controller controls the opening and closing of the artificial light source against day and night, reducing the cooling load during the day and increasing the cooling load at night, improving the utilization rate of the air conditioning unit, reducing the installed capacity, and reducing the initial investment. This patent is only capable of a low-cost circulation system for light and temperature in the plant factory. There is no specific care for the plants, and it cannot automatically complete the observation of whether the plants have abnormal growth.

Chinese patent CN100553443 discloses a closed environment-controlled plant factory that fully utilizes artificial light, including enclosure structure, air circulation system, temperature regulation system, humidity regulation system, _CO2 supply system, light source supply system, and also includes embedded The control system and automatic metering system of network technology; the system is airtight, heat-insulated and opaque, and completely uses artificial light sources; through the control system, the temperature, humidity, _CO2 concentration, light, wind direction, and wind speed in the system are monitored Networked monitoring and control of environmental factors such as air pollution control, air cleanliness and environmental control are combined to provide a clean and optimal growth environment for plant production. The invention has the advantages of low cost and low energy consumption, and can be directly applied to plant genetic resources with no pesticides, high quality and high added value, and low-cost mass rapid propagation and large-scale seedling production to realize standardized and standardized cultivation Manage and plan production. However, this patent can only monitor and control the environmental factors in the entire planting space, and cannot monitor and control the microenvironment for the specific location of the plant, nor can it actively complete the inspection of the plant and determine whether there is any abnormality in the growth status.

In addition, the internal facilities of the existing plant factories do not have complete care equipment, and it is impossible to accurately monitor the production differences of all plants in the entire cultivation area with a small number of personnel, and it is impossible to timely and accurately adjust the plants with abnormal growth early. To avoid the failure to save or regulate the growth state of the corresponding plants due to the discovery of abnormalities in the later stage of cultivation. Therefore, there is a need for a care device that can regularly monitor plant growth and can screen abnormal plants and analyze abnormal symptoms.

In addition, on the one hand, due to differences in the understanding of those skilled in the art; on the other hand, due to the fact that the inventor has studied a large number of documents and patents when making the present invention, but due to space limitations, all details and contents have not been listed in detail, but this is by no means The present invention does not possess the characteristics of these prior art, on the contrary, the present invention already possesses all the characteristics of the prior art, and the applicant reserves the right to add relevant prior art to the background technology.

Contents of the invention

Aiming at the deficiencies of the prior art, the technical solution of the present invention provides a plant care device for a plant factory, which includes: a care acquisition unit, which is used to monitor the growth status of the plant, and which uses infrared imaging and /or visual imaging to collect images of plants; a processing module, which is used to mark plants with abnormal growth status by comparing several plant images with each other, and control the care collection unit and monitoring module to mark plants The collection of double heterogeneous verification data for secondary verification, wherein the care collection unit completes the collection of secondary verification data in the manner of changing the working position of multiple observation angles around the marked plants; the monitoring module can work with simulated plant leaves The state changes its working position, so that the monitoring module can obtain the microenvironmental parameters that can characterize the leaf growth environment.

The technical solution of the present invention also provides a plant care device for a plant factory, which at least includes a shuttle trolley that can move around the cultivation frame in the planting space and can plant on the cultivation frame on the shuttle trolley. The care acquisition unit for image acquisition of the plants, the care acquisition unit can follow the shuttle car along the preset path and move around the cultivation frame while completing the image acquisition of the plants placed on the cultivation frame; the processing module can pass the The care acquisition unit collects several plant images and compares them with each other to mark the plants with abnormal growth status, so that the shuttle car can perform a second fixed-point inspection operation according to the marking results, and install it on the shuttle car The care collection unit and monitoring module collect double heterogeneous verification data for secondary verification of marked plants. Its advantage is that, when a suspicious plant is identified, the application introduces the verification operation of secondary data collection, so that the care device can automatically and accurately complete the confirmation of the abnormal state of the suspicious plant and the preliminary analysis of the disease. In addition, the secondary verification operation can obtain multi-angle clear images of suspicious plants to facilitate later disease analysis. At the same time, a monitoring module that can measure the microenvironmental parameters of plant leaves is introduced, so that data analysis can be performed on the microenvironment of suspicious plant leaves. Therefore, to a certain extent, it can be identified whether the abnormal growth of the plant is caused by the abnormal photosynthesis of the leaves caused by the difference in the environment of the plant in the cultivation frame, so that it can be verified that the nutrient solution in the cultivation frame and the different levels of the cultivation frame have adverse effects on the plants. It is also possible to judge whether there is damage to the lighting module and other components on the cultivation frame according to the micro-environmental parameters.

According to a preferred embodiment, the secondary verification data of the care acquisition unit is to complete the plant image acquisition in a way that it can perform multi-observation angle working position transformation around the marked plant under the drive of the displacement component; the monitoring module The working position can be changed in a manner of simulating the working state of the leaves of the plant, so that the monitoring module can obtain microenvironmental parameters that can characterize the growth environment of the leaves. Its advantage is that by acquiring multi-angle clear images of plants, it is possible to better collect diseased leaves or/and stems of plants, so as to facilitate effective identification of diseases based on sample library data in the later stage. In addition, the monitoring module that can simulate the state of leaves can collect accurate parameter data of the microenvironment where the leaves are located, so as to effectively judge whether the abnormality of the plant is caused by the abnormality of environmental factors, and then find out the environmental factors based on the abnormal amount of data. The corresponding plant factory module is displayed to facilitate targeted detection of the working status of the plant factory module.

According to a preferred embodiment, the labeled plant image data and leaf microenvironmental parameters collected by the care collection unit and the monitoring module can be transmitted to the data analysis unit at the same time, and the data analysis unit uses its pre-stored representation of plant growth. The sample database data of the growth state in the cycle is compared with the collected images of the marked plants to judge whether there is wilting, lodging, chlorosis or yellowing of the plants. Its advantage is that the comparison and analysis can be directly carried out through the pre-stored sample data, which greatly reduces the calculation load of the data analysis unit and reduces its demand for operating parameters, so that the corresponding processing operations can be completed through low-cost processors.

According to a preferred embodiment, the data analysis unit also stores a parameter value sample library of microenvironmental parameters that affect whether the leaves can perform sufficient photosynthesis in multiple time periods of the plant growth cycle, so that the data analysis unit The analysis results are output by comparing the actual microenvironmental parameters of the plant leaves collected by the monitoring module with the required standard parameter values in the same growth period.

According to a preferred embodiment, the processing unit is able to match the plant image with the travel path of the shuttle car while marking the suspicious plant image, so that several plant images collected in the same time period can be reversely calculated The placement positions of different plants on the cultivation frame, so that the coordinate positions of the marked suspicious plants on the cultivation frame can be obtained.

According to a preferred embodiment, when there are plant diseases that cannot be directly determined in the analysis results output by the data analysis unit according to the secondary verification data, the data analysis unit can transmit the image data of the corresponding plants to The control center of the plant factory conducts disease research and judgment and stores disease sample data.

The present application also provides a plant care device for a plant factory, which includes a plant growth supply device, and the plant growth supply device at least includes a nutrient circulation pipeline arranged on a cultivation frame, and the nutrient circulation pipeline is used for hydroponics or aeroponics. The method provides the nutrient components required by the plants to the plants on each layer of the empty frame, and is characterized in that the data analysis unit adjusts the plant growth supply device according to the feedback of the current physical state or characteristics of the plants from the care collection unit, so that the plant growth supply device It can provide variable supply of light and nutrient solution according to the growth state of the plant.

According to a preferred embodiment, the shuttle car is a gantry-shaped structure capable of crossing the nutrient circulation pipeline, and lifting units capable of lifting the seedling trays on the empty frame are arranged on both sides.

According to a preferred embodiment, the shuttle car is provided with the care collection unit and a gripper manipulator for operating plants, wherein the care collection unit is used to monitor the growth status of the plants, and the Based on the information feedback of the growth state, the claw-type manipulator performs planting, thinning or harvesting operations on the plants.

According to a preferred embodiment, when the shuttle car enters the preset range of sensing the plant, the shuttle car can collect the current temperature of the plant by means of infrared imaging and/or visual imaging through the care acquisition unit. Physical state or characteristic.

According to a preferred embodiment, the nutrient circulation pipeline includes a photosynthetic nutrient mist nozzle arranged at the top of the empty frame and a rhizosphere nutrient mist nozzle arranged at the bottom of the empty frame, wherein the photosynthetic nutrient The mist nozzle can release the nutrients required by the plant stems and leaves to the plant stems and leaves in the form of aerosol, and the rhizosphere nutrient mist nozzle can release the nutrients required by the plant roots to the plant roots in the form of aerosol.

According to a preferred embodiment, the shuttle trolley is configured as a gantry-shaped structure capable of crossing the nutrient circulation pipeline, and lifting units capable of jacking up the seedling trays on the empty frame are arranged on both sides.

According to a preferred embodiment, the shuttle trolley is also configured to be able to interact with the pick-and-place lifter to transfer the cultivation board.

According to a preferred embodiment, the pick-and-place lifter can transfer the planting board it transfers to the conveying processing unit, so that the conveying processing unit performs subsequent processing operations on the plants planted on the cultivating board.

Description of drawings

Fig. 1 is a schematic workflow diagram of a preferred embodiment of a plant care device for a plant factory of the present invention;

Fig. 2 is a schematic workflow diagram of Embodiment 4 of a plant care device for a plant factory of the present invention;

Fig. 3 is a schematic workflow diagram of Embodiment 5 of a plant care device for a plant factory of the present invention.

List of reference signs

1: Shuttle car; 2: Nursing collection unit; 3: Processing module; 4: Monitoring module; 5: Data analysis unit; 6: Control unit; 7: Displacement component; 71: First robotic arm; 72: Second robotic arm ; 8: cultivation frame; 9: plant growth supply device; 10: processing unit; 11: light supply unit; 300 plant growth monitoring device; 310: inspection vehicle; 320: data processing center.

Detailed ways

A detailed description will be given below in conjunction with the accompanying drawings.

Under the actual environmental conditions, the physiological status information of the plant is obtained through the corresponding equipment, and nutrients are provided to the plant according to the nutrient control model and the needs of the plant, so that the plant can reach the best growth state. In order to help high-quality cultivation of plants planted in industrialized agriculture, plant factories usually need to create for plants based on environmental monitoring and control technology that can monitor and adjust factors such as temperature, humidity, light, and CO ₂ concentration in the cultivation space. suitable growth and development conditions. Data acquisition is an important part of the entire monitoring and control process. To monitor and adjust environmental conditions, it is first necessary to obtain data information on many environmental factors. The task of collecting data is completed by the data acquisition system, and the sensor is the core of the data acquisition system. An important part of. Due to the different types and properties of various environmental factors, the data acquisition system needs to use sensors with different functions such as temperature sensors, humidity sensors, light sensors, and biological sensors. The data collected by the data acquisition system is displayed after computer statistical analysis and intelligent processing. The computer intelligent system issues instructions according to the displayed data and the optimal conditions required for plant growth, controls the operation of related systems and equipment, and adjusts various environmental factors to the optimum. Optimal condition, to ensure that plant production is carried out in a scientific, orderly and standardized manner.

At present, the environmental control methods adopted in factory agriculture usually assume that the conditions of atmospheric factors such as air temperature and humidity in the facility environment are consistent in the environmental space. In fact, the conditions of these factors are not consistent in the space, but present a kind of Therefore, in order to more accurately create optimal growth conditions for plants, it is necessary to control the distribution of this factor in the facility's environmental space. During the actual monitoring process, it was found that the air humidity distribution in the factory planting area environment is related to the air flow temperature, speed, direction, and the relative position between the plants and the air inlet in the indoor environment. In the planting space of the actual plant factory, the distribution of the air temperature and humidity environment where the plants are located mainly depends on the temperature, speed and direction of the air flow in the planting space. Preferably, by using the neural network model to simulate and verify the relationship between the temperature and humidity distribution and the airflow characteristics in the area, the relationship between the temperature and humidity distribution and the airflow characteristics that facilitates the controllable adjustment of the plant growth environment in the planting space can be obtained. By changing the temperature, speed and direction of the air flow in the facility environment, the temperature distribution in the space can be controlled, so as to obtain the distribution of environmental factors such as the best air and temperature suitable for plant growth.

Example 1

The present application provides a plant care device and method for a plant factory, which can monitor the growth status of the plants in the planting space of the plant factory and perform micro-control adjustment of the growth environment. The plant care device and method for a plant factory includes a shuttle car 1 and a care acquisition unit 2 , a processing module 3 , a monitoring module 4 , a data analysis unit 5 , a control unit 6 and a displacement component 7 arranged on the shuttle car 1 .

According to a specific embodiment shown in FIGS. 1 and 2 , the shuttle trolley 1 walking in the cultivation frame 8 arranged in the planting space can transport the cultivation board for cultivating plants to the designated placement position of the cultivation frame 8 . The care collecting unit 2 that can identify the growth status of the plants on the cultivation frame 8 is also installed on the shuttle car 1 . The care acquisition unit 2 can be supported by the shuttle car 1 at different positions of the cultivation rack 8, so that the care acquisition unit 2 can obtain the growth status of the plants placed at different spatial positions on the cultivation rack 8, and collect information related to the plant growth status. The data information is transmitted to the processing module 3 for comparative processing, thereby distinguishing and marking the plants with problems in the growth condition on the cultivation frame 8. The monitoring module 4 can collect and monitor the environmental parameters of the growth microenvironment where the leaves of the plants with abnormal growth are located according to the marking results of the processing module 3 . The monitoring module 4 can send the acquired environmental parameter data to the data analysis unit 5 . The data analysis unit 5 can analyze the environmental parameter data obtained by the monitoring module 4, and adjust the microenvironment of the abnormally growing plant according to the analysis results of the leaf microenvironment or change the placement position of the abnormally growing plant on the cultivation frame 8, so that Plant leaves are in a good growth microenvironment again.

Preferably, the mobile end of the displacement assembly 7 is equipped with a care acquisition unit 2 capable of acquiring plant images. As shown in FIG. 2 , the care collection unit 2 can follow the shuttle car 1 to move around the cultivation frame 8 on a fixed track, so as to obtain images of all the plants on the entire cultivation frame 8 . Preferably, the displacement component 7 can also adjust the relative position between the care collection unit 2 and the shuttle car 1, so that when the shuttle car stops moving forward, the displacement component 7 can change the position between the care collection unit 2 and the plant to be photographed, Therefore, the image data of different angles of the plants are obtained by using the care collection unit 2 . Preferably, the care collection unit 2 always maintains a relatively fixed working position with the shuttle car 1 when it runs with the shuttle car 1 for the first time. After the processing module 3 receives the plant image data of all the plants cultivated in the same period on the entire cultivation frame 8 captured by the care acquisition unit 2 within a certain period of time, it compares all the plant images, and will show that there may be wilting, lodging, Mark images of plants with abnormal conditions such as chlorosis or yellowing.

Preferably, the shuttle car 1 drives the care collection unit 2 to perform a second run around the same trajectory. When the shuttle car 1 moves to the position of the plant corresponding to the marked image, the shuttle car 1 suspends its movement, and the displacement component 7 drives the care collection unit 2 to change the working position, so that the care collection unit 2 can conduct multi-angle inspection of the marked suspected abnormal plants. Image acquisition is convenient for secondary confirmation of the abnormality of the plant.

Preferably, when the shuttle car is running for the second time, the displacement component 7 can also change the working position of the monitoring module 4, so that the monitoring module 4 can move to the plant while the care collection unit 2 is acquiring multi-angle images of the plant. The leaf area, so as to obtain the microenvironmental parameter data of the plant leaf. Preferably, the double heterogeneous verification data used for the secondary verification of suspicious plants is the marked plant image data and leaf microenvironmental parameters collected respectively by the care collection unit and the monitoring module. Preferably, the high-definition, multi-angle images of suspicious plants acquired by the care acquisition unit 2 through secondary acquisition can be sent to the data analysis unit 5 with the leaf microenvironment parameter data acquired by the monitoring module 4 . Preferably, the data analysis unit 5 can analyze whether there are abnormalities such as wilting, lodging, chlorosis or yellowing of the leaves in the plant images collected by the care collection unit 2 by means of image grayscale processing, leaf contour shape comparison, etc. Preferably, the data analysis unit 5 can also send the analysis result to the plant factory control center according to the difference between the microenvironmental parameters of the plant leaves obtained by the monitoring module 4 and the environmental parameters preset in the planting space, so that the control center can control the cultivation frame The lighting module, humidification module and blowing module on the 8 change the light intensity of the microenvironment of the leaf area of the abnormal plant, as well as the microenvironmental humidity, wind force and wind direction, so that the microenvironment of the plant can be adjusted, which is more conducive to the growth and photosynthesis of the plant leaves .

Example 2

This embodiment is a further improvement on Embodiment 1, and repeated content will not be repeated here.

Preferably, the care collection unit 2 is installed on the shuttle car 1 through a displacement assembly 7 . The displacement component 7 can change the working position of the care collection unit 2 under the control of the control unit 6 . When the processing module 3 completes the initial marking of the suspicious plant image, the processing module 3 can send the position coordinates of the plant on the planting frame and the corresponding driving instructions to the shuttle car 1 and the control unit 6 . After the shuttle car 1 receives the plant position coordinates sent by the processing module 3, it can carry the care collection unit 2 for a second movement on the same path, so that the care collection unit 2 can perform a new round of conventional image collection on non-marked plants and send it to the processing module 3 comparing. When the shuttle car 1 moves to the coordinate position corresponding to the suspicious plant, the movement is suspended, and the control unit 6 controls the displacement assembly 7 to move around a fixed trajectory according to the preset driving command, so that the care collection unit 2 installed on the displacement assembly 7 can monitor the growth. Multi-angle image collection is performed for plants in suspicious state, and the displacement component 7 can also drive the monitoring module 4 to change its position, so that the monitoring module 4 can simulate the growth form of the leaves to obtain environmental parameter data of the leaf microenvironment.

Preferably, the monitoring module 4 can be driven by the displacement assembly 7 controlled by the control unit 6 to move to different positions on the cultivation frame 8, so that the monitoring module 4 can simulate the difference between the real growth position of the plant blade and the same area of the abnormally growing plant. The environment collects environmental parameters. The control unit 6 can control the displacement component 7 according to the position of the abnormally grown plant marked by the processing module 3 to drive the monitoring module 4 simulating the shape of the leaf to move to the leaf area in the middle section of the plant, so that the detection module 4 can imitate the shape of the leaf The environmental parameters in the microenvironment of the leaf area are collected by means of the method. Preferably, the detection module 4 is capable of multi-angle rotation and translation relative to the shuttle cart driven by the displacement assembly 7, so that the detection module 4 can perform position adjustment around the plant.

Preferably, the identification and distinction by the processing unit 3 includes comparing whether there is obvious wilting or lodging of plant leaves in the images, and comparing the plant size, color, etc. among all images. Preferably, the processing unit 3 can sort the plant images according to the pre-planned travel route of the shuttle car 1 during the comparison process of the plant images collected by the nursing collection unit 2 for the first time, so that suspicious plants can be marked while also The coordinates of the plant image can be supplemented, so that the control unit 6 can obtain the coordinate position of the suspicious plant on the cultivation frame 8, and when the shuttle car 1 is controlled to move along the preset path, it can be parked under the control of the control unit 6. The position corresponding to the track and the suspicious plant.

Preferably, the data analysis unit 5 can set a standard sample database related to various parameters characterizing the growth state of the plant in a pre-input manner. For example: the average height of plants in different periods and the threshold range corresponding to the plant height in each growth cycle, the projected area of the outer contour formed by the leaves when a single plant is projected from above, the standard size of the stem diameter of the plant in different periods and its threshold range, The color and size of the leaves in the middle of the plant and whether there is obvious wilting and lodging of the leaves of the plant. Preferably, the data analysis unit 5 also pre-stores a sample database of leaf microenvironmental parameters suitable for plants to maintain an optimal growth state at each stage. Preferably, the sample database at least includes environmental parameters such as temperature, humidity, light, moisture, and CO ₂ that affect leaf photosynthesis, and wind direction and wind force that can cause the above-mentioned environmental parameters to be distributed non-uniformly.

Preferably, the control unit 6 can control the shuttle trolley 1 to inspect and observe the plants between the cultivation racks 8 according to the patrol command issued by the plant factory control center regularly or the drive command issued manually. When there are no abnormal plants, the control unit 6 can continuously drive the shuttle car 1 according to the set time period to complete the inspection operation of the eight kinds of plants on the cultivation frame. When the control unit 6 controls the shuttle car 1 to find suspected abnormal plants for the first time, the control unit 6 can immediately drive the shuttle car 1 to perform the second inspection. Preferably, the control unit 6 can also control the shuttle car 1 to stop at a specific track position during the second inspection process, and drive the displacement component 7 to drive the care collection unit 2 and the monitoring module 4 to change different working positions, thereby obtaining Plant images and microenvironmental parameters that can double-check initial results.

Preferably, when the data analysis unit 5 has an obvious difference between the plant image collected for the second time and the standard data stored in the same growth period and it is diagnosed that the plant has abnormal growth, the data analysis unit 5 can collect the leaf microenvironment according to the monitoring module 4. The difference between the parameters and the standard parameters can be used to judge whether it is the chlorosis, yellowing, wilting and lodging caused by the abnormal environment of the leaves. When the data analysis unit 5 performs image processing on the plant image collected for the second time and finds that there are obvious abnormalities such as white ash deposition, moldy leaves, and white spots on the leaves of the plant, the data analysis unit 5 can also upload the plant picture to the control center of the plant factory The back-end processing platform where it is located enables the staff to manually analyze and judge the disease or the processing platform identifies the disease displayed in the plant image based on the existing network data or plant case record files, so as to treat the disease according to the existing treatment of the corresponding disease The scheme drives the light module, humidification module and blowing module on the shuttle car 1 or the cultivation frame 8 to transfer the plants or treat the leaf environment.

Preferably, the displacement assembly 7 includes a first mechanical arm 71 that can drive the care collection unit 2 to perform multi-working position conversion in a certain area, and can change the blade-shaped The monitoring module 4 also supports the second mechanical arm 72 for collecting micro-environmental parameters in the same blade area. Preferably, the first mechanical arm 71 and the second mechanical arm 72 can also be retracted and accommodated in the accommodation cavity on the shuttle cart 1, so that the monitoring module 4 remains closed when the shuttle cart 1 performs routine inspections. Preferably, the first mechanical arm 71 can support the care collection unit 2 on the shuttle car, so that when the shuttle car moves along the preset track, the care collection unit 2 can continuously collect images of plants located on the cultivation frame 8 beside the track. Preferably, the displacement assembly 7 can be accommodated according to the actual monitoring requirements, which can effectively improve the service life and wear resistance of the mechanical arm components, and avoid the oxidation of the components and the erosion of the external high-humidity environment and abnormal growth of plants when trying to expose Infestation by pathogens.

Example 3

Preferably, the processing module 3 and the data analysis unit 5 can also process and analyze the plant image by performing chromaticity identification on the color of the upper, middle and lower leaves of the plant stalk in the photo and comparing the size of the outer contour of the plant. When there is a certain plant or a small number of plants whose outer contour is obviously smaller than the plants in the rest of the images, the distribution of this part of the plants can be summarized and sorted out, so as to judge whether the same planting board has not effectively completed the planting pre-cleaning, resulting in the cultivation There are disease fungi on the board itself; it may also be that the nutrient solution provided by the cultivation frame 8 for the plants in this area has a ratio error and some nutrient deficiency causes slow growth; it may also be that there is an abnormal voltage or abnormal light in a certain power supply branch, causing The light module failed to provide effective light to the plants in the abnormal growth area. Preferably, the abnormal illumination may be that the lighting lamp is damaged, the light emitting color of the lighting lamp is not the best growing light, the brightness of the light is too high or too low, etc. Preferably, the growth difference of the plants may also be caused by the position of the cultivation frame 8 and the vent, the position of the air outlet, and the level height of the cultivation plate on the cultivation frame 8 .

A suitable environment is the basis for the survival and development of organisms. For example, the photosynthesis of plants requires an environment such as suitable temperature, humidity, light, water, and CO ₂ . Without these environmental factors, survival and growth cannot be established. In addition, leaf micro-environment is also called micro-environment, the optimal control technology of leaf micro-environment (i.e. around the leaf), that is, to control the micro-environment of the designated area on the surface of the plant leaf within the optimum range, without controlling the planting space and The temperature and humidity environment of the whole space of cultivation frame 8, because the temperature and humidity of outside changes no matter how, what really have an impact on plant growth is only the temperature of the blade surface and the air humidity in the 0.5cm of the blade surface. According to experimental research, the temperature and humidity of the micro-domain environment are very different from the temperature and humidity of the seedbed space or the air. In the high temperature season, when the air humidity at 0.5 cm is above 90%, the air humidity at 1.6 cm from the leaf surface is only 40%. , and it is very easy to keep the air humidity within 0.5cm above 90%, and a small amount of mist can be provided at fixed points without consuming a lot of electricity and water.

Preferably, the simulated leaves constructed by the monitoring module 4 are artificial leaves developed by simulating the stomatal structure of plants and the temperature conditions of water metabolism and photosynthesis in vitro, using highly dense circuits, special materials and sensing technologies. It can perceive various factors of the micro-environment of plant leaves: temperature, water evaporation coefficient, water film distribution of leaves, substrate moisture, air humidity, substrate humidity, ion concentration of mineral nutrients (EC value), ambient light and other environmental parameters. The data analysis unit 5 performs analysis and processing by simulating the microenvironmental parameters fed back by the leaves, and uploads the analysis results of abnormally growing plants to the control center, and the control center then controls the actuator to start and stop the peripheral equipment that regulates the plant growth environment according to the analysis results , to regulate the external environment.

The control unit 6 adopts a two-level control structure for the control of the monitoring module 4 and the second mechanical arm 72: the first level is a direct control level, that is, a single-chip intelligent sub-controller, which is composed of an AT89C51 single-chip microcomputer, and is responsible for simulating the blade structure. Environmental factors such as temperature, humidity, light and C0 ₂ are monitored. Preferably, the control unit 6 can also be set to be able to perform critical control on the greenhouse equipment in real time according to the monitoring results of the monitoring module 4 . Critical control means that the monitoring value of a certain microenvironmental parameter in the plant growth environment is not controlled between the upper and lower critical values of the given microenvironmental parameter. Otherwise, when the monitored value exceeds the upper and lower critical values of the microenvironmental parameter, the corresponding control equipment will be activated. This way is beneficial to save energy. Critical control is a low-input, high-output control method. The actuator uses water pumps, geothermal wires, red light plant growth lamps and other equipment. Preferably, the second level is a process management level, which is realized by a plant growth controller, and the plant growth controller is composed of a W78E58B single-chip microcomputer. It mainly completes the management of environmental parameters and the modification of control parameter settings, and can adjust and expand the system at any time. At the same time, the plant growth controller reserves the A/D conversion circuit to process the data from the sensor: it can be used as an independent control system to control the growth task of a single area.

Preferably, the monitoring module 4 is configured to simulate the shape of the blade in a manner that can simulate the actual contact of the blade surface with the environment during the plant growth process. Preferably, the sensors of the monitoring module 4 that can collect environmental parameters such as temperature, humidity, light, nutrition, CO ₂ , and dissolved oxygen are all integrated in the blade-shaped monitoring module 4 . Preferably, the leaf-shaped monitoring module 4 can simulate the stomatal structure, water metabolism, photosynthesis and temperature conditions of plants, and adopts sensing leaves made of a combination of highly dense circuits, special materials and sensing technologies. It can perceive various factors of the micro-environment of plant leaves: temperature, water evaporation coefficient, water film distribution of leaves, substrate moisture, air humidity, substrate humidity, ion concentration of mineral nutrients (EC value), ambient light and other environmental parameters. The control center of the plant factory simulates the sensing parameters of the leaf feedback and performs parameter calculations in combination with the rapid propagation system, and then instructs the automatic control actuator to start and stop the peripheral equipment to regulate the external environment. The monitoring module 4 is a sensing organ capable of monitoring changes in environmental factors (microenvironmental parameters) in the plant production process. It can accurately acquire various parameters that affect the interaction between the leaves and the environment for systematic collection, thereby accurately completing the leaf environment. simulation. Especially when it is found in the image of plant growth obtained by the care collection unit 2 installed on the shuttle car 1 that there are obvious differences in growth and abnormalities in the same area or the same plant, the monitoring module 4 can be positioned and suspended at different leaf positions, thereby simulating The parameter information of the leaf environment in different growth conditions is obtained by means of the environment of the leaves, so that the data analysis unit 5 can analyze the parameters affecting the abnormal results.

Preferably, the monitoring module 4 also includes an infrared CO2 gas analysis unit capable of measuring the CO2 gas produced during respiration of the plant to obtain the photosynthetic rate of the plant. Preferably, when the infrared CO2 gas analysis unit is capable of carrying out the night inspection operation of the shuttle car 1, the existing care collection unit 2 cannot obtain clear images under low light conditions, and the monitoring module 4 can monitor certain plant areas. The change of CO2 content can be used to judge whether the respiration effect of the plant is in normal growth, so that the plants in the abnormal concentration area can be further detected and parameter sampling analysis can be carried out. Preferably, the effective analysis of the CO ₂ gas concentration using infrared rays can fully control the situation of the plants during the night growth process, eliminating the defect that the care collection unit 2 cannot obtain clear pictures at night for accurate analysis.

Preferably, the monitoring module 4 that is leaf-shaped and can be suspended at the corresponding position of the plant leaves can also obtain changes in the leaf environment in a timely and effective manner. The temperature drop in the area closest to the plant leaf surface can be considered as the completion of the adjustment of the plant growth environment parameters. Compared with the existing technology, it is not necessary to cool down the entire plant plant planting area that affects the growth of the plant or the plant in this area. , thereby greatly reducing the efficiency and energy consumption of the plant growth environment adjustment in the plant factory, so that the control center or control unit 6 of the plant factory can change and monitor the parameters collected by the monitoring module 4 in the form of environmental micro-control adjustment according to the parameter data fed back by the monitoring module 4. The growth environment of the plant corresponding to the parameter.

Example 4

The present application also provides a plant care device for a plant factory.

The device includes a shuttle car 1 , a care collection unit 2 , a processing module 3 , a data analysis unit 5 , a cultivation frame 8 and a plant growth supply device 9 .

In the following examples,

The shuttle car 1 of the present application and the inspection car 310, the shuttle car, and the plant inspection robot in the subsequent embodiments all refer to the same device;

The nursing collection unit 2 of the present application and the vision module and camera unit in the subsequent embodiments all refer to the same module;

The processing module 3 of the present application and the processor of the plant growth monitoring device 300 in the subsequent embodiments all refer to the same module;

The data analysis unit 5 of the present application and the data processing center 320 in the subsequent embodiments all refer to the same module;

The cultivation frame 8 of the present application and the cultivation frame and the three-dimensional cultivation frame all refer to the same structure;

The plant growth supply device 9 of the present application and the nutrient solution unit in the subsequent embodiments all refer to the same module.

Hereinafter, the plant growth monitoring device 300 includes an inspection car 310 and a data processing center 320 , so the plant growth monitoring device 300 is the shuttle car 1 with the data analysis unit 5 inside. And the picture taken by the inspection car 310 is the plant photo taken after the care collection unit 2 moves to the set position following the shuttle car 1 .

As shown in Figure 2, the cultivation frame 8 is set as a multi-layer empty frame, and each layer of the empty frame is provided with at least one cultivation area and inspection track. The cultivation area can be used for plant cultivation, and the inspection track can be set around the cultivation area.

The inspection track is arranged on each layer of the cultivation frame 8 in a manner surrounding the cultivation frame 8 , and the inspection vehicle 310 can move based on each layer of the track laid on the cultivation frame 8 . Preferably, the inspection track is continuously set on each layer of the cultivation frame 8 to guide the inspection vehicle 310 to continuously move on each layer of each cultivation frame 8 . The inspection vehicle 310 can realize real-time monitoring of plant growth dynamics by means of infrared and photo shooting when inspecting plants. Preferably, the inspection vehicle is equipped with an infrared camera, a black and white camera, a color camera and a processor.

The inspection vehicle 310 is provided with a vision module and a processor. When the inspection vehicle 310 moves along the inspection track, it can take pictures of the plants cultivated in the cultivation area through the vision module, providing a basis for the analysis of the growth status of the plants. Preferably, the vision module includes the ingestion of black and white pictures and the ingestion of color pictures. The processor of the inspection vehicle 310 can perform simple data extraction and data comparison on black and white pictures, and can be used to send instructions for color picture ingestion when an abnormality is found. Preferably, the inspection vehicle 310 is set as a gantry-shaped structure capable of straddling the nutrient solution tank, and lifting units capable of jacking up the cultivation board are arranged on both sides. The gantry-shaped structure is slidingly connected to the track through the lateral pillars, and the supporting rods connecting the vertical pillars on both sides are arranged horizontally, thereby forming the inspection vehicle 310 of the gantry structure. This structure can allow the track to run parallel to the nutrient solution tank, and the space formed by its support and separated from the ground allows the nutrient solution tank to pass through. At the same time, the pillars on both sides can be controlled by the data processing center 320 to adjust the height of the support rod in a telescopic manner. When the inspection vehicle 310 is around the cultivation frame 8, the support rod can be brought to the same level as one layer of the cultivation frame 8 by raising the pillar, so that the vision module arranged on the support rod can scan the cultivated plants on this layer. way of monitoring.

The data processing center 320 can perform data connection with the cultivation frame 8 and the inspection vehicle 310 in a wired or wireless manner. The data processing center 320 can issue instructions based on the instructions it receives or the data obtained through feedback. The cultivation frame 8 can change the lighting conditions or other plant growth supply conditions set on the cultivation frame 8 based on the instruction of the data processing center 320 . The vision module of the inspection vehicle 310 can take pictures of the plants on the cultivation frame 8 passing by it. The processor or data processing center 320 on the inspection vehicle 310 can obtain the photographed pictures and perform feature extraction on the photographed pictures. By comparing the features in the normal state of the plant picture with the features of the current picture, the abnormality of the current plant growth state can be found, and the cause of the abnormal plant growth state can be deduced based on the abnormal features. Preferably, the data processing center 320 can implement coupled control of multiple environmental factors through man-machine interface interaction, so as to improve control speed and accuracy.

According to a preferred embodiment, the image capture of the inspection vehicle 310 can be divided into black and white image capture, grayscale image capture, and color or full-color image capture based on data volume processing requirements and feature extraction condition requirements. The abnormal state of the plant is mainly a diseased state, and the cause of the diseased state is mainly a disease or an insect. When a disease or pest occurs, the shape and color of the leaves, stems and other tissue parts of the plant will change. Therefore, when judging the abnormal state of the plant, it is only necessary to judge the shape or color of the tissue parts of the plant. Gets whether the plant is in an abnormal or diseased state. The shape and color of plant tissue parts can be judged by taking black and white pictures. For example, when a plant is sick, the leaves may curl up. The inspection vehicle 310 takes black and white photos of the leaves of the plants, and extracts the features of the outline of the leaves with coordinate points, so that the current plant is in an abnormal state based on the reduction of the expanded area of the leaves and the position difference of the coordinate points of the outline of the leaves. Preferably, use candy to extract the edge, and then use minimal bounding or Minimal radius bounding semi-circle to determine.

Furthermore, when plants in an abnormal state are found through black and white photos, the inspection vehicle 310 can selectively take grayscale, color or full-color pictures of the plants in the corresponding area. As shown in Table 1, in the process of judging the abnormal/disease state of the plant, the type of pictures taken can be selected based on the data required for judging the abnormal/disease state of the plant. Preferably, the black-and-white photo can have a specification of 1600*900*2bit.

Table 1

影响因素Influencing factors	组织形态organizational form	虫害位置pest location	虫害形态Pest form	虫害颜色pest color	虫害面积Infested area
图片选择picture selection	黑白black and white	灰度grayscale	灰度grayscale	彩色/全彩color/full color	灰度grayscale

Grayscale images can be used for feature extraction of insect morphology, pest distribution and pest area caused by plant pests, and color or full-color pictures can be taken for the pest distribution of some of the plants. Preferably, the inspection vehicle 310 uses its own processor to process the feature comparison of black and white pictures when moving at high speed. On the one hand, it can detect possible pest problems at the current location in time, stop here, and take pictures in sequence. Grayscale photos of pest-infested plants; on the other hand, the inspection vehicle 310 passing the pest-infested plants has the probability of carrying insect pest eggs. The area of the plant will lead to aggravation of the range of the disease. Therefore, when a plant area that may have pests is detected, the passing inspection vehicle 310 will stop in this area, or carry out bagging protection treatment, or carry out disinfection and cleaning treatment.

After determining the pest species of the plant through the shape, color and position of the disease spot, it is also possible to conduct a full range of pest distribution and area statistics on the front and back of the plant through grayscale photos, so as to determine the degree of plant disease in combination with the depth of the color of the pest. Extent to which the current infestation is affecting plant yield. For example, tomato bollworm. Tomato bollworm disease mainly harms the fruits of crops, which makes the yield of crops decline obviously. Tomato bollworm larvae mainly feed on buds, flowers and fruits, and also damage tender stems, leaves and buds. When the flower buds are injured, the bract leaves open, turn yellow-green, and fall off after 2-3 days. Young fruits are often eaten or rotted and fall off. Although the fruit is only partly eaten by moths, the moth holes are in the pedicle, which is convenient for external water and pathogens to flow in and cause rot. cause a reduction in production. When tomato is in reproductive growth period, tomato bollworm will be distributed on the surface of flower buds or fruits of tomato plants. The inspection vehicle 310 can irradiate the gray-scale pictures of the tomato plants with insect pests, and distinguish the tomato flower buds, fruits and tomato bollworms through the gray-scale color difference of the edges of the flower buds, fruits and tomato bollworms, so as to judge the presence of tomato bollworms. Distribution location, distribution area and morphology of tomato bollworm on tomato.

When it is impossible to determine the type of insects on the plant surface, color or full-color images can be taken further, so as to obtain clear pictures of insects, which are used to provide the final basis for judging the types of insects for the data sorting center.

The current health status of the plant can be evaluated by combining the types of insects, the location of the pests, the area of the pests, and the current status of the insects. Since the plant needs to be sprayed with medicine when it is found that the plant is in a state of pest damage, the current state of plant pest damage can provide an important basis for subsequent treatment, so that the data processing center 320 can select a suitable treatment drug, dosage and application rate for the current plant. medicine way.

The data processing center 320 can evaluate the abnormal state of the plant through the ingestion of picture features. Based on the selection of the color of the picture, a hierarchical progression of plant pest judgment is formed. Each level of pest judgment has different uses and meanings for plant factories. For example, the ingestion of black-and-white pictures, on the one hand, can allow the processor on the inspection vehicle 310 to process by itself, without data transmission, and does not require a high-precision, high-speed processing center, which can reduce costs and increase speed. The speed of data processing enables the inspection vehicle 310 to quickly scan the plants in the cultivation area to screen abnormal plants when moving at high speed along the track; on the other hand, for some plants that need leaves or stems as output plants, leaves or stems When the stalk is damaged by diseases and insect pests, it will not be able to produce again. For example, the damage of plants that need leaves to be produced by the white butterfly, once it happens, the leaves of the plant where the white butterfly is located cannot be used for traditional Chinese medicine. Once it occurs, it is necessary to consider isolating the plants damaged by the cabbage butterfly from the normal plants, and there is no need to consider the ingestion of grayscale or color pictures in the next step.

Through the data processing center 320 and the processor processing the photographed pictures, the specific physiological data of the current state of the plant is obtained. The current physiological data of the plant can be fed back to the environment of the plant factory in real time. Most of the existing technologies focus on the way of regulating environmental factors in plant factories, while ignoring the regulation of environmental factors to serve plant growth. For example, the Chinese patent with publication number CN112470790A provides a plant growth environment monitoring and regulating device and method, including a planting greenhouse, an isolation board, a detection unit, an adjustment unit and a control unit. In the planting greenhouse, the greenhouse is divided into multiple planting rooms by the isolation board. Each planting room is equipped with a detection unit. The detection unit detects the planting environment in the planting room and feeds back to the control unit. The control unit can record the plant growth environment data according to the plant growth status. , match the growth environment suitable for plant growth, and control the adjustment unit to change the planting environment in the planting room according to the detection data of the control unit, and multiple planting rooms can be monitored and adjusted at the same time. The device can only detect the state of plant growth through the gas content in the environment to adjust the temperature and light. However, the growth state of plants is most intuitively reflected in the state of the plant itself, rather than the gas content in the environment, or the gas content in the environment is only a factor affecting the growth state of plants. Therefore, the present invention intuitively judges whether the plant is in a healthy vegetative growth or reproductive growth state by scanning the image of the plant by the inspection vehicle 310 .

The data processing of the data processing center 320 includes at least three priorities, including the first priority of plant black and white pictures, the second priority of plant grayscale pictures and the third priority of plant color pictures.

The image capture of the inspection vehicle 310 includes the black-and-white image capture method of the first priority. When the inspection vehicle 310 moves along the track at high speed, it scans the plants within its field of view through the camera. The processor of the data processing center 320 or the inspection vehicle 310 performs feature extraction and comparison based on the scanned pictures, and extracts the stem and/or leaf shape/profile of the plant, so as to find plants in an abnormal state. Among them, the plants in an abnormal state include plants with unbalanced nutrients or unbalanced light, and plants in which disasters occur. When a plant in an abnormal state is found, the inspection vehicle 310 will image the detected plant in an abnormal state in a manner of increasing the color richness based on the second-priority grayscale image capture instruction sent by the data processing center 320 ingest. The grayscale images involved in the second priority can be used to extract features of the shape, location and area of diseased spots or pests on plant stems and/or leaves.

When the form of disease spots or pests cannot make the data processing center 320 judge the types of disease spots or pests based on the types of known diseases and pests stored in its database, the data processing center 320 can issue instructions to the inspection vehicle 310 to make the inspection The car 310 performs image capture of the third priority. The image acquisition of the third priority can be used for detection of foreign object distribution.

According to a preferred implementation manner, during the high-speed movement of the inspection vehicle 310, the black-and-white camera is preferentially used to scan and photograph the plants on the cultivation frame. Compared with grayscale, color and full-color photos, black-and-white photos have lower data volume and channel requirements, and are only used for judging plant outlines and shapes. Black-and-white photos are fully applicable. The black-and-white photos of plants taken by the inspection vehicle 310 have a small amount of data, and it can process the scanned black-and-white photos through its own processor, which can extract morphological features such as leaves and stems of plants in the photos, such as The contours of stems and leaves are compared with those of healthy plants, so as to detect abnormalities in plant tissues in time.

After identifying the area of diseased plants, the disease depth and diseased taxa of the plants need to be determined. The diseased taxa of plants can help to determine the treatment plan for plants, and the diseased depth of plants can be used as the preset basis for the treatment plan on the one hand, and can also be used to judge the diseased depth of plants on the other hand.

The judgment of plant disease groups depends on the judgment of the color, position and shape of plant disease spots, wherein the position and shape of plant disease spots rely on the inspection vehicle 310 to judge the grayscale pictures taken by plants, and the color of plant disease spots depends on the inspection vehicle 310 Judgments are made on color or full-color pictures of plants. Since the data processing capacity of grayscale pictures is less than that of color or full-color pictures, and the data processing capacity of black and white pictures is less than that of grayscale pictures, therefore, if the feature extraction of plant morphology or plant surface morphology can be satisfied, Image acquisition takes the form of photo ingestion priority. The order of priority can be black and white image > grayscale image > color image > full color image.

Preferably, the inspection car 310 includes at least a first rail car and a second rail car. The vision module of the first rail car is provided with a black and white picture camera unit for first priority picture capture. When the first rail car moves along the track, at least the camera for identifying the growth state of the plants can be used to initially identify the growth state of the plants planted on each cultivation plate in each cultivation layer.

The vision module of the second railcar is provided with a camera unit capable of taking at least grayscale pictures. Both the first rail car and the second rail car can move on and around the cultivation frame 8 along the track, so as to ensure that the second rail car can reach the positioning position sent by the first rail car, and realize the precise positioning of abnormal state plants. When it is recognized that there is an abnormality in the growth state of the plants growing in a certain cultivation area through the black and white picture, the camera unit arranged on the second rail car starts to start and shoots the plants in the cultivation area corresponding to the black and white picture, so as to The category and severity of plant diseases and/or pests are further identified. Preferably, the data information fed back by the first rail car to the data processing center 320 can include the judgment result of the abnormal state of the plant, the location information of the plant in the abnormal state, and the location information of the first rail car. When the data processing center 320 obtains the position information of the plant in abnormal state and the position information of the first rail car, it can send the mobile positioning to control the moving path and stop position of the second rail car, and provide assistance for the scanning direction of the second rail car judge. For example, when the first rail car arrives at the first position of the first cultivation area, the camera unit finds abnormal plants in the fifth row, fourth column, fifth row, fifth column, and fifth row, sixth column of the first cultivation area, then The second rail car can also move to the first position based on the information feedback from the data processing center 320, and look for plants in the fifth row, fourth column, fifth row, fifth column, and fifth row and sixth column of the first cultivation area for the second priority. level image capture.

The camera unit used to identify the growth status of the plants establishes a data connection with the control unit of the intelligent plant factory via the first communication unit of the rail vehicle itself. Preferably, the first rail car is able to conduct preliminary identification of the growth status of the plants planted on each cultivation plate in each cultivation layer along the rail regularly or irregularly.

The first railcar can process the black-and-white pictures taken by itself through its own processor, without sending the black-and-white pictures to the control unit or other modules for identification and analysis, so as to find out whether the plants are abnormal. The data processing of the first rail car itself can increase the speed of data processing, and the results can be fed back in time when the first rail car moves at a high level, and the second rail car can be dispatched for further inspection.

The priority setting of image capture, compared to directly collecting color images of plants in the cultivation plate through the camera, on the one hand, due to the large memory occupied by color pictures/videos, the amount of data that the control unit needs to process for image recognition is huge. As a result, the processing speed of analyzing diseases and/or pests based on image recognition through the camera is not high, which leads to a low maximum speed of the mobile platform that can travel on a dedicated track, and cannot meet the daily inspection and monitoring needs of large-scale plant factories;

Identify the growth state of the plant through a black-and-white camera or a black-and-white picture taken by the camera to further analyze plant diseases and/or pests, and directly pass the camera used to identify the growth state of the plant without using the camera used to identify the growth state of the plant. The black-and-white pictures taken are sent to the control unit to initially identify the growth state of the plants to increase the processing speed of the initial identification. Further, when the processing speed of the initial identification of the control unit is increased, the moving speed of the first rail car can also be significantly increased. , thereby improving the monitoring rate of the plants in the plant factory and increasing the monitoring area of the plants growing on the planting board in the plant factory per unit time on the basis of ensuring the initial identification of whether the growth state of the plants is normal.

The setting of the second rail car can further increase the causes of plants in abnormal states, increase the processing efficiency and shooting efficiency of shooting in an assembly line shooting mode, and avoid unnecessary picture type switching or camera switching.

The system is also provided with a temperature control device, which is also controlled by the data processing center 320 . When the plant is short of water or under high temperature, the leaves of the plant appear curled or turn yellow. When the first rail car finds plants in an abnormal state (for example, leaf curling) through the inspection of the first priority, the second rail car can pass the inspection of the plant in the abnormal state through the second priority. If no foreign matter is found, the data The processing center 320 considers the light, temperature or nutrient imbalance of the plants, and further feeds back to the data processing center 320 . The data processing center 320 will check the humidity, temperature, light and nutrient supply of the plant growth environment, and control the plant growth supply device 9 to adjust the environmental factors to ensure that the abnormal growth of plants has nothing to do with the environmental factors.

According to a preferred embodiment, based on the inspection results of plants in an abnormal state, the data processing center can control the photosynthetic nutrient spray nozzle and/or the rhizosphere nutrient spray nozzle to spray nutrient solution or water to the area where there are plants in an abnormal state, thereby by spraying The nutrient solution or water regulates the state of plant growth.

The cultivation frame 8 can be divided into a sowing seedling raising area, a planting thinning area and a growing area based on different growth periods of plants. The cultivation frame 8 in the sowing seedling area comprises a sponge and a cultivation plate. Vegetable seeds are sown on the seedling sponge block. Specifically, the seeds are sown on the sponge block, neatly placed on the cultivation board through the cultivation basket, and placed on the multi-layer seedling raising rack to raise seedlings after sowing. Before the seeds germinate, turn off the light on the seedling rack, and turn on the light after 2 days after the seeds germinate, and turn on and off the lights according to the time controller setting program. Preferably, the size of the single sponge block is 25mm×25mm×25mm. This section requires an independent air conditioning system. Preferably, the light period is 20°C and the dark period is 18°C. The cultivation frame used for sowing and raising seedlings is equipped with a nutrient solution circulation system and a lighting system on each floor. Preferably, a fluorescent lamp or a white LED lamp is used as the light source, and the light intensity is 10 μmol·m ⁻² ·s ⁻¹ .

The cultivation frame 8 in the planting and thinning area comprises a seedling raising frame. After the seeds stay in the seedling rack for about 15 days, the seedlings grow to a suitable size, and the seedlings on the seedling rack are transferred to the fixed value area for fixed value. The fixed value is to replace the high-density seedling board with a lower-density seedling board to increase the spacing between plants. After the empty seedling board is cleaned, put it in the temporary storage area and wait for the next sowing use. The seedlings fixed on the seedling plate are sent to the growing area cultivation frame to continue growing. After the seedlings grow for about 15 days, they are taken out from the cultivation frame and sent to the thinning station for thinning. The seedlings are taken out from the small seedling board and placed on the large seedling board with lower plant density to provide more space for vegetable growth. After the empty seedling board is cleaned, it is put into the temporary storage area and waits for the next fixed value use. Thinning to the seedlings on the big seedling board is sent to the growing area cultivation frame to continue growing.

The cultivation frame 8 in the growth area can be arranged in the artificial light cultivation room with three layers of full height. Preferably, the artificial light cultivation room has a clear height of 9.3m.

The invention also relates to a pick-and-place lifter, a submerged laser-guided AGV, a fixed value/thinning manipulator, and a high-speed transfer vehicle. The pick-and-place hoist is used to take the cultivation board out of the cultivation frame and put it on the high-speed transfer vehicle. The take-out mechanism is a telescopic fork, which can be telescopic in two directions. A water collection tank is designed in the middle of the fork to collect the nutrient solution dripping from the vegetable roots during the process of picking and placing the cultivation board. The fork can move horizontally on the cargo platform of the elevator, and pick and place two rows of cultivation plates in the same group of cultivation racks. AGV two-wheel differential drive, lithium battery power supply, laser positioning, trackless walking, automatic jacking. It can rotate at a differential speed in situ, and has a strong anti-interference ability against uneven roads, slippery roads, and human pushing. Obstacle-stopping and obstacle-avoiding detour behaviors can be generated according to demand and the central management system. The high-speed transfer vehicle is located at the front end of the warehouse. The transfer vehicle is composed of a base and a slide table. There is a conveyor on the slide table to carry the cultivation board. The high-speed transfer vehicle can connect multiple devices in series, so that the cultivation board can be transferred continuously. The fixed value/thinning manipulator is composed of a truss mechanism, which can automatically complete the fixed value and thinning work. The front end of the manipulator is designed with grippers, which are used to grip the cultivation basket to complete the setting/thinning action. Preferably, the manipulator can be set on the inspection vehicle 310 and work with the inspection vehicle 310 when it moves on the cultivation frame or the circumferentially surrounding track.

According to a preferred embodiment, based on the factory plant production system, it can implement the following production process: manually assemble seedling boards, cultivation baskets, and cultivation sponges in the sowing room on the second floor, sow seeds through a seeder, and then put them into a seedling rack for seedling cultivation. After about 15 days of growth in the seedling raising rack, the seedling raising board is manually taken out, sent to the pipeline in front of the hoist on the second floor by the transfer trolley, and sent to the fixed value area on the first floor by the hoist to set the value. The seedling board temporary storage area is sent to the fixed value station. The small seedling board with a fixed value is sent to the designated position of the cultivation frame by a high-speed transfer car, hoist, and shuttle car. The empty seedling boards generated by the fixed value are sent to the cleaning room on the first floor for cleaning through the AGV. After the cleaning is completed, the AGV is sent to the entrance of the elevator on the first floor by the AGV in a stack, and then the seedling board is sent to the sowing room on the second floor by the elevator. Waiting for the next seeding use.

The seedlings need to be thinned after about 15 days of growth in the cultivation area, and the seedling boards are sent to the thinning area by shuttle cars, elevators, and high-speed transfer vehicles. The empty large seedling board needed for thinning is transported by AGV from the empty large seedling board temporary storage area to the thinning area, and the thinning is automatically completed. After thinning, the large seedling board is sent to the designated location in the cultivation area by a high-speed transfer vehicle, hoist, and shuttle trolley to continue growing.

The factory plant production system in the present invention is also provided with a harvesting and packaging area and a cultivation plate cleaning and storage area.

The harvest packing area is used to handle the harvest of cultivated plants after maturity. The big seedlings grow in about 15 days in the cultivation area, and the small seedling boards are sent to the harvesting area for harvesting through shuttle cars, elevators, and high-speed transfer vehicles. Before harvesting, the roots below the vegetable cultivation basket are cut off, and the cut roots are collected by a root collector. Then the large seedling board enters the picking robot, which automatically picks the vegetables to the conveyor. The empty large seedling boards produced are sent to the north side conveyor line by the high-speed transfer vehicle, and then cleaned by the AGV movement cleaning room, and then sent to the empty large seedling board temporary storage area by the AGV. The picked vegetables are first processed manually, and the qualified vegetables enter the packaging machine for packaging, weighing, and labeling, and then are put into the turnover box by the grabbing manipulator. The vegetables in the turnover box first enter the pre-cooling room for pre-cooling, and then are transported by the AGV to the packaging room for packaging and shipping.

The cultivation board cleaning and storage area is used for the treatment of the cultivation board after use. Due to the reusability of the cultivation board, it can be reused after treatment. The empty cultivation boards produced in each link are sent to the cleaning room by AGV for cleaning. They are cleaned with high pressure by a washing machine, and then the residual moisture is blown off by high-pressure air. They are stacked by a stacking machine, and then sent to the temporary storage area for empty cultivation boards by AGV.

Example 5

As shown in FIG. 3 , the plant care device for a plant factory further includes a processing unit 10 and a light supply unit 11 . The light supply unit 11 is configured to be able to provide light to the plants planted in the three-dimensional cultivation frame. The nutrient solution unit is configured to provide nutrient solution to the plants. The processing unit 10 is configured to at least be able to receive and/or transport the cultivation board used for planting plants in the three-dimensional cultivation rack and perform subsequent processing operations on the plants grown on the cultivation board. The control unit 6 is configured to at least provide the plants with the light and nutrient solution required for plant growth through the light supply unit and the nutrient solution unit respectively based on the growth requirements of the plants, and to perform subsequent processing operations on the plants through the processing unit.

The processing unit is configured to be at least capable of receiving and/or transporting the cultivation board transferred by the transfer mechanism unit and performing subsequent processing operations on the plants planted on the cultivation board. The processing unit comprises at least a plurality of individual conveyors for transporting the cultivation boards. The processing unit also includes a high-speed transfer vehicle, a planting robot, a seedling thinning robot, a stacking machine, a root cutting machine, a picking robot, a packaging machine, a weighing/labeling integrated machine, and a parallel robot, wherein the high-speed transfer vehicle It can be used to place the cultivation boards transferred by the pick-and-place lifter, and transport the cultivation boards to the subsequent operation process of the processing unit.

Preferably, the plants harvested by the picking manipulator can be detected by the quality inspection camera to collect images/videos of the harvested plants, and send the images/videos to the control unit to determine whether the quality of the plants is qualified . If the control unit determines that the quality of the plant is qualified, the control unit will allow the plant to enter the subsequent processing program; if the control unit determines that the quality of the plant is unqualified, the control unit controls the picking manipulator to extract the Harvested plants are transferred to waste collection bins. Preferably, the control unit can acquire the quality inspection information obtained by the quality inspection camera detecting the plants harvested by the harvesting manipulator in real time/non-real time. Particularly preferably, the quality detection information at least includes: the type of the plant, the growth history data of the plant, and the quality information of the plant. Preferably, the growth history data of the plant may include but not limited to: light formula data, nutrient solution data, temperature and humidity data, and carbon dioxide supply data used/experienced from the plant sowing stage to the growth and maturity stage. Preferably, the plant quality information may include but not limited to: plant quality grade, plant height, average length and width of leaves, diameter and weight of plant fruit, and the like. Preferably, plant growth history data can be obtained from the control unit. Through this configuration, the control unit can perform statistics and analysis on the quality of each batch of harvested plants, and conduct traceability analysis on the quality inspection information (especially the growth history data of the plant) to find/summarize the A more reasonable planting plan for similar plants, such as fine-tuning the plant's light formula, carbon dioxide supply, temperature and humidity, and nutrient solution supply plan, to reduce the defective products produced by the plant factory, thereby improving the plants produced by the plant factory (such as vegetables) product quality. For example, if the same vegetable (such as tomato) planted on the same batch of cultivation boards has different quality, such as tomato fruit size is different, and the average diameter of tomato fruit is small, then the control unit can look back to the growth history data of this batch, To optimize the planting process of such plants. For example, the light formula data, nutrient solution data, temperature and humidity data, and carbon dioxide supply data required by this type of plant are counted and compared. After the accumulation of multiple batches of data, the control unit can summarize the optimal growth conditions suitable for this type of plant. program, thereby improving the quality of planting such plants in the plant factory.

It should be noted that the above specific embodiments are exemplary, and those skilled in the art can come up with various solutions inspired by the disclosure of the present invention, and these solutions also belong to the scope of the disclosure of the present invention and fall within the scope of this disclosure. within the scope of protection of the invention. Those skilled in the art should understand that the description and drawings of the present invention are illustrative rather than limiting to the claims. The protection scope of the present invention is defined by the claims and their equivalents. Throughout the text, the features introduced by "preferably" are only optional, and should not be interpreted as having to be set. Therefore, the applicant reserves the right to waive or delete relevant preferred features at any time.

Claims

A plant care device for a plant factory, characterized in that it comprises:

A care collection unit (2), which is used to monitor the growth status of the plants, and which collects images of the plants in the form of infrared imaging and/or visual imaging;

A processing module (3), which is used to mark plants with abnormal growth status by comparing several plant images with each other, and control the care collection unit (2) and monitoring module (4) to mark the plants for a second time Validation of the collection of dual heterogeneous validation data, where,

The care acquisition unit (2) completes the acquisition of secondary verification data in the manner of performing multi-observation angle shifting of working positions around the marked plants;

The monitoring module (4) can change its working position in a manner of simulating the working state of the leaves of the plant, so that the monitoring module (4) can acquire microenvironmental parameters that can characterize the growth environment of the leaves.
The plant care device for plant factories according to claim 1, characterized in that the image data of marked plants and leaf microenvironmental parameters collected by the care collection unit (2) and the monitoring module (4) respectively can be transmitted at the same time To the data analysis unit (5), the data analysis unit (5) judges whether the plant has wilting, Lodging, greening or yellowing.
The plant care device for a plant factory according to claim 2, wherein the data analysis unit (5) also stores microenvironmental parameters that affect whether the leaves can perform sufficient photosynthesis. The parameter value sample library in the time period, so that the data analysis unit (5) outputs the analysis by comparing the actual microenvironmental parameters of the plant leaves collected by the monitoring module (4) with the standard parameter values required in the same growth period result.
A plant care device for a plant factory, which at least includes a shuttle trolley (1) capable of moving around a cultivation frame (8) in a planting space, and a shuttle trolley (1) capable of moving the cultivation frame (8) on the shuttle trolley (1). ) for image acquisition of plants planted on ), characterized in that the care acquisition unit (2) can follow the shuttle car (1) along a preset path while moving around the cultivation frame (8) Complete the image acquisition of the plants placed on the cultivation frame (8);

The processing module (3) can mark the plants with abnormal growth status by comparing the images of several plants collected by the care collection unit (2), so that the shuttle car (1) can carry out two A fixed-point inspection operation, and through the care acquisition unit (2) and the monitoring module (4) installed on the shuttle car (1), the collection of double heterogeneous verification data for the second verification of the marked plants is carried out.
The plant care device for plant factories according to claim 4, characterized in that, the secondary verification data of the care acquisition unit (2) is carried out according to the fact that it can be driven by the displacement component (7) around the marked plant The plant image acquisition is completed by changing the working position of multiple observation angles;

The monitoring module (4) can change its working position in a manner of simulating the working state of the leaves of the plant, so that the monitoring module (4) can acquire microenvironmental parameters that can characterize the growth environment of the leaves.
The plant care device for a plant factory according to claim 5, wherein the processing unit (3) is capable of matching the plant image with the travel path of the shuttle car while marking the suspicious plant image, Several plant images collected at the same time period can be reversely calculated to place different plants on the cultivation frame (8), so that the coordinate positions of marked suspicious plants on the cultivation frame (8) can be obtained.
The plant care device for plant factories according to claim 6, characterized in that, in the analysis results output by the data analysis unit (5) according to the secondary verification data, there are plant diseases that cannot be directly determined The data analysis unit (5) can transmit the image data of the corresponding plants to the control center of the plant factory for disease research and judgment and storage of disease sample data.
A plant care device for a plant factory, which includes a plant growth supply device (9), the plant growth supply device (9) at least includes a nutrient circulation pipeline arranged on the cultivation rack (8), and the nutrient circulation pipeline is supplied with water The way of cultivating or aeroponics provides the nutrient components required by the plants to the plants on each layer of the empty frame, and it is characterized in that the data analysis unit (5) is based on the feedback from the care collection unit (2) to the current physical state or characteristics of the plants. The plant growth supply device (9) is adjusted so that the plant growth supply device (9) can perform variable supply of light and nutrient solution according to the growth state of the plant.
The plant care device for a plant factory according to claim 8, characterized in that, the shuttle car (1) is a gantry-shaped structure capable of crossing the nutrient circulation pipeline, and the two sides are arranged on the empty frame that can jack up The lifting unit of the seedling tray.
The plant care device for a plant factory according to claim 9, wherein the shuttle car (1) is provided with the care collection unit (2) and a claw-type manipulator for operating plants, wherein, The care collection unit (2) is used to monitor the growth status of the plants, and the claw-type manipulator performs planting, thinning or harvesting operations on the plants based on the information feedback of the growth status.
The plant care device for a plant factory according to claim 10, characterized in that, when the shuttle car (1) enters the preset range of sensing the plant, the shuttle car (1) can pass through the The care collection unit (2) collects the current physical state or characteristics of the plant by means of infrared imaging and/or visual imaging.
The plant care device for a plant factory according to claim 11, wherein the nutrient circulation pipeline comprises a photosynthetic nutrient mist spray pipe arranged on the top of the empty frame and a root arranged at the bottom of the empty frame An international nutrient mist nozzle, wherein the photosynthetic nutrient mist nozzle can release the nutrients required by the plant stems and leaves to the plant stems and leaves in the form of aerosol, and the rhizosphere nutrient mist nozzle can release the nutrients required by the plant roots It is released to the root parts of plants in the form of aerosol.
The plant care device for plant factories according to claim 12, characterized in that, the shuttle car (1) is set as a gantry-shaped structure capable of crossing the nutrient circulation pipeline, and the two sides are arranged to lift the Lifting unit for seedling trays on empty racks.
The plant care device for a plant factory according to claim 13, characterized in that, the shuttle car (1) is also configured to be able to interact with a pick-and-place lifter to transfer the cultivation board.
The plant care device for a plant factory according to claim 14, characterized in that, the pick-and-place lifter can transfer its transshipped cultivation plate to the processing unit (10), so that the processing unit (10) Subsequent processing operations are carried out on the plants planted on the cultivation board.