Greenhouse Internet of Things monitoring system

Abstract

The invention relates to the technical field of greenhouse intelligent detection control, and discloses a greenhouse Internet of Things monitoring system, which comprises a meteorological port used for acquiring meteorological data of a region in a future period; the sensor assembly is used for acquiring environment parameters and soil parameters in the greenhouse; the crop monitoring module is used for monitoring the state of crops planted in the greenhouse to obtain the crop state; the control center is used for establishing a parameter demand model according to crop types and crop states; establishing a greenhouse characteristic model according to the environmental parameters and the soil parameters, performing characteristic comparison on the parameter demand model and the greenhouse characteristic model to obtain characteristic adjustment parameters, and determining a greenhouse adjustment strategy according to the characteristic adjustment parameters and the meteorological data; and the execution center is used for executing the greenhouse adjustment strategy. According to the invention, adaptive adjustment can be carried out on parameters in the greenhouse according to meteorological data, and the energy-saving performance of the control process is improved; greenhouse parameters are adjusted more accurately, and a more intelligent greenhouse monitoring control process is realized.

Description

Technical Field

[0001] This application relates to the field of intelligent greenhouse detection and control technology, and in particular to a greenhouse Internet of Things (IoT) monitoring system. Background Technology

[0002] The application of IoT and smart technologies in agriculture can empower crop cultivation. By applying monitoring technology in greenhouses, the crop growth environment can be accurately controlled. Through sensors, automatic control, and computer technology, environmental factors such as temperature, humidity, light, and carbon dioxide concentration in the greenhouse can be automatically adjusted to create the best growing conditions for crops.

[0003] Existing greenhouse monitoring systems primarily rely on sensors to perceive various environmental parameters in real time. By connecting to equipment such as fans, wet curtains, shading nets, sprinkler irrigation, and supplemental lighting, the systems automatically adjust based on environmental data to meet the environmental needs of crops, thereby improving planting efficiency and yield. When environmental parameters are abnormal, the system will issue alarms via on-site sound and light, and SMS messages. Managers can remotely view and control the system via computer or mobile app to ensure the environmental condition within the greenhouse. While existing greenhouse monitoring systems possess relatively accurate information collection and judgment capabilities, they still have some shortcomings. First, existing systems employ a real-time control strategy, which, while ensuring the maintenance of various parameters within the greenhouse, is not energy-efficient. Second, crops have different environmental parameter requirements at different stages, and existing greenhouse monitoring systems cannot adaptively adjust according to the crop's growth status. Therefore, how to integrate meteorological data and crop growth status to achieve a more intelligent greenhouse monitoring and control process is the fundamental problem that this invention aims to solve. Summary of the Invention

[0004] To enable more intelligent greenhouse monitoring and control by integrating meteorological data and crop growth status, this application provides a greenhouse Internet of Things (IoT) monitoring system, employing the following technical solution: A greenhouse IoT monitoring system includes: The meteorological port is used to obtain meteorological data for the region in the future. Sensor components are used to acquire environmental and soil parameters inside the greenhouse; The crop monitoring module is used to monitor the status of crops grown in greenhouses and obtain crop status information. The control center is used to establish parameter demand models based on crop types and crop conditions; to establish greenhouse characteristic models based on environmental and soil parameters; to compare the parameter demand models with the greenhouse characteristic models to obtain characteristic adjustment parameters; and to determine greenhouse adjustment strategies based on the characteristic adjustment parameters and meteorological data. The execution center is used to implement greenhouse adjustment strategies.

[0005] Optionally, the process of obtaining crop status includes: Images of crops are acquired using a multispectral camera in different bands. The images are preprocessed, and the average projected area of ​​the crop plants and color features in different bands are collected based on a deep learning model. The crop growth prediction cycle is determined based on the average projected area and color features. The crop growth cycle is compared with the growth prediction cycle, and the crop growth status is obtained based on the range of the difference between the crop growth cycle and the growth prediction cycle.

[0006] Optionally, the process for determining the crop growth prediction cycle includes: Based on the crop type, the standard plant projection area and standard color characteristics of the crop under different growth cycles and different bands are obtained. Data fitting is performed to obtain the curve of standard plant projection area changing with the cycle and the curve of R channel, G channel and B channel values ​​changing with the cycle under different bands. Substitute the collected average projected area of ​​the plant into the curve of the standard plant's projected area changing with the period to obtain the first reference period. The color features under each band are decomposed into RGB components to obtain the red component Ri, the green component Gi, and the blue component Bi. A constraint formula is then established. The minimum value of y(t) is obtained as the second reference period in this band; where R(t), G(t), and B(t) are the curves of the R channel, G channel, and B channel values ​​changing with the period in this band, respectively, and x = R, G, B. The weight ratio of the x component; The average value is calculated based on the first reference period and the second reference period corresponding to different bands according to a preset ratio, and the average value is used as the growth prediction period.

[0007] Optionally, the process of establishing the parameter requirement model includes: Obtain the standard light requirement coefficient, standard temperature requirement coefficient, and standard humidity requirement coefficient according to the crop type and growth prediction cycle; Judging based on the crop's growth status: If the growth status is normal, then establish a parameter requirement model based on the standard light requirement coefficient, standard temperature requirement coefficient, and standard humidity requirement coefficient. If the growth status is slow, an adjustment strategy is determined based on the range of the difference between the crop growth cycle and the predicted growth cycle. The standard light demand coefficient, standard temperature demand coefficient, and standard humidity demand coefficient are adjusted according to the adjustment strategy. A parameter demand model is established based on the adjusted standard light demand coefficient, standard temperature demand coefficient, and standard humidity demand coefficient.

[0008] Optionally, the environmental parameters include light intensity, ambient temperature, and ambient humidity; The soil parameters include soil temperature and soil moisture; Determine the greenhouse light state coefficient based on light intensity; The greenhouse temperature state coefficient is determined based on the ambient temperature and soil temperature. The greenhouse humidity state coefficient is determined based on ambient humidity and soil moisture. A greenhouse characteristic model is established based on the greenhouse light state coefficient, greenhouse temperature state coefficient, and greenhouse humidity state coefficient.

[0009] Optionally, the feature comparison process includes: The standard light demand coefficient is compared with the greenhouse light state coefficient, the standard temperature demand coefficient is compared with the greenhouse temperature state coefficient, and the standard humidity demand coefficient is compared with the greenhouse humidity state coefficient. The comparison results are used as characteristic adjustment parameters.

[0010] Optionally, the meteorological data includes meteorological light intensity, meteorological temperature, and meteorological humidity; Greenhouse adjustment strategies are determined based on characteristic adjustment parameters, light intensity, meteorological temperature, and meteorological humidity.

[0011] Optionally, the execution center includes a supplementary lighting module, an external sunshade module, a ventilation module, and a heat preservation module.

[0012] Optionally, the environmental parameters also include carbon dioxide concentration; the soil parameters also include soil pH and soil EC values; the carbon dioxide concentration, soil pH, and soil EC values ​​are monitored in real time, and an early warning is issued when any one of them exceeds the corresponding preset range.

[0013] In summary, this application includes at least one of the following beneficial technical effects: On the one hand, this invention can adaptively adjust the parameters in the greenhouse based on meteorological data, making the most of meteorological conditions to adjust the greenhouse parameters and improving the energy efficiency of the control process; on the other hand, by monitoring the crop status through the crop monitoring module, it can more accurately determine the crop's needs for various environmental parameters, and thus more accurately adjust the greenhouse parameters. Therefore, it realizes a more intelligent greenhouse monitoring and control process. Attached Figure Description

[0014] Figure 1 This is a logical block diagram of the greenhouse Internet of Things monitoring system in this invention.

[0015] Figure 2 This is a screenshot of the greenhouse IoT monitoring system in this invention. Detailed Implementation

[0016] The embodiments of this application are described in detail below, and examples of the embodiments are shown in the accompanying drawings.

[0017] In the description of this specification, the references to "certain embodiments," "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples" refer to specific features, structures, materials, or characteristics described in connection with the described embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0018] This application discloses a greenhouse Internet of Things (IoT) monitoring system, referring to... Figure 1 The system includes a meteorological port, sensor components, a control center, and an execution center. The meteorological port acquires meteorological data for future periods in the region; this data includes meteorological light intensity, temperature, and humidity. It obtains this data through a meteorological API interface. The sensor components consist of multiple individual sensors located at various locations within the greenhouse, capable of acquiring environmental and soil parameters. Please refer to the appendix for details. Figure 2 As shown, environmental parameters include light intensity, ambient temperature, and ambient humidity; soil parameters include soil temperature and soil moisture; therefore, the sensor assembly includes at least a temperature sensor, a humidity sensor, and a light sensor; the crop monitoring module is used to monitor the status of crops grown in the greenhouse and obtain crop status; the control center is used to establish a parameter requirement model based on crop type and crop status; the parameter requirement model includes the requirement status of parameters in each dimension, and at the same time, a greenhouse characteristic model is established based on environmental and soil parameters. The greenhouse characteristic model reflects the current status of various dimensions of greenhouse parameters. This embodiment mainly analyzes from three main dimensions: light intensity, temperature, and humidity. Therefore, based on the greenhouse light state coefficient and greenhouse temperature... A greenhouse characteristic model is established using state coefficients and greenhouse humidity state coefficients. The greenhouse light state coefficient is determined based on light intensity, the greenhouse temperature state coefficient is determined based on ambient temperature and soil temperature, and the greenhouse humidity state coefficient is determined based on ambient humidity and soil moisture. Then, the parameter demand model is compared with the greenhouse characteristic model. The standard light demand coefficient is compared with the greenhouse light state coefficient, the standard temperature demand coefficient is compared with the greenhouse temperature state coefficient, and the standard humidity demand coefficient is compared with the greenhouse humidity state coefficient. All comparison results are used as characteristic adjustment parameters. Based on these characteristic adjustment parameters, light intensity, ambient temperature, and ambient humidity, a greenhouse adjustment strategy is determined. Please refer to the appendix for further details. Figure 2As shown, the execution center in this embodiment includes a supplemental lighting module, an external shading module, a ventilation module, and a heat preservation module. It can adjust the light, temperature, and humidity inside the greenhouse according to the greenhouse adjustment strategy, ensuring that the environmental parameters inside the greenhouse meet the requirements. Through the above process, on the one hand, the parameters inside the greenhouse can be adaptively adjusted based on meteorological data, maximizing the use of meteorological conditions to adjust the greenhouse parameters and improving the energy efficiency of the control process. On the other hand, by monitoring the crop status through the crop monitoring module, the crop's needs for various environmental parameters can be more accurately determined, thereby enabling more accurate adjustment of greenhouse parameters. Therefore, a more intelligent greenhouse monitoring and control process is achieved.

[0019] In one embodiment, the process of acquiring crop status includes: acquiring crop images in different bands using a multispectral camera; preprocessing the images, wherein the acquired bands include visible and non-visible light bands; identifying the crop based on a deep learning model to obtain the crop's location; acquiring the average projected area of ​​the crop plant and color features in different bands; determining the crop's growth prediction cycle based on the average projected area and color features; acquiring the standard plant projected area and standard color features in different bands for different growth cycles according to the crop type; performing data fitting to obtain the curve of standard plant projected area changing with the cycle and the curves of R, G, and B channel values ​​changing with the cycle in different bands; substituting the acquired average plant projected area into the curve of standard plant projected area changing with the cycle to obtain the first reference cycle; performing RGB decomposition on the color features in each band to obtain the red component Ri, green component Gi, and blue component Bi, and establishing a constraint formula: The minimum value of y(t) is obtained as the second reference period in this band; where R(t), G(t), and B(t) are the curves of the R channel, G channel, and B channel values ​​changing with the period in this band, respectively, and x = R, G, B. The weighting ratio for the x component is set based on the range of color feature changes in different bands of the test data. The more obvious the color feature changes, the higher the sensitivity, and thus the higher the weighting ratio. Through the above process, the first reference period is determined based on the size of the plant, and multiple second reference periods are determined based on the color features of the plant leaves. Therefore, the average of the first reference period and the second reference periods corresponding to different bands is calculated according to a preset ratio, and the average is used as the growth prediction period, which can improve the accuracy of the crop growth prediction period. The crop growth period is compared with the growth prediction period, and the crop growth status is obtained according to the range of the difference between the crop growth period and the growth prediction period. When the crop growth period is less than or equal to the growth prediction period, the crop growth status is judged to be normal; otherwise, the growth status is judged to be slow. At the same time, different levels are set according to the difference between the crop growth period and the growth prediction period, which can more accurately judge the crop status.

[0020] In addition, the process of establishing the parameter requirement model includes: First, obtaining the standard light requirement coefficient, standard temperature requirement coefficient, and standard humidity requirement coefficient according to the crop type and growth prediction cycle; this acquisition process is based on the summary of empirical data. For different crop types, the required light, temperature, and humidity conditions for different cycles are set according to empirical data, thereby realizing the acquisition of the standard light requirement coefficient, standard temperature requirement coefficient, and standard humidity requirement coefficient; then, judging according to the crop growth status: if the growth status is normal, it means that the current environmental parameters meet the crop growth requirements, so the parameter requirement model is further established based on the standard light requirement coefficient, standard temperature requirement coefficient, and standard humidity requirement coefficient; if the growth status is normal, it means that the current environmental parameters meet the crop growth requirements, so the parameter requirement model is further established based on the standard light requirement coefficient, standard temperature requirement coefficient, and standard humidity requirement coefficient; if the growth status is normal, the parameter requirement model is established based on the standard light requirement coefficient, standard temperature requirement coefficient, and standard humidity requirement coefficient. If the growth rate is too slow, an adjustment strategy is determined based on the range of the difference between the crop growth cycle and the predicted growth cycle. Different levels of adjustment strategies are set based on empirical data regarding the degree of slow crop growth. The adjustment strategy is obtained by considering the difference between the crop growth cycle and the predicted growth cycle. The standard light requirement coefficient, standard temperature requirement coefficient, and standard humidity requirement coefficient are adjusted accordingly. A parameter requirement model is then established based on the adjusted standard light requirement coefficient, standard temperature requirement coefficient, and standard humidity requirement coefficient. Through this process, parameter requirements can be adjusted adaptively according to different crop growth states, thereby meeting the current crop growth needs and improving the crop growth rate.

[0021] In one embodiment, please refer to the appendix. Figure 2As shown, environmental parameters also include carbon dioxide concentration; soil parameters include soil pH and soil EC values; carbon dioxide concentration, soil pH, and soil EC values ​​are monitored in real time, and an early warning is issued when any one of them exceeds the corresponding preset range; since crop growth is also affected by carbon dioxide concentration, soil pH, and soil EC values, the above process can eliminate the influence of these factors, thereby ensuring that the analysis from the three main dimensions of light, temperature, and humidity is more accurate.

[0022] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A greenhouse IoT monitoring system, characterized in that, include: The meteorological port is used to obtain meteorological data for the region in the future. Sensor components are used to acquire environmental and soil parameters inside the greenhouse; The crop monitoring module is used to monitor the status of crops grown in greenhouses and obtain crop status information. The control center is used to establish parameter demand models based on crop types and crop conditions; to establish greenhouse characteristic models based on environmental and soil parameters; to compare the parameter demand models with the greenhouse characteristic models to obtain characteristic adjustment parameters; and to determine greenhouse adjustment strategies based on the characteristic adjustment parameters and meteorological data. The execution center is used to implement greenhouse adjustment strategies.

2. The greenhouse IoT monitoring system according to claim 1, characterized in that, The process of obtaining crop status includes: Images of crops are acquired using a multispectral camera in different bands. The images are preprocessed, and the average projected area of ​​the crop plants and color features in different bands are collected based on a deep learning model. The crop growth prediction cycle is determined based on the average projected area and color features. The crop growth cycle is compared with the growth prediction cycle, and the crop growth status is obtained based on the range of the difference between the crop growth cycle and the growth prediction cycle.

3. The greenhouse IoT monitoring system according to claim 2, characterized in that, The process of determining the crop growth cycle includes: Based on the crop type, the standard plant projection area and standard color characteristics of the crop under different growth cycles and different bands are obtained. Data fitting is performed to obtain the curve of standard plant projection area changing with the cycle and the curve of R channel, G channel and B channel values ​​changing with the cycle under different bands. Substitute the collected average projected area of ​​the plant into the curve of the standard plant's projected area changing with the period to obtain the first reference period. The color features under each band are decomposed into RGB components to obtain the red component Ri, the green component Gi, and the blue component Bi. A constraint formula is then established. The minimum value of y(t) is obtained as the second reference period in this band; where R(t), G(t), and B(t) are the curves of the R channel, G channel, and B channel values ​​changing with the period in this band, respectively, and x = R, G, B. The weight ratio of the x component; The average value is calculated based on the first reference period and the second reference period corresponding to different bands according to a preset ratio, and the average value is used as the growth prediction period.

4. The greenhouse IoT monitoring system according to claim 1, characterized in that, The process of establishing the parameter requirement model includes: Obtain the standard light requirement coefficient, standard temperature requirement coefficient, and standard humidity requirement coefficient according to the crop type and growth prediction cycle; Judging based on the crop's growth status: If the growth status is normal, then establish a parameter requirement model based on the standard light requirement coefficient, standard temperature requirement coefficient, and standard humidity requirement coefficient. If the growth status is slow, an adjustment strategy is determined based on the range of the difference between the crop growth cycle and the predicted growth cycle. The standard light demand coefficient, standard temperature demand coefficient, and standard humidity demand coefficient are adjusted according to the adjustment strategy. A parameter demand model is established based on the adjusted standard light demand coefficient, standard temperature demand coefficient, and standard humidity demand coefficient.

5. A greenhouse IoT monitoring system according to claim 4, characterized in that, The environmental parameters include light intensity, ambient temperature, and ambient humidity; The soil parameters include soil temperature and soil moisture; Determine the greenhouse light state coefficient based on light intensity; The greenhouse temperature state coefficient is determined based on the ambient temperature and soil temperature. The greenhouse humidity state coefficient is determined based on ambient humidity and soil moisture. A greenhouse characteristic model is established based on the greenhouse light state coefficient, greenhouse temperature state coefficient, and greenhouse humidity state coefficient.

6. A greenhouse IoT monitoring system according to claim 5, characterized in that, The feature comparison process includes: The standard light demand coefficient is compared with the greenhouse light state coefficient, the standard temperature demand coefficient is compared with the greenhouse temperature state coefficient, and the standard humidity demand coefficient is compared with the greenhouse humidity state coefficient. The comparison results are used as characteristic adjustment parameters.

7. A greenhouse IoT monitoring system according to claim 6, characterized in that, The meteorological data includes meteorological light intensity, meteorological temperature, and meteorological humidity; Greenhouse adjustment strategies are determined based on characteristic adjustment parameters, light intensity, meteorological temperature, and meteorological humidity.

8. A greenhouse IoT monitoring system according to claim 7, characterized in that, The execution center includes a supplementary lighting module, an external sunshade module, a ventilation module, and a heat preservation module.

9. A greenhouse IoT monitoring system according to claim 4, characterized in that, The environmental parameters also include carbon dioxide concentration; the soil parameters also include soil pH and soil EC values; the carbon dioxide concentration, soil pH, and soil EC values ​​are monitored in real time, and an early warning is issued when any one of them exceeds the corresponding preset range.

Images