Garden plant disease and insect pest intelligent early warning system based on Internet of Things

Abstract

The invention relates to the field of disease and insect pest monitoring, and discloses a garden plant disease and insect pest intelligent early warning system based on Internet of Things, comprising an environment monitoring module for collecting environment data related to disease and insect pest breeding based on a sensor network; the pest trapping and counting module is used for trapping pests by using an intelligent trapping device of a pest attractant and is provided with a counting sensor and a pest classification and identification unit to obtain the population density of different types of pests; the plant phenotype monitoring module captures plant phenotype changes by deploying high-definition multispectral camera equipment, and automatically diagnoses pest and disease damage types by using an image recognition algorithm; and the disease and pest early warning module analyzes by using a preset early warning model based on the data of the environment monitoring module, the pest trapping statistics module and the plant phenotype monitoring module to obtain disease and pest indexes, compares the disease and pest indexes with a preset threshold value, and immediately sends out early warning information once the disease and pest indexes exceed the preset threshold value.

Description

Technical Field

[0001] The present invention relates to the field of pest and disease monitoring, and in particular to an intelligent early warning system for garden plant pests and diseases based on the Internet of Things. Background Art

[0002] In the daily management of existing garden plants, the main objects of supervision are diseases and pests. Once plants are infected with diseases and pests and are not discovered in time, they will lead to a large-scale spread of diseases and pests, seriously affecting the growth or health of the plants and causing garden losses.

[0003] The traditional method of pest and disease control is still through manual inspections. On the one hand, manual inspections require a lot of manpower and material resources. On the other hand, the inspection effect mainly depends on the responsibility and ability of the inspectors. Therefore, the judgment results are highly subjective and prone to missed reports or false reports.

[0004] In order to improve the efficiency of supervision, Internet of Things devices have been introduced, including: sensor networks, which monitor the breeding conditions of pests and diseases through environmental sensors such as temperature, humidity, and light; high-definition camera equipment, which deploys multi-spectral cameras to capture plant phenotypic changes and combines image recognition algorithms such as CNN to automatically diagnose the types of pests and diseases; smart trapping devices, which use sex pheromones or light sources to trap pests and use counting sensors to count the insect population density.

[0005] Although it can solve the problems of traditional methods, it still has some defects, such as:

[0006] The replacement of insect attractants used in intelligent trapping devices relies on a fixed cycle, without considering the impact of environmental factors on their volatilization rate. Manual inspection of the attractant status is time-consuming and labor-intensive, and cannot respond to sudden insect infestations in real time. Summary of the Invention

[0007] The purpose of the present invention is to provide an intelligent early warning system for garden plant diseases and insect pests based on the Internet of Things, so as to solve the technical problems that the replacement of attractants used in intelligent trapping devices depends on a fixed cycle, does not consider the influence of environmental factors on their volatilization rate, and manual inspection of the attractant status is time-consuming and labor-intensive, and cannot respond to sudden insect infestations in real time.

[0008] The purpose of the present invention can be achieved through the following technical solutions:

[0009] An intelligent early warning system for garden plant diseases and insect pests based on the Internet of Things, comprising:

[0010] An environmental monitoring module collects environmental data related to pest and disease breeding based on a sensor network; the sensor network includes: temperature and humidity sensors, light sensors, and soil sensors;

[0011] The pest trapping and statistics module uses an intelligent trapping device with insect attractants to trap pests, and is equipped with a counting sensor and a pest classification and identification unit to obtain the population density of different types of pests;

[0012] The plant phenotypic monitoring module deploys multispectral cameras to capture plant phenotypic changes and uses image recognition algorithms to automatically diagnose pest and disease types;

[0013] The pest and disease early warning module, based on the data from the environmental monitoring module, the pest trapping statistics module, and the plant phenotypic monitoring module, obtains pest and disease indicators through pest and disease early warning model analysis, compares the pest and disease indicators with the preset thresholds, and immediately issues a warning message once the pest and disease indicators exceed the preset thresholds.

[0014] Through the above technical solution, the environmental monitoring module, pest trapping statistics module and plant phenotypic monitoring module work together to collect multi-dimensional data, and use the pest and disease early warning model for analysis. It can accurately calculate pest and disease indicators and compare them with preset thresholds to issue early warning information in a timely and accurate manner, effectively avoiding large-scale outbreaks of pests and diseases and reducing losses in garden plants.

[0015] As a further technical solution, the system further comprises: an insect attractant intelligent management module;

[0016] The insect attractant intelligent management module includes:

[0017] Environmental parameter acquisition unit, used to collect environmental factor data in real time, including air temperature, humidity, and wind speed data;

[0018] A volatilization rate calculation unit is used to calculate the real-time volatilization rate of the insect attractant based on the collected environmental factor data;

[0019] The status monitoring and replacement cycle adjustment unit determines whether to adjust the insect attractant replacement cycle based on a comprehensive analysis of the real-time volatilization rate and the real-time monitoring of the remaining amount of insect attractant.

[0020] Through the above technical solution, the introduction of the attractant intelligent management module can collect environmental factor data in real time, accurately calculate the volatilization rate of the attractant, and adjust the replacement cycle based on a comprehensive analysis of the volatilization rate and the remaining amount of attractant, which not only saves labor costs, but also ensures that the attractant always maintains a good trapping effect.

[0021] As a further technical solution, the image recognition algorithm is a pre-trained convolutional neural network model, and the plant phenotype monitoring module also includes an image preprocessing unit to perform noise reduction, enhancement and normalization on the images obtained by the multispectral camera device.

[0022] As a further technical solution, the environmental data includes air temperature and humidity, light intensity, soil pH, fertility and moisture content parameters.

[0023] Through the above technical solution, the environmental monitoring module uses a sensor network including temperature and humidity sensors, light sensors and soil sensors to comprehensively collect parameters such as air temperature and humidity, light intensity, soil pH, fertility and moisture content, providing rich and accurate data support for pest and disease early warning, making the early warning results more scientific and reliable.

[0024] As a further technical solution, the pest warning model is expressed as follows:

[0025]

[0026] Among them, G is the pest index, g1, g2, g3 are weight coefficients, and g1+g2+g3=1, B is the number of environmental parameters, μ is any environmental parameter, γ μ is the influence coefficient corresponding to any environmental parameter, A is the total number of sampling times after the preset time period from the current moment, x j is the observed value of the current environmental parameter obtained by the j-th sampling, The mean value of the current environmental parameters;

[0027] k i is the weight coefficient of the impact of the i-th pest on the occurrence of pests and diseases, b is the number of pest species, N i is the insect population density value obtained by counting sensors after the i-th type of pest is identified by the pest classification and identification unit, F is the quantitative value of the severity of the pest diagnosed by the image recognition algorithm, and F s It is the reference value for the severity of pests and diseases.

[0028] As a further technical solution, the calculation formula for the real-time volatilization rate of the insect attractant is:

[0029]

[0030] Among them, R is the real-time volatilization rate of the attractant, T is the air temperature, H is the air humidity, W is the wind speed, τ t , τ h , τ w is the impact factor.

[0031] As a further technical solution, the process of determining whether to adjust the attractant replacement cycle is as follows:

[0032] Substitute the calculated real-time volatilization rate R of the attractant into the following formula:

[0033]

[0034] Calculate the adjusted replacement cycle C;

[0035] Where C0 is the initial replacement cycle, ε is the adjustment factor, and Y R,V is the coefficient of variation of the attractant per unit time, is the threshold value of attractant change per unit time.

[0036] As a further technical solution, the calculation formula of the coefficient of variation of the insect attractant per unit time is:

[0037]

[0038] Among them, V(t) is the curve of the volume of the attractant changing with time, R(t) is the curve of the real-time volatilization rate of the attractant changing with time, α and β are the preset proportional coefficients, t i , t i+1 The starting and ending points of the unit time.

[0039] Beneficial effects of the present invention:

[0040] (1) Through the collaborative work of the environmental monitoring module, the pest trapping statistics module and the plant phenotypic monitoring module, multi-dimensional data is collected and analyzed using the pest and disease early warning model. The pest and disease indicators can be accurately calculated and compared with the preset thresholds, and early warning information can be issued in a timely and accurate manner, effectively avoiding large-scale outbreaks of pests and diseases and reducing losses in garden plants.

[0041] (2) The attractant intelligent management module can collect environmental factor data in real time, accurately calculate the volatilization rate of the attractant, and adjust the replacement cycle based on the comprehensive analysis of the volatilization rate and the remaining amount of the attractant, which not only saves labor costs but also ensures that the attractant always maintains a good trapping effect. For example, in hot and windy weather, the system detects that the volatilization rate of the attractant is accelerated and automatically shortens the replacement cycle, ensuring the effectiveness of pest trapping.

[0042] (3) The environmental monitoring module uses a sensor network including temperature and humidity sensors, light sensors and soil sensors to comprehensively collect parameters such as air temperature and humidity, light intensity, soil pH, fertility and moisture content, providing rich and accurate data support for pest and disease early warning, making the early warning results more scientific and reliable. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The present invention will be further described below with reference to the accompanying drawings.

[0044] Figure 1 It is the system logic block diagram of the present invention. DETAILED DESCRIPTION

[0045] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0046] See also Figure 1 As shown, the present invention is an intelligent early warning system for garden plant diseases and insect pests based on the Internet of Things, comprising:

[0047] An environmental monitoring module collects environmental data related to pest and disease breeding based on a sensor network; the sensor network includes: temperature and humidity sensors, light sensors, and soil sensors;

[0048] The pest trapping and statistics module uses an intelligent trapping device that uses insect attractants to trap pests. It is equipped with a counting sensor and a pest classification and identification unit to obtain the population density of different pest types. It should be noted that the pest classification and identification unit is a function configured in existing intelligent trapping devices. It can collect image data from the intelligent trapping device through a surveillance camera and then process it through image recognition technology to achieve pest classification. As long as the above functions can be achieved, it is a mature existing technology, so it will not be elaborated on in detail.

[0049] The plant phenotypic monitoring module deploys multispectral cameras to capture plant phenotypic changes and uses image recognition algorithms to automatically diagnose pest and disease types;

[0050] The pest and disease early warning module, based on the data from the environmental monitoring module, the pest trapping statistics module, and the plant phenotypic monitoring module, obtains pest and disease indicators through pest and disease early warning model analysis, compares the pest and disease indicators with the preset thresholds, and immediately issues a warning message once the pest and disease indicators exceed the preset thresholds.

[0051] The system also includes: an insect attractant intelligent management module;

[0052] The insect attractant intelligent management module includes:

[0053] Environmental parameter acquisition unit, used to collect environmental factor data in real time, including air temperature, humidity, and wind speed data;

[0054] A volatilization rate calculation unit is used to calculate the real-time volatilization rate of the insect attractant based on the collected environmental factor data;

[0055] The status monitoring and replacement cycle adjustment unit determines whether to adjust the insect attractant replacement cycle based on a comprehensive analysis of the real-time volatilization rate and the real-time monitoring of the remaining amount of insect attractant.

[0056] The image recognition algorithm is a pre-trained convolutional neural network model, and the plant phenotype monitoring module also includes an image preprocessing unit that performs noise reduction, enhancement and normalization on images acquired by the multispectral camera device.

[0057] The environmental data include air temperature and humidity, light intensity, soil pH, fertility and moisture content parameters.

[0058] In this embodiment, the environmental monitoring module, the pest trapping statistics module, and the plant phenotyping monitoring module work together. The environmental monitoring module is responsible for collecting multi-dimensional environmental data, covering air temperature and humidity, light intensity, soil pH, etc.; the pest trapping statistics module counts different pest species and corresponding insect population densities; and the plant phenotyping monitoring module diagnoses the severity of pests and diseases.

[0059] The data collected by these modules is aggregated into the pest and disease early warning module, where it is comprehensively quantified using a pre-set early warning model. This comprehensive multi-source data calculation method comprehensively considers all factors that influence the occurrence of pests and diseases. Compared with evaluation methods that rely solely on a single factor or a simple combination of factors, it greatly improves the accuracy and scientific nature of pest and disease early warnings. It can accurately calculate pest and disease indicators and compare them with pre-set thresholds. Once an indicator exceeds the threshold, a warning message can be issued promptly and accurately, effectively avoiding large-scale outbreaks of pests and diseases, thereby reducing losses to garden plants.

[0060] Accurate early warning provides strong support for garden managers, enabling them to timely and accurately grasp the potential risks of pests and diseases in the garden, and formulate and take targeted prevention and control measures in advance; for example, in areas with low pest and disease risks, managers can strengthen daily monitoring; and in areas with higher risks, they can prepare pesticides and arrange prevention and control personnel in advance, so as to effectively reduce the damage of pests and diseases to garden plants, reduce economic losses, and protect the stability and beauty of the garden ecological environment.

[0061] In addition, the intelligent attractant management module in the system plays an important role; it can collect environmental factor data in real time, accurately calculate the volatilization rate of the attractant, and conduct a comprehensive analysis based on the remaining amount of attractant, and then adjust the replacement cycle of the attractant; intelligent attractant management not only saves labor costs, but also ensures that the attractant always maintains a good trapping effect; for example, in hot and windy weather, the module detects that the volatilization rate of the attractant is accelerated, and automatically shortens the replacement cycle, ensuring the effectiveness of pest trapping.

[0062] The expression of the pest early warning model is:

[0063]

[0064] Among them, G is the pest index, g1, g2, and g3 are weight coefficients determined based on historical data analysis, and g1+g2+g3=1, B is the number of environmental parameters, μ is any environmental parameter, γ μ is the influence coefficient corresponding to any environmental parameter, which is formulated based on experimental data and historical data. A is the total number of sampling times after the preset time period from the current moment. j is the observed value of the current environmental parameter obtained by the j-th sampling, The mean value of the current environmental parameters;

[0065] k i is the weight coefficient of the impact of the i-th pest on the occurrence of pests and diseases, b is the number of pest species, N i is the insect population density value obtained by counting sensors after the i-th pest is identified by the pest classification and identification unit. F is the quantitative value of the severity of the pest diagnosed by the image recognition algorithm, for example, it is divided into levels 1-5 from mild to severe. s It is the reference value for the severity of pests and diseases.

[0066] In this embodiment, the expression of the pest warning model is provided: The above formula takes into account environmental parameters, pest factors and the severity of pests and diseases; Ability to accurately calculate the impact of environmental parameter fluctuations on pests and diseases, It can reflect the impact of different pest species and insect population density. It can measure the relationship between the current severity of pests and diseases and the reference value; the pest and disease early warning model comprehensively integrates multi-source data, improves the accuracy and scientificity of pest and disease early warning, and can accurately assess the risk of pest and disease occurrence based on actual monitoring data, providing accurate decision-making basis for garden management, helping to take prevention and control measures in a timely manner and reduce the damage of pests and diseases to garden plants.

[0067] The calculation formula of the real-time volatilization rate of the insect attractant is:

[0068]

[0069] Among them, R is the real-time volatilization rate of the attractant, T is the air temperature, H is the air humidity, W is the wind speed, τ t , τ h , τ w It is an influencing factor, which is determined according to the characteristics of different attractants and experimental data.

[0070] In this embodiment, a calculation formula for the real-time volatilization rate of the insect attractant is provided. By incorporating environmental factors such as air temperature, humidity, and wind speed into the calculation formula, a dynamic calculation of the real-time volatilization rate of the attractant is achieved. The formula comprehensively considers the main environmental factors that affect the volatilization of the attractant, and is more in line with actual conditions than the traditional method of replacing the attractant at a fixed period without considering environmental changes. This achieves the purpose of obtaining the volatilization rate of the attractant in real time and provides a scientific and accurate basis for adjusting the attractant replacement cycle. For example, in an environment with high temperature, low humidity, and strong winds, the volatilization rate calculated by the formula is accelerated, which can be used to shorten the attractant replacement cycle, ensure that the attractant always maintains sufficient concentration and activity, improve the efficiency of the attractant, reduce the risk of ineffective pest control due to the failure of the attractant, reduce pest damage to garden plants, and avoid unnecessary waste of attractants, thereby reducing the cost of control.

[0071] The process for determining whether to adjust the attractant replacement cycle is:

[0072] Substitute the calculated real-time volatilization rate R of the attractant into the following formula:

[0073]

[0074] Calculate the adjusted replacement cycle C;

[0075] Among them, C0 is the initial replacement cycle, ε is the adjustment factor, which is formulated based on historical data and experimental data, and Y R,V is the coefficient of variation of the attractant per unit time, is the change threshold of the attractant per unit time.

[0076] In this embodiment, when the coefficient of variation of the attractant per unit time Y R,V Less than the change threshold When the attractant consumption is relatively stable, the initial replacement cycle is maintained; when the attractant variation coefficient Y R,V Greater than or equal to the change threshold When the volatilization rate is higher, the replacement cycle is adjusted according to the real-time volatilization rate. The faster the volatilization rate is, the shorter the replacement cycle is after adjustment.

[0077] By comparing the coefficient of variation of the attractant per unit time with the threshold of variation, and combining it with the real-time volatilization rate of the attractant, the intelligent and dynamic adjustment of the attractant replacement cycle is achieved. The actual consumption of the attractant (reflected by the coefficient of variation) and the real-time volatilization rate are comprehensively considered to avoid the unreasonable situation that may occur when replacing the attractant at a fixed period. For example, when environmental conditions change and the volatilization of the attractant accelerates, and the coefficient of variation exceeds the threshold, the replacement cycle is shortened to ensure that the attractant continues to work; conversely, if the attractant is consumed slowly, the replacement cycle is appropriately extended. The above adjustment mechanism ensures that the attractant always maintains a good trapping effect, improves the efficiency of pest trapping, effectively reduces the damage caused by pests to garden plants, and optimizes the use of attractants, reduces the cost of manual inspections and replacement of attractants, and improves the efficiency and economy of garden pest control work.

[0078] The calculation formula of the coefficient of variation of the attractant per unit time is:

[0079]

[0080] Among them, V(t) is the curve of the volume of the attractant changing with time, R(t) is the curve of the real-time volatilization rate of the attractant changing with time, α and β are preset proportional coefficients, which are determined based on historical data and experimental data. i , t i+1 The starting and ending points of the unit time.

[0081] In this embodiment, the cumulative change of the volume of the attractant and the real-time volatilization rate per unit time is calculated by integration. Obviously, if the cumulative change is larger, it means that the attractant is consumed faster and evaporated faster within the unit time. Therefore, the coefficient of variation of the attractant per unit time, Y, is R,V The bigger.

[0082] It should be noted that the calculation formulas and various parameters involved in the calculations in the present invention have been dimensionally processed in advance, and the process of dimensionless processing is well known in the industry and will not be described here.

[0083] The above is a detailed description of an embodiment of the present invention. However, the content described is only a preferred embodiment of the present invention and should not be considered to limit the scope of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. An intelligent early warning system for garden plant diseases and insect pests based on the Internet of Things, characterized by: include: Environmental monitoring module, which collects environmental data related to pest and disease breeding based on sensor networks; The sensor network includes: temperature and humidity sensors, light sensors and soil sensors; The pest trapping and statistics module uses an intelligent trapping device with insect attractants to trap pests, and is equipped with a counting sensor and a pest classification and identification unit to obtain the population density of different types of pests; The plant phenotypic monitoring module deploys multispectral cameras to capture plant phenotypic changes and uses image recognition algorithms to automatically diagnose pest and disease types; The pest and disease early warning module, based on the data from the environmental monitoring module, the pest trapping statistics module, and the plant phenotypic monitoring module, obtains pest and disease indicators through pest and disease early warning model analysis, compares the pest and disease indicators with the preset thresholds, and immediately issues a warning message once the pest and disease indicators exceed the preset thresholds.

2. The intelligent early warning system for garden plant diseases and insect pests based on the Internet of Things according to claim 1 is characterized in that: The system also includes: an insect attractant intelligent management module; The insect attractant intelligent management module includes: Environmental parameter acquisition unit, used to collect environmental factor data in real time, including air temperature, humidity, and wind speed data; A volatilization rate calculation unit is used to calculate the real-time volatilization rate of the insect attractant based on the collected environmental factor data; The status monitoring and replacement cycle adjustment unit determines whether to adjust the insect attractant replacement cycle based on a comprehensive analysis of the real-time volatilization rate and the real-time monitoring of the remaining amount of insect attractant.

3. The intelligent early warning system for garden plant diseases and insect pests based on the Internet of Things according to claim 1 or 2, characterized in that: The image recognition algorithm is a pre-trained convolutional neural network model, and the plant phenotype monitoring module also includes an image preprocessing unit that performs noise reduction, enhancement and normalization on images acquired by the multispectral camera device.

4. The intelligent early warning system for garden plant diseases and insect pests based on the Internet of Things according to claim 1 is characterized in that: The environmental data include air temperature and humidity, light intensity, soil pH, fertility and moisture content parameters.

5. The intelligent early warning system for garden plant diseases and insect pests based on the Internet of Things according to claim 1 is characterized in that: The expression of the pest early warning model is: Among them, G is the pest index, g1, g2, g3 are weight coefficients, and g1+g2+g3=1, B is the number of environmental parameters, μ is any environmental parameter, γ μ is the influence coefficient corresponding to any environmental parameter, A is the total number of sampling times after the preset time period from the current moment, x j is the observed value of the current environmental parameter obtained by the j-th sampling, The mean value of the current environmental parameters; k i is the weight coefficient of the impact of the i-th pest on the occurrence of pests and diseases, b is the number of pest species, N i is the insect population density value obtained by counting sensors after the i-th type of pest is identified by the pest classification and identification unit, F is the quantitative value of the severity of the pest diagnosed by the image recognition algorithm, and F s It is the reference value for the severity of pests and diseases.

6. The intelligent early warning system for garden plant diseases and insect pests based on the Internet of Things according to claim 2 is characterized in that: The calculation formula of the real-time volatilization rate of the insect attractant is: Among them, R is the real-time volatilization rate of the attractant, T is the air temperature, H is the air humidity, W is the wind speed, τ t , τ h , τ w is the impact factor.

7. The intelligent early warning system for garden plant diseases and insect pests based on the Internet of Things according to claim 6 is characterized in that: The process for determining whether to adjust the attractant replacement cycle is: Substitute the calculated real-time volatilization rate R of the attractant into the following formula: Calculate the adjusted replacement cycle C; Where C0 is the initial replacement cycle, ε is the adjustment factor, and Y R,V is the coefficient of variation of the attractant per unit time, is the threshold value of attractant change per unit time.

8. The intelligent early warning system for garden plant diseases and insect pests based on the Internet of Things according to claim 7 is characterized in that: The calculation formula of the coefficient of variation of the attractant per unit time is: Among them, V(t) is the curve of the volume of the attractant changing with time, R(t) is the curve of the real-time volatilization rate of the attractant changing with time, α and β are the preset proportional coefficients, t i , t i+1 The starting and ending points of the unit time.

Images