CN-121978016-A - Facility vegetable pest monitoring and predicting method and system based on Internet of things

CN121978016ACN 121978016 ACN121978016 ACN 121978016ACN-121978016-A

Abstract

The invention relates to the technical field of intelligent agriculture and agriculture Internet of things, and discloses a method and a system for monitoring and predicting plant diseases and insect pests of facility vegetables based on the Internet of things, wherein the method comprises the steps of firstly measuring the heat plume transmission delay time; the method comprises the steps of controlling an active photo-thermal excitation unit to emit a modulated optical signal, generating thermal wave propagation in a blade and inducing directional thermotropic convection plume, setting a holographic capture phase window based on delay time, cooperatively collecting infrared image sequences and aerosol particle diffraction patterns on the surface of the blade, extracting thermal impedance characteristics reflecting air hole conductivity through digital phase locking operation, identifying pathogen concentration through holographic reconstruction, and finally fusing thermal impedance and pathogen concentration information to carry out multidimensional judgment. According to the invention, the physiological state and pathogen information of the plant are synchronously acquired by utilizing a heat flow coupling mechanism, so that non-invasive physiological stress and early infection of diseases are effectively distinguished, and the accurate and active monitoring and early warning of the plant diseases and insect pests of the facility vegetables are realized.

Inventors

YAN XIAOBO
GUO YAO
WANG JU
LIU XIAOXIA
LIU JIANMIN
Yan Gezi
LI ZONGLUN
LIU QING

Assignees

河南元丰科技网络股份有限公司

Dates

Publication Date: 20260505
Application Date: 20260114

Claims (10)

1. The facility vegetable pest monitoring and predicting method based on the Internet of things is characterized by comprising the following steps of: S1, acquiring physical distance parameters between a monitoring terminal and a target blade and between the target blade and an air suction port of the monitoring terminal, acquiring current environment temperature and relative humidity, and calculating a thermal plume transmission delay time required by thermal convection plume to be transmitted from the surface of the target blade to the air suction port based on the physical distance parameters, the current environment temperature and the relative humidity; s2, controlling the active photo-thermal excitation unit to emit a modulated periodic optical signal to the target blade, generating thermal wave propagation in the target blade, and heating an air boundary layer on the surface of the target blade so as to generate a directional flowing thermal convection plume; S3, acquiring an infrared image sequence of the surface of a target blade through an infrared thermal image sensing unit, calculating a holographic capture phase window according to the thermal plume transmission delay time, and triggering a microfluidic lens-free holographic sensing unit to acquire diffraction patterns of aerosol particles only when the phase of the periodic optical signal is in the holographic capture phase window; S4, carrying out digital phase locking operation on the infrared image sequence, extracting a thermal wave signal component with the same frequency as the periodic optical signal, calculating to obtain a phase lag diagram of the surface of the target blade, and extracting thermal impedance characteristics reflecting the conductance of the air holes according to the phase lag diagram; S5, carrying out numerical counter propagation reconstruction on the diffraction pattern to obtain a complex amplitude distribution image of the particles, extracting morphological characteristic parameters of the particles from the complex amplitude distribution image, and comparing the morphological characteristic parameters with a pathogen characteristic database to obtain a concentration value of a target pathogen; S6, judging a thermal impedance abnormal grade according to the thermal impedance characteristics, judging a spore concentration abnormal grade according to the concentration value of the target pathogen, carrying out combination judgment on the thermal impedance abnormal grade and the spore concentration abnormal grade according to a preset fusion logic rule, generating an early warning grade and outputting a control instruction.
2. The internet of things-based facility vegetable pest monitoring and forecasting method of claim 1, wherein the calculating of the thermal plume transmission delay time in step S1 includes: Determining an air density, an aerodynamic viscosity and an air thermal expansion coefficient according to the current ambient temperature and the relative humidity; Calculating the average rising speed of the thermally induced convection plume according to the average temperature rise of the surface of the target blade caused by the periodic light signal and the thermal expansion coefficient of the air; And dividing the vertical distance from the center of the surface of the target blade to the air suction port of the microfluidic lens-free holographic sensing unit by the average rising speed to obtain the thermal plume transmission delay time.
3. The method for predicting pest and disease damage of greenhouse vegetable based on the internet of things according to claim 1, wherein in the step S2, the modulation waveform of the periodic optical signal is a sine wave or a square wave, the modulation frequency range of the periodic optical signal is set to be 0.01 hz to 0.5 hz, and the active photo-thermal excitation unit adopts a near infrared light source with a wavelength in a range of 850 nm to 940 nm.
4. The internet of things-based facility vegetable pest monitoring and predicting method of claim 1, wherein the calculating the holographic acquisition phase window in step S3 includes: Converting the thermal plume transmission delay time into a phase delay angle according to the modulation frequency of the periodic optical signal; Superposing the phase delay angle on the energy peak phase of the periodic optical signal to obtain a center phase; And setting a phase interval with a preset width before and after the central phase, taking the phase interval as the holographic capturing phase window, and enabling the microfluidic lens-free holographic sensing unit to execute a collection action only in the holographic capturing phase window to filter out environmental background noise which is not originated from the surface of the target blade.
5. The method for predicting pest and disease damage of greenhouse vegetable based on the internet of things according to claim 1, wherein the step of calculating the phase lag map of the target blade surface in the step S4 comprises: extracting the time-dependent change data of the temperature values of the pixel points for each pixel point in the infrared image sequence to form a temperature time sequence; Performing discrete Fourier transform or integral operation on the temperature time sequence and a preset same-frequency in-phase reference signal and a same-frequency quadrature reference signal respectively to obtain an in-phase component and a quadrature component of the pixel temperature response signal at a modulation frequency; and determining phase lag values of the pixel points by performing arctangent operation on the ratio of the quadrature component to the in-phase component, wherein the phase lag map is formed by the phase lag values of all the pixel points, and the phase lag values are used for representing the local thermal impedance characteristics of the target blade.
6. The internet of things-based facility vegetable pest monitoring and forecasting method of claim 1, wherein the step S5 of performing numerical counter-propagating reconstruction on the diffraction pattern comprises: performing two-dimensional Fourier transform on the preprocessed diffraction pattern so as to convert the diffraction pattern into a spatial spectrum domain; Multiplying in the spatial spectral domain a phase transfer function describing a phase change of a light wave counter propagating from the sensor plane to an original object plane in which the particles are located; and carrying out two-dimensional inverse Fourier transform on the multiplied result to obtain the complex amplitude distribution image containing particle morphology information and phase information.
7. The method for predicting the pest and disease damage of the greenhouse vegetable based on the internet of things according to claim 1, wherein the step S6 comprises the following steps of: when the abnormal thermal impedance level reaches a preset threshold and the abnormal spore concentration level is normal, judging that the spore concentration level is in a non-invasive physiological stress state; When the spore concentration abnormal level reaches a preset threshold and the thermal impedance abnormal level is normal, judging that the spore concentration abnormal level is in an environmental pathogen potential risk state; When the abnormal thermal impedance level and the abnormal spore concentration level reach a preset first-level threshold at the same time, judging that the disease early-stage infection risk state is achieved; and judging an invasive disease outbreak state when the abnormal thermal impedance level reaches a preset second level threshold and the abnormal spore concentration level reaches a preset first level threshold or second level threshold.
8. The internet of things-based facility vegetable pest monitoring and forecasting method of claim 7, wherein the control instructions include: outputting a first-level early warning signal and triggering an irrigation system aiming at the non-invasive physiological stress state; outputting a secondary early warning signal aiming at the potential risk state of the environmental pathogen; outputting three-level early warning signals and triggering an accurate pesticide application system aiming at the early infection risk state of the disease; and outputting a four-level early warning signal and triggering the highest priority intervention measure aiming at the outbreak state of the invasive disease.
9. The internet of things-based facility vegetable pest monitoring and forecasting method of claim 6, wherein the step S5 further comprises a preprocessing step before the numerical counter-propagating reconstruction of the diffraction pattern: Subtracting a pre-collected background diffraction pattern which does not contain particles from the collected diffraction pattern, and eliminating static interference fringe noise; And linearly scaling the intensity value of the diffraction pattern after background subtraction to a preset standard range for normalization processing.
10. The system for monitoring and predicting the plant diseases and insect pests of the greenhouse vegetable based on the Internet of things is characterized by comprising a heat flow coupling monitoring terminal, a network transmission module and an application layer server, wherein the system is used for executing the method for monitoring and predicting the plant diseases and insect pests of the greenhouse vegetable based on the Internet of things, and the method is characterized in that the system comprises the following steps of; The heat flow coupling monitoring terminal comprises an edge calculation and cooperative control unit, an active photo-thermal excitation unit, a microfluidic lens-free holographic sensing unit and an infrared thermal image sensing unit; the active photo-thermal excitation unit is arranged at the lower part of the thermal flow coupling monitoring terminal and is used for irradiating a selected area from the lower part of the target blade and inducing to generate upward thermally induced convection plumes; The air suction port of the microfluidic lens-free holographic sensing unit is arranged at the upper part of the thermal flow coupling monitoring terminal and is aligned to the position right above the irradiation area of the active photo-thermal excitation unit, and the air suction port is used for receiving the thermally induced convection plume and collecting diffraction patterns carrying particles; The infrared thermal image sensing unit is arranged on the heat flow coupling monitoring terminal, and a field of view covers an irradiation area of the active photo-thermal excitation unit and is used for acquiring an infrared image sequence; The edge calculation and cooperative control unit is respectively connected with the active photo-thermal excitation unit, the microfluidic lens-free holographic sensing unit and the infrared thermal image sensing unit and is used for generating a modulation signal, calculating a holographic capture phase window and sending out synchronous acquisition pulses.

Description

Facility vegetable pest monitoring and predicting method and system based on Internet of things Technical Field The invention relates to the technical field of intelligent agriculture and agriculture Internet of things, in particular to a facility vegetable pest and disease damage monitoring and predicting method and system based on the Internet of things. Background Currently, greenhouse vegetable planting is an important industry for guaranteeing stable supply of agricultural products, and the production scale thereof is increasingly enlarged. However, the microclimate characteristics of high temperature, high humidity and relatively closed airflow are common in the greenhouse, and various fungal diseases and insect pests are easily induced in the environment. If the intervention cannot be performed in time at the early stage of disease outbreak, the yield and quality of crops are often reduced. Therefore, the modern Internet of things technology is utilized to monitor the growth environment and the health state of crops in real time and continuously, and the method has become a key link for realizing the accurate management of facility agriculture and reducing the pesticide usage amount. Aiming at disease monitoring in a facility environment, the prior art mainly adopts a monitoring scheme based on machine vision image recognition or environmental spore capture. The machine vision scheme is used for distributing visible light or multispectral cameras in a greenhouse, acquiring crop canopy images at fixed time, and identifying focuses by analyzing color and texture changes of the surfaces of blades through an algorithm. In the spore capturing scheme, an inhalation type sampler is mostly used, air in a greenhouse is inhaled through an internal fan, particles in the air are impacted and settled on a glass slide or a sticky adhesive tape, and then a microscopic imaging system is used for carrying out morphological recognition and counting on settled spores, so that the occurrence probability of diseases is deduced. Although the above approaches have achieved automated monitoring to some extent, there are a number of technical bottlenecks. Firstly, the visual characterization-based method has hysteresis, and can be generally identified only when macroscopic lesions or necrotic tissues appear on the surface of the leaf, and at the moment, pathogens often finish infection and spread in plants, and the best prevention and control time of the submerged period is missed. Secondly, traditional spore capture equipment adopts wide area passive inspiration mode more, and the sampling lacks space directionality, can't distinguish whether the spore that catches is derived from the target plant of current monitoring or drifts along with the air current and get away from the environmental background noise, and easily receive a large amount of raise dust interference in the greenhouse, lead to the false alarm rate higher. In addition, in the existing monitoring system, the thermal infrared information reflecting the physiological state inside the plant and the spore information reflecting the existence of external pathogens are often obtained independently, and the physical and time sequence correlation is lacking. The physiological stomatal closure caused by drought and the defensive stomatal closure caused by diseases are difficult to distinguish by single thermal image data, so that the system cannot accurately identify non-invasive physiological stress and early infection disease risks. Therefore, the invention provides a facility vegetable pest monitoring and predicting method and system based on the Internet of things, which solve the defects in the prior art. Disclosure of Invention Aiming at the defects of the prior art, the invention provides a method and a system for monitoring and predicting the plant diseases and insect pests of the greenhouse vegetable based on the Internet of things, which solve the problems that the monitoring dimension is single, physiological stress and early infection of the plant diseases are difficult to distinguish and early warning is delayed in the existing monitoring technology of the plant diseases and insect pests of the greenhouse vegetable. In order to achieve the above purpose, the invention is realized by the following technical scheme: In a first aspect, the invention provides a method for monitoring and predicting plant diseases and insect pests of a facility vegetable based on the Internet of things, which comprises the following steps: s1, acquiring physical distance parameters between a monitoring terminal and a target blade and between the target blade and an air suction port of the monitoring terminal, acquiring the current ambient temperature and the relative humidity, and calculating a thermal plume transmission delay time required by transmission of a thermally induced convection plume from the surface of the target blade to the air suction port according to the acqu