Facility fruit and vegetable laser light supplementing system and light supplementing evaluation method thereof

Abstract

The application discloses a facility fruit and vegetable laser light supplementing system and a light supplementing evaluation method thereof, relates to the technical field of light supplementing evaluation, and solves the problems of low light energy utilization of a traditional LED light supplementing system, lack of real-time monitoring means and scientific evaluation mechanism in a light supplementing process of an existing laser light supplementing system. The application constructs a facility fruit and vegetable laser light supplementing system, which comprises a sensor module, a central processing unit, a laser light source adjusting module, a spectrum adjusting module, an environment regulating module, a power module and a wireless communication module. Through steps of arranging and installing the sensor module, processing and analyzing compared data collected by the sensor, starting the regulating module to regulate the environment, regularly detecting fruit and vegetable growth index data, judging a promoting effect index and improving measures, a facility fruit and vegetable laser light supplementing evaluation method is constructed. The application can be applied to various facility agricultural scenes such as a greenhouse, a plant factory, an artificial climate chamber and a three-dimensional cultivation system, and has remarkable popularization value and industrial application prospect.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of light supplement evaluation, in particular to a facility fruit and vegetable laser light supplement system and a light supplement evaluation method thereof. BACKGROUND

[0002] With the improvement of people's living standards, the demand for the quality and yield of fruits and vegetables is increasing. Greenhouse planting technology has been widely developed, but the greenhouse framework, covering materials, etc. will block light, and the new and old degree of agricultural film also affects the light intensity, resulting in that the light intensity in the shed is significantly lower than that in the open field. In addition, there are more rain and snow in winter, and the sunshine is severely insufficient, so the weak light environment in the facility will make the fruit and vegetable plants grow weak, the fruit setting rate is low, the yield and quality are decreased, and it is also easy to occur diseases and pests, which limits the high-quality and high-yield cultivation of facility fruits and vegetables.

[0003] To solve this problem, artificial light supplement has become an important way to improve the efficiency of facility fruit and vegetable planting. The traditional light supplement method is to widely use LED light source, which can alleviate the problem of insufficient light to a certain extent, but the light energy utilization rate of the traditional LED light supplement system is only 35%-45%, which exists a certain degree of energy waste phenomenon, which is not conducive to sustainable development. Although the laser light supplement system improves the defect of low light energy utilization rate of the traditional LED light supplement system, and can reach 80%, but the spectral deviation of blue light (450 nm) and red light (660 nm) is more than 20 nm, which leads to insufficient light quality regulation precision. At the same time, the existing laser light supplement system is difficult to accurately match the demand of different growth stages of fruits and vegetables for specific spectrum, and the light energy utilization rate is limited, which cannot ensure the uniform distribution of light intensity in the whole light supplement area, and affects the consistency of fruit and vegetable growth. In addition, the existing technology seriously lacks real-time monitoring and scientific evaluation mechanism for the light supplement process, and it is difficult to realize intelligent and efficient light management goal.

[0004] Therefore, it is necessary to develop a facility fruit and vegetable light supplement evaluation method based on laser technology, which can provide scientific and objective evaluation basis for light supplement effect on the basis of improving light energy utilization efficiency, and promote the efficient development of facility agriculture. SUMMARY

[0005] In order to solve the problems of low light energy utilization rate of traditional LED light supplement system and lack of real-time monitoring means and scientific evaluation mechanism in the light supplement process of existing laser light supplement system, the present application provides a facility fruit and vegetable laser light supplement monitoring and evaluation method. The technical scheme of the present application is as follows:

[0006] A facility fruit and vegetable laser light supplement system, comprising a sensor module, a central processing unit, a laser light source adjusting module, a spectrum adjusting module, an environment regulating module, a power module and a wireless communication module;

[0007] The sensor module is used for real-time detection of light and environmental parameters in the light supplement area;

[0008] The central processing unit is used for collecting, processing and analyzing the data detected by the sensor module in real time, and sending instructions to the spectrum adjustment module and the environment control module according to the analysis results;

[0009] The spectrum adjustment module is used for adjusting the proportion and intensity of the output spectrum of the laser light source module according to the instructions;

[0010] The power module is used for providing power for the system;

[0011] The wireless communication module is used for realizing real-time transmission of data in the system.

[0012] Further, the sensor module includes an illumination intensity sensor, a spectrum sensor and an environment detection sensor; the environment detection sensor includes a temperature sensor, a humidity sensor and a carbon dioxide concentration sensor; the environment control module includes a temperature control sub-module, a humidity control sub-module and a carbon dioxide concentration control sub-module, and the environment control module controls the environment control equipment, including ventilation equipment, sunshade equipment, heating equipment, humidifying equipment, dehumidifying equipment and carbon dioxide supplementing device.

[0013] Further, the central processing unit includes a data collection layer, a data processing and analysis layer and a control instruction output layer; the data collection layer includes an illumination intensity sensor module, a spectrum sensor module and an environment sensor module; the data processing and analysis layer includes a data receiving sub-module, a data processing sub-module and a data analysis and comparison sub-module; the control instruction output layer includes a laser light source control module and an environment control module.

[0014] Further, the central processing unit further includes a data transmission module and a storage module, the data transmission module transmits data through ZigBee protocol based on AES encryption algorithm, and the transmission frequency is 5 min / time; the storage module estimates the storage capacity according to the planting period and the data collection frequency.

[0015] Further, the method for processing data by the data processing and analysis layer includes: removing the abnormal value of the illumination parameter by using 3σ criterion, and smoothing the temperature and humidity parameter data by using Kalman filtering algorithm; comparing the processed data with the preset optimal parameter range of different growth stages of fruits and vegetables to determine whether it meets the expectation; inputting the collected data into the evaluation model based on the neural network algorithm of deep learning to determine the promotion index of the laser light supplement on the growth of fruits and vegetables.

[0016] Further, the laser light source module comprises a laser diode, the laser light quality of the laser diode is adjustable among red light, blue light and green light, the laser wavelength of the laser diode is adjustable in the range of 400-700 nm, and the laser light photon flux density of the laser diode is adjustable; the facility fruit and vegetable laser light supplement system further comprises a display and feedback module for forming a visual interface of monitoring data.

[0017] A facility fruit and vegetable laser light supplement evaluation method is realized by using the above-mentioned facility fruit and vegetable laser light supplement system, and the facility fruit and vegetable laser light supplement evaluation method comprises the following steps:

[0018] S1, layout and installation of a sensor module;

[0019] S2, the central processing unit receives the data collected by the sensor module, and performs data processing and analysis;

[0020] S3, the central processing unit compares and analyzes the processed data with the pre-recorded fruit and vegetable growth model parameter range to determine whether the data collected by the sensor module meets the expectation; if yes, step S4 is entered; if not, the control module is started to perform control, and the process returns to step S2 until the expectation is met, and step S4 is entered;

[0021] S4, regularly detecting fruit and vegetable growth index data;

[0022] S5, collecting growth index data and light and environment parameter data, inputting an evaluation model based on a deep learning neural network algorithm, the evaluation model being a hybrid neural network model of long short-term memory network (LSTM) and convolutional neural network (CNN), the model being trained and optimized by using a large amount of historical experimental and actual planting data to establish a nonlinear relationship between growth index and light intensity, spectral proportion, temperature, humidity, carbon dioxide concentration and other parameters; the model is automatically learned and updated after each input of new data, and an index of promoting effect of light supplement on crop growth is calculated; whether the index meets the expectation is determined, if yes, the process is ended; if not, the data is analyzed in depth to find influencing factors, and improvement measures are taken accordingly, and the process returns to step S2 after improvement until the index meets the expectation, and the process is ended.

[0023] Further, the layout and installation of the sensor module in S1 are as follows: the light intensity sensor is arranged in a region with uniform light and no obstruction in the facility, the arrangement density is 2-3 m 2The number of the spectrum sensors is 8-10, which are arranged on the light receiving surface of the plants, at the four corners of the facility, the center point, near the light source and the edge of the facility; the temperature sensors are arranged at 20-30 cm above the plant canopy, 10-15 cm above the middle of the plant and 10-15 cm above the ground, with 3-5 sensors arranged in each layer; the humidity sensors are arranged at the ventilation openings, wall corners and dense plant areas, with no less than 6 sensors arranged; the carbon dioxide concentration sensors are arranged at a height of 30-40 cm from the plant canopy, with 4-6 sensors arranged; and the data acquisition frequency of the sensor module is 2-10 min / time.

[0024] Further, the central processing unit in S2 needs to pre-enter the environmental growth model parameters suitable for the growth of the planted fruit and vegetable crops at different stages before receiving the data collected by the sensor module.

[0025] Further, the regulation step in S3 specifically includes:

[0026] If the light intensity is lower or higher than the light intensity parameter range suitable for the growth of the fruits and vegetables, the central processing unit calculates the power value that needs to be increased or decreased according to the difference in photosynthetic photon flux density and the light source power-photosynthetic photon flux density response curve, and adjusts the laser light source module to increase or decrease the light source power output through the spectrum adjustment module;

[0027] If the proportion of each color laser output deviates from the laser output proportion parameter range suitable for the growth of the fruits and vegetables, the spectrum adjustment module adjusts the laser light source module to change the laser output proportion;

[0028] If the temperature is higher or lower than the temperature parameter range suitable for the growth of the fruits and vegetables, the temperature regulation sub-module automatically starts the ventilation equipment and the sun-shading equipment or the heating equipment and the heat preservation measures,

[0029] If the humidity is lower or higher than the humidity range parameter suitable for the growth of the fruits and vegetables, the humidity regulation sub-module will start the humidifying equipment or the dehumidifying equipment;

[0030] If the carbon dioxide concentration is lower than the parameter range required for the photosynthesis of the fruits and vegetables, the carbon dioxide concentration regulation sub-module will start the carbon dioxide supplement device;

[0031] Further, the fruit and vegetable growth index data in S4 includes photosynthetic rate data, chlorophyll content, fruit size and weight data.

[0032] Further, the in-depth analysis of the data to find the influencing factors and the improvement measures in S5 include the following steps:

[0033] P1: Light source stability judgment step:

[0034] Obtain the light intensity time series data recorded by the light sensor, calculate the standard deviation σ of the light intensity I , set the light intensity fluctuation threshold σ th , if σ I > σ th , it indicates that the light source stability is poor; the light source needs to be replaced or corrected manually until the light source stability is normal

[0035] Analyze the spectral data recorded by the spectral sensor, calculate the change rate ΔR of the spectral proportion, set the spectral proportion change threshold ΔR th , if ΔR > ΔRth, it indicates that the light source spectral stability is poor; the light source spectrum needs to be corrected manually until the light source spectral stability is normal

[0036] Compare the same environmental parameter data measured by different sensors, calculate the consistency error Ec of the data, set the consistency error threshold Ec th , if Ec > Ec th , the sensor accuracy has a problem; the sensor needs to be replaced or the sensor accuracy needs to be corrected manually until the sensor accuracy is normal

[0037] P2: Environmental regulation and timeliness judgment steps:

[0038] Obtain the environmental parameter data recorded by the environmental detection sensor, calculate the deviation ΔP of the actual environmental parameter and the preset target value, set the deviation threshold ΔP th and the response time threshold t th , if ΔP > ΔP th and the duration exceeds t th , it indicates that the environmental regulation is not timely; the number and position of the environmental detection sensor need to be changed manually until the environmental regulation is timely

[0039] Record the start time and the time of reaching the target value of the environmental regulation equipment, calculate the regulation action delay time t d , if t d exceeds the preset delay threshold t dth , it indicates that there is a delay problem in the environmental regulation; the parameters of the environmental regulation equipment need to be corrected manually until there is no delay problem in the environmental regulation

[0040] Compared with the prior art, the present application solves the problems of low light energy utilization rate of traditional LED light supplement system, lack of real-time monitoring means and scientific evaluation mechanism in the light supplement process of existing laser light supplement system, and has the following beneficial effects:

[0041] 1. Constructing a laser light supplement system: According to the differentiated needs of different types of fruit and vegetable crops in the growth process, the present application constructs a laser light supplement system integrating sensor module, central processing unit, laser light source adjustment module, spectrum adjustment module, environmental regulation module, power module and wireless communication module, realizes precise light supplement in multiple regions and time periods, avoids excessive irradiation and energy waste, improves crop uniformity and yield while reducing operation and maintenance costs. At the same time, the system has remote monitoring and adjustment function, supports intelligent terminal remote control and multi-region collaborative management, reduces manual intervention intensity, improves management efficiency, significantly improves the light resource utilization efficiency of facility agriculture and the comprehensive income of crops, has wide application prospect and industrialization potential.

[0042] 2. Real-time monitoring and feedback: The present application forms a "monitoring-feedback-adjustment" closed-loop control mechanism, uses a multi-sensor system to work together to realize real-time monitoring of light intensity, spectrum distribution, carbon dioxide concentration, temperature, humidity and other parameters in the light supplement area, and feeds the collected data to the central processing unit for intelligent analysis and dynamic regulation, ensuring that all types of fruit and vegetable crops are in the best light environment in different growth stages. At the same time, the present application proposes a light supplement evaluation method based on real-time monitoring data, realizes accurate correspondence and scientific evaluation from "light behavior" to "crop response", effectively improves the scientificity and visualization of light supplement regulation, and significantly improves the planting efficiency and crop quality of facility agriculture.

[0043] 3. Quantifiable evaluation: The present application ingeniously combines growth model and in-depth data analysis, takes the chlorophyll content, leaf photosynthetic rate, carbon assimilation rate and other key indicators of fruits and vegetables as the basis, forms a multi-source data correlation analysis model, which can accurately reflect the relationship between plant growth state and photosynthetic response under different light supplement conditions, effectively improving the traditional manual observation or single indicator judgment method. The quantifiable evaluation method proposed by the present application is based on objective measurement and algorithm deduction, can dynamically track the change trend of light supplement effect in time and space dimensions, comprehensively evaluate the influence of light supplement strategy on actual physiological response of plants, and provide scientific decision basis for optimizing light supplement ratio, adjusting light time sequence and intensity.

[0044] 4. Wide applicability: The laser light supplement system and its light supplement evaluation method proposed by the present application have good wide applicability, are not limited by facility type and scale, and can be flexibly applied to greenhouse, plant factory, artificial climate chamber, three-dimensional cultivation system and other facility agriculture scenes. At the same time, the light supplement system provided by the present application supports remote monitoring and intelligent adjustment, is suitable for centralized management and distributed agricultural scenes, meets the individual needs of small and medium-sized planters, is also suitable for unified deployment and intelligent operation of large-scale facility agricultural bases, has significant popularization value and industrialization application prospect. BRIEF DESCRIPTION OF DRAWINGS

[0045] Figure 1 This is a schematic diagram of a laser illumination system.

[0046] Figure 2 This is a schematic diagram of the control module for a laser illumination system.

[0047] Figure 3 A schematic diagram illustrating the changing trends of fruit and vegetable growth parameters;

[0048] Figure 4 Flowchart for evaluating laser supplemental lighting methods for greenhouse fruits and vegetables. Detailed Implementation

[0049] To make the technical solutions of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. It should be noted that the following embodiments are only used to better understand the technical solutions of the present invention and should not be construed as limiting the present invention.

[0050] Example 1.

[0051] This embodiment constructs a laser supplemental lighting system for fruits and vegetables in a facility, such as... Figure 1 The diagram shows the structure of a laser illumination system. As can be seen, the system includes: a sensor module for real-time detection of illumination and environmental parameters in the illumination area; a spectrum adjustment module for adjusting the ratio and intensity of the output spectrum of the laser source module according to instructions; a power supply module for providing power to the system; a wireless communication module for real-time data transmission within the system; a display and feedback module for creating a visual interface for the monitoring data; and a central processing unit for acquiring, processing, and analyzing the data detected in real-time by the sensor module, and sending instructions to the spectrum adjustment module and the environmental control module based on the analysis results.

[0052] like Figure 2The laser light supplement system control module schematic diagram is shown, the central processing unit includes a data acquisition layer, a data processing and analysis layer, and a control instruction output layer; wherein the data acquisition layer controls the sensor module, the sensor module includes an illumination intensity sensor module, a spectrum sensor module, and an environment detection sensor module, which are respectively used for controlling the illumination intensity sensor, the spectrum sensor, the temperature sensor, the humidity sensor, and the carbon dioxide concentration sensor to collect data. The data acquisition layer transmits the data collected by the sensors to the central processing unit through the data transmission module based on the ZigBee protocol of the AES encryption algorithm, and then transmits the data to the data processing and analysis layer, which completes data processing through the receiving submodule, the data processing submodule, and the data analysis and comparison submodule, respectively. Data processing includes removing illumination parameter outliers using the 3σ rule, and smoothing temperature and humidity parameter data using the Kalman filter algorithm; compare the processed data with the preset optimal parameter range of different growth stages of fruits and vegetables to determine whether it meets the expectations; input the collected data into the evaluation model based on the neural network algorithm of deep learning to determine the promotion index of laser light supplement on fruit and vegetable growth. Finally, the central processing unit transmits the processed data results to the control instruction output layer, and uses the laser light source regulation module to regulate the light quality and laser of the laser light source; the environment regulation module includes a temperature regulation submodule, a humidity regulation submodule, and a carbon dioxide concentration regulation submodule, which can be used to regulate environmental regulation equipment such as ventilation equipment, shading equipment, heating equipment, humidifying equipment, dehumidifying equipment, and carbon dioxide supplement devices. The central processing unit also includes a storage module, which estimates the storage capacity according to the planting cycle and data acquisition frequency.

[0053] Example 2.

[0054] The laser light supplement system constructed in Example 1 is used to layout the fruit and vegetable facility scene of laser light supplement, such as Figure 4 The facility fruit and vegetable laser light supplement evaluation method flowchart is shown, and the specific process steps are described as follows:

[0055] S1, layout and install the sensor module: in the facility environment, according to the demand of planting fruits and vegetables, set the light quality and wavelength adjustable laser light source, respectively 650 nm wavelength red laser, 440 nm wavelength blue laser, 550 nm wavelength green laser, ensure that its spectral characteristics match the photosynthetic demand of different growth stages of fruits and vegetables, at the same time ensure that the light source power output is stable and the adjustment range meets the actual planting demand, the light source power adjustment precision can reach 0.1 μmol / (m 2 s). The illumination intensity sensor is arranged in the area with uniform illumination and no shielding in the facility, and the arrangement density is 3 m 2The light intensity sensor is arranged on the light receiving surface of the plant, and the light spectrum data of the four corners, the center point, the position close to the light source and the edge of the facility are collected. The number of the light spectrum sensor is 10, and the scanning and collection frequency of the light spectrum sensor is 10 min / time, which can accurately capture the subtle changes of the light spectrum composition. The temperature sensor is arranged at 30 cm above the plant canopy, 15 cm above the middle of the plant and 15 cm above the ground in three layers. Each layer is equipped with 5 sensors, and the collection frequency is 5 min / time. The humidity sensor is arranged at the ventilation port, the corner of the wall and the dense area of the plant, and the number of arrangement is not less than 6, and the collection frequency is 5 min / time. The carbon dioxide concentration sensor is arranged at a height of 40 cm from the plant canopy, and the number of arrangement is 6, and the collection frequency is 10 min / time.

[0056] S2, the central processing unit pre-records the growth model parameter range of the suitable light intensity, spectrum proportion, temperature, humidity and carbon dioxide concentration of the planted fruit and vegetable crops at different stages such as germination stage, flowering stage and fruiting stage; the central processing unit receives the data collected by the sensor module, performs data processing and analysis; the central processing unit is set to transmit data based on the ZigBee protocol of AES encryption algorithm, and the transmission frequency is 5 min / time; the storage module of the central processing unit can estimate the storage capacity according to the planting period and the data collection frequency, so as to ensure that at least one complete planting season data can be stored, thereby ensuring stable data transmission and safe storage. Through the above design, the central processing unit not only can realize accurate monitoring and intelligent adjustment of the light supplement environment, but also can ensure the safety and integrity of data transmission, avoid information loss and interference problems. At the same time, the system has long-term data storage capacity, which provides solid data support for subsequent crop growth modeling, light supplement strategy optimization and agronomic management decision-making, and significantly improves the stability, practicality and intelligent level of the system.

[0057] S3, compared with the fruit and vegetable growth model parameter range pre-recorded by the central processing unit, whether the data collected by the sensor module meets the expectation is judged; if it meets, step S4 is entered; if it does not meet, the spectrum adjustment module or / and the environment control module is started to control, and the control is ended to return to step S2 until it meets the expectation, and step S4 is entered. When the light intensity is not in the fruit and vegetable growth model parameter range, if the light intensity in the fruiting stage is lower than 3 μmol / (m 2When the actual temperature is higher than the temperature range suitable for the growth of fruits and vegetables (20-25℃), the central processing unit will immediately start the environmental control module and automatically open the ventilation equipment and sunshade system, and reasonably adjust the ventilation volume and sunshade area according to the temperature rise amplitude and heat exchange characteristics, such as gradually increasing the ventilation opening and closing degree from 30% to 70%, and adjusting the sunshade rate of the sunshade net from 50% to 70%; when the actual temperature is lower than 20℃, the central processing unit immediately starts the environmental control module and automatically opens the heating equipment and insulation measures to maintain the temperature stable by adjusting the heating power and the lifting of the insulation curtain. When the actual humidity is lower than the humidity range suitable for the growth of fruits and vegetables (such as 60%~80%), the central processing unit immediately starts the environmental control module and automatically opens the humidifying equipment, and the humidifying equipment is used to humidify at a rate of 5~10 mL / m 3 per minute, and the dehumidifying equipment is used to dehumidify at a rate of 2~3 L / m 3 per hour. When the actual carbon dioxide concentration is lower than the carbon dioxide concentration range required for the photosynthesis of fruits and vegetables (800~1200 ppm), the central processing unit starts the environmental control module and automatically opens the carbon dioxide supplement device to supplement carbon dioxide gas into the facility at a flow rate of 10~20 mL / m 3 per minute until the carbon dioxide concentration meets the growth conditions of fruits and vegetables.

[0058] S4, regularly detect the growth index data of fruits and vegetables, use a photosynthetic rate detector to randomly select 10~15 fruit and vegetable plants in each planting area at 10~12 am on sunny days, select the upper healthy leaves of the plants to measure the photosynthetic rate, take the average value of 3~5 leaf measurements per plant as the photosynthetic rate data of the area, use a chlorophyll meter to measure the chlorophyll content at the same leaf position, take the average value of 2~3 measurements per plant, and the detection frequency is once every two weeks; measure the fruit size and weight from the fruit enlargement period, measure the fruit diameter with a vernier caliper with a precision of 0.1 mm, and measure the fruit weight with an electronic balance, take the average value of 30~50 fruits measured in each treatment group, and the measurement frequency is once a week, and collect the illumination and environmental parameter data. For example Figure 3The trend of the growth parameters of fruits and vegetables is shown. The photosynthetic rate and chlorophyll content of the plants are relatively low during the germination and seedling stages of fruit and vegetable growth. However, as the plants grow and the number of leaves increases, and the light conditions continue to act, the photosynthetic rate and chlorophyll content show an upward trend (such as when the leaves are fully expanded and the photosynthesis is strong). During the flowering and fruiting stages, the values reach a high level. The size and weight of the fruit are recorded from the swelling stage. As time goes on, the fruit continues to grow, and the size and weight reach a stable value at the mature stage.

[0059] S5, input the growth index data (photosynthetic rate, chlorophyll content, fruit volume and weight), light parameters (light intensity, spectral distribution) and environmental parameters (temperature, humidity, CO2 concentration) into the evaluation model based on the neural network algorithm of deep learning, which is a hybrid neural network model combining long short-term memory network (LSTM) and convolutional neural network (CNN). This model is trained and optimized using a large amount of historical experimental and actual planting data, such as adjusting the neural network weights and biases through the backpropagation algorithm, to establish a complex nonlinear relationship between growth indicators and light intensity, spectral proportion, temperature, humidity, and carbon dioxide concentration. The model automatically learns and updates after each input of new data, improving the prediction accuracy and reliability. The model uses a multi-layer perceptron (MLP) neural network architecture, which receives multi-dimensional feature data through the input layer, passes through the non-linear activation function (ReLU) of the hidden layer layer by layer, and finally generates a light supplement promotion index in the output layer. The model uses the backpropagation algorithm to automatically optimize the weight parameters of each layer of neurons, learning the complex mapping relationship between growth indicators and light supplement environment, and finally outputting a quantitative promotion index value (such as a promotion index value of 15%, indicating that the light supplement makes the growth efficiency 1.15 times that of natural light). The present application ingeniously combines growth models and in-depth data analysis, and forms a multi-source data correlation analysis model based on key indicators such as chlorophyll content, leaf photosynthetic rate, and carbon assimilation rate of fruits and vegetables, accurately reflecting the relationship between plant growth state and photosynthetic response under different light supplement conditions, and effectively improving the traditional manual observation or single indicator judgment method.

[0060] Determine whether the promotion index of light supplement on fruit and vegetable growth meets the expectation (the expected value is set as: 20% for the base value, 10% for the flowering period, 25% for the fruit swelling period, and 15% for leafy vegetables, with an error range of ±5%). If the promotion index meets the expectation, the process ends. If the promotion index does not meet the expectation, further analyze the data to find the influencing factors (such as light source stability, sensor accuracy, environmental regulation timeliness, etc.), and take targeted improvement measures (such as maintaining and calibrating the light source, replacing high-precision sensors, or optimizing the regulation algorithm, etc.). After improvement, return to step S2 until the promotion index meets the expectation, and the process ends. The following is the method for judging whether the growth promotion index meets the expectation and the adjustment measures:

[0061] P1: Light source stability judgment step:

[0062] Obtain the light intensity time series data recorded by the light sensor, calculate the standard deviation σ of the light intensity I , set the light intensity fluctuation threshold σ th , if σ I > σ th , it indicates that the light source stability is poor; need to replace the light source or correct the light source manually until the light source stability is normal;

[0063] Analyze the spectral data recorded by the spectral sensor, calculate the change rate ΔR of the spectral proportion, set the spectral proportion change threshold ΔR th , if ΔR> ΔRth, it indicates that the light source spectral stability is poor; need to correct the light source spectrum manually until the light source spectral stability is normal;

[0064] Compare the same environmental parameter data measured by different sensors, calculate the consistency error Ec of the data, set the consistency error threshold Ec th , if Ec> Ec th , the sensor accuracy has a problem; need to replace the sensor or correct the sensor accuracy manually until the sensor accuracy is normal;

[0065] P2: Environmental regulation and timeliness judgment step:

[0066] Obtain the environmental parameter data recorded by the environmental detection sensor, calculate the deviation ΔP of the actual environmental parameter and the preset target value, set the deviation threshold ΔP th and the response time threshold t th , if ΔP> ΔP th and the duration exceeds t th , it indicates that the environmental regulation is not timely; need to replace the number and position of the environmental detection sensor manually until the environmental regulation is timely;

[0067] Record the start time and the time to reach the target value of the environmental regulation equipment, calculate the regulation action delay time t d , if t d exceeds the preset delay threshold t dth , it indicates that there is a delay problem in the environmental regulation; need to correct the environmental regulation equipment parameters manually until there is no delay problem in the environmental regulation.

[0068] In summary, the application constructs a laser light supplement system integrating sensor module, central processing unit, laser light source adjustment module, spectrum adjustment module, environment regulation module, power module and wireless communication module according to the differentiated needs of different types of fruit and vegetable crops in the growth process, realizes precise light supplement in multiple areas and time periods, forms a "monitoring-feedback-adjustment" closed-loop control mechanism, realizes real-time monitoring of light intensity, spectrum distribution, carbon dioxide concentration, temperature, humidity and other parameters in the light supplement area by the cooperative operation of the multi-sensor system, and feeds back the collected data to the central processing unit for intelligent analysis and dynamic regulation, ensuring that various fruit and vegetable crops are in the best light environment in different growth stages. At the same time, the light supplement evaluation method based on real-time monitoring data realizes accurate correspondence and scientific evaluation from "light behavior" to "crop response", effectively improves the scientificity and visualization of light supplement regulation, and significantly improves the planting efficiency and crop quality of facility agriculture. The laser light supplement system and light supplement evaluation method can be flexibly applied to greenhouse, plant factory, artificial climate chamber, three-dimensional cultivation system and other facility agriculture scenes, and have significant popularization value and industrialization application prospect.

[0069] The above description of the embodiments is only used to help understand the method of the application and its core idea. It should be noted that for ordinary skilled persons in the art, some improvements and modifications can be made to the application without departing from the principles of the application, and these improvements and modifications also fall within the protection scope of the claims of the application.

[0070] The above description of the disclosed embodiments enables those skilled in the art to implement or use the application. Various modifications to the embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the application. Therefore, the application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for evaluating laser supplemental lighting for greenhouse fruits and vegetables, characterized in that, The evaluation method for laser supplemental lighting of greenhouse fruits and vegetables is implemented by a laser supplemental lighting system for greenhouse fruits and vegetables. The laser supplemental lighting system for greenhouse fruits and vegetables includes a sensor module, a central processing unit, a laser source adjustment module, a spectrum adjustment module, an environmental control module, a power supply module, and a wireless communication module. The laser source adjustment module includes a laser diode, the laser light quality of which is adjustable between red and blue light, the laser wavelength of which is adjustable within the range of 400~700 nm, and the laser photosynthetic photon flux density of which is adjustable. The evaluation method for laser supplemental lighting of fruits and vegetables in the facility includes the following steps: S1. Layout and installation of sensor modules; S2. The central processing unit receives data collected by the sensor module and performs data processing and analysis. S3. The data processed by the central processing unit is compared and analyzed with the pre-entered range of fruit and vegetable growth model parameters to determine whether the data collected by the sensor module meets the expectations. If it does, proceed to step S4. If it does not, start the control module to control it. After the control ends, return to step S2 until it meets the expectations, and then proceed to step S4. S4. Regularly monitor the growth indicators of fruits and vegetables; S5. Collect growth index data and light and environmental parameter data, and input them into an evaluation model based on a deep learning neural network algorithm. The evaluation model is a hybrid neural network model that integrates a long short-term memory network and a convolutional neural network. This model is trained and optimized using historical experimental and actual planting data to establish a nonlinear relationship between growth indicators and parameters such as light intensity, spectral ratio, temperature, humidity, and carbon dioxide concentration. The model automatically learns and updates after each new data input, and calculates the growth-promoting effect index of supplemental lighting on crop growth. It is then determined whether the growth-promoting effect index meets expectations. If it does, the process ends. If it does not meet expectations, the data is analyzed in depth to find influencing factors, and targeted improvement measures are taken. After improvement, the process returns to step S2 until the growth-promoting effect index meets expectations, at which point the process ends. The sensor module layout and installation in S1 specifically involves: Light intensity sensors being deployed in areas of the facility with uniform and unobstructed lighting, at a density of 2-3 m². 2 / each; spectral sensors are deployed on the light-receiving surface of the plant, at the four corners, center, near the light source, and at the edge of the facility, with 8-10 spectral sensors; temperature sensors are arranged in three layers, 20-30 cm above the plant canopy, 10-15 cm above the middle of the plant, and 10-15 cm above the ground, with 3-5 sensors in each layer; humidity sensors are placed at ventilation openings, wall corners, and densely planted areas, with no fewer than 6 sensors; carbon dioxide concentration sensors are placed at a height of 30-40 cm above the plant canopy, with 4-6 sensors; the data acquisition frequency of the sensor modules is 2-10 min / time. Before receiving data collected by the sensor module, the central processing unit described in S2 needs to pre-enter environmental growth model parameters suitable for the growth of fruit and vegetable crops at different stages. The regulation described in S3 specifically includes: If the light intensity is lower or higher than the range of light intensity parameters suitable for the growth of fruits and vegetables, the central processing unit calculates the power value that needs to be increased or decreased based on the difference in photosynthetic photon flux density and the power-photon flux density response curve of the light source, and then adjusts the laser light source adjustment module through the spectrum adjustment module to increase or decrease the power output of the light source. If the output ratio of each color laser deviates from the laser output ratio parameter range suitable for the growth of fruits and vegetables, the spectrum adjustment module adjusts the laser source adjustment module to change the laser output ratio. If the temperature is higher or lower than the temperature range suitable for the growth of fruits and vegetables, the temperature control submodule will automatically turn on the ventilation equipment, shading equipment, heating equipment, and insulation measures. If the humidity is lower or higher than the humidity range suitable for the growth of fruits and vegetables, the humidity control submodule will activate the humidification or dehumidification equipment. If the carbon dioxide concentration is lower than the parameter range required for photosynthesis of fruits and vegetables, the carbon dioxide concentration regulation submodule will activate the carbon dioxide replenishment device. The fruit and vegetable growth index data mentioned in S4 include photosynthetic rate data, chlorophyll content, fruit size and weight data; The methods for identifying influencing factors through in-depth data analysis and the improvement measures described in S5: P1: Steps for determining the stability of the light source: Acquire time-series data of light intensity recorded by a light sensor and calculate the standard deviation σ of the light intensity. I Set the light intensity fluctuation threshold σ th If σ I >σ th If the light source is unstable, it indicates poor light source stability. Replace or calibrate the light source until its stability is normal. Analyze the spectral data recorded by the spectral sensor, calculate the rate of change ΔR of the spectral proportion, and set a threshold ΔR for the change in the spectral proportion. th If ΔR > ΔRth, it indicates that the spectral stability of the light source is poor; correct the light source spectrum until the spectral stability of the light source is normal. Compare the same environmental parameter data measured by different sensors, calculate the data consistency error Ec, and set a consistency error threshold Ec. th If Ec > Ec th If the sensor accuracy is not correct, then there is a problem with the sensor accuracy; replace the sensor or calibrate the sensor accuracy until the sensor accuracy is normal. P2: Steps for judging the timeliness of environmental control: Acquire environmental parameter data recorded by environmental monitoring sensors, calculate the deviation ΔP between the actual environmental parameters and the preset target values, and set a deviation threshold ΔP. th and response time threshold t th If ΔP>ΔP th And the duration exceeds t th If so, it indicates that environmental control is not timely; change the number and location of environmental monitoring sensors until environmental control is timely. Record the start-up time and the time to reach the target value of the environmental control equipment, and calculate the control action delay time t. d If t d Exceeding the preset delay threshold t dth If the delay is not observed, it indicates a problem with environmental control; adjust the parameters of the environmental control equipment until the delay problem is resolved.

2. The method for evaluating laser supplemental lighting of greenhouse fruits and vegetables according to claim 1, characterized in that, The sensor module is used to detect the illumination and environmental parameters of the supplemental lighting area in real time; the central processing unit is used to collect, process and analyze the data detected in real time by the sensor module, and send instructions to the spectrum adjustment module and the environmental control module according to the analysis results; the spectrum adjustment module is used to adjust the ratio and intensity of the output spectrum of the laser source adjustment module according to the instructions; the power supply module is used to provide power to the system; the wireless communication module is used to realize the real-time transmission of data within the system; the facility fruit and vegetable laser supplemental lighting system also includes a display and feedback module for forming a visual interface for monitoring data.

3. The method for evaluating laser supplemental lighting of greenhouse fruits and vegetables according to claim 1, characterized in that, The sensor module includes a light intensity sensor, a spectral sensor, and an environmental detection sensor; the environmental detection sensor includes a temperature sensor, a humidity sensor, and a carbon dioxide concentration sensor; the environmental control module includes a temperature control submodule, a humidity control submodule, and a carbon dioxide concentration control submodule, and the environmental control module controls environmental control equipment, including ventilation equipment, shading equipment, heating equipment, humidification equipment, dehumidification equipment, and a carbon dioxide replenishment device.

4. The method for evaluating laser supplemental lighting of greenhouse fruits and vegetables according to claim 1, characterized in that, The central processing unit includes a data acquisition layer, a data processing and analysis layer, and a control command output layer; the data acquisition layer includes a light intensity sensor module, a spectrum sensor module, and an environmental sensor module; the data processing and analysis layer includes a data receiving submodule, a data processing submodule, and a data analysis and comparison submodule; the control command output layer includes a laser source control module and an environmental control module. The central processing unit also includes a data transmission module and a storage module. The data transmission module transmits data via the ZigBee protocol based on the AES encryption algorithm at a frequency of 5 min / time. The storage module estimates its storage capacity based on the planting cycle and data acquisition frequency.

5. The method for evaluating laser supplemental lighting of greenhouse fruits and vegetables according to claim 4, characterized in that, The data processing and analysis layer processes data in the following ways: using the 3σ criterion to remove outliers in light parameters, and using a Kalman filter algorithm to smooth temperature and humidity parameter data; comparing the processed data with the preset optimal parameter ranges for different growth stages of fruits and vegetables to determine whether they meet expectations; and inputting the collected data into an evaluation model based on a deep learning neural network algorithm to determine the index of the promoting effect of laser supplemental lighting on fruit and vegetable growth.

Images