Haematococcus cultivation light system based on edge control and control method thereof

Abstract

The application discloses Haematococcus cultivation light system and control method based on edge control, relates to the technical field of Haematococcus cultivation light control, and comprises a plurality of sensor monitoring modules, a plurality of edge controllers, a plurality of lighting units and a digital twin monitoring platform. The application can dynamically adjust light intensity according to the actual growth state of algae, and avoid the problems of algae growth inhibition or insufficient astaxanthin accumulation caused by the traditional fixed light control mode. All Haematococcus cultivation is divided into multiple areas for more detailed control, an edge controller is arranged in each set area range, and the edge controller can optimize the light mode in the area range based on real-time data analysis. The digital twin monitoring platform collects the data of the sensor monitoring module and the edge controller in real time, establishes a three-dimensional digital model of Haematococcus growth, and realizes real-time visual monitoring.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of Haematococcus pluvialis cultivation light control, in particular to a Haematococcus pluvialis cultivation light system and control method based on edge control. BACKGROUND

[0002] Haematococcus pluvialis, as a single-cell green alga, has attracted much attention in the fields of biotechnology, medicine, health, and food additives due to its high content of astaxanthin and other bioactive substances. Light, as a key environmental factor affecting the growth and astaxanthin synthesis of Haematococcus pluvialis, its precise control is of great significance to improve the efficiency of cultivation and product quality. However, the current light control technology in Haematococcus pluvialis cultivation still has many deficiencies, and innovative solutions are needed to break through the existing technical bottlenecks.

[0003] The current light control technology in Haematococcus pluvialis cultivation mainly relies on traditional control methods and basic photoelectric sensing systems. These technologies can meet the basic light requirements under certain conditions, but lack intelligent and refined control capabilities. According to existing research data, the current status of Haematococcus pluvialis light control technology mainly reflects the following aspects:

[0004] The existing light control system usually uses a simple combination of photoelectric sensors and timers, which cannot accurately control the light intensity according to the actual growth needs of Haematococcus pluvialis. Studies have shown that when the light is too strong, Haematococcus pluvialis will move too fast, causing self-damage; while the light is too weak, the algae will move slowly and easily stick to the wall, affecting the growth efficiency. This inaccurate control not only affects the normal growth of algae, but also may lead to resource waste and increased energy consumption.

[0005] In addition, the existing system usually adjusts the area of solar panels to control the light intensity, but in order not to block other cultivation tubes, the area of solar panels is usually set small, resulting in low collection efficiency, especially when the light intensity is high. This method cannot achieve fine adjustment of light intensity, and it is difficult to meet the light needs of Haematococcus pluvialis at different growth stages.

[0006] The existing light control system lacks dynamic adjustment capability and cannot adjust the light parameters in real time according to changes in environmental conditions and the growth state of algae. The traditional timer control method automatically turns on and off the lighting system based on a preset schedule, but cannot adapt to changes in the growth cycle of Haematococcus pluvialis, because the light needs will change with the growth stage of the algae.

[0007] This static control method not only reduces the light utilization efficiency, but also may cause energy waste. In the case of sufficient light, the system may still turn on the artificial light, causing unnecessary energy consumption; while in the case of insufficient light, it may not provide sufficient light intensity, affecting the growth of algae.

[0008] Existing light control systems usually only provide single spectrum artificial light sources, and cannot adjust the spectrum composition according to the needs of Haematococcus pluvialis at different growth stages. Studies have shown that different wavelengths of light have different effects on the growth and metabolism of algae, and reasonable allocation of light spectrum can significantly improve the growth efficiency of algae and the yield of target products.

[0009] However, the current system lacks the ability to finely control the spectrum, and cannot dynamically adjust the spectrum composition according to the growth state of algae and environmental conditions, which severely limits the effect of light control and the optimization of algae growth.

[0010] Therefore, it is necessary to analyze the current situation and defects of Haematococcus pluvialis light control technology in depth, and propose an innovative light system and control method based on edge control, to provide theoretical basis and practical guidance for the technical upgrading of Haematococcus pluvialis cultivation industry. SUMMARY

[0011] In order to solve the above technical problems, the present application provides a Haematococcus pluvialis cultivation light system and control method based on edge control. The technical scheme adopted is as follows:

[0012] The Haematococcus pluvialis cultivation light system based on edge control comprises a plurality of sensor monitoring modules, a plurality of edge controllers, a plurality of lighting units and a digital twin monitoring platform. The sensor monitoring module is used to monitor the environmental parameters, growth state parameters and visual pictures of Haematococcus pluvialis growth in a set area. The plurality of edge controllers are respectively installed on one side of the plurality of sensor monitoring modules and are in communication connection with the sensor monitoring modules. The environmental parameters and growth state parameters are collected for environmental parameter analysis and growth state analysis to generate light control instructions. The lighting unit is used to supplement the light for Haematococcus pluvialis in the area. The digital twin monitoring platform is in communication connection with the plurality of sensor monitoring modules and the plurality of edge controllers, and performs three-dimensional modeling on the growth state of Haematococcus pluvialis and displays three-dimensional simulation pictures and real-time visual pictures through digital twin.

[0013] Optionally, the sensor monitoring module includes a temperature sensor, a carbon dioxide sensor, a pH sensor, an optical sensor, a microscopic imaging module, a chlorophyll fluorescence sensor, and a visual camera, the temperature sensor is used to monitor the temperature value of the culture solution, the carbon dioxide sensor is used to monitor the environmental carbon dioxide concentration, the pH sensor is used to monitor the pH value of the nutrient solution, the optical sensor is used to monitor the environmental light parameter, the microscopic imaging module and the chlorophyll fluorescence sensor are used to monitor the growth state parameter of Haematococcus pluvialis, and the visual camera is used to shoot the real-time visual picture of Haematococcus pluvialis; the temperature sensor, the carbon dioxide sensor, the pH sensor, the optical sensor, the microscopic imaging module, and the chlorophyll fluorescence sensor are respectively in communication connection with the edge controller.

[0014] By adopting the above technical solution, the multiple sensor monitoring modules collect the environmental parameters (such as light intensity, temperature, pH value, etc.) and the growth state parameters (such as cell density, astaxanthin content, etc.) of Haematococcus pluvialis in real time, and transmit them to the edge controller for analysis. The edge controller generates a light control instruction based on real-time data analysis, directly regulates the output of the multiple lighting units, and realizes precise adjustment of the light intensity.

[0015] Haematococcus pluvialis is extremely sensitive to light conditions, and the demand for light differs significantly at different growth stages. For example, the suitable light intensity is 100-200 μmol / m²·s in the green cell growth stage, and a higher light intensity (such as 5 μmol / m²·s) is required in the astaxanthin accumulation stage. The system can dynamically adjust the light intensity according to the actual growth state of the algae, avoiding the problems of algae growth inhibition or insufficient astaxanthin accumulation that may be caused by traditional fixed light control methods.

[0016] All Haematococcus pluvialis cultivation is divided into multiple regions for more precise control, and an edge controller is set in each set region range. The edge controller can optimize the light mode within the region range based on real-time data analysis. For example, through the appropriate combination of red light and white light, the growth of Haematococcus pluvialis is promoted, and the astaxanthin yield is improved. Studies have shown that red light can regulate the activity of carbonic anhydrase, maintain the pH value of the culture medium between 8-9, promote photosynthesis and fixed rate is improved.

[0017] The system can flexibly switch between different light modes to optimize photosynthesis efficiency, thereby significantly improving the growth rate of algae and the amount of astaxanthin accumulation. Under suitable light conditions, the astaxanthin yield is greatly improved compared with traditional light control.

[0018] The edge controller can adjust the lighting units on demand based on real-time data analysis, avoiding energy waste caused by fixed patterns in traditional lighting control. For example, when algae are in the low light demand stage, the system can automatically reduce the light intensity, thereby reducing energy consumption.

[0019] The digital twin monitoring platform establishes a three-dimensional digital model of the growth of Dunaliella salina by collecting data from the sensor monitoring module and the edge controller in real time, achieving real-time visual monitoring. At the same time, the platform can predict potential problems and issue warnings based on historical data and machine learning algorithms.

[0020] Optionally, the lighting unit includes an LED chip set, a heat dissipation system, and a PWM driver. The LED chip set is installed above the area range by a support and faces Dunaliella salina. The heat dissipation system is installed on the back of the LED chip set. The PWM driver is in control connection with the LED chip set. The edge controller controls the power and spectral combination of the LED chip set through the PWM driver.

[0021] By adopting the above technical solution, the PWM (Pulse Width Modulation) driver can accurately control the output power of the LED chip set, which means that the edge controller can adjust the light intensity with millisecond-level precision according to the real-time data (such as algal cell density, astaxanthin accumulation level, environmental light changes, etc.) from the sensor monitoring module. At the same time, the LED chip set is usually composed of LEDs of different colors (such as red, blue, white, etc.), and the PWM driver can control the power of these different color LEDs respectively or in combination, thereby flexibly adjusting the spectral combination.

[0022] Dunaliella salina has different requirements for light intensity and spectrum at different growth stages (logarithmic growth phase, dormant phase / astaxanthin accumulation phase). For example, red and blue light is crucial for algal growth and astaxanthin synthesis, but the optimal ratio changes with the stage. This system can adjust the light intensity and spectrum in real time and accurately, providing a "tailor-made" light environment for algae, maximizing the promotion of growth and astaxanthin accumulation, which is difficult to achieve by traditional fixed spectrum or simple dimming lighting systems.

[0023] Optionally, the edge controller includes a multi-channel data acquisition device, a memory, an AI chip for analyzing the growth state of Dunaliella salina, and a control chip. The data input end of the multi-channel data acquisition device is in communication connection with each sensor of the sensor monitoring module. The memory is in communication connection with the data output end of the multi-channel data acquisition device. The AI chip is in communication connection with the memory. The control chip is in communication connection with the AI chip. The control chip controls the power and spectral combination of the LED chip set through the PWM driver.

[0024] Optionally, the digital twin monitoring platform is based on a computer.

[0025] By adopting the above technical solution, the edge controller integrates a multi-channel data collector, a memory, an AI chip, and a control chip. This means that it can not only collect sensor data in real time, but also store and perform complex AI analysis locally (close to the data source) without the need to upload all data to the cloud and wait for instructions. The AI chip is specifically designed to analyze the growth state of Haematococcus pluvialis and can handle nonlinear and complex growth patterns and environmental influences.

[0026] This design greatly improves the response speed of the system and the accuracy of decision-making. The AI chip can predict the growth trend of algae, the accumulation rate of astaxanthin, and even identify potential growth stress (such as photoinhibition caused by excessive light, nutrient deficiency, etc.) based on historical data and real-time data. The control chip generates and executes precise light control instructions based on the analysis results of the AI chip, achieving active and intelligent regulation of algae growth, rather than simply responding passively.

[0027] The memory is used to store historical data and model parameters, and the AI chip can use these data to continuously learn and optimize its analysis model. The control chip is responsible for executing these optimized models.

[0028] The system can continuously learn and gradually master the best light strategy for specific batches of algae, specific environmental conditions. For example, it may learn that a certain combination of light spectrum and intensity variation curve can maximize astaxanthin production within a certain temperature range. This learning ability makes the system more and more "understand" the Haematococcus pluvialis being cultivated, continuously optimizing control effects, surpassing traditional control systems based on fixed rules or simple threshold judgments.

[0029] The Haematococcus pluvialis cultivation light control method based on edge control adopts a Haematococcus pluvialis cultivation light control system based on edge control to control the light in the Haematococcus pluvialis cultivation area, including the following steps:

[0030] Step 1: The multi-channel data collector collects data from temperature sensors, carbon dioxide sensors, pH sensors, optical sensors, microscopic imaging modules, and chlorophyll fluorescence sensors at set time intervals and stores them in the memory.

[0031] Step 2: The AI chip executes a lightweight YOLOv8 model to identify microscopic imaging data obtained by the microscopic imaging module, and outputs the number of motile cells, the diameter of immobile spores, and the area proportion of astaxanthin.

[0032] Step 3, the AI chip outputs the Haematococcus pluvialis growth stage according to the trained growth stage determination model, and the input parameters are: the number of motile cells, the diameter of immobile spores, the proportion of astaxanthin area, the Fv / Fm value of the chlorophyll fluorescence sensor, the intensity of the characteristic absorption peak of chlorophyll of the optical sensor, the culture solution temperature value collected by the temperature sensor, and the apparent color HSV value of the algal liquid collected by the visual camera;

[0033] Step 4, the AI chip calculates the light demand parameters according to the Haematococcus pluvialis growth stage;

[0034] Step 5, the control chip generates light control instructions according to the light demand parameters, and transmits the light control instructions to the PWM driver;

[0035] Step 6, the PWM driver executes the light control instructions to control the LED chip set to supply light to the Haematococcus pluvialis according to the set light and spectrum combination.

[0036] Optionally, in step 3, the Haematococcus pluvialis growth stage includes a green growth period and a red stress period.

[0037] Optionally, in step 4, if it is determined that the growth stage of the Haematococcus pluvialis is the green growth period, a combination of red light, blue light and white light is used, and the calculation formula of the target light intensity is:

[0038] ;

[0039] Wherein is the target light intensity, is the temperature of the nutrient solution, is the color enhancement factor;

[0040] ; wherein is the red saturation of the algal liquid,

[0041] The determination formula of the red light proportion is:

[0042] ; wherein is the red light proportion, is the carbon dioxide concentration;

[0043] The determination formula of the blue light proportion is:

[0044] ;

[0045] Wherein is the blue light proportion, is the number of motile cells;

[0046] The determination formula of the white light proportion is:

[0047] .

[0048] Optionally, in step 4, if the growth stage of Haematococcus pluvialis is determined to be the red-turning stress period, a combination of blue light, ultraviolet light, and red light is used. The formula for calculating the target light intensity is:

[0049] base_intensity + diam_adjust;

[0050] in It is the target light intensity. This is the base light intensity; `diam_adjust` is the diameter compensation term.

[0051] ;

[0052] ;

[0053] in It's a nutrient solution. value, It is the average diameter of immobile spores;

[0054] The formula for determining the blue light ratio is:

[0055] ;

[0056] in This is the current proportion of red light;

[0057] The formula for determining the proportion of ultraviolet light is:

[0058] ;

[0059] in It is the proportion of ultraviolet light. It is the area ratio of astaxanthin;

[0060] The formula for determining the proportion of red light is:

[0061] .

[0062] By adopting the above technical solution, steps 2 and 3 utilize an AI chip to execute a lightweight YOLOv8 model and a trained growth stage determination model. By comprehensively analyzing multi-dimensional data such as microscopic images (cell number, diameter, astaxanthin ratio), chlorophyll fluorescence (Fv / Fm), optical characteristics, temperature, and apparent color HSV value, the Haematococcus pluvialis is accurately determined to be in the green growth stage or the red stress stage.

[0063] This intelligent judgment based on multi-source data fusion is much more accurate and objective than traditional single indicators such as visual observation or simple pH judgment. It enables the system to truly understand the current physiological state of algae, providing a scientific basis for subsequent light strategy formulation, avoiding the "one-size-fits-all" control method, and achieving differentiated precision management for different growth stages.

[0064] Differentiated and parameterized light strategy:

[0065] Step 4: Based on the identified growth stage, completely different light combinations (green growth period: red light, blue light, white light; red stress period: blue light, ultraviolet light, red light) and calculation formulas are used to derive light demand parameters (target light intensity and spectral proportion). These formulas not only consider the algae's own state (such as cell number, diameter, astaxanthin proportion), but also consider environmental factors (such as temperature, pH, carbon dioxide concentration).

[0066] Green growth period: Red light, blue light, and white light combination is used to simulate natural light, promoting photosynthesis and cell proliferation. The formula introduces temperature correction factor (temp_factor) and color enhancement factor (color_enhance), as well as red light proportion adjustment based on carbon dioxide concentration (CO2_conc) and blue light proportion adjustment based on cell number (mobile_count), so that the light not only meets the basic growth needs, but also dynamically optimizes according to the environment, improving nutrient utilization efficiency.

[0067] Red stress period: Blue light, ultraviolet light, and red light combination is used, which is the key to inducing astaxanthin synthesis. The formula introduces base intensity (base_intensity) and compensation terms based on pH and immobile spore diameter (diam_adjust) to ensure sufficient and appropriate light intensity stimulation under stress conditions. Blue light proportion is related to red light proportion, and ultraviolet light proportion is directly linked to astaxanthin proportion (astaxanthin_ratio), while red light proportion is dynamically adjusted. This design aims to maximize stress induction while avoiding excessive stress that may cause cell damage.

[0068] This differentiated and parameterized strategy makes light control no longer a simple on-off or fixed mode, but a "customized" solution closely integrated with algae physiological needs and environmental conditions, greatly improving the utilization efficiency of light resources, and is expected to significantly improve the final yield and quality of astaxanthin.

[0069] ​Optionally, it also includes a digital twin display step, the digital twin monitoring platform respectively collects real-time parameters of the plurality of sensor monitoring modules and the plurality of edge controllers, three-dimensional modeling of the growth state of Haematococcus pluvialis is carried out, and a digital twin display three-dimensional simulation picture and a real-time visual picture are displayed, and the display content includes the growth state and the light control parameter.

[0070] In summary, the present application includes at least one of the following beneficial technical effects:

[0071] The present application can provide an edge control-based Haematococcus pluvialis cultivation light system and control method, a plurality of sensor monitoring modules collect environmental parameters and growth state parameters of Haematococcus pluvialis in real time and transmit them to an edge controller for analysis. The edge controller generates light control instructions based on real-time data analysis and directly regulates the output of a plurality of lighting units to achieve precise adjustment of light intensity.

[0072] The light intensity can be dynamically adjusted according to the actual growth state of algae, avoiding the problem of algae growth inhibition or astaxanthin accumulation deficiency caused by traditional fixed light control mode.

[0073] All Haematococcus pluvialis cultivation is divided into multiple regions for more precise control, an edge controller is set in each set region, and the edge controller can optimize the light mode within the region based on real-time data analysis.

[0074] The digital twin monitoring platform establishes a three-dimensional digital model of Haematococcus pluvialis growth by collecting data from sensor monitoring modules and edge controllers in real time, and realizes real-time visual monitoring. BRIEF DESCRIPTION OF DRAWINGS

[0075] Figure 1 is a component communication connection schematic diagram of the Haematococcus pluvialis cultivation light system based on edge control of the present application;

[0076] Figure 2 is a flowchart of the Haematococcus pluvialis cultivation light control method based on edge control of the present application.

[0077] BRIEF DESCRIPTION OF DRAWINGS: 1, sensor monitoring module; 11, temperature sensor; 12, carbon dioxide sensor; 13, pH sensor; 14, optical sensor; 15, microscopic imaging module; 16, chlorophyll fluorescence sensor; 17, visual camera; 2, edge controller; 21, multi-channel data collector; 22, memory; 23, AI chip; 24, control chip; 3, lighting unit; 31, LED chip set; 33, PWM driver; 4, digital twin monitoring platform. DETAILED DESCRIPTION

[0078] The present application will be further described in detail below in conjunction with the drawings.

[0079] The embodiment of the application discloses a Haematococcus cultivation light system based on edge control and a control method.

[0080] Referring to Figure 1 and Figure 2 , embodiment 1, a Haematococcus cultivation light system based on edge control, includes a plurality of sensor monitoring modules 1, a plurality of edge controllers 2, a plurality of lighting units 3 and a digital twin monitoring platform 4, the sensor monitoring module 1 is used to monitor the environmental parameters, growth state parameters and visual pictures of Haematococcus growth in the set area range, the plurality of edge controllers 2 are respectively installed on one side of the plurality of sensor monitoring modules 1, and are in communication connection with the sensor monitoring modules 1, collect the environmental parameters and growth state parameters to generate light control instructions through environmental parameter analysis and growth state analysis, the lighting unit 3 is used to supplement the light for Haematococcus in the area range, the digital twin monitoring platform 4 is in communication connection with the plurality of sensor monitoring modules 1 and the plurality of edge controllers 2, carries out three-dimensional modeling on the growth state of Haematococcus, and carries out digital twin display three-dimensional simulation picture and real-time visual picture.

[0081] Embodiment 2, the sensor monitoring module 1 includes a temperature sensor 11, a carbon dioxide sensor 12, a pH value sensor 13, an optical sensor 14, a microscopic imaging module 15, a chlorophyll fluorescence sensor 16 and a visual camera 17, the temperature sensor 11 is used to monitor the temperature value of the culture solution, the carbon dioxide sensor 12 is used to monitor the environmental carbon dioxide concentration, the pH value sensor 13 is used to monitor the pH value of the nutrient solution, the optical sensor 14 is used to monitor the environmental light parameter, the microscopic imaging module 15 and the chlorophyll fluorescence sensor 16 are used to monitor the growth state parameters of Haematococcus, and the visual camera 17 is used to shoot the real-time visual picture of Haematococcus; the temperature sensor 11, the carbon dioxide sensor 12, the pH value sensor 13, the optical sensor 14, the microscopic imaging module 15 and the chlorophyll fluorescence sensor 16 are in communication connection with the edge controller 2.

[0082] The plurality of sensor monitoring modules 1 collect the environmental parameters (such as light intensity, temperature, pH value, etc.) and growth state parameters (such as cell density, astaxanthin content, etc.) of Haematococcus growth in real time, and transmit them to the edge controller 2 for analysis. The edge controller generates light control instructions based on real-time data analysis, directly regulates the output of the plurality of lighting units 3, and realizes precise adjustment of light intensity.

[0083] Haematococcus pluvialis is extremely sensitive to light conditions, and the demand for light varies significantly at different growth stages. For example, during the green cell growth stage, the appropriate light intensity is 100-200 μmol / m²·s, while during the astaxanthin accumulation stage, higher light intensity (e.g., 145 μmol / m²·s) is required. This system can dynamically adjust the light intensity based on the actual growth state of the algae, avoiding the problems of algae growth inhibition or insufficient astaxanthin accumulation that may occur in traditional fixed light control methods.

[0084] All Haematococcus pluvialis cultivation is divided into multiple zones for more precise control, with an edge controller 2 set in each designated zone. Based on real-time data analysis, the edge controller 2 can optimize the light mode within the zone. For example, through the appropriate combination of red and white light, the growth of Haematococcus pluvialis is promoted, and the astaxanthin yield is increased. Studies have shown that red light, by regulating the activity of carbonic anhydrase, maintains the pH of the culture medium between 8-9, promoting photosynthesis and Fixed rate increase.

[0085] This system can flexibly switch between different light modes, optimizing photosynthetic efficiency and significantly improving algae growth rate and astaxanthin accumulation. Under suitable light conditions, astaxanthin yield is significantly improved compared to traditional light control.

[0086] The edge controller 2 can achieve on-demand adjustment of the lighting unit 3 based on real-time data analysis, avoiding energy waste caused by fixed modes in traditional light control. For example, when the algae are in a low light demand stage, the system can automatically reduce the light intensity, thereby reducing energy consumption.

[0087] The digital twin monitoring platform 4 establishes a three-dimensional digital model of Haematococcus pluvialis growth by collecting real-time data from the sensor monitoring module 1 and the edge controller 2, achieving real-time visual monitoring. At the same time, the platform can predict potential problems and issue warnings based on historical data and machine learning algorithms.

[0088] In Example 3, the lighting unit 3 includes an LED chip set 31, a heat dissipation system, and a PWM driver 33. The LED chip set 31 is installed above the zone range by a support and faces Haematococcus pluvialis. The heat dissipation system is installed on the back of the LED chip set 31. The PWM driver 33 is in control connection with the LED chip set 31. The edge controller 2 controls the power and spectral combination of the LED chip set 31 through the PWM driver 33.

[0089] The PWM (Pulse Width Modulation) driver 33 can precisely control the output power of the LED chip set 31, which means that the edge controller 2 can adjust the light intensity with millisecond-level precision according to the real-time data from the sensor monitoring module 1 (such as algal cell density, astaxanthin accumulation level, environmental light changes, etc.). At the same time, the LED chip set 31 is usually composed of LEDs of different colors (such as red light, blue light, white light, etc.), and the PWM driver can control the power of these different color LEDs separately or in combination, thereby flexibly adjusting the spectral combination.

[0090] The needs of Haematococcus pluvialis for light intensity and spectrum vary greatly at different growth stages (logarithmic growth phase, dormancy phase / astaxanthin accumulation phase). For example, red light and blue light are crucial for algal growth and astaxanthin synthesis, but the optimal ratio changes with the stage. This system can adjust the light intensity and spectrum in real time and accurately, providing a "tailor-made" light environment for algae, maximizing the promotion of growth and astaxanthin accumulation, which is difficult to achieve with traditional fixed spectrum or simple dimming light systems.

[0091] In Example 4, the edge controller 2 includes a multi-channel data collector 21, a memory 22, an AI chip 23 for analyzing the growth state of Haematococcus pluvialis, and a control chip 24. The data input end of the multi-channel data collector 21 is in communication connection with each sensor of the sensor monitoring module 1, the memory 22 is in communication connection with the data output end of the multi-channel data collector 21, the AI chip 23 is in communication connection with the memory 22, and the control chip 24 is in communication connection with the AI chip 23. The control chip 24 controls the power and spectral combination of the LED chip set 31 through the PWM driver 33.

[0092] In Example 5, the digital twin monitoring platform 4 is implemented based on a computer.

[0093] The edge controller 2 integrates the multi-channel data collector 21, the memory 22, the AI chip 23, and the control chip 24. This means that it can not only collect sensor data in real time, but also store and perform complex AI analysis locally (close to the data source) without the need to upload all data to the cloud and wait for instructions. The AI chip 23 is specifically designed to analyze the growth state of Haematococcus pluvialis and can handle nonlinear and complex growth patterns and environmental influences.

[0094] This design greatly improves the response speed and accuracy of decision-making of the system. The AI chip can predict the growth trend of algae, the accumulation rate of astaxanthin, and even identify potential growth stress (such as photoinhibition caused by excessive light, nutrient deficiency, etc.) based on historical data and real-time data. The control chip 24 quickly generates and executes precise light control instructions based on the analysis results of the AI chip, achieving active and intelligent regulation of algal growth, rather than simply responding passively.

[0095] The memory 22 is used to store historical data and model parameters, which can be used by the AI chip 23 to continuously learn and optimize its analysis model. The control chip 24 is responsible for executing these optimized models.

[0096] The system can gradually master the optimal light strategy for a specific batch of algae and specific environmental conditions through continuous learning. For example, it may learn that a certain combination of light spectrum and intensity variation curve can maximize astaxanthin production within a certain temperature range. This learning ability makes the system more and more "understand" the Dunaliella salina being cultivated, and the control effect is continuously optimized, surpassing traditional control systems based on fixed rules or simple threshold judgments.

[0097] Embodiment 6, Dunaliella salina cultivation light control method based on edge control, a Dunaliella salina cultivation light control system based on edge control is used to control the light of the Dunaliella salina cultivation area, which includes the following steps:

[0098] Step 1, the multi-channel data collector 21 collects data of the temperature sensor 11, the carbon dioxide sensor 12, the pH value sensor 13, the optical sensor 14, the microscopic imaging module 15 and the chlorophyll fluorescence sensor 16 every set time interval and stores them in the memory 22;

[0099] Step 2, the AI chip 23 executes the light YOLOv8 model to identify the microscopic imaging data obtained by the microscopic imaging module 15, and outputs the number of motile cells, the diameter of immobile spores and the area proportion of astaxanthin;

[0100] Step 3, the AI chip 23 executes the trained growth stage determination model to output the growth stage of Dunaliella salina, and the input parameters are: the number of motile cells, the diameter of immobile spores, the area proportion of astaxanthin, the Fv / Fm value of the chlorophyll fluorescence sensor 16, the chlorophyll characteristic absorption peak intensity of the optical sensor 14, the culture solution temperature value collected by the temperature sensor 11, and the apparent color HSV value of the algal liquid collected by the visual camera 17;

[0101] Step 4, the AI chip 23 calculates the light demand parameters according to the growth stage of Dunaliella salina;

[0102] Step 5, the control chip 24 generates light control instructions according to the light demand parameters, and transmits the light control instructions to the PWM driver 33;

[0103] Step 6, the PWM driver 33 executes the light control instructions to control the LED chip set 31 to supply light to the Dunaliella salina according to the set light and spectrum combination.

[0104] In embodiment 7, in step 3, the growth stage of Dunaliella salina includes the green growth period and the red stress period.

[0105] In Example 8, in step 4, if it is determined that the growth stage of Haematococcus pluvialis is the green growth period, then a combination of red, blue, and white light is used. The formula for calculating the target light intensity is:

[0106] ;

[0107] in It is the target light intensity. It's the temperature of the nutrient solution. It is a color enhancement factor;

[0108] ;in Red saturation of algal solution;

[0109] The formula for determining the proportion of red light is:

[0110] ;in It's the proportion of red light. It refers to the concentration of carbon dioxide;

[0111] The formula for determining the blue light ratio is:

[0112] ;

[0113] in It's the blue light ratio. It refers to the number of swimming cells;

[0114] The formula for determining the proportion of white light is:

[0115] .

[0116] In Example 9, step 4, if the growth stage of Haematococcus pluvialis is determined to be the reddening stress period, a combination of blue light, ultraviolet light, and red light is used. The formula for calculating the target light intensity is:

[0117] base_intensity + diam_adjust;

[0118] in It is the target light intensity. This is the base light intensity; `diam_adjust` is the diameter compensation term.

[0119] ;

[0120] ;

[0121] in It's a nutrient solution. value, It is the average diameter of immobile spores;

[0122] The determination formula of the blue light proportion is:

[0123]

[0124] wherein is the current red light proportion;

[0125] The determination formula of the ultraviolet light proportion is:

[0126]

[0127] wherein is the ultraviolet light proportion, is the astaxanthin area proportion;

[0128] The determination formula of the red light proportion is:

[0129]

[0130] Steps 2 and 3 use the AI chip 23 to execute the light YOLOv8 model and the trained growth stage determination model, comprehensively analyze the multi-dimensional data such as microscopic images (cell number, diameter, astaxanthin proportion), chlorophyll fluorescence (Fv / Fm), optical characteristics, temperature, apparent color HSV value, and accurately determine whether the Haematococcus pluvialis is in the green growth period or the red stress period.

[0131] This intelligent judgment based on multi-source data fusion is much more accurate and objective than traditional single indicators (such as relying only on naked eye observation or simple pH judgment). It enables the system to truly understand the current physiological state of algae, provides a scientific basis for subsequent light strategy formulation, avoids the "one-size-fits-all" control method, and realizes the differential precision management of different growth stages.

[0132] Growth stage differentiation, parameterized light strategy:

[0133] Step 4 uses completely different light combinations (green growth period: red light, blue light, white light; red stress period: blue light, ultraviolet light, red light) and calculation formulas to derive light demand parameters (target light intensity and each spectrum proportion) according to the identified growth stage. These formulas not only consider the algae's own state (such as cell number, diameter, astaxanthin proportion), but also consider environmental factors (such as temperature, pH, carbon dioxide concentration).

[0134] Green growth period: Use red light, blue light, and white light combination to simulate natural light, promote photosynthesis and cell proliferation. The formula introduces temperature correction factor (temp_factor) and color enhancement factor (color_enhance), as well as carbon dioxide concentration (CO2) based on the growth rate (GR) of Haematococcus pluvialis. ​​​Red light proportion adjustment based on the cell number (mobile_count) to ensure that the light not only meets the basic growth needs but also dynamically optimizes according to the environment to improve nutrient utilization efficiency.

[0135] Red stress period: Blue light, ultraviolet light, and red light are combined, which is the key to inducing astaxanthin synthesis. The formula introduces a base light intensity (base_intensity) and a compensation term based on pH and spore diameter (diam_adjust) to ensure that sufficient and appropriate light intensity is provided under stress conditions. The proportion of blue light is related to the proportion of red light, the proportion of ultraviolet light is directly linked to the proportion of astaxanthin (astaxanthin_ratio), and the proportion of red light is dynamically adjusted. This design aims to maximize the stress induction effect while avoiding excessive stress that can damage cells.

[0136] This differentiated and parameterized strategy makes light control no longer a simple on-off or fixed mode, but a "customized" solution closely integrated with the physiological needs of algae and environmental conditions, greatly improving the utilization efficiency of light resources and promising to significantly improve the final yield and quality of astaxanthin.

[0137] Embodiment 10 further comprises a digital twin display step, wherein the digital twin monitoring platform 4 collects real-time parameters of the plurality of sensor monitoring modules 1 and the plurality of edge controllers 2 respectively, performs three-dimensional modeling on the growth state of Haematococcus pluvialis, and displays a three-dimensional simulation picture and a real-time visual picture of the digital twin, and the display content includes the growth state and the light control parameters.

[0138] The following specific embodiments are used to illustrate the implementation principles of the present application:

[0139] System composition: Cultivation area division: A flat photobioreactor area with a length of 10 meters and a width of 5 meters is divided into 5 independent sub-areas (for example, each sub-area is 2 meters x 5 meters), and each sub-area is considered as a "set area range" for more precise light control.

[0140] Sensor monitoring module 1: One set of sensor monitoring module 1 is installed in each sub-area (a total of 5). Each set of module includes:

[0141] Temperature sensor 11: Placed in the middle of the culture solution, it monitors the culture solution temperature in real time.

[0142] Carbon dioxide sensor 12: Installed above the sub-area, it monitors the environmental concentration.

[0143] pH sensor 13: Immersed in the culture solution, it monitors the pH of the nutrient solution.

[0144] Optical sensor 14: measures ambient light parameters (e.g. PAR, photosynthetically active radiation).

[0145] Microscopic imaging module 15: takes periodic microscopic images of Haematococcus culture in each sub-region through a miniature camera and a microscope lens.

[0146] Chlorophyll fluorescence sensor 16: measures chlorophyll fluorescence parameters (e.g. Fv / Fm) by being immersed in the culture solution.

[0147] Visual camera 17: installed above each sub-region, takes periodic images of the apparent color of the algae solution in the entire sub-region.

[0148] Edge controller 2: one edge controller 2 (total of 5) is installed on one side of each sub-region. Each edge controller 2 contains:

[0149] Multiplexed data collector 21: connects and collects data from all sensors in the corresponding sub-region's sensor monitoring module 1 at regular intervals.

[0150] Memory 22: stores collected raw data and historical data.

[0151] AI chip 23: runs a lightweight YOLOv8 model to identify microscopic images, obtaining the number of motile cells, the diameter of immobile spores, and the area proportion of astaxanthin; runs a trained growth stage determination model to determine the current growth stage of algae (green growth period or red stress period) based on all sensor data.

[0152] Control chip 24: receives the growth stage and light demand parameters output by the AI chip 23, and generates specific light control instructions (target light intensity, spectral proportion of each light).

[0153] Illumination unit 3: one set of illumination unit 3 (total of 5) is installed above each sub-region. Each illumination unit 3 contains:

[0154] LED chip set 31: composed of multiple LEDs of different colors, including red, blue, white, and ultraviolet LEDs, mounted on the sub-region directly above by a support, with the irradiation direction downward.

[0155] Heat dissipation system: installed on the back of the LED chip set 31, effectively dissipating the heat generated during LED operation.

[0156] PWM driver 33: receives light control instructions from the control chip 24 of the corresponding sub-region edge controller 2, accurately controls the power of each color LED in the LED chip set 31, and adjusts the overall light intensity and spectral combination.

[0157] Digital twin monitoring platform 4: realized based on a high-performance computer, and keeps communication connection with all sensor monitoring modules 1 and edge controllers 2 through wired or wireless network.

[0158] System operation flow (omitting calculation process):

[0159] Data acquisition: the sensor monitoring module 1 in each sub-area starts to work, and the multi-channel data collector 21 collects temperature, concentration, pH value, environmental light, microscopic image, chlorophyll fluorescence and apparent color data every 15 minutes, and stores the data into the memory 22.

[0160] AI analysis and growth stage judgment: the AI chip 23 starts to process data. First, the microscopic image is identified to obtain the current number of motile cells, the diameter of immobile spores and the area ratio of astaxanthin. Then, combined with the chlorophyll fluorescence Fv / Fm value, the chlorophyll characteristic absorption peak intensity measured by the optical sensor, the culture solution temperature value measured by the temperature sensor and the apparent color HSV value of the algal liquid photographed by the visual camera, the AI chip 23 runs the growth stage judgment model to judge whether the Haematococcus pluvialis is in the “green growth period” or the “red stress transition period”.

[0161] Light demand parameter calculation: the AI chip 23 calculates the required light parameters according to the judged growth stage by calling the corresponding formula (such as the formula in embodiment 8 or embodiment 9, but the specific calculation steps are omitted). For example, if it is judged to be the green growth period, the target light intensity and the proportion of red light, blue light and white light are calculated; if it is judged to be the red stress transition period, the target light intensity and the proportion of blue light, ultraviolet light and red light are calculated.

[0162] Generation and sending of control instructions: the control chip 24 receives the light demand parameters calculated by the AI chip 23, generates specific PWM control instructions (specifying the duty ratio and frequency of each color LED), and sends the instructions to the PWM driver 33 through the communication interface.

[0163] Execution of light control: after receiving the instructions, the PWM driver 33 immediately adjusts the power output of each color LED in the LED chip set 31, so that the light intensity and spectral combination in the sub-area reach the preset target value, and the Haematococcus pluvialis is supplemented with light.

[0164] ​Digital twin monitoring and display: The digital twin monitoring platform 4 receives data from all sensor monitoring modules 1 and edge controllers 2 in real time. Based on these data, the platform constructs and updates a three-dimensional digital model of the growth state of Haematococcus pluvialis. On the monitoring interface, the operator can see the three-dimensional simulation picture of each sub-area (showing the distribution and density of algae, etc.), the real-time visual picture (color change of the algae liquid), the current growth stage judgment result and the actual executed light control parameters (such as the current light intensity, the proportion of each spectrum). The platform can also provide early warning for potential abnormal situations (such as growth stagnation, insufficient light, etc.) according to historical data and models.

[0165] Through the above embodiments, the system can independently and intelligently regulate and control the light in each sub-area, accurately match the needs of Haematococcus pluvialis at different growth stages and environmental conditions, thereby optimizing its growth and astaxanthin accumulation, while achieving efficient use of energy, and providing intuitive visual monitoring and management through the digital twin platform.

[0166] The above are preferred embodiments of the present application, but do not limit the protection scope of the present application, therefore: any equivalent changes made in accordance with the structure, shape, principle of the present application should be covered within the protection scope of the present application.

Claims

1. A method for controlling light for Haematococcus cultivation based on edge control, characterized in that, The edge control-based Haematococcus pluvialis cultivation light system is used for light control of the Haematococcus pluvialis cultivation area, including the following steps: Step 1, a multi-channel data collector (21) collects data of a temperature sensor (11), a carbon dioxide sensor (12), a pH value sensor (13), an optical sensor (14), a microscopic imaging module (15) and a chlorophyll fluorescence sensor (16) at a set time interval and stores the data in a memory (22); Step 2, an AI chip (23) executes a light YOLOv8 model to identify microscopic imaging data obtained by the microscopic imaging module (15), and outputs the number of motile cells, the diameter of immobile spores and the area proportion of astaxanthin; Step 3, the AI chip (23) executes a trained growth stage determination model to output the growth stage of the Haematococcus pluvialis, and the input parameters are: the number of motile cells, the diameter of immobile spores, the area proportion of astaxanthin, the Fv / Fm value of the chlorophyll fluorescence sensor (16), the chlorophyll characteristic absorption peak intensity of the optical sensor (14), the culture solution temperature value collected by the temperature sensor (11), and the apparent color HSV value of the algal liquid collected by the visual camera (17); Step 4, the AI chip (23) calculates light demand parameters according to the growth stage of the Haematococcus pluvialis; Step 5, a control chip (24) generates a light control instruction according to the light demand parameters, and transmits the light control instruction to a PWM driver (33); Step 6, the PWM driver (33) executes the light control instruction to control the LED chip set (31) to supply light to the Haematococcus pluvialis according to the set light and spectrum combination; In step 3, the growth stage of the Haematococcus pluvialis includes a green growth period and a red stress period; In step 4, if it is determined that the growth stage of the Haematococcus pluvialis is the green growth period, a combination of red light, blue light and white light is used, and the calculation formula of the target light intensity is: ； wherein is the target light intensity, is the nutrient solution temperature, is the color enhancement factor; ; wherein algae liquid red saturation; The determination formula of the proportion of red light is: ; wherein is the red light proportion, is the carbon dioxide concentration; The determination formula of the proportion of blue light is: ； wherein is the blue light proportion, is the number of motile cells; The determination formula of the proportion of white light is: ； In step 4, if it is determined that the growth stage of the Haematococcus pluvialis is the red stress period, a combination of blue light, ultraviolet light and red light is used, and the calculation formula of the target light intensity is: base_intensity + diam_adjust; wherein is the target light intensity, is the base light intensity; diam_adjust is the diameter compensation term; ； ； wherein is the value, is the average diameter of the chlamydospores; The determination formula of the proportion of blue light is: ； wherein is the current red light proportion; The determination formula of the proportion of ultraviolet light is: ； wherein is the proportion of ultraviolet light, is the proportion of astaxanthin area; The determination formula of the proportion of red light is: 。 2. The edge control based Haematococcus cultivation light control method according to claim 1, characterized in that, The edge control-based Haematococcus cultivation light system comprises a plurality of sensor monitoring modules (1), a plurality of edge controllers (2), a plurality of lighting units (3) and a digital twin monitoring platform (4). The sensor monitoring module (1) is used for monitoring the environmental parameters, growth state parameters and visual pictures of Haematococcus in a set area range. The plurality of edge controllers (2) are respectively installed on one side of the plurality of sensor monitoring modules (1) and are in communication connection with the sensor monitoring modules (1). The edge controllers (2) collect the environmental parameters and growth state parameters to generate light control instructions through environmental parameter analysis and growth state analysis. The lighting unit (3) is used for supplementing light to Haematococcus in the area range. The digital twin monitoring platform (4) is in communication connection with the plurality of sensor monitoring modules (1) and the plurality of edge controllers (2), and performs three-dimensional modeling on the growth state of Haematococcus and displays three-dimensional simulation pictures and real-time visual pictures through digital twin.

3. The edge control based Haematococcus cultivation light control method according to claim 2, characterized in that, The sensor monitoring module (1) comprises a temperature sensor (11), a carbon dioxide sensor (12), a pH sensor (13), an optical sensor (14), a microscopic imaging module (15), a chlorophyll fluorescence sensor (16) and a visual camera (17). The temperature sensor (11) is used for monitoring the temperature value of the culture solution. The carbon dioxide sensor (12) is used for monitoring the environmental carbon dioxide concentration. The pH sensor (13) is used for monitoring the pH value of the nutrient solution. The optical sensor (14) is used for monitoring the environmental light parameter. The microscopic imaging module (15) and the chlorophyll fluorescence sensor (16) are used for monitoring the growth state parameters of Haematococcus. The visual camera (17) is used for shooting real-time visual pictures of Haematococcus. The temperature sensor (11), the carbon dioxide sensor (12), the pH sensor (13), the optical sensor (14), the microscopic imaging module (15) and the chlorophyll fluorescence sensor (16) are respectively in communication connection with the edge controller (2).

4. The edge control based Haematococcus cultivation light control method according to claim 3, characterized in that, The lighting unit (3) comprises an LED chip group (31), a heat dissipation system and a PWM driver (33). The LED chip group (31) is installed above the area range through a support and faces Haematococcus. The heat dissipation system is installed on the back of the LED chip group (31). The PWM driver (33) is in control connection with the LED chip group (31). The edge controller (2) controls the power and spectral combination of the LED chip group (31) through the PWM driver (33).

5. The edge control based Haematococcus cultivation light control method according to claim 4, characterized in that, The edge controller (2) comprises a multi-channel data collector (21), a memory (22), an AI chip (23) for analyzing the growth state of Haematococcus pluvialis, and a control chip (24), a data input end of the multi-channel data collector (21) is in communication connection with each sensor of the sensor monitoring module (1) respectively, the memory (22) is in communication connection with a data output end of the multi-channel data collector (21), the AI chip (23) is in communication connection with the memory (22), the control chip (24) is in communication connection with the AI chip (23), and the control chip (24) controls the power and the spectrum combination of the LED chip group (31) through a PWM driver (33).

6. The edge control based Haematococcus cultivation light control method according to claim 5, wherein, The digital twin monitoring platform (4) is realized based on a computer.

7. The edge control based Haematococcus cultivation light control method according to claim 6, wherein, The digital twin display step is further included, the digital twin monitoring platform (4) respectively collects real-time parameters of the plurality of sensor monitoring modules (1) and the plurality of edge controllers (2), three-dimensional modeling is performed on the growth state of Haematococcus pluvialis, and a digital twin is displayed to display a three-dimensional simulation picture and a real-time visual picture, and the display content includes the growth state and the light control parameter.

Images