Haematococcus culture solution dissolved oxygen intelligent cooperative regulation and control method and system

Abstract

The invention discloses an intelligent cooperative regulation and control method and system for dissolved oxygen in a haematococcus culture solution, relates to the field of bioengineering, and controls a decision-making layer to dynamically switch between a growth promotion regulation and control mode and a stress induction regulation and control mode based on biomass data and physiological status data in a haematococcus culture stage so as to realize cooperative regulation and control of dissolved oxygen, illumination, pH and a carbon source. According to the method, a growth promotion mode and a stress induction mode are dynamically switched, biomass accumulation is promoted through dissolved oxygen sine wave pulse fluctuation in the vegetative period, astaxanthin synthesis is induced through high-oxygen and low-oxygen circulation and blue light regulation in the stress period, and compared with traditional static regulation, the biomass is increased, and the yield of astaxanthin is increased. A light-oxygen synergistic factor k is introduced to dynamically adjust the fluctuation range of dissolved oxygen, the problem of illumination-dissolved oxygen mismatching is solved, and the photosynthetic efficiency is improved; a stress intensity index SI is established, stress parameters are adaptively optimized based on the astaxanthin synthesis rate, cell damage caused by over-stress is avoided, and the stability of the astaxanthin synthesis rate in the stress period is improved.

Description

Technical Field

[0001] The present invention relates to the field of bioengineering technology, and in particular to a method and system for intelligent coordinated regulation of dissolved oxygen in Haematococcus culture solution. Background Art

[0002] During the large-scale cultivation of Haematococcus pluvialis, the dissolved oxygen concentration of the culture medium is the core environmental factor regulating its growth, reproduction, and astaxanthin synthesis: during the vegetative growth stage, an appropriate dissolved oxygen level can promote algal cell photosynthesis and biomass accumulation; and during the stress induction stage (the critical period for astaxanthin synthesis), precise dissolved oxygen fluctuations (high oxygen stress-low oxygen recovery cycle) can significantly activate the activity of astaxanthin synthesis-related enzymes and increase the yield of the target product. However, existing Haematococcus pluvialis dissolved oxygen regulation technologies have the following key bottlenecks, making it difficult to meet the needs of efficient, stable, and low-cost industrial cultivation: Existing technologies often use fixed-parameter control strategies, maintaining a single dissolved oxygen range throughout the entire process, such as 50%-70% air saturation. These strategies fail to dynamically adjust control logic based on physiological states such as biomass and photosynthetic efficiency during different growth stages (vegetative and stress phases) of Haematococcus. For example, excessively high dissolved oxygen levels during the vegetative phase can easily lead to oxygen free radical damage, while insufficient dissolved oxygen during the stress phase can effectively induct astaxanthin synthesis, ultimately resulting in low biomass accumulation and target product synthesis.

[0003] Dissolved oxygen concentration is influenced by a combination of factors, including ventilation rate, gas ratio, light, pH, and carbon source availability, and is strongly correlated with Haematococcus algae's photosynthetic efficiency and metabolic rate. Existing technologies often regulate dissolved oxygen in isolation (e.g., maintaining dissolved oxygen levels solely by adjusting ventilation), ignoring the synergistic effects of dissolved oxygen, light, pH, and carbon source. For example, increasing light without simultaneously optimizing dissolved oxygen can lead to decreased photosynthetic efficiency. Blindly increasing dissolved oxygen when carbon source is insufficient can actually increase cellular respiration and waste energy.

[0004] Astaxanthin synthesis relies on a combination of stresses, including high oxygen concentration and blue light. However, the stress intensity, such as the high oxygen concentration, duration, and proportion of blue light, must be precisely matched to the tolerance of the algal cells. Too low an intensity slows astaxanthin synthesis, while too high an intensity inhibits algal cell activity and even causes death. Existing technologies often use fixed stress parameters, such as maintaining high oxygen for 20 minutes. This fails to adaptively adjust the stress intensity based on the astaxanthin synthesis rate of the previous cycle, resulting in large fluctuations in stress efficiency and unstable product yields.

[0005] In summary, there is an urgent need for an intelligent control method and system that can achieve stage adaptation, multi-parameter coordination, data-driven optimization, and experience reuse to break through the efficiency bottleneck of industrial cultivation. Summary of the Invention

[0006] In order to solve the above technical problems, the present invention provides a method and system for intelligent coordinated regulation of dissolved oxygen in Haematococcus culture solution. The following technical solutions are adopted: The method for intelligent coordinated regulation of dissolved oxygen in Haematococcus culture solution comprises the following steps: Step 1: Build a closed-loop control system consisting of a perception layer, an execution layer, a control decision layer, and a cloud platform; Step 2: The control decision layer dynamically switches between growth promotion and stress induction control modes based on biomass data and physiological status data during the Haematococcus cultivation phase, achieving coordinated regulation of dissolved oxygen with light, pH, and carbon source. Step 3: The edge computing gateway synchronizes the full amount of control data to the cloud platform at set intervals. The cloud platform performs multi-objective optimization simulation based on the digital twin model. The optimization objectives include final biomass, astaxanthin production, and energy consumption. Step 4: The cloud platform knowledge base uses a graph neural network to construct a correlation map between Haematococcus strains, environmental parameters, regulation strategies, and output effects; In step 5, when a new batch of cultivation is started, the top N historical cases with the highest similarity are retrieved from the atlas based on the current strain and environmental characteristics, and their optimal control parameter sequence is sent to the edge controller as the initial setting value.

[0007] Optionally, in step 2, when the optical density OD value measured by the online biomass monitoring probe is less than the OD threshold and the maximum photochemical efficiency of PSII measured by the photosynthetic efficiency sensor is greater than the photochemical threshold, the growth promotion regulation mode is triggered; The growth promotion regulation mode controls the three-way mixed gas valve and the micro-nano bubble generator to make the dissolved oxygen level fluctuate in a sinusoidal pulse within the range of 40%-80% air saturation with a cycle of 4-6 hours.

[0008] Optionally, a photo-oxygen synergistic factor k is introduced, ; in is the current light intensity, is the optimal light intensity, is the current dissolved oxygen value, is the optimum dissolved oxygen value; The system dynamically adjusts the sine wave parameters. When the K value deviates from 1 by more than 20%, the original dissolved oxygen fluctuation range of 40%-80% is converged to the current instantaneous dissolved oxygen value by 50%.

[0009] Optionally, the stress-induced regulation mode is triggered when any of the following conditions are met: In the stress-induced regulation mode, the OD value measured by the online biomass monitoring probe is greater than or equal to the OD threshold, and the maximum photochemical efficiency of PSII measured by the photosynthetic efficiency sensor is less than or equal to the photochemical threshold; The growth promotion mode is continuously operated for 7 days or more; The stress-induced regulation mode controls the three-way mixed gas valve to quickly raise the dissolved oxygen to 120%-150% air saturation and maintain it for 10-20 minutes. During this period, the blue light ratio of the LED dimmer is adjusted to 30%-50%; then, strong ventilation is used to quickly reduce the dissolved oxygen to 20%-30% air saturation and maintain it for 45-60 minutes.

[0010] Optionally, the stress-induced regulation mode establishes a stress intensity index SI; ; in is the high oxygen maintenance time, is the maximum permissible hyperoxia time, It is a high oxygen concentration. is the maximum allowable high oxygen concentration, It is a low oxygen concentration. is the baseline dissolved oxygen concentration, is the blue light ratio, is the maximum allowable blue light ratio, 、 、 and They are weight index; The system dynamically adjusts the SI value of this cycle based on the astaxanthin synthesis rate of the previous cycle. If the astaxanthin synthesis rate accelerates, the SI value increases by 10%, otherwise it decreases, achieving adaptive optimization of stress intensity.

[0011] Optionally, a dissolved oxygen soft-sensing model based on a long short-term memory network is constructed, which takes historical ventilation, light, pH, temperature, and biomass as input and dissolved oxygen values ​​as output, providing redundant measurements when the hardware sensor reliability is low.

[0012] Optionally, in step 3, the cloud platform first pre-processes the full amount of data synchronized by the edge gateway; then constructs three types of models: physical mass transfer, growth and metabolism of Haematococcus pluvialis, and energy consumption calculation; then sets a multi-objective function of maximizing biomass, maximizing astaxanthin, and minimizing energy consumption, and sets safety constraints for dissolved oxygen and pH processes; finally, uses a multi-objective optimization algorithm to solve, screen out the optimal control parameters, and convert them into execution instructions synchronized to the edge gateway.

[0013] Optionally, the retrieval process of the graph neural network in step 4 is: using the strain genotype, initial pH, temperature range and cultivation target of the current cultivation task as the query vector, calculating the similarity with the historical case nodes in the knowledge graph, and returning the regulation strategy of the case with the highest similarity.

[0014] Optionally, in step 5, first construct a query vector for the current cultivation task. The query vector includes: strain characteristics, initial environmental parameters, and cultivation target weights, and extract the same-dimensional vectors of historical cases in the knowledge graph. Then, through similarity calculation, select candidate cases that meet the similarity requirements, and select the top N cases in descending order of similarity. If the similarities are the same, give priority to the cases that are closer to the target. Finally, perform a weighted fusion of the control parameters of the top N cases, fine-tune them in combination with the current environmental deviation, generate an initial parameter sequence, and send it to the edge controller, and mark the reference case information.

[0015] The intelligent collaborative control system for dissolved oxygen in Haematococcus algae culture fluid is used to implement the intelligent collaborative control method for dissolved oxygen in Haematococcus algae culture fluid. The system includes a perception layer, an execution layer, a control decision layer, and a cloud platform. The multi-parameter sensors of the sensing layer include a dissolved oxygen sensor, a pH sensor, a temperature sensor, a photosynthetic efficiency sensor and an online biomass monitoring probe; The execution layer includes a three-way mixed gas valve, a micro-nano bubble generator, an LED dimmer and a CO2 injection valve; The control decision layer establishes a dynamic model with ventilation volume, gas ratio, stirring speed, and light as inputs, and dissolved oxygen and pH as outputs. The MPC controller calculates the optimal control instructions through rolling optimization, and drives the various actuators in the execution layer to work together to track the dynamic dissolved oxygen setting curve. The cloud platform builds a virtual model that corresponds one-to-one with the physical cultivation system, receives real-time data from the perception layer, and performs simulation and prediction; The cloud platform stores all historical data.

[0016] In summary, the present invention includes at least one of the following beneficial technical effects: The present invention can provide a method and system for intelligent coordinated regulation of dissolved oxygen in Haematococcus culture fluid. By real-time monitoring of biomass and photosynthetic efficiency, the growth promotion mode and the stress induction mode can be dynamically switched: during the nutrient period, biomass accumulation is promoted through dissolved oxygen sinusoidal pulse fluctuations; during the stress period, astaxanthin synthesis is induced through high oxygen-low oxygen cycle + blue light regulation. Compared with traditional static regulation, biomass is increased by 15%-25%, and astaxanthin production is increased by 20%-30%.

[0017] The photo-oxygen synergistic factor k was introduced to dynamically adjust the dissolved oxygen fluctuation range, solve the light-dissolved oxygen mismatch problem, and increase the photosynthetic efficiency by 10%-15%; a stress intensity index SI was established and the stress parameters were adaptively optimized based on the astaxanthin synthesis rate to avoid cell damage caused by excessive stress. The stability of the astaxanthin synthesis rate during the stress period was improved by more than 25%.

[0018] A dissolved oxygen soft-sensing model based on long-short-term memory networks is constructed to provide redundant measurement data in the event of hardware sensor failure, ensuring uninterrupted control. Combined with real-time data fusion of multi-parameter sensors, the credibility of monitoring data is increased to over 95%, significantly reducing the risk of culture failure due to sensor problems.

[0019] The cloud platform is based on a digital twin model and uses a multi-objective optimization algorithm to solve the optimal control parameters. While ensuring product output, it reduces energy consumption by optimizing parameters such as ventilation volume and light ratio. Compared with traditional control, the energy consumption per unit astaxanthin output is reduced by 18%-25%, and the cost competitiveness of industrial cultivation is significantly improved.

[0020] The system realizes a real-time closed loop of perception-decision-execution through the control decision-making layer, and reduces manual intervention by combining remote monitoring and optimization of the cloud platform. The data collaboration between edge computing and the cloud platform realizes efficient processing and strategy iteration of the entire data, reduces the workload of operation and maintenance personnel, and meets the intelligent management needs of large-scale cultivation. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a schematic flow chart of the method for intelligent coordinated regulation of dissolved oxygen in Haematococcus culture solution of the present invention; Figure 2 It is a curve diagram of the dynamic changes of dissolved oxygen and key parameters during a 14-day culture period in a specific embodiment of the present invention. DETAILED DESCRIPTION

[0022] The present invention will be further described in detail below with reference to the accompanying drawings.

[0023] The embodiments of the present invention disclose a method and system for intelligent coordinated regulation of dissolved oxygen in Haematococcus culture fluid.

[0024] Reference Figure 1 and Figure 2 Example 1: A method for intelligent coordinated regulation of dissolved oxygen in Haematococcus culture fluid, comprising the following steps: Step 1: Build a closed-loop control system consisting of a perception layer, an execution layer, a control decision layer, and a cloud platform; Step 2: The control decision layer dynamically switches between growth promotion and stress induction control modes based on biomass data and physiological status data during the Haematococcus cultivation phase, achieving coordinated regulation of dissolved oxygen with light, pH, and carbon source. Step 3: The edge computing gateway synchronizes the full amount of control data to the cloud platform at set intervals. The cloud platform performs multi-objective optimization simulation based on the digital twin model. The optimization objectives include final biomass, astaxanthin production, and energy consumption. Step 4: The cloud platform knowledge base uses a graph neural network to construct a correlation map between Haematococcus strains, environmental parameters, regulation strategies, and output effects; In step 5, when a new batch of cultivation is started, the top N historical cases with the highest similarity are retrieved from the atlas based on the current strain and environmental characteristics, and their optimal control parameter sequence is sent to the edge controller as the initial setting value.

[0025] By adopting the above technical solution, during the cultivation of Haematococcus pluvialis, there is a real-time interactive relationship between the changes in dissolved oxygen and environmental parameters, the physiological state of algal cells, and the actions of actuators. A closed-loop system is required to realize the complete link of data collection-decision calculation-instruction execution-effect feedback. The perception layer is responsible for capturing the key information of the cultivation system in real time, providing a data basis for regulation; the execution layer, as the carrier of instruction implementation, directly changes the dissolved oxygen and related environmental conditions; the control decision layer assumes the local real-time decision-making function to ensure the response speed of regulation; the cloud platform undertakes the tasks of massive data storage, deep optimization and knowledge precipitation. The four-layer structure is interconnected to form a closed loop with no data breakpoints and no decision delays, avoiding the problems of data disconnection and decision lag in traditional open-loop regulation, and laying the system foundation for subsequent collaborative regulation.

[0026] The life cycle of Haematococcus pluvialis consists of two core phases: vegetative growth and stress metabolism. These phases differ fundamentally in their requirements for dissolved oxygen and related environmental factors. During the vegetative growth phase, algal cell division and biomass accumulation are promoted, requiring dissolved oxygen to remain within a range suitable for photosynthesis, with moderate fluctuations enhancing cellular metabolic activity. During the stress induction phase, enzymes involved in astaxanthin synthesis are activated, generating stress signals through drastic changes in dissolved oxygen combined with adjustments in light and carbon sources.

[0027] The control decision-making layer uses biomass data to reflect the degree of algal cell accumulation and physiological status data to reflect the photosynthetic activity and metabolic direction of the cells. Based on this, it dynamically switches between growth-promoting and stress-inducing control modes to ensure that the control logic is precisely matched to the cultivation stage. Furthermore, dissolved oxygen is not an isolated environmental factor; it influences photosynthetic efficiency together with light, and cellular respiration and carbon metabolism together with pH and carbon source. Therefore, when regulating dissolved oxygen, light, pH, and carbon source are adjusted in tandem to avoid metabolic imbalances caused by single-factor regulation and improve control efficiency.

[0028] The edge computing gateway, located close to the cultivation site, collects and initially processes control data in real time, synchronizing the full data set to the cloud platform at set intervals. This ensures timely data transmission while avoiding excessive network load caused by high-frequency data transmission. The cloud platform boasts powerful computing and modeling capabilities. Based on the digital twin model, it constructs a virtual scene consistent with the actual cultivation system. This virtual environment can simulate the cultivation effects under different control parameters, eliminating the need for repeated trial and error in the actual system, reducing trial and error costs and cultivation risks.

[0029] Industrial cultivation of Haematococcus requires a balanced approach to both output efficiency and cost control. Maximizing biomass or astaxanthin production alone can lead to a surge in energy consumption, while minimizing energy consumption can compromise output. Therefore, the cloud platform sets a multi-objective function encompassing final biomass, astaxanthin production, and energy consumption. Using a multi-objective optimization algorithm, it finds the optimal control parameters that guarantee both high output and low energy consumption. These optimized parameters are then converted into execution instructions and synchronized to the edge gateway, completing a closed-loop data-simulation-optimization-execution process to balance output and cost.

[0030] The effectiveness of Haematococcus cultivation is influenced by multiple factors, including strain characteristics, environmental parameters, and regulatory strategies. These factors exhibit complex nonlinear relationships. Different strains have varying tolerances to environmental parameters, and the effectiveness of the same regulatory strategy under different environmental parameters also varies. Traditional databases struggle to effectively capture these complex relationships, while graph neural networks excel at processing structured data with inter-node connections. They can treat Haematococcus strains, environmental parameters, regulatory strategies, and output results as nodes in a knowledge graph. Using algorithms, they learn and quantify the strength of the connections between nodes, forming a structured knowledge system.

[0031] This association map not only realizes the orderly storage of historical cultivation data, but also converts scattered data into reusable knowledge, providing data support for the parameter setting of subsequent new batch cultivation, and avoiding the waste of knowledge caused by idle historical data.

[0032] When cultivating a new batch of Haematococcus, if the current strain characteristics and initial environmental characteristics are similar to those of a certain historical case, the appropriate control parameters are also highly valuable as a reference. Based on this, we first construct a query vector containing the current strain characteristics, initial environmental parameters, and cultivation target weights. Then, we extract the same-dimensional vectors of historical cases from the knowledge graph. Using similarity calculations, we select the top N historical cases most similar to the current cultivation task, ensuring the relevance and reliability of the reference cases.

[0033] While the control parameters of different historical cases are useful as a reference, they must be adjusted based on the deviations between the current actual environment and the historical environment to avoid inaccurate control caused by direct application. Therefore, the control parameters of the top N cases are weighted and fused, then fine-tuned based on the current environmental deviations to generate an initial parameter sequence suitable for the current training task and send it to the edge controller. This significantly shortens the parameter debugging cycle for new batch training and reduces initial training efficiency caused by parameter inappropriateness. At the same time, the reference case information is annotated to facilitate subsequent traceability and parameter optimization, improving the stability and startup speed of new batch training.

[0034] In Example 2, in step 2, when the optical density OD value measured by the online biomass monitoring probe is less than the OD threshold and the maximum photochemical efficiency of PSII measured by the photosynthetic efficiency sensor is greater than the photochemical threshold, the growth promotion regulation mode is triggered; The growth promotion regulation mode controls the three-way mixed gas valve and the micro-nano bubble generator to make the dissolved oxygen level fluctuate in a sinusoidal pulse within the range of 40%-80% air saturation with a cycle of 4-6 hours.

[0035] Example 3, introducing the photo-oxygen synergistic factor k, ; in is the current light intensity, is the optimal light intensity, is the current dissolved oxygen value, is the optimum dissolved oxygen value; The system dynamically adjusts the sine wave parameters. When the K value deviates from 1 by more than 20%, the original dissolved oxygen fluctuation range of 40%-80% is converged to the current instantaneous dissolved oxygen value by 50%.

[0036] Example 4: The stress-induced regulation mode is triggered when any of the following conditions is met: In the stress-induced regulation mode, the OD value measured by the online biomass monitoring probe is greater than or equal to the OD threshold, and the maximum photochemical efficiency of PSII measured by the photosynthetic efficiency sensor is less than or equal to the photochemical threshold; The growth promotion mode is continuously operated for 7 days or more; The stress-induced regulation mode controls the three-way mixed gas valve to quickly raise the dissolved oxygen to 120%-150% air saturation and maintain it for 10-20 minutes. During this period, the blue light ratio of the LED dimmer is adjusted to 30%-50%; then, strong ventilation is used to quickly reduce the dissolved oxygen to 20%-30% air saturation and maintain it for 45-60 minutes.

[0037] Example 5, stress induction regulation mode to establish stress intensity index SI; ; in is the high oxygen maintenance time, is the maximum permissible hyperoxia time, It is a high oxygen concentration. is the maximum allowable high oxygen concentration, It is a low oxygen concentration. is the baseline dissolved oxygen concentration, is the blue light ratio, is the maximum allowable blue light ratio, 、 、 and They are weight index; The system dynamically adjusts the SI value of this cycle based on the astaxanthin synthesis rate of the previous cycle. If the astaxanthin synthesis rate accelerates, the SI value increases by 10%, otherwise it decreases, achieving adaptive optimization of stress intensity.

[0038] By adopting the above technical solution, the core goal of the vegetative growth stage of Haematococcus pluvialis is to promote algal cell division and proliferation, and accumulate sufficient biomass. This stage requires the dual conditions of biomass not reaching the threshold and sufficient photosynthetic activity. The triggering logic is designed based on these two key physiological status indicators: The significance of optical density (OD) value: The OD value directly reflects the biomass concentration of Haematococcus in the culture medium. If the OD value is less than the OD threshold, it indicates that the current number of algal cells has not yet reached the target accumulation amount in the vegetative growth stage and that growth still needs to be continuously promoted. If the OD value meets the standard, it means that the cells have the biomass basis to enter the subsequent metabolic stage.

[0039] The significance of the maximum photochemical efficiency of PSII: The maximum photochemical efficiency of PSII is the core indicator for measuring the activity of photosynthetic system II of Haematococcus. If its value is greater than the photochemical threshold, it means that the photosynthetic apparatus of the algal cells is functioning intact, can efficiently utilize light energy for photosynthesis and substance synthesis, and has the physiological basis for rapid growth; if the value decreases, it indicates that the photosynthetic activity is declining, the cell growth potential is decreasing, and the regulation direction needs to be adjusted.

[0040] When both indicators are met at the same time, it means that the cells are in the critical period of nutritional growth with low biomass and high photosynthetic activity, triggering the growth-promoting regulatory mode, which can accurately match the cell growth needs and avoid wasting resources by starting other regulatory modes at inappropriate stages.

[0041] In the growth promotion control mode, dissolved oxygen is controlled by using a 40%-80% air saturation and a 4-6 hour period sinusoidal pulse fluctuation method. The core logic revolves around adapting to the laws of photosynthetic metabolism and enhancing cell activity. Principle of dissolved oxygen range selection: 40%-80% air saturation is the suitable dissolved oxygen range for the nutritional growth stage of Haematococcus pluvialis - below 40% will lead to obstruction of the photosynthetic electron transport chain and limit the efficiency of photosynthesis; above 80% may trigger the accumulation of oxygen free radicals and cause oxidative damage to algae cells. This range can balance photosynthetic needs and cell protection.

[0042] Advantages of sinusoidal pulse fluctuations: Compared with constant dissolved oxygen control, sinusoidal wave fluctuations are closer to the dynamic changes of dissolved oxygen in the natural environment, and can continuously provide moderate stimulation to algae cells - the rising stage of dissolved oxygen can meet the oxygen demand when the cell photosynthetic rate increases, and the falling stage avoids metabolic inhibition caused by excessive oxygen concentration, promotes the maintenance of cell metabolic enzyme activity at a high level, and thus accelerates the biomass accumulation rate.

[0043] The actuators' collaborative control principle: The three-way gas mixture valve adjusts the mixing ratio of air, oxygen, and other gases to control the oxygen content entering the culture medium. The micro-nano bubble generator produces tiny bubbles, increasing the contact area between the gas and the culture medium and improving the dissolved oxygen mass transfer efficiency. Working together, these two valves precisely control the dissolved oxygen concentration to follow a set sinusoidal curve, preventing excessive fluctuations or deviations from the target range, thereby ensuring precise control.

[0044] The photosynthetic efficiency of Haematococcus pluvialis depends on the synergistic matching of light and dissolved oxygen. Light provides energy for photosynthesis, while dissolved oxygen is an important intermediate product and environmental factor in photosynthetic metabolism. Both need to be maintained at an appropriate level to maximize photosynthetic efficiency. The light-oxygen synergy factor k is an indicator used to quantify the matching degree between the current light-oxygen state and the optimal light-oxygen state: When the k value is close to 1, it indicates that the current light intensity and dissolved oxygen value are close to their respective optimal values, the light-oxygen matching degree is high, and the photosynthetic system can operate efficiently; When the k value deviates from 1, it means that the light-oxygen state is unbalanced (such as the light is too strong but the dissolved oxygen is insufficient, or the dissolved oxygen is too high but the light is insufficient). At this time, if the original dissolved oxygen control logic is still maintained, it will aggravate the imbalance of photosynthetic metabolism and lead to a decrease in photosynthetic efficiency.

[0045] When the k value deviates from 1 by more than 20%, it indicates that the light-oxygen imbalance has reached a level that requires intervention. At this time, the original 40%-80% dissolved oxygen fluctuation range is converged to the current instantaneous dissolved oxygen value by 50%. The core purpose is to quickly alleviate the light-oxygen imbalance and maintain stable photosynthetic efficiency: The necessity of converging the fluctuation range: When there is an imbalance between light and oxygen, the original large fluctuation of dissolved oxygen may further expand the degree of imbalance. For example, when the light intensity is far below the optimum value (the k value is too small), the photosynthetic rate of algae cells decreases and the consumption of dissolved oxygen decreases. If the upper limit of dissolved oxygen is still maintained at 80%, the dissolved oxygen will continue to accumulate and cause oxygen damage. At this time, converging the fluctuation range can prevent the dissolved oxygen from shifting to extreme values ​​and reduce the negative impact of the imbalance.

[0046] The design logic of the 50% convergence ratio: Convergence of 50% can significantly reduce the fluctuation range of dissolved oxygen and quickly bring the dissolved oxygen state closer to the current optimum level, but will not completely eliminate the fluctuation of dissolved oxygen (avoiding metabolic adaptation problems caused by constant dissolved oxygen). It finds a balance between alleviating imbalance and maintaining cell activity stimulation, ensuring that the photosynthetic efficiency can still be maintained within an acceptable range when there is a light-oxygen imbalance. After the light or other conditions are adjusted, the original fluctuation range will be gradually restored.

[0047] Astaxanthin synthesis in Haematococcus pluvialis needs to be initiated under the stress state of cell growth being basically stopped and metabolism shifting to secondary metabolism. The triggering conditions are designed to accurately capture the conversion signals at this stage, while also setting a time backup mechanism to ensure the orderly progress of the cultivation process: The dual indicators of biomass and photosynthetic activity are triggered: when the OD value is greater than or equal to the OD threshold, it means that the biomass has reached the target accumulation amount and the cells have the material basis for synthesizing astaxanthin; the maximum photochemical efficiency of PSII is less than or equal to the photochemical threshold, indicating that the photosynthetic activity is declining and the cell growth potential is decreasing. At this time, metabolic resources can be tilted towards secondary metabolism (astaxanthin synthesis), which is in line with the physiological law of stage transition.

[0048] Time backup trigger: The growth promotion mode runs continuously for 7 days, which is based on the regular cycle setting of the nutritional growth stage of Haematococcus pluvialis. Even if the biomass or photosynthetic activity indicators do not reach the threshold due to environmental fluctuations, 7 days of growth has basically completed the biomass accumulation. If the growth promotion mode is maintained, it will lead to excessive cell proliferation and exhaustion of culture medium nutrients, which will affect the subsequent astaxanthin synthesis. Therefore, a time backup is set to ensure that the stage transition is not delayed.

[0049] The stress-induced regulation mode creates a compound stress environment through high oxygen-low oxygen cycle + blue light regulation. The core is to activate the enzyme system related to astaxanthin synthesis (such as β-carotene ketolase) while protecting cell activity: The design principle of hyperoxia stress is to quickly raise the dissolved oxygen to 120%-150% air saturation and maintain it for 10-20 minutes. High oxygen concentration will produce an appropriate amount of reactive oxygen species (ROS) in the cells. ROS, as a signal molecule, can activate the regulatory pathway of astaxanthin synthesis. The maintenance time is controlled at 10-20 minutes because excessive high oxygen for too long will lead to excessive accumulation of ROS and cause cell damage. This duration can achieve a balance between generating stress signals and protecting cells.

[0050] The principle of blue light synergy: Blue light (30%-50% ratio) can regulate the expression of key genes for astaxanthin synthesis through photoreceptors (such as rhodopsin-like protein), form a synergistic effect with hyperoxia stress, and significantly improve the efficiency of stress induction; the 30%-50% blue light ratio can effectively activate gene expression without causing damage to the photosynthetic apparatus due to excessive blue light.

[0051] The principle of hypoxia recovery: After hyperoxia stress, strong ventilation is used to quickly reduce the dissolved oxygen to 20%-30% air saturation and maintain it for 45-60 minutes. This is to allow cells to eliminate excess ROS in a hypoxic environment and restore metabolic balance. If high oxygen continues, cells will lose the ability to synthesize astaxanthin due to oxidative damage. The hypoxia recovery phase can repair cell function and prepare for the next cycle of stress. Strong ventilation can ensure that the dissolved oxygen drops rapidly, avoiding a long recovery phase that affects the efficiency of stress.

[0052] The astaxanthin synthesis efficiency of Haematococcus pluvialis is directly related to the stress intensity, but a single stress factor (such as high oxygen concentration, blue light ratio) cannot fully reflect the stress effect. It is necessary to integrate multi-dimensional stress factors to construct a comprehensive index. The design of SI is based on the law that multiple factors synergistically affect the stress effect: The factor selection logic of SI: the maintenance time of high oxygen and high oxygen concentration directly determine the intensity of high oxygen stress; low oxygen concentration affects the efficiency of cell recovery and indirectly affects the stress cycle effect; the blue light ratio is the core indicator of light stress - these four factors together constitute the key dimensions of the stress environment. By adjusting the influence of each factor through the weight index, the accuracy of SI's characterization of the actual stress effect can be optimized according to the differences in the sensitivity of different Haematococcus strains to stress.

[0053] The significance of setting the maximum allowable value: The maximum allowable values ​​of high oxygen time, high oxygen concentration, and blue light ratio are safety thresholds set based on the tolerance limit of Haematococcus cells, to avoid cell death caused by a single factor exceeding the threshold, and to ensure that the SI value fluctuates within the range of effective stress and cell safety.

[0054] The optimization of stress intensity requires feedback from the astaxanthin synthesis effect. The SI value of this cycle is adjusted based on the astaxanthin synthesis rate of the previous cycle. The core is to achieve precise matching of cellular stress response characteristics: Positive feedback adjustment (SI value increases by 10%): If the astaxanthin synthesis rate in the previous cycle accelerates, it means that the current stress intensity has not reached the optimal response threshold of the cell. Moderately increasing the SI value (such as increasing the high oxygen concentration and prolonging the high oxygen time) can further enhance the stress signal, activate more astaxanthin synthase systems, and increase the synthesis rate. A 10% increase can effectively increase the stress without causing the cells to suddenly become unable to adapt due to excessive increases.

[0055] Negative feedback adjustment (SI value decreasing): If the astaxanthin synthesis rate slows down in the previous cycle, it may be that the stress intensity is too high (causing cell damage) or too low (insufficient stress signal). At this time, lowering the SI value can adjust the stress intensity - if the intensity is too high, decreasing it can reduce cell damage and restore synthesis capacity; if the intensity is insufficient, after decreasing it, further judgment can be made through observation of subsequent cycles to avoid blindly increasing the stress.

[0056] Through this adaptive mechanism of effect feedback and intensity adjustment, the optimal stress intensity under the current culture conditions can be dynamically found, avoiding the problems of insufficient or excessive stress caused by traditional fixed stress parameters, ensuring that the astaxanthin synthesis rate continues to maintain a high level, and improving the stability of product yield.

[0057] Example 6: A dissolved oxygen soft-sensing model based on a long short-term memory network is constructed, with historical ventilation, light, pH, temperature, and biomass as input and dissolved oxygen value as output, providing redundant measurements when the hardware sensor reliability is low.

[0058] By employing the above technical solution, the long-short-term memory network (LSTM) is capable of capturing the correlation characteristics of time-series data and effectively handling the dynamic dependencies between historical parameters and current dissolved oxygen values ​​during dissolved oxygen fluctuations. Therefore, this network was selected to construct a dissolved oxygen soft-sensing model. The model inputs include historical ventilation, light, pH, temperature, and biomass because these parameters all have direct or indirect influences on dissolved oxygen values. Ventilation directly determines the efficiency of oxygen transfer to the culture medium; light influences dissolved oxygen production by affecting the photosynthesis rate of Haematococcus; pH and temperature indirectly affect dissolved oxygen levels by influencing algal physiological activities and oxygen solubility; and biomass reflects the overall scale of algal oxygen consumption and production. These parameters, combined, comprehensively capture the key factors influencing dissolved oxygen fluctuations. The model output is set as the dissolved oxygen value. Through training on historical data, the model is able to infer dissolved oxygen values ​​based on the input parameters. When hardware dissolved oxygen sensors experience data drift or failure, resulting in low reliability, the soft-sensing model can replace or supplement the hardware measurement results, providing continuous, reliable, and redundant data for dissolved oxygen control, thus preventing interruptions or deviations caused by hardware issues.

[0059] In Example 7, in step 3, the cloud platform first preprocesses the full data synchronized by the edge gateway; then constructs three models of physical mass transfer, Haematococcus growth, metabolism, and energy consumption calculation; then sets a multi-objective function of maximizing biomass, maximizing astaxanthin, and minimizing energy consumption, and sets safety constraints for dissolved oxygen and pH processes; finally, uses a multi-objective optimization algorithm to solve, screens out the optimal control parameters, and converts them into execution instructions synchronized to the edge gateway.

[0060] By adopting the above technical solution, the cloud platform first pre-processes the full amount of control data synchronized by the edge gateway. The purpose is to eliminate noise in the data, fill missing values ​​and unify the data format, ensure the accuracy and consistency of the data, and provide a reliable data foundation for subsequent modeling and optimization.

[0061] Then, three types of core models were constructed. Among them, the physical mass transfer model is used to simulate the transfer rules of substances such as oxygen and carbon source in the culture medium system, and accurately reflect the exchange process of substances between the liquid phase and the gas phase; the growth model and metabolic model of Haematococcus pluvialis are used to characterize the growth rate change rules of Haematococcus pluvialis under different environmental conditions, as well as the substance transformation pathways in its body, especially the metabolic mechanism of astaxanthin synthesis; the energy consumption calculation model is used to quantify the energy consumption of actuators such as three-way mixing gas valves and micro-nano bubble generators during operation, so as to realize the accurate calculation of the energy consumption of the control process.

[0062] Subsequently, a multi-objective function was set up, with maximizing the final biomass of Haematococcus pluvialis and maximizing the astaxanthin production as the core output goals, while minimizing the energy consumption of the entire regulation process was set as the cost control goal, forming a multi-dimensional optimization direction that takes into account both output and efficiency; on this basis, safety constraints were set for the dissolved oxygen and pH processes, and the reasonable fluctuation range of the two was clarified to avoid the growth inhibition or death of Haematococcus pluvialis due to parameters exceeding the safety threshold.

[0063] Finally, a multi-objective optimization algorithm is used to solve the above function. This algorithm can coordinate the conflicting relationships between different objectives while satisfying safety constraints, and select the control parameters with the best comprehensive performance in terms of biomass, astaxanthin production and energy consumption. These parameters are then converted into execution instructions that can be recognized by the execution layer and synchronized to the edge gateway, providing optimized control basis for the precise operation of subsequent actuators.

[0064] In Example 8, the retrieval process of the graph neural network in step 4 is: using the strain genotype, initial pH, temperature range and culture target of the current cultivation task as the query vector, calculating the similarity with the historical case nodes in the knowledge graph, and returning the regulation strategy of the case with the highest similarity.

[0065] By adopting the above technical solution, a query vector is constructed based on the strain genotype, initial pH, temperature range and cultivation objectives of the current cultivation task. The similarity between this vector and the historical case nodes in the knowledge graph is calculated with the help of a graph neural network. Finally, the control strategy corresponding to the case with the highest similarity is returned, realizing matching retrieval between historical experience and the current task.

[0066] In Example 9, in step 5, a query vector for the current cultivation task is first constructed. The query vector includes: strain characteristics, initial environmental parameters, and cultivation target weights, and the same-dimensional vectors of historical cases in the knowledge graph are extracted. Then, candidate cases that meet the similarity requirements are screened out through similarity calculation, and the top N cases are selected in descending order of similarity. If the similarities are the same, the case that is closer to the target is prioritized. Finally, the control parameters of the top N cases are weighted and fused, and fine-tuned in combination with the current environmental deviation to generate an initial parameter sequence, which is sent to the edge controller and annotated with reference case information.

[0067] By adopting the above technical solution, we first construct a query vector around the strain characteristics, initial environmental parameters, and cultivation goal weights of the current cultivation task, and extract the same-dimensional vectors of historical cases in the knowledge graph to ensure that the two have a comparable basis; then, we screen the qualified candidate cases through similarity calculation, and take the top N cases in descending order of similarity. If the similarity is the same, we give priority to the case whose output is closer to the current goal to ensure the relevance and practicality of the reference case; finally, we weight the fusion of the control parameters of the top N cases, and fine-tune them based on the current and historical environmental deviations to generate an initial parameter sequence adapted to the current task and send it to the edge controller. At the same time, we mark the reference case information for traceability, so as to achieve effective reuse of historical experience and precise adaptation to current needs.

[0068] Example 10, a system for intelligent coordinated regulation of dissolved oxygen in Haematococcus algae culture fluid, for implementing a method for intelligent coordinated regulation of dissolved oxygen in Haematococcus algae culture fluid, the system comprising a perception layer, an execution layer, a control decision layer, and a cloud platform; The multi-parameter sensors of the sensing layer include a dissolved oxygen sensor, a pH sensor, a temperature sensor, a photosynthetic efficiency sensor and an online biomass monitoring probe; The execution layer includes a three-way mixed gas valve, a micro-nano bubble generator, an LED dimmer and a CO2 injection valve; The control decision layer establishes a dynamic model with ventilation volume, gas ratio, stirring speed, and light as inputs, and dissolved oxygen and pH as outputs. The MPC controller calculates the optimal control instructions through rolling optimization, and drives the various actuators in the execution layer to work together to track the dynamic dissolved oxygen setting curve. The cloud platform builds a virtual model that corresponds one-to-one with the physical cultivation system, receives real-time data from the perception layer, and performs simulation and prediction; The cloud platform stores all historical data.

[0069] The following specific embodiments are used to illustrate the implementation principle of the present invention: A large-scale cultivation experiment of Haematococcus pluvialis was conducted in a 500L flat-plate photobioreactor to verify the feasibility and effectiveness of the intelligent coordinated regulation method and system for dissolved oxygen. The details are as follows: Culture scale: 500L flat-plate photobioreactor; Haematococcus strain: HA-01 strain; Initial environmental parameters: initial pH 7.1±0.1, culture temperature 25±1℃, initial biomass (OD 680 )0.1, initial light intensity 150μmol・m⁻ 2 ・s⁻ 1 (white light, blue light accounts for 10%); Culture period: 14 days (7 days of vegetative growth phase + 7 days of stress induction phase).

[0070] Control system construction: Perception layer configuration: Dissolved oxygen sensor: Hach LDOII, measuring range 0-200% air saturation, accuracy ±0.1%; pH sensor: Mettler-Toledo InPro3250, measuring range 0-14, accuracy ±0.01; Temperature sensor: PT100 platinum resistance, measuring range 0-50℃, accuracy ±0.1℃; Photosynthetic efficiency sensor: Walz PAM-2500, which can monitor the maximum photochemical efficiency of PSII (Fv / Fm) in real time with an accuracy of ±0.01; Online biomass monitoring probe: Ocean Optics STS-VIS model based on near-infrared spectroscopy, real-time output of OD680 value, measurement range 0-3.0, accuracy ±0.02.

[0071] Execution layer configuration: Three-way gas mixing valve: SMCVX3100, which can adjust the air and oxygen mixing ratio (0-100% oxygen ratio); Micro-nano bubble generator: pore size 5-10μm, aeration efficiency ≥90%, ventilation range 0.2-2.0vvm; LED dimmer: adjustable white light / blue light ratio (0-100% blue light ratio), light intensity range 50-300μmol・m⁻ 2 ・s⁻ 1 ; CO2 injection valve: Baode 2033 model, CO2 injection range 0-0.2vvm, response time ≤1s.

[0072] Control decision layer configuration: Hardware: Industrial-grade edge controller (Advantech UNO-2484G), sampling period of 10 minutes, communication protocol MQTT; Dynamic model: A nonlinear dynamic model was established with ventilation volume, oxygen ratio, stirring rate, and light intensity as inputs and dissolved oxygen and pH as outputs; MPC controller: The prediction time domain is 2 hours, the control time domain is 1 hour, and the rolling optimization objectives are to minimize the dissolved oxygen tracking error and smooth the actuator action.

[0073] Cloud platform configuration: Data preprocessing: 3σ criterion was used to eliminate outliers and linear interpolation was used to fill missing values; The digital twin model consists of three sub-models: Physical mass transfer model (based on double membrane theory, simulating the efficiency of oxygen transfer between gas, liquid and algae cells); Haematococcus algae growth model (Logistic equation, fitting biomass growth: ; Metabolism-energy consumption model (Monod equation describes astaxanthin synthesis, and energy consumption model quantifies the energy consumption of ventilation, illumination, and agitation: E=0.8Q+0.05I+0.02N, where Q is ventilation volume, I is light intensity, and N is agitation rate); Multi-objective optimization: NSGA-II algorithm was used, with the optimization objectives of max biomass X, max astaxanthin yield A, and min energy consumption E. Constraints included dissolved oxygen 20%-150% air saturation, and pH 6.5-8.0. Knowledge graph: constructed based on graph neural network (GNN), with nodes including strain genotype, initial pH, temperature range, regulation strategy, biomass, astaxanthin production, and edge weight as the association strength (0-1).

[0074] Complete control process: Phase 1: Vegetative Growth Phase (Days 1-7): Mode trigger: Set OD 680 Threshold value = 1.5, Fv / Fm threshold value = 0.75; on days 1-6, online monitoring showed OD 680 =0.3-1.4, Fv / Fm=0.76-0.82, satisfying OD<threshold and Fv / Fm>threshold, triggering the growth promotion regulation mode.

[0075] Dissolved oxygen control: Control the three-way mixed gas valve (oxygen content 5%-15%) and the micro-nano bubble generator to ensure that the dissolved oxygen fluctuates according to a sinusoidal pulse pattern of 40%-80% air saturation and a 5-hour period (e.g., dissolved oxygen curve on the third day: 40% at 8:00 → 60% at 10:30 → 80% at 13:00 → 60% at 15:30 → 40% at 18:00).

[0076] Photo-oxygen synergistic adjustment: set the optimal light intensity = 200μmol・m⁻ 2 ・s⁻ 1 , the optimum dissolved oxygen = 60% air saturation; on the 5th day, due to cloudy weather, the actual light intensity dropped to 120μmol・m⁻ 2 ・s⁻ 1 , the current dissolved oxygen = 70%, the calculated light-oxygen synergy factor k = (120 / 200) × (70 / 60) = 0.7, deviating from 1 by more than 20%; the system automatically converges the dissolved oxygen fluctuation range to 70% by 50% (original amplitude 40% → new amplitude 20%), and the new range is 60%-80% air saturation to avoid excessive accumulation of dissolved oxygen and causing oxygen damage.

[0077] Phase 2: Stress induction phase (Days 7-14): Mode trigger: On the 7th day, the growth promotion mode has lasted for 7 days, and the monitoring shows OD 680 =1.6 (≥threshold 1.5), Fv / Fm=0.72 (≤threshold 0.75), meeting the dual-index + time backup trigger conditions, and switching to the stress-induced regulation mode.

[0078] Stress parameter control: Hyperoxia stage: The three-way mixed gas valve increases the oxygen content to 40%, and the dissolved oxygen rises to 130% air saturation within 10 minutes, which is maintained for 15 minutes; at the same time, the LED dimmer adjusts the blue light ratio to 40% (total light intensity 250μmol・m⁻ 2 ・s⁻ 1 ); Hypoxia stage: strong ventilation (ventilation volume increased to 1.5vvm), dissolved oxygen dropped to 25% air saturation within 5 minutes, maintained for 50 minutes; Adaptive optimization of stress intensity index (SI): Set weights α = 0.3 (hyperoxia time), β = 0.4 (hyperoxia concentration), γ = 0.15 (hypooxia concentration), and δ = 0.15 (blue light ratio); maximum allowable hyperoxia time = 20 minutes, maximum allowable hyperoxia concentration = 150%, baseline dissolved oxygen = 60%, and maximum allowable blue light ratio = 50%; SI calculation for the first cycle on day 7: (15 / 20) × 0.3 + (130 / 150) × 0.4 + ((60-25) / (60-20)) × 0.15 + (40 / 50) × 0.15 = 0.225 + 0.347 + 0.131 + 0.12 = 0.823; On the 8th day, the astaxanthin synthesis rate of the previous cycle was monitored = 1.0 mg・L⁻ 1 ・d⁻ 1 (Compared to 0.8mg・L⁻ on the 7th day 1 ・d⁻ 1 Accelerate), SI is adjusted to 0.905 by 10%; simultaneously increase the high oxygen time to 17 minutes, high oxygen concentration to 135%, and blue light ratio to 42% to further activate the astaxanthin synthase system.

[0079] On the 10th day, the dissolved oxygen sensor experienced data drift due to contamination of the culture medium (displayed dissolved oxygen = 100%, but the algae solution was actually normal). The system automatically started the LSTM-based dissolved oxygen soft-sensing model (input: ventilation volume 0.8vvm in the past 24 hours, light 220μmol·m⁻ 2 ・s⁻ 1 , pH 7.3, temperature 25℃, biomass OD380 = 1.8, output dissolved oxygen = 85%); soft measurement data is used as the basis for control to avoid control deviations caused by hardware failure.

[0080] Cloud optimization: The edge gateway synchronizes full data to the cloud platform every 30 minutes. The cloud platform uses the NSGA-II algorithm to solve the multi-objective function and outputs the optimal control parameters on the 12th day: ventilation volume 1.0 vvm, oxygen ratio 35%, blue light ratio 43%, and CO2 injection volume 0.08 vvm. After the instructions are synchronized to the edge controller, the astaxanthin synthesis rate increases to 1.2 mg·L⁻ 1 ・d⁻ 1 , energy consumption is reduced by 8%.

[0081] New batch case reuse: Start a new batch of culture on day 15 (strain HA-01, initial pH 7.0, temperature 24-26°C, target astaxanthin production ≥15mg・L⁻ 1 ); Construct a query vector: strain characteristics (HA-01 genotype), initial parameters (pH 7.0, temperature 24-26°C), target weights (astaxanthin 0.6, biomass 0.3, energy consumption 0.1); Search the knowledge graph: After calculating the similarity, the top 3 historical cases were selected (similarities 92%, 88%, and 88%). The third case showed an astaxanthin production of 16.2 mg / L⁻. 1 Closer to the goal; Parameter fusion and fine-tuning: We weighted the parameters of the top three cases (weights 0.5, 0.25, and 0.25), combined with the current temperature being 1°C higher than the historical value, and fine-tuned the ventilation volume by +5% to generate an initial parameter sequence. After issuance, the startup cycle for new batches was shortened from the traditional three days to one day, and the initial dissolved oxygen control error was less than 5%.

[0082] After 14 days of cultivation, the measured indicators are as follows: Biomass (dry weight): 10.2g・L⁻ 1 ; Astaxanthin production: 16.5mg・L⁻ 1 ; Energy consumption per unit astaxanthin: 8.2kWh・kg⁻ 1 ; Batch-to-batch astaxanthin yield fluctuation: 7.2%; Dissolved oxygen monitoring reliability: 96% (soft measurement model seamlessly connected when sensor fails).

[0083] Traditional methods for regulating dissolved oxygen in Haematococcus are typically characterized by static parameter fixation, single-factor regulation, no data optimization, and no empirical reuse (e.g., maintaining dissolved oxygen at 50%-70% air saturation throughout the entire process, adjusting dissolved oxygen solely through ventilation, and no phase switching or cloud-based optimization). A comparison of key performance indicators between this technical solution and traditional methods is shown in Table 1: Table 1 Biomass and astaxanthin production increased by 19.0% and 61.8% respectively, solving the problem of insufficient oxygen during the nutrient period and ineffective oxygen during the stress period caused by traditional static regulation. The multi-objective optimization algorithm reduces the energy consumption per unit of astaxanthin by 34.4%, avoiding the energy waste caused by blind ventilation and illumination in traditional methods; Reusing historical cases shortened the startup cycle by 66.7% and reduced batch fluctuations by 52.0%, resolving the pain points of traditional methods, such as long parameter debugging and large batch differences. The dissolved oxygen soft-sensing model increases monitoring reliability to 96%, avoiding the risks of traditional methods that rely on hardware and suffer from failures and interruptions.

[0084] In summary, this technical solution provides a feasible path for the efficient industrial cultivation of Haematococcus pluvialis by comprehensively breaking through the bottlenecks of traditional methods.

[0085] The above are all preferred embodiments of the present invention, and are not intended to limit the scope of protection of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for intelligent coordinated regulation of dissolved oxygen in Haematococcus culture fluid, characterized in that: The following steps are involved: Step 1: Build a closed-loop control system consisting of a perception layer, an execution layer, a control decision layer, and a cloud platform; Step 2: The control decision layer dynamically switches between growth promotion and stress induction control modes based on biomass data and physiological status data during the Haematococcus cultivation phase, achieving coordinated regulation of dissolved oxygen with light, pH, and carbon source. Step 3: The edge computing gateway synchronizes the full amount of control data to the cloud platform at set intervals. The cloud platform performs multi-objective optimization simulation based on the digital twin model. The optimization objectives include final biomass, astaxanthin production, and energy consumption. Step 4: The cloud platform knowledge base uses a graph neural network to construct a correlation map between Haematococcus strains, environmental parameters, regulation strategies, and output effects; In step 5, when a new batch of cultivation is started, the top N historical cases with the highest similarity are retrieved from the atlas based on the current strain and environmental characteristics, and their optimal control parameter sequence is sent to the edge controller as the initial setting value.

2. The intelligent coordinated regulation method for dissolved oxygen in Haematococcus culture solution according to claim 1, characterized in that: In step 2, when the optical density OD value measured by the online biomass monitoring probe is less than the OD threshold and the maximum photochemical efficiency of PSII measured by the photosynthetic efficiency sensor is greater than the photochemical threshold, the growth promotion regulation mode is triggered; The growth promotion regulation mode controls the three-way mixed gas valve and the micro-nano bubble generator to make the dissolved oxygen level fluctuate in a sinusoidal pulse within the range of 40%-80% air saturation with a cycle of 4-6 hours.

3. The intelligent coordinated regulation method for dissolved oxygen in Haematococcus culture solution according to claim 2, characterized in that: Introducing the photo-oxidation synergistic factor k, ; in is the current light intensity, is the optimal light intensity, is the current dissolved oxygen value, is the optimum dissolved oxygen value; The system dynamically adjusts the sine wave parameters. When the K value deviates from 1 by more than 20%, the original dissolved oxygen fluctuation range of 40%-80% is converged to the current instantaneous dissolved oxygen value by 50%.

4. The intelligent coordinated control method for dissolved oxygen in Haematococcus culture solution according to claim 3, characterized in that: The stress-induced regulation mode is triggered when any of the following conditions are met: In the stress-induced regulation mode, the OD value measured by the online biomass monitoring probe is greater than or equal to the OD threshold, and the maximum photochemical efficiency of PSII measured by the photosynthetic efficiency sensor is less than or equal to the photochemical threshold; The growth promotion mode is continuously operated for 7 days or more; The stress-induced regulation mode controls the three-way mixed gas valve to quickly raise the dissolved oxygen to 120%-150% air saturation and maintain it for 10-20 minutes. During this period, the blue light ratio of the LED dimmer is adjusted to 30%-50%; then, strong ventilation is used to quickly reduce the dissolved oxygen to 20%-30% air saturation and maintain it for 45-60 minutes.

5. The intelligent coordinated regulation method for dissolved oxygen in Haematococcus culture solution according to claim 4, characterized in that: The stress-induced regulatory model establishes the stress intensity index SI; ； in is the high oxygen maintenance time, is the maximum permissible hyperoxia time, It is a high oxygen concentration. is the maximum allowable high oxygen concentration, It is a low oxygen concentration. is the baseline dissolved oxygen concentration, is the blue light ratio, is the maximum allowable blue light ratio, 、 、 and They are weight index; The system dynamically adjusts the SI value of this cycle based on the astaxanthin synthesis rate of the previous cycle. If the astaxanthin synthesis rate accelerates, the SI value increases by 10%, otherwise it decreases, achieving adaptive optimization of stress intensity.

6. The intelligent coordinated regulation method for dissolved oxygen in Haematococcus culture solution according to claim 5, characterized in that: A dissolved oxygen soft-sensing model based on long short-term memory network is constructed, which takes historical ventilation, light, pH, temperature, and biomass as input and dissolved oxygen value as output, providing redundant measurement when the reliability of hardware sensors is low.

7. The intelligent coordinated regulation method for dissolved oxygen in Haematococcus culture solution according to claim 6, characterized in that: In step 3, the cloud platform first pre-processes the full amount of data synchronized by the edge gateway; then constructs three types of models: physical mass transfer, growth and metabolism of Haematococcus, and energy consumption calculation; then sets a multi-objective function to maximize biomass, maximize astaxanthin, and minimize energy consumption, and sets safety constraints for dissolved oxygen and pH processes; finally, uses a multi-objective optimization algorithm to solve and screen out the optimal control parameters, which are converted into execution instructions and synchronized to the edge gateway.

8. The intelligent coordinated regulation method for dissolved oxygen in Haematococcus culture solution according to claim 7, characterized in that: In step 4, the retrieval process of the graph neural network is as follows: the strain genotype, initial pH, temperature range, and cultivation target of the current cultivation task are used as query vectors, the similarity with the historical case nodes in the knowledge graph is calculated, and the regulation strategy of the case with the highest similarity is returned.

9. The intelligent coordinated regulation method for dissolved oxygen in Haematococcus culture solution according to claim 8, characterized in that: In step 5, a query vector for the current cultivation task is first constructed. The query vector includes: strain characteristics, initial environmental parameters, and cultivation target weights, and the same-dimensional vectors of historical cases in the knowledge graph are extracted. Then, candidate cases that meet the similarity requirements are screened out through similarity calculation, and the top N cases are selected in descending order of similarity. If the similarities are the same, the case that produces output closer to the target is given priority. Finally, the control parameters of the top N cases are weighted and fused, combined with the current environmental deviation for fine-tuning, to generate an initial parameter sequence, which is sent to the edge controller and annotated with reference case information.

10. Intelligent coordinated control system for dissolved oxygen in Haematococcus culture fluid, characterized in that: For implementing the intelligent coordinated control method for dissolved oxygen in Haematococcus culture solution according to claim 9, the system includes a perception layer, an execution layer, a control decision layer and a cloud platform; The multi-parameter sensors of the sensing layer include a dissolved oxygen sensor, a pH sensor, a temperature sensor, a photosynthetic efficiency sensor and an online biomass monitoring probe; The execution layer includes a three-way mixed gas valve, a micro-nano bubble generator, an LED dimmer and a CO2 injection valve; The control decision layer establishes a dynamic model with ventilation volume, gas ratio, stirring speed, and light as inputs, and dissolved oxygen and pH as outputs. The MPC controller calculates the optimal control instructions through rolling optimization, and drives the various actuators in the execution layer to work together to track the dynamic dissolved oxygen setting curve. The cloud platform builds a virtual model that corresponds one-to-one with the physical cultivation system, receives real-time data from the perception layer, and performs simulation and prediction; The cloud platform stores all historical data.

Images