Circulating water microbial community regulation and control method and system

Abstract

The invention relates to a method and system for regulating and controlling microbial communities in a circulating water body, and the method comprises the steps: deploying a network composed of a plurality of water quality sensors which can collect various key parameters of the water body in real time and upload the key parameters to a cloud server; processing the collected data by using a big data analysis platform, identifying main factors influencing the development of the microbial community, training a predictive ecological model by using a machine learning algorithm, simulating the change trend of the microbial community in different scenes, evaluating the influence of the change trend on the water quality, and the like. A self-adaptive control theory is introduced, a closed-loop feedback system is constructed to optimize a microbial community structure and functional performance thereof, a small ecological environment most beneficial to survival and reproduction of target microorganisms is created, a targeted inhibition control strategy is implemented in the face of emergencies, the stability and safety of a water body ecological system are guaranteed, and the water body ecological system is protected. According to the method, the capability of dealing with emergency situations is improved, and the risk of environmental pollution is reduced.

Description

Technical Field

[0001] The invention relates to a circulating water microbial community control method and system, belonging to the technical field of water circulation treatment. Background Art

[0002] In circulating water systems, microbial communities play a vital role in water quality management and ecological balance. However, traditional management methods often rely on regular manual sampling and laboratory analysis. This method is not only time-consuming and labor-intensive, but also difficult to capture the real-time dynamic changes of microbial communities, resulting in delayed control measures and an inability to effectively respond to rapidly changing environmental conditions or sudden pollution incidents. In addition, due to the lack of accurate data support, traditional control methods are usually extensive, which can easily lead to waste of resources or poor results.

[0003] Therefore, it is urgent to develop a method that can monitor, intelligently analyze and automatically regulate microbial communities in real time to ensure stable water quality, improve water resource utilization efficiency, and reduce environmental pollution risks. Summary of the invention

[0004] The purpose of the present invention is to timely understand the dynamic changes of circulating water microbial communities and solve the problem of circulating water microbial community regulation, and to propose a circulating water microbial community regulation method and system.

[0005] The technical solution implemented by the present invention is as follows: a method for regulating microbial communities in circulating water, wherein the method optimizes the microbial community structure by constructing a closed-loop feedback control system, and the regulation steps are as follows: (1) Real-time monitoring and data collection. The closed-loop feedback control system relies on a network of multiple water quality sensors deployed in the water body. These sensors can continuously collect key parameters of the water body, including pH, dissolved oxygen, temperature, conductivity, ammonia nitrogen, nitrate, and phosphate, and transmit these data to the cloud server through a low-power wireless communication module; water samples are collected regularly, including high-throughput gene sequencing, to obtain detailed microbial community information, and all data will be stored in a large database; (2) Data analysis and model prediction: The big data analysis platform on the cloud server processes the collected data to identify the main factors affecting the development of microbial communities; a predictive ecological model is trained using machine learning algorithms. This model can simulate the changing trends of microbial communities under different scenarios, thereby predicting their changes and their impact on water quality; (3) Implementation of dynamic control measures: Based on the recommendations provided by the ecological model, the system takes a series of specific control measures to optimize the microbial community, including adding specific types of beneficial bacteria to improve water quality and adjusting light and water flow conditions to create the best living environment for beneficial microorganisms; If an abnormal situation is detected (such as the entry of harmful pathogens or the deviation of water quality parameters from the normal range), the closed-loop feedback control system will immediately trigger the corresponding adjustment action to ensure that the entire system is always in the optimal state; In the event of an emergency, the system can autonomously and dynamically adjust parameters, simulate the growth trend of biological communities under emergency conditions, and implement targeted suppression and control strategies to ensure the stability and safety of the water ecosystem; (4) Adaptive control and optimization. The closed-loop feedback control system introduces adaptive control theory. It is not just a one-time adjustment, but a continuous monitoring of the system output and comparison with the actual observed value. When significant changes in certain parameters are detected, the system can respond quickly and start the emergency response mode to quickly adjust relevant parameters, including changing light intensity, water flow rate, and nutrient concentration factors to simulate and predict the changing trend of the biological community under sudden conditions, thereby optimizing the microbial community structure and its functional performance. (5) Objective function and penalty coefficient. In order to achieve more precise control, an objective function is set. When it is necessary to deal with emergencies or abnormal situations, a penalty coefficient is introduced for calculation. The penalty coefficient is an index adjustment value set based on the influence of each factor in the current environment. It aims to find the most influential factor set and mark it so that the most effective control measures can be taken.

[0006] The water quality sensor is selected to be suitable for different water quality parameters, including pH value, dissolved oxygen, temperature, conductivity, ammonia nitrogen, nitrate, and phosphate, to ensure that the water quality sensor has good corrosion resistance and stability, and can work stably in an underwater environment for a long time; the position of the water quality sensor is reasonably arranged according to the specific conditions of the water body to ensure that the entire monitoring area is covered; the water quality sensor is firmly installed on the bottom of the water or at a specific height in the water using a suitable fixing device to prevent displacement caused by water flow impact, and the water quality sensor is regularly calibrated and maintained to ensure data accuracy.

[0007] Each water quality sensor node is equipped with a low-power wireless communication module, which is responsible for transmitting the collected data to the gateway device; the gateway is then connected to the cloud server via the Internet.

[0008] The method for predicting the change trend of the microbial community is as follows: construct an exponentially weighted moving average feature of a time series, evaluate the strength of the relationship between different variables through the Pearson correlation coefficient, extract and construct new features that are helpful for model training, and the calculation formula is as follows: ; 123 Among them, for x The i-th observation value of ; for y The i-th observation value of ; for x The average value of for y The average value of After the processing is completed, the LSTM model structure is defined, the equation is updated, and the LSTM model is trained using the cross entropy loss function to make the predicted value as close to the true label as possible. In this process, the softmax function is used for probability distribution conversion. The conversion formula is as follows: ; in is the true category label, is the probability distribution predicted by the model; Then, a variety of different operating scenarios were designed, such as changing light intensity, water flow rate, adding specific bacteria species, etc., to simulate the impact of these changes on the microbial community. Based on the trained LSTM model, parameter combinations under various scenarios were input to predict the changing trend of the microbial community and its impact on water quality.

[0009] The specific regulatory measures include: (1) Add specific types of beneficial bacteria to improve water quality.

[0010] (2) Adjust light and water flow conditions to create an optimal living environment for beneficial microorganisms.

[0011] (3) Setting up physical or chemical barriers to prevent harmful pathogens from entering the water body; physical barriers are physical obstacles that separate the pollution source from the water body, including fences and filters; chemical barriers are to prevent harmful substances from entering the water body by adding chemical agents or to change the water environment to make it unfavorable for the survival of harmful microorganisms.

[0012] (4) In the event of an emergency, the system can dynamically adjust parameters to simulate the growth trend of the biological community under the emergency state.

[0013] (5) Implement targeted suppression and control strategies to ensure the stability and safety of aquatic ecosystems.

[0014] After the prediction of the change trend of the microbial community is completed, the corresponding factor items are targeted for inhibition and control according to the predicted situation, and the gradient descent method is used to find the best parameter combination, so as to dynamically complete autonomous control.

[0015] The specific method of autonomously and dynamically adjusting parameters to simulate the growth trend of biological communities under sudden conditions is as follows: (1) Setting up an adaptive control system that relies on a controller to receive data input, dynamically adjust parameters based on preset rules and learned experience, and continuously monitor the system output and compare it with the actual observed value; (2) Define a set of adjustable parameters P, each of which represents a factor that affects the development of the microbial community, including light intensity, water flow rate, and nutrient concentration; (3) Set an objective function. When a significant change in certain parameters is detected, the system immediately starts the emergency response mode, quickly adjusts the relevant parameters to simulate the growth trend of the biological community under the emergency state, and introduces a penalty coefficient for calculation. The formula is as follows: ; in, represents the component value of the corresponding parameter, It is the penalty coefficient. The penalty coefficient needs to be adjusted in the range of -1 to 1 according to the parameter set of the factors that affect the development of the microbial community that are independently selected. The greater the proportion of the influence of the selected factors in the current environment, the smaller the range of the index calculation. The smaller the proportion of the influence of the selected factors in the current environment, the larger the range of the index calculation. The most influential factor set is obtained and these factors are marked.

[0016] A system for regulating microbial communities in circulating water includes various types of water quality sensors, a cloud server, a wireless communication module, a large database, a sampling device, an automatic dosing device, and a flow rate controller. All water quality sensor nodes are equipped with a low-power wireless communication module, and the water quality parameters collected by the water quality sensor are uploaded to the cloud server through the wireless communication module; the water sample gene sequencing data and microbial community information collected by the sampling device are stored in a large database and sent to the cloud server; the cloud server issues instructions to the actuator based on the circulating water information obtained, automatically adds drugs to the circulating water, adjusts the composition of the water microbial community, and starts the flow rate controller to control the flow rate of the water flow, so that the water microbial community is in a normal growth state.

[0017] The beneficial effect of the present invention lies in that the present invention introduces adaptive control theory and constructs a closed-loop feedback system to optimize the structure of microbial communities and their functional performance. On the one hand, the system can automatically adjust conditions such as light, water flow and nutrient supply according to actual monitoring data to create a microhabitat that is most conducive to the survival and reproduction of target microorganisms. On the other hand, when faced with emergencies, it can respond quickly by changing specific parameter combinations to simulate and predict the changing trends of biological communities under emergency conditions, and then implement targeted inhibition and control strategies to ensure the stability and safety of water ecosystems. This method improves the ability to respond to emergencies and reduces the risk of environmental pollution. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 The present invention is a flowchart of the steps of the circulating water microbial community regulation method; Figure 2It is a flowchart of the steps of the autonomous dynamic adjustment method of the present invention; Figure 3 It is a schematic diagram of the structure of the circulating water microbial community regulation system of the present invention. DETAILED DESCRIPTION

[0019] like Figure 1 As shown, this embodiment provides a method for regulating microbial communities in circulating water, and the steps are as follows: Step 1: Collect water samples regularly and deploy a network of multiple water quality sensors that can collect key parameters of the water body in real time and upload them to the cloud server; Step 2: Use the big data analysis platform to process the collected data, identify the main factors affecting the development of microbial communities, use machine learning algorithms to train predictive ecological models, simulate the changing trends of microbial communities under different scenarios, thereby predicting the changing trends of microbial communities and evaluating their impact on water quality; Step 3: Based on the recommendations provided by the ecological model, a series of specific regulatory measures are taken, including adding specific types of beneficial bacteria to improve water quality when necessary, adjusting light and water flow conditions to create an optimal living environment for beneficial microorganisms, and setting up physical or chemical barriers to prevent harmful pathogens from entering the water body; Step 4: Establish a closed-loop control system to automatically monitor changes in water quality parameters. If an abnormality is detected, the corresponding adjustment action is immediately triggered to ensure that the entire system is always in the optimal state.

[0020] In order to obtain detailed information about the microbial community, water samples will be collected regularly for high-throughput gene sequencing, and all data will be stored in a large database for subsequent analysis.

[0021] This embodiment selects sensors suitable for different water quality parameters, including pH value, dissolved oxygen, temperature, conductivity, ammonia nitrogen, nitrate, phosphate, etc., to ensure that the sensors have good corrosion resistance and stability, and can work stably in underwater environments for a long time. According to the specific conditions of the water body, the positions of the sensors are reasonably arranged to ensure that the entire monitoring area is covered. The sensors are firmly installed on the bottom of the water or at a specific height in the water using suitable fixing devices to prevent displacement caused by water flow impact. The sensors are calibrated and maintained regularly to ensure data accuracy.

[0022] Each sensor node is equipped with a low-power wireless communication module, which is responsible for transmitting the collected data to the gateway device. The gateway is then connected to the cloud server via the Internet.

[0023] The method for predicting the change trend of the microbial community in this embodiment is as follows: construct an exponentially weighted moving average feature of a time series, evaluate the strength of the relationship between different variables through the Pearson correlation coefficient, extract and construct new features that are helpful for model training, and the calculation formula is as follows: ; in, for x The i-th observation value of ; for y The i-th observation value of ; for x The average value of for y The average value of After the processing is completed, the LSTM model structure is defined, the equation is updated, and the LSTM model is trained using the cross entropy loss function to make the predicted value as close to the true label as possible. In this process, the softmax function is used for probability distribution conversion. The conversion formula is as follows: ; Where is the true category label and is the probability distribution predicted by the model; Then, a variety of different operating scenarios were designed, such as changing light intensity, water flow rate, adding specific bacteria species, etc., to simulate the impact of these changes on the microbial community. Based on the trained LSTM model, parameter combinations under various scenarios were input to predict the changing trend of the microbial community and its impact on water quality.

[0024] like Figure 2 As shown, in the event of an emergency, the parameters are adjusted dynamically to simulate the growth trend of the biological community under the emergency state. The specific method is as follows: Step 1: Set up an adaptive control system that relies on a controller to receive data input, dynamically adjust parameters based on preset rules and learned experience, and continuously monitor the system output and compare it with the actual observed value; Step 2: In this process, a set of adjustable parameters P is defined, each parameter represents a factor that affects the development of microbial communities, such as light intensity, water flow rate, nutrient concentration, etc. Step 3: Then set an objective function. When significant changes are detected in certain parameters, the system immediately starts the emergency response mode, quickly adjusts the relevant parameters to simulate the growth trend of the biological community under the emergency state, and introduces the penalty coefficient for calculation. The formula is as follows: ; in, represents the component value of the corresponding parameter, It is the penalty coefficient. The penalty coefficient needs to be adjusted in the range of -1 to 1 according to the parameter set of the factors that affect the development of the microbial community that are independently selected. The greater the proportion of the influence of the selected factors in the current environment, the smaller the range of the index calculation. The smaller the proportion of the influence of the selected factors in the current environment, the larger the range of the index calculation. The most influential factor set is obtained and these factors are marked.

[0025] After the emergency prediction is completed, targeted suppression control is taken on the corresponding factors according to the predicted situation, and the gradient descent method is used to find the optimal parameter combination, so as to dynamically complete autonomous control.

[0026] like Figure 3 As shown, a circulating water microbial community regulation system includes a hardware part and a software part. The hardware part includes but is not limited to various types of water quality sensors, cloud servers, wireless communication modules, sampling devices, automatic dosing equipment, and flow rate controllers. All hardware components must have good corrosion resistance and stability to adapt to the complex underwater working environment.

[0027] All water quality sensor nodes are equipped with a low-power wireless communication module. The water quality parameters collected by the water quality sensors are uploaded to the cloud server through the wireless communication module. The water sample gene sequencing data and microbial community information collected by the sampling device are stored in a large database and sent to the cloud server. The cloud server issues instructions to the actuator based on the circulating water information obtained, automatically adds drugs to the circulating water, adjusts the composition of the water microbial community, and starts the flow rate controller to control the flow rate of the water so that the water microbial community is in a normal growth state.

[0028] The hardware part of this embodiment also includes a computer storage medium, on which a computer program is stored. The computer program is executed by the processor to perform adaptive control of the system, and the microbial community of the circulating water body is automatically regulated by adjusting the pH value of the water, the flow rate of the water, the temperature of the water, the conductivity of the water, the oxygen content of the water, the light intensity of the water, the nutritional status of the water, etc.; the changing trend of the microbial community under different scenarios is simulated; and specific regulation suggestions are generated based on the model prediction results to guide the system to take appropriate measures to optimize the microbial community structure and its functional performance.

Claims

1. A method for regulating microbial communities in circulating water, characterized in that: The method optimizes the microbial community structure by constructing a closed-loop feedback control system, and the regulation steps are as follows: (1) Collect water samples regularly and deploy a network of multiple water quality sensors that can collect key parameters of the water body in real time and upload them to the cloud server; (2) Use the big data analysis platform to process the collected data and identify the main factors affecting the development of microbial communities; Use machine learning algorithms to train predictive ecological models to simulate the changing trends of microbial communities under different scenarios, thereby predicting the changing trends of microbial communities and assessing their impact on water quality; (3) Based on the recommendations provided by the ecological model, a series of specific regulatory measures are taken, such as adding specific types of beneficial bacteria to improve water quality when necessary, adjusting light and water flow conditions to create an optimal living environment for beneficial microorganisms, and setting up physical or chemical barriers to prevent harmful pathogens from entering the water body; in the event of an emergency, the parameters are adjusted dynamically to simulate the growth trend of the biological community under the emergency state; (4) Adaptive control optimization: The closed-loop feedback control system introduces adaptive control theory to continuously monitor the system output and compare it with the actual observed value; When significant changes are detected in certain parameters, the system responds quickly and activates emergency response mode, quickly adjusting relevant parameters, including changes in light intensity, water flow rate, and nutrient concentration factors, to simulate and predict changing trends in biological communities under sudden conditions, thereby optimizing the structure of microbial communities and their functional performance; automatically monitor changes in water quality parameters, and if an abnormality is detected, immediately trigger corresponding adjustment actions to ensure that the entire system is always in the optimal state.

2. The method for regulating circulating water microbial communities according to claim 1, characterized in that: The regular collection of water samples includes high-throughput gene sequencing to obtain detailed microbial community information, and all data will be stored in a large database for subsequent analysis.

3. The method for regulating microbial communities in circulating water according to claim 1, characterized in that: The water quality sensor is selected to be suitable for different water quality parameters, including pH value, dissolved oxygen, temperature, conductivity, ammonia nitrogen, nitrate, and phosphate, to ensure that the water quality sensor has good corrosion resistance and stability, and can work stably in an underwater environment for a long time; the position of the water quality sensor is reasonably arranged according to the specific conditions of the water body to ensure that the entire monitoring area is covered; the water quality sensor is firmly installed on the bottom of the water or at a specific height in the water using a suitable fixing device to prevent displacement caused by water flow impact, and the water quality sensor is regularly calibrated and maintained to ensure data accuracy.

4. The method for regulating circulating water microbial communities according to claim 1, characterized in that: The node of the water quality sensor is equipped with a low-power wireless communication module, which is responsible for transmitting the collected data to the gateway device; the gateway is then connected to the cloud server via the Internet.

5. The method for regulating circulating water microbial communities according to claim 1, characterized in that: The method for predicting the change trend of the microbial community is as follows: construct an exponentially weighted moving average feature of a time series, evaluate the strength of the relationship between different variables through the Pearson correlation coefficient, extract and construct new features that are helpful for model training, and the calculation formula is as follows: ; in, x , y is a variable parameter; for x No. i observations; for y No. i observations; for x The average value of for y The average value of After the processing is completed, define the LSTM model structure, update the equation, and use the cross entropy loss function to train the LSTM model so that the predicted value is as close to the true label as possible. In this process, the softmax function is used to convert the probability distribution. The conversion formula is as follows; ; in is the true category label, is the probability distribution predicted by the model; Then, a variety of different operating scenarios were designed, such as changing light intensity, water flow rate, adding specific bacteria species, etc., to simulate the impact of these changes on the microbial community. Based on the trained LSTM model, parameter combinations under various scenarios were input to predict the changing trend of the microbial community and its impact on water quality.

6. The method for regulating microbial communities in circulating water according to claim 1, characterized in that: The specific method of autonomously and dynamically adjusting parameters to simulate the growth trend of biological communities under sudden conditions is as follows: (1) Setting up an adaptive control system that relies on a controller to receive data input, dynamically adjust parameters based on preset rules and learned experience, and continuously monitor the system output and compare it with the actual observed value; (2) Define a set of adjustable parameters P, each of which represents a factor that affects the development of the microbial community, including light intensity, water flow rate, and nutrient concentration; (3) Set an objective function. When a significant change in certain parameters is detected, the system immediately starts the emergency response mode, quickly adjusts the relevant parameters to simulate the growth trend of the biological community under the emergency state, and introduces a penalty coefficient for calculation. The formula is as follows: ; in, represents the component value of the corresponding parameter, It is the penalty coefficient. The penalty coefficient needs to be adjusted in the range of -1 to 1 according to the parameter set of the factors that affect the development of the microbial community that are independently selected. The greater the proportion of the influence of the selected factors in the current environment, the smaller the range of the index calculation. The smaller the proportion of the influence of the selected factors in the current environment, the larger the range of the index calculation. The most influential factor set is obtained and these factors are marked.

7. The method for regulating circulating water microbial communities according to claim 1, characterized in that: The regulatory measures include: (1) Adding specific types of beneficial bacteria to improve water quality; (2) Adjust light and water flow conditions to create an optimal living environment for beneficial microorganisms; (3) Setting up physical or chemical barriers to prevent harmful pathogens from entering the water body; physical barriers are physical barriers that separate the pollution source from the water body, including fences and filters; chemical barriers are to prevent harmful substances from entering the water body by adding chemical agents or to change the water environment to make it unfavorable for the survival of harmful microorganisms; (4) In the event of an emergency, the system can dynamically adjust parameters to simulate the growth trend of the biological community under the emergency state; (5) Implement targeted suppression and control strategies to ensure the stability and safety of aquatic ecosystems.

8. The method for regulating circulating water microbial communities according to claim 5, characterized in that: After the prediction of the change trend of the microbial community is completed, the corresponding factor items are targeted for inhibition and control according to the predicted situation, and the gradient descent method is used to find the best parameter combination, so as to dynamically complete autonomous control.

9. A circulating water microbial community control system for implementing a circulating water microbial community control method as claimed in claims 1 to 7, characterized in that: The system includes various types of water quality sensors, a cloud server, a wireless communication module, a large database, a sampling device, an automatic dosing device and a flow rate controller; all water quality sensor nodes are equipped with a low-power wireless communication module, and the water quality parameters collected by the water quality sensor are uploaded to the cloud server through the wireless communication module; the water sample gene sequencing data and microbial community information collected by the sampling device are stored in the large database and sent to the cloud server; The cloud server sends instructions to the actuator based on the circulating water information obtained, automatically adds medicine to the circulating water, adjusts the composition of the water microbial community, and starts the flow rate controller to control the flow rate of the water flow, so that the water microbial community is in a normal growth state; The system also includes a computer storage medium on which a computer program is stored. The computer program is executed by a processor to adaptively control the system, and the microbial community of the circulating water body is automatically regulated by adjusting the pH value of the water, the flow rate of the water, the temperature of the water, the conductivity of the water, the oxygen content of the water, the light intensity of the water, and the nutritional status of the water; the changing trend of the microbial community under different scenarios is simulated; and specific regulation suggestions are generated based on the model prediction results to guide the system to take appropriate measures to optimize the microbial community structure and its functional performance.

Images