Airborne microorganism enrichment operation control method and system based on sample analysis

Abstract

This invention relates to the field of air sampling technology, and in particular to a method and system for controlling air microbial enrichment operations based on sample analysis. This invention integrates the abundance of target and other microorganisms in air samples, microbial competition relationships, and enrichment operation conditions. Through a constructed hybrid neural network model, it can accurately predict the biomass of the target microorganisms after the operation. It analyzes the impact of the enrichment operation on the equipment status based on the operation and equipment operating conditions, enabling early prevention of equipment failures. By combining the biomass prediction results with the impact of equipment status on the enrichment operation mode, it helps to select the most suitable mode, improving the targeting and effectiveness of the enrichment operation, optimizing equipment use, and greatly enhancing the enrichment efficiency of the target microorganisms.

Description

Technical Field

[0001] This invention relates to the field of air sampling technology, and in particular to an operational control method and system for airborne microbial enrichment based on sample analysis. Background Technology

[0002] In the fields of airborne microbiology research and related industrial production, the enrichment culture of target microorganisms is a crucial fundamental operation. Accurate and efficient enrichment of target microorganisms not only facilitates in-depth research into their biological characteristics and metabolic mechanisms but also provides key support for numerous fields such as biopharmaceuticals, fermentation engineering, and environmental remediation. Traditional microbial enrichment methods mainly rely on empirical operations and simple culture medium adjustments. These methods often lack in-depth consideration of the complex interrelationships among members of the microbial community, focusing only on the growth conditions of the target microorganism itself. However, in natural environments or actual samples, microorganisms exist in the form of communities, with various interactions such as competition and symbiosis among different microorganisms. These interactions significantly affect the growth and enrichment effect of target microorganisms. For example, some non-target microorganisms may compete with target microorganisms for nutrients and living space, thereby inhibiting the growth of target microorganisms and leading to low enrichment efficiency.

[0003] Furthermore, existing enrichment operation modes are usually based on fixed processes and parameters, lacking real-time monitoring and adjustment of various dynamic factors during the operation. During the enrichment process, the operating status of the equipment is affected by a variety of factors, such as byproducts produced by microbial growth and metabolism, and changes in the physicochemical properties of the culture medium. If the impact of these factors on the equipment status cannot be understood in a timely manner, it may lead to equipment failure, thereby affecting the continuity and stability of the enrichment operation.

[0004] In view of this, the applicant proposes an operational control method and system for airborne microbial enrichment based on sample analysis. Summary of the Invention

[0005] To overcome the defects and shortcomings of existing technologies, this invention provides a method and system for controlling airborne microbial enrichment operations based on sample analysis. This application combines biomass prediction results and equipment status to perform matching analysis on enrichment operation modes, which helps to select the most suitable mode, improves the targeting and effectiveness of enrichment operations, optimizes equipment use, and greatly enhances the enrichment efficiency of target microorganisms.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] In a first aspect, the present invention provides a method for controlling the enrichment of airborne microorganisms based on sample analysis, comprising the following steps:

[0008] S100: Collect air samples using sampling equipment, identify the types of microorganisms in the air using a microbial identification module, obtain the abundance of target microorganisms and other microorganisms, and obtain the operation status of various enrichment operation modes at each time.

[0009] S200. Predict the biomass of the target microorganism after the operation by considering the operation status at each time point of the enrichment operation mode, the abundance of the target microorganism, the abundance of other microorganisms, and the competitive relationship between microorganisms.

[0010] S300. Analyze the impact of enrichment operations on the state of enrichment equipment by considering the operational status at various times and the operating status of the enrichment equipment.

[0011] S400. Matching analysis of various enrichment operation modes is performed based on the predicted biomass of target microorganisms after operation and the influence of the state of the enrichment equipment.

[0012] S500: Selects an enrichment operation mode through matching analysis of various enrichment operation modes and performs enrichment operations accordingly.

[0013] In one implementation of the present invention, step S100 includes the following specific contents:

[0014] A set amount of air samples were collected at the corresponding collection locations using sampling equipment. Species identification was performed using qPCR and nanopore sequencing technologies. The abundance of the target microorganism in the collected samples was obtained. 16S rRNA sequencing was performed on other microorganisms, and species were annotated based on a species annotation database. The results were stored according to phylum, genus, and species. The raw data were converted into microbial concentrations per unit volume. The competition coefficient between the target microorganism and other microorganisms was obtained by looking up the microbial competition table. The operation status of each enrichment operation mode at each time point was obtained, and the equipment parameters were matched with the enrichment operation time points.

[0015] In one implementation of the present invention, the prediction of target microbial biomass after operation in step S200 includes the following specific steps:

[0016] Step 210: Obtain the operation status of each time step in the historical enrichment operation mode, the abundance of the target microorganism, the abundance of other microorganisms, and the competitive relationship between microorganisms. The competitive relationship includes the competition coefficient and the co-existence coefficient. Construct a hybrid neural network model with the operation status of each time step in the enrichment operation mode, the abundance of the target microorganism, the abundance of other microorganisms, and the competitive relationship between microorganisms as inputs, and the target microorganism biomass prediction value after the enrichment operation is completed as output.

[0017] Step 220: Obtain the operation status of various enrichment operation modes at each time step, the abundance of target microorganisms, the abundance of other microorganisms, and the competitive relationship between microorganisms. Import these information into the constructed hybrid neural network model and output the target microbial biomass after the operation of various enrichment operation modes.

[0018] In one implementation of the present invention, the analysis of the impact of the enrichment operation on the state of the enrichment device specifically includes the following:

[0019] Step 310: Obtain the change curves of each control mode parameter during the operation, and at the same time obtain the safety range data of the corresponding mode parameter of the corresponding enrichment device.

[0020] Step 320: Analyze the average rate of change of parameters by analyzing the change curves of each control mode parameter, and divide the average absolute value of the change of parameters by the range of the safe range data of the corresponding mode parameter by analyzing the change curves of adjacent time points during operation. This yields the influence coefficient of the change of control parameters on the state of the corresponding module, thus analyzing the impact of sudden changes in output parameters on equipment operation.

[0021] Step 330: Weighted summation of the state influence coefficients of all modules to obtain the state influence of the enrichment device. The enrichment device is usually composed of multiple modules, and the state of each module will affect the overall operation of the device. By weighted summation of the state influence coefficients of all modules, a comprehensive index can be obtained to reflect the overall state influence of the device. By weighted summation, different weights can be assigned according to the importance of different modules in the device.

[0022] In one implementation of the present invention, the matching analysis of the enrichment operation mode includes the following specific aspects:

[0023] The process involves multiplying the status impact of the enrichment equipment by the influence coefficient of equipment malfunction on microbial biomass to obtain the biomass impact anomaly. Subtracting this biomass impact anomaly from the calculated value and multiplying the difference by the target microbial biomass after the enrichment operation mode is then performed to obtain the revised target microbial biomass. The absolute value of the difference between the revised target microbial biomass and the required target microbial biomass is then calculated, and its reciprocal is taken to obtain the matching result for the corresponding enrichment operation mode. This process incorporates the status impact of the enrichment equipment while also considering the impact of equipment malfunctions on microbial biomass. During microbial enrichment, the normal operation of the equipment is crucial for microbial growth and reproduction. This method allows for a comprehensive assessment of the combined impact of equipment factors on the target microbial biomass throughout the entire enrichment system.

[0024] In one implementation of the present invention, the selection of an enrichment operation mode for enrichment operation includes the following specific aspects:

[0025] The state impact of the enrichment device is compared with the corresponding state impact threshold. Enrichment operations with state impact less than or equal to the corresponding state impact threshold are selected as pre-selected operations, while enrichment operations with state impact greater than the corresponding state impact threshold are not selected. The final matching results of the enrichment operation modes are sorted in descending order, and the matching result of the corresponding enrichment operation mode with the largest value in the predicted operations is selected as the enrichment operation mode.

[0026] Secondly, the present invention also provides an airborne microbial enrichment operation and control system based on sample analysis, comprising:

[0027] The data acquisition module collects air samples through sampling equipment and identifies the types of microorganisms in the air through the microbial identification module, obtaining the abundance of target microorganisms and the abundance of other microorganisms, while also acquiring the operation status of various enrichment operation modes at various times.

[0028] The biomass prediction module predicts the biomass of the target microorganism after the operation by considering the operation status at each time point in the enrichment operation mode, the abundance of the target microorganism, the abundance of other microorganisms, and the competitive relationship between microorganisms.

[0029] The state impact analysis module analyzes the state impact of enrichment operations on the enrichment equipment by considering the operational status at various times and the operating status of the enrichment equipment.

[0030] The matching analysis module performs matching analysis on various enrichment operation modes based on the predicted biomass of the target microorganisms after the operation and the influence of the state of the enrichment equipment.

[0031] The enrichment operation selection module selects an enrichment operation mode for enrichment operation through matching analysis of various enrichment operation modes.

[0032] Thirdly, the present invention provides an electronic device comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes an airborne microbial enrichment operation control method based on sample analysis by calling the computer program stored in the memory.

[0033] Fourthly, the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform an airborne microbial enrichment operation control method based on sample analysis.

[0034] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0035] By combining the abundance of target and other microorganisms in air samples, microbial competition relationships, and enrichment operations, the constructed hybrid neural network model can accurately predict the biomass of target microorganisms after the operation.

[0036] Analyzing the impact of enrichment operations on equipment status based on operational and equipment operating conditions can help prevent equipment failures in advance.

[0037] Matching enrichment operation modes with biomass prediction results and equipment status impact helps select the most suitable mode, improves the targeting and effectiveness of enrichment operations, optimizes equipment use, and greatly enhances the enrichment efficiency of target microorganisms. Attached Figure Description

[0038] Other features, objects, and advantages of the invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0039] Figure 1 This is a schematic diagram of the overall process structure of an embodiment of the method of the present invention;

[0040] Figure 2 This is a schematic diagram of the target microbial biomass prediction process of the present invention;

[0041] Figure 3 This is a schematic diagram of the module composition structure of an embodiment of the system of the present invention;

[0042] Figure 4 This is a schematic diagram illustrating the process of constructing the hybrid neural network model of this invention. Detailed Implementation

[0043] The technical solution of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations thereof. In the absence of conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.

[0044] Please see Figure 1 , Figure 1 This is a schematic diagram of the overall process of the airborne microbial enrichment operation control method based on sample analysis provided in this embodiment of the invention, which specifically includes the following steps:

[0045] S100: Collect air samples using sampling equipment, identify the types of microorganisms in the air using a microbial identification module, obtain the abundance of target microorganisms and other microorganisms, and obtain the operation status of various enrichment operation modes at each time.

[0046] In this embodiment, step S100 includes the following specific contents:

[0047] Air samples of a set amount were collected at corresponding sampling locations using sampling equipment. Species identification was performed using qPCR and nanopore sequencing technologies. The abundance of the target microorganism in the collected samples was obtained. 16S rRNA sequencing was performed on other microorganisms, and species were annotated based on a species annotation database. The results were stored according to phylum, genus, and species. The raw data was converted into microbial concentration per unit volume. The competition coefficient between the target microorganism and other microorganisms was obtained by referring to the microbial competition table. The operational conditions at each time point of each enrichment operation mode were obtained, and the equipment parameters (such as temperature, humidity, nutrient solution flow rate, and aeration rate) were obtained and matched with the enrichment operation time points. For example, the effect of "temperature 30℃ and glucose flow rate 2mL / min" on microbial abundance was recorded to provide input for modeling. The microbial competition table was obtained through the two experiments.

[0048] S200. Predict the biomass of the target microorganism after the operation by considering the operation status at each time point of the enrichment operation mode, the abundance of the target microorganism, the abundance of other microorganisms, and the competitive relationship between microorganisms.

[0049] In this embodiment, as Figure 2 As shown, the target microbial biomass prediction after operation in S200 includes the following specific steps:

[0050] Step 210: Obtain the operation status of each time step in the historical enrichment operation mode, the abundance of the target microorganism, the abundance of other microorganisms, and the competitive relationship between microorganisms. The competitive relationship includes the competition coefficient and the co-existence coefficient. Construct a hybrid neural network model with the operation status of each time step in the enrichment operation mode, the abundance of the target microorganism, the abundance of other microorganisms, and the competitive relationship between microorganisms as inputs, and the target microorganism biomass prediction value after the enrichment operation is completed as output.

[0051] Among them, such as Figure 4 As shown, the specific steps for constructing a hybrid neural network model are as follows:

[0052] First, time-series data needs to be collected, including enrichment operation mode parameters (such as temperature, humidity, oxygen concentration, nutrient solution flow rate, stirring speed, etc.), qPCR or sequencing abundance data of the target microorganism, and abundance data of other microorganisms. At the same time, the competition relationship between microorganisms (such as competition coefficient or co-existence coefficient) needs to be obtained, and the final biomass measured offline (such as dry weight method) is used as a label for supervised learning. Then, a data preprocessing process is performed, including time alignment (such as interpolation to unify sampling interval), normalization (MinMax or Z-score standardization), feature engineering (such as calculating sliding window statistics, competition ratio, growth rate, etc.), and the data is divided into training set (70%), validation set (15%) and test set (15%) according to time order.

[0053] Then, the acquired data is divided into dynamic and static data:

[0054] Dynamic time-series data (LSTM branch): format is sequence(T,D), where T is the number of time steps (e.g., 100 time points) and D is the number of features (e.g., temperature, oxygen, pH, microbial abundance, etc.); Static feature data (fully connected branch): format is sequence(M), where M is the number of static features (e.g., microbial competition coefficient, initial concentration, mean environmental parameters, etc.); Features need to be normalized to the same scale (e.g., to [0,1]); Target variable (supervised learning): final biomass;

[0055] Furthermore, the construction of the neural network is carried out: LSTM time-series processing construction process: Input layer: The function of this layer is to receive time-series data. The time-series data here has a specific shape, its time step size is T, and the data dimension of each time step is D. That is to say, the input is a time-series data sequence containing T time steps, each time step having D features.

[0056] LSTM Layers: Number of Layers and Units: A Long Short-Term Memory (LSTM) network with 1 to 3 layers is used. Each layer contains between 64 and 128 LSTM units. The number of LSTM units essentially determines the dimension of the hidden states, which in turn determines the information capacity that the LSTM layer can learn and remember.

[0057] Dropout regularization: Add a Dropout layer after each LSTM layer. The Dropout ratio is set between 0.2 and 0.5. Dropout is a common way to prevent overfitting, so that the model does not rely too much on certain neurons, thereby enhancing the model's generalization ability.

[0058] Static feature processing construction process: Input layer: This input layer is used to receive static data. The shape of the input static data is (M), which represents a one-dimensional vector with M features;

[0059] Fully connected layers: Number of layers and neurons: Use 1 to 2 fully connected layers. The number of neurons in each layer is between 32 and 64. Fully connected layers can perform non-linear transformations on the input features and learn complex relationships between features. Activation function: Fully connected layers use ReLU (Modified Linear Unit) as the activation function, which can introduce non-linear factors, allowing the model to learn more complex patterns while maintaining high computational efficiency.

[0060] Next, the splicing process is constructed: the outputs of the LSTM temporal processing branch and the static feature processing branch are spliced ​​together along the feature dimension. Fusion layer: Fully connected layer settings: 1 to 2 fully connected layers are used for further feature fusion, with each layer having 16 to 32 neurons. The ReLU activation function is also used to introduce non-linear transformation and enhance the model's expressive power. Output layer: The output layer uses one neuron, and its function is to directly predict biomass; the output result is the predicted value of biomass.

[0061] Finally, the prediction bias was optimized using mean squared error or Huber loss, and the evaluation metrics were R² and MAE. The optimizer used was Adam (initial learning rate 0.001), combined with L2 regularization and EarlyStopping (the model terminated after 5 rounds of validation if the loss did not decrease). Ultimately, the model can predict the biomass of the target microorganism under different operating conditions.

[0062] Step 220: Obtain the operation status of various enrichment operation modes at each time step, the abundance of target microorganisms, the abundance of other microorganisms, and the competitive relationship between microorganisms. Import these information into the constructed hybrid neural network model and output the target microbial biomass after the operation of various enrichment operation modes.

[0063] S300. Analyze the impact of enrichment operations on the state of enrichment equipment by considering the operational status at various times and the operating status of the enrichment equipment.

[0064] In this embodiment, the analysis of the impact of enrichment operations on the state of the enrichment device includes the following specific contents:

[0065] Step 310: Obtain the change curves of each control mode parameter during the operation, and at the same time obtain the safety range data of the corresponding mode parameter of the corresponding enrichment device.

[0066] Step 320: Analyze the average rate of change of parameters through the change curves of each control mode parameter. Divide the average absolute value of the parameter change by the range of the corresponding mode parameter's safety range data to obtain the state influence coefficient of the control parameter change on the corresponding module. This analyzes the impact of sudden changes in output parameters on equipment operation. For example, if the stirring speed needs to suddenly change from 500 rpm to 200 rpm within a certain time, this sudden change in stirring speed will negatively affect the operation of the stirring equipment. The average rate of change of parameters reflects the speed of parameter change. When the rate of change suddenly increases, it may mean that the parameter has undergone a sudden change, which may have an adverse effect on the operation of the equipment. For example, a sudden change in stirring speed may lead to uneven stirring, affecting product quality. Dividing the average absolute value of the parameter change by the range of the safety range data can measure the relative magnitude of the parameter change within the safety range. Even if the parameter does not exceed the safety range, if the relative magnitude of the change is large, it may still pose a potential risk to the operation of the equipment. The state influence coefficient comprehensively considers the rate of change and the relative magnitude of the parameter change, providing a quantitative indicator for assessing the impact of control parameter changes on the corresponding module.

[0067] Step 330: The state influence coefficients of all modules are weighted and summed to obtain the state influence of the enrichment device. The enrichment device typically consists of multiple modules, and the state of each module affects the overall operation of the device. By weighting and summing the state influence coefficients of all modules, a comprehensive index reflecting the overall state influence of the device can be obtained. The weighted summation method allows for the allocation of different weights based on the importance of different modules within the device. This more accurately reflects the degree of influence of different modules on the overall state of the device. The weights are obtained by collecting relevant data from each module, such as parameter change rates and magnitudes, standardizing the data to eliminate the dimensional influence between different indicators, and calculating the information entropy of each indicator. Information entropy reflects the amount of information contained in the indicator. The weight of each indicator is calculated based on the information entropy; the smaller the information entropy, the greater the degree of variation of the indicator, the more information it contains, and therefore the greater its weight.

[0068] S400. Matching analysis of various enrichment operation modes is performed based on the predicted biomass of target microorganisms after operation and the influence of the state of the enrichment equipment.

[0069] In this embodiment, the matching analysis of enrichment operation patterns includes the following specific contents:

[0070] The process involves multiplying the impact of the enrichment equipment's status by the influence coefficient of the equipment's malfunction on microbial biomass to obtain the biomass impact anomaly. Subtracting this biomass impact anomaly from the calculated value and multiplying it by the target microbial biomass after the enrichment operation mode's operation yields the revised target microbial biomass. The absolute value of the difference between the revised target microbial biomass and the required target microbial biomass is then used to calculate the reciprocal of the difference, resulting in the matching result for the corresponding enrichment operation mode. This process considers both the status of the enrichment equipment and the impact of equipment malfunctions on microbial biomass. During microbial enrichment, the normal operation of the equipment is crucial for microbial growth and reproduction. This method allows for a comprehensive assessment of the combined impact of equipment factors on the target microbial biomass throughout the enrichment system, avoiding evaluation biases caused by focusing on a single factor. Combining equipment status and the biomass influence coefficient to calculate the biomass impact anomaly enables more accurate prediction of the actual biomass of the target microorganisms under different enrichment operation modes. This helps in proactively implementing countermeasures during actual operation, improving the success rate and efficiency of microbial enrichment.

[0071] S500: Selects an enrichment operation mode through matching analysis of various enrichment operation modes and performs enrichment operations accordingly.

[0072] In this embodiment, the enrichment operation mode is selected for the enrichment operation, including the following specific contents:

[0073] The state impact of the enrichment device is compared with the corresponding state impact threshold. Enrichment operations with a state impact less than or equal to the corresponding state impact threshold are selected as pre-selected operations, while enrichment operations with a state impact greater than the corresponding state impact threshold are not selected. The final matching results of the enrichment operation modes are sorted in descending order, and the matching result of the enrichment operation mode corresponding to the largest matching result in the predicted operations is selected as the enrichment operation mode. The user operates the enrichment device to perform enrichment operations according to the selected enrichment operation mode.

[0074] In this embodiment, the unspecified setting parameters and thresholds are obtained by fitting historical data. Specifically, the abundance of historical target microorganisms and other microorganisms is obtained, along with the operation status of various enrichment operation modes at each time point. These are then imported into the steps of this embodiment for selecting the enrichment operation mode. Simultaneously, historical microorganisms are evenly distributed across all enrichment operation modes to conduct experiments and obtain the enrichment operation mode with the highest matching result. The selection result and experimental result are then imported into MATLAB fitting software for data fitting, and the values ​​of the setting parameters and thresholds with the highest accuracy in matching the judgment are output.

[0075] Furthermore, the scheme in this embodiment, by comprehensively considering the abundance of target and other microorganisms in air samples, microbial competition relationships, and enrichment operation conditions, can accurately predict the biomass of target microorganisms after the operation through the constructed hybrid neural network model; the operation and equipment operation status analysis can prevent equipment failure in advance; and the combination of biomass prediction results and equipment status impact analysis to match enrichment operation modes helps to select the most suitable mode, which can improve the targeting and effectiveness of enrichment operations, optimize equipment use, and greatly improve the enrichment efficiency of target microorganisms.

[0076] Please see Figure 3 , Figure 3 This is a schematic diagram of the structure of the airborne microbial enrichment operation and control system based on sample analysis provided in an embodiment of the present invention, including:

[0077] The data acquisition module collects air samples through sampling equipment and identifies the types of microorganisms in the air through the microbial identification module, obtaining the abundance of target microorganisms and the abundance of other microorganisms, while also acquiring the operation status of various enrichment operation modes at various times.

[0078] The biomass prediction module predicts the biomass of the target microorganism after the operation by considering the operation status at each time point in the enrichment operation mode, the abundance of the target microorganism, the abundance of other microorganisms, and the competitive relationship between microorganisms.

[0079] The state impact analysis module analyzes the state impact of enrichment operations on the enrichment equipment by considering the operational status at various times and the operating status of the enrichment equipment.

[0080] The matching analysis module performs matching analysis on various enrichment operation modes based on the predicted biomass of the target microorganisms after the operation and the influence of the state of the enrichment equipment.

[0081] The enrichment operation selection module selects an enrichment operation mode for enrichment operation through matching analysis of various enrichment operation modes.

[0082] The parameters and steps of each unit module in the sample analysis-based airborne microbial enrichment operation control system of the present invention that achieve their respective functions can be referred to the parameters and steps in the embodiments of the sample analysis-based airborne microbial enrichment operation control method described above, and will not be repeated here.

[0083] Embodiments of the present invention also provide an electronic device, including a memory, a processor, and a communication bus; the memory and the processor are connected via the communication bus. The memory stores an airborne microbial enrichment operation control method based on sample analysis, which can be loaded by the processor and executed as provided in the above embodiments.

[0084] The memory can be used to store instructions, programs, code, code sets, or instruction sets. The memory may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for at least one function, and instructions for implementing the airborne microbial enrichment operation control method based on sample analysis provided in the above embodiments, etc. The data storage area may store data involved in the airborne microbial enrichment operation control method based on sample analysis provided in the above embodiments, etc.

[0085] A processor may include one or more processing cores. The processor executes instructions, programs, code sets, or instruction sets stored in memory, and calls data stored in memory to perform various functions and process data according to the present invention. The processor may be at least one of the following: Application-Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), Central Processing Unit (CPU), controller, microcontroller, and microprocessor. It is understood that, for different devices, the electronic devices used to implement the above-described processor functions may also be other types, and the embodiments of the present invention do not specifically limit this.

[0086] A communication bus can include a pathway for transmitting information between the aforementioned components. The communication bus can be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Communication buses can be categorized as address buses, data buses, control buses, etc.

[0087] This invention provides a computer-readable storage medium storing a computer program that can be loaded by a processor and executed as described in the above embodiments, which is a sample analysis-based airborne microbial enrichment operation control method.

[0088] In this embodiment of the invention, the computer-readable storage medium can be a tangible device that holds and stores instructions used by an instruction execution device. The computer-readable storage medium can be, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination thereof. Specifically, the computer-readable storage medium can be a portable computer disk, a hard disk, a USB flash drive, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), spoofing random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory stick, floppy disk, optical disk, magnetic disk, mechanical encoding device, or any combination thereof.

[0089] The terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0090] The above description is merely a preferred embodiment of the present invention and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this application is not limited to the technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the foregoing concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions claimed in this invention.

Claims

1. A method for operational control of airborne microbial enrichment based on sample analysis, characterized in that, Includes the following steps: S100: Collect air samples using sampling equipment, identify the types of microorganisms in the air using a microbial identification module, obtain the abundance of target microorganisms and other microorganisms, and obtain the operation status of various enrichment operation modes at each time. S200. Predict the biomass of the target microorganism after the operation by considering the operation status at each time point of the enrichment operation mode, the abundance of the target microorganism, the abundance of other microorganisms, and the competitive relationship between microorganisms. This is achieved by constructing a hybrid neural network model that takes as input the operation status at each time step of the enrichment operation mode, the abundance of the target microorganism, the abundance of other microorganisms, and the competitive relationship between microorganisms, and outputs the predicted value of the target microorganism biomass after the enrichment operation is completed. S300. Analyze the impact of enrichment operations on the state of enrichment equipment by considering the operational status at various times and the operating status of the enrichment equipment. Specifically, it includes the following content: Acquire the change curves of parameters of each control mode during the operation, and at the same time acquire the safety range data of the corresponding mode parameters of the corresponding enrichment device; By analyzing the average rate of change of parameters through the change curves of each control mode parameter, and by dividing the average absolute value of the change of parameters through the change curves of adjacent time points during operation by the range of the safe range data of the corresponding mode parameter, the influence coefficient of the change of control parameters on the state of the corresponding module is obtained. The corresponding module is each component module of the enrichment device. The state influence coefficients of all modules are weighted and summed to obtain the state influence of the enriched device. S400. Matching analysis of various enrichment operation modes is performed based on the predicted results of target microbial biomass after operation and the influence of the state of the enrichment equipment. Includes the following specific content: The impact of the corresponding enrichment equipment status is multiplied by the impact coefficient of the enrichment equipment anomaly on microbial biomass to obtain the biomass impact anomaly. The difference between the value and the biomass impact anomaly is multiplied by the predicted target microbial biomass after the enrichment operation mode to obtain the revised target microbial biomass. The absolute value of the difference between the revised target microbial biomass and the required target microbial biomass is obtained and its reciprocal is calculated to obtain the matching result of the corresponding enrichment operation mode. S500: Select an enrichment operation mode through matching analysis of various enrichment operation modes and perform enrichment operation. Includes the following specific content: The state impact of the enrichment device is compared with the corresponding state impact threshold. Enrichment operations with state impact less than or equal to the corresponding state impact threshold are selected as pre-selected operations. The matching results of the corresponding enrichment operation modes are sorted in descending order, and the matching result of the corresponding enrichment operation mode with the largest value in the predicted operations is selected as the enrichment operation mode.

2. The method for controlling the enrichment of airborne microorganisms based on sample analysis according to claim 1, characterized in that, Step S100 includes the following specific contents: A set amount of air samples were collected at the corresponding collection locations using sampling equipment. Species identification was performed using qPCR and nanopore sequencing technologies. The abundance of the target microorganism in the collected samples was obtained. Other microorganisms were sequenced, and species were annotated based on a species annotation database. The results were stored by phylum, genus, and species. The raw data were converted into microbial concentrations per unit volume. The competition coefficient between the target microorganism and other microorganisms was obtained by looking up the microbial competition table. The operation status of each enrichment operation mode at each time point was obtained. At the same time, the equipment parameters were obtained and matched with the enrichment operation time points.

3. The method for controlling the enrichment of airborne microorganisms based on sample analysis according to claim 1, characterized in that, The target microbial biomass prediction after the operation in S200 includes the following specific steps: The model acquires the operational status of historical enrichment operation modes at each time point, the abundance of target microorganisms, the abundance of other microorganisms, and the competitive relationships among microorganisms. The competitive relationships include competition coefficients and co-existence coefficients. A hybrid neural network model is constructed with the operational status of enrichment operation modes at each time point, the abundance of target microorganisms, the abundance of other microorganisms, and the competitive relationships among microorganisms as inputs, and the target microorganism biomass prediction value after the enrichment operation is completed as output. The operation status at each time step of various optional enrichment operation modes, the abundance of target microorganisms, the abundance of other microorganisms, and the competitive relationships between microorganisms are obtained and imported into the constructed hybrid neural network model, which outputs the target microbial biomass after the operation of various optional enrichment operation modes.

4. An airborne microbial enrichment operation control system based on sample analysis, used to implement the airborne microbial enrichment operation control method based on sample analysis as described in any one of claims 1-3, characterized in that, Specifically, it includes: The data acquisition module collects air samples through sampling equipment and identifies the types of microorganisms in the air through the microbial identification module, obtaining the abundance of target microorganisms and the abundance of other microorganisms, while also acquiring the operation status of various enrichment operation modes at various times. The biomass prediction module predicts the biomass of the target microorganism after the operation by considering the operation status at each time point in the enrichment operation mode, the abundance of the target microorganism, the abundance of other microorganisms, and the competitive relationship between microorganisms. The state impact analysis module analyzes the state impact of enrichment operations on the enrichment equipment by considering the operational status at various times and the operating status of the enrichment equipment. The matching analysis module performs matching analysis on various enrichment operation modes based on the predicted biomass of the target microorganisms after the operation and the influence of the state of the enrichment equipment. The enrichment operation selection module selects an enrichment operation mode for enrichment operation through matching analysis of various enrichment operation modes.

5. An electronic device, comprising: A processor and a memory, wherein the memory stores a computer program for the processor to call; characterized in that the processor executes the airborne microbial enrichment operation control method based on sample analysis as described in any one of claims 1-3 by calling the computer program stored in the memory.

Images