Environmental Monitoring Method and System for Microbial Decomposition of Odorous Gases

Abstract

The present application provides an environmental monitoring method and system for microbial decomposition of odor gases, which relates to the field of automation control technology, and includes: obtaining the threshold ranges of the decomposition effect and decomposition efficiency of a microbial decomposition odor device, which are defined as double-constraint objectives; constructing a quality monitoring database, and performing full-link environmental quality feature extraction to obtain a key quality monitoring feature set; building a microbial decomposition environment prediction network library, inputting the key quality monitoring feature set, and outputting the predicted quality prediction trend of the microbial decomposition environment; establishing a mapping relationship between the quality prediction trend and the key features, calculating the risk contribution degrees of the key features at each process node, and generating a first optimization instruction; and optimizing the quality of the microbial decomposition environment based on the first optimization instruction. The present application realizes the technical effects of automatically and precisely controlling the microbial decomposition environment by monitoring and optimizing the decomposition environment parameters in real time.

Description

Technical Field

[0001] This application relates to the field of automation control technology, and particularly to an environmental monitoring method and system for microbial decomposition of odor gases. Background Art

[0002] The device for microbial decomposition of odor gases is specifically used to treat odor-containing gases. It uses the metabolic reactions of microorganisms to neutralize and decompose specific substances in the odor gases to achieve the purpose of gas purification. Since microorganisms have the unique metabolic function of converting harmful or odor-producing components in the odor gases into harmless substances, this device provides an effective way to solve the problem of odor gases and is of great significance in improving air quality and reducing odor pollution.

[0003] Currently, the process of microbial decomposition of odor gases is easily restricted by various environmental factors, such as the quantity and activity of microorganisms themselves, and decomposition environmental factors such as temperature, humidity, and pH value. Compared with other advanced environmental protection technologies, the degree of intelligence of the device for microbial decomposition of odor gases is relatively low, and its automated control system has poor real-time performance and is difficult to accurately measure and control numerous influencing factors. This makes it difficult to ensure both the effect and efficiency of microbial decomposition of odor gases during actual operation. This imbalance may lead to serious consequences, and even the gas emissions may not meet the environmental protection standards, which is an urgent problem to be solved by the device for microbial decomposition of odor gases. Summary of the Invention

[0004] This application provides an environmental monitoring method and system for microbial decomposition of odor gases, which solves the technical problem that the prior art, due to its relatively low degree of intelligence, cannot cope with the environment of microbial decomposition of odor gases restricted by various factors and is difficult to ensure both the effect and efficiency during microbial decomposition of odor gases. The method provided by this application aims at the effect and efficiency of microbial decomposition of odor gases, and monitors and optimizes the decomposition environmental parameters in real time, achieving the technical effects of automating and precisely controlling the decomposition environment.

[0005] In view of the above problems, this application provides an environmental monitoring method for microbial decomposition of odor gases. The method includes:

[0006] Obtain the threshold ranges of the decomposition effect and decomposition efficiency of the device for microbial decomposition of odor gases, which are defined as double-constraint objectives. The decomposition effect is the direct basis for meeting the emission standards, and the decomposition efficiency is the instantaneous metabolic capacity of microorganisms to decompose odor gases;

[0007] Collect multi-dimensional monitoring data of the device for microbial decomposition of odor gases through an environmental monitoring sensor group, including the inlet concentration and inlet flow rate of odor gases, liquid flow rate, temperature, humidity, dissolved oxygen concentration, pH value of the microbial reaction unit, and the residual concentration of odor gases, and construct a quality monitoring database for the microbial decomposition environment;

[0008] Extract the quality characteristics of the full-link microbial decomposition environment based on the quality monitoring database to obtain the key feature set of the quality monitoring of the microbial decomposition environment;

[0009] Build a prediction network library for the microbial decomposition environment, input the key feature set of quality monitoring, and output the predicted quality prediction trend of the microbial decomposition environment;

[0010] Traverse the attribution table of process nodes - key feature sets of quality monitoring for the quality prediction trend, establish a mapping relationship with key quality features, calculate the risk contribution degree of key features on each process node, sort the risk contribution degrees by priority, and generate the first optimization instruction. Here, the attribution table of process nodes - key feature sets of quality monitoring is used to represent the key features corresponding to each process node;

[0011] Optimize the quality of the microbial decomposition environment based on the first optimization instruction.

[0012] This application also provides an environmental monitoring system for microbial decomposition of odor gases. The system includes:

[0013] A dual-constraint module. The dual-constraint module is used to obtain the threshold ranges of the decomposition effect and decomposition efficiency of the microbial decomposition odor device, which are defined as dual-constraint objectives. The decomposition effect is the direct basis for meeting the emission standards, and the decomposition efficiency is the instantaneous metabolic capacity of the microbial decomposition of odor gases;

[0014] A quality monitoring database module. The quality monitoring database module is used to collect multi-dimensional monitoring data of the microbial decomposition odor device through an environmental monitoring sensor group, including the inlet concentration of odor gases, inlet flow rate, liquid flow rate, temperature, humidity, dissolved oxygen concentration, pH value of the microbial reaction unit, and the residual concentration of odor gases, and construct a quality monitoring database for the microbial decomposition environment;

[0015] A key feature set module for quality monitoring. The multi-dimensional feature set module for quality monitoring is used to extract the quality characteristics of the full-link microbial decomposition environment based on the quality monitoring database to obtain the key feature set of the quality monitoring of the microbial decomposition environment;

[0016] An environmental quality prediction trend module. The environmental quality prediction trend module is used to build a prediction network library for the microbial decomposition environment, input the key feature set of quality monitoring, and output the predicted quality prediction trend of the microbial decomposition environment;

[0017] The first optimization instruction module is used to traverse the attribution table of the process node-quality monitoring key feature set for the quality prediction trend, establish a mapping relationship with the key quality features, calculate the risk contribution degree of the key features on each process node, sort the risk contribution degrees by priority, and generate the first optimization instruction. The attribution table of the process node-quality monitoring key feature set is used to characterize the key features corresponding to each process node.

[0018] The decomposition environment optimization module is used to optimize the quality of the microbial decomposition environment based on the first optimization instruction.

[0019] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0020] By setting dual constraint objectives in this application, it realizes the transformation from single-object passive response to dual-object active optimization. By real-time monitoring and optimizing the parameters of the microbial decomposition environment, it ensures compliance of the emission concentration and maximizes the decomposition efficiency, achieving a win-win situation of safety and benefit. It changes from experience-driven to data-driven, improves the scientificity and reliability of the system, ensures the best operation of the microbial odor decomposition device under different working conditions, improves the accuracy, adaptability and robustness of system control, effectively improves the decomposition efficiency of odor gases, and at the same time ensures the effect of the discharged gas after decomposition. Description of the Drawings

[0021] Figure 1 It is a schematic flow chart of the environmental monitoring method for microbial decomposition of odor gases provided by an embodiment of this application.

[0022] Figure 2 It is a schematic structural diagram of the environmental monitoring system for microbial decomposition of odor gases provided by an embodiment of this application.

[0023] Description of the reference numerals: Dual constraint module 10, Quality monitoring database module 20, Quality monitoring key feature set module 30, Environmental quality prediction trend module 40, First optimization instruction module 50, Decomposition environment optimization module 60. Detailed Embodiments

[0024] The above description is only an overview of the technical solution of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the description. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the following specifically gives the detailed embodiments of this application.

[0025] To make the objectives, technical solutions, and advantages of this application clearer, the following will further describe this application in detail with reference to the accompanying drawings. The described embodiments should not be regarded as limitations of this application. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of this application.

[0026] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with each other without conflict. The terms "first / second" merely distinguish similar objects and do not represent a specific order for the objects. The terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, platform, product, or server that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application.

[0027] The embodiments of this application provide an environmental monitoring system for microbial decomposition of odor gases, as Figure 1 shown. The method includes:

[0028] Obtain the threshold ranges of the decomposition effect and decomposition efficiency of the microbial decomposition of odor device, which are defined as double-constraint objectives. The decomposition effect is the direct basis for meeting the emission standards, and the decomposition efficiency is the instantaneous metabolic ability of the microbial decomposition of odor gases.

[0029] In one embodiment, the microbial decomposition of odor device uses the metabolic action of microorganisms in the microbial reaction unit to convert odor gases carried by substances such as sulfur-containing and nitrogen-containing compounds into harmless or low-toxicity gases, thereby effectively removing odors and optimizing air quality. The decomposition effect of the microbial decomposition of odor gases is the direct basis for meeting the emission standards, that is, the residual concentration of odor gases monitored at the exhaust port of the device, which is the direct basis for ensuring the final purification ability of the system and meeting the emission standards; the microbial decomposition efficiency (where η is the decomposition efficiency, C in is the inlet concentration of odor gases, C outThe residual concentration of odor gas (), which directly reflects the instantaneous metabolic capacity of the microbial community, is the core index of the process performance. The decomposition effect and efficiency of the microbial decomposition of odor gas convert the complex biochemical reaction process into an intuitively operable two-dimensional control parameter space. The threshold range of the decomposition effect is a parameter space determined according to the emission standard, which is an insurmountable hard constraint. The threshold range of the decomposition efficiency is a parameter space clarified through long-term monitoring of the microbial odor decomposition device, which is a flexible optimization goal. The decomposition effect and efficiency are both the constraint conditions for dynamically adjusting parameters and the optimization direction for the decomposition environment regulation of the microbial decomposition of odor gas, that is, the dual optimization balance of the decomposition effect and efficiency is the optimization direction. By monitoring the decomposition environment in real time and dynamically adjusting relevant parameters according to the monitoring results, it can be promoted to develop in the direction of the dual optimization balance of the decomposition effect and efficiency, which can not only ensure that the residual concentration of odor gas meets the emission standard and achieve good decomposition effect, but also systematically improve the decomposition efficiency and achieve the dual goals of the combination of hardness and softness of the decomposition effect and efficiency.

[0030] Collect multi-dimensional monitoring data of the microbial odor decomposition device through the environmental monitoring sensor group, including the inlet concentration of odor gas, inlet flow rate, liquid flow rate, temperature, humidity, dissolved oxygen concentration, pH value of the microbial reaction unit, and the residual concentration of odor gas, and construct a quality monitoring database for the microbial decomposition environment.

[0031] In one embodiment, an environmental monitoring sensor group is arranged on the odor removal device to monitor the entire-link working environment of the process path in the odor decomposition device in real time, so as to ensure that the odor gas decomposition efficiency remains stable and complies with relevant regulations. The quality monitoring database is a database that stores multi-dimensional monitoring data with time series collected from the same odor decomposition device, and is used to analyze and extract key features of the monitored entire-link working environment. These monitoring data include key parameters such as the odor gas concentration at the inlet end, the inlet flow rate, the liquid flow rate, the temperature, humidity, dissolved oxygen concentration, and pH value of the microbial reaction unit, and the residual odor gas concentration at the outlet end. By obtaining these monitoring data, the entire-link working environment of the process path in the odor decomposition device can be understood in real time. For example, the odor gas concentration at the inlet end is the starting point of the entire-link monitoring and an important indicator for measuring the pollution degree entering the odor decomposition device. By comparing it with the residual odor gas concentration at the outlet end, the treatment effect of the odor decomposition device can be intuitively evaluated; the inlet flow rate directly affects the residence time of the odor in the filter bed. An overly high concentration of odor may inhibit the metabolic activity of microorganisms. Monitoring the flow rate can dynamically adjust the load to prevent the inactivation of microorganisms due to overload; the liquid flow rate. The water washing unit is usually set after the inlet end to remove pollutants such as particulate matter and volatile organic compounds (VOCs) in the gas, and prevent them from directly entering the microbial decomposition unit to cause biofilm blockage or toxicity inhibition. An overly large flow rate will shorten the contact cycle between microorganisms and pollutants, resulting in insufficient degradation; an overly small flow rate may cause local anaerobic conditions or nutrient deficiencies; the microbial reaction unit is the core treatment part for microorganisms to treat odor gases, including a biological filler layer and a microbial flora. The biological filler layer fixes the microorganisms and forms a biofilm, and the microbial flora adheres to specific microorganisms (such as nitrifying bacteria, sulfur-oxidizing bacteria, etc.) on the surface of the filler, which is a key point of the entire-link monitoring. Its temperature is one of the key environmental factors affecting the metabolic activities of microorganisms. A sudden fluctuation in temperature may imply problems with the insulation system of the device or abnormal heat generation or absorption during the microbial metabolic process; its humidity helps maintain the activity and normal physiological functions of microbial cells, affects the diffusion speed and mode of odor gases in the microbial reaction unit, and affects the overall treatment effect; its dissolved oxygen concentration can reflect the respiratory state of microorganisms. In the microbial metabolic process dominated by aerobic respiration, a stable dissolved oxygen concentration means normal microbial respiration and the ability to continuously and effectively decompose odor gases; its pH value. A suitable pH value helps maintain the microbial community structure in the microbial reaction unit and can efficiently catalyze metabolic reactions; the residual odor gas concentration at the outlet end is the end of the entire-link monitoring and a direct indicator for testing the treatment effect of the odor decomposition device. Through the quality monitoring database, multi-dimensional monitoring data can be obtained, providing a comprehensive data basis for subsequent data analysis and model construction, and improving the accuracy and reliability of subsequent data analysis.

[0032] Furthermore, the present application provides a quality monitoring database for constructing a microbial decomposition environment, including:

[0033] Identifying outliers and performing data cleaning on the inlet concentration of odor gas, inlet flow rate, liquid flow rate, temperature, humidity, dissolved oxygen concentration, pH value of the microbial reaction unit, and the residual concentration of odor gas, to obtain available multi-dimensional monitoring data;

[0034] Establishing a node mapping relationship between the multi-dimensional monitoring data and the process nodes of the microbial decomposition of odor gas;

[0035] Obtaining the time series difference of the node states of the microbial decomposition of odor gas process, corresponding the multi-dimensional monitoring data based on the time series difference of the node states, and constructing a quality monitoring database.

[0036] In one embodiment, the residual concentration and decomposition efficiency of the odor gas in the microbial odor decomposition device are affected by multi-parameter coupling. Multi-dimensional key data collection is the prerequisite. The edge processing unit processes the multi-dimensional monitoring data collected on-site, transmits the available multi-dimensional monitoring data after outlier identification and data cleaning to the intelligent control system, establishes a corresponding relationship between the available multi-dimensional monitoring data and each node in the odor decomposition gas process. For each process node, the monitoring parameters corresponding to the node can be determined, and the causal relationship chain affected by the parameters can be clarified. For example, the odor gas flow rate at the inlet end is related to the residence time of the odor gas in the odor decomposition device, which affects the reaction time between the odor gas and the microbial reaction unit. A mapping relationship is established between the odor gas flow rate at the inlet end and the inlet end node - load shock; the temperature, humidity, dissolved oxygen concentration, pH value, and microbial ATP concentration in the microbial reaction unit. The microbial reaction unit includes a first reaction zone, a second reaction zone, and a third reaction zone. The temperature, humidity, dissolved oxygen concentration, pH value, and microbial ATP concentration in each reaction zone directly affect the activity, community structure, metabolic function, etc. of the microorganisms in the reaction zone. A mapping relationship is established between the temperature, humidity, dissolved oxygen concentration, pH value, and microbial ATP concentration in each reaction zone and the corresponding reaction zone label - reaction efficiency respectively. By traversing each operation node of the odor decomposition device and determining the monitoring parameters corresponding to each node, multiple node mapping relationships are established. Since the operating speeds or response times of different nodes are different, there are differences in the time sequence of the state data of different nodes, that is, the node state time difference. According to this node state time difference, a time alignment operation is performed on the available multi-dimensional monitoring data to unify the timestamps of different nodes and different monitoring data, ensuring the consistency of all data in terms of time. For example, there is a gas residence time lag effect in microbial degradation, and the time difference needs to be corrected to achieve data synchronization. The change in the inlet concentration affects the outlet concentration after 2 - 3 times the empty bed residence time (EBRT). Then, when constructing the local monitoring database, the time difference of the residence time needs to be taken into account, and the gas flow rate data collected when the odor gas enters the odor decomposition gas device and the odor gas residual concentration data collected after the residence time are arranged in the correct time sequence. Select a suitable method, such as using a transfer function model or applying dynamic time warping for time alignment, so that the data in the constructed local monitoring database is coherent and consistent in terms of time. This makes the subsequent analysis of the data more accurate and reliable, avoiding data misreading or incorrect analysis caused by time asynchronization, and providing a guarantee for accurately mining useful information in the data.

[0037] Extract the quality monitoring key feature set of the full-link microbial decomposition environment according to the quality monitoring database.

[0038] Furthermore, the obtained quality monitoring key feature set includes:

[0039] Obtain the inlet concentration and residual concentration of odor gas in the quality monitoring database, obtain the current decomposition effect and current decomposition efficiency, evaluate the current decomposition environment of microorganisms through the current decomposition effect and current decomposition efficiency, and obtain the comprehensive performance and dominant mode of the current decomposition environment of microorganisms. The comprehensive performance includes high-efficiency area, medium-efficiency area and low-efficiency area, and the dominant mode includes efficiency-dominated, effect-dominated and balanced area. The decomposition effect is the residual concentration of odor gas, and the decomposition efficiency is the difference between the inlet concentration and residual concentration of odor gas divided by the inlet concentration of odor gas;

[0040] According to the comprehensive performance and dominant mode of the current decomposition environment of microorganisms, use the expert experience method to assign initial weights to the inlet flow rate, liquid flow rate, temperature, humidity, dissolved oxygen concentration, and pH value of the microbial reaction unit;

[0041] Perform a correlation analysis on the inlet flow rate, liquid flow rate, temperature, humidity, dissolved oxygen concentration, and pH value in the quality monitoring database and the decomposition effect, obtain the correlation coefficients of each monitoring data, and adjust the initial weights according to the correlation coefficients to obtain the weights of each monitoring data after adjustment;

[0042] Input the inlet flow rate, liquid flow rate, temperature, humidity, dissolved oxygen concentration, and pH value in the quality monitoring database into the decomposition effect prediction model to obtain the importance scores of each monitoring data for the residual concentration of odor gas. Among them, the decomposition effect prediction model is constructed based on the random forest model, and the optimal number of trees and splitting rules are determined through cross-validation. The model is trained to predict the residual concentration of odor gas, and the initial importance scores of each monitoring data are output synchronously. Multiply the initial importance scores of each monitoring data output by the random forest model and the weights of each monitoring data after adjustment and normalize them to generate importance scores;

[0043] Preset a score threshold, extract the monitoring data with importance scores greater than the score threshold as key monitoring data, and extract the characteristics of the key monitoring data to obtain the quality monitoring key feature set.

[0044] In one embodiment, a matrix is constructed based on the decomposition efficiency and decomposition effect to obtain a matrix of comprehensive performance levels and dominant mode combinations. The first vertical column of the matrix is the comprehensive performance level, including the high-efficiency area, medium-efficiency area, and low-efficiency area. The second vertical column is the dominant mode, including efficiency-dominated, effect-dominated, and balanced areas. The third vertical column is the threshold interval of the comprehensive performance level. The fourth vertical column is the boundary of the dominant mode interval. The fifth vertical column is the description of the microbial decomposition environment state for any combination of comprehensive performance level and dominant mode. According to the current decomposition effect and decomposition efficiency, the comprehensive performance and dominant mode that match the current decomposition environment of the microorganism are found in the matrix of comprehensive performance and dominant mode combinations. The current decomposition environment of the microorganism is in the medium-efficiency area of comprehensive performance and the balanced area of the dominant mode. Through the expert experience method, based on the current decomposition environment of the microorganism in the medium-efficiency area of comprehensive performance and the balanced area of the dominant mode, the original weights are assigned to the intake air flow, liquid flow, temperature, humidity, dissolved oxygen concentration, and pH value in the quality monitoring database. The correlation strength between each monitoring data in the quality monitoring database and the decomposition effect is quantified, such as by the Pearson correlation coefficient method. The correlation coefficient adjusts the initial weight. The higher the absolute value of the correlation coefficient, the more significantly the weight is enhanced. The smaller the absolute value of the correlation coefficient, the lower the weight. The adjustment formula is as follows: adjusted weight = initial weight × (1 + |r|), where r is the correlation coefficient. The subjective weight is corrected through data-driven methods to avoid expert experience bias. The intake air flow, liquid flow, temperature, humidity, dissolved oxygen concentration, and pH value are input into the decomposition effect prediction model to obtain the importance score of each monitoring data for predicting the decomposition effect. The contribution of each monitoring data to predicting the decomposition effect can be quantified by calculating the importance score through the model. A decomposition effect prediction model is constructed by integrating monitoring data such as intake air flow, liquid flow, temperature, humidity, dissolved oxygen concentration, and pH value as the input feature set. These features cover the environmental factors and material flow factors during the operation of the microbial reaction unit and have a potential association with predicting the residual concentration of odor gas. The input features are standardized using the Z-score standardization method. A random forest regression model is constructed, and the hyperparameters of the model are set, such as the number of trees and the number of features considered at each split. The number of trees affects the complexity and generalization ability of the model, while the number of features considered at each split controls the randomness and search space of the model when constructing decision trees. The standardized input feature set and the target variable (residual concentration of odor gas) are input into the model for training. The initial importance score of each feature is calculated by the reduction in the mean squared error. For example, when constructing each decision tree, if a certain feature is used to split a node, the difference in the mean squared error before and after the split is calculated, and then the differences in the mean squared error of this feature in all decision trees are averaged to obtain the initial importance score of this feature. This score reflects the relative importance degree of each feature in the model for predicting the residual concentration of odor gas.Multiply the initial importance score output by the model with the adjusted weight item by item, normalize the multiplied result, and obtain the importance score of each monitoring data, as follows:

[0045]

[0046] Here, i represents the index of the currently calculated monitoring data. When there are multiple monitoring data such as intake flow, liquid flow, and temperature, i = 1 represents the intake flow monitoring data, i = 2 represents the liquid flow, and so on. j represents the summation index, which traverses all monitoring data from 1 to n. When calculating the final score i, it is necessary to sum the product of the initial importance scores of all monitoring data (from the 1st to the nth) and the adjusted weights. j is the index variable used in this summation process; n represents the total number of monitoring data. The importance score reflects the actual contribution of each monitoring data to the prediction of odor gas residual concentration. It takes into account both the model's internal assessment of feature importance and external weight adjustment factors. Based on the importance score, it can determine which parameters are most critical to controlling the odor gas residual concentration, so that these parameters can be adjusted first to improve the microbial decomposition effect.

[0047] Furthermore, the current decomposition environment of the microorganisms is evaluated through the current decomposition effect and current decomposition efficiency, and the comprehensive performance and dominant mode of the current decomposition environment of the microorganisms are obtained, including:

[0048] A sampling sliding window is preset, and the intake concentration of odorous gas and the residual concentration of odorous gas are obtained within the sampling sliding window to obtain the decomposition efficiency and decomposition effect;

[0049] The decomposition efficiency and decomposition effect are normalized and mapped to the polar coordinate system. The radial distance of the polar coordinate system represents the comprehensive performance strength, and the polar angle represents the balance between the decomposition efficiency and the decomposition effect. The formula is as follows:

[0050] Normalization processing:

[0051]

[0052] Among them, η norm is the normalized decomposition efficiency, η (t) is the decomposition efficiency calculated at time t, η min is the minimum value in the parameter space of decomposition efficiency, η max is the maximum value in the parameter space of decomposition efficiency,

[0053] E norm is the decomposition effect after normalization, is the decomposition effect index, that is, the reciprocal of the residual concentration of odorous gas, ε is the minimum constant, E minis the minimum value in the parameter space of the decomposition effect, E max is the maximum value in the parameter space of the decomposition effect;

[0054] The polar coordinate transformation formula is as follows:

[0055]

[0056] where r(t) is the radial distance at time t, η norm is the normalized decomposition efficiency, E norm is the normalized decomposition effect, θ(t) is the polar angle at time t, θ ∈ [-π, π], t = 1, 2, 3..., T, t is each sampling time within the sampling sliding window, and all sampling times are the data of the sampling sliding window;

[0057] Analyze the density distribution of the radial distance through the histogram method to determine the grade threshold interval of the comprehensive performance. The grades of the comprehensive performance include high efficiency, medium efficiency, and low efficiency;

[0058] Divide the polar angle into N fan-shaped areas through polar coordinate transformation and the clustering method to determine the interval boundaries of the dominant mode. The multi-dimensional dominant mode includes the decomposition efficiency dominant area, the effect dominant area, and the equilibrium area;

[0059] Perform a Cartesian combination of the grade threshold interval of the comprehensive performance and the interval boundaries of the dominant mode to generate a matrix of the combination of the comprehensive performance and the dominant mode;

[0060] Calculate the radial distance and polar angle corresponding to the current decomposition effect and the current decomposition efficiency, and traverse the matrix of the combination of the comprehensive performance and the dominant mode to obtain the comprehensive performance and the dominant mode of the current decomposition environment of the microorganism.

[0061] In one embodiment, during the microbial decomposition process, there may be a non-linear correlation between the decomposition efficiency and the decomposition effect: 1) When the inlet concentration of the odor gas is fixed: the decomposition efficiency and the decomposition effect are strongly negatively correlated, and the data is distributed along the diagonal in the rectangular coordinate system, making it difficult for traditional methods to effectively divide the quadrants; 2) When the inlet concentration of the odor gas is changed, the two variables may show a complex relationship, increasing the analysis difficulty. To address the problems brought by the dimensional correlation, decouple the correlation through polar coordinate transformation. The formula is as follows:

[0062] Normalization processing:

[0063]

[0064] where η norm is the normalized decomposition efficiency, η (t) is the decomposition efficiency calculated at time t, η min is the minimum value in the parameter space of the decomposition efficiency, η maxis the maximum value in the parameter space of decomposition efficiency, E norm is the decomposition effect after normalization, is the decomposition effect index at time t, that is, the reciprocal of the residual concentration of odorous gas, ε is the minimum constant, E min is the minimum value in the parameter space of the decomposition effect, E max is the maximum value in the parameter space of the decomposition effect;

[0065] The polar coordinate conversion formula is as follows:

[0066]

[0067] Among them, r(t) is the radial distance at time t, η norm is the normalized decomposition efficiency, E norm is the decomposition effect after normalization, θ(t) is the polar angle at time t, θ∈[-π,π], t=1,2,3...,T, t is each sampling moment in the sampling sliding window, and all sampling moments are sampling sliding window data. The sampling sliding window is preset, and the window size of the sliding window = the decomposition cycle of the microbial odor removal device divided by the sampling interval. The sampling interval is based on the high-frequency step size, and the step size is 1 / 3 of the window size. The normalization process uniformly scales the decomposition efficiency and decomposition results to the [0,1] interval, which is convenient for multi-dimensional joint analysis. The extreme value of the parameter space makes the model adapt to data fluctuations under different working conditions, and C is avoided by ε. outDivide-by-zero error when it is equal to 0, enhancing the robustness of the algorithm. The radial distance r(t) comprehensively characterizes the performance, weakening the dominance of a single dimension. It is the geometric synthesis of the normalized decomposition efficiency and the normalized decomposition effect. The larger the value of r(t), the higher the decomposition efficiency and the lower the residual concentration of the system, that is, the overall performance is excellent. The smaller the value of r(t), the lower the decomposition efficiency or the higher the residual concentration, and process adjustment is required; the polar angle θ(t) captures the proportional relationship between efficiency and effect. Different θ values correspond to different efficiency-effect dominance modes. A larger θ indicates that the effect is prioritized. For example, when the angle is large: the decomposition effect is dominant (the residual concentration is extremely low, but the efficiency may not reach the optimum). When the angle is small: the decomposition efficiency is dominant (high efficiency, but the residual concentration may be high). When the angle is moderate: the decomposition efficiency and the decomposition effect are balanced. Use the histogram method or the kernel density estimation method to analyze the density distribution of the radial distance, and set the threshold boundaries for the high-efficiency, medium-efficiency, and low-efficiency regions. For example, the high-efficiency region is 0.8 ≤ r ≤ 1.2, the medium-efficiency region is 0.5 ≤ r < 0.8, and the low-efficiency region is r < 0.5. Preset the number of clusters N. N = 3 corresponds to the efficiency-dominant, effect-dominant, and balanced regions. Establish its corresponding relationship with the polar angle. A larger angle corresponds to the decomposition effect being dominant, a moderate angle corresponds to the balanced region, and a smaller angle corresponds to the decomposition efficiency being dominant. Map the range of the polar angle to the two-dimensional coordinates on the unit circle, x = cos(θ) and y = sin(θ) to achieve the conversion, convert the circular data of the polar angle into plane coordinates, and calculate the center point (x c , y c ) of each cluster according to the preset number of clusters for the converted plane coordinates (x, y), and calculate its polar angle Then adjust the calculated polar angle to the interval [-π, π]. Sort the clustering center angles, and take the median of adjacent center angles as the boundary. For example, if there are 3 clusters, the clustering center angles are -30°, 45°, and 120° respectively. After sorting, they are still -30°, 45°, and 120°. The median of the boundaries is calculated as (-30° + 45°) / 2 = 7.5° and (45° + 120°) / 2 = 82.5°. The finally determined fan-shaped regions are [-180°, 7.5°), [7.5°, 82.5°), and [82.5°, 180°]. Use the Cartesian product combination to cross-combine the comprehensive performance levels (high efficiency, medium efficiency, low efficiency) and the dominance modes (efficiency-dominant, effect-dominant, balanced) to form a comprehensive performance level-dominance mode matrix. Example matrix:

[0068]

[0069] Build a microbial decomposition environment prediction network library, input the key feature set of quality monitoring, and output the quality prediction trend of the predicted microbial decomposition environment.

[0070] In one embodiment, a model is established to predict the quality prediction trend of the microbial decomposition environment. The key feature set of quality monitoring is input into the prediction network library of the working environment for decomposing odor gas to obtain the prediction trend of the working environment for decomposing odor gas by microorganisms. The prediction provides a quantitative description of the future state. Based on preset rules and real-time target weights, the predicted value is converted into specific action instructions to solve the problem of "what to do after prediction".

[0071] Further, a prediction network library for the environment of decomposing odor gas is built, including:

[0072] Mine and obtain the monitoring database for decomposing odor gas, and extract the key feature data of the full-link monitoring;

[0073] Classify and label the key feature data of the full-link monitoring according to the types of odor gas to obtain a classified data set for monitoring the environment of decomposing odor gas;

[0074] Respectively perform feature extraction on the classified data set for monitoring the environment of decomposing odor gas to obtain a classified feature set for monitoring the environment of decomposing odor gas;

[0075] Respectively perform training on the quality trend prediction of the working environment for the classified feature set of monitoring the environment of decomposing odor gas to obtain a multi-dimensional decomposition environment trend prediction branch network set;

[0076] Classify and concatenate and fuse the multi-dimensional decomposition environment trend prediction branch network set according to the types of odor gas to generate multiple prediction network sets for the decomposition environment of different odor gas types;

[0077] Perform identification and integration on the prediction network set for the environment of multiple odor gas types to build a prediction network library for the working environment of decomposing odor gas.

[0078] In one embodiment, the full-link monitoring data of the excavation is mined and key features are extracted. The key features may include temperature, pH, dissolved oxygen, etc., which is consistent with the previous acquisition. The odor gases may have different components, such as H2S, NH3, VOCs, etc. The decomposition mechanisms and required environmental parameters of different gases are different. Therefore, classification processing can optimize the model specifically. Feature extraction is performed on each classification data set to capture the dynamic changes during the decomposition of different gases, and the environmental trend prediction branch network is trained. The branch network here should be a prediction model for a specific gas type. For example, it predicts the trends of environmental parameters in the future period, such as the changes in temperature, pH, etc. These trends may affect the decomposition efficiency and compliance. Each branch network focuses on one gas type, which may improve the prediction accuracy. The neural network model is trained respectively through the classification features of each odor gas and the corresponding data trends until the model training is completed to obtain a set of trend prediction branch networks. The multi-dimensional environmental trend prediction branch network set is used to predict the future environmental parameter trends based on the known environmental data. The multi-dimensional environmental trend prediction branch network set is classified and concatenated according to the odor gas type, that is, according to the environmental characteristics corresponding to the odor gas type, multiple multi-dimensional environmental trend predictions are concatenated to generate a prediction network set for the working environment of microbial decomposition of odor gases. The identification integration of the working environment prediction network set is to identify the corresponding odor gas category for each odor gas type environmental prediction network. The branch networks are concatenated and fused according to the type. Concatenation means integrating the prediction networks of different gas types to form a comprehensive prediction system that can handle multiple gas situations simultaneously, integrating the network set, and building a prediction network library. The final network library can flexibly call the prediction models of different gases to adapt to the complex application scenario environment.

[0079] Traverse the process node - quality monitoring key feature set attribution table of the quality prediction trend, establish a mapping relationship with the key quality features, calculate the risk contribution degree of the key features on each process node, sort the risk contribution degrees in priority, and generate the first optimization instruction. The process node - quality monitoring key feature set attribution table is used to characterize the key features corresponding to each process node.

[0080] In one embodiment, traversing the attribution table of the process node-quality monitoring key feature set for the quality prediction trend and establishing a mapping relationship helps to deeply understand the internal connection between the quality prediction trend and the key quality features in each process node. If the quality prediction trend indicates that the product quality may decline, through this mapping relationship, it can be determined which key quality features in which process nodes may be the reasons for this trend. This mapping relationship can accurately locate the process links where the key factors that may affect quality are located. Calculating the risk contribution degree of the key features on each process node quantifies the degree to which each key feature affects quality. Different key features may have different degrees of influence on the final quality result. By calculating the risk contribution degree, the contribution size of each key feature to the quality risk in the entire process can be clarified. This helps to reasonably allocate resources in the quality control and improvement process. If the risk contribution degree of a certain key feature is very high, then when resources are limited, this key feature can be preferentially improved or controlled to improve the overall quality. Prioritizing the risk contribution degrees can determine the order of improvement of the key features of each process node. When facing multiple key features that need to be improved, processing them in the order of priority can more efficiently improve the overall quality. Generating the first optimization instruction provides specific directions and operation guides for actual process improvement. This instruction can clarify which key features of which process nodes the automatic control system should adjust and how.

[0081] Further, an attribution table of the process node-quality monitoring key feature set is established to characterize the key features corresponding to each process node, including:

[0082] Obtain the available multi-dimensional monitoring data and establish a mapping relationship with the process nodes of the microbial decomposition of odor gases, and establish an attribution table of the process nodes and the available multi-dimensional monitoring data;

[0083] Obtain the key monitoring data and the quality monitoring key feature set, extract the attribution table of the process nodes and the key monitoring data from the attribution table of the process nodes and the available multi-dimensional monitoring data according to the key monitoring data, and establish an attribution table of the process node-quality monitoring key feature set according to the corresponding relationship between the key monitoring data and the quality monitoring key feature set.

[0084] In one embodiment, during the process of microbial decomposition of odor gas, multi-dimensional monitoring data reflects the state of process nodes. By establishing such a mapping relationship, the internal connection between process nodes and monitoring data can be better understood. Establishing an attribution table for process nodes and available multi-dimensional monitoring data can systematically organize and record these relationships. This helps to quickly query and determine the range of monitoring data corresponding to specific process nodes in subsequent analysis and operations, providing a data structure basis for comprehensively understanding the process of microbial decomposition of odor gas. Obtaining key monitoring data and the key feature set of quality monitoring, and then extracting the attribution table of process nodes and key monitoring data from the existing attribution table of process nodes and multi-dimensional monitoring data based on the key monitoring data is to perform data screening and extraction based on the previously established relationships. Establishing an attribution table of process nodes - key feature set of quality monitoring according to the corresponding relationship between key monitoring data and the key feature set of quality monitoring is to further integrate data relationships on the basis of the foregoing steps. This attribution table can characterize the key features corresponding to each process node, providing an important data basis for in-depth analysis of the optimization of the decomposition environment during the process of microbial decomposition of odor gas.

[0085] Furthermore, generating the first optimization instruction includes:

[0086] Decompose the quality prediction trend of the microbial decomposition environment into multi-dimensional independent trend factors, traverse the attribution table of process nodes - key feature set of quality monitoring, and establish a mapping relationship with the key features;

[0087] Preset a grading standard, discretize the trends of the multi-dimensional independent trend factors, and generate an intensity vector of the multi-dimensional trend factors;

[0088] Pre-construct a discrete contribution degree function, and calculate the discrete contribution degree of each key feature;

[0089] Preset an optimization grading scale, perform an optimization level grading on the contribution degrees of each key feature according to the optimization grading scale, and extract the first optimization instruction;

[0090] Based on the first optimization instruction, optimize the parameters of the key features corresponding to the process nodes to optimize the quality of the microbial decomposition environment.

[0091] In one embodiment, the quality prediction trend of the microbial decomposition environment is decomposed into multi-dimensional independent trend factors. By traversing the attribution table of the process node-quality monitoring key feature set, each trend factor is matched and associated with the corresponding key feature. The mapping relationship between the trend factor and the key feature can be determined through statistical analysis. The complex trend is decomposed into independent factors, and the complex environmental quality change trend is decomposed into multiple independent trend factors (such as compliance factor, efficiency factor, environmental factor, etc.), reducing the complexity of the data dimension and facilitating targeted analysis for better analysis and processing. A preset grading standard is selected to choose a threshold division or clustering algorithm to discretize the trend factors and generate an intensity vector. An intensity vector is generated for each trend factor (for example, [0.8, 0.2, 0] represents "high" intensity), reflecting the change intensity of different factors in time or space. A discrete contribution function is pre-constructed to calculate the contribution of each key feature, which refers to evaluating the influence degree of each factor on the overall trend. Finally, the hierarchical grading is optimized to generate multi-level optimization instructions, and the optimal first optimization instruction is extracted. During the optimization process, the system can be comprehensively monitored and evaluated to detect potential fault hazards in advance and take timely measures for repair or adjustment, avoiding system downtime or a significant decrease in efficiency caused by equipment failures or process anomalies, and improving the operation stability and continuity of the system. Ensuring that the decomposition efficiency of the odor gas remains above the preset threshold can guarantee that the emitted gas meets strict environmental protection standards, reduce environmental pollution, and meet the requirements of increasingly strict environmental protection regulations. In the process of microbial decomposition of odor gas, the full-link process may involve multiple links such as inoculation and cultivation of microorganisms, introduction and export of gas. The first optimization instruction focuses on the most basic and crucial links. By optimizing the key parameters on the full-link process nodes, the first optimization control parameters are obtained, approaching the optimal parameter combination that can meet the decomposition efficiency and decomposition effect, improving the efficiency and effect of optimization.

[0092] The embodiment of the present application provides an environmental monitoring system for microbial decomposition of odor gas, such as Figure 2 shown. The system includes:

[0093] A dual-constraint module 10, which is used to obtain the threshold range of the decomposition effect and decomposition efficiency of the microbial decomposition odor device, defined as the dual-constraint target. The decomposition effect is the direct basis for meeting the emission standard, and the decomposition efficiency is the instantaneous metabolic ability of the microbial decomposition of odor gas;

[0094] A quality monitoring database module 20, which is used to collect multi-dimensional monitoring data of the microbial decomposition odor device through an environmental monitoring sensor group, including the inlet concentration of the odor gas, inlet flow rate, liquid flow rate, temperature, humidity, dissolved oxygen concentration, pH value of the microbial reaction unit, and the residual concentration of the odor gas, and construct a quality monitoring database for the microbial decomposition environment;

[0095] Quality monitoring key feature set module 30. The quality monitoring multi-dimensional feature set module 30 is used to extract the quality characteristics of the full-link microbial decomposition environment based on the quality monitoring database, and obtain the quality monitoring key feature set of the microbial decomposition environment;

[0096] Environmental quality prediction trend module 40. The environmental quality prediction trend module 40 is used to build a prediction network library for the microbial decomposition environment, input the quality monitoring key feature set, and output the quality prediction trend of the predicted microbial decomposition environment;

[0097] The first optimization instruction module 50. The first optimization instruction module 50 is used to traverse the attribution table of the process node - quality monitoring key feature set for the quality prediction trend, establish a mapping relationship with the key quality features, calculate the risk contribution degree of the key features on each process node, sort the risk contribution degrees by priority, and generate the first optimization instruction. Among them, the attribution table of the process node - quality monitoring key feature set is used to represent the key features corresponding to each process node;

[0098] Decomposition environment optimization module 60. The decomposition environment optimization module 60 is used to optimize the quality of the microbial decomposition environment based on the first optimization instruction.

[0099] Overall, this application realizes the transformation from single-object passive response to multi-object active optimization by setting double constraint objectives, achieving a win-win situation for safety and benefits; it changes from experience-driven to data-mechanism fusion-driven, enhancing the scientificity and reliability of the system, ensuring the best operation of the odor decomposition device under different working conditions, improving the accuracy, adaptability and robustness of system control, effectively improving the decomposition efficiency of odor gases, and reducing the emission of odor gases.

[0100] The above description of the disclosed embodiments enables those skilled in the art to implement or use this application. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application will not be limited to the embodiments shown herein, but will be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An environmental monitoring method for microbial decomposition of odorous gases, characterized in that: Methods include: Obtain the threshold ranges of the decomposition effect and decomposition efficiency of the microbial decomposition device, which are defined as dual-constraint objectives. The decomposition effect is the direct basis for meeting emission standards, and the decomposition efficiency is the instantaneous metabolic capacity of microorganisms to decompose odorous gases. The environmental monitoring sensor group collects multi-dimensional monitoring data of the microbial decomposition device, including the odor gas intake concentration, intake flow, liquid flow, temperature, humidity, dissolved oxygen concentration, pH value of the microbial reaction unit, and residual concentration of odor gas, to build a quality monitoring database for the microbial decomposition environment; Extract the quality features of the microbial decomposition environment in the entire chain based on the quality monitoring database to obtain the key feature set for quality monitoring of the microbial decomposition environment; Build a microbial decomposition environment prediction network library, input the key feature set of quality monitoring, and output the predicted quality prediction trend of the microbial decomposition environment; Traverse the quality prediction trend through the attribute table of the process node-quality monitoring key feature set, establish a mapping relationship with the key features, calculate the risk contribution of the key features on each process node, prioritize the risk contributions, and generate a first optimization instruction, wherein the attribute table of the process node-quality monitoring key feature set is used to characterize the key features corresponding to each process node; Based on the first optimization instruction, the quality of the microbial decomposition environment is optimized.

2. The environmental monitoring method for microbial decomposition of odorous gases according to claim 1, characterized in that: Construct a quality monitoring database for microbial decomposition environments, including: Perform outlier identification and data cleaning on the intake concentration, intake flow rate, liquid flow rate, temperature, humidity, dissolved oxygen concentration, pH value of the microbial reaction unit, and residual concentration of odorous gas to obtain usable multi-dimensional monitoring data; Establish node mapping relationship between available multi-dimensional monitoring data and process nodes of microbial decomposition of odorous gas; The node state time series difference of the microbial decomposition process of odorous gas is obtained, and the multi-dimensional monitoring data are time-correlated based on the node state time series difference to build a quality monitoring database.

3. The environmental monitoring method for microbial decomposition of odorous gases according to claim 1, characterized in that: Obtain a set of key characteristics for quality monitoring of microbial decomposition environment, including: Obtaining the intake concentration of odorous gas and the residual concentration of odorous gas from the quality monitoring database, obtaining the current decomposition effect and the current decomposition efficiency, evaluating the current decomposition environment of the microorganisms based on the current decomposition effect and the current decomposition efficiency, and obtaining the comprehensive performance and dominant mode of the current decomposition environment of the microorganisms, wherein the comprehensive performance includes a high-efficiency zone, a medium-efficiency zone, and a low-efficiency zone, and the dominant mode includes an efficiency-dominant zone, an effect-dominant zone, and a balanced zone. The decomposition effect is the residual concentration of the odorous gas, and the decomposition efficiency is the difference between the intake concentration of the odorous gas and the residual concentration of the odorous gas divided by the intake concentration of the odorous gas; According to the comprehensive performance and dominant mode of the current microbial decomposition environment, the expert experience method is used to assign initial weights to the air flow rate, liquid flow rate, temperature, humidity, dissolved oxygen concentration, and pH value of the microbial reaction unit; The air inlet flow rate, liquid flow rate, temperature, humidity, dissolved oxygen concentration, pH value of the microbial reaction unit in the quality monitoring database and the decomposition effect are analyzed to obtain the correlation coefficient of each monitoring data. The initial weight is adjusted according to the correlation coefficient to obtain the adjusted weight of each monitoring data; The air inlet flow rate, liquid flow rate, temperature, humidity, dissolved oxygen concentration, and pH value of the microbial reaction unit in the quality monitoring database are input into the decomposition effect prediction model to obtain the importance score of each monitoring data to the residual concentration of the odorous gas. The decomposition effect prediction model is constructed based on the random forest model. The optimal number of trees and splitting rules are determined through cross-validation. The model is trained to predict the residual concentration of the odorous gas and the initial importance score of each monitoring data is output simultaneously. The initial importance score of each monitoring data output by the random forest model is multiplied by the adjusted weight of each monitoring data and normalized to generate an importance score. A score threshold is preset, and monitoring data with importance scores greater than the score threshold is extracted as key monitoring data. The features of the key monitoring data are extracted to obtain a key feature set for quality monitoring.

4. The environmental monitoring method for microbial decomposition of odorous gases according to claim 3, characterized in that: The current decomposition environment of microorganisms is evaluated by the current decomposition effect and current decomposition efficiency, and the comprehensive performance and dominant mode of the current decomposition environment of microorganisms are obtained, including: A sampling sliding window is preset, and the intake concentration of odorous gas and the residual concentration of odorous gas are obtained within the sampling sliding window to obtain the decomposition efficiency and decomposition effect; The decomposition efficiency and decomposition effect are normalized and mapped to the polar coordinate system. The radial distance of the polar coordinate system represents the comprehensive performance strength, and the polar angle represents the balance between the decomposition efficiency and the decomposition effect. The formula is as follows: Normalization processing: Among them, η norm is the normalized decomposition efficiency, η (t) is the decomposition efficiency calculated at time t, η min is the minimum value in the threshold range of decomposition efficiency, η max is the maximum value in the threshold range of decomposition efficiency, E norm is the decomposition effect after normalization, is the decomposition effect index, that is, the reciprocal of the residual concentration of odorous gas, ε is the minimum constant, E min is the minimum value in the threshold range of the decomposition effect, E max is the maximum value in the threshold range of the decomposition effect; The polar coordinate conversion formula is as follows: Among them, r(t) is the radial distance at time t, η norm is the normalized decomposition efficiency, E norm is the decomposition effect after normalization, θ(t) is the polar angle at time t, θ∈[-π,π], t=1,2,3...,T, t is each sampling moment in the sampling sliding window, and all sampling moments are sampling sliding window data; The density distribution of radial distance is analyzed by histogram method to determine the threshold range of comprehensive performance. The comprehensive performance levels include high efficiency, medium efficiency and low efficiency. The polar angle is divided into N sectors through polar angle coordinate transformation and clustering method to determine the interval boundary of the dominant mode. The multi-dimensional dominant mode includes decomposition efficiency dominant zone, effect dominant zone and equilibrium zone. Cartesian combination of the level threshold interval of the comprehensive performance and the interval boundary of the dominant mode is performed to generate a matrix of the combination of the comprehensive performance and the dominant mode; The radial distance and polar angle corresponding to the current decomposition effect and the current decomposition efficiency are calculated, and the matrix of the combination of comprehensive performance and dominant mode is traversed to obtain the comprehensive performance and dominant mode of the current decomposition environment of the microorganism.

5. The environmental monitoring method for microbial decomposition of odorous gas according to claim 1, characterized in that: Build a microbial decomposition environment prediction network library, including: Mining and obtaining the decomposition odor gas monitoring database, extracting key feature data for full-link monitoring; The key feature data of the full-link monitoring are classified and identified according to the type of odorous gas to obtain the decomposed odorous gas monitoring classification data set; Feature extraction is performed on the decomposition odor gas monitoring classification data set to obtain the decomposition odor gas monitoring classification feature set; The decomposition odor gas monitoring classification feature set is trained for working environment quality trend prediction respectively to obtain a multi-dimensional decomposition environment trend prediction branch network set; The multi-dimensional decomposition environmental trend prediction branch network set is classified and connected in series according to the odor gas type to generate multiple odor gas type decomposition environmental prediction network sets; The decomposition environment prediction network sets of multiple odorous gas types are identified and integrated to build a microbial decomposition environment prediction network library.

6. The environmental monitoring method for microbial decomposition of odorous gas according to claim 2 or 3, characterized in that: Establish a table of process node-quality monitoring key feature sets to characterize the key features corresponding to each process node, including: Acquire available multi-dimensional monitoring data and establish a mapping relationship with the process nodes of microbial decomposition of odorous gases, and establish an attribution table between the process nodes and the available multi-dimensional monitoring data; Obtain key monitoring data and quality monitoring key feature sets, extract the attribution table of process nodes and key monitoring data from the attribution table of process nodes and available multi-dimensional monitoring data based on the key monitoring data, and establish the attribution table of process nodes-quality monitoring key feature sets based on the correspondence between key monitoring data and quality monitoring key feature sets.

7. The environmental monitoring method for microbial decomposition of odorous gases according to claim 6, characterized in that: Generate a first optimization instruction, including: Decompose the quality prediction trend of the microbial decomposition environment into multi-dimensional independent trend factors, traverse the attribution table of the process node-quality monitoring key feature set, and establish a mapping relationship with the key features; The classification standard is preset to discretize the trend of multi-dimensional independent trend factors and generate the intensity vector of multi-dimensional trend factors; Pre-built discrete contribution function to calculate the discrete contribution of each key feature to evaluate the impact of each factor on the overall trend; Preset an optimization grading scale, perform optimization hierarchical grading on the contribution of each key feature according to the optimization grading scale, and extract the first optimization instruction; Based on the first optimization instruction, the parameters of the key features corresponding to the process nodes are optimized to optimize the quality of the microbial decomposition environment.

8. An environmental monitoring system for microbial decomposition of odorous gases, characterized in that: The system includes: The dual-constraint module is used to obtain the threshold range of the decomposition effect and decomposition efficiency of the microbial decomposition device, which is defined as a dual-constraint target. The decomposition effect is the direct basis for meeting the emission standards, and the decomposition efficiency is the instantaneous metabolic capacity of microorganisms to decompose odorous gases. The quality monitoring database module is used to collect multi-dimensional monitoring data of the microbial decomposition odor device through the environmental monitoring sensor group, including the odor gas intake concentration, intake flow, liquid flow, temperature, humidity, dissolved oxygen concentration, pH value of the microbial reaction unit, and residual concentration of odor gas, to build a quality monitoring database of the microbial decomposition environment; The quality monitoring key feature set module is used to extract the quality features of the microbial decomposition environment in the entire link based on the quality monitoring database to obtain the quality monitoring key feature set of the microbial decomposition environment; Environmental quality prediction trend module: This module is used to build a microbial decomposition environment prediction network library, input the key feature set of quality monitoring, and output the predicted quality prediction trend of the microbial decomposition environment; A first optimization instruction module is used to traverse the quality prediction trend through the attribute table of the process node-quality monitoring key feature set, establish a mapping relationship with the key features, calculate the risk contribution of the key features on each process node, prioritize the risk contribution, and generate a first optimization instruction, wherein the attribute table of the process node-quality monitoring key feature set is used to characterize the key features corresponding to each process node; The decomposition environment optimization module is used to optimize the quality of the microbial decomposition environment based on the first optimization instruction.

Images