Sewage sediment aggregate porosity prediction method, device, equipment and storage medium

Abstract

The present application relates to the technical field of drainage engineering, and discloses a sewage sediment aggregate porosity prediction method, device, equipment and storage medium, the method comprising: obtaining the measured water quality parameters of sewage in the target sewage pipeline, the target gas generation rate and the target extracellular polymer production rate of the sewage sediment aggregate; inputting the measured water quality parameters of sewage in the target sewage pipeline, the target gas generation rate and the target extracellular polymer production rate into a pre-constructed sediment aggregate microstructure prediction model, so that the sediment aggregate microstructure prediction model outputs the target microstructure image of the sewage sediment aggregate in the target sewage pipeline, and the sediment aggregate microstructure prediction model is used to represent the correlation between the water quality parameters of sewage, the target gas generation rate, the extracellular polymer production rate and the microstructure image of the sewage sediment aggregate; and determining the target porosity of the sediment aggregate in the target sewage pipeline based on the target microstructure image.

Description

Technical Field

[0001] This invention relates to the field of drainage engineering technology, specifically to a method, apparatus, equipment, and storage medium for predicting the porosity of sewage sediments. Background Technology

[0002] Deposits inside sewage pipelines are formed by a mixture of microbial cells, extracellular polymers, and impurity particles. The porosity of these deposits is a key parameter characterizing their microstructure. Porosity directly determines the substrate diffusion and mass transfer efficiency within the deposits, affecting the rate of microbial metabolic gas production and the level of extracellular polymer formation. This, in turn, relates to the risks of pipeline corrosion, blockage, and the release of harmful gases. Therefore, monitoring the porosity of deposits is necessary to provide a basis for assessing pipeline operational status.

[0003] In related technologies, the porosity of sedimentary aggregates is typically obtained by combining on-site sampling with scanning electron microscopy (SEM) image analysis. This method requires collecting physical samples of sedimentary aggregates from inside the sewage pipe, performing a series of preprocessing steps, and then obtaining two-dimensional microscopic cross-sectional images of the aggregates using SEM. The images are then binary segmented, and the porosity is calculated by statistically analyzing the percentage of pore pixels. However, this monitoring method can only perform post-event testing on already formed sedimentary aggregate samples, providing only the porosity results of the aggregates formed at the time of sampling. Given the dynamic fluctuations in pipeline water quality, relying solely on post-event sampling and testing is insufficient to anticipate the evolution of porosity and to predict the risks of pipe blockage and corrosion caused by porosity deterioration. This approach fails to meet the practical needs of pre-assessment of sewage pipeline operational risks. Summary of the Invention

[0004] This invention provides a method for predicting the porosity of sewage sediments, which solves the problem that the method of collecting physical samples of sediments to determine the porosity of sediments in related technologies cannot provide a prediction before the risk of pipeline blockage and corrosion occurs due to porosity deterioration, and thus cannot meet the practical needs of pre-assessment of sewage pipeline operation risks.

[0005] In a first aspect, the present invention provides a method for predicting the porosity of wastewater sediment aggregates. The method includes: acquiring measured water quality parameters, target gas generation rate, and target extracellular polymer generation rate of wastewater in a target wastewater pipeline; inputting the measured water quality parameters, target gas generation rate, and target extracellular polymer generation rate of wastewater in the target wastewater pipeline into a pre-constructed microstructure prediction model of sediment aggregates, so that the microstructure prediction model of sediment aggregates outputs a target microstructure image of wastewater sediment aggregates in the target wastewater pipeline, wherein the microstructure prediction model of sediment aggregates is used to characterize the correlation between the water quality parameters, target gas generation rate, extracellular polymer generation rate, and microstructure image of wastewater sediment aggregates; and determining the target porosity of sediment aggregates in the target wastewater pipeline based on the target microstructure image.

[0006] The wastewater sediment porosity prediction method provided by this invention eliminates the need for physical sampling of sediments within pipelines, thus avoiding damage to the original microstructure of the sediments caused by sampling operations and sample pretreatment. Based on measured water quality parameters, target gas generation rates, and target extracellular polymer generation rates, and utilizing a pre-constructed sediment microstructure prediction model, a correlation is established between water quality parameters, metabolic yields, and microstructure images. The target microstructure image is directly output, and porosity is determined accordingly. This method overcomes the limitation of related technologies that can only obtain the porosity status at the sampling time. It can adapt to the actual operating conditions of dynamic fluctuations in pipeline water quality, and perform sediment porosity prediction based on pipeline water quality conditions. It allows for early understanding of porosity evolution trends and risk prediction before porosity deterioration induces pipeline blockage and corrosion risks, better meeting the application needs of pre-assessment of wastewater pipeline operation risks.

[0007] In one optional implementation, the step of obtaining the measured water quality parameters of the wastewater in the target wastewater pipeline, the target gas generation rate, and the target extracellular polymer generation rate of the wastewater sediment aggregates includes: obtaining the measured water quality parameters of the wastewater in the target wastewater pipeline; inputting the measured water quality parameters into a pre-constructed microbial reaction kinetic model for solution, and obtaining the target gas generation rate and the target extracellular polymer generation rate under the measured water quality parameter conditions. The microbial reaction kinetic model is used to describe the dynamic relationship between substrate degradation, product generation, and microbial growth during microbial metabolism.

[0008] The method provided by this optional implementation does not require on-site measurement of gas generation rate and extracellular polymeric substance (LCS) generation rate. Instead, it relies solely on on-site measured water quality parameters and uses a microbial reaction kinetic model to solve for the corresponding target gas generation rate and LCS generation rate. This avoids the practical difficulty of directly detecting gas yield and LCS generation rate in situ under pipeline conditions, providing reliable input conditions for the microstructure prediction model of sediment aggregates and ensuring the smooth progress of subsequent porosity prediction.

[0009] In one optional implementation, the sediment aggregate microstructure prediction model is constructed through the following steps: acquiring multiple sets of effective water quality parameters, target gas generation rates and extracellular polymer generation rates of each set of effective feature parameters, and multiple virtual microstructure images; associating the multiple effective water quality parameters, target gas generation rates and extracellular polymer generation rates of the multiple sets of effective feature parameters with the multiple virtual microstructure images based on preset association rules to obtain an association dataset; using the effective feature parameters, target gas generation rates, and extracellular polymer generation rates as inputs and the virtual microstructure images as outputs, training the pre-constructed generative adversarial network using the association dataset until the model accuracy meets preset conditions, thereby obtaining the sediment aggregate microstructure prediction model.

[0010] The method provided in this optional implementation method establishes a mapping relationship between water quality parameters, gas generation rate, extracellular polymer generation rate and virtual microstructure image by constructing an associated dataset to train a generative adversarial network. This enables the model to reliably output the corresponding microstructure image based on the input operating conditions, providing a model basis for subsequent porosity prediction.

[0011] In one optional implementation, multiple sets of effective water quality parameters, target gas generation rates, extracellular polymer generation rates, and multiple virtual microstructure images are acquired. This includes: acquiring wastewater water quality parameter sequence data for a target time period, target gas generation rates, extracellular polymer generation rates, and real microstructure images for each set of real water quality parameters within the water quality parameter sequence data. The water quality parameter sequence data, target gas generation rates, extracellular polymer generation rates, and real microstructure images are obtained by simulating the static water deposition conditions of wastewater pipelines using a wastewater microbial culture system; extracting key feature parameters and statistical feature parameters from each real microstructure image. The key feature parameters characterize the overall state of wastewater sediment aggregates, and the statistical feature parameters characterize the spatial distribution characteristics of the microstructure of wastewater sediment aggregates; using the statistical feature parameters of each real microstructure image as constraints, a preset random generation algorithm is used to generate multiple virtual microstructure images corresponding to the real microstructure images. The key feature parameters of the image are the same as those of the corresponding real microstructure image; multiple sets of initial water quality parameters are obtained; each set of initial water quality parameters is used as a boundary condition to solve a pre-constructed microbial reaction kinetic model to obtain the target gas generation rate and extracellular polymer generation rate under the corresponding initial water quality parameter conditions; based on preset association rules, at least one set of target initial water quality parameters corresponding to each set of real water quality parameters in the water quality parameter sequence data are determined, and the key feature parameters of each target initial water quality parameter are the same as those of the corresponding real water quality parameters; the target gas generation rate and extracellular polymer generation rate of each set of real water quality parameters are compared with the target gas generation rate and extracellular polymer generation rate of each set of target initial water quality parameters to determine the first deviation value and the second deviation value of the corresponding target gas generation rate; among the multiple sets of target initial water quality parameters, the target initial water quality parameters whose corresponding first deviation value and / or second deviation value are greater than the preset threshold are removed to obtain multiple sets of effective water quality parameter data.

[0012] The method provided in this optional implementation simulates the static water sedimentation conditions in a pipeline using a wastewater microbial culture system. It acquires real water quality, metabolic, and microstructural image data corresponding to these conditions, and uses this data as a constraint to generate virtual microstructural images. This ensures that the virtual images can reproduce the overall state and microscopic spatial distribution characteristics of the real sediment aggregates. Then, a microbial reaction kinetic model is used to solve for the metabolic yield corresponding to the initial water quality parameters. Samples exceeding the deviation threshold are then filtered to obtain valid water quality parameter data, achieving quality control screening of training samples. This method not only solves the problem of the limited number of samples obtainable under real-world conditions, expanding the sample size required for model training, but also ensures that the metabolic characteristics of the selected valid samples deviate from the simulated and measured results within a controllable range. This improves the data quality of subsequent training datasets and is beneficial for improving the prediction accuracy of the sediment aggregate microstructure prediction model.

[0013] In one optional implementation, multiple effective water quality parameters, the standard gas generation rate of multiple sets of effective feature parameters, the extracellular polymer generation rate, and multiple virtual microstructure images are associated with each other based on preset association rules to obtain an associated dataset. This includes: determining the virtual microstructure image corresponding to each set of effective water quality parameters based on the key feature parameters of multiple sets of effective water quality parameters and the key feature parameters of multiple virtual microstructure images; and associating the standard gas generation rate of multiple sets of effective feature parameters, the extracellular polymer generation rate, and multiple virtual microstructure images with each set of effective water quality parameters based on the virtual microstructure images corresponding to each set of effective water quality parameters to obtain an associated dataset.

[0014] The method provided in this optional implementation completes the matching and correspondence between effective water quality parameters and virtual microstructure images through key feature parameters, realizes a reliable correlation between water quality, metabolic yield and virtual microstructure images, ensures that the input features in the associated dataset are compatible with the working condition features of the output image, avoids feature mismatch problems, improves the data consistency of the associated dataset, provides well-matched training samples for generative adversarial networks, and further ensures the training convergence effect and prediction reliability of the sediment aggregate microstructure prediction model.

[0015] In one optional implementation, multiple sets of initial water quality parameters are obtained, including: obtaining typical water quality parameter range data; uniformly sampling the typical water quality parameter range data to obtain multiple sets of initial water quality parameters.

[0016] The method provided by this optional implementation method obtains multiple sets of initial water quality parameters by uniformly sampling based on typical water quality parameter ranges. This can cover common water quality operating conditions in sewage pipelines, and the sample distribution is uniform and comprehensive, avoiding the concentration of samples in local operating condition ranges. The initial water quality parameters obtained in this way can enrich the diversity of operating conditions, provide a sufficient and reasonably distributed sample basis for subsequent screening of effective water quality parameters, and help improve the model's generalization prediction ability for different water quality operating conditions.

[0017] Secondly, the present invention provides a device for predicting the porosity of sewage deposits, the device comprising: an acquisition module for acquiring measured water quality parameters, target gas generation rate, and target extracellular polymer generation rate of sewage in a target sewage pipeline; a first determination module for inputting the measured water quality parameters, target gas generation rate, and target extracellular polymer generation rate of sewage in the target sewage pipeline into a pre-constructed microstructure prediction model of the deposits, so that the microstructure prediction model outputs a target microstructure image of the sewage deposits in the target sewage pipeline, the microstructure prediction model being used to characterize the correlation between the water quality parameters, target gas generation rate, extracellular polymer generation rate of the sewage and the microstructure image of the sewage deposits; and a second determination module for determining the target porosity of the deposits in the target sewage pipeline based on the target microstructure image.

[0018] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the wastewater sediment aggregate porosity prediction method of the first aspect or any corresponding embodiment described above.

[0019] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the wastewater sediment porosity prediction method of the first aspect or any corresponding embodiment thereof.

[0020] Fifthly, the present invention provides a computer program product, including computer instructions for causing a computer to execute the wastewater sediment porosity prediction method of the first aspect or any corresponding embodiment thereof. Attached Figure Description

[0021] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0022] Figure 1 This is a schematic diagram of an application scenario according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the first process of a method for predicting the porosity of wastewater sediments according to an embodiment of the present invention; Figure 3This is a schematic diagram of the second process of the wastewater sediment porosity prediction method according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the wastewater microbial culture system in the embodiments of this application; Figure 5 This is a schematic diagram of the microstructure of sewage sediment aggregates in the application embodiment; Figure 6 This is a structural block diagram of a wastewater sediment porosity prediction device according to an embodiment of the present invention; Figure 7 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0025] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0026] As an optional application scenario of this invention, the specific application environment architecture or specific hardware architecture on which the wastewater sediment porosity prediction method depends is described herein. For example... Figure 1 As shown, the architecture system may include at least one terminal device and at least one server. Figure 1 The system is illustrated in the example, which includes a computer 101, a mobile terminal 102, and a server 103, and the terminal devices such as the computer 101 and the mobile terminal 102 are connected to the server 103 through a network 110.

[0027] Specifically, the terminal device can be a smartphone, tablet, laptop, PDA, desktop computer, game console, smart TV, smart wearable device, in-vehicle terminal, VR (Virtual Reality) device, AR (Augmented Reality) device, etc. Server 103 can be a standalone physical server, a server cluster, a distributed system, or a cloud server providing cloud services. Network 110 can be a wired or wireless network, examples of which include, but are not limited to, the Internet, corporate intranet, local area network, wide area network, mobile communication network, and combinations thereof.

[0028] In related technologies, the porosity of sedimentary aggregates is typically obtained by combining on-site sampling with scanning electron microscopy (SEM) image analysis. This method requires collecting physical samples of sedimentary aggregates from inside the sewage pipe, performing a series of preprocessing steps, and then obtaining two-dimensional microscopic cross-sectional images of the aggregates using SEM. The images are then binary segmented, and the porosity is calculated by statistically analyzing the percentage of pore pixels. However, this monitoring method can only perform post-event testing on already formed sedimentary aggregate samples, providing only the porosity results of the aggregates formed at the time of sampling. Given the dynamic fluctuations in pipeline water quality, relying solely on post-event sampling and testing is insufficient to anticipate the evolution of porosity and to predict the risks of pipe blockage and corrosion caused by porosity deterioration. This approach fails to meet the practical needs of pre-assessment of sewage pipeline operational risks.

[0029] In view of this, this application provides a method for predicting the porosity of sewage sediment aggregates, which can be applied to a server to predict the porosity of sewage sediment aggregates. The method provided in this application does not require physical sampling of sediment aggregates within the pipeline, thus avoiding damage to the original microstructure of the aggregates caused by sampling operations and sample pretreatment. Based on measured water quality parameters, target gas generation rate, and target extracellular polymer generation rate, and using a pre-constructed sediment aggregate microstructure prediction model, a correspondence between water quality parameters, metabolic yield, and microstructure image is established, directly outputting the target microstructure image and determining the porosity accordingly. This method overcomes the limitation of related technologies that can only obtain the current porosity at the sampling time, adapting to the actual operating conditions of dynamic fluctuations in pipeline water quality. It completes the prediction of sediment aggregate porosity based on pipeline water quality conditions, allowing for early understanding of porosity evolution trends and risk prediction before porosity deterioration induces pipeline blockage and corrosion risks, better meeting the application needs of pre-assessment of sewage pipeline operation risks.

[0030] According to an embodiment of the present invention, a method for predicting the porosity of wastewater sediment aggregates is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0031] This embodiment provides a method for predicting the porosity of wastewater sediment aggregates, which can be used in the aforementioned server. Figure 2 This is a flowchart of a wastewater sediment porosity prediction method according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps: Step S201: Obtain the measured water quality parameters of the sewage in the target sewage pipe, the target gas generation rate, and the target extracellular polymer generation rate of the sewage sediment aggregates.

[0032] For example, the target sewage pipeline is the sewage pipeline for which the porosity of the deposits needs to be predicted; the measured water quality parameters are sewage water quality indicators actually collected and detected on-site at the target sewage pipeline, which may include, but are not limited to, organic substrate concentration, nutrient concentration, pH value, temperature, etc., and are on-site measured data reflecting the actual water quality of the sewage in the pipeline; the sewage deposits refer to the flocculent aggregates formed by the interweaving and deposition of microbial cells, extracellular polymers, and impurity particles under the static water deposition conditions of the sewage pipeline, and are the objects of porosity calculation; the target gas generation rate refers to the rate at which gas is produced by the metabolic activity of microorganisms in the deposits within the pipeline under the current water quality conditions of the target sewage pipeline, characterizing the amount of gas generated by microbial metabolism per unit time, which is not directly measured on-site, but can be solved and output by a microbial reaction kinetic model. In this embodiment, the target gas may include, but is not limited to, methane and hydrogen sulfide; the target extracellular polymer generation rate represents the rate at which microorganisms in the deposits synthesize extracellular polymers (EPPs) under the current water quality conditions of the target sewage pipeline. The rate of Substances (EPS), which characterizes the amount of extracellular polymeric substances generated per unit time, can be solved and output by a microbial reaction kinetic model.

[0033] Step S202: Input the measured water quality parameters, target gas generation rate, and target extracellular polymer generation rate of the sewage in the target sewage pipeline into the pre-constructed sedimentation aggregate microstructure prediction model, so that the sedimentation aggregate microstructure prediction model outputs the target microstructure image of the sewage sedimentation aggregate in the target sewage pipeline. The sedimentation aggregate microstructure prediction model is used to characterize the correlation between the water quality parameters, target gas generation rate, extracellular polymer generation rate and the microstructure image of the sewage sedimentation aggregate.

[0034] For example, in this embodiment of the application, the measured water quality parameters obtained on-site, as well as the target gas generation rate and target extracellular polymer generation rate calculated by the kinetic model, are used as input conditions and fed into the trained sediment aggregate microstructure prediction model. The model calls the internally learned mapping relationships to perform calculations and inferences on the input operating condition features, and directly outputs a target microstructure image adapted to the set of operating conditions. The sediment aggregate microstructure prediction model is obtained by training a generative adversarial network using a pre-built dataset.

[0035] Step S203: Determine the target porosity of the deposited aggregates in the target sewage pipe based on the target microstructure image.

[0036] For example, in this embodiment of the application, the target microstructure image is subjected to binary segmentation processing to distinguish between solid aggregate regions and pore regions in the image, and the number of pixels or voxels in the pore regions and the entire image is counted. The target porosity of the deposited aggregate is calculated based on the proportion of pixels or voxels in the pore regions to the total number of pixels or voxels in the image.

[0037] The wastewater sediment porosity prediction method provided in this embodiment eliminates the need for physical sampling of sediments within the pipeline, thus avoiding damage to the original microstructure of the sediments caused by sampling operations and sample pretreatment. Based on measured water quality parameters, target gas generation rate, and target extracellular polymer generation rate, and utilizing a pre-constructed sediment microstructure prediction model, a correlation is established between water quality parameters, metabolic yield, and microstructure images. The target microstructure image is directly output, and porosity is determined accordingly. This method overcomes the limitation of related technologies that can only obtain the current porosity at the sampling time. It can adapt to the actual operating conditions of dynamic fluctuations in pipeline water quality, and perform sediment porosity prediction based on pipeline water quality conditions. It allows for early understanding of porosity evolution trends and risk prediction before porosity deterioration induces pipeline blockage and corrosion risks, better meeting the application needs of pre-assessment of wastewater pipeline operation risks.

[0038] This embodiment provides a method for predicting the porosity of wastewater sediment aggregates, which can be used in the aforementioned server. Figure 3 This is a flowchart of a wastewater sediment porosity prediction method according to an embodiment of the present invention, such as... Figure 3 As shown, the process includes the following steps: Step S301: Obtain the measured water quality parameters of the sewage in the target sewage pipeline, the target gas generation rate, and the target extracellular polymer generation rate of the sewage sediment aggregates.

[0039] Specifically, step S301 includes: Step S3011: Obtain the measured water quality parameters of the sewage in the target sewage pipeline.

[0040] For example, in this embodiment of the application, a wastewater sample is collected from the target wastewater pipeline, and the sample is analyzed on-site or in the laboratory to obtain the measured water quality parameters corresponding to the wastewater. The water quality parameters may include, but are not limited to, chemical oxygen demand (COD), ammonia nitrogen concentration, sulfate concentration, dissolved oxygen (DO) concentration, pH value, and water temperature.

[0041] Step S3012: Input the measured water quality parameters into the pre-constructed microbial reaction kinetic model for solution to obtain the target gas generation rate and the target extracellular polymer generation rate under the measured water quality parameter conditions. The microbial reaction kinetic model is used to describe the dynamic relationship between substrate degradation, product generation and microbial growth during microbial metabolism.

[0042] For example, measured water quality parameters are used as the initial input and boundary conditions of the microbial reaction kinetics model, and substituted into a set of differential equations describing substrate degradation, microbial growth, and product generation for iterative solution. The microbial metabolic evolution process within the pipeline is simulated over time until the system reaches a steady state. The calculated output results under steady-state conditions are then read to obtain the target gas generation rate and extracellular polymer generation rate corresponding to the water quality condition. In this embodiment, the microbial reaction kinetics model is shown in the following equation:

[0043]

[0044]

[0045] in, Indicates the rate of production of the target extracellular polymeric substance (EPS); The EPS production coefficient represents the ability of microorganisms to generate EPS through metabolism. This indicates the substrate utilization rate, the rate at which wastewater substrates are consumed by microorganisms; This indicates the substrate concentration, which refers to the organic substrates in wastewater that can be utilized and degraded by anaerobic microorganisms such as acid-producing bacteria, methanogenic bacteria, and sulfate-reducing bacteria in the pipeline. It mainly corresponds to dissolved COD. This represents the first-order hydrolysis coefficient of EPS, characterizing the rate of EPS hydrolysis and degradation. This indicates the current concentration of tightly bound extracellular polymeric substances in the system. Indicates liquid flow rate; Indicates the initial EPS concentration of the input fluid; Indicates the volume of liquid in the reaction system; : This represents the generation term of EPS (expanded power reserves) due to substrate electron transfer, and the EPS generation rate. : The term represents the EPS loss rate caused by hydrolysis; This indicates the EPS input item brought in by the incoming water; This indicates the EPS outflow item carried away by the effluent; Indicates the rate of hydrogen sulfide production; This indicates the long-term average sulfate concentration in wastewater; It represents the long-term average COD concentration in wastewater, i.e., dissolved chemical oxygen demand; , Represents the model fit coefficients; Indicates the rate of methanogenesis; This indicates the long-term average sulfate concentration in wastewater; This indicates the long-term average COD concentration in wastewater; , , This represents the model fit coefficient.

[0046] Step 302: Input the measured water quality parameters of the sewage in the target sewage pipeline, the target gas generation rate, and the target extracellular polymer generation rate into the pre-constructed sedimentation aggregate microstructure prediction model, so that the sedimentation aggregate microstructure prediction model outputs the target microstructure image of the sewage sedimentation aggregate in the target sewage pipeline. The sedimentation aggregate microstructure prediction model is used to characterize the correlation between the water quality parameters of the sewage, the target gas generation rate, the extracellular polymer generation rate, and the microstructure image of the sewage sedimentation aggregate.

[0047] In some alternative implementations, the sediment aggregate microstructure prediction model is constructed through the following steps: Step a1: Obtain multiple sets of effective water quality parameters, target gas generation rate of each set of effective characteristic parameters, extracellular polymer generation rate, and multiple virtual microstructure images.

[0048] Specifically, step a1 above includes: Step a11: Obtain the water quality parameter sequence data of the wastewater within the target time period, the target gas generation rate, extracellular polymer generation rate, and real microstructure image of each group of real water quality parameters in the water quality parameter sequence data. The water quality parameter sequence data, target gas generation rate, extracellular polymer generation rate, and real microstructure image are obtained by simulating the static water deposition conditions of the wastewater pipeline through a wastewater microbial culture system.

[0049] For example, a wastewater microbial culture system was constructed to simulate the static sedimentation conditions of wastewater pipelines. The simulation system was continuously run within a target time period, and wastewater quality parameters were collected periodically to obtain water quality parameter sequence data. Simultaneously, the gas release rate and extracellular polymer content at corresponding times within the system were collected, obtaining target gas release rate sequence data and extracellular polymer content sequence data, respectively. These were then converted to calculate the target gas generation rate and extracellular polymer generation rate corresponding to each set of real water quality parameters. Simultaneously, sediment aggregate samples were collected periodically to obtain corresponding real microstructure images, resulting in microstructure image sequence data. The real microstructure images of each set of real water quality parameters can be obtained using environmental scanning electron microscopy and Micro-CT detection instruments.

[0050] In this embodiment, the wastewater microbial culture system includes: a wastewater preparation module, a peristaltic pump, a culture container, several columnar sediment accumulation culture modules, a mixer, a water quality monitoring module, and a gas collection module. The wastewater preparation module is used to artificially prepare simulated wastewater and dynamically adjusts the water quality indicators of the wastewater delivered to the culture container via the peristaltic pump to simulate the water quality changes in a real wastewater pipeline. A schematic diagram of the wastewater microbial culture system is shown below. Figure 4 As shown, the wastewater preparation module includes at least one volumetric flask 1 and an inlet hose 2. One end of the inlet hose 2 is placed in the volumetric flask 1, and the other end is connected to the inlet of a multi-channel independently controlled peristaltic pump 3 via a pipeline. The outlet pipeline of the peristaltic pump 3 is connected to the inlet 4 of the culture container. A mixing agitator 6 is installed on the outlet pipeline of the peristaltic pump 3 and is used to mix the artificially prepared wastewater evenly under the control of a motor 5. Several columnar sediment accumulation culture modules 8 are placed inside the culture container 7, and each columnar sediment accumulation culture module 8 contains a sediment accumulation sample collected on-site. A gas outlet is provided at the top of the culture container 7 and is connected to a gas collection module 11 via a pipeline. The sensor probe 9 of the water quality monitoring module 10 is immersed below the liquid surface in the culture container and is used to monitor water quality indicators in real time, including pH, water temperature, dissolved oxygen, conductivity, turbidity, COD, ammonia nitrogen, and total phosphorus. The concentration of sulfate is measured manually. The culture container 3 is used to simulate the high-water-level static water condition of the wastewater pipeline, and the stripping effect of water flow on sediment accumulation is not considered. The columnar sediment aggregate culture module 8 is designed as a removable, mesh-like structure that is permeable to water and air, but the entire sediment can be removed so that individual modules can be taken out for subsequent analysis at predetermined time intervals. The gas collection module 11 uses manual gas extraction to collect the gas generated during the culture process and is equipped with a gas chromatograph for quantitative analysis of gas components. A schematic diagram of the microstructure of the wastewater sediment aggregate is shown below. Figure 5 As shown.

[0051] Step a12: Extract key feature parameters and statistical feature parameters from each real microstructure image. Key feature parameters are used to characterize the overall state of sewage sediments, while statistical feature parameters are used to characterize the spatial distribution characteristics of the microstructure of sewage sediments.

[0052] For example, key characteristic parameters may include, but are not limited to, the intermediate particle size (d) and porosity of the aggregate; statistical characteristic parameters may include, but are not limited to, the porosity distribution function, the pore size distribution function, the two-point probability function, the fractal dimension, and the anisotropy parameter. In this embodiment, a binary segmentation is performed on the real microstructure image to distinguish the solid phase region and the pore region of the aggregate. Based on the segmented binary image, calculation processing is performed to obtain the statistical porosity distribution function and the pore size distribution function. The statistical porosity distribution function and the pore size distribution function characterize the distribution law of pore size; the two-point probability function is calculated to describe the spatial positional relationship between the solid phase and the pore region; the fractal dimension is solved to characterize the complexity of the microstructure; and the anisotropy parameter is calculated to reflect the morphological differences of the structure in different directions, thereby obtaining all statistical characteristic parameters.

[0053] Step a13: Using the statistical feature parameters of each real microstructure image as a constraint, a preset random generation algorithm is used to generate multiple virtual microstructure images corresponding to the real microstructure images. The key feature parameters of the virtual microstructure images are the same as those of the corresponding real microstructure images.

[0054] For example, the preset random generation algorithm may include, but is not limited to, the Quartet Structure Generation Set (QSGS) algorithm for porous media microstructures. In this embodiment, a random generation algorithm is used to generate N virtual microstructure images with statistical feature parameters as constraints, where N≥1000. Each virtual image is statistically distributed the same as the real image, but the specific pore morphology and spatial arrangement have random differences.

[0055] Step a14: Obtain multiple sets of initial water quality parameters.

[0056] For example, in this embodiment of the application, typical water quality parameter range data are obtained; the typical water quality parameter range data are uniformly sampled to obtain multiple sets of initial water quality parameters.

[0057] Step a15: Input each set of initial water quality parameters as boundary conditions into the pre-constructed microbial reaction kinetic model for solution, and obtain the target gas generation rate and extracellular polymer generation rate under the corresponding initial water quality parameter conditions.

[0058] For example, in the embodiments of this application, each set of initial water quality parameters is set as the initial value and boundary condition of the microbial reaction kinetic model, and the coupled differential equations of substrate degradation, microbial growth and product generation are substituted into the model to carry out iterative calculations, simulating the microbial metabolic evolution process until the calculation reaches a steady state, and outputting the target gas generation rate and extracellular polymer generation rate corresponding to each initial water quality parameter.

[0059] Step a16: Based on preset association rules, determine at least one set of target initial water quality parameters corresponding to each set of real water quality parameters in the water quality parameter sequence data. The key feature parameters of each target initial water quality parameter are the same as the key feature parameters of the corresponding real water quality parameters.

[0060] For example, in the embodiments of this application, for each set of real water quality parameters, based on the pre-set allowable deviation threshold of each water quality parameter, at least one set of initial water quality parameters (COD, ammonia nitrogen, sulfate, pH, DO, water temperature) with similar water quality parameters is found in the entire set of initial water quality parameters.

[0061] Step a17: Compare the target gas generation rate and extracellular polymer generation rate of each group of real water quality parameters with the target gas generation rate and extracellular polymer generation rate of the corresponding initial water quality parameters to determine the first deviation value of the target gas generation rate and the second deviation value of the extracellular polymer generation rate.

[0062] Step a18: Among multiple sets of target initial water quality parameters, remove the target initial water quality parameters whose corresponding first deviation value and / or second deviation value is greater than a preset threshold, and obtain multiple sets of valid water quality parameter data.

[0063] For example, the preset threshold can be determined based on actual needs, and this application embodiment does not impose specific limitations. In this application embodiment, based on at least one set of target initial water quality parameters corresponding to each set of real water quality parameters, the relative error between the simulated index and the corresponding measured index is calculated, and simulation results with a relative error of less than 5% are retained as valid samples. The target initial water quality conditions that meet the error requirements and their corresponding simulation outputs are recorded by group, and each group includes a complete set of water quality parameters and the corresponding methane gas production rate, hydrogen sulfide gas production rate, and EPS generation rate.

[0064] Step a2 involves associating multiple effective water quality parameters, target gas generation rates, extracellular polymeric substance generation rates, and multiple virtual microstructure images based on preset association rules to obtain an associated dataset. Exemplarily, in this embodiment, matching is performed based on key feature parameters. For each set of effective water quality parameters, a corresponding and suitable virtual microstructure image is matched. The effective water quality parameters, the corresponding target gas generation rates, extracellular polymeric substance generation rates, and the matched virtual microstructure images are paired one-to-one to form an associated dataset.

[0065] Specifically, step a2 above includes: Step a21: Determine the virtual microstructure image corresponding to each set of effective water quality parameters based on the key feature parameters of multiple sets of effective water quality parameters and the key feature parameters of multiple virtual microstructure images.

[0066] For example, in this embodiment of the application, key feature parameters corresponding to each group of effective water quality parameters are extracted, key feature parameters of multiple virtual microstructure images are traversed, key feature parameters of the two are compared, and virtual microstructure images that match the key feature parameters of the effective water quality parameters are selected, thereby determining the virtual microstructure images corresponding to each group of effective water quality parameters.

[0067] Step a22: Based on the virtual microstructure images corresponding to each group of effective water quality parameters, the standard gas generation rate and extracellular polymer generation rate of multiple effective water quality parameters and multiple groups of effective feature parameters are correlated with multiple virtual microstructure images to obtain a correlated dataset.

[0068] For example, based on the correspondence between the already matched effective water quality parameters and the virtual microstructure images, each set of effective water quality parameters, its corresponding target gas generation rate, extracellular polymer generation rate, and the already matched virtual microstructure images are bound one by one to obtain an associated dataset for model training.

[0069] Step a3 involves taking the effective feature parameters, target gas generation rate, and extracellular polymer generation rate as inputs, and the virtual microstructure image as output. The pre-constructed generative adversarial network is then trained using the associated dataset until the model accuracy meets the preset conditions, thus obtaining the microstructure prediction model of the sedimentary aggregates.

[0070] For example, in this embodiment, the associated dataset is divided into a training set, a validation set, and a test set at a ratio of 70%, 15%, and 15%, respectively. The input feature vectors are standardized to ensure all features are on the same order of magnitude. The target image is normalized, mapping pixel values ​​to the [-1, 1] interval, and data augmentation is performed through random rotation, flipping, etc., to suppress overfitting and improve the model's generalization ability. The pre-built generative adversarial network can include, but is not limited to, a conditional generative adversarial network (cGAN). A conditional generative adversarial network includes a generator network and a discriminator network. The generator network adopts an encoder-decoder structure. The encoder extracts an abstract representation of the input features through layer-by-layer downsampling, and the decoder restores the target image from the abstract representation through layer-by-layer upsampling. Features of the same resolution are passed between the encoder and decoder through skip connections to preserve spatial details such as aperture edges and hole shapes. To effectively incorporate water quality and metabolic yield features into the generation process, an adaptive feature modulation mechanism is employed. This transforms the input feature vector into modulation parameters, scaling and shifting the feature maps of each layer of the generation network to continuously constrain the image generation direction across the entire resolution scale. The discriminant network divides the input image into several local image patches, independently judging the authenticity of each patch before providing a comprehensive judgment. This structure effectively captures local texture and edge details of the image, while requiring fewer parameters and achieving high training efficiency. The input to the discriminant network is paired data between water quality features and the image, and the output is the probability of whether the pairing is genuine and reliable. The model training employs a triple loss joint optimization. The adversarial loss ensures that the generated image approximates the real image in its overall distribution; the pixel loss constrains the pixel-by-pixel consistency between the generated and real images, using absolute value loss to better preserve edge details; and the physical constraint loss ensures that the porosity of the generated image and the metabolic yield in the input conditions satisfy known physical laws (such as the negative correlation between EPS yield and porosity), making the prediction results physically reasonable and reliable.

[0071] Training employs an alternating optimization approach between the generator and discriminator networks. In each iteration, the generator network is initially fixed while the discriminator network is updated to enable it to distinguish between real and fake images; then, the discriminator network is fixed while the generator network is updated to generate more realistic images. The two networks co-evolve in an adversarial game, eventually reaching an equilibrium state. The Adam optimizer is used to automatically adjust the learning rate, which gradually decays as training progresses to ensure stable convergence.

[0072] During training, after each iteration, the peak signal-to-noise ratio (PSNR) and structural similarity index of the generated images, as well as the porosity prediction error, are calculated on the validation set. When the validation set loss no longer decreases significantly, or the mean absolute error of porosity prediction is less than a preset threshold, the model is considered to have converged and training is stopped. The parameters of the generated network are saved as the final prediction model.

[0073] The model was comprehensively evaluated using a test set, with evaluation metrics including image pixel accuracy, porosity prediction coefficient of determination, and consistency of pore morphology distribution. When the evaluation results met the requirements, the model was confirmed to be suitable for practical applications.

[0074] Step S303: Determine the target porosity of the deposited aggregates in the target sewage pipe based on the target microstructure image. For details, please refer to [link to relevant documentation]. Figure 2 Step S203 of the illustrated embodiment will not be described again here.

[0075] The method provided in this application significantly reduces the cost and time required for porosity detection. Traditional porosity measurement relies on expensive equipment such as Micro-CT and environmental scanning electron microscopes, as well as destructive sampling. This patent only requires conventional online water quality monitoring parameters (COD, ammonia nitrogen, DO, pH, etc.) to calculate porosity in real time, eliminating the need for frequent sampling and high-end imaging, thus significantly saving detection costs and time. It enables long-term, continuous, and non-invasive porosity monitoring. Existing methods mostly involve sampling at discrete time points, failing to reflect the dynamic evolution of pore structure. The method provided in this application utilizes continuous water quality monitoring data to drive a model, predicting changes in porosity within biofilms daily or even hourly, providing real-time decision-making support for sewage pipeline maintenance and sediment control. It also demonstrates high generalization ability under small sample conditions. Even with only about ten real images available, tens of thousands of pairs of virtual data are generated through a physical model, combined with a transfer learning strategy, still training a high-precision, low-overfit generative model, significantly outperforming pure data-driven methods that directly use a small number of real samples, demonstrating strong engineering practical value.

[0076] This embodiment also provides a wastewater sediment porosity prediction device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0077] This embodiment provides a device for predicting the porosity of wastewater sediment aggregates, such as... Figure 6 As shown, it includes: The acquisition module 601 is used to acquire the measured water quality parameters of the sewage in the target sewage pipeline, the target gas generation rate, and the target extracellular polymer generation rate of the sewage sediment aggregates. The first determining module 602 is used to input the measured water quality parameters of the sewage in the target sewage pipeline, the target gas generation rate, and the target extracellular polymer generation rate into a pre-constructed sedimentation aggregate microstructure prediction model, so that the sedimentation aggregate microstructure prediction model outputs the target microstructure image of the sewage sedimentation aggregate in the target sewage pipeline. The sedimentation aggregate microstructure prediction model is used to characterize the correlation between the water quality parameters of the sewage, the target gas generation rate, the extracellular polymer generation rate, and the microstructure image of the sewage sedimentation aggregate. The second determining module 603 is used to determine the target porosity of deposited aggregates in the target sewage pipe based on the target microstructure image.

[0078] In some alternative implementations, the acquisition module 601 includes: The acquisition submodule is used to acquire the measured water quality parameters of the sewage in the target sewage pipeline; The solution submodule is used to input measured water quality parameters into a pre-constructed microbial reaction kinetic model for solution, and obtain the target gas generation rate and target extracellular polymer generation rate under the measured water quality parameter conditions. The microbial reaction kinetic model is used to describe the dynamic relationship between substrate degradation, product generation and microbial growth during microbial metabolism.

[0079] In some alternative implementations, the sediment aggregate microstructure prediction model is constructed through the following steps: Acquire multiple sets of effective water quality parameters, target gas generation rate of each set of effective characteristic parameters, extracellular polymer generation rate, and multiple virtual microstructure images; Based on preset association rules, multiple effective water quality parameters, multiple sets of effective feature parameters, standard gas generation rate, extracellular polymer generation rate and multiple virtual microstructure images are associated to obtain an associated dataset; Using effective feature parameters, target gas generation rate, and extracellular polymer generation rate as inputs, and virtual microstructure images as outputs, a pre-constructed generative adversarial network is trained using associated datasets until the model accuracy meets preset conditions, thus obtaining a microstructure prediction model for sedimentary aggregates.

[0080] In some optional implementations, multiple sets of effective water quality parameters, target gas generation rates of each set of effective characteristic parameters, extracellular polymer generation rates, and multiple virtual microstructure images are acquired, including: The water quality parameter sequence data of wastewater within the target time period, the target gas generation rate, extracellular polymer generation rate and real microstructure image of each group of real water quality parameters in the water quality parameter sequence data are obtained. The water quality parameter sequence data, target gas generation rate, extracellular polymer generation rate and real microstructure image are obtained by simulating the static water deposition condition of wastewater pipeline through a wastewater microbial culture system. Key feature parameters and statistical feature parameters are extracted from each real microstructure image. The key feature parameters are used to characterize the overall state of sewage sediments and aggregates, while the statistical feature parameters are used to characterize the spatial distribution characteristics of the microstructure of sewage sediments and aggregates. Using the statistical feature parameters of each real microstructure image as a constraint, a preset random generation algorithm is used to generate multiple virtual microstructure images corresponding to the real microstructure images. The key feature parameters of the virtual microstructure images are the same as those of the corresponding real microstructure images. Obtain multiple sets of initial water quality parameters; Each set of initial water quality parameters is used as boundary conditions to input into a pre-constructed microbial reaction kinetic model for solution, thereby obtaining the target gas generation rate and extracellular polymer generation rate under the corresponding initial water quality parameter conditions. Based on preset association rules, at least one set of target initial water quality parameters is determined for each set of real water quality parameters in the water quality parameter sequence data. The key feature parameters of each target initial water quality parameter are the same as the key feature parameters of the corresponding real water quality parameters. The target gas generation rate and extracellular polymer generation rate of each group of real water quality parameters are compared with the target gas generation rate and extracellular polymer generation rate of the corresponding initial water quality parameters to determine the first deviation value of the target gas generation rate and the second deviation value of the extracellular polymer generation rate. Among multiple sets of target initial water quality parameters, the target initial water quality parameters whose corresponding first deviation value and / or second deviation value are greater than the preset threshold are removed to obtain multiple sets of effective water quality parameter data.

[0081] In some optional implementations, multiple effective water quality parameters, multiple sets of effective feature parameters, standard gas generation rates, extracellular polymer generation rates, and multiple virtual microstructure images are associated based on preset association rules to obtain an associated dataset, including: Based on the key feature parameters of multiple sets of effective water quality parameters and the key feature parameters of multiple virtual microstructure images, the virtual microstructure images corresponding to each set of effective water quality parameters are determined. Based on the virtual microstructure images corresponding to each set of effective water quality parameters, the standard gas generation rate and extracellular polymer generation rate of multiple effective water quality parameters and multiple sets of effective feature parameters are correlated with multiple virtual microstructure images to obtain a correlated dataset.

[0082] In some optional implementations, multiple sets of initial water quality parameters are obtained, including: obtaining typical water quality parameter range data; uniformly sampling the typical water quality parameter range data to obtain multiple sets of initial water quality parameters.

[0083] The wastewater sediment porosity prediction device provided in this embodiment of the invention can execute the wastewater sediment porosity prediction method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method. Further functional descriptions of the various modules and units are the same as in the corresponding embodiments described above, and will not be repeated here.

[0084] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0085] The following is a detailed reference. Figure 7 This diagram illustrates a suitable structural schematic for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 701, which can perform various appropriate actions and processes based on a program stored in read-only memory (ROM) 702 or a program loaded from memory 708 into random access memory (RAM) 703. The RAM 703 also stores various programs and data required for the operation of the electronic device. The processor 701, ROM 702, and RAM 703 are interconnected via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0086] Typically, the following devices can be connected to I / O interface 705: input devices 706 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 707 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 708 including, for example, magnetic tapes, hard disks, etc.; and communication devices 709. Communication device 709 allows electronic devices to exchange data via wireless or wired communication with other devices. Although Figure 7 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0087] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 709, or installed from a memory 708, or installed from a ROM 702. When the computer program is executed by the processor 701, it performs the functions defined in the wastewater sediment aggregate porosity prediction method of the embodiments of the present invention.

[0088] Figure 7 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0089] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the wastewater sediment aggregate porosity prediction method shown in the above embodiments is implemented.

[0090] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0091] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for predicting the porosity of wastewater sediment aggregates, characterized in that, The method includes: Obtain measured water quality parameters, target gas generation rate, and target extracellular polymer generation rate of sewage deposits in the target sewage pipeline; The measured water quality parameters, target gas generation rate, and target extracellular polymer generation rate of the wastewater in the target wastewater pipeline are input into a pre-constructed sedimentation aggregate microstructure prediction model, so that the sedimentation aggregate microstructure prediction model outputs a target microstructure image of the wastewater sedimentation aggregate in the target wastewater pipeline. The sedimentation aggregate microstructure prediction model is used to characterize the correlation between the wastewater water quality parameters, target gas generation rate, extracellular polymer generation rate, and the microstructure image of the wastewater sedimentation aggregate. The target porosity of deposited aggregates in the target sewage pipe is determined based on the target microstructure image.

2. The method according to claim 1, characterized in that, The steps of obtaining the measured water quality parameters of the wastewater in the target wastewater pipeline, the target gas generation rate, and the target extracellular polymer generation rate of the wastewater deposits include: Obtain measured water quality parameters of the sewage in the target sewage pipeline; The measured water quality parameters are input into a pre-constructed microbial reaction kinetic model for solution, to obtain the target gas generation rate and the target extracellular polymer generation rate under the measured water quality parameter conditions. The microbial reaction kinetic model is used to describe the dynamic relationship between substrate degradation, product generation and microbial growth during microbial metabolism.

3. The method according to claim 1 or 2, characterized in that, The microstructure prediction model for sedimentary aggregates was constructed through the following steps: Acquire multiple sets of effective water quality parameters, target gas generation rate of each set of effective characteristic parameters, extracellular polymer generation rate, and multiple virtual microstructure images; Based on preset association rules, multiple effective water quality parameters, multiple sets of effective feature parameters, standard gas generation rate, extracellular polymer generation rate are associated with the multiple virtual microstructure images to obtain an association dataset; Using the effective feature parameters, target gas generation rate, and extracellular polymer generation rate as inputs, and the virtual microstructure image as output, the pre-constructed generative adversarial network is trained using the associated dataset until the model accuracy meets the preset conditions, thus obtaining the microstructure prediction model of the sedimentary aggregate.

4. The method according to claim 3, characterized in that, The acquisition of multiple sets of effective water quality parameters, target gas generation rate of each set of effective characteristic parameters, extracellular polymer generation rate, and multiple virtual microstructure images includes: The water quality parameter sequence data of wastewater within the target time period, the target gas generation rate, extracellular polymer generation rate and real microstructure image of each group of real water quality parameters in the water quality parameter sequence data are obtained. The water quality parameter sequence data, the target gas generation rate, the extracellular polymer generation rate and the real microstructure image are obtained by simulating the static water deposition conditions of wastewater pipelines through a wastewater microbial culture system. Key feature parameters and statistical feature parameters are extracted from each real microstructure image. The key feature parameters are used to characterize the overall state of sewage sediments and the statistical feature parameters are used to characterize the spatial distribution characteristics of the microstructure of sewage sediments. Using the statistical feature parameters of each real microstructure image as a constraint, a preset random generation algorithm is used to generate multiple virtual microstructure images corresponding to the real microstructure images. The key feature parameters of the virtual microstructure images are the same as those of the corresponding real microstructure images. Obtain multiple sets of initial water quality parameters; Each set of initial water quality parameters is used as boundary conditions to input into a pre-constructed microbial reaction kinetic model for solution, thereby obtaining the target gas generation rate and extracellular polymer generation rate under the corresponding initial water quality parameter conditions. Based on preset association rules, at least one set of target initial water quality parameters is determined for each set of real water quality parameters in the water quality parameter sequence data. The key feature parameters of each target initial water quality parameter are the same as the key feature parameters of the corresponding real water quality parameters. The target gas generation rate and extracellular polymer generation rate of each group of real water quality parameters are compared with the target gas generation rate and extracellular polymer generation rate of the corresponding initial water quality parameters to determine the first deviation value of the target gas generation rate and the second deviation value of the extracellular polymer generation rate. Among multiple sets of target initial water quality parameters, the target initial water quality parameters whose corresponding first deviation value and / or second deviation value are greater than the preset threshold are removed to obtain multiple sets of effective water quality parameter data.

5. The method according to claim 4, characterized in that, The process involves associating multiple effective water quality parameters, multiple sets of effective feature parameters (standard gas generation rate, extracellular polymer generation rate), and multiple virtual microstructure images based on preset association rules to obtain an associated dataset, including: Based on the key feature parameters of multiple sets of effective water quality parameters and the key feature parameters of multiple virtual microstructure images, the virtual microstructure images corresponding to each set of effective water quality parameters are determined. Based on the virtual microstructure images corresponding to each set of effective water quality parameters, the standard gas generation rate and extracellular polymer generation rate of multiple effective water quality parameters and multiple sets of effective feature parameters are correlated with the multiple virtual microstructure images to obtain a correlated dataset.

6. The method according to claim 4, characterized in that, The acquisition of multiple sets of initial water quality parameters includes: Obtain typical water quality parameter range data; The typical water quality parameter range data were uniformly sampled to obtain multiple sets of initial water quality parameters.

7. A device for predicting the porosity of wastewater sediment aggregates, characterized in that, The device includes: The acquisition module is used to acquire the measured water quality parameters of the sewage in the target sewage pipeline, the target gas generation rate, and the target extracellular polymer generation rate of the sewage sediment aggregates; The first determining module is used to input the measured water quality parameters of the sewage in the target sewage pipeline, the target gas generation rate, and the target extracellular polymer generation rate into a pre-constructed sedimentation aggregate microstructure prediction model, so that the sedimentation aggregate microstructure prediction model outputs a target microstructure image of the sewage sedimentation aggregate in the target sewage pipeline. The sedimentation aggregate microstructure prediction model is used to characterize the correlation between the water quality parameters of the sewage, the target gas generation rate, the extracellular polymer generation rate, and the microstructure image of the sewage sedimentation aggregate. The second determining module is used to determine the target porosity of deposited aggregates in the target sewage pipe based on the target microstructure image.

8. An electronic device, characterized in that, include: A memory and a processor are communicatively connected, the memory storing computer instructions, and the processor executing the computer instructions to perform the wastewater sediment porosity prediction method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to execute the wastewater sediment porosity prediction method according to any one of claims 1 to 6.

10. A computer program product, characterized in that, Includes computer instructions for causing a computer to perform the wastewater sediment porosity prediction method according to any one of claims 1 to 6.

Images