Sewage treatment effect evaluation method and system based on data analysis

Abstract

The invention relates to the technical field of sewage treatment, in particular to a sewage treatment effect assessment method and system based on data analysis, which improve the quality of sewage treatment effect assessment and realize accurate assessment of sewage treatment effect. The method comprises the following steps: acquiring biochemical data information of a water quality sample before and after sewage treatment and microscopic image information of the water quality sample after sewage treatment; performing water quality biochemical feature extraction on the water quality sample biochemical data information before and after sewage treatment, and calculating to obtain water quality biochemical feature change vectors before and after sewage treatment; inputting the water quality biochemical characteristic change vector into a water quality treatment biochemical effect evaluation model to obtain a first-order sewage treatment effect evaluation result; performing water quality image feature extraction on the water quality sample microscopic image information after sewage treatment to obtain a water quality image feature set; and aiming at each water quality image feature in the water quality image feature set, respectively comparing with a corresponding preset image feature.

Description

Technical Field

[0001] The present invention relates to the technical field of sewage treatment, and in particular to a sewage treatment effect evaluation method and system based on data analysis. Background Art

[0002] With the acceleration of industrialization and the continuous growth of population, water resources are facing unprecedented pressure, among which the problem of sewage discharge and treatment is particularly prominent; sewage without effective treatment is directly discharged into the natural environment, which will seriously pollute water sources, soil and air, destroy the balance of the ecosystem, affect biodiversity, and thus threaten human drinking water safety, agricultural production and living environment. Sewage treatment is an important measure to maintain ecological balance and protect human health, and its effect evaluation is particularly important.

[0003] Traditional sewage treatment effect evaluation methods often rely on the monitoring of a single water quality indicator, such as the detection of biochemical parameters such as chemical oxygen demand (COD) and ammonia nitrogen (NH3-N). Although this method can reflect the changes in the concentration of some pollutants in sewage, it is difficult to comprehensively and intuitively reflect the multi-dimensional improvement of water quality during sewage treatment, especially the changes in complex water quality characteristics such as microbial community structure and suspended matter morphology. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a sewage treatment effect evaluation method and system based on data analysis, which improves the quality of sewage treatment effect evaluation and realizes accurate evaluation of sewage treatment effect.

[0005] In a first aspect, the present invention provides a method for evaluating the effect of sewage treatment based on data analysis, the method comprising:

[0006] Obtain biochemical data information of water quality samples before and after sewage treatment and microscopic image information of water quality samples after sewage treatment;

[0007] Extract water quality biochemical characteristics from the biochemical data of water quality samples before and after sewage treatment, and calculate the change vector of water quality biochemical characteristics before and after sewage treatment;

[0008] The water quality biochemical characteristic change vector is input into the water quality treatment biochemical effect evaluation model to obtain the first-order sewage treatment effect evaluation result;

[0009] Extract water quality image features from the microscopic image information of the water quality samples after sewage treatment to obtain a water quality image feature set;

[0010] Each water quality image feature in the water quality image feature set is compared with the corresponding preset image feature. If each water quality image feature meets the preset image feature, the first-order sewage treatment effect evaluation result is output as the final evaluation result; if there is a water quality image feature that does not meet the preset image feature, the water quality image features that do not meet the preset image feature are summarized to obtain a water quality abnormal image feature set;

[0011] The water quality abnormal image feature set and the water quality biochemical feature change vector are taken as input and input into the treatment effect abnormality analysis model to obtain the second-order sewage treatment effect evaluation result, and the second-order sewage treatment effect evaluation result is output as the final evaluation result.

[0012] Furthermore, the water quality biochemical characteristic change vector is:

[0013] V=[Δx1,Δx2,..,Δx n ]

[0014] Among them, V represents the change vector of water quality biochemical characteristics, Δx n Represents the change in the nth biochemical index before and after treatment.

[0015] Furthermore, the method for obtaining the water quality biochemical characteristic change vector before and after sewage treatment includes:

[0016] Clean the biochemical data of water quality samples before and after sewage treatment to remove invalid values ​​and outliers;

[0017] Select features from the collected biochemical parameters according to the wastewater treatment goals and assessment needs;

[0018] For the selected features, further extract the transformation and highlight its change characteristics;

[0019] For each selected feature, its change before and after sewage treatment is calculated;

[0020] The changes of all characteristic parameters are combined in order into a vector, namely the water quality biochemical characteristic change vector.

[0021] Furthermore, the method for constructing the water quality treatment biochemical effect evaluation model comprises:

[0022] Collect water quality biochemical data, including biochemical characteristics before and after sewage treatment;

[0023] Preprocess the collected data, including data cleaning, data standardization and normalization;

[0024] Selecting a machine learning model as the basic framework of the water quality treatment biochemical effect evaluation model, wherein the machine learning model includes linear regression, support vector machine, decision tree, random forest and neural network;

[0025] The collected data is divided into a training set and a validation set. The training set is used to train the model, and the validation set is used to adjust the model parameters and evaluate the model performance.

[0026] Use the training set data to train the selected model and adjust the model parameters to optimize model performance;

[0027] Cross-validation techniques were used to evaluate the generalization ability of the model;

[0028] Deploy the trained water quality treatment biochemical effect evaluation model into the system.

[0029] Furthermore, the method for acquiring the water quality image feature set includes:

[0030] Performing image correction on the microscopic image information of the water quality sample, the correction steps include brightness contrast adjustment, color correction and noise removal;

[0031] The background and foreground in the image are separated by threshold segmentation and edge detection, highlighting the target object in the water sample;

[0032] Perform feature extraction on the image to extract texture features, shape features, color features and structural features;

[0033] The extracted features are combined to form a complete water quality image feature set.

[0034] Furthermore, the influencing factors for setting the preset image features include microbial community structure, the morphology, color and transparency of suspended particles, flocculent stock, foam content and image texture features.

[0035] Furthermore, the method for constructing the abnormal analysis model of governance effect includes:

[0036] Collect data on abnormal sewage treatment effects and pre-process the data, including data cleaning, feature selection and data standardization;

[0037] Divide the processed data into training set and test set;

[0038] Selecting a machine learning model as the infrastructure of the governance effect anomaly analysis model, wherein the machine learning model includes a support vector machine, a random forest, and a neural network;

[0039] Use the training set to train the model to ensure the generalization ability of the model;

[0040] Adjust the model's hyperparameters through cross-validation methods to optimize model performance;

[0041] Use the test set to evaluate the performance of the model and verify the effectiveness and reliability of the model;

[0042] Once the model is trained, it is deployed to actual applications.

[0043] On the other hand, the present application also provides a sewage treatment effect evaluation system based on data analysis, the system comprising:

[0044] The sample data acquisition module obtains the biochemical data information of water quality samples before and after sewage treatment and the microscopic image information of water quality samples after sewage treatment;

[0045] The biochemical feature extraction module extracts the biochemical features of the water quality samples before and after the sewage treatment, and calculates the change vector of the water quality biochemical features before and after the sewage treatment;

[0046] The first-order sewage treatment effect evaluation module inputs the water quality biochemical characteristic change vector into the water quality treatment biochemical effect evaluation model to obtain the first-order sewage treatment effect evaluation result;

[0047] An image feature extraction module extracts water quality image features from the microscopic image information of the water quality sample after sewage treatment to obtain a water quality image feature set;

[0048] The image feature comparison module compares each water quality image feature in the water quality image feature set with the corresponding preset image feature. If each water quality image feature meets the preset image feature, the first-order sewage treatment effect evaluation result is output as the final evaluation result; if there are water quality image features that do not meet the preset image features, the water quality image features that do not meet the preset image features are summarized to obtain a water quality abnormal image feature set;

[0049] The anomaly analysis and result output module takes the water quality anomaly image feature set and the water quality biochemical feature change vector as input, inputs them into the treatment effect anomaly analysis model, obtains the second-order sewage treatment effect evaluation result, and outputs the second-order sewage treatment effect evaluation result as the final evaluation result.

[0050] In a third aspect, the present application provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and the computer program, when executed by the processor, implements the steps of any one of the above methods.

[0051] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps in any one of the above-mentioned methods when executed by a processor.

[0052] Compared with the prior art, the present invention has the following beneficial effects: the method not only takes into account the changes in traditional biochemical parameters, but also combines the microscopic image information of water quality samples to achieve a multi-dimensional assessment of water quality; it can more comprehensively and meticulously reflect the improvement of water quality during sewage treatment, including changes in complex characteristics such as microbial community structure and suspended matter morphology, thereby providing more accurate and comprehensive assessment results;

[0053] By extracting and comparing microscopic image information, this method can intuitively display changes in water quality in the form of images, making the evaluation results easier to understand and accept, and helping managers and the public to more intuitively understand the effects of sewage treatment.

[0054] The entire evaluation process involves steps such as automatic data collection, automatic feature extraction, and automatic model evaluation, which realizes the intelligentization and automation of the evaluation work; greatly improves the efficiency and accuracy of the evaluation, reduces the interference of human factors, and makes the evaluation results more objective and reliable;

[0055] This method can identify water quality image features that do not meet the preset image features, and summarize and analyze them as anomalies; it helps to quickly discover problems and bottlenecks in the treatment process, and conduct in-depth analysis through the treatment effect anomaly analysis model to find out the causes and solutions of the problems;

[0056] This method has good flexibility and scalability. With the continuous advancement of sewage treatment technology and the continuous changes in assessment needs, the assessment model can be easily adjusted and optimized to adapt to new assessment standards and requirements. At the same time, more water quality parameters and image features can be included in the assessment scope to further improve the comprehensiveness and accuracy of the assessment.

[0057] Through regular evaluation and analysis, this method can provide strong support for sewage treatment work; the evaluation results can serve as an important reference for treatment effects, helping managers understand the progress and effectiveness of treatment work, and timely adjust and optimize treatment strategies to ensure continuous improvement of treatment effects; at the same time, it also provides important data support and basis for the improvement and innovation of treatment technology;

[0058] In summary, this method improves the quality of sewage treatment effect evaluation by comprehensively using multiple data sources and analysis methods, realizes accurate evaluation of sewage treatment effects, ensures that water quality restoration meets environmental protection standards, and protects the ecological environment and human health. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 is a flow chart of the present invention;

[0060] Figure 2 It is a flowchart of the method for constructing a governance effect anomaly analysis model;

[0061] Figure 3 It is a structural diagram of the sewage treatment effect evaluation system based on data analysis. DETAILED DESCRIPTION

[0062] In the description of the present application, those skilled in the art should know that the present application can be implemented as a method, an apparatus, an electronic device, and a computer-readable storage medium. Therefore, the present application can be specifically implemented in the following forms: complete hardware, complete software (including firmware, resident software, microcode, etc.), a combination of hardware and software. In addition, in some embodiments, the present application can also be implemented in the form of a computer program product in one or more computer-readable storage media, and the computer-readable storage medium contains computer program code.

[0063] The above-mentioned computer-readable storage medium may adopt any combination of one or more computer-readable storage media. Computer-readable storage media include: electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media include: portable computer disks, hard disks, random access memories, read-only memories, erasable programmable read-only memories, flash memories, optical fibers, optical disc read-only memories, optical storage devices, magnetic storage devices, or any combination of the above. In the present application, computer-readable storage media can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or device.

[0064] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws.

[0065] The present application describes the provided methods, devices, and electronic devices through flowcharts and / or block diagrams.

[0066] It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer-readable program instructions. These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine, and these computer-readable program instructions are executed by a computer or other programmable data processing device to produce a device that implements the functions / operations specified by the boxes in the flowchart and / or block diagram.

[0067] These computer-readable program instructions may also be stored in a computer-readable storage medium that enables a computer or other programmable data processing device to work in a specific manner. In this way, the instructions stored in the computer-readable storage medium produce an instruction device product including functions / operations specified in the blocks in the flowchart and / or block diagram.

[0068] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby enabling the instructions executed on the computer or other programmable data processing apparatus to provide a process for implementing the functions / operations specified in the blocks in the flowchart and / or block diagram.

[0069] The present application is described below in conjunction with the drawings in the present application.

[0070] Embodiment 1: Figure 1 to Figure 2 As shown, the sewage treatment effect evaluation method based on data analysis of the present invention specifically includes the following steps:

[0071] S1. Obtain biochemical data information of water quality samples before and after sewage treatment and microscopic image information of water quality samples after sewage treatment;

[0072] The method for obtaining biochemical data information of water quality samples before and after sewage treatment and microscopic image information of water quality samples after sewage treatment includes:

[0073] Select representative sampling points, including the inlet before sewage treatment and the outlet after treatment. The selection of sampling points should take into account the actual situation of the sewage treatment system;

[0074] Determine the appropriate sampling frequency based on the load of the sewage treatment facility and the changes in sewage quality;

[0075] Use appropriate sampling equipment to ensure that the sample is representative; avoid cross contamination when sampling, and process and store the sample in a timely manner after sampling;

[0076] Using standardized laboratory analysis methods to detect biochemical indicators and obtain biochemical data information, the biochemical data information includes chemical oxygen demand, ammonia nitrogen, suspended solids, total phosphorus and total nitrogen;

[0077] Pre-treat the collected sewage samples to remove large particles of impurities and make the samples suitable for microscopic observation;

[0078] Stain the sample as needed to enhance the features in the sample for easier observation and analysis;

[0079] Use a microscope for observation. Common microscopes include optical microscopes, scanning electron microscopes, and transmission electron microscopes. Choose the appropriate microscope type and magnification according to the observation target.

[0080] Observe the sample under a microscope and use digital image acquisition equipment to obtain high-resolution microscopic images that cover representative areas of the sample for subsequent analysis;

[0081] Chemical oxygen demand reflects the content of organic matter in sewage and is usually determined by chemical oxidation method;

[0082] Ammonia nitrogen refers to the concentration of ammonia in wastewater, which is determined by distillation or ion-selective electrode method;

[0083] Total phosphorus and total nitrogen reflect the phosphorus and nitrogen content in sewage respectively, which involves the problem of eutrophication of water bodies;

[0084] The content of suspended matter affects the sedimentation and turbidity of water.

[0085] In this step, by selecting representative sampling points and considering the actual situation of the sewage treatment system, the comprehensiveness and representativeness of the collected samples are ensured; at the same time, standardized laboratory analysis methods are used for biochemical index detection to ensure the accuracy of biochemical data information, providing a solid foundation for subsequent analysis and evaluation; biochemical data information covers multiple key indicators such as chemical oxygen demand, ammonia nitrogen, suspended solids, total phosphorus and total nitrogen, which can comprehensively reflect the concentration changes of organic pollutants, nitrogen and phosphorus nutrients and other substances in sewage; and microscopic image information provides an intuitive display of complex water quality characteristics such as microbial community structure and suspended solids morphology in water quality samples, which helps to have a more comprehensive understanding of the sewage treatment effect; during the sampling process, Attention was paid to avoid cross contamination, and timely processing and preservation were performed after sampling to ensure the originality and reliability of the samples; at the same time, the use of appropriate microscopes and digital image acquisition equipment to obtain high-resolution microscopic images further improved the scientificity and reliability of image information, providing strong support for subsequent image feature extraction and comparison analysis; the biochemical data information and microscopic image information obtained through the S1 step provided a rich data source for the subsequent water quality biochemical feature extraction, water quality image feature extraction, and the construction of a treatment effect evaluation model; these data sources will support us in more in-depth analysis of the water quality change patterns and treatment effects in the sewage treatment process, and provide a strong basis for optimizing sewage treatment processes and formulating scientific treatment strategies.

[0086] S2. Extracting water quality biochemical characteristics from the biochemical data information of water quality samples before and after sewage treatment, and calculating the water quality biochemical characteristic change vector before and after sewage treatment;

[0087] The method for obtaining the water quality biochemical characteristic change vector before and after sewage treatment includes:

[0088] Clean the biochemical data of water quality samples before and after sewage treatment to remove invalid values ​​and outliers to ensure data quality; erroneous and inaccurate data will affect the accuracy of subsequent analysis;

[0089] Select key features from the collected biochemical parameters according to the wastewater treatment goals and assessment requirements;

[0090] For the selected features, further extraction or transformation is performed to highlight their changing characteristics;

[0091] For each selected feature, calculate its change before and after sewage treatment; subtract the value before treatment from the value after treatment to obtain the change. For some parameters, the calculation of the change needs to consider its nonlinear characteristics;

[0092] The changes of all characteristic parameters are combined into a vector in order, namely, the water quality biochemical characteristic change vector; each element of this vector corresponds to the change of a characteristic parameter, reflecting the change of this parameter during the sewage treatment process;

[0093] In order to eliminate the differences in magnitude of changes in different characteristic parameters, the change vectors are standardized;

[0094] The constructed water quality biochemical characteristic change vector is used as the output. The water quality biochemical characteristic change vector is an important basis for evaluating the effect of sewage treatment and can comprehensively reflect the improvement of sewage in multiple biochemical parameters.

[0095] The water quality biochemical characteristic change vector is:

[0096] V=[Δx1,Δx2,..,Δx n ]

[0097] Among them, V represents the change vector of water quality biochemical characteristics, Δx n It indicates the change of the nth biochemical index before and after treatment;

[0098] In this step, the biochemical data information of water quality samples before and after sewage treatment is cleaned to remove invalid values ​​and outliers, ensuring the data quality relied on by subsequent analysis and ensuring the basis for the accuracy and reliability of the evaluation results; according to the goals and evaluation needs of sewage treatment, key features are carefully selected from a large number of biochemical parameters, which not only reduces the complexity of data processing, but also improves the efficiency and accuracy of the evaluation, so that the evaluation results are more focused on key indicators; the selected features are further extracted or converted to highlight their changing characteristics; this helps to more clearly show the changing trends and degrees of various parameters in the sewage treatment process, providing a more intuitive and powerful basis for evaluating the sewage treatment effect; by calculating the change in each selected feature before and after sewage treatment, a quantitative evaluation of the sewage treatment effect is achieved; this quantitative evaluation method not only It is objective, accurate, and convenient for comparison and optimization of different treatment schemes; the changes of all characteristic parameters are combined into a water quality biochemical characteristic change vector, which comprehensively reflects the improvement of sewage in multiple biochemical parameters; it can more comprehensively reveal the effect of sewage treatment and avoid the one-sidedness that may be caused by single indicator evaluation; the change vector is standardized to eliminate the difference in magnitude of the changes of different characteristic parameters, making the comparison between different parameters more fair and accurate; it helps to improve the comparability and scientificity of the evaluation results; the constructed water quality biochemical characteristic change vector is used as an important basis for evaluating the effect of sewage treatment, and provides comprehensive and accurate data support for subsequent evaluation models; this evaluation method based on data analysis not only improves the accuracy and reliability of the evaluation, but also provides strong data support for the optimization and improvement of sewage treatment schemes.

[0099] S3, inputting the water quality biochemical characteristic change vector into the water quality treatment biochemical effect evaluation model to obtain the first-order sewage treatment effect evaluation result;

[0100] The method for constructing the water quality treatment biochemical effect evaluation model comprises:

[0101] Collect water quality biochemical data, including biochemical characteristics before and after sewage treatment, from different types of sewage treatment facilities to increase the generalization ability of the model;

[0102] Preprocess the collected data, including data cleaning, data standardization and normalization, to ensure data consistency and comparability;

[0103] Selecting a machine learning model as the basic framework of the water quality treatment biochemical effect evaluation model, wherein the machine learning model includes linear regression, support vector machine, decision tree, random forest and neural network;

[0104] The collected data is divided into a training set and a validation set. The training set is used to train the model, and the validation set is used to adjust model parameters and evaluate model performance.

[0105] Use the training set data to train the selected model and adjust the model parameters to optimize model performance;

[0106] Use cross-validation techniques to evaluate the generalization ability of the model to ensure that the model not only performs well on the training data, but also gives reliable predictions on unseen data;

[0107] Deploy the trained water quality treatment biochemical effect evaluation model into the system;

[0108] The biochemical characteristic change vector is input into the trained model, and the model outputs the first-order sewage treatment effect evaluation result.

[0109] In this step, by collecting water quality biochemical data from different types of sewage treatment facilities, the model can learn a wider and more comprehensive range of water quality change characteristics, thereby improving the accuracy and comprehensiveness of the evaluation results; it helps to more realistically reflect the actual effect of sewage treatment; compared with the traditional single water quality indicator monitoring method, this method uses a machine learning model to conduct a comprehensive analysis of the water quality biochemical characteristic change vector, which can capture multi-dimensional information on water quality improvement, including pollutant removal efficiency, water quality indicator improvement, and changes in microbial community structure, providing a more comprehensive evaluation perspective for sewage treatment effects; through data preprocessing and selecting a variety of machine learning models for training, the model has a strong generalization ability; this means that the model can not only perform well on training data, but also perform reliably on unseen data. Relying on prediction, the applicability and reliability of the evaluation results are improved; once the model training is completed and deployed to the system, it can automatically receive the water quality biochemical characteristic change vector as input and quickly output the first-order sewage treatment effect evaluation result; this greatly improves the efficiency and automation of the evaluation work, and reduces the impact of human intervention and subjective judgment; the evaluation results can provide a scientific basis for decision-making and optimization of sewage treatment work; by understanding the actual effects and existing problems of sewage treatment, timely adjust the treatment strategies and technical means to further improve the efficiency and effect of sewage treatment; the application of this method promotes technological innovation and development in the field of sewage treatment; by continuously collecting new data and optimizing model algorithms, it can promote the continuous advancement and improvement of sewage treatment technology and make greater contributions to the protection and sustainable utilization of water resources.

[0110] S4, extracting water quality image features from the microscopic image information of the water quality sample after sewage treatment to obtain a water quality image feature set;

[0111] The method for acquiring the water quality image feature set comprises:

[0112] The images taken by the microscope may be affected by factors such as light source and focus, so it is necessary to perform image correction on the microscopic image information of the water quality sample. The correction steps include brightness contrast adjustment, color correction and noise removal to ensure the consistency and high quality of the image;

[0113] The background and foreground in the image are separated by threshold segmentation and edge detection to highlight the target object in the water sample;

[0114] Extract features from images, including texture features, shape features, color features, and structural features; extract texture features from images, including the roughness and uniformity of particles, which can help identify different substances in water quality; extract shape features of particles or microorganisms, such as size, aspect ratio, roundness, etc., which help identify different types of microorganisms or suspended matter in water samples; for color images, extract color features, which help distinguish different types of substances; analyze the structure of microbial communities or the spatial distribution of suspended matter, which can provide information about biological activities or the distribution of pollutants in water quality;

[0115] The various features extracted above are combined to form a complete water quality image feature set; the water quality image feature set can comprehensively describe the microscopic characteristics of water quality samples.

[0116] In this step, through image feature extraction, multi-dimensional information such as texture, shape, color and structure in water quality samples can be captured, so as to more comprehensively evaluate the water quality status; the image correction step ensures the consistency and high quality of the image, and reduces the influence of factors such as light source and focus on the evaluation results; at the same time, through image processing technologies such as threshold segmentation and edge detection, the target objects in the water sample can be more accurately identified, and the precision and accuracy of feature extraction are improved; through the analysis of the water quality image feature set, abnormal changes in water quality can be discovered in time, and these abnormal changes are often precursors to water quality deterioration, so it is helpful to achieve early warning and diagnosis, and provide a scientific basis for timely taking treatment measures; the water quality image feature set provides rich data support for the evaluation of sewage treatment effects; by comparing the changes in water quality image features under different treatment schemes, the treatment effects of different schemes can be evaluated, providing a strong basis for formulating and optimizing sewage treatment strategies; with the continuous development of image processing technology and machine learning algorithms, the method of water quality image feature extraction is also constantly innovating and improving; the implementation of this step not only promotes technological innovation in the field of sewage treatment, but also provides new ideas and methods for research and application in related fields.

[0117] S5. For each water quality image feature in the water quality image feature set, compare it with the corresponding preset image feature. If each water quality image feature meets the preset image feature, the first-order sewage treatment effect evaluation result is output as the final evaluation result; if there is a water quality image feature that does not meet the preset image feature, the water quality image features that do not meet the preset image feature are summarized to obtain a water quality abnormal image feature set;

[0118] In order to perform effective comparison, it is necessary to first establish preset image features. The method for obtaining the preset image features includes:

[0119] Collect a large number of microscopic image samples from known, verified areas of high water quality;

[0120] After collecting enough samples, image processing technology is used to extract key features of these images; these features include the number and type of microorganisms, the size and shape of suspended particles, color, and texture;

[0121] Standardize the extracted features, including normalizing feature values, removing noise, and correcting brightness and contrast to facilitate subsequent analysis and comparison;

[0122] The processed feature information is stored in a database, which contains various microscopic image features of water quality samples under ideal conditions, namely, preset image features;

[0123] The factors affecting the setting of the preset image features include:

[0124] Microbial community structure: Healthy water bodies usually have a certain proportion and diversity of microbial communities; the preset image features should include the types, quantity, distribution density and interactions of these microorganisms;

[0125] Morphology of suspended particles: The preset features should include a morphological description of the particles, including the size distribution range, shape, and transparency of the particles;

[0126] Color and transparency: The color and transparency of water can reflect the content of dissolved substances in the water; good water quality is usually manifested by higher transparency, less suspended matter, and natural water color;

[0127] Floc stock: Flocs are large particles formed by the aggregation of colloidal substances in water. In the effective sewage treatment process, the formation of flocs helps to remove suspended matter and pollutants in water. The preset image features should take into account the size, density and distribution of flocs.

[0128] Foam content: When a large amount of surfactant is present, there will be a certain amount of foam in the water. The preset characteristics should consider whether there are abnormal bubbles or foam phenomena;

[0129] Image texture features: The overall texture features of the image can also provide additional information about water quality; good water quality usually shows a relatively uniform texture, while heavily polluted water may show complex texture patterns.

[0130] In this step, by combining the comparison of water quality image features, this step can comprehensively and intuitively reflect the improvement of water quality after sewage treatment; compared with the monitoring of single water quality biochemical indicators, image features can capture more dimensional changes in water quality, thereby providing more comprehensive evaluation results; the establishment of preset image features is based on a large number of verified microscopic image samples of high-quality water quality areas, and key features are extracted through image processing technology to ensure the accuracy and reliability of the comparison benchmark; reduce the subjectivity of human judgment and improve the accuracy of the evaluation results; in the comparison process, once it is found that the water quality image features do not match the preset image features, they can be quickly It can quickly identify water quality anomalies and summarize these anomaly features into a water quality anomaly image feature set; it helps to quickly locate the root cause of the problem and take targeted measures to improve it; the output results of this step provide strong data support for decision makers; whether it is directly using the first-order evaluation results as the final conclusion or further refining the evaluation through second-order analysis, it can provide a scientific basis for the optimization, adjustment and implementation of sewage treatment plans; this step uses a scientific and comprehensive water quality image feature comparison method to not only improve the accuracy and intuitiveness of sewage treatment effect evaluation, but also provide strong support for subsequent problem diagnosis, decision support and technological progress.

[0131] S6. Taking the water quality abnormal image feature set and the water quality biochemical feature change vector as input, inputting them into the treatment effect abnormality analysis model, obtaining the second-order sewage treatment effect evaluation result, and outputting the second-order sewage treatment effect evaluation result as the final evaluation result;

[0132] The method for constructing the abnormal analysis model of governance effect includes:

[0133] Collect a large amount of data on abnormal sewage treatment effects and pre-process the data, including data cleaning, feature selection and data standardization;

[0134] Divide the processed data into training set and test set;

[0135] Selecting a machine learning model as the infrastructure of the governance effect anomaly analysis model, wherein the machine learning model includes a support vector machine, a random forest, and a neural network;

[0136] Use the training set to train the model. In this process, the model learns how to predict whether the processing effect is normal based on the input features to ensure the generalization ability of the model.

[0137] Adjust the model's hyperparameters through cross-validation methods to find the best model configuration and optimize model performance so that it can perform well on new data;

[0138] Use the test set to evaluate the performance of the model. Evaluation indicators include accuracy, recall, F1 score, etc. to verify the effectiveness and reliability of the model.

[0139] Once the model is trained, it is deployed in real-time or batch analysis of water quality treatment effects.

[0140] In this step, the treatment effect abnormality analysis model not only takes into account the traditional changes in water quality biochemical characteristics, but also incorporates water quality image characteristics, realizing a multi-dimensional comprehensive evaluation of sewage treatment effects, and can capture subtle changes that are difficult to detect with traditional methods, thereby improving the accuracy and reliability of the evaluation. By learning and analyzing a large amount of data on abnormal sewage treatment effects, the model can automatically identify and diagnose problems in the treatment process. When it is found that abnormal water quality image characteristics or biochemical characteristic changes do not meet expectations, the model can respond quickly and provide strong support for subsequent improvement measures. Traditional sewage treatment effect evaluation often requires manual participation, which is time-consuming, labor-intensive, and easily affected by subjective factors. The treatment effect abnormality analysis model based on data analysis can be automated. Evaluation greatly improves decision-making efficiency; decision makers can make quick judgments based on the evaluation results of the model and take corresponding treatment measures; the application of the model is not limited to a single evaluation, but can also be used as a tool for continuous improvement; by continuously collecting new data and retraining the model, the performance of the model is continuously optimized, and its ability to identify abnormal sewage treatment effects and its prediction accuracy are improved; this continuous improvement mechanism helps to promote the continuous advancement of sewage treatment technology; through open and transparent sewage treatment effect evaluation results, the public's awareness and participation in environmental protection can be enhanced; when the public sees that sewage treatment has achieved remarkable results, they will be more supportive of and actively participate in environmental protection actions; and when it is found that the treatment effect is not good, it will also urge the relevant departments to take timely measures to improve it.

[0141] Embodiment 2: Figure 3 As shown, the sewage treatment effect evaluation system based on data analysis of the present invention specifically includes the following modules:

[0142] The sample data acquisition module obtains the biochemical data information of water quality samples before and after sewage treatment and the microscopic image information of water quality samples after sewage treatment;

[0143] The biochemical feature extraction module extracts the biochemical features of the water quality samples before and after the sewage treatment, and calculates the change vector of the water quality biochemical features before and after the sewage treatment;

[0144] The first-order sewage treatment effect evaluation module inputs the water quality biochemical characteristic change vector into the water quality treatment biochemical effect evaluation model to obtain the first-order sewage treatment effect evaluation result;

[0145] An image feature extraction module extracts water quality image features from the microscopic image information of the water quality sample after sewage treatment to obtain a water quality image feature set;

[0146] The image feature comparison module compares each water quality image feature in the water quality image feature set with the corresponding preset image feature. If each water quality image feature meets the preset image feature, the first-order sewage treatment effect evaluation result is output as the final evaluation result; if there are water quality image features that do not meet the preset image features, the water quality image features that do not meet the preset image features are summarized to obtain a water quality abnormal image feature set;

[0147] The anomaly analysis and result output module takes the water quality anomaly image feature set and the water quality biochemical feature change vector as input, inputs them into the treatment effect anomaly analysis model, obtains the second-order sewage treatment effect evaluation result, and outputs the second-order sewage treatment effect evaluation result as the final evaluation result.

[0148] The system not only relies on traditional biochemical parameters for effect evaluation, but also combines microscopic image information of water quality samples; this multi-dimensional method can more comprehensively and intuitively reflect the improvement of water quality, including changes in complex water quality characteristics such as microbial community structure and suspended matter morphology, thereby providing more accurate evaluation results; through automated collection of sample data, feature extraction, comparative analysis and output of results, the system greatly improves the efficiency and accuracy of the evaluation and reduces interference from human factors; at the same time, the use of machine learning or deep learning models for intelligent analysis makes the evaluation process more scientific and objective; the system can collect and process data in real time, promptly reflect changes in water quality during sewage treatment, and provide managers with timely decision-making support; in addition, through continuous monitoring, it can dynamically evaluate the treatment effect, and The system can adjust the treatment strategy in time to ensure the continuous optimization of the treatment effect; when it is found that the water quality image features do not meet the preset standards, the system can accurately identify the abnormal features and further analyze the reasons through the abnormal analysis model, provide specific guidance for the optimization of the treatment plan, and help to quickly solve the problems in the treatment process and improve the treatment efficiency; through detailed evaluation reports and visual displays, the system makes the evaluation process of sewage treatment effects more transparent, which helps to enhance the public's trust and support for the treatment work; at the same time, it also provides effective supervision means for the regulatory authorities to ensure that the treatment work meets the relevant standards and requirements; the application of the system has promoted technological innovation and upgrading in the field of sewage treatment, promoted the development and application of related technologies, and provided more advanced and efficient solutions for future sewage treatment work;

[0149] In summary, the system provides new ideas and technical means for the evaluation of sewage treatment effects, which helps to improve the accuracy and efficiency of the evaluation, realize accurate evaluation of sewage treatment effects, ensure that water quality restoration meets environmental protection standards, and protect the ecological environment and human health.

[0150] The various variations and specific embodiments of the sewage treatment effect evaluation method based on data analysis in the aforementioned embodiment 1 are also applicable to the sewage treatment effect evaluation system based on data analysis in this embodiment. Through the aforementioned detailed description of the sewage treatment effect evaluation method based on data analysis, technical personnel in this field can clearly know the implementation method of the sewage treatment effect evaluation system based on data analysis in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.

[0151] In addition, the present application also provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor. The transceiver, the memory, and the processor are respectively connected via a bus. When the computer program is executed by the processor, each process of the above-mentioned method for controlling output data is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0152] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for evaluating the effect of sewage treatment based on data analysis, characterized in that: The method comprises: Obtain biochemical data information of water quality samples before and after sewage treatment and microscopic image information of water quality samples after sewage treatment; Extract water quality biochemical characteristics from the biochemical data of water quality samples before and after sewage treatment, and calculate the change vector of water quality biochemical characteristics before and after sewage treatment; The water quality biochemical characteristic change vector is input into the water quality treatment biochemical effect evaluation model to obtain the first-order sewage treatment effect evaluation result; Extract water quality image features from the microscopic image information of the water quality samples after sewage treatment to obtain a water quality image feature set; Each water quality image feature in the water quality image feature set is compared with the corresponding preset image feature. If each water quality image feature meets the preset image feature, the first-order sewage treatment effect evaluation result is output as the final evaluation result; if there is a water quality image feature that does not meet the preset image feature, the water quality image features that do not meet the preset image feature are summarized to obtain a water quality abnormal image feature set; The water quality abnormal image feature set and the water quality biochemical feature change vector are taken as input and input into the treatment effect abnormality analysis model to obtain the second-order sewage treatment effect evaluation result, and the second-order sewage treatment effect evaluation result is output as the final evaluation result.

2. The method for evaluating the effect of sewage treatment based on data analysis according to claim 1, characterized in that: The water quality biochemical characteristic change vector is: V=[Δx1,Δx2,...,Δx n ] Among them, V represents the change vector of water quality biochemical characteristics, Δx n Represents the change of the nth biochemical index before and after treatment.

3. The method for evaluating the effect of sewage treatment based on data analysis according to claim 2, characterized in that: The method for obtaining the water quality biochemical characteristic change vector before and after sewage treatment includes: Clean the biochemical data of water quality samples before and after sewage treatment to remove invalid values ​​and outliers; Select features from the collected biochemical parameters according to the wastewater treatment goals and assessment needs; For the selected features, further extract the transformation and highlight its change characteristics; For each selected feature, its change before and after sewage treatment is calculated; The changes of all characteristic parameters are combined in order into a vector, namely the water quality biochemical characteristic change vector.

4. The method for evaluating the effect of sewage treatment based on data analysis according to claim 1, characterized in that: The method for constructing the water quality treatment biochemical effect evaluation model comprises: Collect water quality biochemical data, including biochemical characteristics before and after sewage treatment; Preprocess the collected data, including data cleaning, data standardization and normalization; Selecting a machine learning model as the basic framework of the water quality treatment biochemical effect evaluation model, wherein the machine learning model includes linear regression, support vector machine, decision tree, random forest and neural network; The collected data is divided into a training set and a validation set. The training set is used to train the model, and the validation set is used to adjust the model parameters and evaluate the model performance. Use the training set data to train the selected model and adjust the model parameters to optimize model performance; Cross-validation techniques were used to evaluate the generalization ability of the model; Deploy the trained water quality treatment biochemical effect evaluation model into the system.

5. The method for evaluating the effect of sewage treatment based on data analysis according to claim 1, characterized in that: The method for acquiring the water quality image feature set comprises: Performing image correction on the microscopic image information of the water quality sample, the correction steps include brightness contrast adjustment, color correction and noise removal; The background and foreground in the image are separated by threshold segmentation and edge detection, highlighting the target object in the water sample; Perform feature extraction on the image to extract texture features, shape features, color features and structural features; The extracted features are combined to form a complete water quality image feature set.

6. The method for evaluating the effect of sewage treatment based on data analysis according to claim 1, characterized in that: The influencing factors for setting the preset image features include microbial community structure, the morphology, color and transparency of suspended particles, flocculent stock, foam content and image texture features.

7. The method for evaluating the effect of sewage treatment based on data analysis according to claim 1, characterized in that: The method for constructing the abnormal analysis model of governance effect includes: Collect data on abnormal sewage treatment effects and pre-process the data, including data cleaning, feature selection and data standardization; Divide the processed data into training set and test set; Selecting a machine learning model as the infrastructure of the governance effect anomaly analysis model, wherein the machine learning model includes a support vector machine, a random forest, and a neural network; Use the training set to train the model to ensure the generalization ability of the model; Adjust the model's hyperparameters through cross-validation methods to optimize model performance; Use the test set to evaluate the performance of the model and verify the effectiveness and reliability of the model; Once the model is trained, it is deployed to actual applications.

8. A sewage treatment effect evaluation system based on data analysis, characterized in that: The system comprises: The sample data acquisition module obtains the biochemical data information of water quality samples before and after sewage treatment and the microscopic image information of water quality samples after sewage treatment; The biochemical feature extraction module extracts the biochemical features of the water quality samples before and after the sewage treatment, and calculates the change vector of the water quality biochemical features before and after the sewage treatment; The first-order sewage treatment effect evaluation module inputs the water quality biochemical characteristic change vector into the water quality treatment biochemical effect evaluation model to obtain the first-order sewage treatment effect evaluation result; An image feature extraction module extracts water quality image features from the microscopic image information of the water quality sample after sewage treatment to obtain a water quality image feature set; The image feature comparison module compares each water quality image feature in the water quality image feature set with the corresponding preset image feature. If each water quality image feature meets the preset image feature, the first-order sewage treatment effect evaluation result is output as the final evaluation result; if there are water quality image features that do not meet the preset image features, the water quality image features that do not meet the preset image features are summarized to obtain a water quality abnormal image feature set; The anomaly analysis and result output module takes the water quality anomaly image feature set and the water quality biochemical feature change vector as input, inputs them into the treatment effect anomaly analysis model, obtains the second-order sewage treatment effect evaluation result, and outputs the second-order sewage treatment effect evaluation result as the final evaluation result.

9. An electronic device for evaluating the effect of sewage treatment based on data analysis, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and characterized in that: When the computer program is executed by the processor, the steps in the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the method according to any one of claims 1 to 7 are implemented.

Images