Water source pollution risk assessment method and system based on microelectrolysis technology

Abstract

The invention discloses a water source pollution risk assessment method and system based on a micro-electrolysis technology, and relates to the technical field of data analysis, and the method comprises the steps: defining attributes reflecting data, dividing the reflecting data into two attributes of short-time-variant data and long-time-variant data, and providing a reliable basis for subsequent data preprocessing. An evaluation standard of each treatment stage is formulated according to wastewater source information, and a plurality of micro-electrolysis process simulation models are established, so that the evaluation standards are formulated. And the reflection data is correspondingly preprocessed according to the attributes of the reflection data, so that random errors and random fluctuations in the reflection data acquisition process are specifically reduced, the accuracy of the original data is improved, and the reliability of subsequent evaluation is ensured. On the evaluation standard of each processing stage, all types of reflection data are integrated to generate evaluation indexes, and the micro-electrolysis condition is comprehensively evaluated from multiple angles and under multiple dimensions of multiple processing stages, so that the water source pollution risk is evaluated, and the comprehensiveness and adaptability of water source pollution risk evaluation are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and particularly to a method and system for assessing the risk of water source pollution based on the microelectrolysis technology. Background Art

[0002] The background art of the water source pollution risk assessment scheme based on the microelectrolysis technology stems from the current increasingly severe situation of water source pollution and the limitations of traditional treatment technologies. With the acceleration of industrialization and urbanization, the pollution risks faced by water source areas are constantly increasing, and traditional treatment technologies are difficult to efficiently treat high-concentration and refractory organic pollutants. As a new water treatment technology, the microelectrolysis technology uses the nascent hydrogen and ferrous ions generated by the iron-carbon microelectrolysis reaction to effectively degrade pollutants through oxidation-reduction, adsorption and flocculation, etc., and improve water quality. This scheme aims to comprehensively evaluate the pollution risks of water source areas by introducing the microelectrolysis technology, including the types, concentrations, distributions and potential hazards of pollutants, etc., to provide technical support for formulating scientific and effective pollution control measures, ensuring the water quality safety of water source areas, and meeting people's urgent need for clean water resources.

[0003] In the prior art, the pollution risk of the wastewater source after microelectrolysis treatment is often only described by the water quality detection results, without considering the relevant situation of microelectrolysis treatment, resulting in low accuracy and adaptability of the water source pollution risk assessment and unable to effectively ensure environmental pollution safety.

[0004] Therefore, how to improve the accuracy and adaptability of the water source pollution risk assessment is a technical problem to be solved at present. Summary of the Invention

[0005] The purpose of the present invention is to solve the problem of low accuracy and adaptability in the assessment of the risk of water source pollution in the prior art, and to propose a method for assessing the risk of water source pollution based on the microelectrolysis technology. The method includes:

[0006] Dividing the microelectrolysis process into multiple treatment stages, identifying all the reaction data involved in each treatment stage, and defining the attributes of the reaction data;

[0007] Collecting wastewater source information, formulating evaluation criteria for each treatment stage according to the wastewater source information, performing microelectrolysis treatment on the wastewater source, and simultaneously collecting the reaction data generated during the microelectrolysis treatment process;

[0008] After the microelectrolysis is completed, perform corresponding preprocessing on the reaction data according to the attributes of the reaction data, and classify the reaction data from different perspectives;

[0009] Integrate all categories of reaction data to generate evaluation indicators based on the evaluation criteria of each treatment stage, so as to assess the pollution risk of the wastewater source after microelectrolysis.

[0010] In some embodiments of the present application, the treatment stage includes a primary battery formation stage, an electrochemical reaction stage, a pollutant removal stage, and a post-treatment stage.

[0011] In some embodiments of the present application, attributes reflecting data are defined, including

[0012] The reflected data involved in each treatment stage includes first reflected data and second reflected data. The first reflected data describes the treatment effect of the treatment stage, and the second reflected data describes the reaction conditions of the treatment stage;

[0013] Based on the first reflected data and the second reflected data, calculate the maximum information coefficient and the Pearson correlation coefficient between various reflected data, generate a correlation coefficient by combining the maximum information coefficient and the Pearson correlation coefficient, and screen the corresponding relationship of the reflected data according to the correlation coefficient, and record it as a set of strongly correlated reflected data;

[0014] Perform data standardization processing on the set of strongly correlated reflected data, calculate the covariance matrix, solve the eigenvalues of the covariance matrix, sort the eigenvalues by size, select the types of reflected data corresponding to the sizes of the first several eigenvalues as the principal components, and construct an electrochemical reaction stability index based on the principal components;

[0015] Obtain the historical reflected data of the microelectrolysis process, construct a reflected data timeline in chronological order, divide the reflected data timeline by virtue of the electrochemical reaction stability index, and define the attributes of each reflected data.

[0016] In some embodiments of the present application, divide the reflected data timeline by virtue of the electrochemical reaction stability index, and define the attributes of each reflected data, including

[0017] The attribute of the reflected data is short-time variable data or long-time variable data;

[0018] Calculate the electrochemical reaction stability index per time unit according to the principal components on the reflected data timeline, and divide the reflected data timeline into two parts: an electrochemical reaction stable timeline and an electrochemical reaction unstable timeline according to the electrochemical reaction stability index;

[0019] Set a variation threshold for each reflected data for both the electrochemical reaction stable timeline and the electrochemical reaction unstable timeline, calculate the coefficient of variation of each reflected data, compare the coefficient of variation of each reflected data with the variation threshold, and obtain a comparison result;

[0020] Integrate the comparison results of the electrochemical reaction stable timeline and the electrochemical reaction unstable timeline, and divide the attributes of each reflected data into short-time variable data or long-time variable data.

[0021] In some embodiments of the present application, evaluation criteria for each treatment stage are formulated according to wastewater source information, including

[0022] Multiple simulation models are established according to wastewater source information, and the multiple simulation models are integrated to describe the simulated micro-electrolysis process. Model parameter settings are performed to formulate evaluation criteria for the reflection data of each treatment stage.

[0023] In some embodiments of the present application, corresponding preprocessing is performed on the reflection data according to the attributes of the reflection data, including

[0024] For short-term variable data, a change curve of short-term variable data under the complete micro-electrolysis process is plotted, the data range size on the change curve of short-term variable data is statistically calculated, the change curve of short-term variable data is split into multiple curve segments according to the data range size, the multiple curve segments are arranged in chronological order, the slope change of each curve segment is calculated, a weakening factor of a smoothing index is confirmed according to the slope changes of all curve segments, and an exponentially weighted moving average is performed on the change curve of short-term variable data according to the weakening factor of the smoothing index to eliminate random fluctuations on the change curve of short-term variable data;

[0025] For long-term variable data, the first-order difference of the long-term variable data sequence is calculated, the difference between adjacent first-order differences of the long-term variable data sequence is calculated at a first preset interval to obtain a first-order difference change index. If the first-order difference change index is not lower than the change threshold, the complexity of the long-term variable data is mapped according to the first-order difference change index;

[0026] If the first-order difference change index is lower than the change threshold, the second-order difference of the long-term variable data sequence is calculated, the difference between adjacent second-order differences of the long-term variable data sequence is calculated at a second preset interval to obtain a second-order difference change index, and the complexity of the long-term variable data is mapped according to the second-order difference change index;

[0027] The order of the trend line is selected through the complexity of the long-term variable data, and the trend line of the long-term variable data sequence is fitted based on the order of the trend line to eliminate random errors on the long-term variable data sequence.

[0028] In some embodiments of the present application, the classification perspectives of the reflection data include treatment effect, water quality safety, process stability, and pollution discharge. The classification perspectives of the reflection data involved in each treatment stage include one or more of treatment effect, water quality safety, process stability, and pollution discharge.

[0029] In some embodiments of the present application, all categories of reflection data are integrated to generate evaluation indicators, including

[0030] For the evaluation criteria at each processing stage, the response data at each processing stage is evaluated to obtain the evaluation of a single response data. The evaluations of the single response data of all categories of response data are integrated to obtain the evaluation of the processing stage;

[0031] The evaluation indexes are generated by integrating the evaluations of all processing stages.

[0032] Correspondingly, the present application also provides a water source pollution risk assessment system based on the micro-electrolysis technology, including,

[0033] The first module is used to divide the micro-electrolysis process into multiple processing stages, confirm all the response data involved in each processing stage, and define the attributes of the response data;

[0034] The second module is used to collect waste water source information, formulate the evaluation criteria for each processing stage according to the waste water source information, perform micro-electrolysis treatment on the waste water source, and collect the response data generated during the micro-electrolysis treatment process at the same time;

[0035] The third module is used to perform corresponding preprocessing on the response data according to the attributes of the response data after the micro-electrolysis is completed, and classify the response data from different perspectives;

[0036] The fourth module is used to generate evaluation indexes by integrating all categories of response data according to the evaluation criteria at each processing stage, so as to evaluate the pollution risk of the waste water source after micro-electrolysis.

[0037] The present application has the following beneficial effects:

[0038] 1. Confirm all the response data involved in each processing stage, define the attributes of the response data, divide the response data into two attributes of short-time variable data and long-time variable data, and provide a reliable basis for subsequent data preprocessing. Formulate the evaluation criteria for each processing stage according to the waste water source information, and establish multiple micro-electrolysis process simulation models, so as to formulate the evaluation criteria.

[0039] 2. Perform corresponding preprocessing on the response data according to the attributes of the response data, so as to specifically reduce the random error and random fluctuation in the response data collection process, improve the accuracy of the original data, and ensure the reliability of subsequent evaluations. Generate evaluation indexes by integrating all categories of response data according to the evaluation criteria at each processing stage, comprehensively evaluate the micro-electrolysis situation from multiple angles and multiple dimensions of multiple processing stages, so as to evaluate the water source pollution risk, improve the comprehensiveness and adaptability of the water source pollution risk assessment, and ensure the accurate capture of environmental pollution risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a schematic flow chart of the water source pollution risk assessment method based on the micro-electrolysis technology proposed by the present invention;

[0041] Figure 2 This is a schematic structural diagram of a water source pollution risk assessment system based on the microelectrolysis technology proposed by the present invention. Specific embodiments

[0042] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments.

[0043] Referring to Figure 1 , a water source pollution risk assessment method based on the microelectrolysis technology includes the following steps:

[0044] Step S101: Divide the microelectrolysis process into multiple treatment stages, confirm all the reaction data involved in each treatment stage, and define the attributes of the reaction data.

[0045] In this embodiment, the microelectrolysis technology can degrade organic pollutants in wastewater, remove heavy metal ions, etc., thereby reducing the pollutant concentration in the water source. The microelectrolysis treatment can also improve the biodegradability of the wastewater, making the subsequent biological treatment process more effective. However, the treatment effect of microelectrolysis may be affected by various factors such as wastewater quality, water volume, and reaction conditions, resulting in unstable treatment effects. This instability may introduce additional errors. By-products or secondary pollutants such as iron ions and hydroxide ions may be generated during the microelectrolysis process. If these by-products or secondary pollutants are not effectively treated or removed, they may pose a new pollution risk to the water source. Therefore, the pollution risk does not disappear after using the microelectrolysis technology. It is more necessary to pay attention to the microelectrolysis treatment situation to comprehensively evaluate the pollution risk.

[0046] In this embodiment, the reaction data includes electrode potential difference, number of primary batteries, current intensity, voltage change, pollutant concentration, etc. The attributes of the reaction data are short-term variable data or long-term variable data. Short-term variable data is data that changes relatively frequently, and long-term variable data is data that changes infrequently.

[0047] In some embodiments of the present application, the treatment stages include a primary battery formation stage, an electrochemical reaction stage, a pollutant removal stage, and a post-treatment stage.

[0048] In this embodiment, the microelectrolysis process can be divided into four core stages:

[0049] Primary battery formation stage: The electrode materials are immersed in the wastewater to form a micro-battery structure.

[0050] Electrochemical reaction stage: Pollutants undergo oxidation-reduction reactions on the electrode surface.

[0051] Pollutant removal stage: Separate the pollutants through flocculation precipitation or flotation.

[0052] Subsequent processing stage: including finalizing work such as sediment filtration and water quality adjustment.

[0053] In some embodiments of the present application, the attributes reflecting data are defined, including

[0054] The reflection data involved in each processing stage includes first reflection data and second reflection data. The first reflection data describes the processing effect of the processing stage, and the second reflection data describes the reaction conditions of the processing stage;

[0055] Based on the first reflection data and the second reflection data, calculate the maximum information coefficient and the Pearson correlation coefficient between various reflection data, generate a correlation coefficient by combining the maximum information coefficient and the Pearson correlation coefficient, screen the corresponding relationship of the reflection data according to the correlation coefficient, and record it as a set of strongly correlated reflection data;

[0056] Perform data standardization processing on the set of strongly correlated reflection data, calculate the covariance matrix, solve the eigenvalues of the covariance matrix, sort the eigenvalues by size, select the types of reflection data corresponding to the sizes of the first several eigenvalues as the principal components, and construct an electro-chemical reaction stability index based on the principal components;

[0057] Obtain the historical reflection data of the micro-electrolysis process, construct a reflection data timeline in chronological order, divide the reflection data timeline by the electro-chemical reaction stability index, and define the attributes of each type of reflection data.

[0058] In this embodiment, the first reflection data describes the treatment effect in the treatment stage, such as treatment effect conditions like current efficiency, pollutant degradation rate, and effluent water quality indicators. The second reflection data describes the reaction conditions in the treatment stage, such as reaction condition situations like current intensity, voltage, electrode corrosion rate, pH value, and temperature. Based on the first reflection data and the second reflection data (between the first reflection data and the second reflection data, between the first reflection data, and between the second reflection data), calculate the maximum information coefficient (MIC, non-linear) and Pearson correlation coefficient (Pearson Correlation Coefficient, linear) between them. Combine the MIC and Pearson correlation coefficient to generate a comprehensive correlation coefficient for measuring the correlation strength between the reflection data. According to the correlation coefficient, screen out the strongly correlated reflection data sets, and the data in these sets will be focused on in subsequent analysis. If there is a strong correlation between the selected data, the PCA method can be used to extract the principal components of the data. Use the principal components as new comprehensive indicators, that is, the electro-chemical reaction stability index. The PCA method can reduce the dimension of the data while retaining the main information. MIC: A non-parametric method based on mutual information that can detect complex non-linear relationships (such as quadratic and exponential relationships), Pearson correlation coefficient: Measures the strength of linear correlation (value range [-1, 1], the closer the absolute value is to 1, the stronger the linear relationship)

[0059] In this embodiment, perform Z-score standardization, covariance matrix calculation, eigenvalue decomposition, and principal component selection (sort by eigenvalue size and select the top k principal components with a cumulative variance contribution rate > 85%) on the original data (such as current intensity, voltage change rate, pollutant removal rate, etc.). Sum the weighted top k principal components to construct the electro-chemical reaction stability index.

[0060] In some embodiments of the present application, divide the reflection data time axis by virtue of the electro-chemical reaction stability index and define the attributes of each reflection data, including

[0061] The attribute of the reflection data is short-term variable data or long-term variable data;

[0062] Calculate the electro-chemical reaction stability index for each time unit according to the principal components on the reflection data time axis, and divide the reflection data time axis into two parts: the electro-chemical reaction stable time axis and the electro-chemical reaction unstable time axis according to the electro-chemical reaction stability index;

[0063] Set the variation threshold for each reflection data for both the electro-chemical reaction stable time axis and the electro-chemical reaction unstable time axis, calculate the coefficient of variation of each reflection data, and compare the coefficient of variation of each reflection data with the variation threshold to obtain the comparison result;

[0064] Integrate the comparison results of the two parts of the electro-chemical reaction stable time axis and the electro-chemical reaction unstable time axis, and classify the attributes of each type of reflected data as short-term variable data or long-term variable data.

[0065] In this embodiment, for the two parts of the electro-chemical reaction stable time axis and the electro-chemical reaction unstable time axis, the electro-chemical reaction stable time axis means that the reaction in this part of the processing stage is relatively stable, and the electro-chemical reaction unstable time axis means that the reaction in this part of the processing stage fluctuates greatly and is unstable. Set the variation threshold for each type of reflected data respectively. The variation threshold for each type of reflected data is set according to the perimeter of the time axis, the electro-chemical reaction stability index, and the characteristics of this type of reflected data. Within the variation threshold, it indicates that the change of this type of reflected data is reasonable, otherwise the change fluctuates greatly. The comparison result can be the deviation between the coefficient of variation and the variation threshold, and the deviation can be a positive deviation (stable) and a negative deviation (unstable). Integrate the comparison results of the two parts of the electro-chemical reaction stable time axis and the electro-chemical reaction unstable time axis for each type of reflected data to generate the determination index (Indicators for Assessing Reflected Data) for each type of reflected data. The specific calculation formula is as follows:

[0066]

[0067] Wherein, is the determination index of the i1-th reflected data, β1 and β2 are the respective combination coefficients of the two parts of the electro-chemical reaction stable time axis and the electro-chemical reaction unstable time axis respectively, n1 and n2 are the respective quantities of the two parts of the electro-chemical reaction stable time axis and the electro-chemical reaction unstable time axis respectively. There will be multiple axes in the two parts under one type of reflected data. are the combination weights of the i2-th electro-chemical reaction stable time axis and the i3-th electro-chemical reaction unstable time axis of the i1-th reflected data respectively (which can be determined according to the axis length, that is, time). are the deviations of the i2-th electro-chemical reaction stable time axis and the i3-th electro-chemical reaction unstable time axis of the i1-th reflected data respectively. are respectively the maximum value and the minimum value in, are the first constant and the second constant of the i1-th reflected data respectively. and respectively represent the corrections of the maximum value and the minimum value in to the class average of the sum of the deviations. The class average of the electro-chemical reaction stable time axis is a little smaller than the average value, and the class average of the electro-chemical reaction unstable time axis is a little larger than the average value.

[0068] Step S102, collect wastewater source information, formulate evaluation criteria for each treatment stage based on the wastewater source information, conduct micro-electrolysis treatment on the wastewater source, and simultaneously collect the reaction data generated during the micro-electrolysis treatment.

[0069] In this embodiment, the wastewater source information includes the following:

[0070] Source and composition: industrial wastewater (such as electroplating wastewater containing heavy metals), domestic sewage (containing organic matter), etc.

[0071] Pollutant concentration: COD, BOD, ammonia nitrogen, heavy metal content, etc.

[0072] Water quality characteristics: pH value, conductivity, temperature, etc.

[0073] Based on the wastewater source information, formulate stage-by-stage evaluation criteria, for example:

[0074] Primary battery formation stage: The electrode potential difference needs to be stabilized within ±50 mV, and the number of primary batteries reaches 80% of the theoretical value.

[0075] Electrochemical reaction stage: The current efficiency needs to be higher than 70%, and the pollutant degradation rate increases by 5% per hour.

[0076] Pollutant removal stage: The turbidity is reduced to below 5 NTU, and the amount of sediment accounts for 10%-15% of the treatment volume.

[0077] Subsequent treatment stage: The pH value of the effluent is controlled between 6-9, and the water quality after filtration meets the discharge standard.

[0078] On-line monitoring: current intensity, voltage change, pH value, etc. Experimental analysis: pollutant concentration, turbidity, sediment amount, etc.

[0079] In some embodiments of the present application, formulating the evaluation criteria for each treatment stage according to the wastewater source information includes,

[0080] Establish multiple simulation models according to the wastewater source information, integrate multiple simulation models to describe the simulated micro-electrolysis process, and perform model parameter settings to formulate the evaluation criteria for the reaction data of each treatment stage.

[0081] In this embodiment, the simulation models include an electrochemical model and a hydrodynamics model, etc.

[0082] Electrochemical model

[0083] Equivalent circuit model: Simplify the micro-electrolysis process into an equivalent circuit, and simulate the electrochemical reaction process through circuit parameters (such as resistance, capacitance, inductance, etc.). This model can predict key parameters such as current intensity and voltage change, and provide a basis for formulating the evaluation criteria for the electrochemical reaction stage.

[0084] Electrode reaction kinetic model: Based on the principles of electrode reaction kinetics, a model is established to describe the reaction rate on the electrode surface and the distribution of reaction products. This model can simulate the changes in parameters such as electrode potential difference and current efficiency, providing guidance for optimizing the electro-chemical reaction conditions.

[0085] Computational Fluid Dynamics (CFD) model

[0086] Flow field simulation: By using the CFD model, the flow situation of wastewater in the reactor is simulated, including parameters such as flow velocity and turbulence intensity. This helps to understand the mass transfer process between the wastewater and the electrode, providing a basis for formulating the evaluation criteria in the pollutant removal stage.

[0087] Concentration field simulation: Combining the results of the flow field simulation, the changes in the concentrations of various pollutants in the wastewater are predicted. This helps to evaluate the treatment effect and provides guidance for optimizing the treatment process.

[0088] Multi-physical field coupling model: Combining the electrochemical model, CFD model, etc., a multi-physical field coupling model is formed. This model can comprehensively simulate the electrochemical reactions, mass transfer processes, hydrodynamic characteristics, etc. in the micro-electrolysis process, providing a more accurate and comprehensive basis for formulating the evaluation criteria for each stage.

[0089] Implementation process

[0090] Data collection and preprocessing: Collect key information of the wastewater source (such as source, composition, pollutant concentration, water quality characteristics, etc.) and perform preprocessing (such as cleaning, standardization, etc.).

[0091] Model selection and construction: According to the characteristics of the wastewater source and treatment requirements, select appropriate models (such as PCA, clustering analysis, electrochemical model, CFD model, etc.) for construction.

[0092] Parameter setting and simulation run: Set the model parameters according to historical data, experimental data or expert experience, and perform the simulation run.

[0093] Result analysis and evaluation criterion formulation: Analyze the simulation results, extract key parameters and characteristics, and formulate the evaluation criteria for each stage in combination with the treatment requirements.

[0094] In step S103, after the micro-electrolysis is completed, the reaction data is preprocessed correspondingly according to the attributes of the reaction data, and the reaction data is classified from different angles.

[0095] In this embodiment, there are many random errors and fluctuations in the collected original reaction data, which need to be eliminated by targeted preprocessing according to the data attributes.

[0096] In some embodiments of the present application, the reaction data is preprocessed correspondingly according to the attributes of the reaction data, including

[0097] For short-term variable data, plot the change curve of short-term variable data under the complete process of micro-electrolysis, count the size of the data range on the change curve of short-term variable data, split the change curve of short-term variable data into multiple curve segments according to the size of the data range, arrange the multiple curve segments in chronological order, calculate the slope change of each curve segment, confirm a weakening factor of the smoothing index according to the slope changes of all curve segments, and perform exponentially weighted moving average on the change curve of short-term variable data according to the weakening factor of the smoothing index, so as to eliminate the random fluctuations on the change curve of short-term variable data;

[0098] For long-term variable data, calculate the first-order difference of the long-term variable data sequence, calculate the difference between adjacent first-order differences of the long-term variable data sequence at the first preset interval to obtain a first-order difference change index, and if the first-order difference change index is not lower than the change threshold, map the long-term variable data complexity according to the first-order difference change index;

[0099] If the first-order difference change index is lower than the change threshold, calculate the second-order difference of the long-term variable data sequence, calculate the difference between adjacent second-order differences of the long-term variable data sequence at the second preset interval to obtain a second-order difference change index, and map the long-term variable data complexity according to the second-order difference change index;

[0100] Select the order of the trend line through the long-term variable data complexity, and fit the trend line of the long-term variable data sequence based on the order of the trend line, so as to eliminate the random error on the long-term variable data sequence.

[0101] In this embodiment, the purpose of short-time variable data preprocessing is to smooth fluctuations: Short-time variable data (such as current intensity, voltage change, etc.) often contains a large amount of random fluctuations and noise, and these fluctuations may obscure the true trends and patterns of the data. Through smoothing processing, these random fluctuations can be eliminated, making the data more stable and facilitating subsequent analysis and modeling. The purpose of long-time variable data preprocessing is to eliminate random errors: Although long-time variable data (such as pollutant removal rate, electrode corrosion rate, etc.) does not change frequently, it may be affected by various random factors and generate errors. Through piecewise averaging or trend analysis, these random errors can be eliminated, making the data more accurate and reliable. Exponentially Weighted Moving Average (EWMA): Implementation process: Perform weighted averaging on the short-time variable data sequence, where newer data points are assigned larger weights and older data points are assigned smaller weights. The weights decay exponentially over time. Alpha: The weakening factor of the smoothing exponent, that is, the weight assignment at a given time point. It should be a number between 0 and 1. A larger value means giving greater weight to past observations, while a smaller value tends to make the prediction smoother. Trend analysis method: Implementation process: Reveal the long-term trends and change patterns of the data by fitting a trend line (such as a straight line, curve, etc.) to the data sequence. The trend line can be fitted by methods such as the least squares method, maximum likelihood estimation, etc. The type and order of the trend line are key parameters. The appropriate type and order of the trend line should be selected according to the distribution characteristics and change trends of the data.

[0102] In this embodiment, a smoothing exponent weakening factor is confirmed according to the slope change of the time series of different curve segments. The order of the trend line is selected according to the complexity of the long-time variable data. Low-order trend line: For data with relatively simple changes, select a low-order trend line (such as a linear trend line, quadratic polynomial trend line). High-order trend line: For data with relatively complex changes, select a high-order trend line (such as a cubic polynomial trend line, higher-order polynomial trend line, or complex non-linear trend line).

[0103] In this embodiment, the first-order difference can directly reflect the change amount between adjacent data points in a data sequence, which is very useful for identifying mutation points or trend changes in the data sequence. In long-term time-varying data, even if the changes are not frequent, the first-order difference can help identify the subtle changes in the data sequence, thereby revealing potential change trends. The second-order difference can reveal the change acceleration of the data sequence, which is very useful for analyzing whether the change trend of the data sequence is stable or whether there are periodic changes. In long-term time-varying data, the second-order difference can help identify the long-term trend or periodic fluctuations in the data sequence, thereby providing a more in-depth analysis of the change trend. When analyzing long-term time-varying data, usually the first-order difference is first calculated to observe the change amount between adjacent data points in the data sequence. If the change of the first-order difference is large or there are obvious mutation points, it indicates that the change trend of the data sequence is relatively complex and may require further analysis. Then analyze the second-order difference: if the change of the first-order difference is not obvious or cannot provide enough information to reveal the change trend of the data sequence, the second-order difference can be further calculated. The second-order difference can reveal the change acceleration of the data sequence and provide a more in-depth analysis of the change trend. Through the second-order difference, features such as long-term trends, periodic fluctuations, or acceleration changes in the data sequence can be identified.

[0104] In some embodiments of the present application, the classification angles reflecting data include treatment effect, water quality safety, process stability, and pollution discharge. The classification angles reflecting data involved in each treatment stage include one or more of treatment effect, water quality safety, process stability, and pollution discharge.

[0105] In this embodiment, for example, in the primary battery formation stage, only the treatment effect (in this stage, the formation efficiency of the primary battery is mainly concerned, such as the stability of the electrode potential difference, the achievement of the number of primary batteries, etc., which can be indirectly reflected as the potential effect of subsequent electrochemical reactions and pollutant removal) and the pollution discharge angle (pay attention to the generation of waste gas and waste residue during the start-up and operation of the equipment to ensure compliance with environmental protection standards).

[0106] Step S104, based on the evaluation criteria of each treatment stage, integrate all categories of reflected data to generate evaluation indicators, so as to conduct a pollution risk assessment on the wastewater source after micro-electrolysis.

[0107] In this embodiment, the category of the reflected data here is the above classification angle, so as to conduct a comprehensive evaluation in terms of the treatment stage and classification angle, thereby determining the pollution risk.

[0108] In some embodiments of the present application, integrating all categories of reflected data to generate evaluation indicators includes

[0109] On the evaluation criteria for each processing stage, the reflection data for each processing stage is evaluated to obtain the evaluation of a single reflection data. The evaluations of the single reflection data for all category reflection data are integrated to obtain the evaluation of the processing stage.

[0110] The evaluation indicators are generated by integrating the evaluations of all processing stages.

[0111] In this embodiment, the evaluations of the single reflection data for all category reflection data are integrated, and the evaluations from four perspectives are integrated to obtain the evaluation of each processing stage. The calculation formula for the evaluation indicators generated based on the result parameters after micro-electrolysis treatment (such as pollutant conditions, water quality conditions) and the evaluations of all processing stages is as follows:

[0112]

[0113] where Ei is the evaluation indicator, 4 represents four stages: the primary battery formation stage, the electrochemical reaction stage, the pollutant removal stage, and the post-treatment stage, γ j is the combined weight of the j-th processing stage, W j is the evaluation of the j-th processing stage, τ is the final quality parameter determined according to the result parameters after micro-electrolysis treatment (such as pollutant conditions, water quality conditions), k3 is the third constant, represents the correction of the sum of the evaluations of the four processing stages by the final quality parameter.

[0114] Correspondingly, the present application also provides a water source pollution risk assessment system based on the micro-electrolysis technology, as Figure 2 shown, including,

[0115] The first module is used to divide the micro-electrolysis process into multiple processing stages, identify all the reflection data involved in each processing stage, and define the attributes of the reflection data;

[0116] The second module is used to collect wastewater source information, formulate the evaluation criteria for each processing stage according to the wastewater source information, perform micro-electrolysis treatment on the wastewater source, and simultaneously collect the reflection data generated during the micro-electrolysis process;

[0117] The third module is used to, after the micro-electrolysis is completed, perform corresponding preprocessing on the reflection data according to the attributes of the reflection data, and classify the reflection data from different perspectives;

[0118] The fourth module is used to generate evaluation indicators by integrating all category reflection data based on the evaluation criteria for each processing stage, so as to conduct pollution risk assessment on the wastewater source after micro-electrolysis.

[0119] The present application has the following beneficial effects:

[0120] 1. Confirm all the reflection data involved in each processing stage, define the attributes of the reflection data, divide the reflection data into two attributes: short-term variable data and long-term variable data, and provide a reliable basis for subsequent data preprocessing. Develop the evaluation criteria for each processing stage according to the wastewater source information, and establish multiple micro-electrolysis process simulation models to formulate the evaluation criteria.

[0121] 2. Perform corresponding preprocessing on the reflection data according to the attributes of the reflection data, so as to specifically reduce the random errors and random fluctuations in the process of collecting the reflection data, improve the accuracy of the original data, and ensure the reliability of subsequent evaluations. Based on the evaluation criteria for each processing stage, integrate all categories of reflection data to generate evaluation indicators, comprehensively evaluate the micro-electrolysis situation from multiple perspectives and multiple dimensions of multiple processing stages, thereby assessing the water source pollution risk, improving the comprehensiveness and adaptability of the water source pollution risk assessment, and ensuring the accurate capture of environmental pollution risks.

[0122] From the description of the above implementation manners, those skilled in the art can clearly understand that the present invention can be implemented through hardware or by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various implementation scenarios of the present invention.

[0123] Those skilled in the art can understand that the drawings are only schematic diagrams of a preferred implementation scenario, and the modules or processes in the drawings are not necessarily essential for implementing the present invention.

[0124] Those skilled in the art can understand that the modules in the system in the implementation scenario can be distributed in the system of the implementation scenario according to the description of the implementation scenario, or can be correspondingly changed and located in one or more systems different from the present implementation scenario. The modules in the above implementation scenario can be combined into one module, or can be further split into multiple sub-modules.

[0125] The above is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, makes equivalent substitutions or changes, and should be covered by the protection scope of the present invention.

Claims

1. A method for assessing the risk of water source pollution based on the micro-electrolysis technology, characterized in that, including divide the micro-electrolysis process into multiple treatment stages, confirm all reaction data involved in each treatment stage, and define the attributes of the reaction data collect wastewater source information, formulate evaluation criteria for each treatment stage according to the wastewater source information, conduct micro-electrolysis treatment on the wastewater source, and simultaneously collect the reaction data generated during the micro-electrolysis process after micro-electrolysis is completed, perform corresponding preprocessing on the reaction data according to the attributes of the reaction data, and classify the reaction data from different perspectives integrate all categories of reaction data to generate evaluation indicators based on the evaluation criteria for each treatment stage, so as to conduct pollution risk assessment on the wastewater source after micro-electrolysis 2. The method for evaluating the risk of water source pollution based on the microelectrolysis technology according to claim 1, wherein The treatment stages include the primary battery formation stage, the electrochemical reaction stage, the pollutant removal stage, and the post-treatment stage 3. The method for assessing the risk of water source pollution based on the micro-electrolysis technology according to claim 1, wherein and define the attributes of the reaction data, including the reaction data involved in each treatment stage includes the first reaction data and the second reaction data. The first reaction data describes the treatment effect of the treatment stage, and the second reaction data describes the reaction conditions of the treatment stage calculate the maximum information coefficient and Pearson correlation coefficient between various reaction data based on the first reaction data and the second reaction data, generate a correlation coefficient by combining the maximum information coefficient and the Pearson correlation coefficient, screen the corresponding relationship of the reaction data according to the correlation coefficient, and record it as a set of strongly correlated reaction data perform data standardization processing on the set of strongly correlated reaction data, calculate the covariance matrix, solve the eigenvalues of the covariance matrix, sort the eigenvalues by size, select the types of reaction data corresponding to the sizes of the first several eigenvalues as the principal components, and construct an electrochemical reaction stability index based on the principal components obtain the historical reaction data of the micro-electrolysis process, construct a reaction data timeline in chronological order, divide the reaction data timeline by virtue of the electrochemical reaction stability index, and define the attributes of each type of reaction data 4. The method for assessing the risk of water source pollution based on the microelectrolysis technology according to claim 3, wherein divide the reaction data timeline by virtue of the electrochemical reaction stability index, and define the attributes of each type of reaction data, including the attribute of the reaction data is short-term variable data or long-term variable data calculate the electrochemical reaction stability index for each time unit based on the principal components on the reaction data timeline, and divide the reaction data timeline into two parts: the electrochemical reaction stable timeline and the electrochemical reaction unstable timeline according to the electrochemical reaction stability index set the variation threshold for each type of reaction data for the electrochemical reaction stable timeline and the electrochemical reaction unstable timeline respectively, calculate the coefficient of variation of each type of reaction data, compare the coefficient of variation of each type of reaction data with the variation threshold, and obtain the comparison result integrate the comparison results of the electrochemical reaction stable timeline and the electrochemical reaction unstable timeline, and divide the attribute of each type of reaction data into short-term variable data or long-term variable data 5. The method for evaluating the risk of water source pollution based on the micro-electrolysis technology according to claim 1, wherein formulate evaluation criteria for each treatment stage according to the wastewater source information, including establish multiple simulation models according to the wastewater source information, integrate multiple simulation models to describe the simulated micro-electrolysis process, and perform model parameter settings to formulate the evaluation criteria for the reaction data of each treatment stage 6. The method for assessing the risk of water source pollution based on the microelectrolysis technology according to claim 4, wherein perform corresponding preprocessing on the reaction data according to the attributes of the reaction data, including For short-term variable data, plot the short-term variable data change curve under the complete micro-electrolysis process, count the size of the data range on the short-term variable data change curve, split the short-term variable data change curve into multiple curve segments according to the size of the data range, arrange the multiple curve segments in chronological order, calculate the slope change of each curve segment, confirm a weakening factor of the smoothing index according to the slope changes of all curve segments, and perform exponentially weighted moving average on the short-term variable data change curve according to the weakening factor of the smoothing index to eliminate the random fluctuations on the short-term variable data curve; For long-term variable data, calculate the first-order difference of the long-term variable data sequence, calculate the difference between adjacent first-order differences of the long-term variable data sequence at the first preset interval to obtain a first-order difference change index. If the first-order difference change index is not lower than the change threshold, map the long-term variable data complexity according to the first-order difference change index; If the first-order difference change index is lower than the change threshold, calculate the second-order difference of the long-term variable data sequence, calculate the difference between adjacent second-order differences of the long-term variable data sequence at the second preset interval to obtain a second-order difference change index, and map the long-term variable data complexity according to the second-order difference change index; Select the order of the trend line through the long-term variable data complexity, and fit the trend line of the long-term variable data sequence based on the order of the trend line to eliminate the random error on the long-term variable data sequence.

7. The method for evaluating the risk of water source pollution based on the micro-electrolysis technology according to claim 2, wherein The classification angles reflecting data include treatment effect, water quality safety, process stability, and pollution discharge. The classification angles reflecting data involved in each treatment stage include one or more of treatment effect, water quality safety, process stability, and pollution discharge.

8. The method for assessing the risk of water source pollution based on the micro-electrolysis technology according to claim 1, wherein Integrate all categories of reflected data to generate evaluation indicators, including, On the evaluation criteria for each treatment stage, evaluate the reflected data of each treatment stage to obtain the evaluation of a single reflected data, and integrate the evaluations of the single reflected data of all categories of reflected data to obtain the evaluation of the treatment stage; Generate evaluation indicators by synthesizing the evaluations of all treatment stages.

9. A water source pollution risk assessment system based on micro-electrolysis technology, characterized in that, including, The first module is used to divide the micro-electrolysis process into multiple treatment stages, confirm all the reflected data involved in each treatment stage, and define the attributes of the reflected data; The second module is used to collect waste water source information, formulate the evaluation criteria for each treatment stage according to the waste water source information, perform micro-electrolysis treatment on the waste water source, and collect the reflected data generated during the micro-electrolysis treatment process at the same time; The third module is used to perform corresponding preprocessing on the reflected data according to the attributes of the reflected data after the micro-electrolysis is completed, and classify the reflected data from different angles; The fourth module is used to generate evaluation indicators by integrating all categories of reflected data on the evaluation criteria for each treatment stage, so as to evaluate the pollution risk of the waste water source after micro-electrolysis.

Images