A method for evaluating sewage treatment results

Abstract

The present invention relates to the technical field of sewage data processing, and more specifically, to a method for evaluating sewage treatment results, the method comprising: obtaining COD data segments on both sides of a COD data point in a sewage COD data time series sequence, respectively, and obtaining a dissolved oxygen data segment corresponding to the COD data segment in a dissolved oxygen data time series sequence; obtaining the stability of the COD data segment through data fluctuations in the COD data segment; calculating the correlation between the COD data segment and the corresponding dissolved oxygen data segment; obtaining the reliability of the COD data segment through the correlation between the COD data segment and the corresponding dissolved oxygen data segment and the stability of the COD data segment; presetting the window length of the COD data point, setting the window position based on the reliability of the COD data segments on both sides of the COD data point, and realizing denoising of the COD data time series sequence; obtaining a sewage treatment evaluation result based on the denoised COD data time series sequence, and effectively improving the accuracy of the sewage treatment evaluation result.

Description

Technical Field

[0001] The present invention relates to the technical field of sewage data processing. More specifically, the present invention relates to a method for evaluating sewage treatment results. Background Art

[0002] Sewage contains a large amount of wastewater, organic matter, chemical substances, etc. Directly discharging it into water bodies will cause water quality deterioration. By removing harmful substances in sewage through sewage treatment, water quality can be improved and the harm of sewage to aquatic organisms and the water ecosystem can be reduced.

[0003] In order to ensure the quality and effectiveness of sewage treatment, it is necessary to evaluate the sewage treatment results. There are many research methods for evaluating sewage treatment effects in the prior art. For example, the patent application document with the publication number CN117591890A discloses a sewage treatment evaluation system and method based on big data. This application obtains historical terminal record data in the sewage treatment system; the feature factor set analysis module in the big data evaluation system is used to analyze the feature factor set of the sewage treatment system, and the safety evaluation module is used to construct an operation safety evaluation module corresponding to the target feature factor and calculate the safety evaluation index; the inspection drone is used to collect the state data of the sewage treatment area; the evaluation response module locates the ceramic membrane and the position of the acquisition sensor and stores data such as the water quality of the sewage treatment area; the Web display device displays the evaluation data to discover and handle abnormal problems.

[0004] Although the above prior art can achieve sewage treatment evaluation by collecting historical terminal record data, during the process of transmitting sewage data, it will experience multi-channel data acquisition, network transmission, etc. During this process, noise data may be generated, thus affecting the accuracy of sewage data evaluation.

[0005] Based on this, how to accurately achieve sewage treatment result evaluation is an urgent problem to be solved by those skilled in the art. Summary of the Invention

[0006] To solve the above technical problem of how to accurately achieve sewage treatment result evaluation, the present invention proposes a method for evaluating sewage treatment results, which includes the following steps:

[0007] Obtain the COD data segments on the left and right sides of the COD data points in the COD data time series of sewage, and obtain the corresponding dissolved oxygen data segments of the COD data segments in the dissolved oxygen data time series; obtain the stability of the COD data segments through the data fluctuation conditions in the COD data segments; calculate the correlation between the COD data segments and the corresponding dissolved oxygen data segments:

[0008] ;

[0009] is the correlation between the th COD data segment and the corresponding dissolved oxygen data segment, is the Pearson correlation coefficient between the th COD data segment and the corresponding dissolved oxygen data segment, is the number of COD data points in the th COD data segment, and are the maximum values in the th COD data segment and the corresponding dissolved oxygen data segment respectively, and are the values of the th COD data point in the th COD data segment and the th dissolved oxygen data point in the corresponding dissolved oxygen data segment respectively, and are the ranges in the th COD data segment and the corresponding dissolved oxygen data segment respectively; is the exponential function with base e; the reliability of the COD data segment is obtained through the correlation between the COD data segment and the corresponding dissolved oxygen data segment and the stability of the COD data segment; a preset window length of the COD data points is set, the window position is set based on the reliability of the COD data segments on the left and right sides of the COD data points, and the denoising of the COD data time series is achieved through the data in the window; the sewage treatment evaluation result is obtained based on the denoised COD data time series.

[0010] In the present invention, the sewage treatment evaluation result is obtained by denoising the COD data time series, which can effectively reduce the influence of noise data on the accuracy of the sewage treatment evaluation result. In this process, considering that when constructing the window for filtering the COD data points, data points with higher noise performance may be included in the COD data point window, resulting in poor filtering effect. Based on this, the present invention analyzes the data fluctuation conditions of the data segments on the left and right sides of the COD data points, obtains more data points in the COD data segment with higher stability, reduces the influence of data points with higher noise performance on the filtering effect, and improves the accuracy of denoising the COD data time series; on this basis, the present invention also considers that some noise data may be relatively similar to the COD data itself, so the stability of the COD data segment is further verified by further obtaining the dissolved oxygen data correlated with the COD data, effectively improving the accuracy of constructing the window for the COD data points, and thus effectively improving the accuracy of the sewage treatment evaluation result.

[0011] A sewage treatment result evaluation method provided by the present invention, to obtain a COD data segment and a corresponding dissolved oxygen data segment, further includes: after collecting COD data and dissolved oxygen data, performing preprocessing to obtain a COD data time series sequence and a dissolved oxygen data time series sequence.

[0012] The present invention takes into account that there may be problems such as data loss in the originally collected COD data and dissolved oxygen data. Therefore, preprocessing is carried out to improve the overall quality of the data and prepare for subsequent data processing.

[0013] A sewage treatment result evaluation method provided by the present invention, the stability of the COD data segment satisfies the relational expression: ; is the stability of the th COD data segment, is the th COD data segment, the mean of the absolute values of the differences between all data points and the mean of the th COD data segment, is the th COD data segment, the mean of the absolute values of the differences between all adjacent data points, is the exponential function with base e.

[0014] A sewage treatment result evaluation method provided by the present invention, obtaining the reliability of the COD data segment through the correlation between the COD data segment and the corresponding dissolved oxygen data segment and the stability of the COD data segment, includes: multiplying the correlation between the COD data segment and the corresponding dissolved oxygen data segment by the stability of the COD data segment and then performing normalization processing to obtain the reliability of the COD data segment.

[0015] A sewage treatment result evaluation method provided by the present invention, setting the window position based on the reliability of the COD data segments on the left and right sides of the COD data point, includes:

[0016] ; is the length of the left end position of the window of the th, respectively are the reliabilities of the COD data segments on the left and right sides of the th COD data point, is the floor function symbol;

[0017] ; is the length of the right end position of the window of the

[0018] The present invention provides an accurate window length allocation method. By allocating more window lengths to COD data segments with higher reliability and setting the window positions, it can effectively avoid the influence of COD data points with higher noise levels on the denoising effect.

[0019] According to a sewage treatment result evaluation method provided by the present invention, denoising of the COD data time series is achieved through the data in the window, including: using the window of each COD data point in the SG filtering algorithm to perform denoising processing on the COD data time series.

[0020] The present invention takes into account that the noise data in the COD data time series will affect the accuracy of the sewage treatment evaluation result. Therefore, by performing denoising processing on the COD data time series through the SG filtering algorithm, it can effectively avoid the influence of noise data on the sewage treatment evaluation result and improve the accuracy of the sewage treatment evaluation result.

[0021] According to a sewage treatment result evaluation method provided by the present invention, obtaining the sewage treatment evaluation result based on the denoised COD data time series includes: performing anomaly detection on the denoised COD data time series through the box plot algorithm, and obtaining the sewage treatment evaluation result based on the comparison result between the proportion of anomaly data points in the COD data time series and a preset threshold.

[0022] According to a sewage treatment result evaluation method provided by the present invention, after obtaining the sewage treatment evaluation result, it further includes: generating an evaluation report with the denoised COD data time series and the corresponding sewage treatment evaluation result.

[0023] The present invention takes into account that sewage treatment is a time-consuming process and historical COD data time series and corresponding sewage treatment evaluation results need to be continuously collected for analysis. Therefore, by generating an evaluation report with the denoised COD data time series and the corresponding sewage treatment evaluation result, it is convenient for staff to analyze the long-term trend and periodic changes of sewage treatment.

[0024] The present invention has the following beneficial effects:

[0025] Based on the above technical solution, when determining the sewage treatment evaluation result, the present invention obtains the sewage treatment evaluation result by denoising the COD data time series, which can effectively reduce the influence of noise data on the accuracy of the sewage treatment evaluation result. In this process, the present invention analyzes the data fluctuations of the data segments on the left and right sides of the COD data points, obtains more data points in the COD data segment with higher stability, reduces the influence of data points with higher noise performance on the filtering effect, and improves the accuracy of denoising the COD data time series; on this basis, the present invention also obtains the dissolved oxygen data correlated with the COD data to further verify the stability of the COD data segment, eliminates some noise data that may be relatively similar to the COD data itself, effectively improves the accuracy of constructing the window of the COD data points, and thus effectively improves the accuracy of the sewage treatment evaluation result. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] By referring to the accompanying drawings and reading the following detailed description, the above and other objects, features, and advantages of the exemplary embodiments of the present invention will become readily understood. In the drawings, several embodiments of the present invention are shown in an exemplary rather than restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0027] Figure 1 It is a schematic flow chart of a method for evaluating sewage treatment results provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0029] The following will describe the specific embodiments of the present invention in detail with reference to the accompanying drawings.

[0030] It should be noted that sewage contains a large amount of wastewater, organic matter, chemical substances, and microorganisms, etc. Directly discharging it into water bodies will cause water quality deterioration. By removing harmful substances in sewage through sewage treatment, the water quality can be improved, and the harm of sewage to aquatic organisms and the water ecosystem can be reduced. In order to ensure the quality and effectiveness of sewage treatment, it is necessary to evaluate the sewage treatment results. Chemical Oxygen Demand (COD for short) is one of the parameters for measuring sewage pollution, and its abnormal degree can be used as an important indicator for evaluating the sewage treatment effect.

[0031] In the process of transmitting sewage-related data in the prior art, multi-channel data acquisition, network transmission, etc. will be experienced. During this process, noise data may be generated, thus affecting the accuracy of sewage data evaluation. The SG filtering algorithm is a digital signal processing technology. By selecting a sliding window in a local area to fit the data, it can achieve smoothing and denoising of the data.

[0032] Based on this, an embodiment of the present invention discloses a method for evaluating sewage treatment results. This method performs denoising processing on chemical oxygen demand data through the SG filtering algorithm, and accurately obtains the sewage treatment evaluation result based on the denoised chemical oxygen demand data. Please refer to Figure 1 shown in Figure 1 which is a schematic flowchart of a method for evaluating sewage treatment results provided by an embodiment of the present invention. This method specifically includes the following steps.

[0033] S1: Obtain the COD data segments on the left and right sides of the COD data point respectively in the COD data time series of sewage.

[0034] Among them, the initial length of the COD data segment can be the length of the COD data point window minus 1.

[0035] It should be noted that when the SG filtering algorithm constructs a window, it takes the data point to be processed currently as the center, and obtains other data points equally on both sides of the data point. However, there may be potential noise data in the COD data time series. If such noise data is also used as the data in the COD data point window, it will cause errors in data filtering, resulting in a lower accuracy of the sewage treatment evaluation result.

[0036] Based on this, an embodiment of the present invention obtains the COD data segments on the left and right sides of the COD data point respectively, analyzes the reliability of the data in the chemical oxygen demand data segment, and allocates the window length based on the reliability of the data in the chemical oxygen demand data segment, and sets the window position, so as to accurately obtain the window of the COD data point.

[0037] Exemplarily, in an embodiment of the present invention, before obtaining the COD data segment, it further includes: preprocessing the collected COD data to obtain the COD data time series.

[0038] Among them, the preprocessing can be data curve fitting, data format conversion, etc., and can be specifically set according to actual needs. Embodiments of the present invention do not limit this too much here.

[0039] Specifically, COD data can be collected by a COD analyzer. The value of the COD data obtained at each collection moment is a COD data point. All COD data points are arranged in the collection order to obtain a COD data time series. Among them, the collection duration can be 2 hours, and the collection frequency can be once every 2 seconds. The collection duration and collection frequency can be specifically set according to actual needs, and the embodiments of the present invention do not impose too many restrictions here.

[0040] After obtaining the COD data segments on the left and right sides of the COD data point based on the above steps, the following steps can be continued to analyze the data change situation in the COD data segments, so as to obtain its data stability.

[0041] S2: Obtain the stability of the COD data segment through the data fluctuation situation in the COD data segment.

[0042] It should be noted that if the data distribution in the COD data segment is more concentrated and the change between adjacent data points in the COD data segment is smoother, it indicates that the possibility of the existence of noise is smaller. Based on this, the embodiments of the present invention obtain the stability of the COD data segment by analyzing the data fluctuation situation in the COD data segment.

[0043] It can be understood that the lengths of the COD data segments on both sides of the COD data point obtained based on the above steps are equal. The embodiments of the present invention take the calculation of the stability of any one of the COD data segments as an example for illustration, but it does not mean that the embodiments of the present invention are only limited to this.

[0044] Exemplarily, in the embodiments of the present invention, to determine the stability of the COD data segment, the following relational expression can be specifically referred to:

[0045] ;

[0046] In the formula, is the stability of the th COD data segment, is the average value of the absolute values of the differences between all data points in the th COD data segment and the average value of the th COD data segment, is the average value of the absolute values of the differences between all adjacent data points in the th COD data segment, is the exponential function with e as the base.

[0047] In the above formula, The smaller it is, the more concentrated the numerical distribution in the th COD data segment is, the more stable the data change is. Therefore, the possibility of the existence of noise data is also lower, and the stability of this COD data segment is higher; conversely, the smaller this value is, the more concentrated the numerical distribution in the The more discrete the values in a COD data segment are, the more disordered the data changes, so the higher the possibility of the existence of noise data, and the lower the stability of the COD data segment.

[0048] The smaller it is, it indicates that the change between adjacent data points in the COD data segment is smoother, the greater the credibility that the data fluctuations in the COD data segment are relatively stable, and the higher the stability of the COD data segment.

[0049] After obtaining the stability of each COD data segment based on the above formula, continue to execute the following steps.

[0050] S3: Obtain the dissolved oxygen data segment corresponding to the COD data segment in the time series of dissolved oxygen data, and calculate the correlation between the COD data segment and the corresponding dissolved oxygen data segment.

[0051] It should be noted that based on the above steps to analyze the data fluctuation situation of the COD data segment itself, the stability of the COD data segment can be obtained, and thus the possibility of the existence of noise data in the COD data segment can be obtained. However, the values of the noise data may be close to the real COD data, so the stability obtained only through the data changes of the COD data itself cannot accurately identify the noise data close to the real data.

[0052] It needs to be further explained that in the sewage data, the higher the COD, the higher the concentration of organic matter in the sewage, and the more oxygen is required by microorganisms to degrade the organic matter, resulting in a decrease in the dissolved oxygen in the sewage; on the contrary, the lower the COD, the lower the concentration of organic matter in the sewage, and the lower the oxygen consumption of microorganisms. There is a good negative correlation between COD and dissolved oxygen.

[0053] Based on this, the embodiment of the present invention obtains the dissolved oxygen data having a negative correlation with the COD data segment, calculates the correlation between the two, and corrects the stability of the COD data segment through the correlation between the two.

[0054] Exemplarily, in the embodiment of the present invention, obtaining the dissolved oxygen data segment corresponding to the COD data segment in the time series of dissolved oxygen data includes: preprocessing the collected dissolved oxygen data to obtain the time series of dissolved oxygen data; obtaining the corresponding dissolved oxygen data segment from the time series of dissolved oxygen data within the same collection period of the COD data segment.

[0055] Among them, the number of COD data points in the COD data segment is the same as the number of dissolved oxygen data points in the dissolved oxygen data segment and they correspond one by one.

[0056] Exemplarily, the dissolved oxygen content data can be collected by a dissolved oxygen detector. For the preprocessing, collection frequency, and collection duration, reference can be made to the preprocessing, collection frequency, and collection duration of COD data, which can be specifically set according to actual needs and will not be elaborated in the embodiments of the present invention.

[0057] Exemplarily, in the embodiments of the present invention, to determine the correlation between a COD data segment and the corresponding dissolved oxygen content data segment, reference can be specifically made to the following relational expression:

[0058] ;

[0059] In the formula, is the correlation between the th COD data segment and the corresponding dissolved oxygen content data segment, is the Pearson correlation coefficient between the th COD data segment and the corresponding dissolved oxygen content data segment, is the number of COD data points in the th COD data segment, , are respectively the maximum values in the th COD data segment and the corresponding dissolved oxygen content data segment, , are respectively the values of the th COD data point in the th COD data segment and the th dissolved oxygen content data point in the corresponding dissolved oxygen content data segment, , are respectively the ranges in the th COD data segment and the corresponding dissolved oxygen content data segment, is the exponential function with base e.

[0060] In the above formula, represents the degree of correlation between the th COD data segment and the corresponding dissolved oxygen content data segment. The smaller this value is, the closer the Pearson correlation coefficient between the th COD data segment and the corresponding dissolved oxygen content data segment is to -1, indicating a stronger negative correlation between the COD data and the dissolved oxygen content data during the collection period of the th COD data segment, and a lower possibility of noise data existing in the COD data during this collection period, that is, a lower possibility of noise data existing in the th COD data segment.

[0061] represents the th COD data point in the th COD data segment at the The relative size in a COD data segment, indicating the relative size of the oxygen dissolved amount data point corresponding to the

[0062] oxygen dissolved amount data segment in the oxygen dissolved amount data segment where the oxygen dissolved amount data point is located. indicating the negative correlation degree between the COD data segment and the corresponding oxygen dissolved amount data segment. The smaller this value is, the stronger the negative correlation between the COD data and the oxygen dissolved amount data during the acquisition period of the COD data segment, and the lower the possibility of noise data existing in the

[0063] COD data segment.

[0064] S4: Obtain the reliability of the COD data segment through the correlation between the COD data segment and the corresponding oxygen dissolved amount data segment and the stability of the COD data segment; preset the window length of the COD data point, set the window position based on the reliability of the COD data segments on the left and right sides of the COD data point, and denoise the COD data time series through the data in the window.

[0065] Among them, the window length of the COD data point is the number of COD data points included in the window. The window length can be preset to 15, and can be specifically set according to actual needs. The embodiments of the present invention do not limit this too much here.

[0066] Exemplarily, in the embodiments of the present invention, obtaining the reliability of the COD data segment through the correlation between the COD data segment and the corresponding oxygen dissolved amount data segment and the stability of the COD data segment includes: multiplying the correlation between the COD data segment and the corresponding oxygen dissolved amount data segment by the stability of the COD data segment and then performing normalization processing to obtain the reliability of the COD data segment.

[0067] It should be noted that based on the above steps, the reliability of the COD data segments on the left and right sides of any COD data point can be obtained. The higher the reliability, the lower the possibility of noise data existing in the COD data segment, and the higher the data authenticity. When constructing the window for filtering the corresponding COD data point, more COD data points can be obtained in the COD data segment with higher reliability. Based on this, the window of the COD data point can be constructed.

[0068] Exemplarily, in the embodiments of the present invention, the window position is set based on the reliability of the COD data segments on the left and right sides of the COD data point. Specifically, reference can be made to the following relational expressions:

[0069] ;

[0070] In the formula, is the length of the left end position of the window of the i-th COD data point, , are the reliabilities of the COD data segments on the left and right sides of the i-th COD data point respectively, is the window length of the COD data point, is the floor function symbol.

[0071] ;

[0072] In the formula, is the length of the right end position of the window of the i-th COD data point, is the length of the left end position of the window of the i-th COD data point, is the window length of the COD data point.

[0073] After obtaining the windows of each COD data point based on the above steps, the windows of each COD data point can be used for filtering and denoising in the SG filtering algorithm.

[0074] Exemplarily, in the embodiments of the present invention, denoising of the COD data time series is achieved through the data in the window, including: using the windows of each COD data point in the SG filtering algorithm to perform denoising processing on the COD data time series.

[0075] Specifically, when using the windows of each COD data point in the SG filtering algorithm to perform denoising processing on the COD data time series, a preset polynomial order can be set, and based on the preset polynomial order, the window of the COD data point is fitted to obtain polynomial coefficients; through the polynomial coefficients and the data values within the window of the COD data point, the filtered value of this COD data point is obtained; similarly, the filtered values of all COD data points in the COD data time series are obtained.

[0076] Among them, the preset polynomial order can be specifically set to 1, and can be specifically set according to actual needs. The specific steps of denoising the COD data time series through the SG filtering algorithm can be implemented by the prior art, and the embodiments of the present invention will not elaborate herein.

[0077] After denoising the COD data time series based on the above steps, its evaluation result can be obtained based on the denoised COD data time series.

[0078] S5: Obtain the sewage treatment evaluation result based on the denoised COD data time series.

[0079] It should be noted that the degree of abnormality of the COD data can be an important indicator for evaluating the sewage treatment effect. Based on this, in the embodiments of the present invention, the degree of abnormality is obtained by performing anomaly detection on the denoised COD data time series.

[0080] Exemplarily, in the embodiments of the present invention, obtaining the sewage treatment evaluation result based on the denoised COD data time series includes: performing anomaly detection on the denoised COD data time series through the box plot algorithm, and obtaining the sewage treatment evaluation result based on the comparison result between the proportion of abnormal data points in the COD data time series and a preset threshold.

[0081] Among them, the preset threshold can be set to 0.01; specifically, the threshold can be set according to actual needs, and the embodiments of the present invention do not limit this too much here.

[0082] Specifically, when performing anomaly detection on the denoised COD data time series through the box plot algorithm, the denoised COD data time series can be sorted first to obtain the median, upper quartile, and lower quartile in the denoised COD data time series, draw a box plot based on the median, upper quartile, and lower quartile, determine the inner limit in the box plot, and record the COD data points outside the inner limit position as abnormal data points.

[0083] Among them, the specific steps of performing anomaly detection on the denoised COD data time series through the box plot algorithm can be implemented by the prior art, and the embodiments of the present invention do not elaborate here.

[0084] Exemplarily, in the embodiments of the present invention, obtaining the sewage treatment evaluation result based on the comparison result between the proportion of abnormal data points in the COD data time series and a preset threshold includes: if the proportion of abnormal data points is greater than the preset threshold, the sewage treatment evaluation result is average; otherwise, the sewage treatment evaluation result is good.

[0085] It can be understood that if the proportion of abnormal data points is greater than the preset threshold, it means that there are more abnormal data points in the denoised COD data time series, the degree of abnormality of the COD data is higher, indicating that the current sewage treatment effect of improving water quality is poor. If the proportion of abnormal data points is not greater than the preset threshold, it means that the number of abnormal data points in the denoised COD data time series is small, the degree of abnormality of the COD data is low, indicating that the current sewage treatment effect of improving water quality is good.

[0086] After obtaining the sewage treatment evaluation result based on the above steps, a report can also be generated according to the historically collected COD data and the corresponding sewage treatment evaluation results, so as to facilitate the analysis of the long-term trend and periodic changes of sewage treatment.

[0087] Exemplarily, in the embodiment of the present invention, after obtaining the sewage treatment evaluation result, it further includes: generating an evaluation report from the denoised COD data time series and the corresponding sewage treatment evaluation result.

[0088] Among them, the specific steps of generating the evaluation report can be implemented by existing technologies, and the embodiments of the present invention will not elaborate herein.

[0089] It can be seen that in the embodiment of the present invention, when determining the sewage treatment evaluation result, COD data segments on the left and right sides of the COD data point can be respectively obtained in the COD data time series, and the dissolved oxygen data segments corresponding to the COD data segments can be obtained in the dissolved oxygen data time series; the stability of the COD data segment can be obtained through the data fluctuation condition in the COD data segment; the correlation between the COD data segment and the corresponding dissolved oxygen data segment can be calculated; the reliability of the COD data segment can be obtained through the correlation between the COD data segment and the corresponding dissolved oxygen data segment and the stability of the COD data segment; a window length of the COD data point is preset, the window position is set based on the reliability of the COD data segments on the left and right sides of the COD data point, and the denoising of the COD data time series is realized through the data in the window; the sewage treatment evaluation result is obtained based on the denoised COD data time series.

[0090] In this way, in the embodiment of the present invention, the sewage treatment evaluation result is obtained by denoising the COD data time series, which can effectively reduce the influence of noise data on the accuracy of the sewage treatment evaluation result. In this process, the embodiment of the present invention considers that when constructing the window for filtering the COD data point, data points with higher noise performance may be included in the COD data point window, resulting in poor filtering effect. Based on this, the embodiment of the present invention analyzes the data fluctuation conditions of the data segments on the left and right sides of the COD data point, obtains more data points in the COD data segment with higher stability, reduces the influence of data points with higher noise performance on the filtering effect, and improves the accuracy of denoising the COD data time series; on this basis, the embodiment of the present invention also considers that some noise data may be relatively similar to the COD data itself, so the stability of the COD data segment is further verified by further obtaining the dissolved oxygen data correlated with the COD data, effectively improving the accuracy of constructing the window for the COD data point, and thus effectively improving the accuracy of the sewage treatment evaluation result.

[0091] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for evaluating sewage treatment results, characterized in that: include: In the COD data time series of sewage, the COD data segments on the left and right sides of the COD data point are obtained respectively, and in the dissolved oxygen data time series, the dissolved oxygen data segment corresponding to the COD data segment is obtained; The stability of the COD data segment is obtained through the data fluctuation in the COD data segment, satisfying the relationship: , For the The stability of each COD data segment, For the All data points in the COD data segment are consistent with the The mean of the absolute values ​​of the differences between the means of the COD data segments, For the The mean of the absolute values ​​of the differences between all adjacent data points in a COD data segment, is an exponential function with e as the base; calculate the correlation between the COD data segment and the corresponding dissolved oxygen data segment: ； For the The correlation between each COD data segment and the corresponding dissolved oxygen data segment, For the The Pearson correlation coefficient between each COD data segment and the corresponding dissolved oxygen data segment, For the The number of COD data points in a COD data segment, , Respectively The maximum value of the COD data segment and the corresponding dissolved oxygen data segment, , Respectively The COD data segment and the corresponding dissolved oxygen data segment COD data points, The value of the dissolved oxygen data point, , Respectively The range of each COD data segment and the corresponding dissolved oxygen data segment; The reliability of the COD data segment is obtained by the correlation between the COD data segment and the corresponding dissolved oxygen data segment and the stability of the COD data segment, including: multiplying the correlation between the COD data segment and the corresponding dissolved oxygen data segment by the stability of the COD data segment and then performing normalization processing to obtain the reliability of the COD data segment; Preset the window length of the COD data point; set the window position based on the reliability of the COD data segments on the left and right sides of the COD data point, including: , ; is the length of the left end position of the window of the i-th COD data point, , are the reliability of the COD data segments on the left and right of the i-th COD data point, The window length of COD data points is the number of COD data points contained in the window. is the floor symbol, is the length of the right end position of the window of the i-th COD data point; the COD data time series sequence is denoised through the data in the window; and the sewage treatment evaluation result is obtained based on the denoised COD data time series sequence.

2. A method for evaluating sewage treatment results according to claim 1, characterized in that: Get the COD data segment and the corresponding dissolved oxygen data segment, which also includes: After collecting COD data and dissolved oxygen data, preprocessing is performed to obtain COD data time series and dissolved oxygen data time series.

3. A method for evaluating sewage treatment results according to claim 1, characterized in that: The denoising of the COD data time series is achieved through the data in the window, including: In the SG filtering algorithm, the window of each COD data point is used to denoise the COD data time series.

4. A method for evaluating sewage treatment results according to claim 1, characterized in that: The sewage treatment assessment result is obtained based on the denoised COD data time series, including: The box plot algorithm is used to detect anomalies in the denoised COD data time series, and the sewage treatment assessment results are obtained based on the comparison between the proportion of abnormal data points in the COD data time series and the preset threshold.

5. A method for evaluating sewage treatment results according to claim 4, characterized in that: The sewage treatment evaluation result is obtained, and then further includes: An assessment report is generated based on the denoised COD data time series and the corresponding sewage treatment assessment results.

Images