Fine filtration method and system for sewage treatment monitoring

Abstract

The application relates to the sewage treatment technical field, in particular to a fine filtration method and system for sewage treatment monitoring, which comprises the following steps: acquiring sewage index change sequences of various sewage measurement indexes; constructing sewage characteristic change sequences of each sewage measurement index at each collection time; determining pollution trend change indexes and sewage level stability characteristic indexes of each sewage measurement index at each collection time, and then calculating sewage pollution change characteristic indexes of each sewage measurement index at each collection time; determining filtration characteristic variation degrees and adjacent filtration performance difference degrees of each sewage measurement index at each collection time, calculating filtration blocking characteristic indexes, determining filtration blocking characteristic evaluation indexes at each collection time, judging ceramic membrane filtration conditions by combining an abnormality detection algorithm, and completing fine filtration of the ceramic membrane. The application can accurately analyze the ceramic membrane filtration process, determine whether the ceramic membrane needs to be cleaned, and improve the fine filtration efficiency of the ceramic membrane.

Description

TECHNICAL FIELD

[0001] The present application relates to the sewage treatment technical field, and in particular to a fine filtration method and system for sewage treatment monitoring. BACKGROUND

[0002] With the improvement of industrial production technology and people's living standards, the scale of sewage discharge is showing a rapid growth trend, and people are paying more and more attention to sewage treatment and putting forward more stringent requirements for sewage treatment. In order to ensure that sewage treatment meets the specified discharge requirements, it is often necessary to strictly monitor sewage treatment, and the rationality of the current sewage treatment monitoring technology application is of great significance to ensure that the sewage discharge meets the standards.

[0003] With the development of sewage treatment technology, ceramic membranes are increasingly used in sewage treatment. Ceramic membranes are often used for sewage filtration. Compared with traditional separation and purification filtration technology, ceramic membranes have good stability, uniform pore size distribution, high temperature resistance and corrosion resistance, and can be effectively applied to sewage treatment to ensure that the sewage treatment meets the discharge standards.

[0004] However, as the service life of ceramic membranes is prolonged, the adhesion and accumulation of pollutants on the ceramic membranes will affect the filtration performance of the ceramic membranes, and the ceramic membrane surface will be cleaned regularly. In order to improve the filtration efficiency of the ceramic membranes, the process of sewage treatment using ceramic membranes is often monitored, and abnormal detection methods are used to identify abnormal conditions of the ceramic membrane filtration, and then the ceramic membrane surface is cleaned, so as to avoid regular cleaning of the ceramic membrane surface and reduce the filtration efficiency of the ceramic membranes. However, due to the complexity of the sewage treatment process, the traditional abnormal detection method often cannot accurately identify the status of the ceramic membrane filtration process, thereby affecting the cleaning of the ceramic membrane surface and resulting in the inability to effectively improve the filtration efficiency of the ceramic membranes. SUMMARY

[0005] To solve the above technical problems, the purpose of the present application is to provide a fine filtration method and system for sewage treatment monitoring, and the technical solution adopted is as follows:

[0006] In a first aspect, the present application provides a fine filtration method for sewage treatment monitoring, which comprises the following steps:

[0007] Collecting data of each sewage measurement index of the water quality after fine filtration of the ceramic membrane, and arranging the data in ascending order of time to form a sewage index change sequence of each sewage measurement index;

[0008] constructing a sewage characteristic change sequence of each sewage measurement index at each collection time based on the change sequence of the sewage index;

[0009] determining a sewage pollution change characteristic index of each sewage measurement index at each collection time based on the pollution trend change index and the pollution level stability characteristic index;

[0010] determining a filtering characteristic variation degree and a neighboring filtering performance difference degree of each sewage measurement index at each collection time based on the difference and change degree of the sewage pollution change characteristic index of each sewage measurement index at each collection time and the collection time adjacent to each collection time;

[0011] determining a filtering resistance characteristic index of each sewage measurement index at each collection time based on the sewage pollution change characteristic index, the filtering characteristic variation degree and the neighboring filtering performance difference degree of each sewage measurement index at each collection time;

[0012] taking the average of the filtering resistance characteristic indexes of all sewage measurement indexes at each collection time as a filtering resistance characteristic evaluation index of each collection time;

[0013] determining the ceramic membrane filtration based on the filtering resistance characteristic evaluation index by using an anomaly detection algorithm, and completing fine filtration of the ceramic membrane.

[0014] Preferably, the sewage characteristic change sequence of each sewage measurement index at each collection time is constructed, including:

[0015] taking all data of each sewage measurement index at each collection time in the sewage index change sequence as the input of the density peak value clustering algorithm, and outputting all data within the neighborhood cutting distance range of the data at each collection time by the density peak value clustering algorithm, and arranging all data within the neighborhood cutting distance range of the data at each collection time in ascending order of time to form the sewage characteristic change sequence corresponding to each collection time of each sewage measurement index.

[0016] Preferably, the pollution trend change index of each sewage measurement index at each collection time is determined based on the change of the data in the sewage characteristic change sequence, including:

[0017] the trend change sequence of each sewage measurement index at each collection time is obtained by performing a detrended fluctuation analysis on the sewage characteristic change sequence of each sewage measurement index at each collection time, the absolute value of the difference between the sewage characteristic change sequence at each collection time and the data at the same position in the detrended sewage characteristic sequence is calculated, and all the absolute values are arranged in ascending order of time to form the trend change sequence of each sewage measurement index at each collection time;

[0018] the pollution trend change index of the ith sewage measurement index at the jth collection time is denoted as the expression is:

[0019]

[0020] wherein N represents the number of data in the trend change sequence of the ith sewage measurement index at the jth collection time, exp() is an exponential function with a natural constant as the base number, represents the standard deviation of all data in the detrended sewage characteristic sequence of the ith sewage measurement index at the jth collection time, and respectively represent the s-th and s-1-th data in the trend change sequence of the ith sewage measurement index at the jth collection time, and ∈ is a coordination factor.

[0021] Preferably, the pollution level stability characteristic index of each sewage measurement index at each collection time is determined based on the information entropy and data distribution of the sewage characteristic change sequence, and the pollution change characteristic index of each sewage measurement index at each collection time is determined based on the pollution trend change index and the pollution level stability characteristic index, and the pollution change characteristic index of each sewage measurement index at each collection time is determined based on the pollution trend change index and the pollution level stability characteristic index, and the pollution change characteristic index of each sewage measurement index at each collection time is determined based on the pollution trend change index and the pollution level stability characteristic index.

[0022] for the sewage characteristic change sequence of each sewage measurement index at each collection time;

[0023] the information entropy and the mean value of all data in the sewage characteristic change sequence are calculated, the absolute value of the difference between each data in the sewage characteristic change sequence and the mean value is calculated, the sum of the absolute value and a preset coordination factor is obtained, and the reciprocal of the information entropy is taken as the index of an exponential function with a natural constant as the base number;

[0024] the ratio of the calculation result of the exponential function to the sum value is obtained;

[0025] the mean value of the ratio of all data in the sewage characteristic change sequence is taken as the pollution level stability characteristic index of each sewage measurement index at each collection time.

[0026] Preferably, the pollution change characteristic index of each sewage measurement index at each collection time is determined based on the pollution trend change index and the pollution level stability characteristic index, and the pollution change characteristic index of each sewage measurement index at each collection time is determined based on the pollution trend change index and the pollution level stability characteristic index, and the pollution change characteristic index of each sewage measurement index at each collection time is determined based on the pollution trend change index and the pollution level stability characteristic index, and the pollution change characteristic index of each sewage measurement index at each collection time is determined based on the pollution trend change index and the pollution level stability characteristic index.

[0027] The sum of the pollution level stability characteristic index of each sewage measurement index at each collection time and the preset coordination factor, the ratio of the pollution trend index of each sewage measurement index at each collection time to the sum, is taken as the sewage pollution change characteristic index of each sewage measurement index at each collection time.

[0028] Preferably, the filtering characteristic variation degree comprises:

[0029] The sewage pollution change characteristic indexes of each sewage measurement index at all collection times are arranged in a sequence in ascending order of time to form a pollution degree change characteristic sequence of each sewage measurement index;

[0030] In the pollution degree change characteristic sequence of each sewage measurement index, the pollution degree change indexes of each collection time and a preset number of collection times before and after each collection time are arranged in ascending order of time to form a filtering performance evaluation sequence of each collection time of each sewage measurement index;

[0031] The filtering performance evaluation sequence of each collection time of each sewage measurement index, the absolute value of the difference between any two data in the filtering performance evaluation sequence, the coefficient of variation of the filtering performance evaluation sequence, the mean of the product of the absolute value between any two data in the filtering performance evaluation sequence and the coefficient of variation, are calculated, and the mean is taken as the filtering characteristic variation degree of each sewage measurement index at each collection time.

[0032] Preferably, the adjacent filtering performance difference degree comprises:

[0033] The dtw distances between the filtering performance evaluation sequences of each collection time of each sewage measurement index and the adjacent collection times before and after each collection time are calculated respectively, and the sum of the two dtw distances is taken as the adjacent filtering performance difference degree of each sewage measurement index at each collection time.

[0034] Preferably, the determination of the filtering resistance characteristic index of each sewage measurement index at each collection time comprises:

[0035] The product of the filtering characteristic variation degree and the adjacent filtering performance difference degree of each sewage measurement index at each collection time is calculated, the inverse of the product is taken as the index of the exponential function with the natural constant as the base number, the sum of the sewage pollution change characteristic index of each sewage measurement index at each collection time and the preset coordination factor is obtained;

[0036] The ratio of the calculation result of the exponential function to the sum is calculated;

[0037] The difference between the number 1 and the ratio is taken as the filtering resistance characteristic index of each sewage measurement index at each collection time.

[0038] Preferably, the filtration resistance characteristic evaluation index is used to determine the ceramic membrane filtration condition by using an anomaly detection algorithm, including:

[0039] The LOF value of the filtration resistance characteristic evaluation index of each collection time is obtained by using the anomaly detection algorithm, if the LOF values of multiple filtration resistance characteristic evaluation indexes are higher than the preset anomaly detection threshold, the ceramic membrane filtration is abnormal, and the ceramic membrane is cleaned; otherwise, the ceramic membrane filtration is normal.

[0040] In a second aspect, the embodiments of the present application also provide a fine filtration system for sewage treatment monitoring, including a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the steps of the method of any one of the above when executing the computer program.

[0041] The present application has at least the following beneficial effects:

[0042] Based on the analysis of the ceramic membrane filtration effluent water quality pollution characteristics, the sewage pollution change characteristic index is constructed, which reflects the change of the sewage pollution degree of different sewage treatment indexes at different collection times, can effectively avoid the problem of low precision in the single sewage index analysis process, and the greater the change of the sewage pollution degree, the worse the effect of the ceramic membrane fine filtration; based on the analysis of the blocking effect during the ceramic membrane filtration, the filtration resistance characteristic index is constructed, which reflects the abnormal characteristic size of the filtration resistance effect of the ceramic membrane filtration at different collection times; based on the data fusion method, the filtration resistance characteristic evaluation index is constructed, which is used to comprehensively evaluate the abnormal characteristic size of the filtration resistance effect of the ceramic membrane filtration at different collection times; based on the filtration resistance characteristic evaluation index, the filtration resistance characteristic evaluation sequence is constructed, and the LOF anomaly detection algorithm is used to identify whether the ceramic membrane filtration is abnormal, so as to determine the cleaning time of the ceramic membrane;

[0043] The present application considers the ceramic membrane filtration effluent water quality pollution characteristics and the blocking effect during the ceramic membrane filtration, and then constructs the filtration resistance characteristic evaluation index, which can more accurately analyze the condition of the ceramic membrane filtration, and then clean the ceramic membrane, thereby improving the efficiency of the ceramic membrane fine filtration. BRIEF DESCRIPTION OF DRAWINGS

[0044] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the drawings needed in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0045] Figure 1A step flow chart of a fine filtration method for sewage treatment monitoring provided by an embodiment of the present application is shown in FIG. 1.

[0046] Figure 2 An extraction flow chart of filtration resistance characteristic evaluation indexes for each collection time is shown in FIG. 2. DETAILED DESCRIPTION

[0047] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined purposes, the specific embodiments, structures, features and effects of the fine filtration method and system for sewage treatment monitoring according to the present application are described in detail as follows in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0048] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0049] The specific scheme of the fine filtration method and system for sewage treatment monitoring provided by the present application is described in detail below in combination with the accompanying drawings.

[0050] Please refer to Figure 1 which shows a step flow chart of a fine filtration method for sewage treatment monitoring provided by an embodiment of the present application. The method comprises the following steps:

[0051] In step S001, sewage measurement index data of water quality after ceramic membrane fine filtration is collected, and the sewage measurement index data is preprocessed to obtain a sewage index change sequence.

[0052] The purpose of the present embodiment is to more accurately identify abnormal phenomena occurring during ceramic membrane fine filtration, so as to adaptively adjust the cleaning time of the ceramic membrane surface, thereby improving the efficiency of ceramic membrane fine filtration.

[0053] In the sewage treatment using the ceramic membrane for fine filtration, the pH value of the water quality is measured by the acidity meter, the COD content and the ammonia nitrogen content of the water quality are measured by the ammonia nitrogen double parameter measuring instrument respectively, and the turbidity of the water quality is measured by the turbidity measuring instrument. In this embodiment, the collection interval is 20 minutes, the collection frequency per day is 50, and the collection days are one week. The pH value, the COD content, the ammonia nitrogen content and the turbidity are respectively taken as each sewage measurement index. The implementer can determine the collection interval, the collection frequency per day and the collection days according to actual needs. It should be noted that the pH value, the COD content, the ammonia nitrogen content and the turbidity are common pollutant measurement indexes. In this embodiment, the sewage measurement indexes are collected according to the actual situation of sewage treatment. The implementer can collect other sewage treatment indexes to supplement or replace them according to the actual situation of sewage treatment.

[0054] Further, in order to facilitate subsequent analysis of abnormal phenomena occurring during fine filtration of the ceramic membrane, improve the accuracy of the analysis of abnormal phenomena, and avoid missing of measurement data, an average interpolation algorithm is used to perform average interpolation processing on the data to ensure data integrity. The sequence composed of each sewage measurement index data in ascending order of time is taken as a sewage index change sequence of each sewage measurement index. In this embodiment, the sewage index change sequence includes a pH value change sequence, a COD content change sequence, an ammonia nitrogen content change sequence and a turbidity change sequence. The average interpolation algorithm is a known technology, and the specific process is not described again.

[0055] At this point, the sewage index change sequence is obtained, which is used for subsequent accurate analysis of the fine filtration process of the ceramic membrane.

[0056] In step S002, the pollution trend change index and the pollution level stability characteristic index are calculated to obtain a sewage pollution change characteristic index. A pollution degree change characteristic sequence is constructed to obtain a filtration characteristic variation degree and a neighboring filtration performance difference degree. Based on this, a filtration blocking characteristic index is calculated to determine a filtration blocking characteristic evaluation index.

[0057] Generally, the pore size distribution of the ceramic membrane is uniform, and the ceramic membrane can effectively purify water quality by fine filtration of pollutants. However, due to the influence of the pollution degree of sewage, and with the use of the ceramic membrane, the pollutants are easy to adhere and accumulate on the membrane surface and in the membrane pores, which often leads to a decrease in membrane pore size and a decrease in membrane flux. This phenomenon is called membrane pollution phenomenon, which greatly affects the efficiency of fine filtration of the ceramic membrane.

[0058] In order to improve the efficiency of ceramic membrane fine filtration, it is often necessary to identify abnormal phenomena in the ceramic membrane fine filtration process, and then reasonably select the cleaning time of the ceramic membrane to reduce the influence of membrane pollution phenomenon on the filtration efficiency of the ceramic membrane. However, due to the complexity of the sewage treatment process, the traditional abnormality detection method often cannot accurately identify the abnormal phenomena occurring during the ceramic membrane filtration, thereby affecting the cleaning time of the ceramic membrane surface, resulting in the inability to effectively improve the filtration efficiency of the ceramic membrane. Therefore, it is necessary to more accurately analyze the abnormal phenomena occurring during the ceramic membrane fine filtration.

[0059] Specifically, in order to extract the purification characteristics of the sewage measurement index at different times, all data in the sewage index change sequence of each sewage measurement index is taken as the input of the DPC density peak clustering algorithm (Density Peaks Clustering, DPC), the preset cutoff distance parameter is 20, the output of the DPC density peak clustering algorithm is taken as all data in the neighborhood cutoff distance range of each data, and the sequence composed of all data in the neighborhood cutoff distance range of each data in ascending order of time is taken as the sewage feature change sequence corresponding to each collection time of each sewage measurement index. The DPC density peak clustering algorithm is a known technology, and the specific process will not be described again.

[0060] In order to accurately reflect the trend rule in the sewage feature change sequence, the sewage feature change sequence at each collection time is subjected to detrend analysis, so as to calculate the purification characteristic index at different times. In this embodiment, for each sewage measurement index, the sewage feature change sequence at each collection time is taken as the input of the DFA detrend fluctuation analysis algorithm (Detrended Fluctuation Analysis, DFA), the DFA detrend fluctuation analysis algorithm outputs the detrended sewage feature sequence at each collection time, the absolute value of the difference between the sewage feature change sequence at each collection time and the corresponding data at the same position in the detrended sewage feature sequence is calculated, and the sequence composed of all absolute values in ascending order of time is taken as the trend change sequence at each collection time of each sewage measurement index. The DFA detrend fluctuation analysis algorithm is a known technology, and the specific process will not be described again.

[0061] Further, based on the above analysis, the sewage pollution change characteristic index of each sewage measurement index at each collection time is calculated, which reflects the change of sewage pollution degree embodied by different sewage treatment indexes at different collection times. The greater the change of sewage pollution degree, the worse the effect of ceramic membrane fine filtration at this time. Its calculation formula is as follows:

[0062]

[0063] In the formula, represents the pollution trend index of the i-th sewage measurement index at the j-th collection time, N represents the number of data in the trend change sequence of the i-th sewage measurement index at the j-th collection time, exp() is the exponential function with the natural constant as the base, represents the standard deviation of all data in the detrended sewage characteristic sequence of the i-th sewage measurement index at the j-th collection time, and respectively represent the s-th and s-1-th data in the trend change sequence of the i-th sewage measurement index at the j-th collection time, ∈ is a coordination factor to avoid the denominator taking a value of 0, and the value of the coordination factor is 1;

[0064] represents the pollution level stability characteristic index of the i-th sewage measurement index at the j-th collection time, R represents the number of data in the sewage characteristic change sequence of the i-th sewage measurement index at the j-th collection time, represents the information entropy of all data in the sewage characteristic change sequence of the i-th sewage measurement index at the j-th collection time, represents the r-th data in the sewage characteristic change sequence of the i-th sewage measurement index at the j-th collection time, represents the mean of all data in the sewage characteristic change sequence of the i-th sewage measurement index at the j-th collection time, and the calculation of the information entropy is a known technology, and the specific process is not described again;

[0065] represents the sewage pollution change characteristic index of the i-th sewage measurement index at the j-th collection time.

[0066] Difference between data The greater the pollution trend index, the more significant the trend change of the data in the trend change sequence, which to some extent indicates that the purification capacity of the ceramic membrane filtration changes at this time, and the sewage treatment effect is worse at this time. At the same time, the standard deviation The greater the pollution trend index, the more significant the trend change of the data in the trend change sequence, which to some extent indicates that the purification capacity of the ceramic membrane filtration changes at this time, and the sewage treatment effect is worse at this time. At the same time, the standard deviation

[0067] Information entropy The greater the pollution trend index, the more significant the trend change of the data in the trend change sequence, which to some extent indicates that the purification capacity of the ceramic membrane filtration changes at this time, and the sewage treatment effect is worse at this time. At the same time, the standard deviation The greater the pollution trend index, the more significant the trend change of the data in the trend change sequence, which to some extent indicates that the purification capacity of the ceramic membrane filtration changes at this time, and the sewage treatment effect is worse at this time. At the same time, the standard deviation

[0068] Therefore, the pollution trend index The greater, the more stable the sewage treatment index The smaller, the weaker the stable change degree of the sewage treatment index, at this time the ceramic membrane filtration is more likely to appear abnormal conditions, resulting in a larger change in the degree of sewage pollution, and the greater the sewage pollution change characteristic index.

[0069] Based on the above analysis, the sewage pollution change characteristic index of each sewage measurement index at each collection time is obtained, which reflects the pollution change characteristics of the effluent quality at different times. The greater the sewage pollution change characteristic index, the greater the change in the degree of sewage pollution, and the worse the effect of ceramic membrane fine filtration at this time. The smaller the sewage pollution change characteristic index, the smaller the change in the degree of sewage pollution, that is, the better the stability of ceramic membrane filtration, and the better the effect of ceramic membrane fine filtration at this time.

[0070] Further, in order to more accurately identify the abnormal conditions of ceramic membrane filtration, the abnormal characteristics of the change in the degree of sewage pollution are extracted, and the filtration performance abnormal characteristics of the ceramic membrane are analyzed.

[0071] Specifically, the sewage pollution change characteristic index of each sewage measurement index at all collection times is arranged in ascending order of time to form a sequence as the pollution degree change characteristic sequence of each sewage measurement index. One sewage measurement index change corresponds to one pollution degree change characteristic sequence.

[0072] In order to analyze the filtration performance abnormal characteristics of each collection time, for the pollution degree change characteristic sequence of each sewage measurement index, the i-th sewage measurement index is taken as an example, and the pollution degree change index of each collection time and the pollution degree change index of each collection time before and after P collection times are arranged in ascending order of time to form a filtration performance evaluation sequence of each collection time.

[0073] Based on the above analysis, the filtration resistance characteristic index of each sewage measurement index at each collection time is calculated, which reflects the abnormal characteristic size of the filtration resistance effect of the ceramic membrane filtration at different collection times. Its calculation formula is as follows:

[0074]

[0075] In the formula, H represents the data number in the filtration performance evaluation sequence of the i-th sewage measurement index at the j-th collection time, and f i j,g and f i j,h respectively represent the g-th and h-th data in the filtration performance evaluation sequence of the i-th sewage measurement index at the j-th collection time, Coefficient of variation of all data in the filtration performance evaluation sequence of the i-th sewage measurement index at the j-th collection time, the calculation of the coefficient of variation is a known technology, and the specific process will not be described again.

[0076] Difference degree of adjacent filtration performance of the i-th sewage measurement index at the j-th collection time, dtw() is a dtw distance function, f i j-1 , f i j , f i j+1 respectively represent the filtration performance evaluation sequence of the i-th sewage measurement index at the j-1th, jth and j+1th collection time, dtw(f i j , f i j-1 ) represents the dtw distance between the filtration performance evaluation sequences of the i-th sewage measurement index at the jth and j-1th collection time, dtw(f i j , f i j+1 ) represents the dtw distance between the filtration performance evaluation sequences of the i-th sewage measurement index at the jth and j+1th collection time.

[0077] Filtration resistance characteristic index of the i-th sewage measurement index at the j-th collection time, exp() is an exponential function with natural constant as base, Sewage pollution change characteristic index of the i-th sewage measurement index at the j-th collection time, ∈ is a coordination factor to avoid the denominator taking value 0, and the value of the coordination factor is 1.

[0078] The difference between the data |f i j,g -f i j,h is larger, indicating that the difference between the data in the filtration performance evaluation sequence is larger, which to some extent indicates that abnormal fluctuations occur during ceramic membrane filtration, and it is more likely to be affected by the resistance during filtration. At the same time, the coefficient of variation is larger, which to some extent indicates that there is a larger fluctuation in the filtration performance during ceramic membrane filtration, and the variation characteristic of the data is stronger, which is more likely to be affected by the resistance during filtration, and the filtration characteristic variation degree is larger.

[0079] The greater the dtw distance between each collection time and the filtration performance evaluation sequence of the adjacent two collection times, the smaller the similarity between the filtration performance evaluation sequences, the worse the stability of the ceramic membrane filtration, the more likely the filtration performance to have greater difference, the more likely to be affected by the blocking effect during filtration, and the greater the adjacent filtration performance difference degree.

[0080] Therefore, the greater the filtration characteristic variation degree and the greater the adjacent filtration performance difference degree , the more likely it is to be affected by the blocking effect during filtration, and the greater the sewage pollution change characteristic index , the more likely it is that the ceramic membrane filtration will have abnormal conditions, resulting in a greater change in the degree of sewage pollution, and the greater the filtration blocking characteristic index.

[0081] Further, in order to more accurately identify the abnormal phenomena occurring during ceramic membrane filtration, based on the filtration blocking characteristic index, a data fusion method is adopted to calculate the filtration blocking characteristic evaluation index of each collection time, which is used to comprehensively evaluate the abnormal characteristic size of the filtration blocking effect of ceramic membrane filtration at different collection times. The calculation formula is as follows:

[0082]

[0083] In the formula, L j represents the filtration blocking characteristic evaluation index of the jth collection time, m represents the number of sewage measurement indexes, represents the filtration blocking characteristic index of the ith sewage measurement index at the jth collection time.

[0084] The greater the filtration blocking characteristic index , the greater the abnormal characteristic of the filtration blocking effect of ceramic membrane filtration at this time, and the greater the filtration blocking characteristic evaluation index. The extraction process of the filtration blocking characteristic evaluation index of each collection time is specifically shown in Figure 2 .

[0085] At this point, the filtration blocking characteristic evaluation index of each collection time is obtained, which is used for subsequent identification of abnormal phenomena occurring during fine ceramic membrane filtration.

[0086] Step S003, based on the filtration blocking characteristic evaluation index, obtain the filtration blocking characteristic evaluation sequence, use the anomaly detection algorithm to obtain the anomaly detection result based on the filtration blocking characteristic evaluation sequence, and detect and determine the fine ceramic membrane filtration process.

[0087] Further, to more accurately analyze the ceramic membrane fine filtration process, all filtration resistance characteristic evaluation indexes at the collection time are taken as inputs of a LOF (Local outlier factor) anomaly data detection algorithm, a preset neighborhood parameter is 15, and the LOF anomaly data detection algorithm outputs LOF values of the filtration resistance characteristic evaluation indexes in the filtration resistance characteristic evaluation sequence, wherein the LOF anomaly data detection algorithm is a known technology, and details are not described herein.

[0088] If the LOF values of the preset number of filtration resistance characteristic evaluation indexes are higher than the preset anomaly detection threshold, the ceramic membrane filtration in the corresponding time period is abnormal, and the ceramic membrane is cleaned at this time; otherwise, the ceramic membrane filtration in the corresponding time period is not abnormal, and the ceramic membrane is continuously used for fine filtration at this time, and the ceramic membrane does not need to be cleaned. In this embodiment, the preset number is 5, and the anomaly detection threshold is set to 1 in this embodiment.

[0089] At this point, according to the above process of this embodiment, whether the ceramic membrane needs to be cleaned is determined according to the analysis of each sewage measurement index of the water quality after the ceramic membrane filtration, so as to improve the efficiency of the ceramic membrane fine filtration.

[0090] Based on the same inventive concept as the above method, the embodiments of the present application also provide a fine filtration system for sewage treatment monitoring, which comprises a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the steps of any one of the above fine filtration methods for sewage treatment monitoring when executing the computer program.

[0091] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. Moreover, the above description is made for specific embodiments of the present application. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are possible or can be advantageous.

[0092] Each embodiment in the present specification is described in a progressive manner, and the same or similar parts between each embodiment can be referred to each other, and each embodiment mainly describes the differences from other embodiments.

[0093] The above only describes the preferred embodiments of the present application, and does not limit the present application. Any modification, equivalent replacement, improvement, etc. made within the principles of the present application shall be included in the protection scope of the present application.

Claims

1. A fine filtration method for sewage treatment monitoring, characterized by, The method comprises the following steps: Collecting data of each sewage measurement index of water quality after ceramic membrane fine filtration, and arranging the data in ascending order of time to form a sewage index change sequence of each sewage measurement index; Based on the sewage index change sequence, constructing a sewage characteristic change sequence of each sewage measurement index at each collection time; determining a pollution trend change index of each sewage measurement index at each collection time based on the change of data in the sewage characteristic change sequence; determining a pollution level stability characteristic index of each sewage measurement index at each collection time based on the information entropy and data distribution of the sewage characteristic change sequence; Based on the pollution trend change index and the pollution level stability characteristic index, determining a sewage pollution change characteristic index of each sewage measurement index at each collection time; Based on the difference and change degree of the sewage pollution change characteristic index of each sewage measurement index at each collection time, determining a filtration characteristic variation degree and a neighboring filtration performance difference degree of each sewage measurement index at each collection time; Based on the sewage pollution change characteristic index, the filtration characteristic variation degree and the neighboring filtration performance difference degree of each sewage measurement index at each collection time, determining a filtration resistance characteristic index of each sewage measurement index at each collection time; Taking the average value of the filtration resistance characteristic index of all sewage measurement indexes at each collection time as a filtration resistance characteristic evaluation index of each collection time; Based on the filtration resistance characteristic evaluation index, using an anomaly detection algorithm to determine the ceramic membrane filtration condition, and completing the fine filtration of the ceramic membrane; The method comprises the following steps: Performing detrended fluctuation analysis on the sewage characteristic change sequence of each sewage measurement index at each collection time to obtain a detrended sewage characteristic sequence at each collection time, calculating the absolute value of the difference between the data at the same position in the sewage characteristic change sequence and the detrended sewage characteristic sequence at each collection time, and arranging all the absolute values in ascending order of time to form a trend change sequence of each sewage measurement index at each collection time; The pollution trend index of the ith sewage measurement index at the jth collection time is denoted as , and the expression is: wherein, represents the number of data in the trend sequence of the i-th wastewater measurement index at the j-th collection time point, is an exponential function with a natural constant as the base number, represents the standard deviation of all data in the detrended wastewater characteristic sequence of the i-th wastewater measurement index at the j-th collection time point, and respectively represent the s-th and s-1-th data in the trend sequence of the i-th wastewater measurement index at the j-th collection time point, is a coordination factor; The method comprises the following steps: Calculating the product of the filtration characteristic variation degree and the neighboring filtration performance difference degree of each sewage measurement index at each collection time, taking the opposite number of the product as the index of an exponential function with a natural constant as the base, obtaining the sum of the sewage pollution change characteristic index and a preset coordination factor of each sewage measurement index at each collection time; Calculating the ratio of the calculation result of the exponential function and the sum; Taking the difference between the number 1 and the ratio as the filtration resistance characteristic index of each sewage measurement index at each collection time; The method comprises the following steps: Using an anomaly detection algorithm to obtain the LOF value of the filtration resistance characteristic evaluation index at each collection time, if the LOF values of multiple filtration resistance characteristic evaluation indexes are higher than a preset anomaly detection threshold, the ceramic membrane filtration is abnormal, and the ceramic membrane needs to be cleaned; otherwise, the ceramic membrane filtration is normal.

2. The fine filtration method for sewage treatment monitoring according to claim 1, characterized by, The sewage characteristic change sequence of each sewage measurement index at each collection time point is constructed, including: The data of all collection time points in the sewage index change sequence of each sewage measurement index is taken as the input of the density peak clustering algorithm, and the density peak clustering algorithm outputs all data within the neighborhood cutting distance range of the data of each collection time point. All data within the neighborhood cutting distance range of the data of each collection time point is arranged in ascending order of time to form the sewage characteristic change sequence corresponding to each collection time point of each sewage measurement index.

3. The fine filtration method for sewage treatment monitoring according to claim 1, characterized by, The sewage level stability characteristic index of each sewage measurement index at each collection time point is determined based on the information entropy and data distribution of the sewage characteristic change sequence, including: For the sewage characteristic change sequence of each sewage measurement index at each collection time point; The information entropy and mean value of all data in the sewage characteristic change sequence are calculated, the absolute value of the difference between each data in the sewage characteristic change sequence and the mean value is calculated, the sum of the absolute value and a preset coordination factor is obtained, and the reciprocal of the information entropy is taken as the index of an exponential function with a natural constant as the base number; The ratio of the calculation result of the exponential function to the sum value is obtained; The mean value of the ratio of all data in the sewage characteristic change sequence is taken as the sewage level stability characteristic index of each sewage measurement index at each collection time point.

4. The fine filtration method for sewage treatment monitoring according to claim 1, characterized by, The sewage pollution change characteristic index of each sewage measurement index at each collection time point is determined based on the pollution trend change index and the sewage level stability characteristic index, including: The sum of the sewage level stability characteristic index of each sewage measurement index at each collection time point and a preset coordination factor is obtained, and the ratio of the pollution trend change index of each sewage measurement index at each collection time point to the sum is taken as the sewage pollution change characteristic index of each sewage measurement index at each collection time point.

5. The fine filtration method for sewage treatment monitoring according to claim 1, characterized by, The filtration characteristic variation degree includes: The sewage pollution change characteristic index of each sewage measurement index at all collection time points is arranged in ascending order of time to form a sequence, which is taken as the pollution degree change characteristic sequence of each sewage measurement index; The pollution degree change index of each collection time point and a preset number of collection time points before and after each collection time point in the pollution degree change characteristic sequence of each sewage measurement index is arranged in ascending order of time to form the filtration performance evaluation sequence of each collection time point of each sewage measurement index; The filtration performance evaluation sequence of each collection time point of each sewage measurement index is calculated, the absolute value of the difference between any two data in the filtration performance evaluation sequence is calculated, the coefficient of variation of the filtration performance evaluation sequence is calculated, and the mean value of the product of the absolute value between all arbitrary two data in the filtration performance evaluation sequence and the coefficient of variation is taken as the filtration characteristic variation degree of each sewage measurement index at each collection time point.

6. The fine filtration method for sewage treatment monitoring according to claim 5, characterized by, The adjacent filtration performance difference degree includes: The dtw distance between the filtration performance evaluation sequence of each collection time point of each sewage measurement index and the filtration performance evaluation sequence of adjacent previous and subsequent collection time points is calculated, and the sum of the two dtw distances is taken as the adjacent filtration performance difference degree of each sewage measurement index at each collection time point.

7. A fine filtration system for sewage treatment monitoring, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, The processor executes the computer program to realize the steps of the method of any one of claims 1-6.

Images