Fine filtering method and system for sewage treatment monitoring

Abstract

The invention relates to the technical field of sewage treatment, in particular to a fine filtering method and system for sewage treatment monitoring, and the method comprises the following steps: obtaining a sewage index change sequence of each sewage measurement index; constructing a sewage characteristic change sequence of each sewage measurement index at each collection moment, determining a pollution tendency gradient index and a sewage stable characteristic index of each sewage measurement index at each collection moment, and further calculating a sewage pollution change characteristic index of each sewage measurement index at each collection moment; and determining the filtering characteristic variation degree and the adjacent filtering performance difference degree of each sewage measurement index at each acquisition moment so as to calculate a filtering retardation characteristic index, determining a filtering retardation characteristic evaluation index at each acquisition moment, and judging the filtering condition of the ceramic membrane in combination with an anomaly detection algorithm so as to finish fine filtering of the ceramic membrane. The method can accurately analyze the filtering process of the ceramic membrane to judge whether the ceramic membrane needs to be cleaned or not, so that the fine filtering efficiency of the ceramic membrane is improved.

Description

Technical Field

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

[0002] With the improvement of industrial production technology and people's living standards, the scale of sewage discharge has shown a rapid growth trend. 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 prescribed discharge requirements, strict monitoring of sewage treatment is often required. The rational application of sewage treatment monitoring technology is currently of great significance to ensure that sewage discharge meets the standards.

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

[0004] However, as the life cycle of ceramic membranes increases, pollutants adhere to and accumulate on the ceramic membranes, affecting their filtration performance. Therefore, most membrane surfaces are cleaned regularly. To improve the filtration efficiency of ceramic membranes, the sewage treatment process using ceramic membranes is often monitored, and anomaly detection methods are used to identify anomalies in the filtration process. The membrane surface is then cleaned, thereby avoiding regular cleaning of the membrane surface and reducing the filtration efficiency. However, due to the complexity of the sewage treatment process, traditional anomaly detection methods are often unable to accurately identify conditions during the filtration process, which affects the cleaning of the membrane surface and makes it impossible to effectively improve the filtration efficiency of the membrane. Summary of the Invention

[0005] In order to solve the above technical problems, the purpose of this application is to provide a fine filtration method and system for sewage treatment monitoring. The technical solutions adopted are as follows:

[0006] In a first aspect, an embodiment of the present application provides a fine filtration method for sewage treatment monitoring, the method comprising the following steps:

[0007] Collect data on various sewage measurement indicators of water quality after fine filtration by ceramic membranes, and arrange them in ascending time order to form a sewage indicator change sequence of each sewage measurement indicator;

[0008] Based on the sewage index change sequence, a sewage characteristic change sequence for each sewage measurement index at each collection time is constructed; based on the change of data in the sewage characteristic change sequence, the pollution trend variation 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, the sewage stability characteristic index of each sewage measurement index at each collection time is determined;

[0009] Based on the pollution trend variation index and sewage stability characteristic index, the sewage pollution variation characteristic index of each sewage measurement indicator at each collection time is determined;

[0010] Based on the difference and degree of change in the sewage pollution change characteristic index of each sewage measurement indicator at each collection time and the neighboring collection time, the filtration characteristic variation and the neighboring filtration performance difference of each sewage measurement indicator at each collection time are determined;

[0011] Based on the sewage pollution change characteristic index, filtration characteristic variation and adjacent filtration performance difference of each sewage measurement indicator at each collection time, the filtration retardation characteristic index of each sewage measurement indicator at each collection time is determined;

[0012] The average of the filtration retardation characteristic indexes of all sewage measurement indicators at each collection time is used as the filtration retardation characteristic evaluation index at each collection time;

[0013] Based on the filtration blockage characteristic evaluation index and using the anomaly detection algorithm, the filtration condition of the ceramic membrane is judged to complete the fine filtration of the ceramic membrane.

[0014] Preferably, the step of constructing a sewage characteristic change sequence at each collection moment for each sewage measurement indicator includes:

[0015] The data of all collection moments in the sewage indicator change sequence of each sewage measurement indicator are used as the input of the density peak clustering algorithm. The density peak clustering algorithm outputs all data within the neighborhood cutoff distance of the data at each collection moment. All data within the neighborhood cutoff distance of the data at each collection moment are arranged in ascending order of time to form the sewage characteristic change sequence corresponding to each collection moment of each sewage measurement indicator.

[0016] Preferably, the method of determining the pollution trend variation index of each sewage measurement indicator at each collection moment based on the change of data in the sewage characteristic change sequence includes:

[0017] Performing a detrended fluctuation analysis on the sewage characteristic change sequence at each collection moment for each sewage measurement indicator to obtain a detrended sewage characteristic sequence at each collection moment, calculating the absolute value of the difference between the sewage characteristic change sequence at each collection moment and the data at the same position in the detrended sewage characteristic sequence, and arranging all the absolute values of the difference in ascending time order to form a trend change sequence for each sewage measurement indicator at each collection moment;

[0018] The pollution trend variation index of the i-th sewage measurement index at the j-th collection time is recorded as The expression is:

[0019]

[0020] Where N represents the number of data in the trend change sequence of the i-th sewage measurement indicator at the j-th collection moment, exp() is an exponential function with a natural constant as the base, It represents the standard deviation of all data in the detrended sewage characteristic sequence of the i-th sewage measurement indicator at the j-th collection moment, and They respectively represent the sth and s-1th data in the trend change sequence of the i-th sewage measurement indicator at the j-th collection moment, and ∈ is the coordination factor.

[0021] Preferably, the method of determining the sewage stationary characteristic index of each sewage measurement indicator at each collection moment based on the information entropy and data distribution of the sewage characteristic change sequence includes:

[0022] For each sewage measurement indicator, the sewage characteristic change sequence at each collection moment;

[0023] Calculating the information entropy and mean of all data in the sewage characteristic change sequence, calculating the absolute value of the difference between each data in the sewage characteristic change sequence and the mean, obtaining the sum of the absolute value of the difference and a preset coordination factor, and using the inverse of the information entropy as the exponent of an exponential function with a natural constant as the base;

[0024] Obtaining a ratio of a calculation result of the exponential function to the sum value;

[0025] The mean of the ratios of all data in the sewage characteristic change sequence is used as the sewage stable characteristic index of each sewage measurement indicator at each collection moment.

[0026] Preferably, the method of determining the sewage pollution change characteristic index of each sewage measurement indicator at each collection time based on the pollution trend variation index and the sewage stability characteristic index includes:

[0027] The sum of the sewage stability characteristic index of each sewage measurement indicator at each collection moment and the preset coordination factor is obtained, and the ratio of the pollution trend variation index of each sewage measurement indicator at each collection moment to the summation result is used as the sewage pollution change characteristic index of each sewage measurement indicator at each collection moment.

[0028] Preferably, the filtering feature variability includes:

[0029] The sequence of sewage pollution change characteristic indexes of each sewage measurement indicator at all collection moments in ascending time order is used as the pollution degree change characteristic sequence of each sewage measurement indicator;

[0030] The pollution degree change characteristic sequence of each sewage measurement indicator is composed of a preset number of pollution degree change indexes at each collection moment and before and after each collection moment, and arranged in ascending order of time to form a filtration performance evaluation sequence for each sewage measurement indicator at each collection moment;

[0031] The filtration performance evaluation sequence of each sewage measurement indicator at each collection moment 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 average of the product of the absolute value and the coefficient of variation between all any two data in the filtration performance evaluation sequence is used as the filtration characteristic variation of each sewage measurement indicator at each collection moment.

[0032] Preferably, the proximity filtering performance difference includes:

[0033] The DTW distances between each collection moment of each sewage measurement indicator and the filtration performance evaluation sequences of the adjacent collection moments are calculated respectively, and the sum of the two DTW distances is taken as the adjacent filtration performance difference of each sewage measurement indicator at each collection moment.

[0034] Preferably, the determining of the filtration retardation characteristic index of each sewage measurement indicator at each collection time includes:

[0035] Calculate the product of the filtration characteristic variation of each sewage measurement indicator at each collection time and the adjacent filtration performance difference, use the inverse of the product as the exponent of an exponential function with a natural constant as the base, and obtain the sum of the sewage pollution change characteristic index of each sewage measurement indicator at each collection time and a preset coordination factor;

[0036] Calculating a ratio of a calculation result of the exponential function to the sum value;

[0037] The difference between the number 1 and the ratio is used as the filtration retardation characteristic index of each sewage measurement indicator at each collection time.

[0038] Preferably, the method of determining the filtration condition of the ceramic membrane by using an abnormality detection algorithm based on the filtration retardation characteristic evaluation index includes:

[0039] An anomaly detection algorithm is used to obtain the LOF value of the filtration blockage characteristic evaluation index at each collection moment. If there are multiple LOF values of the filtration blockage characteristic evaluation index that are higher than the 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.

[0040] In a second aspect, an embodiment of the present application also provides 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, wherein the processor implements the steps of any one of the above methods when executing the computer program.

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

[0042] Based on the analysis of the water quality pollution characteristics of the effluent from ceramic membrane filtration, the present application constructs a sewage pollution change characteristic index, which reflects the changes in sewage pollution levels reflected by different sewage treatment indicators at different collection times, and can effectively avoid the problem of low accuracy in the analysis of a single sewage indicator. The greater the change in sewage pollution level, the worse the effect of fine filtration by the ceramic membrane. Based on the analysis of the blocking effect occurring during ceramic membrane filtration, a filtration blocking characteristic index is constructed to reflect the abnormal characteristic size of the filtration blocking effect occurring in ceramic membrane filtration at different collection times. Based on the data fusion method, a filtration blocking characteristic evaluation index is constructed to comprehensively evaluate the abnormal characteristic size of the filtration blocking effect occurring in ceramic membrane filtration at different collection times. Based on the filtration blocking characteristic evaluation index, a filtration blocking characteristic evaluation sequence is constructed to identify whether ceramic membrane filtration has abnormalities by utilizing the LOF anomaly detection algorithm, so as to determine the cleaning time of the ceramic membrane.

[0043] This application considers the water quality pollution characteristics of the effluent from ceramic membrane filtration and the blocking effect that occurs during ceramic membrane filtration, and then constructs a filtration blocking characteristic evaluation index to more accurately analyze the conditions during ceramic membrane filtration, and then cleans the ceramic membrane, thereby improving the efficiency of ceramic membrane fine filtration. BRIEF DESCRIPTION OF THE 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 following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0045] Figure 1A flowchart of a fine filtration method for sewage treatment monitoring provided in one embodiment of the present application;

[0046] Figure 2 Schematic diagram of the extraction process of the filter retardation characteristic evaluation index at each acquisition time. DETAILED DESCRIPTION

[0047] To further illustrate the technical means and effectiveness of this application to achieve the intended invention objectives, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail the specific implementation, structure, features, and effectiveness of a fine filtration method and system for sewage treatment monitoring proposed in this application. In the following description, different references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

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

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

[0050] See also Figure 1 , which shows a flowchart of a fine filtration method for sewage treatment monitoring provided by an embodiment of the present application, the method comprising the following steps:

[0051] Step S001: collecting sewage measurement index data of water quality after fine filtration by a ceramic membrane, and pre-processing the sewage measurement index data to obtain a sewage index change sequence.

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

[0053] In wastewater treatment using ceramic membranes for fine filtration, this embodiment uses a pH meter to measure the pH value of the effluent water quality, uses an ammonia nitrogen dual-parameter meter to measure the COD content and ammonia nitrogen content of the effluent water quality, and uses a turbidity meter to measure the turbidity of the effluent water quality. In this embodiment, the collection interval is 20 minutes, the number of collections per day is 50, and the number of collection days is one week. The pH value, COD content, ammonia nitrogen content, and turbidity are used as each sewage measurement indicator. The implementer can determine the value of the collection interval, the number of collections per day, and the number of collection days according to actual needs. It should be noted that pH value, COD content, ammonia nitrogen content, and turbidity are common pollutant measurement indicators. This embodiment takes into account the actual situation of sewage treatment and collects the sewage measurement indicators. The implementer can collect other sewage treatment indicators to supplement or replace them according to the actual situation of sewage treatment.

[0054] Furthermore, to facilitate subsequent analysis of abnormal phenomena that occur during fine filtration of ceramic membranes, improve the accuracy of abnormal phenomenon analysis, and avoid missing measurement data, an average interpolation algorithm is used to perform average interpolation processing on the data to ensure data integrity. A sequence of each sewage measurement index data in ascending chronological order is used as the sewage index change sequence for 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 well-known technology, and the specific process will not be repeated here.

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

[0056] Step S002, calculate the pollution trend variation index and the sewage stability characteristic index to obtain the sewage pollution change characteristic index; construct a pollution degree change characteristic sequence, obtain the filtration characteristic variation and the adjacent filtration performance difference, based on which calculate the filtration blockage characteristic index, and determine the filtration blockage characteristic evaluation index.

[0057] Typically, ceramic membranes have a uniform pore size distribution, allowing them to effectively filter pollutants and purify water. However, due to the degree of sewage contamination and the increasing use of ceramic membranes, pollutants tend to adhere to and accumulate on the membrane surface and within the pores, often leading to a decrease in membrane pore size and flux. This phenomenon, known as membrane fouling, significantly impacts the efficiency of ceramic membrane fine filtration.

[0058] To improve the efficiency of ceramic membrane fine filtration, it is often necessary to identify anomalies during the process and then rationally select the membrane cleaning time to reduce the impact of membrane fouling on the filtration efficiency. However, due to the complexity of the wastewater treatment process, traditional anomaly detection methods often fail to accurately identify anomalies during ceramic membrane filtration, thus affecting the cleaning time of the ceramic membrane surface and failing to effectively improve the filtration efficiency of the ceramic membrane. Therefore, a more accurate analysis of anomalies during ceramic membrane fine filtration is needed.

[0059] Specifically, in order to extract the purification characteristics of sewage measurement indicators at different times, all data in the sewage indicator change sequence of each sewage measurement indicator are used as the input of the DPC density peak clustering algorithm (Density Peaks Clustering, DPC), the preset truncation distance parameter value is 20, and the output of the DPC density peak clustering algorithm is used as all data within the neighborhood truncation distance range of each data. A sequence composed of all data within the neighborhood truncation distance range of each data in ascending time order is used as the sewage characteristic change sequence corresponding to each collection moment of each sewage measurement indicator. The DPC density peak clustering algorithm is a well-known technology, and the specific process will not be repeated here.

[0060] In order to accurately reflect the trend law within the sewage characteristic change sequence, the sewage characteristic change sequence at each collection moment is subjected to detrending analysis, thereby calculating the purification characteristic index at different moments. In this embodiment, for each sewage measurement index, the sewage characteristic change sequence at each collection moment is used as the input of the DFA detrended fluctuation analysis algorithm (DFA), which outputs the detrended sewage characteristic sequence at each collection moment, calculates the absolute value of the difference between the sewage characteristic change sequence at each collection moment and the corresponding data at the same position in the detrended sewage characteristic sequence, and takes a sequence composed of all the absolute values of the difference in ascending time order as the trend change sequence at each collection moment of each sewage measurement index. The DFA detrended fluctuation analysis algorithm is a well-known technology, and the specific process will not be repeated here.

[0061] Furthermore, based on the above analysis, the sewage pollution change characteristic index of each sewage measurement indicator at each collection time is calculated, reflecting the change in sewage pollution degree reflected by different sewage treatment indicators at different collection times. The greater the change in sewage pollution degree, the worse the effect of ceramic membrane fine filtration. The calculation formula is as follows:

[0062]

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

[0064] represents the sewage stability characteristic index of the i-th sewage measurement indicator at the j-th collection time, R represents the number of data in the sewage characteristic change sequence of the i-th sewage measurement indicator 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 indicator at the j-th collection moment, represents the rth data in the sewage characteristic change sequence of the i-th sewage measurement indicator at the j-th collection moment, represents the mean value of all data in the sewage characteristic change sequence of the i-th sewage measurement indicator at the j-th collection moment, wherein the calculation of information entropy is a well-known technology and the specific process is not repeated here;

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

[0066] Differences between data The larger the value, the more significant the trend change of the data in the trend change sequence is. To a certain extent, it indicates that the purification capacity of the ceramic membrane filtration has changed. At this time, the sewage treatment effect is worse. At the same time, the standard deviation The larger the value is, the greater the degree of dispersion of the data in the detrended sewage characteristic sequence is, and the greater the change in sewage treatment indicators is. At this time, the stronger the trend characteristics of sewage pollution are, the greater the pollution trend variation index is.

[0067] Information entropy The larger the value is, the greater the degree of chaos in the data within the sewage characteristic change sequence, and the weaker the stable characteristics of the sewage treatment indicators. At this time, the ceramic membrane is more likely to have abnormal filtration conditions. At the same time, the difference between the data and the mean is greater. The larger the value is, the weaker the stability of the data in the sewage characteristic change sequence is, which shows that the filtration of ceramic membrane is more likely to have abnormal conditions, and the smaller the sewage stability characteristic index is;

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

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

[0070] Furthermore, in order to more accurately identify abnormal conditions occurring in ceramic membrane filtration, the abnormal characteristics of changes in sewage pollution levels are extracted, and the abnormal characteristics of the filtration performance of the ceramic membrane are analyzed.

[0071] Specifically, the sequence of sewage pollution change characteristic indices of each sewage measurement indicator at all collection moments in ascending time order is used as the pollution degree change characteristic sequence of each sewage measurement indicator. One sewage measurement indicator change corresponds to one pollution degree change characteristic sequence.

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

[0073] Based on the above analysis, the filtration retardation characteristic index of each sewage measurement indicator at each collection time is calculated to reflect the abnormal characteristic size of the filtration retardation effect of ceramic membrane filtration at different collection times. The calculation is shown as follows:

[0074]

[0075] Where, represents the filtration characteristic variation of the i-th sewage measurement index at the j-th collection time, H represents the number of data 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 They represent the gth and hth data in the filtration performance evaluation sequence of the jth collection moment of the i-th sewage measurement indicator, respectively. represents the coefficient of variation of all data in the filtration performance evaluation sequence of the i-th sewage measurement indicator at the j-th collection moment. The calculation of the coefficient of variation is a well-known technique, and the specific process will not be repeated here.

[0076] represents the difference in the neighboring filtration performance of the i-th sewage measurement index at the j-th collection time, dtw() is the dtw distance function, and f i j-1 、f i j 、f i j+1 They represent the filtration performance evaluation sequence of the j-1th, jth, and j+1th collection moments of the i-th sewage measurement indicator, dtw(f i j ,f i j-1 ) represents the dtw distance between the filtration performance evaluation sequences of the jth and j-1th collection moments of the i-th sewage measurement index, dtw(f i j ,f i j+1 ) represents the dtw distance between the filtration performance evaluation sequences of the jth and j+1th collection moments of the i-th sewage measurement indicator;

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

[0078] Differences between data |f i j,g -f i j,h The larger the coefficient of variation, the greater the difference in the data within the filtration performance evaluation sequence. To a certain extent, it indicates that abnormal fluctuations occurred during ceramic membrane filtration, and it is more likely that the filtration was affected by the blocking effect. The larger the value is, the greater the fluctuation of the filtration performance of the ceramic membrane. The stronger the variation characteristics of the data, the more likely it is that the filtration is affected by the blocking effect, and the greater the variation of the filtration characteristics.

[0079] The larger the dtw distance between each acquisition time and the filtration performance evaluation sequences of the two adjacent acquisition times, the smaller the similarity between the filtration performance evaluation sequences. In this case, the stability of the ceramic membrane filtration is poorer, the filtration performance is more likely to have a large difference, and the filtration is more likely to be affected by the blocking effect during filtration, and the greater the difference in adjacent filtration performance.

[0080] Therefore, filtering feature variability The larger the difference in adjacent filtering performance The larger it is, the more likely it is that the filtration is affected by the blocking effect, and the sewage pollution change characteristic index The larger the value is, the more likely it is that abnormal conditions will occur during ceramic membrane filtration, resulting in a greater change in the degree of sewage pollution, and the larger the filtration retardation characteristic index is.

[0081] Furthermore, in order to more accurately identify abnormal phenomena occurring during ceramic membrane filtration, based on the filtration retardation characteristic index, a data fusion method is adopted to calculate the filtration retardation characteristic evaluation index at each acquisition moment. This is used to comprehensively evaluate the abnormal characteristic size of the filtration retardation effect occurring during ceramic membrane filtration at different acquisition moments. The calculation formula is as follows:

[0082]

[0083] Where, L j represents the filtration retardation characteristic evaluation index at the jth collection moment, m represents the number of sewage measurement indicators, It represents the filtration retardation characteristic index of the i-th sewage measurement index at the j-th collection time.

[0084] Filtration Retardation Characteristic Index The larger the value is, the greater the abnormal characteristics of the filtration retardation effect of the ceramic membrane filtration at this time, and the greater the filtration retardation characteristic evaluation index. The specific flow diagram of the filtration retardation characteristic evaluation index extraction process at each collection moment is as follows: Figure 2 shown.

[0085] At this point, the filtration blockage characteristic evaluation index at each acquisition moment is obtained, which is used to subsequently identify abnormalities that occur during fine filtration of ceramic membranes.

[0086] Step S003: obtaining a filtration blockage characteristic evaluation sequence based on the filtration blockage characteristic evaluation index, obtaining an abnormality detection result based on the filtration blockage characteristic evaluation sequence using an abnormality detection algorithm, and detecting and judging the ceramic membrane fine filtration process.

[0087] Furthermore, in order to more accurately analyze the fine filtration process of the ceramic membrane, the filtration blockage characteristic evaluation index at all acquisition moments is used as the input of the LOF abnormal data detection algorithm (Local outlier factor, LOF), and the preset neighborhood parameter is 15. The LOF abnormal data detection algorithm outputs the LOF value of each filtration blockage characteristic evaluation index in the filtration blockage characteristic evaluation sequence. The LOF abnormal data detection algorithm is a well-known technology, and the specific process will not be repeated here.

[0088] If a preset number of LOF values for the filtration retardation characteristic evaluation index exceed a preset abnormality detection threshold, an abnormality has occurred in the ceramic membrane filtration during the corresponding time period, and the ceramic membrane should be cleaned. Otherwise, no abnormality has occurred in the ceramic membrane filtration during the corresponding time period, and fine filtration continues using the ceramic membrane without cleaning. In this embodiment, the preset number is 5, and the abnormality detection threshold is set to 1.

[0089] Thus, according to the above process of this embodiment, the analysis of various sewage measurement indicators of the water quality after the ceramic membrane filtration can be combined to determine whether the ceramic membrane needs to be cleaned, so as to improve the efficiency of the ceramic membrane fine filtration.

[0090] Based on the same inventive concept as the above method, an embodiment of the present application also provides 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. When the processor executes the computer program, the steps of any one of the above-mentioned fine filtration methods for sewage treatment monitoring are implemented.

[0091] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0092] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0093] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A fine filtration method for sewage treatment monitoring, characterized in that: The method comprises the following steps: Collect data on various sewage measurement indicators of water quality after fine filtration by ceramic membranes, and arrange them in ascending time order to form a sewage indicator change sequence of each sewage measurement indicator; Based on the sewage index change sequence, a sewage characteristic change sequence for each sewage measurement index at each collection time is constructed; based on the change of data in the sewage characteristic change sequence, the pollution trend variation 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, the sewage stability characteristic index of each sewage measurement index at each collection time is determined; Based on the pollution trend variation index and sewage stability characteristic index, the sewage pollution variation characteristic index of each sewage measurement indicator at each collection time is determined; Based on the difference and degree of change in the sewage pollution change characteristic index of each sewage measurement indicator at each collection time and the neighboring collection time, the filtration characteristic variation and the neighboring filtration performance difference of each sewage measurement indicator at each collection time are determined; Based on the sewage pollution change characteristic index, filtration characteristic variation and adjacent filtration performance difference of each sewage measurement indicator at each collection time, the filtration retardation characteristic index of each sewage measurement indicator at each collection time is determined; The average of the filtration retardation characteristic indexes of all sewage measurement indicators at each collection time is used as the filtration retardation characteristic evaluation index at each collection time; Based on the filtration blockage characteristic evaluation index and using the anomaly detection algorithm, the filtration condition of the ceramic membrane is judged to complete the fine filtration of the ceramic membrane.

2. A fine filtration method for sewage treatment monitoring according to claim 1, characterized in that: The method of constructing a sewage characteristic change sequence at each collection moment for each sewage measurement indicator includes: The data of all collection moments in the sewage indicator change sequence of each sewage measurement indicator are used as the input of the density peak clustering algorithm. The density peak clustering algorithm outputs all data within the neighborhood cutoff distance of the data at each collection moment. All data within the neighborhood cutoff distance of the data at each collection moment are arranged in ascending order of time to form the sewage characteristic change sequence corresponding to each collection moment of each sewage measurement indicator.

3. A fine filtration method for sewage treatment monitoring according to claim 1, characterized in that: The method of determining the pollution trend variation index of each sewage measurement indicator at each collection moment based on the change of data in the sewage characteristic change sequence includes: Performing a detrended fluctuation analysis on the sewage characteristic change sequence at each collection moment for each sewage measurement indicator to obtain a detrended sewage characteristic sequence at each collection moment, calculating the absolute value of the difference between the sewage characteristic change sequence at each collection moment and the data at the same position in the detrended sewage characteristic sequence, and arranging all the absolute values of the difference in ascending time order to form a trend change sequence for each sewage measurement indicator at each collection moment; The pollution trend variation index of the i-th sewage measurement index at the j-th collection time is recorded as The expression is: Where N represents the number of data in the trend change sequence of the i-th sewage measurement indicator at the j-th collection moment, exp() is an exponential function with a natural constant as the base, It represents the standard deviation of all data in the detrended sewage characteristic sequence of the i-th sewage measurement indicator at the j-th collection moment, and They respectively represent the sth and s-1th data in the trend change sequence of the i-th sewage measurement indicator at the j-th collection moment, and ∈ is the coordination factor.

4. A fine filtration method for sewage treatment monitoring according to claim 1, characterized in that: The method of determining the sewage stationary characteristic index of each sewage measurement indicator at each collection moment based on the information entropy and data distribution of the sewage characteristic change sequence includes: For each sewage measurement indicator, the sewage characteristic change sequence at each collection moment; Calculating the information entropy and mean of all data in the sewage characteristic change sequence, calculating the absolute value of the difference between each data in the sewage characteristic change sequence and the mean, obtaining the sum of the absolute value of the difference and a preset coordination factor, and using the inverse of the information entropy as the exponent of an exponential function with a natural constant as the base; Obtaining a ratio of a calculation result of the exponential function to the sum value; The mean of the ratios of all data in the sewage characteristic change sequence is used as the sewage stable characteristic index of each sewage measurement indicator at each collection moment.

5. A fine filtration method for sewage treatment monitoring according to claim 1, characterized in that: The method of determining the sewage pollution change characteristic index of each sewage measurement indicator at each collection time based on the pollution trend variation index and the sewage stability characteristic index includes: The sum of the sewage stability characteristic index of each sewage measurement indicator at each collection moment and the preset coordination factor is obtained, and the ratio of the pollution trend variation index of each sewage measurement indicator at each collection moment to the summation result is used as the sewage pollution change characteristic index of each sewage measurement indicator at each collection moment.

6. A fine filtration method for sewage treatment monitoring according to claim 1, characterized in that: The filtering feature variability includes: The sequence of sewage pollution change characteristic indexes of each sewage measurement indicator at all collection moments in ascending time order is used as the pollution degree change characteristic sequence of each sewage measurement indicator; The pollution degree change characteristic sequence of each sewage measurement indicator is composed of a preset number of pollution degree change indexes at each collection moment and before and after each collection moment, and arranged in ascending order of time to form a filtration performance evaluation sequence for each sewage measurement indicator at each collection moment; The filtration performance evaluation sequence of each sewage measurement indicator at each collection moment 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 average of the product of the absolute value and the coefficient of variation between all any two data in the filtration performance evaluation sequence is used as the filtration characteristic variation of each sewage measurement indicator at each collection moment.

7. A fine filtration method for sewage treatment monitoring according to claim 6, characterized in that: The proximity filtering performance difference includes: The DTW distances between each collection moment of each sewage measurement indicator and the filtration performance evaluation sequences of the adjacent collection moments are calculated respectively, and the sum of the two DTW distances is taken as the adjacent filtration performance difference of each sewage measurement indicator at each collection moment.

8. A fine filtration method for sewage treatment monitoring according to claim 1, characterized in that: Determining the filtration retardation characteristic index of each sewage measurement indicator at each collection time includes: Calculate the product of the filtration characteristic variation of each sewage measurement indicator at each collection time and the adjacent filtration performance difference, use the inverse of the product as the exponent of an exponential function with a natural constant as the base, and obtain the sum of the sewage pollution change characteristic index of each sewage measurement indicator at each collection time and a preset coordination factor; Calculating a ratio of a calculation result of the exponential function to the sum value; The difference between the number 1 and the ratio is used as the filtration retardation characteristic index of each sewage measurement indicator at each collection time.

9. A fine filtration method for sewage treatment monitoring according to claim 1, characterized in that: The method of determining the filtration condition of the ceramic membrane by using an abnormality detection algorithm based on the filtration retardation characteristic evaluation index includes: An anomaly detection algorithm is used to obtain the LOF value of the filtration blockage characteristic evaluation index at each collection moment. If there are multiple LOF values of the filtration blockage characteristic evaluation index that are higher than the 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.

10. A fine filtration system for monitoring sewage treatment, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 9 are implemented.

Images