Sewage treatment method, device and system in coal tar deep processing process

Abstract

The invention relates to the technical field of sewage treatment, in particular to a sewage treatment method, device and system in a coal tar deep processing process. The method comprises the following steps: firstly, historical data and real-time data of various indexes are acquired; further predicting the pollution degree coefficient of the adjusting tank at the corresponding next moment according to the change of the feed-forward index; further screening out an abnormal fluctuation section of the data of the pollution degree coefficient and each feedback index; further obtaining a response fluctuation section corresponding to the abnormal fluctuation section of the pollution degree coefficient; and finally, adjusting the water inlet flow of the high-concentration wastewater. According to the invention, the wastewater concentration in the regulating reservoir is predicted through the feedforward index, and the influence degree of the wastewater concentration on sewage treatment is predicted in combination with the response characteristics of the feedforward index, so that the water inlet flow rate is adjusted based on the current wastewater concentration change, the system load is dynamically predicted, and the water inlet amount is accurately regulated and controlled; the sewage treatment efficiency and the system stability are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of sewage treatment, and particularly relates to a sewage treatment method, device and system in the process of deep processing of coal tar. Background Art

[0002] The sewage generated in the process of deep processing of coal tar has a relatively complex composition and usually contains highly toxic and difficult-to-degrade pollutants (such as phenols, ammonia nitrogen, sulfides, cyanides, etc.), and needs to be treated through multiple stages to achieve up-to-standard discharge or reuse.

[0003] Due to the extremely large fluctuation of the water quality of coal tar sewage, in order to avoid the instantaneous impact of highly toxic or high-load wastewater on the microbial activity, resulting in sludge poisoning or a large number of deaths, the process of stabilizing the water quality through water quality regulation (that is, mixing and adjusting high-concentration wastewater and low-concentration wastewater) is carried out to avoid load impact, reduce the difficulty of physical and chemical treatment, and improve the treatment efficiency.

[0004] Existing methods usually adaptively adjust the flow rate of the high-concentration wastewater inlet pump through real-time water quality data to ensure uniform mixing of high- and low-concentration sewage. However, in the actual operation process, the concentration differences of the wastewater discharged from different processing procedures of coal tar are extremely large and the switching is relatively frequent. Existing methods are difficult to timely adjust the flow rate of the inlet pump based on the frequent changes, which may result in abnormal regulation and affect the treatment effects of subsequent biochemical and physical and chemical steps. Summary of the Invention

[0005] In order to solve the technical problem that the existing water quality regulation method is difficult to cope with the frequent change of the sewage concentration of coal tar, and is prone to abnormal regulation, affecting the sewage treatment effect, the purpose of the present invention is to provide a sewage treatment method, device and system in the process of deep processing of coal tar, and the specific technical solutions adopted are as follows: A sewage treatment method in the process of deep processing of coal tar, the method includes: Obtain historical data and real-time data of preset feedforward indicators and feedback indicators in the sewage treatment process, and divide them at a preset period; Obtain the growth segments of the feedforward indicators; according to the growth trend of each growth segment and the data values at each moment in the segment, obtain the growth coefficients corresponding to each moment; according to the growth coefficients of all feedforward indicators at each moment, and combining the correlation characteristics between the feedforward indicators, obtain the pollution degree coefficient of the adjustment tank at the corresponding next moment; Within each historical preset period, the data of the pollution degree coefficient and each feedback index are divided in time series with adjacent extreme points to obtain respective fluctuation segments; according to the fluctuation amplitude and fluctuation prominence within each fluctuation segment, an anomaly index is obtained and the abnormal fluctuation segments are screened out; according to the time interval between the abnormal fluctuation segment of the pollution degree coefficient and the abnormal fluctuation segment of the subsequent feedback index, combined with the similarity of the anomaly index, the corresponding response fluctuation segment of the abnormal fluctuation segment of the pollution degree coefficient is obtained. According to the overall response characteristics of the response fluctuation segments of each feedback index in the historical data to the pollution degree coefficient, combined with the change trend of the pollution degree coefficient at the current moment, the influent interference index at the current moment is obtained; based on the influent interference index at the current moment and the pollution degree coefficient at the next moment, the influent flow rate of the high-concentration wastewater is adjusted.

[0006] Furthermore, the method for obtaining the growth coefficient includes: According to the number of first-order difference values in the growth segment, the overall characteristics of the first-order difference values, and the data values at each moment in the segment, the growth coefficient corresponding to each moment is obtained.

[0007] Furthermore, the method for obtaining the pollution degree coefficient includes: Select any moment as the target moment; based on all the data from the target moment to the start moment of the preset period to which it belongs, the Pearson correlation coefficient matrix between the respective feedforward indexes at the target moment is obtained and the eigenvector matrix is obtained; Based on the vector elements corresponding to the respective feedforward indexes in the eigenvector corresponding to the maximum eigenvalue, the growth coefficients of the respective feedforward indexes at the target moment are weighted and summed, and the weighted sum result is used as the pollution degree coefficient at the next moment of the target moment.

[0008] Furthermore, the method for obtaining the anomaly index includes: According to the overall fluctuation amplitude of the fluctuation segment, combined with the overall difference between the data of the fluctuation segment and all historical data of the same dimension, the anomaly index corresponding to the fluctuation segment is obtained; the overall fluctuation amplitude is positively correlated with the anomaly index.

[0009] Furthermore, the method for obtaining the response fluctuation segment includes: Select any one of the feedback indexes as the feedback target index, select any abnormal fluctuation segment of the pollution degree coefficient as the target fluctuation segment, and use each abnormal fluctuation segment of the feedback target index within the preset period to which the target fluctuation segment belongs and within the time domain after the start moment of the target fluctuation segment as the fluctuation segments to be analyzed; According to the time interval between the start time of each fluctuation segment to be analyzed and the target fluctuation segment, and in combination with the similarity of the anomaly index, obtain the matching coefficient corresponding to each fluctuation segment to be analyzed; select the fluctuation segment to be analyzed with the largest matching coefficient as the response fluctuation segment of the target fluctuation segment.

[0010] Further, the method for obtaining the influent interference index includes: Based on the increase and decrease of the abnormal fluctuation segments of the pollution degree coefficient, divide all the response fluctuation segments into two categories; For each category of response fluctuation segments, according to the time interval between the start time of a category of response fluctuation segments and the corresponding abnormal fluctuation segment of the pollution degree coefficient, and in combination with the time interval between the end time of a category of response fluctuation segments and the start time of the corresponding abnormal fluctuation segment of the pollution degree coefficient, obtain the predicted response duration; According to the distribution characteristics of the fluctuation amplitude of a category of response fluctuation segments, and in combination with the predicted response duration, obtain the influent interference index of a category of response fluctuation segments; According to the increase and decrease trend of the pollution degree coefficient at the current moment, select the corresponding influent interference index.

[0011] Further, the method for obtaining the influent flow rate includes: If the pollution degree coefficient at the current moment shows an increasing trend, fuse the influent interference index at the current moment and the pollution degree coefficient at the next moment to obtain an adjustment factor; both the influent interference index and the pollution degree coefficient at the next moment are negatively correlated with the adjustment factor; If the pollution degree coefficient at the current moment shows a decreasing trend, fuse the influent interference index at the current moment and the pollution degree coefficient at the next moment to obtain an adjustment factor; the influent interference index is positively correlated with the adjustment factor; the pollution degree coefficient at the next moment is negatively correlated with the adjustment factor; Based on the adjustment factor, adjust the influent flow rate at the current moment.

[0012] Further, the time domain length of the growth segment is at least 3.

[0013] The present invention also proposes a sewage treatment system in the deep processing of coal tar, and the system includes: Data acquisition module: Obtain the historical data and real-time data of the preset feedforward indexes and feedback indexes in the sewage treatment process, and divide them according to a preset period; Data prediction module: Obtain the growth segments of the feedforward metrics; according to the growth trends of each growth segment and the data values at each moment in the segment, obtain the growth coefficients corresponding to each moment; according to the growth coefficients of all feedforward metrics at each moment, and combining the correlation characteristics between various feedforward metrics, obtain the pollution degree coefficient of the regulation tank at the corresponding next moment. Response matching module: In each historical preset period, perform time series partitioning on the pollution degree coefficient and the data of each feedback metric with adjacent extreme points, and obtain the fluctuation segments respectively; according to the fluctuation amplitude and fluctuation salience in each fluctuation segment, obtain the anomaly index and screen out the abnormal fluctuation segments; according to the time interval between the abnormal fluctuation segment of the pollution degree coefficient and the abnormal fluctuation segment of the subsequent feedback metric, and combining the similarity of the anomaly index, obtain the response fluctuation segment corresponding to the abnormal fluctuation segment of the pollution degree coefficient. Inlet water regulation module: According to the overall response characteristics of the response fluctuation segments of each feedback metric in the historical data to the pollution degree coefficient, and combining the change trend of the pollution degree coefficient at the current moment, obtain the inlet water interference index at the current moment; based on the inlet water interference index at the current moment and the pollution degree coefficient at the next moment, regulate the inlet water flow of the high-concentration wastewater.

[0014] The present invention also proposes a sewage treatment device in the process of coal tar deep processing. The device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of any one of the sewage treatment methods in the process of coal tar deep processing are implemented.

[0015] The present invention has the following beneficial effects: The present invention first obtains the historical data and real-time data of various indicators to provide a data basis; further, according to the growth trend of each growth segment and the data values at each moment in the segment, the growth degree at the growth moment is quantified, providing a basis for subsequently predicting the pollution degree by synthesizing multiple feedforward indicators; further, the pollution degree coefficient of the regulating pond at the corresponding next moment is obtained to anticipate the system load in advance, facilitating the subsequent adjustment of the influent flow rate; further, the abnormal fluctuation segments of the pollution degree coefficient and various feedback indicators are screened out, and they are matched according to the similarity of the time interval and the abnormal index to obtain the corresponding response fluctuation segment of the abnormal fluctuation segment of the pollution degree coefficient, facilitating the subsequent analysis of the response of the feedback indicators to the abnormal fluctuation of the pollution degree coefficient and predicting the impact of the pollution degree on the subsequent water purification steps; further, according to the response characteristics of the response fluctuation segments of various feedback indicators in the historical data to the overall response of the pollution degree coefficient, the response law is analyzed, and then combined with the change trend of the pollution degree coefficient at the current moment and the pollution degree coefficient at the next moment, the interference of the wastewater concentration on the sewage treatment is predicted, and the influent flow rate of the high-concentration wastewater is adjusted. The present invention predicts the wastewater concentration in the regulating pond through feedforward indicators, combines the response characteristics of the feedback indicators, predicts the influence degree of the wastewater concentration on the sewage treatment, thereby adjusts the influent flow rate based on the current change of the wastewater concentration, dynamically predicts the system load, accurately controls the influent volume, and effectively improves the sewage treatment efficiency and system stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required to be used in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0017] Figure 1 It is a flowchart of the sewage treatment for the deep processing of coal tar provided by an embodiment of the present invention; Figure 2 It is a flowchart of the sewage treatment method in the process of the deep processing of coal tar provided by an embodiment of the present invention; Figure 3 It is a system block diagram of the sewage treatment system in the process of the deep processing of coal tar provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following specifically describes, in conjunction with the accompanying drawings and preferred embodiments, a sewage treatment method, device, and system in the deep processing of coal tar, including its specific implementation manner, structure, features, and effects. 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.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0020] The following specifically describes, in conjunction with the accompanying drawings, the specific solutions of a sewage treatment method, device, and system in the deep processing of coal tar provided by the present invention.

[0021] Please refer to Figure 1 , which shows a flow chart of sewage treatment in the deep processing of coal tar provided by an embodiment of the present invention. Figure 1 It shows that the sewage mainly undergoes three levels of treatment processes. The incoming water first enters the pretreatment. After passing through the regulating oil removal tank, oil-water separator, phenol removal and ammonia distillation tower, and regulating tank, it enters the biochemical treatment. After passing through the hydrolysis acidification tank, UASB / IC reactor, A / O process, and MBR membrane tank, it enters the advanced treatment. After passing through coagulation sedimentation, adsorption, ultrafiltration, and reverse osmosis, it is determined whether the treated water meets the standard, and the effluent is discharged or reused accordingly.

[0022] It can be briefly described as: pretreatment (oil separation, regulating tank) → biochemical treatment (A / O, MBR) → advanced treatment (coagulation sedimentation, advanced oxidation) → resource recovery.

[0023] Among them, the pretreatment of high-concentration wastewater includes: ammonia distillation and phenol removal, oil removal treatment, water quality regulation (balancing the water quality and quantity through the regulating tank to avoid system shock), etc. The water quality regulation process is as follows: Using an online static mixer, the high-concentration wastewater (usually the wastewater after ammonia distillation and phenol removal, oil removal treatment) is mixed with the low-concentration wastewater (usually circulating cooling water, flushing water, etc.) at the inlet of the regulating tank and is fully mixed by the stirring equipment.

[0024] When the treated water meets the industrial circulating cooling water standard, it is reused in production. When the water quality is good but does not meet the direct reuse standard, it is transported back to the regulating tank to achieve water circulation.

[0025] Please refer to Figure 2 , which shows a flow chart of a sewage treatment method in the deep processing of coal tar provided by an embodiment of the present invention, specifically including: Step S1: Obtain the historical data and real-time data of the preset feedforward indicators and feedback indicators during the sewage treatment process, and divide them at a preset cycle.

[0026] In the embodiment of the present invention, mainly before the wastewater regulation, combined with the historical data and the current actual monitoring indicators, predict the change of pollutant concentration in the regulation tank, and analyze the influence degree of wastewater concentration on sewage treatment.

[0027] In an embodiment of the present invention, the monitoring indicators and collection methods include: ① Use a ZDL-9 intelligent sulfur analyzer to monitor the sulfur content (%) of the raw material; ② Use a temperature sensor to monitor the temperature in the ammonia distillation and phenol removal unit (°C); ③ Use an ultraviolet fluorescence method sensor to monitor the oil content in the oil removal treatment (mg / L); ④ Use a TOC analyzer to monitor the COD (chemical oxygen demand) in the regulation tank and the biochemical unit (mg / L); ⑤ Use an infrared scattering method on-line sludge concentration monitor to monitor the sludge concentration in the biochemical unit (mg / L); ⑥ Use a fluorescence method DO sensor to monitor the dissolved oxygen concentration in the biochemical unit (mg / L); ⑦ Use a chemiluminescence method on-line analyzer to monitor the residual amount of oxidant in the advanced treatment unit (mg / L).

[0028] Take 24 hours of each day as a preset cycle, one day as a cycle, to avoid the data being too long and covering up the subtle features of the data; the collection frequency is once every 5 seconds, obtain the historical data of the most recent 30 days of the current day, and obtain the data of each item of the current day in real time.

[0029] It should be noted that when collecting each item of monitoring data, it can be preprocessed by normalization. The normalization is carried out under the corresponding data dimension. The normalization methods adopted in the embodiments of the present invention can all adopt this method, such as using linear normalization, which is a well-known technical means for those skilled in the art and will not be elaborated here.

[0030] Step S2: Obtain the growth segments of the feedforward indicators; according to the growth trend of each growth segment and the data values at each moment in the segment, obtain the growth coefficient corresponding to each moment; according to the growth coefficients of all feedforward indicators at each moment, combined with the correlation characteristics between the feedforward indicators, obtain the pollution degree coefficient of the regulation tank at the corresponding next moment.

[0031] In the ammonia distillation and phenol removal process, an increase in temperature will accelerate the cracking of polycyclic aromatic hydrocarbons and phenolic substances in tar, resulting in an increase in the COD and phenolic concentrations in the wastewater. At the same time, when the sulfur content in the raw material (coal tar) increases, the concentration of mercaptan substances in the wastewater increases, which may reduce the rate of organic matter degradation, leading to COD accumulation and further growth of COD in the regulation tank. Moreover, if the oil content in the regulation tank actually increases to a large extent, it indicates that a large amount of high-concentration organic phase enters the regulation tank at this time, resulting in a further superimposition of pollutant loads. Therefore, the increase in these monitoring indicators will cause the severity of water pollution in the regulation tank to increase faster, so the pollution degree of the regulation tank can be predicted based on these monitoring indicators.

[0032] In an embodiment of the present invention, the preset feedforward indicators at least include distillation temperature (ZT), raw material sulfur content (S), COD (C), and oil content (O).

[0033] Obtain the growth segments of the feedforward indicators to facilitate predicting the pollution degree coefficient according to the growth conditions of the monitored feedforward indicators.

[0034] In an embodiment of the present invention, obtain the extreme points of the feedforward indicators within each preset period. The period between the minimum extreme point and the adjacent next maximum extreme point is used as a growth segment. To exclude the influence of short-term data fluctuations, the time domain length of the growth segment is limited to at least 3.

[0035] In other embodiments of the present invention, the implementer can also obtain the first-order difference of the data, and use the data segments corresponding to two or more consecutive difference values greater than 0 as a growth segment.

[0036] In the same way, obtain all the growth segments of all the target data.

[0037] Considering that the growth conditions of different growth segments and different moments in the growth segment are different, so according to the growth trend of each growth segment and the data value at each moment in the segment, obtain the growth coefficient corresponding to each moment, quantify the growth degree at the growth moment, and provide a basis for predicting the pollution degree by comprehensively considering multiple feedforward indicators later.

[0038] Preferably, in an embodiment of the present invention, considering that the larger the number of first-order difference values of the growth segment, the longer the duration of the growth segment; the larger the overall first-order difference value, the greater the growth rate; and the larger the data value at the selected moment, the greater the impact of the continuous growth on the regulation tank. Therefore, according to the number of first-order difference values of the growth segment, the overall characteristics of the first-order difference values, and the data value at each moment in the segment, obtain the growth coefficient corresponding to each moment.

[0039] As an example, considering that there are differences in the data distribution patterns of different dimensions, the growth characteristics can be highlighted by the ratio of the data value to the mean value of all historical data. Therefore, after normalizing the product of the ratio of the data value at each moment to the mean value of all historical data in the same dimension, the number of first-order difference values in the growth segment, and the mean value of the first-order difference values, the normalized result is used as the growth coefficient for each corresponding moment.

[0040] The overall characteristics of the first-order difference values are represented by the mean value. With the number of first-order difference values in the growth segment and the mean value of the first-order difference values, the growth trend of the growth segment is shown from the perspective of the growth duration and the growth rate.

[0041] It should be noted that the growth coefficient at the moment of the non-growth segment is set to zero; the same dimension refers to the same dimension, such as the temperature data dimension.

[0042] Considering that there are correlations among multiple feedforward indicators and the growth of different feedforward indicators has different impacts on the regulating tank, according to the growth coefficients of all feedforward indicators at each moment and in combination with the correlation characteristics among the feedforward indicators, a more comprehensive and mutually verified prediction model can be constructed. Thus, the growth coefficients of multiple feedforward indicators are fused to obtain the pollution degree coefficient of the regulating tank at the corresponding next moment, predicting the system load in advance, which helps to identify potential overloading risks in advance, helps to adjust the influent flow rate subsequently, take peak shaving measures before the pollution increases, and improve the treatment efficiency when the pollution decreases, enhancing the response ability and stability of the system.

[0043] Preferably, in an embodiment of the present invention, any moment is selected as the target moment; considering that the Pearson correlation coefficient matrix depicts the correlations between variables and reflects the "co-variation" pattern among the feedforward indicators, the correlation characteristics among the feedforward indicators are shown by means of the Pearson correlation coefficient matrix, analyzing the linear correlation structure among the feedforward indicators and showing the characteristic pattern of the same or opposite changes among the indicators; and the eigenvector corresponding to the largest eigenvalue in the eigenvector matrix (i.e., the principal eigenvector) can be regarded as the direction representing the main change trend of the system, and each element therein represents the "weight" or "contribution degree" of the original variables (feedforward indicators) in the main direction, which can be used as the weighted weights of the growth coefficients of each monitored feedforward indicator. Among them, the correlation characteristics among the feedforward indicators specifically refer to the linear correlation relationship among the feedforward indicators and the weights of each indicator in the direction of the main change trend.

[0044] Based on this, based on all the data from the target moment to the starting moment of the preset cycle to which it belongs, the Pearson correlation coefficients between a single feedforward indicator and the remaining feedforward indicators are calculated respectively to obtain the Pearson correlation coefficient matrix among the feedforward indicators at the target moment and obtain the eigenvector matrix. Based on the vector elements corresponding to each feedforward index in the eigenvector corresponding to the maximum eigenvalue, perform a weighted sum of the growth coefficients of each feedforward index at the target moment, and use the weighted sum result as the pollution degree coefficient at the next moment of the target moment.

[0045] As an example, after mapping the vector elements corresponding to each feedforward index in the eigenvector corresponding to the maximum eigenvalue through the softmax function, use the mapped values as the weighted weights of each feedforward index, perform a weighted sum of the growth coefficients at the target moment based on the weighted weights, and use the result as the pollution degree coefficient at the next moment of the target moment, adaptively integrating the growth trends of each pollution feedforward index and accurately predicting the future pollution degree.

[0046] It should be noted that the Pearson correlation coefficient, the formation of the Pearson correlation coefficient matrix, the acquisition of the eigenvector matrix, the acquisition of the maximum eigenvalue, and the softmax function are all existing technologies and will not be elaborated here.

[0047] Traverse all historical data and real-time data to obtain the pollution degree coefficients at the next moment corresponding to all moments.

[0048] Step S3: In each historical preset period, perform time series partitioning on the data of the pollution degree coefficient and each feedback index with adjacent extreme points to obtain fluctuation segments respectively; according to the fluctuation amplitude and fluctuation saliency within each fluctuation segment, obtain the anomaly index and screen out the abnormal fluctuation segments; according to the time interval between the abnormal fluctuation segment of the pollution degree coefficient and the abnormal fluctuation segment of the subsequent feedback index, and combining the similarity of the anomaly index, obtain the response fluctuation segment corresponding to the abnormal fluctuation segment of the pollution degree coefficient.

[0049] Through step S2, a feedforward prediction of the wastewater degree in the regulation tank is performed, and a pollution degree coefficient corresponds to all moments; the subsequent operation steps of the regulation tank include biochemical reactions, and its response to the wastewater concentration in the regulation tank has a lag, that is, when the wastewater concentration in the current regulation tank changes, the monitoring indicators in the subsequent operation steps will take a long time to generate corresponding fluctuations in response to this change in wastewater concentration.

[0050] In an embodiment of the present invention, the preset feedback indicators at least include the COD content, sludge concentration, dissolved oxygen concentration in the biochemical unit, and the residual amount of oxidant in the advanced treatment unit.

[0051] Considering that when the concentration of wastewater in the regulating tank increases or decreases too much, it is not conducive to maintaining the stability of the concentration in the regulating tank. Therefore, the abnormal fluctuation data segments of the pollution degree of the wastewater in the regulating tank within a single cycle are screened. At the same time, the abnormal pollution degree will cause the data of the feedback index to also show abnormal fluctuations, which is convenient for subsequent analysis of the corresponding situation of the feedback index for the abnormal fluctuation of the pollution degree coefficient. The data of each feedback index are also divided and the abnormal fluctuation data segments are screened.

[0052] Considering that the historical data has been determined, which is convenient for analyzing the response of the feedback index to the abnormality of the pollution degree coefficient, so the analysis is carried out within the preset historical cycle; considering that the data fluctuation trends between adjacent extreme points are the same, so within each preset cycle, the data of the pollution degree coefficient and each feedback index are divided according to the adjacent extreme points in time series, and the fluctuation segments are obtained respectively.

[0053] It should be noted that the method for obtaining the extreme points of the time series data sequence is already a well-known technical means for those skilled in the art. The implementer can also limit the shortest lower limit of the fluctuation segment, such as limiting the shortest length of the fluctuation segment to 3 to reduce the influence of short-term fluctuations caused by noise, which will not be elaborated here.

[0054] Considering that both the fluctuation amplitude and the fluctuation prominent feature of the fluctuation segment reflect the unstable situation of the fluctuation segment and show the abnormal characteristics of the fluctuation segment, so according to the fluctuation amplitude and the fluctuation prominence within each fluctuation segment, the abnormal index is obtained and the abnormal fluctuation segments are screened, and the segmented pollution degree coefficient with abnormal fluctuations and the segmented data of each feedback index are determined, which is convenient for subsequent analysis of the response of each feedback index to the abnormal pollution degree coefficient.

[0055] Preferably, in an embodiment of the present invention, considering that when the overall fluctuation amplitude of a fluctuation segment is larger, the increase or decrease amplitude is larger, the more unstable it is, and the higher the abnormal index; at the same time, when the difference between the data in the fluctuation segment and the conventional mode of the historical data of the same dimension is larger, the abnormal characteristics are more obvious and the abnormal index is higher; Based on this, according to the overall fluctuation amplitude of the fluctuation segment, combined with the overall difference between the data of the fluctuation segment and all the historical data of the same dimension, the abnormal index corresponding to the fluctuation segment is obtained; the overall fluctuation amplitude is positively correlated with the abnormal index.

[0056] As an example, since the fluctuation segments are divided by adjacent extreme points, the data within the fluctuation segments is monotonic. The absolute value of the difference between the data values at the beginning and end moments of the fluctuation segment is used as the overall fluctuation amplitude of the entire fluctuation segment, representing the fluctuation amplitude within the fluctuation segment. The absolute value of the difference between the mean value of the data in the fluctuation segment and the mean value of all historical data in the same dimension is used as the numerator, and the mean value of all historical data in the same dimension is used as the denominator. The fractional ratio is used as the fluctuation prominence coefficient. Based on the mean value of all historical data in the same dimension, which represents the normal pattern of the data in the same dimension, the overall difference between the data in the fluctuation segment and all historical data in the same dimension is reflected, showing the fluctuation prominence within the fluctuation segment.

[0057] After linearly normalizing the product of the overall fluctuation amplitude and the fluctuation prominence coefficient, the mapped value is used as the anomaly index corresponding to the fluctuation segment.

[0058] Considering that the larger the anomaly index, the more obvious the abnormal characteristics of the fluctuation segment, and the more likely it is an abnormal fluctuation segment, an abnormal fluctuation threshold of 0.5 (empirical value) is set. The fluctuation segments with anomaly indices greater than the abnormal fluctuation threshold are marked as abnormal fluctuation segments, and the abnormal fluctuation segments are screened out.

[0059] Analyze the fluctuation segments of the pollution degree coefficient and each feedback index within all preset periods, and screen out the abnormal fluctuation segments in each data dimension.

[0060] It should be noted that the normalization of the anomaly index for each type of data is performed within its respective data dimension; in other embodiments of the present invention, the implementer can also use the sigmoid function for normalization and adjust the abnormal fluctuation threshold, such as 0.8.

[0061] Considering that the abnormal fluctuation segments of the pollution degree coefficient will affect the feedback indices in the subsequent time domain, causing similar abnormal fluctuation segments in the feedback indices, and at the same time, the time interval also reflects the possibility that the abnormal fluctuation segments of the feedback indices are caused by the abnormal fluctuation segments of the pollution degree coefficient. Therefore, according to the time interval between the abnormal fluctuation segments of the pollution degree coefficient and the abnormal fluctuation segments of the subsequent feedback indices, combined with the similarity of the anomaly indices, the corresponding response fluctuation segments of the abnormal fluctuation segments of the pollution degree coefficient are obtained, and the abnormal fluctuation segments of the pollution degree coefficient are matched with the abnormal fluctuation segments of the feedback indices, which is convenient for analyzing the influence characteristics of the pollution degree on the feedback indices and provides a basis for predicting and adjusting the influent flow rate of high-concentration wastewater and maintaining the sewage treatment effect of each link in the future.

[0062] Preferably, in an embodiment of the present invention, any one of the feedback indices is selected as the feedback target index, and any one of the abnormal fluctuation segments of the pollution degree coefficient is selected as the target fluctuation segment, which is convenient for comparing and matching the pollution degree coefficient with each feedback index dimension one by one; During the preset period to which the target fluctuation segment belongs, and within the time domain after the starting moment of the target fluctuation segment, each abnormal fluctuation segment that feeds back the target index is used as the fluctuation segment to be analyzed. First, determine the abnormal fluctuation segments in the target feedback index that can be compared; Considering that the closer the starting moment of the fluctuation segment to be analyzed is to the target fluctuation segment, the stronger the causal connection with the target fluctuation segment, and at the same time, the more similar the abnormal indices are and the more reliable the response relationship is. Therefore, according to the time interval between the starting moment of each fluctuation segment to be analyzed and the target fluctuation segment, combined with the similarity of the abnormal indices, obtain the matching coefficient corresponding to each fluctuation segment to be analyzed; select the fluctuation segment to be analyzed with the largest matching coefficient as the response fluctuation segment of the target fluctuation segment.

[0063] As an example, take the reciprocal of the time interval between the starting moment of the fluctuation segment to be analyzed and the target fluctuation segment as the first matching factor; take the absolute value of the difference between the abnormal index of the fluctuation segment to be analyzed and the target fluctuation segment as the numerator, and the abnormal index of the target fluctuation segment as the denominator, and the fractional ratio as the abnormal difference factor. After taking the reciprocal of the sum value of the abnormal difference factor and a preset non-zero positive parameter such as 0.01, use it as the second matching factor; Take the product of the first matching factor and the second matching factor as the matching coefficient corresponding to the fluctuation segment to be analyzed; select the fluctuation segment to be analyzed with the largest matching coefficient as the response fluctuation segment of the target fluctuation segment.

[0064] Among them, since the fluctuation of the pollution degree coefficient is transmitted to the subsequent sewage treatment, it takes time for the feedback index to fluctuate. Therefore, the starting moment of the fluctuation segment to be analyzed must be after the starting moment of the target fluctuation segment, so the time interval must be greater than zero; considering that the abnormal indices may be the same, to prevent the denominator from being zero, perform a division-by-zero operation before taking the reciprocal; based on the abnormal index of the target fluctuation segment, obtain the abnormal difference factor to quantify the difference characteristics, and then perform a negative correlation mapping by taking the reciprocal to show the similarity of the abnormal indices, and finally obtain the response fluctuation segment.

[0065] Transform the feedback target index to obtain the response fluctuation segments of the corresponding feedback indices of the target fluctuation segment; traverse all abnormal fluctuation segments of the pollution degree coefficient in all historical preset periods to obtain all response fluctuation segments.

[0066] Step S4: According to the overall response characteristics of the response fluctuation segments of each feedback index in the historical data to the pollution degree coefficient, combined with the change trend of the pollution degree coefficient at the current moment, obtain the influent interference index at the current moment; adjust the influent flow rate of the high-concentration wastewater based on the influent interference index at the current moment and the pollution degree coefficient at the next moment.

[0067] Considering that the change trend of the pollution degree coefficient often causes response fluctuations of the feedback index in the time domain, by analyzing the abnormal fluctuation segments of the pollution degree coefficient in the historical data and the response fluctuation segments of the feedback index caused by the time shift, the typical behavior patterns of the pollution source's feedback response to the system can be extracted. Based on this response law and combined with the change trend of the pollution degree coefficient at the current moment, the degree of disturbance risk faced by the system can be predicted; Therefore, according to the response characteristics of the feedback index in the historical data to the overall response of the pollution degree coefficient, combined with the change trend of the pollution degree coefficient at the current moment, the influent interference index at the current moment is obtained to enhance the pre-identification ability of the system disturbance risk, which is convenient for timely adjusting the influent flow rate of the high-concentration wastewater.

[0068] Preferably, in an embodiment of the present invention, considering that the pollution degree coefficient is mainly divided into two cases: abnormal increase and abnormal decrease, and different change cases may have different effects on the feedback index. Therefore, based on the increase and decrease of the abnormal fluctuation segments of the pollution degree coefficient, all response fluctuation segments are divided into two categories for classification analysis; one category is the increasing type of response fluctuation segment, and the other category is the decreasing type of response fluctuation segment.

[0069] Considering that the overall characteristics of the time interval between the start time of a type of response fluctuation segment and the abnormal fluctuation segment of the corresponding pollution degree coefficient reflect the response delay of the pollution disturbance effect in the system, that is, the time required for the overall appearance of various feedback indexes; combined with the overall characteristics of the time interval between the end time of a type of response fluctuation segment and the start time of the abnormal fluctuation segment of the corresponding pollution degree coefficient, which reflects the time required for the overall end of the response of various feedback indexes, the predicted response duration of this type of disturbance in the feedback index can be effectively estimated; Based on this, for each type of response fluctuation segment, according to the time interval between the start time of a type of response fluctuation segment and the abnormal fluctuation segment of the corresponding pollution degree coefficient, combined with the time interval between the end time of a type of response fluctuation segment and the start time of the abnormal fluctuation segment of the corresponding pollution degree coefficient, the predicted response duration is obtained; As an example, the mean value of the time interval between the start time of a type of response fluctuation segment and the abnormal fluctuation segment of the corresponding pollution degree coefficient is used as the predicted response start time; the mean value of the time interval between the end time of a type of response fluctuation segment and the start time of the abnormal fluctuation segment of the corresponding pollution degree coefficient is used as the predicted response end time; the difference between the predicted response end time and the predicted response start time is used as the predicted response duration of this type of response fluctuation segment.

[0070] Considering that when the fluctuation amplitude of a class of response fluctuation segments is larger, it indicates that the response to the change in the pollution degree coefficient is more sensitive; at the same time, when the distribution of the fluctuation amplitude of a class of response fluctuation segments is more concentrated, it indicates that the change trend is more stable, and the influence of the pollution degree coefficient on the feedback index is greater; and the larger the predicted response duration, the longer the influence duration of the pollution degree coefficient on the feedback index and the stronger the interference. Therefore, according to the distribution characteristics of the fluctuation amplitude of a class of response fluctuation segments and combining the predicted response duration, the influent interference index of a class of response fluctuation segments is obtained. As an example, the product of the mean value of the fluctuation amplitude of a class of response fluctuation segments and the predicted response duration is used as the numerator, the range of the fluctuation amplitude of this class of response fluctuation segments is used as the denominator, and the fractional ratio is used as the influent interference index of this class of response fluctuation segments.

[0071] The fluctuation amplitude of each fluctuation segment is the absolute value of the difference between the data values at the beginning and end moments of the fluctuation segment. The mean value of the fluctuation amplitude represents the response sensitivity of all feedback indexes to the change in the pollution degree of a class, and the range shows the discrete characteristics of the fluctuation amplitude. The smaller the range, the more stable the change of all fluctuation segments, the stronger the interference of the pollution degree coefficient, and the larger the influent interference index; combined with the predicted response duration, which represents the expected response duration of the feedback index, it jointly shows the overall response characteristics of the response fluctuation segment of the feedback index to the pollution degree coefficient.

[0072] Finally, according to the increasing or decreasing trend of the pollution degree coefficient at the current moment, the corresponding influent interference index is selected.

[0073] It should be noted that in an embodiment of the present invention, the increasing or decreasing trend in the change trend of the pollution degree coefficient is judged according to the slope of the pollution degree coefficient at the current moment: obtain the time series curve of the pollution degree coefficient on the current day. When the slope of the current moment on the time series curve is greater than zero, the pollution degree coefficient at the current moment shows an increasing trend; when the slope of the current moment on the time series curve is less than zero, the pollution degree coefficient at the current moment shows a decreasing trend.

[0074] If the slope of the current moment on the time series curve is zero, it is considered that the pollution degree is stable, the existing state of the system is stable, and the influent flow rate is not adjusted.

[0075] Considering that the influent interference index at the current moment represents the interference situation of the current influent state on the sewage treatment, and the pollution degree coefficient at the next moment represents the pollution degree situation that the system will face, so the influent flow rate of the high-concentration wastewater is adjusted based on the influent interference index at the current moment and the pollution degree coefficient at the next moment, improving the forward-looking and initiative of the system adjustment, reducing the influence of the adjustment on the feedback index, and ensuring the sewage treatment effect.

[0076] Preferably, in an embodiment of the present invention, when it is considered that the pollution degree coefficient at the current moment shows an increasing trend, it is necessary to reduce the influent flow rate of the high-concentration wastewater to avoid causing too much load on the subsequent biochemical and physical-chemical steps and affecting the sewage treatment effect; at the same time, the greater the predicted pollution degree coefficient at the next moment, the greater the net water purification pressure faced by the system, the smaller the influent flow rate required, and the greater the amplitude of the reduction in the influent flow rate should be; When it is considered that the pollution degree coefficient at the current moment shows a decreasing trend, it is necessary to increase the influent flow rate of the high-concentration wastewater to maintain the treatment efficiency of the subsequent biochemical and physical-chemical steps and improve the overall sewage treatment efficiency; at the same time, the greater the predicted pollution degree coefficient at the next moment, the greater the net water purification pressure faced by the system, the smaller the influent flow rate required, and the smaller the amplitude of the increase in the influent flow rate should be; Based on this, if the pollution degree coefficient at the current moment shows an increasing trend, the adjustment factor is obtained by fusing the influent interference index at the current moment and the pollution degree coefficient at the next moment; both the influent interference index and the pollution degree coefficient at the next moment are negatively correlated with the adjustment factor; If the pollution degree coefficient at the current moment shows a decreasing trend, the adjustment factor is obtained by fusing the influent interference index at the current moment and the pollution degree coefficient at the next moment; the influent interference index is positively correlated with the adjustment factor; the pollution degree coefficient at the next moment is negatively correlated with the adjustment factor; The influent flow rate at the current moment is adjusted based on the adjustment factor.

[0077] As an example, the calculation formula for the adjusted influent flow rate of the high-concentration wastewater includes: ; Wherein, represents the influent flow rate of the high-concentration wastewater before adjustment at the current i-th moment; The influent flow rate of the high-concentration wastewater after adjustment at the current i-th moment; represents the influent interference index at the current i-th moment; represents the pollution degree coefficient at the next moment of the current i-th moment; represents the slope on the time series curve of the pollution degree coefficient at the current i-th moment; represents the linear normalization function.

[0078] In the formula, when , the influent interference index at the current moment and the pollution degree coefficient at the next moment are fused by addition, and through addition first, then normalization, and finally subtracting the normalized value from the constant 1, is negatively correlated and normalized to obtain the adjustment factor , which is multiplied and fused with the influent flow rate before adjustment at the current moment to reduce the influent flow rate and meet the adjustment logic when the pollution degree coefficient shows an increasing trend; At At this time, the influent interference index at the current moment and the pollution degree coefficient at the next moment are fused by subtraction. By first subtracting, then normalizing, and finally adding a constant 1, the adjustment factor is obtained. This is multiplied by the influent flow rate before adjustment at the current moment for fusion to increase the influent flow rate, meeting the adjustment logic when the pollution degree coefficient shows a decreasing trend.

[0079] It should be noted that in the calculation process of adjusting the influent flow rate, because the calculation methods of the adjustment factors for the increasing and decreasing trends of the pollution degree coefficient are different, two data dimensions are used for normalization, that is One data dimension, One data dimension.

[0080] In other embodiments of the present invention, the implementer can perform normalization on and respectively before fusion, so that and have the same influence on the adjustment factor, avoiding the influence of the order of magnitude and dimension; the implementer can also add an adjustment range coefficient to control the adjustment range of the influent flow rate per time, such as is the adjustment range coefficient, then the adjustment range is controlled within 80% to 120% of

[0081] In an embodiment of the present invention, is used as the predicted value of the influent flow rate of high-concentration wastewater at the next moment and transmitted to the PLC control system; based on the control signal of the electric control valve output by the PLC control system, the influent flow rate of high-concentration wastewater at the next moment is pre-adjusted by using the electric control valve. When the remaining capacity of the regulation tank is less than 10%, the water inlet is stopped.

[0082] And the output device is used to output the predicted value of the influent flow rate of high-concentration wastewater at the next moment and the measured values of the indexes of each link in the current state.

[0083] An embodiment of the present invention also provides a sewage treatment system in the process of coal tar deep processing. Please refer to Figure 3 which shows the system block diagram of a sewage treatment system in the process of coal tar deep processing provided by an embodiment of the present invention, specifically including: a data acquisition module 101, a data prediction module 102, a response matching module 103, and an influent adjustment module 104.

[0084] Data acquisition module 101: Obtain the historical data and real-time data of the preset feedforward indexes and feedback indexes in the sewage treatment process and divide them at a preset cycle; ​Data prediction module 102: Obtain the growth segments of the feedforward metrics; obtain the growth coefficient for each moment according to the growth trend of each growth segment and the data value at each moment in the segment; obtain the pollution degree coefficient of the regulating tank at the corresponding next moment according to the growth coefficients of all feedforward metrics at each moment and the correlation characteristics between various feedforward metrics. Response matching module 103: Within each historical preset period, perform time series partitioning on the data of the pollution degree coefficient and each feedback metric with adjacent extreme points, and obtain the fluctuation segments respectively; obtain the anomaly index and screen out the abnormal fluctuation segments according to the fluctuation amplitude and fluctuation prominence within each fluctuation segment; obtain the response fluctuation segment corresponding to the abnormal fluctuation segment of the pollution degree coefficient according to the time interval between the abnormal fluctuation segment of the pollution degree coefficient and the abnormal fluctuation segment of the subsequent feedback metric, in combination with the similarity of the anomaly index. Inlet water regulation module 104: Obtain the inlet water interference index at the current moment according to the overall response characteristics of the response fluctuation segments of each feedback metric in the historical data to the pollution degree coefficient, in combination with the change trend of the pollution degree coefficient at the current moment; regulate the inlet water flow of the high-concentration wastewater based on the inlet water interference index at the current moment and the pollution degree coefficient at the next moment.

[0085] The implementation manners of all modules of a sewage treatment system in the coal tar deep processing process have been described in a sewage treatment method in the coal tar deep processing process described in steps S1 - S4, and will not be repeated here.

[0086] An embodiment of the present invention further provides a sewage treatment device in the coal tar deep processing process. The device includes a memory, a processor, and a computer program, where the memory is used to store the corresponding computer program, the processor is used to run the corresponding computer program, and when the computer program runs in the processor, it can implement the sewage treatment method in the coal tar deep processing process described in steps S1 - S4.

[0087] In summary, in view of the technical problem that the existing water quality regulation methods are difficult to cope with the frequent changes in the sewage concentration of coal tar, and it is easy to have abnormal regulation, affecting the sewage treatment effect, the present invention proposes a sewage treatment method, device and system in the process of coal tar deep processing. The present invention first obtains the historical data and real-time data of various indicators; further predicts the pollution degree coefficient of the regulation tank at the corresponding next moment according to the change of the feedforward indicator; further screens out the abnormal fluctuation segments of the pollution degree coefficient and the data of each feedback indicator; further obtains the response fluctuation segment corresponding to the abnormal fluctuation segment of the pollution degree coefficient; finally, according to the overall response characteristics of the response fluctuation segments of each feedback indicator in the historical data to the pollution degree coefficient, combined with the change trend of the pollution degree coefficient at the current moment and the pollution degree coefficient at the next moment, the influent flow rate of the high-concentration wastewater is adjusted. The present invention predicts the wastewater concentration in the regulation tank through the feedforward indicator, and combines the response characteristics of the feedback indicator to predict the influence degree of the wastewater concentration on the sewage treatment, so as to adjust the influent flow rate based on the current wastewater concentration change, dynamically predict the system load, accurately control the influent volume, and effectively improve the sewage treatment efficiency and system stability.

[0088] It should be noted that the above order of the embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0089] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. The key point of each embodiment is to illustrate the differences from other embodiments.

Claims

1. A sewage treatment method in the deep processing of coal tar, characterized in that, The method includes: Obtaining historical data and real-time data of preset feedforward indicators and feedback indicators in the sewage treatment process, and dividing them at preset intervals; Obtaining the growth segments of the feedforward indicators; according to the growth trends of each growth segment and the data values at each moment in the segment, obtaining the growth coefficients corresponding to each moment; according to the growth coefficients of all feedforward indicators at each moment, combining the correlation characteristics between various feedforward indicators, obtaining the pollution degree coefficient of the regulation tank at the corresponding next moment; Within each historical preset interval, performing time series division on the data of the pollution degree coefficient and each feedback indicator with adjacent extreme points, respectively obtaining fluctuation segments; according to the fluctuation amplitude and fluctuation prominence within each fluctuation segment, obtaining the anomaly index and screening out the abnormal fluctuation segments; according to the time interval between the abnormal fluctuation segment of the pollution degree coefficient and the abnormal fluctuation segment of the subsequent feedback indicator, combining the similarity of the anomaly index, obtaining the response fluctuation segment corresponding to the abnormal fluctuation segment of the pollution degree coefficient; According to the overall response characteristics of the response fluctuation segments of each feedback indicator in the historical data to the pollution degree coefficient, combining the change trend of the pollution degree coefficient at the current moment, obtaining the influent interference index at the current moment; adjusting the influent flow rate of the high-concentration wastewater based on the influent interference index at the current moment and the pollution degree coefficient at the next moment.

2. The sewage treatment method in the deep processing of coal tar according to claim 1, characterized in that, The method for obtaining the growth coefficient includes: According to the number of first-order difference values of the growth segment, the overall characteristics of the first-order difference values, and the data values at each moment in the segment, obtaining the growth coefficient corresponding to each moment.

3. The sewage treatment method in the deep processing of coal tar according to claim 1, characterized in that, The method for obtaining the pollution degree coefficient includes: Selecting any moment as the target moment; based on all the data from the target moment to the start moment of the preset interval to which it belongs, obtaining the Pearson correlation coefficient matrix between the feedforward indicators at the target moment and obtaining the eigenvector matrix; Based on the vector elements corresponding to the feedforward indicators at the target moment in the eigenvector corresponding to the maximum eigenvalue, performing weighted summation on the growth coefficients of the feedforward indicators at the target moment, and taking the weighted summation result as the pollution degree coefficient at the next moment of the target moment.

4. The sewage treatment method in the deep processing of coal tar according to claim 1, characterized in that, The method for obtaining the anomaly index includes: According to the overall fluctuation amplitude of the fluctuation segment, combining the overall difference between the data of the fluctuation segment and all historical data of the same dimension, obtaining the anomaly index corresponding to the fluctuation segment; the overall fluctuation amplitude is positively correlated with the anomaly index.

5. A sewage treatment method in the deep processing of coal tar according to claim 1, characterized in that, The method for obtaining the response fluctuation segment includes: Selecting any one of the feedback indicators as the feedback target indicator, selecting any abnormal fluctuation segment of the pollution degree coefficient as the target fluctuation segment, and taking each abnormal fluctuation segment of the feedback target indicator within the preset interval to which the target fluctuation segment belongs and within the time domain after the start moment of the target fluctuation segment as the fluctuation segment to be analyzed; According to the time interval between each fluctuation segment to be analyzed and the start moment of the target fluctuation segment, combining the similarity of the anomaly index, obtaining the matching coefficient corresponding to each fluctuation segment to be analyzed; selecting the fluctuation segment to be analyzed with the largest matching coefficient as the response fluctuation segment of the target fluctuation segment.

6. The sewage treatment method in the deep processing of coal tar according to claim 1, characterized in that, The method for obtaining the influent interference index includes: Based on the increase or decrease of the abnormal fluctuation segments of the pollution degree coefficient, all the response fluctuation segments are divided into two categories; For each category of the response fluctuation segments, according to the time interval between the start time of a category of the response fluctuation segments and the start time of the corresponding abnormal fluctuation segment of the pollution degree coefficient, and combining the time interval between the end time of a category of the response fluctuation segments and the start time of the corresponding abnormal fluctuation segment of the pollution degree coefficient, the predicted response duration is obtained; According to the distribution characteristics of the fluctuation amplitude of a category of the response fluctuation segments, and combining the predicted response duration, the influent interference index of a category of the response fluctuation segments is obtained; According to the increase or decrease trend of the pollution degree coefficient at the current moment, the corresponding influent interference index is selected.

7. The sewage treatment method in the deep processing of coal tar according to claim 1, wherein The method for obtaining the influent flow rate includes: If the pollution degree coefficient at the current moment shows an increasing trend, the influent interference index at the current moment and the pollution degree coefficient at the next moment are fused to obtain an adjustment factor; both the influent interference index and the pollution degree coefficient at the next moment are negatively correlated with the adjustment factor; If the pollution degree coefficient at the current moment shows a decreasing trend, the influent interference index at the current moment and the pollution degree coefficient at the next moment are fused to obtain an adjustment factor; the influent interference index is positively correlated with the adjustment factor; the pollution degree coefficient at the next moment is negatively correlated with the adjustment factor; Based on the adjustment factor, the influent flow rate at the current moment is adjusted.

8. The sewage treatment method in the deep processing of coal tar according to claim 1, characterized in that, The time domain length of the growth segment is at least 3.

9. A sewage treatment system in the deep processing of coal tar, characterized in that, The system includes: Data acquisition module: acquiring historical data and real-time data of preset feedforward indicators and feedback indicators during the sewage treatment process, and dividing them at a preset cycle; Data prediction module: acquiring the growth segments of the feedforward indicators; according to the growth trend of each growth segment and combining the data values at each moment in the segment, obtaining the growth coefficient corresponding to each moment; according to the growth coefficients of all feedforward indicators at each moment, and combining the correlation characteristics between the various feedforward indicators, obtaining the pollution degree coefficient of the regulating tank at the corresponding next moment; Response matching module: within each historical preset cycle, using adjacent extreme points to perform time series partitioning on the data of the pollution degree coefficient and various feedback indicators, respectively obtaining fluctuation segments; according to the fluctuation amplitude and fluctuation prominence within each fluctuation segment, obtaining an anomaly index and screening out abnormal fluctuation segments; according to the time interval between the abnormal fluctuation segment of the pollution degree coefficient and the abnormal fluctuation segment of the subsequent feedback indicator, and combining the similarity of the anomaly index, obtaining the response fluctuation segment corresponding to the abnormal fluctuation segment of the pollution degree coefficient; Influent regulation module: according to the overall response characteristics of the response fluctuation segments of various feedback indicators in the historical data to the pollution degree coefficient, and combining the change trend of the pollution degree coefficient at the current moment, obtaining the influent interference index at the current moment; adjusting the influent flow rate of the high-concentration wastewater based on the influent interference index at the current moment and the pollution degree coefficient at the next moment.

10. A sewage treatment device in the deep processing of coal tar, the device includes a memory, a processor, and a computer program stored in the memory and operable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the sewage treatment method in any one of claims 1 to 8.

Images