An intelligent treatment method for wastewater from thermal power plants based on artificial intelligence

Abstract

The present application relates to the field of wastewater treatment technology, and specifically to an intelligent treatment method for wastewater from a thermal power plant based on artificial intelligence, the method comprising: detecting the volume of wastewater and collecting the concentration data of various pollutants in each batch of wastewater; determining a single pollution concentration data sequence of various pollutants; determining the degree of difference between each data and the single pollution concentration data sequence; determining the average change difference index between various pollutants and all other pollutants in each batch of wastewater; determining the stable treatment degree of the concentration of all pollutants in each batch of wastewater based on the similarity and difference between the concentration of all pollutants in each batch of wastewater and the concentration of all pollutants in previous wastewater; determining the change index of all pollutants in each batch of wastewater; judging the adjustment of wastewater treatment equipment based on the change index of all pollutants in the current batch of wastewater. The present application aims to improve the wastewater treatment effect.

Description

Technical Field

[0001] The present application relates to the technical field of wastewater treatment, and in particular to an intelligent treatment method for wastewater from a thermal power plant based on artificial intelligence. Background Art

[0002] With the acceleration of industrialization, thermal power plants, as an important pillar of energy supply, play a vital role worldwide. However, the efficient power generation process of thermal power plants is accompanied by the generation of a large amount of wastewater. These wastewaters not only occupy precious water resources, but also pose a serious threat to the environment due to their complex composition and high concentration of harmful substances. Once the wastewater from thermal power plants is not properly treated and is directly discharged into surface water bodies or infiltrates into the ground, it will have long-term and far-reaching negative impacts on water ecology, soil quality and even human health.

[0003] Although the current wastewater treatment technology of thermal power plants has achieved wastewater purification and pollutant reduction to a certain extent, there are still some problems that need to be solved in practical applications. For example, due to the complex composition of wastewater from thermal power plants and certain interactions between pollutants, the existing treatment methods are difficult to adjust the wastewater treatment equipment according to the sudden change of pollutant concentration in the wastewater, and cannot accurately treat pollutants with sudden concentration changes, resulting in poor wastewater treatment effects. Summary of the invention

[0004] In view of the above, it is necessary to provide an intelligent treatment method for wastewater from thermal power plants based on artificial intelligence, which improves the wastewater treatment effect compared with traditional intelligent treatment methods for wastewater from thermal power plants.

[0005] The present invention discloses an intelligent treatment method for wastewater from a thermal power plant based on artificial intelligence, which adopts the following technical solutions:

[0006] An embodiment of the present application provides an intelligent treatment method for wastewater from a thermal power plant based on artificial intelligence, the method comprising the following steps:

[0007] Detect wastewater volume and collect concentration data of various pollutants in each batch of wastewater;

[0008] Determine the single pollution concentration data series of various pollutants based on the concentration data of various pollutants in all batches of wastewater; determine the degree of difference between each data and the single pollution concentration data series based on the distribution of data in each single pollution concentration data series;

[0009] According to the distribution of data in the single pollution concentration data series of all pollutants and the degree of difference between each data and the single pollution concentration data series, determine the average change difference index between various pollutants and all other pollutants in each batch of wastewater;

[0010] Determine the stable treatment degree of all pollutant concentrations in each batch of wastewater based on the similarities and differences between all pollutant concentrations in each batch of wastewater and those in previous wastewaters;

[0011] Determine the change index of all pollutants in each batch of wastewater according to the average change difference index and stable treatment degree corresponding to all pollutants in each batch of wastewater;

[0012] Determine the adjustment of wastewater treatment equipment based on the change index of all pollutants in the current batch of wastewater.

[0013] In one embodiment, the method for determining the single pollution concentration data sequence is:

[0014] The normalized values ​​of the concentration data of all pollutants in each batch of wastewater are used to form the pollutant concentration sequence of each single batch of wastewater;

[0015] The concentration matrix is ​​constructed by inserting the single batch wastewater pollutant concentration sequence of each batch of wastewater row by row;

[0016] The data corresponding to various pollutants are extracted from the concentration matrix respectively to form various horizontal sequences, which are recorded as single pollution concentration data sequences of various pollutants.

[0017] In one embodiment, the method for determining the degree of difference is:

[0018] Clustering algorithms are used to cluster the data in each single pollution concentration data series;

[0019] For each single pollution concentration data sequence, the outlier factor of each data in the single pollution concentration data sequence is determined according to the distribution of the data in the single pollution concentration data sequence and the elements in the clusters corresponding to each data in the single pollution concentration data sequence;

[0020] Calculate the difference in standard deviation between each cluster corresponding to a single pollution concentration data sequence and all elements in the remaining clusters, recorded as the first difference, calculate the difference in the mean of all elements in each cluster corresponding to a single pollution concentration data sequence and all elements in the remaining clusters, recorded as the second difference, calculate the product of the first difference and the second difference, recorded as the difference product, calculate the cumulative sum of all the difference products of each cluster corresponding to the single pollution concentration data sequence, and the degree of difference between each data and the single pollution concentration data sequence is positively correlated with the cumulative sum of the cluster where each data is located and the outlier factor of each data, respectively.

[0021] In one embodiment, the method for determining the outlier factor is:

[0022] Calculate the absolute value of the difference between each data in the single pollution concentration data sequence and its adjacent previous data and adjacent next data, and record them as the previous difference absolute value and the next difference absolute value; wherein, when the data is located at the first or last position in the single pollution concentration data sequence, the corresponding previous difference absolute value or the next difference absolute value is set to 0;

[0023] The number of elements with the same value as each data in the cluster where each data is located is counted, and the sum of the absolute value of the previous difference and the absolute value of the latter difference is calculated. The outlier factor of each data is positively correlated with the sum corresponding to each data and the number of elements in the cluster where each data is located, and is negatively correlated with the number corresponding to each data.

[0024] In one embodiment, the method for determining the average change difference index is:

[0025] Determine the corresponding degree of change between any two pollutants in each batch of wastewater according to the change in concentration data of any two pollutants in all batches of wastewater;

[0026] Determine the historical change difference between the arbitrary two pollutants in each batch of wastewater according to the difference between the corresponding change degree between the arbitrary two pollutants in each batch of wastewater relative to the corresponding change degree between the arbitrary two pollutants in all batches of wastewater;

[0027] The mean of the historical change differences between various pollutants and all other pollutants in each batch of wastewater is calculated and recorded as the mean of the comprehensive change degree. The average change difference index between various pollutants and all other pollutants in each batch of wastewater is positively correlated with the mean of the comprehensive change degree of various pollutants in each batch of wastewater and the corresponding difference degree of concentration data of various pollutants.

[0028] In one embodiment, the method for determining the corresponding degree of change is:

[0029] Calculate the mean and standard deviation of all data in the single pollution concentration data sequence of the arbitrary two pollutants, recorded as the concentration mean and concentration standard deviation, respectively calculate the difference between the normalized value of the concentration data of the arbitrary two pollutants in each batch of wastewater and the corresponding concentration mean, recorded as the concentration change difference, calculate the product of the concentration change differences of the arbitrary two pollutants in each batch of wastewater, recorded as the first concentration change product; calculate the product of the concentration standard deviations of the arbitrary two pollutants, recorded as the second concentration change product; in each batch of wastewater, the corresponding change degree between the arbitrary two pollutants is positively correlated with the absolute value of the first concentration change product corresponding to each batch of wastewater, and negatively correlated with the second concentration change product.

[0030] In one embodiment, the method for determining the historical change difference is:

[0031] Calculate the mean of the corresponding change degrees between any two pollutants in all batches of wastewater, record it as the mean change degree, and take the absolute value of the difference between the corresponding change degree between any two pollutants in each batch of wastewater and the mean change degree as the historical change difference between the any two pollutants in each batch of wastewater.

[0032] In one embodiment, the method for determining the stability degree is:

[0033] The mean of each column of data in the concentration matrix is ​​used to form a concentration mean sequence;

[0034] The difference between the pollutant concentration sequence of each single batch of wastewater and the corresponding position data in the concentration mean sequence is used as the independent variable of the sign function, and the calculation results of the sign function are used to form a comparison sequence of each batch of wastewater;

[0035] Calculate the distance between the comparison sequence of each batch of wastewater and the comparison sequences of other batches of wastewater, and take the number of times the distance is 0 as the number of occurrences of the comparison sequence of each batch of wastewater;

[0036] Calculate the sum of all elements in the concentration mean sequence, recorded as the first concentration sum, calculate the sum of all elements in the single batch wastewater pollutant concentration sequence of each batch of wastewater, recorded as the second concentration sum, calculate the product of the range of the concentration mean sequence and the first concentration sum, recorded as the first concentration product, calculate the product of the range of the single batch wastewater pollutant concentration sequence of each batch of wastewater and the corresponding second concentration sum, recorded as the second concentration product, calculate the absolute value of the difference between the second concentration product and the first concentration product of each batch of wastewater, the stable treatment degree of all pollutant concentrations in each batch of wastewater is negatively correlated with the absolute value of the difference of each batch of wastewater, and is positively correlated with the number of occurrences of the comparison sequence of each batch of wastewater.

[0037] In one embodiment, the method for determining the change index is:

[0038] The average value of the average change difference index corresponding to all pollutants in each batch of wastewater is calculated. The change index of all pollutants in each batch of wastewater is positively correlated with the said average value of each batch of wastewater, and negatively correlated with the stable treatment degree of all pollutant concentrations in each batch of wastewater.

[0039] In one embodiment, the process of determining the adjustment status of the wastewater treatment equipment according to the change index of the pollutants in the current batch of wastewater is:

[0040] Calculate the change index of all pollutants in the current batch of wastewater. If the change index value is less than or equal to the preset change index threshold, do not adjust the wastewater treatment equipment; otherwise, adjust the wastewater treatment equipment;

[0041] When adjusting the wastewater treatment equipment, the discharge volume of the current batch of wastewater, the degree of difference corresponding to each pollutant in the wastewater, and the average change difference index corresponding to each pollutant are used as inputs of the neural network, and the output of the neural network is the dosage of the agent corresponding to each pollutant.

[0042] This application has at least the following beneficial effects:

[0043] This application analyzes the wastewater generation process and the concentration characteristics of pollutants in the wastewater, performs cluster analysis on the concentration data of various pollutants in multiple batches of wastewater, and constructs the degree of difference, which can effectively identify whether there is a data mutation in the data sequence corresponding to various pollutants;

[0044] Considering the potential correlation between pollutants, an average change difference index is constructed to evaluate the correlation between pollutants. Through the difference in correlation with historical data, it is verified whether the correlation between pollutants still conforms to the historical correlation.

[0045] The degree of recurrence of pollutant concentration data in wastewater in historical data is calculated, and the concentration of pollutants is comprehensively tested through the difference between it and the pollutant concentration in multiple batches of wastewater to determine whether the degree of change is significant; finally, a change index is constructed to characterize the difference between the pollutant concentration data and historical data. It can detect whether the concentration of pollutants has changed dramatically, and adjust the treatment equipment when the pollutant concentration changes dramatically, thereby improving the wastewater treatment effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. 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 creative work.

[0047] Figure 1 A flowchart of the steps of an intelligent treatment method for wastewater from a thermal power plant based on artificial intelligence provided in this application;

[0048] Figure 2 This is a schematic diagram of the process flow for determining the adjustment status of wastewater treatment equipment. DETAILED DESCRIPTION

[0049] In the description of the embodiments of the present application, words such as "exemplary", "or", "for example" and the like are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "or", "for example" and the like is intended to present related concepts in a concrete manner.

[0050] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art in the present application. The terms used in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. It should be understood that, unless otherwise specified, " / " means or.

[0051] It should also be noted that the terms "first" and "second" in the specification, claims and drawings of this application are used to distinguish similar objects, rather than to describe a specific order or sequence. The method disclosed in the embodiments of this application or the method shown in the flowchart includes one or more steps for implementing the method. Without departing from the scope of the claims, the execution order of multiple steps can be interchanged with each other, and some steps can also be deleted.

[0052] The specific scheme of an intelligent treatment method for wastewater from a thermal power plant based on artificial intelligence provided by the present application is described in detail below with reference to the accompanying drawings.

[0053] An embodiment of the present application provides an intelligent treatment method for wastewater from a thermal power plant based on artificial intelligence. Specifically, the following intelligent treatment method for wastewater from a thermal power plant based on artificial intelligence is provided. Figure 1 , the method comprises the following steps:

[0054] Step S001, detecting the volume of wastewater, collecting concentration data of pollutants in the wastewater, and preprocessing the concentration data.

[0055] Detect wastewater volume and collect concentration data of various pollutants in each batch of wastewater.

[0056] It should be noted that the detection of wastewater volume and the collection of concentration data of various pollutants in the wastewater can be carried out through corresponding sensors and monitoring instruments. In this embodiment, an ultrasonic liquid level sensor is used to detect the volume of wastewater discharged in each batch; a spectrometer is used to determine the concentration of various heavy metals in the wastewater, such as copper, lead, zinc, mercury and cadmium.

[0057] In order to avoid the influence of different data dimensions, the concentration data of all pollutants in N batches of wastewater are normalized, and the normalized values ​​of the concentration data of all pollutants in each batch of wastewater are combined into the pollutant concentration sequence of each single batch of wastewater.

[0058] The concentration matrix is ​​constructed by inserting the single batch wastewater pollutant concentration sequence of N batches of wastewater obtained from the thermal power plant row by row.

[0059] In one embodiment of the present application, a maximum normalization method is used to obtain a normalized value of the concentration data. As other implementations, implementers may also use other existing technologies to obtain a normalized value of the concentration data, and the present application does not impose any special restrictions.

[0060] It should be noted that the types of pollutants and the value of N can be set by the implementer according to the actual working site of the wastewater treatment equipment in the thermal power plant. This application does not impose any special restrictions. In this embodiment, N is 800.

[0061] Step S002, constructing the degree of difference by analyzing the concentration characteristics of pollutants; constructing the average change difference index by analyzing the correlation between pollutants; and calculating the stable treatment degree and change index of all pollutant concentrations in each batch of wastewater.

[0062] Generally, if the concentration of pollutants in wastewater is not much different from the previous concentration, the pollutants in wastewater can be removed by existing wastewater treatment equipment to achieve wastewater treatment. If the concentration of pollutants in wastewater is significantly different from the previous concentration, for example, the content of a certain pollutant exceeds the standard or is very low, the wastewater treatment equipment will have a poor treatment effect on the wastewater. Therefore, the wastewater treatment equipment needs to be adjusted to achieve more accurate and efficient treatment of wastewater.

[0063] Since pollutants in wastewater from thermal power plants usually come from specific links or specific raw materials in the production process, the generation of pollutants under normal circumstances has a certain regularity and repeatability. Therefore, the concentration of pollutants in the wastewater is usually relatively stable, and the values ​​fluctuate within a certain range.

[0064] Sub-step 1: determine the single pollution concentration data sequence of various pollutants based on the concentration data of various pollutants in all batches of wastewater; and determine the degree of difference between each data and the single pollution concentration data sequence according to the distribution of data in each single pollution concentration data sequence.

[0065] The data corresponding to various pollutants are extracted from the concentration matrix to form various horizontal sequences, which are recorded as single pollution concentration data sequences of various pollutants. The data in each single pollution concentration data sequence is used as input and clustering is performed using a clustering algorithm.

[0066] In one embodiment of the present application, a k-means algorithm is used for clustering. As other implementation methods, on the basis of realizing clustering of data in each single pollution concentration data sequence, the implementer may use other existing technologies to cluster the data in each single pollution concentration data sequence, and the present application does not impose any special restrictions.

[0067] For each single pollution concentration data sequence, the outlier factor of each data in the single pollution concentration data sequence is determined according to the distribution of the data in the single pollution concentration data sequence and the elements in the clusters corresponding to each data in the single pollution concentration data sequence. The specific process is:

[0068] Calculate the absolute value of the difference between each data in the single pollution concentration data sequence and its adjacent previous data and adjacent next data, and record them as the previous difference absolute value and the next difference absolute value; wherein, when the data is located at the first or last position in the single pollution concentration data sequence, the corresponding previous difference absolute value or the next difference absolute value is set to 0;

[0069] The number of elements with the same value as each data in the cluster where each data is located is counted, and the sum of the absolute value of the previous difference and the absolute value of the latter difference is calculated. The outlier factor of each data is positively correlated with the sum corresponding to each data and the number of elements in the cluster where each data is located, and is negatively correlated with the number corresponding to each data.

[0070] It should be understood that: positive correlation means that the changing trends of the dependent variable and the independent variable are in the same direction, such as a multiplication relationship, an addition relationship, and the idempotence of an exponential function. The implementer can set it according to the actual situation, and this application does not impose any special restrictions; negative correlation means that the changing trends of the dependent variable and the independent variable are in opposite directions, such as a subtraction relationship, a division relationship, etc. The implementer can set it according to the actual situation, and this application does not impose any special restrictions.

[0071] In one embodiment of the present application, the product of the sum value corresponding to each data and the number of elements in the cluster where each data is located is calculated, and the sum value of the number corresponding to each data and a preset adjustment parameter coefficient greater than 0 is calculated and recorded as the adjustment parameter sum value, and the ratio of the product to the adjustment parameter sum value is used as the outlier factor of each data.

[0072] It should be noted that: since the data is discrete data, each data item does not have a time trend feature with the adjacent data. Therefore, if the data is mutation data, the absolute value of the difference between the data and the adjacent previous data and the adjacent next data is large; and because the generation of pollutants under normal circumstances has a certain regularity and repeatability, the fewer the number of elements in the cluster where the data is located with the same value as the data. The larger the value of the outlier factor of the data, the greater the possibility that the data is mutation data.

[0073] Furthermore, for each single pollution concentration data sequence, the difference between each data and the single pollution concentration data sequence is determined according to the distribution of elements in all clusters corresponding to the single pollution concentration data sequence and the outlier factor of each data in the single pollution concentration data sequence. The specific process is as follows:

[0074] Calculate the difference in standard deviation between each cluster corresponding to a single pollution concentration data sequence and all elements in the remaining clusters, recorded as the first difference, calculate the difference in the mean of all elements in each cluster corresponding to a single pollution concentration data sequence and all elements in the remaining clusters, recorded as the second difference, calculate the product of the first difference and the second difference, recorded as the difference product, calculate the cumulative sum of all the difference products of each cluster corresponding to the single pollution concentration data sequence, and the degree of difference between each data and the single pollution concentration data sequence is positively correlated with the cumulative sum of the cluster where each data is located and the outlier factor of each data, respectively.

[0075] In one embodiment of the present application, the product of the cumulative sum of the clusters where each data is located and the outlier factor of each data is used as the degree of difference between each data and the single pollution concentration data sequence where the data is located.

[0076] It should be noted that: under normal circumstances, the data differences within each cluster are small, the standard deviation is small, and the standard deviations of each cluster are relatively consistent, so the first difference is small; similarly, due to the small data fluctuations, the difference between the data is small, so the second difference between the clusters is small. At this time, if the value of the difference between the data and the single pollution concentration data sequence is smaller, the possibility that the data is mutation data is smaller; the greater the value of the difference between the data and the single pollution concentration data sequence, the greater the possibility that the data is mutation data.

[0077] At this point, by calculating the degree of difference between the data and the single pollution concentration data sequence, the degree of deviation of the data relative to the single pollution concentration data sequence can be reflected; the greater the degree of difference, the greater the possibility that the data is mutation data.

[0078] Sub-step 2, based on the distribution of data in the single pollution concentration data sequence of all pollutants and the degree of difference between each data and the single pollution concentration data sequence, determine the average change difference index between various pollutants and all other pollutants in each batch of wastewater.

[0079] Generally speaking, the concentration of pollutants has a certain degree of stability, but if there is a problem in the wastewater discharge process or a certain link in the mineral material, it will have a greater impact on the concentration of pollutants, and may also cause changes in the concentrations of multiple pollutants, that is, the concentration of a certain pollutant will change synchronously with the concentrations of other pollutants.

[0080] According to the change of concentration data of any two pollutants in all batches of wastewater, the corresponding change degree between the any two pollutants in each batch of wastewater is determined. The specific process is:

[0081] Calculate the mean and standard deviation of all data in the single pollution concentration data sequence of the arbitrary two pollutants, recorded as the concentration mean and concentration standard deviation, respectively calculate the difference between the normalized value of the concentration data of the arbitrary two pollutants in each batch of wastewater and the corresponding concentration mean, recorded as the concentration change difference, calculate the product of the concentration change differences of the arbitrary two pollutants in each batch of wastewater, recorded as the first concentration change product; calculate the product of the concentration standard deviations of the arbitrary two pollutants, recorded as the second concentration change product; in each batch of wastewater, the corresponding change degree between the arbitrary two pollutants is positively correlated with the absolute value of the first concentration change product corresponding to each batch of wastewater, and negatively correlated with the second concentration change product.

[0082] In one embodiment of the present application, the ratio of the absolute value of the first concentration change product corresponding to each batch of wastewater to the second concentration change product is used as the corresponding degree of change between the any two pollutants in each batch of wastewater.

[0083] It should be noted that: the concentration change difference represents the deviation between the normalized value of the concentration data of any two pollutants and their respective historical average concentrations in each batch of wastewater; if the concentration change difference of any two pollutants changes in the same direction, it means that in each batch of wastewater, the concentration change trend of the any two pollutants is becoming more consistent; the original product is standardized by the standard deviation to avoid differences between the units of pollutant concentrations, and the problem of difficulty in comparing the results in subsequent calculations. At this time, the larger the value of the corresponding degree of change between the any two pollutants, the more correlation there is between the any two pollutants in each batch of wastewater.

[0084] Further, according to the difference in the corresponding change degree between the two pollutants in each batch of wastewater relative to the corresponding change degree between the two pollutants in all batches of wastewater, the historical change difference between the two pollutants in each batch of wastewater is determined, and the specific process is:

[0085] Calculate the mean of the corresponding change degrees between any two pollutants in all batches of wastewater, record it as the mean change degree, and take the absolute value of the difference between the corresponding change degree between any two pollutants in each batch of wastewater and the mean change degree as the historical change difference between the any two pollutants in each batch of wastewater.

[0086] It should be noted that the historical change difference between any two pollutants in each batch of wastewater represents the difference between the correlation between any two pollutants in each batch of wastewater and the historical correlation. The larger the value, the greater the difference, and the correlation in each batch of wastewater is less consistent with the historical correlation.

[0087] Furthermore, according to the historical change difference between each pollutant and all other pollutants in each batch of wastewater, and the degree of difference corresponding to the concentration data of each pollutant in each batch of wastewater, the average change difference index between each pollutant and all other pollutants in each batch of wastewater is determined. The specific process is:

[0088] The mean of the historical change differences between various pollutants and all other pollutants in each batch of wastewater is calculated and recorded as the mean of the comprehensive change degree. The average change difference index between various pollutants and all other pollutants in each batch of wastewater is positively correlated with the mean of the comprehensive change degree of various pollutants in each batch of wastewater and the corresponding difference degree of concentration data of various pollutants.

[0089] In one embodiment of the present application, the product of the mean value of the comprehensive change degree of various pollutants in each batch of wastewater and the difference degree corresponding to the concentration data of various pollutants is used as the average change difference index between various pollutants and all other pollutants in each batch of wastewater.

[0090] It should be noted that: the smaller the value of the average change difference index between each pollutant and all other pollutants in each batch of wastewater, the more the concentration of each pollutant in each batch of wastewater is not much different from previous data, and the more the correlation between each pollutant and all other pollutants is in line with the historical correlation, the smaller the possibility of a sudden change in the concentration of each pollutant in each batch of wastewater, and the existing wastewater treatment equipment can still treat the wastewater normally; otherwise, it means that the possibility of a sudden change in the concentration of each pollutant is greater.

[0091] Sub-step 3, determining the stable treatment degree of all pollutant concentrations in each batch of wastewater based on the similarities and differences between the concentrations of all pollutants in each batch of wastewater and those in previous wastewater.

[0092] The mean of each column of data in the concentration matrix is ​​used to form a concentration mean sequence. The difference between the pollutant concentration sequence of each single batch of wastewater and the corresponding position data in the concentration mean sequence is used as the independent variable of the sign function, and the calculation results of the sign function are used to form a comparison sequence of each batch of wastewater.

[0093] The number of occurrences of the comparison sequence of each batch of wastewater is counted to determine whether there is a significant difference with previous data. The specific process is as follows:

[0094] The distance between the comparison sequence of each batch of wastewater and the comparison sequences of other batches of wastewater is calculated, and the number of times the distance is 0 is taken as the number of occurrences of the comparison sequence of each batch of wastewater.

[0095] In one embodiment of the present application, the distance is the Manhattan distance. As other implementations, on the basis of measuring the distance between two sequences, the implementer may use other existing technologies to measure the distance between two sequences, and the present application does not impose any special restrictions.

[0096] Furthermore, according to the distribution of data in the single batch wastewater pollutant concentration sequence and the concentration mean sequence of each batch of wastewater, as well as the number of occurrences of the comparison sequence of each batch of wastewater, the stable treatment degree of all pollutant concentrations in each batch of wastewater is determined. The specific process is:

[0097] Calculate the sum of all elements in the concentration mean sequence, recorded as the first concentration sum, calculate the sum of all elements in the single batch wastewater pollutant concentration sequence of each batch of wastewater, recorded as the second concentration sum, calculate the product of the range of the concentration mean sequence and the first concentration sum, recorded as the first concentration product, calculate the product of the range of the single batch wastewater pollutant concentration sequence of each batch of wastewater and the corresponding second concentration sum, recorded as the second concentration product, calculate the absolute value of the difference between the second concentration product and the first concentration product of each batch of wastewater, the stable treatment degree of all pollutant concentrations in each batch of wastewater is negatively correlated with the absolute value of the difference of each batch of wastewater, and is positively correlated with the number of occurrences of the comparison sequence of each batch of wastewater.

[0098] In one embodiment of the present application, the absolute value of the difference of each batch of wastewater is summed with a preset parameter adjustment coefficient greater than 0, and the ratio of the number of occurrences of the comparison sequence of each batch of wastewater to the calculated result of the sum is used as the stable treatment degree of all pollutant concentrations in each batch of wastewater.

[0099] It should be noted that: if the concentration of various pollutants in each batch of wastewater is not much different from its corresponding mean, and the range is small, the absolute value of the difference is small; and if the comparison sequence of each batch of wastewater appears more times in the comparison matrix, it means that it is more universal. If the concentration of pollutants in each batch of wastewater mutates, and the concentration of a certain pollutant exceeds the standard or is extremely low, the absolute value of the difference is large, and if the comparison sequence of each batch of wastewater has never appeared in the comparison matrix, it means that the more unique it is, the greater the possibility of a sudden change in the concentration of pollutants. At this time, if the value of the stable treatment degree of the concentration of all pollutants in a batch of wastewater is larger, it means that the difference between its concentration and that of pollutants in previous wastewater is not large, and the existing wastewater treatment device can still be used to treat the wastewater; otherwise, it means that the difference between its concentration and that of pollutants in previous wastewater is large, and the wastewater treatment device needs to be adjusted to a certain extent in order to treat the wastewater more accurately and efficiently.

[0100] Sub-step 4, determining the change index of all pollutants in each batch of wastewater according to the average change difference index and stable treatment degree corresponding to all pollutants in each batch of wastewater.

[0101] According to the average change difference index and stable treatment degree corresponding to all pollutants in each batch of wastewater, the change index of all pollutants in each batch of wastewater is determined. The specific process is:

[0102] The average value of the average change difference index corresponding to all pollutants in each batch of wastewater is calculated. The change index of all pollutants in each batch of wastewater is positively correlated with the said average value of each batch of wastewater, and negatively correlated with the stable treatment degree of all pollutant concentrations in each batch of wastewater.

[0103] In one embodiment of the present application, the ratio of the average value of each batch of wastewater to the stable treatment degree of all pollutant concentrations in each batch of wastewater is used as the change index of all pollutants in each batch of wastewater.

[0104] It should be noted that: if the concentration of each pollutant in each batch of wastewater is not much different from that of the corresponding pollutant in previous wastewater, the average value will be smaller, the stable treatment degree of the concentration of all pollutants in each batch of wastewater will be larger, and the change index of all pollutants in each batch of wastewater will be smaller, indicating that the concentration of each pollutant in each batch of wastewater has not increased sharply or decreased suddenly.

[0105] Step S003, judging the adjustment status of the wastewater treatment equipment according to the change index of all pollutants in the current batch of wastewater.

[0106] Collect the concentration data of various pollutants in the wastewater discharged in the current batch, and calculate the change index of all pollutants in the wastewater discharged in the current batch. If the change index value is less than or equal to the preset change index threshold, it means that the pollutant concentration in the current batch of wastewater has not changed significantly, and the wastewater can still be treated and discharged through the existing wastewater treatment equipment; otherwise, it means that the pollutant concentration in the current batch of wastewater has changed significantly, and the wastewater treatment equipment needs to be adjusted. The flow chart for judging the adjustment of wastewater treatment equipment is as follows: Figure 2 shown.

[0107] In one embodiment of the present application, the preset change index threshold is 0.5. The value of the preset change index threshold is artificially preset and can be set by the implementer. This application does not impose any special restrictions.

[0108] When adjusting the wastewater treatment equipment, the discharge volume of the current batch of wastewater, the degree of difference corresponding to each pollutant in the wastewater, and the average change difference index corresponding to each pollutant are used as the input of the neural network, and the output of the neural network is the dosage of the corresponding reagent. The output of the neural network is used as the input of the wastewater treatment equipment of the thermal power plant. According to the input dosage of the reagent, the treatment data of the sedimentation tank, filtration device, biological filter, electrochemical treatment tank and other equipment in the wastewater treatment equipment are adjusted, and targeted physical and chemical treatment is carried out according to the changes in the concentration of pollutants in the wastewater to improve the efficiency and quality of wastewater treatment.

[0109] In one embodiment of the present application, the neural network is a BP (Back Propagation) neural network, and the optimization algorithm of the BP neural network is a stochastic gradient descent algorithm. The implementer may also use other neural networks to obtain the dosage of the agent corresponding to each pollutant, and the present application does not impose any special restrictions.

[0110] In summary, this application analyzes the wastewater generation process and the concentration characteristics of pollutants in the wastewater, performs cluster analysis on the concentration data of various pollutants in multiple batches of wastewater, and constructs the degree of difference, which can effectively identify whether there is a data mutation in the data sequence corresponding to various pollutants;

[0111] Furthermore, considering the potential correlation between pollutants, an average change difference index is constructed to evaluate the correlation between pollutants. Through the difference in correlation with historical data, it is verified whether the correlation between pollutants still conforms to the historical correlation.

[0112] Furthermore, the degree of recurrence of pollutant concentration data in wastewater in historical data is calculated, and the concentration of pollutants is comprehensively tested through the difference between it and the pollutant concentrations in multiple batches of wastewater to determine whether the degree of change is significant; finally, a change index is constructed to characterize the difference between the pollutant concentration data and historical data. It can detect whether the concentration of pollutants has changed drastically, and adjust the treatment equipment when the pollutant concentration changes drastically, thereby improving the wastewater treatment effect.

[0113] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

[0114] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and that the present application can be implemented in other specific forms without departing from the spirit or basic features of the present application. Therefore, no matter from which point of view, the above embodiments of the present application should be regarded as exemplary and non-restrictive, and the scope of the present application is defined by the attached claims rather than the above description, and therefore it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present application.

Claims

1. An intelligent treatment method for wastewater from a thermal power plant based on artificial intelligence, characterized in that: The method comprises the following steps: Detect wastewater volume and collect concentration data of various pollutants in each batch of wastewater; Determine the single pollution concentration data series of various pollutants based on the concentration data of various pollutants in all batches of wastewater; determine the degree of difference between each data and the single pollution concentration data series based on the distribution of data in each single pollution concentration data series; According to the distribution of data in the single pollution concentration data series of all pollutants and the degree of difference between each data and the single pollution concentration data series, determine the average change difference index between various pollutants and all other pollutants in each batch of wastewater; Determine the stable treatment degree of all pollutant concentrations in each batch of wastewater based on the similarities and differences between all pollutant concentrations in each batch of wastewater and those in previous wastewaters; Determine the change index of all pollutants in each batch of wastewater according to the average change difference index and stable treatment degree corresponding to all pollutants in each batch of wastewater; Determine the adjustment of wastewater treatment equipment based on the change index of all pollutants in the current batch of wastewater; The method for determining the single pollution concentration data sequence is: The normalized values ​​of the concentration data of all pollutants in each batch of wastewater are used to form the pollutant concentration sequence of each single batch of wastewater; The concentration matrix is ​​constructed by inserting the single batch wastewater pollutant concentration sequence of each batch of wastewater row by row; Extract the data corresponding to various pollutants from the concentration matrix respectively to form various horizontal sequences, which are recorded as single pollution concentration data sequences of various pollutants; The method for determining the mean change difference index is: Determine the corresponding degree of change between any two pollutants in each batch of wastewater according to the change in concentration data of any two pollutants in all batches of wastewater; Determine the historical change difference between the arbitrary two pollutants in each batch of wastewater according to the difference between the corresponding change degree between the arbitrary two pollutants in each batch of wastewater relative to the corresponding change degree between the arbitrary two pollutants in all batches of wastewater; The mean of the historical change difference between various pollutants in each batch of wastewater and all other pollutants is calculated and recorded as the mean of the comprehensive change degree. The average change difference index between various pollutants and all other pollutants in each batch of wastewater is positively correlated with the mean of the comprehensive change degree of various pollutants in each batch of wastewater and the difference degree corresponding to the concentration data of various pollutants; The method for determining the stability treatment degree is: The mean of each column of data in the concentration matrix is ​​used to form a concentration mean sequence; The difference between the pollutant concentration sequence of each single batch of wastewater and the corresponding position data in the concentration mean sequence is used as the independent variable of the sign function, and the calculation results of the sign function are used to form a comparison sequence of each batch of wastewater; Calculate the distance between the comparison sequence of each batch of wastewater and the comparison sequences of other batches of wastewater, and take the number of times the distance is 0 as the number of occurrences of the comparison sequence of each batch of wastewater; Calculate the sum of all elements in the concentration mean sequence, recorded as the first concentration sum, calculate the sum of all elements in the single batch wastewater pollutant concentration sequence of each batch of wastewater, recorded as the second concentration sum, calculate the product of the range of the concentration mean sequence and the first concentration sum, recorded as the first concentration product, calculate the product of the range of the single batch wastewater pollutant concentration sequence of each batch of wastewater and the corresponding second concentration sum, recorded as the second concentration product, calculate the absolute value of the difference between the second concentration product and the first concentration product of each batch of wastewater, the stable treatment degree of all pollutant concentrations in each batch of wastewater is negatively correlated with the absolute value of the difference of each batch of wastewater, and is positively correlated with the number of occurrences of the comparison sequence of each batch of wastewater; The method for determining the change index is: The average value of the average change difference index corresponding to all pollutants in each batch of wastewater is calculated. The change index of all pollutants in each batch of wastewater is positively correlated with the said average value of each batch of wastewater, and negatively correlated with the stable treatment degree of all pollutant concentrations in each batch of wastewater.

2. The method for intelligently treating wastewater from a thermal power plant based on artificial intelligence according to claim 1, characterized in that: The degree of difference is determined by: Clustering algorithms are used to cluster the data in each single pollution concentration data series; For each single pollution concentration data sequence, the outlier factor of each data in the single pollution concentration data sequence is determined according to the distribution of the data in the single pollution concentration data sequence and the elements in the clusters corresponding to each data in the single pollution concentration data sequence; Calculate the difference in standard deviation between each cluster corresponding to a single pollution concentration data sequence and all elements in the remaining clusters, recorded as the first difference, calculate the difference in the mean of all elements in each cluster corresponding to a single pollution concentration data sequence and all elements in the remaining clusters, recorded as the second difference, calculate the product of the first difference and the second difference, recorded as the difference product, calculate the cumulative sum of all the difference products of each cluster corresponding to the single pollution concentration data sequence, and the degree of difference between each data and the single pollution concentration data sequence is positively correlated with the cumulative sum of the cluster where each data is located and the outlier factor of each data, respectively.

3. The method for intelligent treatment of wastewater from a thermal power plant based on artificial intelligence as claimed in claim 2, characterized in that: The method for determining the outlier factor is: Calculate the absolute value of the difference between each data in the single pollution concentration data sequence and its adjacent previous data and adjacent next data, and record them as the previous difference absolute value and the next difference absolute value; wherein, when the data is located at the first or last position in the single pollution concentration data sequence, the corresponding previous difference absolute value or the next difference absolute value is set to 0; The number of elements with the same value as each data in the cluster where each data is located is counted, and the sum of the absolute value of the previous difference and the absolute value of the latter difference is calculated. The outlier factor of each data is positively correlated with the sum corresponding to each data and the number of elements in the cluster where each data is located, and is negatively correlated with the number corresponding to each data.

4. The method for intelligent treatment of wastewater from a thermal power plant based on artificial intelligence according to claim 1, characterized in that: The method for determining the corresponding degree of change is: Calculate the mean and standard deviation of all data in the single pollution concentration data sequence of the arbitrary two pollutants, recorded as the concentration mean and concentration standard deviation, respectively calculate the difference between the normalized value of the concentration data of the arbitrary two pollutants in each batch of wastewater and the corresponding concentration mean, recorded as the concentration change difference, calculate the product of the concentration change differences of the arbitrary two pollutants in each batch of wastewater, recorded as the first concentration change product; calculate the product of the concentration standard deviations of the arbitrary two pollutants, recorded as the second concentration change product; in each batch of wastewater, the corresponding change degree between the arbitrary two pollutants is positively correlated with the absolute value of the first concentration change product corresponding to each batch of wastewater, and negatively correlated with the second concentration change product.

5. The method for intelligent treatment of wastewater from a thermal power plant based on artificial intelligence according to claim 1, characterized in that: The method for determining the historical change difference is: Calculate the mean of the corresponding change degrees between any two pollutants in all batches of wastewater, record it as the mean change degree, and take the absolute value of the difference between the corresponding change degree between any two pollutants in each batch of wastewater and the mean change degree as the historical change difference between the any two pollutants in each batch of wastewater.

6. The method for intelligent treatment of wastewater from a thermal power plant based on artificial intelligence according to claim 1, characterized in that: The process of judging the adjustment of the wastewater treatment equipment according to the change index of the pollutants in the current batch of wastewater is as follows: Calculate the change index of all pollutants in the current batch of wastewater. If the change index value is less than or equal to the preset change index threshold, do not adjust the wastewater treatment equipment; otherwise, adjust the wastewater treatment equipment; When adjusting the wastewater treatment equipment, the discharge volume of the current batch of wastewater, the degree of difference corresponding to each pollutant in the wastewater, and the average change difference index corresponding to each pollutant are used as inputs of the neural network, and the output of the neural network is the dosage of the agent corresponding to each pollutant.

Images