A sewage treatment intelligent monitoring system and method based on big data

Abstract

The invention discloses an intelligent monitoring system and method for sewage treatment based on big data, comprising a data acquisition module, a sample acquisition module, a detection module, a data screening module, a database module, a data processing module and a data output module; the sample acquisition module is used for analyzing sewage pool parameter information and historical detection data to determine sample collection points; the detection module is used for detecting samples to be detected; the data screening module is used for screening indicator data according to real-time data information; the invention obtains historical detection data of each detection indicator in sewage, analyzes the state and concentration degree of the longitudinal distribution of each detection indicator in the sewage pool, and judges the distribution state and distribution characteristics of each detection indicator in the sewage pool; when sampling, sampling is carried out in a targeted manner according to the characteristics of each detection indicator to avoid the blindness of random sampling, so as to obtain representative sample data, thereby improving the accuracy and reliability of the system monitoring.

Description

Technical Field

[0001] The present invention relates to the field of sewage treatment, and in particular to a sewage treatment intelligent monitoring system and method based on big data. Background Art

[0002] The sewage treatment process takes a long time, and there are many important on-site parameters and information (such as sewage flow, liquid level, pH value, temperature, dissolved oxygen concentration, etc.) that need to be monitored in real time by the monitoring system; the process of the monitoring system obtaining data requires sampling and testing of the sewage, and judging the sewage status based on the test results; however, the current sampling method is basically based on the experience of the staff and random sampling; however, different parameters have different characteristics, and the randomly obtained samples are poorly representative and difficult to reflect the true status of the sewage pool, which in turn affects the accuracy of the monitoring system. To solve this problem, an intelligent sewage treatment monitoring system and method based on big data is proposed. Summary of the invention

[0003] The technical problem to be solved by the present invention is: how to solve the problem that the existing safety protection system has a single protection type, resulting in poor protection effect and bringing certain impacts on the use of the safety protection system. A sewage treatment intelligent monitoring system and method based on big data is provided.

[0004] The present invention solves the above technical problems through the following technical solutions, and the present invention includes a data acquisition module, a sample acquisition module, a detection module, a data screening module, a database module, a data processing module, and a data output module;

[0005] The data acquisition module is used to collect real-time data information of the sewage pool;

[0006] The database module is used to store historical test data, sewage pool parameter information and standard indicator information;

[0007] The sample collection module is used to receive and analyze the sewage pool parameter information and historical detection data to determine the sample collection point, and collect the samples to be tested in the sewage pool;

[0008] The detection module is used to detect the samples to be detected and obtain the index data of the samples to be detected;

[0009] The data screening module is used to receive indicator data and screen the indicator data according to real-time data information to obtain valid indicator data;

[0010] The data processing module is used to receive indicator data, standard indicator information and historical detection data, and issue a monitoring report based on the analysis of the standard indicator information and historical detection data;

[0011] The data output module is used to receive and output monitoring reports.

[0012] Preferably, the sewage pool parameter information data includes the sewage pool profile information data, and the specific processing process of the sample collection module is:

[0013] Import the contour information data of the sewage pool to obtain the contour position of the sewage pool;

[0014] Draw parallel lines from the contour line La in the sewage pool liquid surface to obtain multiple contour parallel lines, and the multiple contour parallel lines enclose a closed interval A1;

[0015] Get the geometric center point a of the closed interval A1;

[0016] Draw a vertical line L through point a, and make a cylinder A2 with the vertical line L as the axis and the preset size Re as the radius;

[0017] Import historical test data of different test indicators at different test depths;

[0018] The first rule is used to determine the correlation r between the detection values ​​Y of the plurality of detection marks and the depth D;

[0019] The first rule is:

[0020] A set of historical test data is randomly retrieved to obtain multiple indicator test values ​​of the same test indicator, which are Y1, Y2, Y3, ..., Yn;

[0021] The detection depths for obtaining multiple index values ​​are D1, D2, D3, ..., Dn;

[0022] Calculate the correlation r. The specific calculation process is:

[0023]

[0024] in, is the average value of multiple indicator detection values, The average depth of detection for multiple indicator values;

[0025] Calculate the correlation r between multiple detection indicators and depth respectively;

[0026] When |r|≥0.5, the detection index is first marked, and the slope K of the regression line of the index is calculated. The calculation process of the slope K is:

[0027]

[0028] Calculate the average value of the detection index of multiple first markers

[0029] Divide the cylinder A2 longitudinally into X sub-cylinders, and let the height of each sub-cylinder be Dx;

[0030] make Get Dx;

[0031] A plurality of detection points are randomly selected in the plurality of sub-cylinders as first detection points, and samples to be detected are collected.

[0032] Preferably, when |r|<0.5, the processing of the sample collection module further includes:

[0033] Performing a second marking on the detection index;

[0034] Retrieve a set of historical detection data, derive the detection depth De of the same second mark detection indicator, and the detection depths of multiple second mark detection indicators are respectively: De1, De2, De3, ..., Den;

[0035] Get the average value of the detection depth of multiple detection indicators

[0036] Calculate the discrete degree S of the detection depth of multiple second mark detection indicators. The specific calculation process is:

[0037]

[0038] When the discrete degree S is less than the preset threshold Q1, the detection depth A horizontal detection area A3 is established, and multiple detection points are randomly selected as second detection points, and samples to be detected are collected.

[0039] Preferably, the calculation process of the discrete degree S also includes:

[0040] Obtain multiple detection depths of multiple same second mark detection indicators, namely: De1, De2, De3, ..., Den;

[0041] When importing the average value of multiple detection depths

[0042] Calculate the deviation Sr of each second mark detection index respectively, and the specific calculation process is:

[0043]

[0044] When the deviation Sr>preset threshold Q2, the indicator is eliminated and the detection depth of the horizontal detection area A3 is recalculated and determined.

[0045] Preferably, the real-time data information includes the real-time flow rate data of each detection point, and the specific processing process of the data screening module is:

[0046] Obtain the index data of the xth detection index in each sub-cylinder, which are B1, B2, B3, ..., Bn;

[0047] Calculate the dispersion degree θ1 of each indicator value. The specific calculation process is:

[0048]

[0049] in, is the average value of the indicator data of the xth indicator;

[0050] Get the real-time flow rate of the xth indicator at different detection points, which are V1, V2, V3, ..., Vn;

[0051] Calculate the dispersion degree θ2 of the liquid flow velocity at different detection points. The specific collection and dispersion process is:

[0052]

[0053] in, is the average value of liquid flow velocity at different detection points;

[0054] When θ1≤preset threshold Q3 and θ2≤preset threshold Q4, the indicator data is valid;

[0055] When θ1>preset threshold Q3 and θ2>preset threshold Q4, the indicator data is deleted;

[0056] When θ1>preset threshold Q3 and θ2≤preset threshold Q4, an instruction for resampling the detection point is generated.

[0057] Preferably, when the detection indicator is the first marking indicator, the processing process of the data screening module further includes:

[0058] Collect the index data of the xth index in the sub-cylinder at adjacent depths, which are C1, C2, C3, ..., Cn;

[0059] Calculate the average value of each indicator

[0060] Calculate the difference degree θ3 of adjacent index values. The specific calculation process is:

[0061]

[0062] When the difference degree θ3>preset threshold Q5, an instruction for resampling the detection point is generated.

[0063] Preferably, the specific processing process of the data processing module is:

[0064] Import standard indicator information and obtain the standard value H1 of each indicator data;

[0065] Import the index value of the detection index, and set the index value of each Nth detection index to be H2;

[0066] When the index value H2>the standard value H1, a monitoring report is generated.

[0067] Preferably, the system further comprises a control module, a warning module and an execution module, wherein the control module is used to classify monitoring reports, the warning module is used to generate warning actions, the execution module is used to execute sewage treatment actions, the monitoring report comprises a warning report and an execution report, and the processing process of the data processing module further comprises:

[0068] When the index value H2> the standard value H1, an execution report is generated and sent to the execution module;

[0069] Import historical test data to obtain different indicator data and test time;

[0070] Assume that the historical index value of the Xth detection index is U1, and the detection time is T1;

[0071] Read the indicator data of the detection indicator, set the indicator value to U2, and the detection time to T2;

[0072] Calculate the increase J of the index value of the detection index. The specific calculation process is:

[0073] J = (U2-U1) / (T2-T1)

[0074] When the increase J> the preset threshold Q6, a warning report is generated and sent to the warning module.

[0075] A method for intelligent monitoring of sewage treatment based on big data, comprising the following steps:

[0076] Collect real-time data information of sewage pool;

[0077] Receive and analyze sewage pool parameter information and historical test data to determine sample collection points, and collect samples to be tested in the sewage pool;

[0078] Testing the samples to be tested and obtaining index data of the samples to be tested;

[0079] Receive indicator data and filter the indicator data according to real-time data information to obtain valid indicator data;

[0080] Receive indicator data, standard indicator information and historical test data, and issue monitoring reports based on the analysis of standard indicator information and historical test data;

[0081] Receive and output monitoring reports.

[0082] Compared with the prior art, the present invention has the following advantages: the monitoring system obtains historical detection data of each detection index in sewage, analyzes the longitudinal distribution state and concentration degree of each detection index in the sewage pool, and determines the distribution state and distribution characteristics of each detection index in the sewage pool; when sampling, targeted sampling is carried out according to the characteristics of each detection index to avoid the blindness of random sampling, so as to obtain representative sample data, thereby improving the accuracy and reliability of the system monitoring, making the system more worthy of popularization and use. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] Figure 1 It is the overall module diagram of the present invention. DETAILED DESCRIPTION

[0084] The following is a detailed description of an embodiment of the present invention. This embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation method and a specific operation process are given, but the protection scope of the present invention is not limited to the following embodiment.

[0085] like Figure 1 As shown, this embodiment provides a technical solution: a sewage treatment intelligent monitoring system and method based on big data, including a data acquisition module, a sample acquisition module, a detection module, a data screening module, a database module, a data processing module, and a data output module;

[0086] The data acquisition module is used to collect real-time data information of the sewage pool;

[0087] The database module is used to store historical test data, sewage pool parameter information and standard indicator information;

[0088] It should be noted that the standard indicator data is the reference value for the data to meet the preset standards when managing each indicator.

[0089] The sample collection module is used to receive and analyze the sewage pool parameter information and historical detection data to determine the sample collection point, and collect the samples to be tested in the sewage pool;

[0090] The detection module is used to detect the samples to be detected and obtain the index data of the samples to be detected;

[0091] The data screening module is used to receive indicator data and screen the indicator data according to real-time data information to obtain valid indicator data;

[0092] The data processing module is used to receive indicator data, standard indicator information and historical detection data, and issue a monitoring report based on the analysis of the standard indicator information and historical detection data;

[0093] The data output module is used to receive and output monitoring reports.

[0094] The monitoring system obtains the historical detection data of each detection index in the sewage, analyzes the longitudinal distribution status and concentration of each detection index in the sewage pool, and determines the distribution status and distribution characteristics of each detection index in the sewage pool; when sampling, targeted sampling is carried out according to the characteristics of each detection index to avoid the blindness of random sampling, so as to obtain representative sample data, thereby improving the accuracy and reliability of the system monitoring.

[0095] Among them, the sewage pool parameter information data includes the contour information data of the sewage pool, and the specific processing process of the sample collection module is:

[0096] Import the contour information data of the sewage pool to obtain the contour position of the sewage pool;

[0097] Draw parallel lines from the contour line La in the sewage pool liquid surface to obtain multiple contour parallel lines, and the multiple contour parallel lines enclose a closed interval A1;

[0098] Get the geometric center point a of the closed interval A1;

[0099] Draw a vertical line L through point a, and make a cylinder A2 with the vertical line L as the axis and the preset size Re as the radius;

[0100] Import historical test data of different test indicators at different test depths;

[0101] The first rule is used to determine the correlation r between the detection values ​​Y of the plurality of detection marks and the depth D;

[0102] The first rule is:

[0103] A set of historical test data is randomly retrieved to obtain multiple indicator test values ​​of the same test indicator, which are Y1, Y2, Y3, ..., Yn;

[0104] The detection depths for obtaining multiple index values ​​are D1, D2, D3, ..., Dn;

[0105] Calculate the correlation r. The specific calculation process is:

[0106]

[0107] in, is the average value of multiple indicator detection values, The average depth of detection for multiple indicator values;

[0108] Calculate the correlation r between multiple detection indicators and depth respectively;

[0109] When |r|≥0.5, the detection index is first marked, and the slope K of the regression line of the index is calculated. The calculation process of the slope K is:

[0110]

[0111] Calculate the average value of the detection index of multiple first markers

[0112] Divide the cylinder A2 longitudinally into X sub-cylinders, and let the height of each sub-cylinder be Dx;

[0113] make Get Dx;

[0114] A plurality of detection points are randomly selected in the plurality of sub-cylinders as first detection points, and samples to be detected are collected.

[0115] In this technical solution, the correlation between the index value of the detection index and the depth is first calculated to determine the distribution status of the detection index in the sewage pool; then the slopes of the regression lines between the index values ​​of different detection indicators and the depth are calculated respectively, and finally the average slope is used to limit the gradient depth value in the depth direction during sampling to avoid a large difference in index values ​​due to excessive depth during sampling, which makes it difficult to fully reflect the true situation of each indicator in the sewage pool; at the same time, it also avoids subtle differences in index values ​​due to excessive depth, which reduces the detection efficiency of the imaging system.

[0116] Furthermore, when |r|<0.5, the processing of the sample collection module further includes:

[0117] Performing a second marking on the detection index;

[0118] Retrieve a set of historical detection data, derive the detection depth De of the same second mark detection indicator, and the detection depths of multiple second mark detection indicators are respectively: De1, De2, De3, ..., Den;

[0119] Get the average value of the detection depth of multiple detection indicators

[0120] Calculate the discrete degree S of the detection depth of multiple second mark detection indicators. The specific calculation process is:

[0121]

[0122] When the discrete degree S is less than the preset threshold Q1, the detection depth A horizontal detection area A3 is established, and multiple detection points are randomly selected as second detection points, and samples to be detected are collected.

[0123] In this technical solution, the average value of the detection index is calculated first, and then the degree of dispersion of each detection index is calculated. When the degree of dispersion is small, it indicates that the detection index is mainly distributed in an area at a certain depth. At this time, horizontal sampling is performed at this depth. Sampling is performed according to the characteristics of the detection index. This can improve the accuracy of the sampling data of the index and improve the monitoring accuracy of the system.

[0124] It should be noted that some data has nothing to do with depth, and this data can be obtained through random sampling. Therefore, sampling following the first mark detection indicator or the second mark detection indicator has no effect on the result.

[0125] Furthermore, the calculation process of the discrete degree S also includes:

[0126] Obtain multiple detection depths of multiple same second mark detection indicators, namely: De1, De2, De3, ..., Den;

[0127] When importing the average value of multiple detection depths

[0128] Calculate the deviation Sr of each second mark detection index respectively, and the specific calculation process is:

[0129]

[0130] When the deviation Sr>preset threshold Q2, the indicator is eliminated and the detection depth of the horizontal detection area A3 is recalculated and determined.

[0131] There are a small number of data with relatively scattered distribution areas. When determining the detection depth of the horizontal detection area A3, they are eliminated, which can improve the representativeness of the overall sampling of the indicator and improve the overall accuracy of the indicator.

[0132] Since sewage flow data has a certain influence on each detection index, when the above scheme is used for depth gradient sampling, the index difference of the detection index has abnormal values ​​due to the excessive or insufficient liquid flow rate in the sewage pool inlet, outlet and internal structure. The abnormal value cannot reflect the overall level of the index in the area and affects the accuracy of the sample. When the difference in some of the detection data is large, it is necessary to determine whether the index data is abnormal, so the following technical schemes are eliminated:

[0133] Real-time data information includes real-time flow rate data of each detection point. The specific processing process of the data screening module is as follows:

[0134] Obtain the index data of the xth detection index in each sub-cylinder, which are B1, B2, B3, ..., Bn;

[0135] Calculate the dispersion degree θ1 of each indicator value. The specific calculation process is:

[0136]

[0137] in, is the average value of the indicator data of the xth indicator;

[0138] Get the real-time flow rate of the xth indicator at different detection points, which are V1, V2, V3, ..., Vn;

[0139] Calculate the dispersion degree θ2 of the liquid flow velocity at different detection points. The specific collection and dispersion process is:

[0140]

[0141] in, is the average value of liquid flow velocity at different detection points;

[0142] When θ1≤preset threshold Q3 and θ2≤preset threshold Q4, the indicator data is valid;

[0143] When θ1>preset threshold Q3 and θ2>preset threshold Q4, the indicator data is deleted;

[0144] When θ1>preset threshold Q3 and θ2≤preset threshold Q4, an instruction for resampling the detection point is generated.

[0145] In the present technical solution, the abnormality of the index value is inferred by obtaining the dispersion degree of the index value in the horizontal direction of each detection index and the dispersion degree of the liquid flow velocity. When it is found that the index values ​​of some indicators deviate greatly from the average value, and the flow velocity at the indicator detection point also deviates greatly from the average flow velocity, it is inferred that the position of the detection point is special and the index value is abnormal, so it is deleted; when only the index value is abnormal, re-sampling is performed at the point to detect the index value at that position, and the abnormal position is recorded to ensure the reliability of system monitoring.

[0146] Furthermore, when the detection indicator is the first marking indicator, the processing process of the data screening module also includes:

[0147] Collect the index data of the xth index in the sub-cylinder at adjacent depths, which are C1, C2, C3, ..., Cn;

[0148] Calculate the average value of each indicator

[0149] Calculate the difference degree θ3 of adjacent index values. The specific calculation process is:

[0150]

[0151] When the difference degree θ3>preset threshold Q5, an instruction for resampling the detection point is generated.

[0152] When performing gradient detection on the first marking indicator, when the indicator value at a certain depth is abnormal as a whole, it indicates that there is an abnormality inside the sewage pool. At this time, it is necessary to re-collect samples and confirm the abnormal situation to ensure the authenticity of the system monitoring.

[0153] Among them, the specific processing process of the data processing module is:

[0154] Import standard indicator information and obtain the standard value H1 of each indicator data;

[0155] Import the index value of the detection index, and set the index value of each Nth detection index to be H2;

[0156] When the index value H2>the standard value H1, a monitoring report is generated.

[0157] Furthermore, the system also includes a control module, a warning module, and an execution module. The control module is used to classify the monitoring report, the warning module is used to generate a warning action, and the execution module is used to execute the sewage treatment action. The monitoring report includes a warning report and an execution report. The processing process of the data processing module also includes:

[0158] When the index value H2> the standard value H1, an execution report is generated and sent to the execution module;

[0159] Import historical test data to obtain different indicator data and test time;

[0160] Assume that the historical index value of the Xth detection index is U1, and the detection time is T1;

[0161] Read the indicator data of the detection indicator, set the indicator value to U2, and the detection time to T2;

[0162] Calculate the increase J of the index value of the detection index. The specific calculation process is:

[0163] J = (U2-U1) / (T2-T1)

[0164] When the increase J> the preset threshold Q6, a warning report is generated and sent to the warning module.

[0165] The system determines abnormal situations of indicators by calculating the increase of detection indicators. When the indicator value is within the normal range but the increase of the indicator is abnormal, a warning report is prepared to remind staff to pay timely attention.

[0166] It should be noted that the average value calculation method in the present invention is the arithmetic mean, which is the existing technology and will not be described in detail.

[0167] A method for intelligent monitoring of sewage treatment based on big data, comprising the following steps:

[0168] Collect real-time data information of sewage pool;

[0169] Receive and analyze sewage pool parameter information and historical test data to determine sample collection points, and collect samples to be tested in the sewage pool;

[0170] Testing the samples to be tested and obtaining index data of the samples to be tested;

[0171] Receive indicator data and filter the indicator data according to real-time data information to obtain valid indicator data;

[0172] Receive indicator data, standard indicator information and historical test data, and issue monitoring reports based on the analysis of standard indicator information and historical test data;

[0173] Receive and output monitoring reports.

[0174] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0175] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0176] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A sewage treatment intelligent monitoring system based on big data, characterized in that: It includes data acquisition module, sample acquisition module, detection module, data screening module, database module, data processing module and data output module; The data acquisition module is used to collect real-time data information of the sewage pool; The database module is used to store historical test data, sewage pool parameter information and standard indicator information; The sample collection module is used to receive and analyze the sewage pool parameter information and historical detection data to determine the sample collection point, and collect the samples to be tested in the sewage pool; The detection module is used to detect the samples to be detected and obtain the index data of the samples to be detected; The data screening module is used to receive indicator data and screen the indicator data according to real-time data information to obtain valid indicator data; The data processing module is used to receive indicator data, standard indicator information and historical detection data, and issue a monitoring report based on the analysis of the standard indicator information and historical detection data; The data output module is used to receive and output monitoring reports; The sewage pool parameter information data includes the sewage pool contour information data. The specific processing process of the sample collection module is as follows: Import the contour information data of the sewage pool to obtain the contour position of the sewage pool; Draw parallel lines from the contour line La in the sewage pool liquid surface to obtain multiple contour parallel lines, and the multiple contour parallel lines enclose a closed interval A1; Get the geometric center point a of the closed interval A1; Draw a vertical line L through point a, and make a cylinder A2 with the vertical line L as the axis and the preset size Re as the radius; Import historical test data of different test indicators at different test depths; The first rule is used to determine the correlation r between the detection values ​​Y of the plurality of detection marks and the depth D; The first rule is: A set of historical test data is randomly retrieved to obtain multiple indicator test values ​​of the same test indicator, which are Y1, Y2, Y3, ..., Yn; The detection depths for obtaining multiple index values ​​are D1, D2, D3, ..., Dn; Calculate the correlation r. The specific calculation process is: in, is the average value of multiple indicator detection values, The average depth of detection for multiple indicator values; Calculate the correlation r between multiple detection indicators and depth respectively; When |r|≥0.5, the detection index is first marked, and the slope K of the regression line of the index is calculated. The calculation process of the slope K is: Calculate the average value of the detection index of multiple first markers Divide the cylinder A2 longitudinally into X sub-cylinders, and let the height of each sub-cylinder be Dx; make Get Dx; A plurality of detection points are randomly selected in the plurality of sub-cylinders as first detection points, and samples to be detected are collected.

2. According to claim 1, a sewage treatment intelligent monitoring system based on big data is characterized in that: When |r|<0.5, the processing process of the sample collection module also includes: Performing a second marking on the detection index; Retrieve a set of historical detection data, derive the detection depth De of the same second mark detection indicator, and the detection depths of multiple second mark detection indicators are respectively: De1, De2, De3, ..., Den; Get the average value of the detection depth of multiple detection indicators Calculate the discrete degree S of the detection depth of multiple second mark detection indicators. The specific calculation process is: When the discrete degree S is less than the preset threshold Q1, the detection depth A horizontal detection area A3 is established, and multiple detection points are randomly selected as second detection points, and samples to be detected are collected.

3. The intelligent monitoring system for sewage treatment based on big data according to claim 2 is characterized by: The calculation process of the discrete degree S also includes: Obtain multiple detection depths of multiple same second mark detection indicators, namely: De1, De2, De3, ..., Den; When importing the average value of multiple detection depths Calculate the deviation Sr of each second mark detection index respectively, and the specific calculation process is: When the deviation Sr>preset threshold Q2, the indicator is eliminated and the detection depth of the horizontal detection area A3 is recalculated and determined.

4. The intelligent monitoring system for sewage treatment based on big data according to claim 1 or 2 is characterized in that: Real-time data information includes real-time flow rate data of each detection point. The specific processing process of the data screening module is as follows: Obtain the index data of the xth detection index in each sub-cylinder, which are B1, B2, B3, ..., Bn; Calculate the dispersion degree θ1 of each indicator value. The specific calculation process is: in, is the average value of the indicator data of the xth indicator; Get the real-time flow rate of the xth indicator at different detection points, which are V1, V2, V3, ..., Vn; Calculate the dispersion degree θ2 of the liquid flow velocity at different detection points. The specific collection and dispersion process is: in, is the average value of liquid flow velocity at different detection points; When θ1≤preset threshold Q3 and θ2≤preset threshold Q4, the indicator data is valid; When θ1>preset threshold Q3 and θ2>preset threshold Q4, the indicator data is deleted; When θ1>preset threshold Q3 and θ2≤preset threshold Q4, an instruction for resampling the detection point is generated.

5. The intelligent monitoring system for sewage treatment based on big data according to claim 4 is characterized by: When the detection indicator is the first marking indicator, the processing process of the data screening module further includes: Collect the index data of the xth index in the sub-cylinder at adjacent depths, which are C1, C2, C3, ..., Cn; Calculate the average value of each indicator Calculate the difference degree θ3 of adjacent index values. The specific calculation process is: When the difference degree θ3>preset threshold Q5, an instruction for resampling the detection point is generated.

6. The intelligent monitoring system for sewage treatment based on big data according to claim 1 is characterized by: The specific processing process of the data processing module is as follows: Import standard indicator information and obtain the standard value H1 of each indicator data; Import the index value of the detection index, and set the index value of each Nth detection index to be H2; When the index value H2>the standard value H1, a monitoring report is generated.

7. The intelligent monitoring system for sewage treatment based on big data according to claim 6 is characterized by: It also includes a control module, an alarm module, and an execution module. The control module is used to classify monitoring reports, the alarm module is used to generate alarm actions, and the execution module is used to execute sewage treatment actions. The monitoring report includes an alarm report and an execution report. The processing process of the data processing module also includes: When the index value H2> the standard value H1, an execution report is generated and sent to the execution module; Import historical test data to obtain different indicator data and test time; Assume that the historical index value of the Xth detection index is U1, and the detection time is T1; Read the indicator data of the detection indicator, set the indicator value to U2, and the detection time to T2; Calculate the increase J of the index value of the detection index. The specific calculation process is: J = (U2-U1) / (T2-T1) When the increase J> the preset threshold Q6, a warning report is generated and sent to the warning module.

8. A method for intelligent monitoring of sewage treatment based on big data, characterized in that: A sewage treatment intelligent monitoring system based on big data according to any one of claims 1 to 7 is used, comprising the following steps: Collect real-time data information of sewage pool; Receive and analyze sewage pool parameter information and historical test data to determine sample collection points, and collect samples to be tested in the sewage pool; Testing the samples to be tested and obtaining index data of the samples to be tested; Receive indicator data and filter the indicator data according to real-time data information to obtain valid indicator data; Receive indicator data, standard indicator information and historical test data, and issue monitoring reports based on the analysis of standard indicator information and historical test data; Receive and output monitoring reports.

Images