Water quality safety monitoring management method and system based on big data

Abstract

The invention relates to the technical field of water quality safety monitoring, and discloses a water quality safety monitoring management method and system based on big data, and the key points of the technical scheme are as follows: whether continuously flowing pollutants exist in a pipe is judged according to the pollutant concentration; judging whether the pipeline nodes have continuously flowing pollutants or not; judging whether the reservoir has continuously flowing pollutants or not; when flowing pollutants are detected in any step, a polynomial regression model is adopted to predict the concentration of mud and algae; correcting the response of the fluorescence sensor according to the estimated concentrations of the algae and the mud, and judging whether the reservoir contains coliform bacteria or not; a large amount of data information is collected from a reservoir through an over-conductivity sensor, and whether continuously flowing pollutants exist in a pipe or not is judged; and a polynomial regression model is adopted to predict the concentration of mud and algae. The response of the fluorescence sensor is corrected according to the concentration of the mud and algae, and whether the coliform is contained in the reservoir or not is judged.

Description

Technical Field

[0001] The present invention relates to the technical field of water quality safety monitoring, and more specifically, to a water quality safety monitoring management method and system based on big data. Background Art

[0002] Most cities need to get water from reservoirs every day. In reservoirs and pipelines, water may be contaminated by pollutants in different ways. For example, long-term accumulation will cause mud to settle; insufficient filtration will cause algae to grow. Therefore, the water quality safety monitoring system in the prior art usually monitors mud and algae to ensure water quality safety.

[0003] However, reservoirs in some areas may be contaminated by bacteria, such as heat-resistant coliform bacteria. When the concentration of mud and algae is high, it may mask the bacterial contamination and make it impossible to monitor the water quality safely.

[0004] Therefore, the present invention provides a water quality safety monitoring and management method and system based on big data, which improves the above-mentioned technical problems. Summary of the invention

[0005] The disclosed embodiments aim to address the deficiencies of the prior art and provide a water quality safety monitoring management method and system based on big data. The present invention uses a conductivity sensor to collect a large amount of data information from the reservoir to determine whether there are continuously flowing pollutants in the pipe, whether there are continuously flowing pollutants at the pipeline node, and whether there are continuously flowing pollutants in the reservoir; when flowing pollutants are detected in any of them, a polynomial regression model is used to predict the concentration of mud and algae. The response of the fluorescent sensor is corrected according to the estimated concentration of mud and algae to determine whether there are coliform bacteria in the reservoir.

[0006] The above technical purpose of the present invention is achieved through the following technical solutions: A water quality safety monitoring and management method based on big data, comprising the following steps: S1, detecting the pollutant concentration in the pipeline range by a conductivity sensor, and judging whether there are continuously flowing pollutants in the pipe according to the pollutant concentration;

[0007] S2, determine whether there is a continuous flow of pollutants at the pipeline node;

[0008] S3. Determine whether there are continuously flowing pollutants in the reservoir;

[0009] S4, when flowing pollutants are detected in any step of S1-S3, a polynomial regression model is used to predict the concentration of mud and algae;

[0010] S5. Correcting the response of the fluorescence sensor based on the estimated algae and mud concentrations.

[0011] As a preferred technical solution of the present invention, the calculation formula for determining whether there are continuously flowing pollutants in the pipe is:

[0012]

[0013] Where C is the contaminant concentration in the pipeline, p is the volume flow rate in the pipeline, B is the cross-sectional area of ​​the pipeline, y is the distance of the positive flow pipeline, t is the time, and θ(C) is the pipeline reaction rate.

[0014] As a preferred technical solution of the present invention, when continuously flowing pollutants are detected, the first-order kinetic rate equation is used to calculate the change in the pollutant concentration in the pipeline:

[0015] θ(C)=lC

[0016] Where I is the first-order reaction rate coefficient, C is the total flow rate of the pollutant; when the pollutant increases, the change in the pollutant concentration in the pipeline is a positive number; when the pollutant decreases, the change in the pollutant concentration in the pipeline is a negative number.

[0017] As a preferred technical solution of the present invention, the calculation formula for determining whether there is a continuous flow of pollutants at a pipeline node is:

[0018]

[0019] Among them, C l is the pollutant node I; I is the pipeline node into which the water currently flows.

[0020] As a preferred technical solution of the present invention, the calculation formula for determining whether there are continuous flowing pollutants in the reservoir is:

[0021]

[0022] Among them, C Z and U Z is the reservoir pollution concentration and reservoir volume, C in is the water flow in the input pipe, θ′(C Z ) is the reaction rate in the reservoir.

[0023] As a preferred technical solution of the present invention, the basic features of S are expanded by including a deviation term and introducing a polynomial combination of a characteristic degree ≤ 2 related to the spectrophotometer response in S; the final feature vector is obtained

[0024] v∈R d , (d=12);

[0025] The expression of the eigenvector is:

[0026] It consists of the components of S, the square of each component in S, and the intermediate product between every two components; the polynomial regression coefficients are estimated using the ordinary least squares (OLS) method with L2 regularization;

[0027] Next, the concentrations of algae and mud are expressed as c a and c m as two target variables, so the coefficients of the two polynomial regression models are stacked into a matrix A∈R d×2 Columns; complete the estimation of algae and mud concentrations:

[0028] The concentrations of algae and mud are estimated using the formula:

[0029] in, represents the estimated regression coefficients for the two models independently; and are the estimated concentrations of algae and mud, respectively.

[0030] As a preferred technical solution of the present invention, according to the estimated and To correct it, it is expressed as r fl The response of the fluorescence sensor;

[0031] The concentration of L-tryptophan is estimated by the formula:

[0032]

[0033] Among them, the linear regression model The regression coefficient β 0-3 The estimation is done using the OLS method with L2 regularization.

[0034] As a preferred technical solution of the present invention, the system is used to implement a water quality safety monitoring and management method based on big data as described in any one of claims 1 to 7, and the system includes: a conductivity sensor, a turbidity meter, a spectrophotometer, and a fluorescence sensor;

[0035] The conductivity sensor is used to detect pollution concentration, and when the amount of dissolved solids in water increases, the conductivity of the conductivity sensor increases;

[0036] The turbidity meter is used to detect suspended particles and is composed of a light source and a light detector placed perpendicular to each other;

[0037] The spectrophotometer is used to detect dissolved minerals;

[0038] The fluorescent sensor is used to detect heat-resistant coliform bacteria.

[0039] In summary, the present invention has the following beneficial effects: a large amount of data information is collected from the reservoir through the conductivity sensor to determine whether there are continuously flowing pollutants in the pipe, whether there are continuously flowing pollutants at the pipeline node, and whether there are continuously flowing pollutants in the reservoir; when flowing pollutants are detected in any of them, a polynomial regression model is used to predict the concentration of mud and algae.

[0040] According to the fluorometer fl L-Tryptophan c TLF 、Algae a and mud m The responses of different concentration combinations; and the c a and c m The ratio of the selected c under different combinations TLF The actual value of r and the observed water sample fl , through the linear regression model Determine the correction factor for fluorometer measurements. Use the estimation matrix Obtain estimated concentrations of algae and mud

[0041] According to the estimated and To correct it, it is expressed as r fl The response of the fluorescent sensor is used to determine whether the reservoir contains coliform bacteria. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A flow chart of a water quality safety monitoring and management method based on big data provided by an embodiment of the present invention;

[0043] Figure 2 The spectrophotometer responses to the mean and extreme values ​​of algae and mud concentrations at all possible values ​​of L-tryptophan concentration are provided for embodiments of the present invention.

[0044] Figure 3 The Pearson correlation coefficient between the spectrophotometer absorbance and the L-tryptophan concentration at different wavelengths provided in the embodiment of the present invention. DETAILED DESCRIPTION

[0045] The present application is described in detail below in conjunction with specific embodiments. The following embodiments will help those skilled in the art to further understand the present application, but do not limit the present application in any form. It should be noted that, for those of ordinary skill in the art, several variations and improvements can also be made without departing from the concept of the present application. These all belong to the protection scope of the present application.

[0046] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0047] It should be noted that, if there is no conflict, the various features in the embodiments of the present application can be combined with each other, all within the scope of protection of the present application. In addition, although the functional module division is performed in the device schematic diagram and the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in a sequence different from the module division in the device or the flow chart. In addition, the words "first", "second", "third", etc. used herein do not limit the data and execution order, but only distinguish the same items or similar items with basically the same functions and effects.

[0048] Unless otherwise defined, all technical and scientific terms used in this specification have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used in this specification and in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The term "and / or" used in this specification includes any and all combinations of one or more of the related listed items.

[0049] In addition, the technical features involved in each embodiment of the present application described below can be combined with each other as long as they do not conflict with each other.

[0050] The water quality safety monitoring and management system based on big data described in the embodiment of the present disclosure is composed of the following:

[0051] Conductivity sensors are used to detect pollution concentrations; an increase in dissolved solids in water will increase conductivity.

[0052] Turbidimeter, used to detect suspended particles, consists of a light source and a light detector placed perpendicular to each other.

[0053] Spectrophotometer, used to detect dissolved minerals; the prior art generally uses a multi-spectral chipset as a miniature discrete wavelength spectrophotometer.

[0054] Fluorescent sensor for the detection of thermotolerant coliform bacteria.

[0055] Please refer to Figure 1 , Figure 1 The flowchart of the embodiment of the present disclosure for implementing a water quality safety monitoring and management system based on big data is shown, and the overall steps are as follows:

[0056] Step 1: Use a conductivity sensor to detect the pollutant concentration in the pipeline, and determine whether there is continuous flow of pollutants in the pipe based on the pollutant concentration.

[0057] The calculation formula for determining whether there is continuous flow of contaminants in the pipe is:

[0058]

[0059] Where C is the contaminant concentration in the pipeline, p is the volume flow rate in the pipeline, B is the cross-sectional area of ​​the pipeline, y is the distance of the positive flow pipeline, t is the time, and θ(C) is the pipeline reaction rate.

[0060] When detecting a continuous flow of pollutants, the first-order kinetic rate equation is used to calculate the change in pollutant concentration in the pipeline:

[0061] θ(C)=lC

[0062] Where I is the first-order reaction rate coefficient and C is the total flow rate of the pollutant. When the pollutant increases, the change in the pollutant concentration in the pipeline is a positive number; when the pollutant decreases, the change in the pollutant concentration in the pipeline is a negative number.

[0063] Step 2: Determine whether there is continuous flow of pollutants at the pipeline node.

[0064] The calculation formula to determine whether there is continuous flow of pollutants at a pipeline node is:

[0065]

[0066] Among them, C l is the pollutant node I; I is the pipeline node into which the water currently flows.

[0067] Step 3: Determine whether the reservoir has a continuous flow of pollutants.

[0068] The calculation formula for determining whether there are continuous flowing pollutants in the reservoir is:

[0069]

[0070] Among them, C Z and U Z is the reservoir pollution concentration and reservoir volume, C in is the water flow in the input pipe, θ′(C Z ) is the reaction rate in the reservoir.

[0071] Step 4: When flowing pollutants are detected in any of steps 1-3, a polynomial regression model is used to predict the concentration of mud and algae;

[0072] Examples, such as Figure 2As shown, water samples were taken from 560cm, 680cm and 810cm in the reservoir respectively; Figure 2 It can be seen that the concentrations of mud and algae show an opposite correlation, which makes it easy to distinguish the appearance of mud and algae. Let the vector be s∈R k , (k = 5); the basic feature set in the vector includes: the water sample absorption values ​​(s 560 ,s 680 ,s 810 ,), and turbidity meters NF and conductivity sensors CS .

[0073] The expression of the vector is: s = [s 560 ,s 680 ,s 810 ,s NF ,s CS ] T ;

[0074] The basic features of S are extended by including a bias term and introducing a polynomial combination of feature degree ≤ 2 related to the spectrophotometer response in S; the final feature vector v∈R d , (d=12);

[0075] The expression of the eigenvector is:

[0076] It consists of the components of S, the square of each component in S, and the intermediate product between every two components. The polynomial regression coefficients are estimated using the ordinary least squares (OLS) method with L2 regularization.

[0077] Next, the concentrations of algae and mud are expressed as c a and c m As two target variables, the coefficients of the two polynomial regression models are stacked into a matrix R∈R d×2 Columns; complete the estimation of algae and mud concentrations:

[0078] The concentrations of algae and mud are estimated using the formula:

[0079] in, represents the estimated regression coefficients for the two models independently; and are the estimated concentrations of algae and mud, respectively.

[0080] Step 5: Based on the estimated and To correct it, it is expressed as r flThe response of the fluorescent sensor is used to determine whether the reservoir contains coliform bacteria.

[0081] like Figure 3 As shown, the selected concentration range of L-tryptophan in the sample water is [0, 30 ppb], which includes the critical concentration value of 6.9 ppb, above which water pollution is classified as highly critical (equivalent to > 1 CFU / ml). The concentrations of algae and mud are selected in the following ranges, respectively [0, 200 kj / ml] and [0, 100 mg / l].

[0082] The concentration of L-tryptophan is estimated by the formula:

[0083]

[0084] Among them, the linear regression model The regression coefficient β 0-3 The estimation is done using the OLS method with L2 regularization.

[0085] A large amount of data information is collected from the reservoir through conductivity sensors, and then the feature sets at each depth in the reservoir are cross-validated by collecting water samples, estimating polynomial regression coefficients and stacking them into a matrix The standard deviation of the estimated coefficients does not exceed 0.02. According to the average absolute values ​​of the estimated coefficients obtained after cross-validation, the responses of the conductivity sensor and the turbidity meter have the greatest impact on the estimation of algae and mud concentrations. In addition to the response of the conductivity sensor, the estimation of algae concentration is most affected by the absorbance value of the water sample at 680 cm by the spectrophotometer, that is, the feature s created. 680 2 and 680 .

[0086] According to the fluorometer fl L-Tryptophan c TLF 、Algae a and mud m The responses of different concentration combinations; and the c a and c m The ratio of the selected c under different combinations TLF The actual value of r and the observed water sample fl , through the linear regression model Determine the correction factor for fluorometer measurements. Use the estimation matrix Obtain estimated concentrations of algae and mud Then estimate the regression coefficient β of f 0-3 .

[0087] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A water quality safety monitoring and management method based on big data, characterized in that: The method comprises the following steps: S1. Detect the pollutant concentration in the pipeline range through the conductivity sensor, and determine whether there is a continuous flow of pollutants in the pipe according to the pollutant concentration; S2, determine whether there is a continuous flow of pollutants at the pipeline node; S3. Determine whether there are continuously flowing pollutants in the reservoir; S4, when flowing pollutants are detected in any step of S1-S3, a polynomial regression model is used to predict the concentration of mud and algae; S5. Correct the response of the fluorescence sensor according to the estimated algae and mud concentrations to determine whether the reservoir contains coliform bacteria.

2. A water quality safety monitoring and management method based on big data according to claim 1, characterized in that: The calculation formula for determining whether there is continuous flow of contaminants in the pipe is: Where C is the contaminant concentration in the pipeline, p is the volume flow rate in the pipeline, B is the cross-sectional area of ​​the pipeline, y is the distance of the positive flow pipeline, t is the time, and θ(C) is the pipeline reaction rate.

3. A water quality safety monitoring and management method based on big data according to claim 2, characterized in that: When detecting a continuous flow of pollutants, the first-order kinetic rate equation is used to calculate the change in pollutant concentration in the pipeline: θ(C)=lC Where I is the first-order reaction rate coefficient, C is the total flow rate of the pollutant; when the pollutant increases, the change in the pollutant concentration in the pipeline is a positive number; when the pollutant decreases, the change in the pollutant concentration in the pipeline is a negative number.

4. The water quality safety monitoring and management method based on big data according to claim 1 is characterized in that: The calculation formula to determine whether there is continuous flow of pollutants at the pipeline node is: Among them, C l is the pollutant node I; I is the pipeline node into which the water currently flows.

5. The water quality safety monitoring and management method based on big data according to claim 1 is characterized in that: The calculation formula for determining whether there are continuous flowing pollutants in the reservoir is: Among them, C Z and U Z is the reservoir pollution concentration and reservoir volume, C in is the water flow in the input pipe, θ′(C Z ) is the reaction rate in the reservoir.

6. The water quality safety monitoring and management method based on big data according to claim 1 is characterized in that: The basic features of S are extended by including a bias term and introducing a polynomial combination of feature degree ≤ 2 related to the spectrophotometer response in S; the final feature vector v∈R d , (d=12); The expression of the eigenvector is: It consists of the components of S, the square of each component in S, and the intermediate product between every two components; the polynomial regression coefficients are estimated using the ordinary least squares (OLS) method with L2 regularization; Next, the concentrations of algae and mud are expressed as c a and c m As two target variables, the coefficients of the two polynomial regression models are stacked into a matrix A∈R d×2 Columns; complete the estimation of algae and mud concentrations: The concentrations of algae and mud are estimated using the formula: in, represents the estimated regression coefficients for the two models independently; and are the estimated concentrations of algae and mud, respectively.

7. The water quality safety monitoring and management method based on big data according to claim 1 is characterized in that: According to the estimated and To correct it, it is expressed as r fl The response of the fluorescence sensor; The concentration of L-tryptophan is estimated by the formula: Among them, the linear regression model The regression coefficient β 0-3 The estimation is done using the OLS method with L2 regularization.

8. A water quality safety monitoring and management system based on big data, characterized in that: The system is used to implement a water quality safety monitoring and management method based on big data as described in any one of claims 1 to 7, and the system comprises: a conductivity sensor, a turbidity meter, a spectrophotometer, and a fluorescence sensor; The conductivity sensor is used to detect pollution concentration, and when the amount of dissolved solids in water increases, the conductivity of the conductivity sensor increases; The turbidity meter is used to detect suspended particles and is composed of a light source and a light detector placed perpendicular to each other; The spectrophotometer is used to detect dissolved minerals; The fluorescent sensor is used to detect heat-resistant coliform bacteria.

Images