Water quality monitoring method and system based on drainage pipe network

Abstract

The invention relates to a water quality monitoring method and system based on a drainage pipe network, and belongs to the technical field of water quality monitoring. The method comprises the following steps: collecting water quality data through a sensor, obtaining a sensor number, obtaining time sequence water quality data by adding a timestamp according to the water quality data, and storing the time sequence water quality data according to the sensor number to obtain a water quality data sequence; calculating to obtain a preprocessed water quality data sequence through a preprocessing model according to the water quality data sequence, and calculating to obtain a prediction result through a prediction model according to the preprocessed water quality data sequence; and according to the prediction result, an early warning grade is calculated through an early warning grade model, and the intelligent terminal transmits the early warning grade to the human-computer interaction interface. Water quality prediction of the drainage pipe network is realized, and early warning of water quality of the high-pollution-level drainage pipe network can be carried out in time.

Description

Technical Field

[0001] The present invention belongs to the technical field of water quality monitoring, and in particular relates to a water quality monitoring method and system based on a drainage network. Background Art

[0002] Water quality monitoring of drainage networks is an important part of ensuring urban water environment quality and public health. With the acceleration of urbanization, traditional drainage network monitoring methods have been unable to meet the needs of modern cities. Therefore, the research and development of water quality monitoring methods and systems based on drainage networks is particularly important.

[0003] At present, the means of monitoring the water quality of the drainage network is to install various sensors at key locations of the drainage network to collect relevant data. These data are transmitted to the Internet of Things platform using wireless communication technology to achieve remote monitoring. However, this monitoring method relies on real-time reflection of the data collected by the sensor. Since there will be time delays in the transmission and analysis of the data, some high-risk sewage will be discharged during the data transmission and analysis, which will lead to delays in governance and cause water pollution problems. Summary of the invention

[0004] In order to solve the above problems existing in the prior art, the present invention provides a water quality monitoring method and system based on a drainage network. The purpose of the present invention can be achieved through the following technical solutions: Collect water quality data through a sensor, obtain a sensor number, obtain time series water quality data by adding a timestamp to the water quality data, and store the time series water quality data according to the sensor number to obtain a water quality data sequence; A preprocessed water quality data sequence is obtained by calculating the preprocessing model according to the water quality data sequence, and a prediction result is obtained by calculating the prediction model according to the preprocessed water quality data sequence; The warning level is calculated by the warning level model according to the prediction result, and the intelligent terminal transmits the warning level to the human-computer interaction interface.

[0005] Specifically, the preprocessing model includes: Filling missing values ​​according to the water quality data sequence by linear interpolation to obtain a filled water quality data sequence; Performing horizontal processing on the filled water quality data sequence by the mean smoothing method to obtain a removed water quality data sequence; The pre-processed water quality data sequence is obtained by performing denoising on the eliminated water quality data sequence through a denoising model.

[0006] Specifically, the denoising model is implemented based on improved wavelet analysis, and specifically includes: Obtaining discrete detail coefficients through wavelet decomposition according to the removed water quality data sequence; Preset a filtering threshold rule, and perform threshold quantization processing on the discrete detail coefficient according to the filtering threshold rule to obtain a quantized detail coefficient; The pre-processed water quality data sequence is obtained by performing wavelet reconstruction on the eliminated water quality data sequence according to the quantized detail coefficients.

[0007] Specifically, the prediction model includes: S301: Obtain decomposition components by performing variational mode decomposition according to the preprocessed water quality data sequence; S302: Obtaining each modal influence factor by using a Pearson correlation analysis method according to the decomposed components, and obtaining a feature vector by parallel concatenation according to each modal influence factor; S303: normalizing the feature vector by a minimum-maximum normalization method to obtain normalized data; S304: Calculate the prediction result using a BP neural network according to the normalized data.

[0008] Specifically, the warning level model first calculates the water quality score according to the prediction result, and then calculates the warning level through a classifier according to the water quality score.

[0009] Specifically, water quality data include physical indicators, chemical indicators, and biological indicators.

[0010] Specifically, the physical indicators include water temperature, turbidity, chromaticity, suspended matter content, and transparency; the chemical indicators include pH value, dissolved oxygen, biochemical oxygen demand, chemical oxygen demand, total organic carbon, ion content, nutrient salt content, heavy metal content, oil content, organic matter content, and pesticide residue; the biological indicators include Escherichia coli content and fecal coliform content.

[0011] A water quality monitoring system based on a drainage network, comprising: a data acquisition module, a data prediction module, and a control module; The data acquisition module is used to collect water quality data through a sensor, obtain a sensor number, obtain time series water quality data by adding a timestamp to the water quality data, and store the time series water quality data according to the sensor number to obtain a water quality data sequence; The data prediction module is used to calculate a preprocessed water quality data sequence through a preprocessing model according to the water quality data sequence, and to calculate a prediction result through a prediction model according to the preprocessed water quality data sequence; The control module is used to calculate the warning level through the warning level model according to the prediction result, and the intelligent terminal transmits the warning level to the human-computer interaction interface.

[0012] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the water quality monitoring method based on the drainage network as described above is implemented.

[0013] A storage medium containing computer executable instructions, which are used to execute the water quality monitoring method based on the drainage network as described above when executed by a computer processor.

[0014] The beneficial effects of the present invention are: (1) By setting up a preprocessing model, the data is interpolated for missing values, mean smoothed, and denoised through the preprocessing model, ensuring the accuracy of the data when predicting water quality and improving the accuracy of data prediction.

[0015] (2) By setting up a prediction model, the prediction model is used to predict the pre-processed water quality data sequence to obtain the prediction result, which realizes the prediction of future water quality data based on historical data, and solves the time delay caused by the real-time data collection, transmission and calculation of the sensor, which leads to the discharge of polluted water sources.

[0016] (3) By setting up an early warning level model, the prediction results are classified into different levels through the early warning level model, thus making the prediction results intuitive. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0018] Figure 1 The present invention is a flow chart of a water quality monitoring method based on a drainage network. DETAILED DESCRIPTION

[0019] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0020] See also Figure 1 , a water quality monitoring method based on drainage network, Collect water quality data through a sensor, obtain a sensor number, obtain time series water quality data by adding a timestamp to the water quality data, and store the time series water quality data according to the sensor number to obtain a water quality data sequence; A preprocessed water quality data sequence is obtained by calculating the preprocessing model according to the water quality data sequence, and a prediction result is obtained by calculating the prediction model according to the preprocessed water quality data sequence; The warning level is calculated by the warning level model according to the prediction result, and the intelligent terminal transmits the warning level to the human-computer interaction interface.

[0021] Specifically, the preprocessing model includes: Filling missing values ​​according to the water quality data sequence by linear interpolation to obtain a filled water quality data sequence; The linear interpolation calculation formula is: , in, x k+i is the missing value, x k is the water quality data at the kth moment, x k+j is the water quality data at the k+jth moment, i and j is a variable parameter; Performing horizontal processing on the filled water quality data sequence by the mean smoothing method to obtain a removed water quality data sequence; The mean smoothing method calculation formula is: , in x k is the water quality data at time k, x k-1 is the water quality data at time k-1, x k+1 is the water quality data at time k+1, i 1 , i 2 is the adjacent data error threshold; The pre-processed water quality data sequence is obtained by performing denoising on the eliminated water quality data sequence through a denoising model.

[0022] Specifically, the denoising model is implemented based on improved wavelet analysis, and specifically includes: Obtaining discrete detail coefficients through wavelet decomposition according to the removed water quality data sequence; Preset a filtering threshold rule, and perform threshold quantization processing on the discrete detail coefficient according to the filtering threshold rule to obtain a quantized detail coefficient; It should be noted that the threshold quantization is a commonly used technology in data compression and model optimization, which maps continuous numerical data to a limited numerical range. Threshold quantization includes but is not limited to MinMax quantization, KLD quantization, and ADMM quantization.

[0023] The pre-processed water quality data sequence is obtained by performing wavelet reconstruction on the eliminated water quality data sequence according to the quantized detail coefficients.

[0024] Specifically, the prediction model includes: S301: Obtain decomposition components by performing variational mode decomposition according to the preprocessed water quality data sequence; S302: Obtaining each modal influence factor by using a Pearson correlation analysis method according to the decomposed components, and obtaining a feature vector by parallel concatenation according to each modal influence factor; The Pearson correlation analysis method calculation formula is: , in, r X，Y is the Pearson correlation coefficient, COV (X,Y) is the covariance of X and Y, X is the decomposed component, Y is the water quality index sequence, σx is the standard deviation of the decomposition component, and σx is the standard deviation of the water quality index sequence.

[0025] S303: normalizing the feature vector by a minimum-maximum normalization method to obtain normalized data; S304: Calculate the prediction result using a BP neural network according to the normalized data.

[0026] In this embodiment, the BP neural network includes an input layer, an output layer, and six hidden layers. The design of the BP neural network with such a structure can improve the accuracy of calculation while increasing the calculation speed, and respond to water pollution in a timely manner.

[0027] Specifically, the warning level model includes calculating a water quality score according to the prediction result, and calculating the warning level through a classifier according to the water quality score. The water quality score calculation formula is: , in, Y Score the water quality. i is a variable parameter, n is the number of water quality data indicators, a is the weight value, X For the prediction results.

[0028] Specifically, the water quality data includes physical indicators, chemical indicators, and biological indicators.

[0029] Specifically, the physical indicators include water temperature, turbidity, chromaticity, suspended matter content, and transparency; the chemical indicators include pH value, dissolved oxygen, biochemical oxygen demand, chemical oxygen demand, total organic carbon, ion content, nutrient salt content, heavy metal content, oil content, organic matter content, and pesticide residue; the biological indicators include Escherichia coli content and fecal coliform content.

[0030] In this embodiment, the sensor is a KNF-500 multi-parameter water quality sensor. The KNF-500 multi-parameter water quality sensor can be used to collect water quality data and provide comprehensive water quality analysis.

[0031] A water quality monitoring system based on a drainage network, comprising: a data acquisition module, a data prediction module, and a control module; The data acquisition module is used to collect water quality data through a sensor, obtain a sensor number, obtain time series water quality data by adding a timestamp to the water quality data, and store the time series water quality data according to the sensor number to obtain a water quality data sequence; The data prediction module is used to calculate a preprocessed water quality data sequence through a preprocessing model according to the water quality data sequence, and to calculate a prediction result through a prediction model according to the preprocessed water quality data sequence; The control module is used to calculate the warning level through the warning level model according to the prediction result, and the intelligent terminal transmits the warning level to the human-computer interaction interface.

[0032] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the water quality monitoring method based on the drainage network as described above is implemented.

[0033] A storage medium containing computer executable instructions, which are used to execute the water quality monitoring method based on the drainage network as described above when executed by a computer processor.

[0034] The computer storage medium of the embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device.

[0035] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0036] The program code contained on the computer-readable medium can be transmitted with any appropriate medium, including but not limited to wireless, wire, optical cable, RF, etc., or any suitable combination of the above. The computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or a combination thereof, and the programming language includes an object-oriented programming language-such as Java, Smalltalk, C++, and also includes a conventional procedural programming language-such as "C" language or similar programming language. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0037] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A water quality monitoring method based on a drainage network, characterized in that: include: Collect water quality data through a sensor, obtain a sensor number, obtain time series water quality data by adding a timestamp to the water quality data, and store the time series water quality data according to the sensor number to obtain a water quality data sequence; A preprocessed water quality data sequence is obtained by calculating the preprocessing model according to the water quality data sequence, and a prediction result is obtained by calculating the prediction model according to the preprocessed water quality data sequence; The warning level is calculated by the warning level model according to the prediction result, and the intelligent terminal transmits the warning level to the human-computer interaction interface.

2. The water quality monitoring method based on the drainage network according to claim 1 is characterized in that: The preprocessing model includes: Filling missing values ​​according to the water quality data sequence by linear interpolation to obtain a filled water quality data sequence; According to the padded water quality data sequence, horizontal processing is performed by the mean smoothing method to obtain a removed water quality data sequence; The pre-processed water quality data sequence is obtained by performing denoising on the eliminated water quality data sequence through a denoising model.

3. The water quality monitoring method based on the drainage network according to claim 2 is characterized in that: The noise reduction model is implemented based on improved wavelet analysis, and specifically includes: Obtaining discrete detail coefficients through wavelet decomposition according to the removed water quality data sequence; Preset a filtering threshold rule, and perform threshold quantization processing on the discrete detail coefficient according to the filtering threshold rule to obtain a quantized detail coefficient; The pre-processed water quality data sequence is obtained by performing wavelet reconstruction on the eliminated water quality data sequence according to the quantized detail coefficients.

4. The water quality monitoring method based on the drainage network according to claim 1 is characterized in that: The prediction model includes: Decomposing the pre-processed water quality data sequence by variational mode decomposition to obtain decomposition components; Obtaining each modal influence factor by using a Pearson correlation analysis method according to the decomposed components, and obtaining a feature vector by parallel concatenation according to each modal influence factor; Normalizing the feature vector by a minimum-maximum normalization method to obtain normalized data; The prediction result is obtained by calculating through a BP neural network according to the normalized data.

5. The water quality monitoring method based on the drainage network according to claim 1 is characterized in that: The warning level model first calculates the water quality score according to the prediction result, and then calculates the warning level through a classifier according to the water quality score.

6. The water quality monitoring method based on the drainage network according to claim 1 is characterized in that: The water quality data include physical indicators, chemical indicators, and biological indicators.

7. The water quality monitoring method based on the drainage network according to claim 6 is characterized in that: The physical indicators include water temperature, turbidity, chromaticity, suspended matter content, and transparency; the chemical indicators include pH value, dissolved oxygen, biochemical oxygen demand, chemical oxygen demand, total organic carbon, ion content, nutrient salt content, heavy metal content, oil content, organic matter content, and pesticide residue; the biological indicators include Escherichia coli content and fecal coliform content.

8. A water quality monitoring system based on a drainage network, characterized in that: include: Data acquisition module, data prediction module, control module; The data acquisition module is used to collect water quality data through a sensor, obtain a sensor number, obtain time series water quality data by adding a timestamp to the water quality data, and store the time series water quality data according to the sensor number to obtain a water quality data sequence; The data prediction module is used to calculate a preprocessed water quality data sequence through a preprocessing model according to the water quality data sequence, and to calculate a prediction result through a prediction model according to the preprocessed water quality data sequence; The control module is used to calculate the warning level through the warning level model according to the prediction result, and the intelligent terminal transmits the warning level to the human-computer interaction interface.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the water quality monitoring method based on the drainage network as described in any one of claims 1-7 is implemented.

10. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions are used to execute the water quality monitoring method based on the drainage network as described in any one of claims 1 to 7 when executed by a computer processor.

Images