Intelligent monitoring method and system for water quality pollution

Abstract

The invention relates to the technical field of water quality pollution monitoring, in particular to an intelligent water quality pollution monitoring method and system.The method comprises the steps that low-concentration pollutants are screened by collecting water body information, the low-concentration pollutants are enriched, low-concentration pollution groups are obtained, photoelectric composite configuration is set according to the low-concentration pollution groups, and the photoelectric composite configuration is set according to the low-concentration pollution groups; and acquiring an output photoelectric signal according to the photoelectric composite configuration, amplifying the output photoelectric signal, acquiring target electrochemical characteristics, identifying the target electrochemical characteristics by establishing a pollution characteristic database, and outputting low-concentration pollution monitoring information. According to the invention, the problem of insufficient sensitivity of a traditional water quality pollution monitoring method in a low-concentration pollutant detection process is effectively solved, efficient screening and accurate identification of the low-concentration pollutants in the water quality monitoring process are realized, monitoring errors and omission of the traditional method are reduced to the greatest extent, and the detection accuracy of the low-concentration pollutants in the water quality monitoring process is improved. And the real-time performance and the accuracy of monitoring are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of water pollution monitoring, and particularly to an intelligent water pollution monitoring method and system. Background Art

[0002] With the acceleration of the industrialization process and the growth of the global population, water resource pollution has become one of the major environmental problems faced globally. In the fields of environmental protection and water resource management, the detection of low-concentration pollutants has always been a technical challenge. Low-concentration pollutants, especially those chemical substances at trace or ultra-trace levels, such as heavy metals, pesticide residues, and drug residues, pose a great potential threat to human health and the ecological environment. However, due to their extremely low concentrations, conventional water quality monitoring methods often cannot achieve the required detection sensitivity or require complex and time-consuming pretreatment steps to conduct effective detection.

[0003] Traditional low-concentration pollutant detection technologies usually require complex sample pretreatment, expensive instruments, and professional operations, which not only increase the detection cost but also prolong the analysis time. In addition, these methods often lack sufficient sensitivity to detect extremely low-concentration pollutants.

[0004] The information disclosed in this background art section is only intended to deepen the understanding of the overall background art of the present disclosure and should not be regarded as an admission or any form of implication that this information constitutes the prior art known to those skilled in the art. Summary of the Invention

[0005] The present invention provides an intelligent water pollution monitoring method and system, which can effectively solve the problems in the background art.

[0006] In order to achieve the above object, the technical solution adopted by the present invention is: An intelligent water pollution monitoring method, the method comprising: Collecting water body information, screening low-concentration pollutants according to the water body information, and enriching the low-concentration pollutants to obtain a low-concentration pollution mass, where the enrichment is used to increase the concentration of the low-concentration pollution; Setting an optoelectronic composite configuration according to the low-concentration pollution mass, and obtaining an output optoelectronic signal, amplifying the output optoelectronic signal to obtain a target optoelectrochemical characteristic; Establishing a pollution characteristic database, and identifying the target optoelectrochemical characteristic according to the pollution characteristic database to output low-concentration pollution monitoring information.

[0007] Further, collecting water body information includes: Obtaining a plurality of historical water body sampling points, and obtaining a plurality of initial water body sampling schemes, where the initial water body sampling scheme includes a plurality of water body sampling points; According to a number of the initial water sampling schemes, the water area to be sampled is divided into river basins according to water velocity and flow direction, and a number of water body partitions are obtained, with each of the water body partitions corresponding to the water velocity and flow direction respectively; An optimization algorithm is used to adaptively screen the initial water sampling schemes to obtain a sampling execution scheme; Water quality detection sensors are arranged according to the sampling execution scheme, and water body information is obtained according to the water quality detection sensors.

[0008] Further, using an optimization algorithm to adaptively screen a number of the initial water sampling schemes includes: Construct a pollution assessment function according to water pollution assessment criteria; S1: Analyze a number of the initial water sampling schemes respectively according to the pollution assessment function, screen the schemes according to the actual performance, and obtain a number of first-generation sampling schemes; S2: Exchange the water sampling points of the corresponding water body partitions for a number of the first-generation sampling schemes to obtain second-generation sampling schemes; S3: Re-select sampling points for any one of the water body partitions of a number of the second-generation sampling schemes, and use the re-selected scheme as the new initial sampling scheme; Set an iteration threshold according to historical optimization experience, and perform iteration according to steps S1, S2, and S3 until the number of iterations reaches the iteration threshold, and output the sampling execution scheme.

[0009] Further, set an optoelectronic composite configuration according to the low-concentration pollution mass and obtain an output optoelectronic signal, including: Set electrodes according to the low-concentration pollution mass, immerse the electrodes in the water body to be measured containing the low-concentration pollution mass, apply an alternating current signal to the water body to be measured, and obtain an electrochemical response; Use electrochemical analysis software to analyze the electrochemical response to obtain a preliminary electrochemical signal; Irradiate the water body to be measured with an external laser source, collect the scattered light of the irradiated water body to be measured, and use spectral analysis software to obtain the molecular vibration signal of the low-concentration pollution mass; Integrate the preliminary electrochemical signal and the molecular vibration signal to identify the optoelectronic signal of the low-concentration pollution mass.

[0010] Further, amplify the output optoelectronic signal to obtain target optoelectrochemical characteristics, including: Perform preliminary amplification on the output optoelectronic signal to obtain a pre-amplified signal; Use a filtering algorithm to denoise the pre-amplified signal, and adjust the amplification factor by monitoring the amplitude of the electrochemical response, and obtain a target electrochemical signal; Convert the target electrochemical signal into a digital data format to obtain target electrochemical features.

[0011] Further, establish a pollution feature database, including: Collect historical low-concentration pollution information and extract historical low-concentration pollution features; Use a multi-dimensional feature extraction algorithm to reduce the dimension of the historical low-concentration pollution features to obtain the main historical low-concentration pollution features; Construct a multi-dimensional pollution matrix based on the main historical low-concentration pollution features, where the rows of the matrix represent low-concentration pollution types and the columns of the matrix represent electrochemical features; Further, using a multi-dimensional feature extraction algorithm to reduce the dimension of the historical low-concentration pollution features includes: Standardize the historical low-concentration pollution features, calculate the correlation of several standardized historical low-concentration pollution features to obtain a feature correlation matrix, and the feature correlation matrix is used to represent the correlation between several low-concentration pollution types and electrochemical features; Calculate the eigenvalues and the eigenvectors corresponding to the eigenvalues according to the feature correlation matrix, and serialize the eigenvalues; Set a cumulative feature contribution threshold according to the historical low-concentration pollution features, calculate the feature contribution rates of several eigenvalues respectively, and screen several eigenvalues according to the cumulative feature contribution threshold to obtain the main historical low-concentration pollution features.

[0012] Further, enrich the low-concentration pollutants to obtain a low-concentration pollution mass, including: Make an adsorption bag with an adsorption material and place the adsorption bag according to the sampling execution plan; Set an adsorption period according to the historical low-concentration pollution information, and monitor the adsorption bag in real time according to the adsorption period to obtain adsorbed pollutants; Elute the adsorbed pollutants to obtain a low-concentration pollution mass.

[0013] An intelligent water pollution monitoring system, the system includes: A pollution enrichment collection module that collects water body information, screens low-concentration pollutants according to the water body information, and enriches the low-concentration pollutants to obtain a low-concentration pollution mass, and the enrichment is used to increase the concentration of low-concentration pollution; A signal extraction and amplification module that sets an optoelectronic composite configuration according to the low-concentration pollution mass, obtains an output optoelectronic signal, and amplifies the output optoelectronic signal to obtain target optoelectrochemical features; A pollution feature comparison module that establishes a pollution feature database, identifies the target electrochemical features according to the pollution feature database, and outputs low-concentration pollution monitoring information.

[0014] Furthermore, the signal extraction and amplification module includes: An electrochemical response acquisition unit, which sets electrodes according to the low-concentration pollution mass, immerses the electrodes into the water body to be measured containing the low-concentration pollution mass, applies an alternating current signal to the water body to be measured, and acquires an electrochemical response; An electrochemical analysis unit, which analyzes the electrochemical response using electrochemical analysis software to obtain a preliminary electrochemical signal; A laser scattering analysis unit, which irradiates the water body to be measured with an external laser source, collects the scattered light irradiating the water body to be measured, and acquires the molecular vibration signal of the low-concentration pollution mass using spectral analysis software; A signal fusion and recognition unit, which comprehensively combines the preliminary electrochemical signal and the molecular vibration signal to identify the output optoelectronic signal of the low-concentration pollution mass.

[0015] Through the technical solution of the present invention, the following technical effects can be achieved: It effectively solves the problem of insufficient sensitivity in the detection of low-concentration pollutants in traditional water quality pollution monitoring methods, realizes the efficient screening and accurate identification of low-concentration pollutants in the water quality monitoring process, minimizes the monitoring errors and omissions of traditional methods to the greatest extent, and improves the real-time performance and accuracy of monitoring.

[0016] The above description is only an overview of the technical solution of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the following specifically illustrates the specific embodiments of this application. Description of the Drawings

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or in the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0018] Figure 1 It is a schematic flow chart of the intelligent water quality pollution monitoring method; Figure 2 It is a schematic flow chart of the water body collection process; Figure 3 It is a flow chart of the adaptive screening of the sampling plan; Figure 4 It is a schematic flow chart of the acquisition of the output optoelectronic signal; Figure 5 It is a schematic diagram of the output optoelectronic signal acquisition system. Detailed Embodiments

[0019] Next, in combination with the accompanying drawings in the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this invention belongs. The terms used in the specification of this invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0021] Embodiment 1 As Figure 1 shown, the present application provides an intelligent monitoring method for water pollution, and the method includes: S100: Collect water body information, screen out low-concentration pollutants according to the water body information, and enrich the low-concentration pollutants to obtain low-concentration pollution clusters. Enrichment is used to increase the concentration of low-concentration pollution; S200: Set up an optoelectronic composite configuration according to the low-concentration pollution cluster, obtain the output optoelectronic signal, amplify the output optoelectronic signal, and obtain the target optoelectrochemical characteristics; S300: Establish a pollution characteristics database, identify the target optoelectrochemical characteristics according to the pollution characteristics database, and output low-concentration pollution monitoring information.

[0022] Specifically, first, install a water quality detection sensor in the target water area to collect water body information, including but not limited to the pH value, dissolved oxygen, conductivity, turbidity, and temperature of the water, etc. Then, through the data processing unit, the collected water body information is preliminarily screened to screen out areas where low-concentration organic pollutants or low-concentration heavy metal pollutants may exist. Low-concentration organic pollutants include but are not limited to industrial chemicals, organic solvents, pesticide residues, etc., and heavy metal pollutants include lead, mercury, cadmium, etc. After the screening stage of low-concentration organic pollutants or low-concentration heavy metal pollutants, enrichment technologies, such as adsorption materials or other enrichment technologies, are used to increase the concentration of organic or heavy metal pollutants, capture and aggregate low-concentration organic or heavy metal pollutants to form pollution clusters. The concentration of the pollution clusters is higher than that of the original water sample, which is beneficial to subsequent high-sensitivity detection. After obtaining the low-concentration pollution clusters, by setting up an optoelectronic composite configuration, the output optoelectronic signal is obtained, and through amplification processing of the output optoelectronic signal, high-precision target optoelectrochemical characteristics are obtained. Establish a pollution characteristics database, and by comparing with the pollutant characteristics in the database, low-concentration organic or heavy metal pollutants can be accurately identified, and the pollution information of the water body can be output in real time.

[0023] Through the technical solution of the present invention, the problem of insufficient sensitivity in the detection of low-concentration pollutants in the traditional water quality pollution monitoring method is effectively solved, the efficient screening and accurate identification of low-concentration pollutants in the water quality monitoring process are realized, the monitoring errors and omissions of the traditional method are minimized to the greatest extent, and the real-time performance and accuracy of the monitoring are improved.

[0024] Furthermore, as Figure 2 shown, collect water body information, including: S110: Obtain a number of historical water body sampling points, and obtain a number of initial water body sampling schemes, where the initial water body sampling scheme includes a number of water body sampling points; S120: Divide the collected water area into basins according to the water body flow velocity and direction according to a number of initial water body sampling schemes, and obtain a number of water body partitions, each of which corresponds to the water body flow velocity and direction respectively; S130: Use an optimization algorithm to adaptively screen the initial water body sampling scheme to obtain a sampling execution scheme; S140: Arrange water quality detection sensors according to the sampling execution scheme, and obtain water body information according to the water quality detection sensors.

[0025] As a preference of the above embodiments, before implementation, in some embodiments, several representative historical water body sampling points are selected through historical water quality monitoring data and water body flow models. These sampling points should cover the characteristic areas of different water areas to ensure the comprehensiveness and diversity of monitoring. According to the historical sampling point data, an initial water body sampling plan is designed. This plan includes several sampling points. According to the sampling points in the initial water body sampling plan, first, the flow velocity and direction of the water area in the sampling area are measured. In at least one embodiment, a water flow velocity meter and a flow direction instrument are used for measurement to obtain the speed, direction, and change law of the water flow. On this basis, a groundwater system is used as an embodiment. According to some embodiments, the groundwater system is divided into several sub-regions by using a watershed division algorithm. The division basis for each sub-region includes the flow velocity and direction of the water flow. For example, in areas with relatively fast groundwater flow velocities, such as fault zones or fracture zones, they can be used as independent groundwater sub-regions; while in areas with relatively slow groundwater flow velocities, such as deep aquifers or groundwater retention areas, they can be used as another independent sub-region. Each water body sub-region will be defined according to the changes in flow velocity and direction to ensure the comprehensive coverage of the water area. To improve the accuracy and adaptability of the sampling plan, an optimization algorithm, such as a genetic algorithm, a particle swarm algorithm, etc., is used to adaptively screen the initial water body sampling plan. The selection of sampling points can be screened according to the following factors: whether the distribution between sampling points is uniform, avoiding being too concentrated or too scattered; whether the water quality characteristics that each sampling point can represent are sufficient to ensure that the sampling points can cover different pollution sources in the water area, etc. According to the sampling execution plan, the layout positions of water quality detection sensors are selected. According to the information obtained by the sensors, the water quality detection sensors can also be called water quality monitoring detection devices, which are devices that measure various parameters (such as pH value, dissolved oxygen, conductivity, etc.) in the water body through physical or chemical methods. In some embodiments, the water quality detection sensors can be connected to a collection unit or a real-time monitoring system to obtain water body information in real time.

[0026] Furthermore, as Figure 3 shown, using an optimization algorithm to adaptively screen several initial water body sampling plans includes: Constructing a pollution assessment function according to the water body pollution assessment standard; S1: Analyze several initial water body sampling plans respectively according to the pollution assessment function, screen the plans according to the actual performance, and obtain several first-generation sampling plans; S2: Exchange the water body sampling points of the corresponding water body sub-regions for several first-generation sampling plans to obtain second-generation sampling plans; S3: Re-select sampling points for any water body sub-region of several second-generation sampling plans respectively, and use the re-selected plans as new initial sampling plans; Set the iteration threshold according to historical optimization experience, and perform iterations according to steps S1, S2, and S3 until the number of iterations reaches the iteration threshold, and output the sampling execution plan.

[0027] In this embodiment, the groundwater system is used as an example for water body assessment. First, collect the water body pollution assessment criteria. In some embodiments, based on factors such as the concentration, type of organic or heavy metal pollutants in the water body, and the mobility of the groundwater body, the assessment criteria can be set according to key parameters such as the concentration of pesticides, solvents, industrial chemicals, and heavy metal ions in the water body. Then, construct a pollution assessment function according to the water body pollution assessment criteria. The pollution assessment function performs weighted calculations by combining key water quality parameters in the water body to evaluate the overall pollution degree of the water body. Then, through the set pollution standards and weights, the score output by the function can be used to screen and optimize the sampling plan. In some embodiments, the function evaluates the quality of the sampling plan in the following way: input various water quality parameters of the water body and the location of the sampling points, and score according to the pollution assessment criteria. A sampling plan with a higher score output by the function indicates that the sampling point can better represent the pollution situation of the water body; then, screen the plan through the performance results output by the pollution assessment function. The screening method is as follows: first, obtain a generation of sampling plans through the pollution assessment function. The generation of sampling plans is a plan with better performance initially screened according to the pollution assessment function. Then, group any two of the several generation of sampling plans, select the same water body partition at will, and select the sampling points corresponding to the water flow velocity or water flow direction of the water body for exchange. After the exchange, obtain several groups of new plans, called the second-generation sampling plans. Re-select the sampling points corresponding to the water flow direction or water flow velocity of any water body partition of the several second-generation sampling plans, and the re-selected sampling points do not include the initial sampling points, to obtain a brand-new sampling plan. Re-initialize these plans as the initial sampling plan and perform screening, exchange, and re-selection again, and set this iteration threshold according to historical optimization experience. In each round of iteration, continue the sampling point exchange and re-selection process based on the optimization results of the previous round to gradually improve the accuracy of the sampling plan and output the final sampling execution plan, which will be used for the actual water quality monitoring sampling plan.

[0028] Furthermore, as Figure 4 and 5 shown, set up an optoelectronic composite configuration according to the low-concentration pollution mass and obtain the output optoelectronic signal, including: S210: Set up electrodes according to the low-concentration pollution mass, immerse the electrodes in the water body to be measured containing the low-concentration pollution mass, apply an alternating current signal to the water body to be measured, and obtain an electrochemical response; S220: Use electrochemical analysis software to analyze the electrochemical response to obtain a preliminary electrochemical signal; S230: Irradiate the water body to be measured with an external laser source, collect the scattered light of the irradiated water body to be measured, and use spectral analysis software to obtain the molecular vibration signal of the low-concentration pollution mass; S240: Synthesize the preliminary electrochemical signal and the molecular vibration signal to identify the output optoelectronic signal of the low-concentration pollution mass.

[0029] Specifically, the configuration of the electrodes mainly includes three categories: the working electrode, the reference electrode, and the counter electrode. The working electrode is the electrode that is in direct contact with the water body to be measured, responsible for transmitting current or potential changes and conducting electrochemical reactions. In at least one embodiment, conductive materials such as platinum, gold, and carbon are used. The reference electrode provides a stable potential reference for comparing the potential difference with the working electrode, and silver / silver chloride electrode (Ag / AgCl) and saturated calomel electrode (SCE) are used. The counter electrode is used to close the circuit, allow current to flow, and complete the electrochemical reaction. By immersing the configured electrodes into the water body to be measured containing low-concentration pollution clusters and applying an alternating current signal to the water body to be measured, in some embodiments, the frequency range is set from 1 Hz to 10 kHz to stimulate the pollution clusters to generate electrochemical responses. The obtained electrochemical response data is input into electrochemical analysis software, such as ZView and EC-Lab, and the Nyquist plot is used to display the complex impedance data. According to the semicircular characteristics, bending degree, and straight-line part of the Nyquist plot, combined with the amplitude plot and phase plot of the Bode plot, the preliminary electrochemical characteristics are analyzed. The preliminary electrochemical signals can be used to judge the types and concentration ranges of low-concentration organic pollutants or heavy metal pollutants in the water body, providing reference data for subsequent spectral analysis. Subsequently, an external laser source is used to irradiate the water body to be measured. The laser wavelength is usually selected as ultraviolet light or visible light. Lasers of these wavelengths have sufficient energy to excite the molecules of organic pollution clusters or heavy metal pollution clusters in the water body, causing them to vibrate or rotate. The vibration spectral signal can provide information about the molecular characteristics of the pollution clusters. In the water body, organic pollutants (such as pesticides, solvents, and industrial chemicals) will interact with the laser beam, absorb the laser energy, and undergo molecular vibrations. The phenomenon of light scattering will occur accordingly, generating characteristic scattered light. For heavy metal pollutants, heavy metal pollutants often form complexes or coordination compounds with organic molecules, inorganic ions, or ligands in the water through their ionic states. Under the irradiation of external lasers, these complexes or coordination compounds will undergo molecular vibrations or energy transfer processes. Although the spectral characteristics of these metal ions themselves may not be as obvious as those of organic pollutants, through interaction with other components in the water, heavy metal pollutants may still cause the generation of certain characteristic scattered light. The intensity and frequency changes of the scattered light are closely related to the molecular vibration states of organic pollution clusters or heavy metal pollution clusters. Optical fibers or lens systems can be used to collect the scattered light, and the collected scattered light is transmitted to a spectrometer, which can perform spectral analysis. Raman spectroscopy analysis technology can be used to obtain the molecular vibration signals of organic pollution clusters or heavy metal pollution clusters. By analyzing the characteristic peaks in the spectrum, the molecular structure and type of the pollution clusters can be determined. The molecular vibration signal can provide more accurate information about the pollution clusters. Subsequently, the electrochemical signal and the molecular vibration signal are comprehensively analyzed, and through data fusion technologies, such as weighted average and principal component analysis, the optoelectronic signal of the low-concentration pollution clusters is obtained, which can more accurately identify the concentration and types of pollutants in the water body.

[0030] Furthermore, amplify the output optoelectronic signal to obtain the target optoelectrochemical characteristics, including: Preliminarily amplify the output optoelectronic signal to obtain a pre-amplified signal; Use a filtering algorithm to denoise the pre-amplified signal, and adjust the amplification factor by monitoring the amplitude of the electrochemical response to obtain the target electrochemical signal; Convert the target electrochemical signal into a digital data format to obtain the target optoelectrochemical characteristics.

[0031] As a preference of the above embodiment, input the weak electrochemical signal measured by the electrochemical response into a high-gain amplification circuit. This circuit design uses an operational amplifier or a low-noise amplifier to provide sufficient gain to amplify the weak electrochemical signal so that the amplitude of the signal reaches a level suitable for further analysis. And amplify the optical signal obtained by scattering through an optical amplifier. The optical amplifier can also be called an optical signal intensifier, which is a device that amplifies the optical signal by using a gain medium. Set the amplification gain according to the collected electrochemical signal, optical signal intensity and ambient noise level. It should be noted that too high a gain will lead to distortion and nonlinear failure. The gain is set between 20 and 100 times in some embodiments to obtain a pre-amplified signal. Then use a digital filtering algorithm to process the pre-amplified signal, and adjust the amplification factor in real time by monitoring the signal amplitude. For example, when the signal amplitude is small (such as below 1 mV), the amplification circuit automatically increases the gain (for example, adjusts the amplification factor from 10 times to 100 times). After filtering and amplification factor adjustment, the obtained target electrochemical signal has a high signal-to-noise ratio. Input the target electrochemical signal into an analog-to-digital converter to convert the analog signal into a digital signal. By further processing the digitized target electrochemical signal (such as Fourier transform, principal component analysis, etc.), extract the target optoelectrochemical characteristics, such as the electrochemical reaction rate, impedance characteristics, molecular vibration modes, etc. These characteristics can provide detailed information about the pollution clusters in the water body.

[0032] Furthermore, establish a pollution characteristic database, including: Collect historical low-concentration pollution information and extract historical low-concentration pollution characteristics; Use a multi-dimensional feature extraction algorithm to reduce the dimension of the historical low-concentration pollution characteristics to obtain the main historical low-concentration pollution characteristics; Construct a multi-dimensional pollution matrix according to the main historical low-concentration pollution characteristics. The rows of the matrix represent the types of low-concentration pollution, and the columns of the matrix represent electrochemical characteristics; Create an index relationship according to the multi-dimensional pollution matrix to create a pollution characteristic database.

[0033] In this embodiment, historical low-concentration pollution data is collected in different underground water body regions through water quality monitoring sensors. The historical low-concentration pollution data is mainly historical low-concentration organic pollution. The monitored water quality parameters include pesticide residues, industrial solvents, plasticizers, etc. Features related to low-concentration organic pollution are extracted from the collected original data. For example, features such as redox potential, current change amplitude, response time, etc. are extracted according to the change patterns of electrochemical signals. These features can help identify the presence and types of low-concentration pollutants in the water body. According to some embodiments, dimensionality reduction algorithms such as principal component analysis (PCA), linear discriminant analysis, etc. are used to perform dimensionality reduction on the extracted historical low-concentration pollution features. The purpose of dimensionality reduction is to remove redundant data and retain the most representative features, making the data structure more concise. After dimensionality reduction, the main features of historical low-concentration pollution are obtained, and the extracted main features are organized into a multi-dimensional pollution matrix. The rows of the matrix represent different types of low-concentration organic pollutants (such as pesticide residues, industrial chemicals, petroleum pollutants, etc.) or heavy metal pollutants (such as heavy metal ions like lead, mercury, cadmium, etc.), and the columns represent the corresponding electrochemical features (such as electrochemical response amplitude, charge transfer impedance, potential, etc.). For the convenience of subsequent query and data retrieval, indexes are set according to the rows and columns of the pollution matrix. The index relationship can be bidirectionally indexed according to the pollutant types and electrochemical features, enabling rapid data access. For example, hash tables can be established for each pollutant type and electrochemical feature to reduce the search time. The pollution matrix and the index relationship are stored in a database together to form a pollution feature database. This database can use a relational database or a NoSQL database for storage.

[0034] Furthermore, a multi-dimensional feature extraction algorithm is used to perform dimensionality reduction on the historical low-concentration pollution features, including: Standardize the historical low-concentration pollution features, calculate the correlation of a number of standardized historical low-concentration pollution features to obtain a feature correlation matrix, and the feature correlation matrix is used to represent the correlation degree between a number of low-concentration pollution types and electrochemical features; Calculate the eigenvalues and the eigenvectors corresponding to the eigenvalues based on the feature correlation matrix, and serialize the eigenvalues; Set a cumulative feature contribution threshold according to the historical low-concentration pollution features, calculate the feature contribution rates of a number of eigenvalues respectively, and screen a number of eigenvalues according to the cumulative feature contribution threshold to obtain the main features of historical low-concentration pollution.

[0035] Specifically, the characteristics of historical low-concentration pollution mainly include the characteristics of historical low-concentration organic pollution. First, standardize the extracted historical low-concentration pollution characteristics. The standardization method can use Z-score standardization, that is, subtract the mean from each characteristic value and divide by the standard deviation. The standardized data will be used for subsequent correlation calculation and dimensionality reduction processing. Conduct a correlation analysis on the standardized characteristic data, calculate the correlation between different characteristics, and the Pearson correlation coefficient method can be used. According to the calculated correlation coefficient, generate a characteristic correlation matrix. This matrix represents the correlation between different low-concentration organic or heavy metal pollution types and electrochemical characteristics. Each element in the matrix represents the degree of correlation between two characteristics. The closer the value is to 1 or -1, the stronger the correlation between these two characteristics. Then, in at least one embodiment, use algorithms such as eigenvalue decomposition or principal component analysis to calculate the eigenvalues and eigenvectors from the characteristic correlation matrix. These eigenvalues reflect the main information volume in the data, and the eigenvectors represent the main component directions in the data. Sort the calculated eigenvalues to determine the contribution size of each characteristic to the overall data variance. The larger the information volume represented by the corresponding eigenvector, and set a cumulative contribution threshold according to the distribution of historical low-concentration pollution characteristics, such as a total contribution rate of 95%. This threshold is used to determine how many eigenvalues are selected. Calculate the characteristic contribution rate corresponding to each eigenvalue, that is, the ratio of the eigenvalue to the sum of all eigenvalues. Then, sort the eigenvalues in descending order of contribution rate, select the first few eigenvalues so that the cumulative contribution rate reaches the set threshold. According to the set contribution threshold, screen out several main characteristics. These characteristics represent the core characteristics of low-concentration organic pollution or heavy metal pollution in the water body. The screened main characteristics will be used for further analysis to reduce the data dimension while retaining the important information in the data.

[0036] Furthermore, enrich the low-concentration pollutants to obtain low-concentration pollution clusters, including: Make adsorption bags using adsorption materials and place the adsorption bags according to the sampling execution plan; Set the adsorption cycle according to the historical low-concentration pollution information and monitor the adsorption bags in real time according to the adsorption cycle to obtain the adsorbed pollutants; Elute the adsorbed pollutants to obtain low-concentration pollution clusters.

[0037] As a preference of the above embodiments, for low-concentration organic pollutants, adsorption materials suitable for organic pollutants can be selected, such as activated carbon, molecular sieve, modified silica gel or customized polymer adsorbents. For low-concentration heavy metal pollutants, activated carbon, modified zeolite (molecular sieve), biomass materials (charcoal, coconut shell charcoal), etc. can be selected as adsorption materials. According to the adsorption requirements of organic pollutants, materials with good air permeability, such as non-woven fabric, nylon mesh, etc., are selected to make a bag body. The adsorption materials are evenly filled in the bag body, and the edges of the adsorption bag are sealed to avoid leakage of the adsorption materials. Then, according to the characteristics and concentration range of organic pollutants, the size of the adsorption bag and the filling amount of the adsorption materials are designed. Subsequently, according to the low-concentration pollution information, such as the generation amount of organic pollutants, diffusion rate and environmental temperature and humidity, the adsorption cycle is determined. The initial adsorption cycle can be set to 1-2 weeks and adjusted in a timely manner according to the monitoring results. In addition, a VOC detector can be used to quickly analyze the change in the concentration of organic pollutants in the air near the adsorption bag, and some adsorption bag samples are regularly detected to evaluate the adsorption effect and saturation situation. Finally, the saturated adsorption bags are collected for elution operation. The elution operation steps can be carried out as follows: Take out the adsorption materials in the adsorption bag and place them in an elution container. According to the characteristics of the adsorption materials, select an appropriate eluent (such as ethanol, acetone, pure water, or acid-base solution, etc.), slowly add the eluent to the container, and stir or use ultrasonic assistance to promote the desorption of pollutants. Collect the eluate and further concentrate it by an appropriate concentration method (such as rotary evaporation, vacuum distillation) to obtain a low-concentration pollution mass. For low-concentration heavy metal pollutants, activated carbon, modified zeolite (molecular sieve), biomass materials (charcoal, coconut shell charcoal), etc. can be selected as adsorption materials. These materials have a high surface area and an appropriate pore structure, and can effectively carry out adsorption reactions with heavy metal ions in water. According to the nature and concentration of pollutants, the size of the adsorption bag and the filling amount of the adsorption materials are designed to ensure sufficient adsorption surface area and adsorption capacity. To ensure the enrichment effect, a suitable bag body material, such as non-woven fabric or nylon mesh, should be selected. They have good air permeability and mechanical strength and can prevent leakage of the adsorption materials. Different from organic pollutants, the adsorption of heavy metals is often affected by factors such as the pH value and temperature of the water body. Therefore, during the enrichment process, the placement time of the adsorption bag and the type of adsorption materials need to be appropriately adjusted according to the specific environmental conditions. For the enrichment process of low-concentration heavy metal pollutants, the initial adsorption cycle can also be set to 1-2 weeks, and the adsorption cycle is adjusted in a timely manner according to the monitoring results. The length and frequency of the adsorption cycle are closely related to the concentration of heavy metals, environmental temperature, humidity, and pH value in the water body. During the enrichment process, water sample analysis can be regularly carried out using instruments such as atomic absorption spectrometry (AAS) or inductively coupled plasma mass spectrometry (ICP-MS) to monitor the change in the concentration of heavy metal ions in the water and evaluate the adsorption effect.

[0038] Example 2 Based on the same inventive concept as the intelligent water pollution monitoring method in the foregoing embodiments, the present invention also provides an intelligent water pollution monitoring system, which includes: A pollution enrichment module that collects water body information, screens low-concentration pollutants according to the water body information, enriches the low-concentration pollutants, obtains low-concentration pollution clusters, and enriches to increase the concentration of low-concentration pollution; A signal extraction and amplification module that sets an optoelectronic composite configuration according to the low-concentration pollution cluster, obtains an output optoelectronic signal, amplifies the output optoelectronic signal, and obtains a target optoelectrochemical characteristic; A pollution characteristic comparison module that establishes a pollution characteristic database, identifies the target electrochemical characteristic according to the pollution characteristic database, and outputs low-concentration pollution monitoring information.

[0039] The above adjustment system in the present invention can effectively implement the intelligent water pollution monitoring method, and the technical effects that can be achieved are as described in the foregoing embodiments, which will not be elaborated here.

[0040] Furthermore, the signal extraction and amplification module includes: An electrochemical response acquisition unit that sets an electrode according to the low-concentration pollution cluster, immerses the electrode in the water body to be measured containing the low-concentration pollution cluster, applies an alternating current signal to the water body to be measured, and obtains an electrochemical response; An electrochemical analysis unit that analyzes the electrochemical response using electrochemical analysis software to obtain a preliminary electrochemical signal; A laser scattering analysis unit that irradiates the water body to be measured with an external laser source, collects the scattered light of the irradiated water body to be measured, and uses spectral analysis software to obtain the molecular vibration signal of the low-concentration pollution cluster; A signal fusion and recognition unit that synthesizes the preliminary electrochemical signal and the molecular vibration signal to recognize the output optoelectronic signal of the low-concentration pollution cluster.

[0041] Similarly, for the above optimization solutions of the system, the corresponding optimization effects of the methods in Embodiment 1 can also be respectively achieved, which will not be elaborated here either.

[0042] Although the present application has been described in combination with specific features and their embodiments, it is obvious that various modifications and combinations can be made without departing from the spirit and scope of the present application. Accordingly, the present specification and the drawings are merely exemplary descriptions of the present application as defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. An intelligent water pollution monitoring method, characterized in that: The method comprises: Collecting water body information, screening low-concentration pollutants according to the water body information, and enriching the low-concentration pollutants to obtain low-concentration pollutant clusters, wherein the enrichment is used to increase the concentration of the low-concentration pollutants; Setting a photoelectric composite configuration according to the low-concentration contamination group, obtaining an output photoelectric signal, amplifying the output photoelectric signal, and obtaining a target photoelectrochemical characteristic; A pollution characteristic database is established, the target photoelectrochemical characteristics are identified according to the pollution characteristic database, and low-concentration pollution monitoring information is output.

2. The intelligent water pollution monitoring method according to claim 1 is characterized in that: Collect water body information, including: Acquire a number of historical water body sampling points and acquire a number of initial water body sampling plans, wherein the initial water body sampling plans include a number of water body sampling points; According to the initial water sampling schemes, the water area to be sampled is divided according to the water flow velocity and flow direction to obtain a plurality of water partitions, each of which corresponds to the water flow velocity and flow direction; Adopting an optimization algorithm to adaptively screen the initial water body sampling plan to obtain a sampling execution plan; Water quality detection sensors are arranged according to the sampling execution scheme, and water body information is acquired according to the water quality detection sensors.

3. The intelligent water pollution monitoring method according to claim 2 is characterized in that: An optimization algorithm is used to adaptively screen several of the initial water sampling schemes, including: Construct pollution assessment function according to water pollution assessment standard; S1: Analyze several initial water body sampling schemes respectively according to the pollution assessment function, screen the schemes according to actual performance, and obtain several first-generation sampling schemes; S2: exchanging the water body sampling points corresponding to the water body partitions for a number of the first-generation sampling schemes to obtain a second-generation sampling scheme; S3: reselecting sampling points for any of the water body partitions of the second-generation sampling schemes, and using the reselected scheme as the new initial sampling scheme; An iteration threshold is set according to historical optimization experience, and iterations are performed according to steps S1, S2, and S3 until the number of iterations reaches the iteration threshold, and a sampling execution plan is output.

4. The intelligent water pollution monitoring method according to claim 1 is characterized in that: The photoelectric composite configuration is set according to the low-concentration pollution group, and the output photoelectric signal is obtained, including: Setting electrodes according to the low-concentration pollutant group, immersing the electrodes in a water body to be tested containing the low-concentration pollutant group, applying an alternating current signal to the water body to be tested, and obtaining an electrochemical response; Using electrochemical analysis software to analyze the electrochemical response to obtain a preliminary electrochemical signal; Using an external laser source to irradiate the water body to be tested, collecting scattered light irradiating the water body to be tested, and using spectrum analysis software to obtain molecular vibration signals of the low-concentration pollutant group; The preliminary electrochemical signal and the molecular vibration signal are integrated to identify the output photoelectric signal of the low-concentration contaminant.

5. The intelligent water pollution monitoring method according to claim 4 is characterized in that: Amplifying the output photoelectric signal to obtain target photoelectrochemical characteristics includes: Preliminarily amplifying the output photoelectric signal to obtain a pre-amplified signal; The pre-amplified signal is de-noised by using a filtering algorithm, and the amplification factor is adjusted by monitoring the electrochemical response amplitude to obtain a target electrochemical signal; The target electrochemical signal is converted into a digital data format to obtain the target photoelectrochemical characteristics.

6. The intelligent water pollution monitoring method according to claim 1 is characterized in that: Establish a pollution characteristics database, including: Collect historical low-concentration pollution information and extract historical low-concentration pollution characteristics; Using a multi-dimensional feature extraction algorithm to reduce the dimension of the historical low-concentration pollution features to obtain the main features of the historical low-concentration pollution; Constructing a multidimensional pollution matrix based on the main characteristics of the historical low-concentration pollution, wherein the rows of the matrix represent the types of low-concentration pollution and the columns of the matrix represent the electrochemical characteristics; An index relationship is created according to the multi-dimensional pollution matrix, and a pollution feature database is created.

7. The intelligent water pollution monitoring method according to claim 6 is characterized in that: A multi-dimensional feature extraction algorithm is used to reduce the dimension of the historical low-concentration pollution features, including: Standardizing the historical low-concentration pollution characteristics, performing correlation calculation on a number of the standardized historical low-concentration pollution characteristics, and obtaining a characteristic correlation matrix, wherein the characteristic correlation matrix is ​​used to represent the correlation between a number of low-concentration pollution types and electrochemical characteristics; Calculating eigenvalues ​​and eigenvectors corresponding to the eigenvalues ​​according to the characteristic correlation matrix, and serializing the eigenvalues; A cumulative characteristic contribution threshold is set according to the historical low-concentration pollution characteristics, characteristic contribution rates of several characteristic values ​​are calculated respectively, and several characteristic values ​​are screened according to the cumulative characteristic contribution threshold to obtain the main characteristics of the historical low-concentration pollution.

8. The intelligent water pollution monitoring method according to claim 3 is characterized in that: The low-concentration pollutants are enriched to obtain low-concentration pollutant clusters, including: Adsorbent bags are made of adsorbent material and placed according to the sampling execution plan; Setting an adsorption cycle according to historical low-concentration pollution information, and monitoring the adsorption bag in real time according to the adsorption cycle to obtain adsorbed pollutants; The adsorbed pollutants are eluted to obtain low-concentration pollutant clusters.

9. An intelligent water pollution monitoring system, characterized in that: The system comprises: A pollution collection and enrichment module collects water body information, screens low-concentration pollutants according to the water body information, and enriches the low-concentration pollutants to obtain low-concentration pollution clusters, wherein the enrichment is used to increase the concentration of low-concentration pollution; A signal extraction and amplification module is used to set a photoelectric composite configuration according to the low-concentration contaminant, obtain an output photoelectric signal, amplify the output photoelectric signal, and obtain a target photoelectrochemical characteristic; The pollution characteristic comparison module establishes a pollution characteristic database, identifies the target electrochemical characteristic according to the pollution characteristic database, and outputs low-concentration pollution monitoring information.

10. The intelligent water pollution monitoring system according to claim 9 is characterized in that: The signal extraction and amplification module comprises: An electrochemical response acquisition unit is configured to set an electrode according to the low-concentration pollutant group, immerse the electrode in a water body to be tested containing the low-concentration pollutant group, apply an alternating current signal to the water body to be tested, and acquire an electrochemical response; An electrochemical analysis unit, using electrochemical analysis software to analyze the electrochemical response to obtain a preliminary electrochemical signal; A laser scattering analysis unit, which uses an external laser source to irradiate the water body to be tested, collects scattered light irradiating the water body to be tested, and uses spectrum analysis software to obtain molecular vibration signals of the low-concentration pollutant group; The signal fusion recognition unit integrates the preliminary electrochemical signal and the molecular vibration signal to recognize the output photoelectric signal of the low-concentration contaminant.

Images