Intelligent water quality monitoring system and method based on turbidity sensor

Abstract

The invention discloses an intelligent water quality monitoring system and method based on a turbidity sensor, and relates to the technical field of water quality monitoring. Data acquisition nodes are arranged in a water area to be monitored, data are acquired by using the turbidity sensor and an intelligent water quality monitoring equipment group, an environment data set S is constructed, and preprocessing is performed; acquiring a turbidity change coefficient # imgabs0 # according to a turbidity data set in the preprocessed environment data set S, performing primary evaluation, marking abnormal data acquisition nodes, acquiring a particulate matter dynamic index KL and a pollution index WR according to a particulate matter data set and an organic pollutant data set in the environment data set S, and performing secondary evaluation according to the turbidity change coefficient # imgabs1 # and the turbidity change coefficient # imgabs0 # in combination with the particulate matter dynamic index KL and the pollution index WR. Acquiring a comprehensive water quality score Q, performing secondary evaluation, and constructing a water quality prediction model to predict the water quality change and regulate and control the water quality for the data acquisition nodes which are normally evaluated for the second time; the intelligent level of water quality monitoring is improved, the accuracy of water quality monitoring is enhanced, and the safety of water quality is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of water quality monitoring, and in particular to an intelligent water quality monitoring system and method based on a turbidity sensor. Background Art

[0002] Water quality monitoring is one of the important research directions in the field of environmental protection. It is widely used in pollution prevention and control, water resources management and ecological protection. In this field, sewage treatment plants, as key nodes, treat industrial and domestic wastewater to meet emission standards or achieve reuse. The effluent quality of sewage treatment plants directly affects the environmental safety and ecological health of downstream water bodies. One of the core indicators of effluent is water turbidity, which can reflect the concentration of suspended particulate matter and the clarity of water quality. The intelligent water quality monitoring system based on turbidity sensors is a commonly used technical means in this scenario, which is used to monitor and evaluate the stability and effectiveness of sewage treatment in real time.

[0003] In the Chinese invention patent with application publication number CN111928889A, an intelligent water quality monitoring system is disclosed, including multiple unmanned boats and a remote control terminal, each of which includes a water quality monitoring subsystem and a positioning subsystem. The remote control terminal is connected to each unmanned boat and includes an interaction module, a storage module, a monitoring module and a remote control module. Through this technical solution, it is possible to achieve the necessary monitoring of large-scale water sources such as rivers, lakes and seas, without the need for relevant personnel to drive a boat to conduct on-site water surface sampling, avoiding related safety risks, simplifying the cumbersome process while being able to conduct timely and effective sampling and testing of water samples, avoiding damage to water samples during transportation, and making the test results more accurate; at the same time, the use of remote control makes the adjustment of the sampling area and sampling range more flexible, and the addition of cloud data analysis functions also makes the water quality test results traceable, and the changes in the water body are more clear at a glance.

[0004] The above intelligent water quality monitoring system can make the water quality test results traceable, the changes in the water body are more clear at a glance, and avoid the related safety risks of field water surface sampling. However, in addition to this, the existing water quality monitoring methods generally use manual sampling and traditional online equipment monitoring sampling, which has certain limitations.

[0005] However, although this intelligent water quality monitoring system can adjust the sampling area and sampling range more flexibly, the timeliness of the collected data cannot be guaranteed. It cannot collect environmental data of the water area to be tested in real time and monitor water quality changes.

[0006] To this end, the present invention provides an intelligent water quality monitoring system and method based on a turbidity sensor. Summary of the invention

[0007] 1. Technical issues to be resolved

[0008] In view of the shortcomings of the prior art, the present invention provides an intelligent water quality monitoring system and method based on turbidity sensors, which sets data collection nodes in the water area to be tested, uses turbidity sensors and intelligent water quality monitoring equipment to collect data, constructs an environmental data set S, performs preprocessing, and obtains the turbidity variation coefficient based on the turbidity data set in the preprocessed environmental data set S. , conduct an initial assessment, mark the abnormal data collection nodes, and obtain the particle dynamic index KL and pollution index WR based on the particle data group and organic pollutant data group in the environmental data set S, combined with the turbidity change coefficient , obtain the comprehensive water quality score Q, conduct a secondary evaluation, and for the data collection nodes that are normal in the secondary evaluation, build a water quality prediction model to predict the water quality changes at future time points (t+k) and regulate the water quality; improve the intelligence level of water quality monitoring, enhance the accuracy of water quality monitoring, and ensure water quality safety, thereby solving the problems in the above-mentioned background technology.

[0009] (II) Technical solution

[0010] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent water quality monitoring system based on turbidity sensor, including a data acquisition module, a preprocessing module, a preliminary evaluation module, a comprehensive evaluation module and a water quality prediction module;

[0011] The data acquisition module is used to set up data acquisition nodes, and deploy turbidity sensors and intelligent water quality monitoring equipment groups at the data acquisition nodes, collect environmental data of the data acquisition nodes in real time, and construct an environmental data set S;

[0012] The preprocessing module is used to preprocess the constructed environmental data set S;

[0013] The preliminary evaluation module is used to obtain the turbidity variation coefficient according to the turbidity data set in the environmental data set S. , combined with the preset turbidity change threshold , assess changes in water quality;

[0014] The comprehensive evaluation module is used to obtain the particle dynamic index KL and the pollution index WR based on the particle data group and the organic pollutant data group in the environmental data set S, and combined with the turbidity change threshold , obtain the comprehensive water quality score Q, and compare and analyze the comprehensive water quality score Q with the water quality threshold W to evaluate the water quality status;

[0015] The water quality prediction module is used to construct a water quality prediction model, obtain the comprehensive water quality score Q(t+k) at a future time point (t+k), and obtain the normal fluctuation range of water quality in combination with historical environmental data. , the comprehensive water quality score Q(t+k) and the normal fluctuation range of water quality Conduct comparative analysis and regulate water quality.

[0016] Preferably, the data acquisition module includes a turbidity data acquisition unit, a particulate matter data acquisition unit and an organic pollutant data acquisition unit;

[0017] The turbidity data acquisition unit is used to deploy turbidity sensors and intelligent water quality monitoring equipment groups in the water area to be tested, and set the data acquisition time interval to , use the turbidity sensor to emit laser to the water area to be tested, monitor the scattered light signal of the laser, and convert the scattered light signal into an electrical signal to obtain the turbidity data of the water area to be tested, construct a turbidity data group, and transmit the constructed turbidity data group to the data processing center through the wireless network device on the turbidity sensor.

[0018] Preferably, the particle data collection unit is used according to the intelligent water quality monitoring equipment group of the water area to be tested, and combined with the set data collection time interval , collect the particle data of the water area to be tested in real time and construct a particle data group;

[0019] The organic pollutant data collection unit is used to collect the organic pollutant data of the water area to be tested in real time based on the intelligent water quality monitoring equipment group of the water area to be tested, and construct an organic pollutant data group;

[0020] The constructed particulate matter data set and organic pollutant data set are transmitted to the data processing center, and the environmental data set S is constructed according to the turbidity data set, the particulate matter data set and the organic pollutant data set;

[0021] The intelligent water quality monitoring equipment group includes a laser particle size analyzer, a COD online analyzer, an ultraviolet sensor, a TOC online analyzer and a DOC online detector.

[0022] Preferably, the preprocessing module is used to preprocess the environmental data set S, and the preprocessing steps include missing value processing, smoothing processing, outlier detection and elimination, and data normalization;

[0023] The missing value processing is to fill the missing values ​​in the collected data using linear interpolation;

[0024] The smoothing process is to use a sliding window to calculate the average value of each time point to reduce random fluctuations;

[0025] The outlier detection and elimination is to perform statistical analysis on the collected data, identify outliers, and eliminate them;

[0026] The data normalization refers to dimensionless processing of the collected data to eliminate the influence of different dimensions and normalize the data.

[0027] Preferably, the preliminary evaluation module includes a turbidity data analysis unit and a turbidity data evaluation unit;

[0028] The turbidity data analysis unit is used to perform summary calculation based on the turbidity data group in the pre-processed environmental data set S to obtain the turbidity change coefficient of each data collection node ;

[0029] The turbidity variation coefficient The method of obtaining is:

[0030] ;

[0031] Where n is the total number of data collection times, is the turbidity value collected at the i-th time point, is the turbidity value collected at the i-1th time point, is the data collection time interval.

[0032] Preferably, the turbidity data evaluation unit is used to preset the turbidity change threshold , and the turbidity variation coefficient obtained With the preset turbidity change threshold Conduct comparative analysis and evaluate water quality. The specific evaluation contents are as follows:

[0033] If the turbidity variation coefficient Less than turbidity change threshold ,Right now When the water quality fluctuation is within the normal range, the normal turbidity data monitoring is maintained;

[0034] If the turbidity variation coefficient Greater than or equal to the turbidity change threshold ,Right now When the water quality fluctuation is within the abnormal range, the data collection node where the water quality fluctuation is within the abnormal range is marked as an abnormal data collection node, and an alarm mechanism is triggered.

[0035] Preferably, the comprehensive evaluation module includes a data analysis unit and a secondary evaluation unit;

[0036] The data analysis unit is used to perform summary analysis based on the particulate matter data group and the organic pollutant data group in the pre-processed environmental data set S to obtain the particulate matter dynamic index KL and the pollution index WR;

[0037] The particle data group includes the volume proportion p of particles of different particle sizes in each data collection node;

[0038] The volume proportion of particles of the particle size p is measured by using a laser particle size analyzer to measure the particle size distribution, and the volume proportion of particles of each particle size is calculated according to the particle size range;

[0039] The organic pollutant data group includes the chemical oxygen demand COD, ultraviolet absorption value UV254, total organic carbon TOC and dissolved organic carbon content DOC of each data collection node;

[0040] The chemical oxygen demand COD is obtained by a COD online analyzer;

[0041] The ultraviolet absorption value UV254 is obtained by an ultraviolet sensor;

[0042] The total organic carbon TOC is obtained by a TOC online analyzer;

[0043] The dissolved organic carbon content DOC is obtained by a DOC online detector.

[0044] Preferably, the secondary evaluation unit is used to obtain the particle dynamic index KL, pollution index WR and turbidity variation coefficient. Perform summary calculations to obtain a comprehensive water quality score Q;

[0045] The comprehensive water quality score Q is obtained as follows:

[0046] ;

[0047] In the formula, , and They are the particle dynamic index KL, the pollution index WR and the turbidity variation coefficient. The weight coefficient of , is the correction constant;

[0048] The preset water quality threshold W is compared and analyzed with the comprehensive water quality score Q to evaluate the water quality status. The specific evaluation contents are as follows:

[0049] If the comprehensive water quality score Q is less than the water quality threshold W, that is, Q<W, the water quality is judged to be within a safe range, the water quality changes are continuously monitored, and the water quality data is recorded to generate a water quality monitoring report, which is stored in the water quality monitoring data center;

[0050] If the comprehensive water quality score Q is greater than or equal to the water quality threshold W, that is, Q≥W, the water quality is judged to be within the dangerous range, triggering the alarm mechanism, and marking the data collection nodes where the water quality is within the dangerous range. A distribution map of abnormal water quality areas is generated based on the marked data collection nodes, and the distribution map of abnormal water quality areas is sent to water quality monitoring personnel, and the water quality monitoring personnel are continuously warned until they respond.

[0051] Preferably, the water quality prediction module is used to predict the water quality status of data collection nodes whose water quality is within a safe range;

[0052] The water quality prediction module includes a model building unit and an early warning unit;

[0053] The model building unit is used to build a water quality prediction model based on an autoregressive integrated moving average algorithm, and extract historical environmental data from a water quality monitoring data center, use the extracted historical environmental data as training data to input the water quality prediction model, perform model training, and compare the predicted value of the water quality prediction model with the actual value in the historical environmental data to optimize the model;

[0054] The early warning unit is used to input the real-time collected water quality data into the trained water quality prediction model to obtain the comprehensive water quality score Q(t+k) at the future time point (t+k), and compare the obtained comprehensive water quality score Q(t+k) with the normal fluctuation range of water quality obtained according to historical environmental data. Conduct comparative analysis to assess the water quality risk at a future time point (t+k). If the comprehensive water quality score Q(t+k) is not within the normal fluctuation range of water quality, If the water quality fluctuation at the future time point (t+k) is within t+k, it is determined that the water quality fluctuation is abnormal, triggering the early warning mechanism, and dispatching water quality monitoring personnel to the data collection node where the water quality fluctuation is abnormal to carry out water quality regulation.

[0055] An intelligent water quality monitoring method based on turbidity sensor comprises the following steps:

[0056] Step 1: Set up data collection nodes, deploy turbidity sensors and intelligent water quality monitoring equipment groups at the data collection nodes, collect environmental data of the data collection nodes in real time, and construct an environmental data set S;

[0057] Step 2: preprocess the constructed environmental data set S;

[0058] Step 3: Obtain the turbidity variation coefficient based on the turbidity data set in the environmental data set S , combined with the preset turbidity change threshold , assess changes in water quality;

[0059] Step 4: Based on the particle data set and organic pollutant data set in the environmental data set S, obtain the particle dynamic index KL and the pollution index WR, and combine the turbidity change threshold , obtain the comprehensive water quality score Q, and compare and analyze the comprehensive water quality score Q with the water quality threshold W to evaluate the water quality status;

[0060] Step 5: Build a water quality prediction model to obtain the comprehensive water quality score Q(t+k) at the future time point (t+k), and combine historical environmental data to obtain the normal fluctuation range of water quality , the comprehensive water quality score Q(t+k) and the normal fluctuation range of water quality Conduct comparative analysis and regulate water quality.

[0061] (III) Beneficial effects

[0062] The present invention provides an intelligent water quality monitoring system and method based on turbidity sensor, which has the following beneficial effects:

[0063] (1) The present invention uses turbidity sensors, laser particle size analyzers, COD online analyzers, ultraviolet sensors, TOC online analyzers and DOC online detectors to collect turbidity data, particulate matter data and organic pollutant data in real time and construct an environmental data set S. Compared with the methods of using a single or a small number of water quality parameters for analysis in the prior art, the system can obtain more comprehensive water quality information, covering the dynamic change characteristics of particulate matter distribution, organic pollutant concentration and water turbidity. Through the comprehensive evaluation module, the particle dynamic index KL, pollution index WR and comprehensive water quality score Q are further obtained, realizing the deep integration and analysis of multi-dimensional data, greatly improving the accuracy and reliability of water quality monitoring.

[0064] (2) The present invention constructs a water quality prediction module based on the comprehensive water quality assessment module. By analyzing historical environmental data and real-time monitoring data and using the autoregressive integral sliding average algorithm, the comprehensive water quality score Q(t+k) at the future time point (t+k) is predicted. At the same time, the predicted value is compared with the normal fluctuation range of historical water quality to accurately identify water quality anomalies that may occur in the future and trigger an early warning mechanism. This dynamic assessment and prediction function can not only detect risks in advance before water quality deterioration occurs, but also provide a decision-making basis for water quality regulation, thereby significantly improving the initiative and effectiveness of water quality management.

[0065] (3) This system adopts a modular design, including an acquisition module, a preprocessing module, a preliminary evaluation module, a comprehensive evaluation module, and a water quality prediction module. The modules work closely together and are highly flexible. The adaptability of the model is improved by means of data cleaning, outlier removal, and weight optimization. In addition, the adjustment coefficient ϵ and the water quality prediction model are continuously optimized using historical monitoring data to ensure the accuracy and robustness of the system's analysis when facing different water quality environments. Compared with traditional water quality monitoring methods, this system can adapt to complex and changeable water quality conditions, thereby achieving accurate water quality monitoring and scientific water quality management. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 The present invention is a block diagram of an intelligent water quality monitoring system based on a turbidity sensor.

[0067] Figure 2 The present invention is a schematic flow chart of an intelligent water quality monitoring method based on a turbidity sensor. DETAILED DESCRIPTION

[0068] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0069] Example 1, please refer to Figure 1 , the present invention provides an intelligent water quality monitoring system based on turbidity sensor, including a data acquisition module, a preprocessing module, a preliminary evaluation module, a comprehensive evaluation module and a water quality prediction module;

[0070] The data acquisition module is used to set up data acquisition nodes, and deploy turbidity sensors and intelligent water quality monitoring equipment groups at the data acquisition nodes, collect environmental data of the data acquisition nodes in real time, and construct an environmental data set S;

[0071] The preprocessing module is used to preprocess the constructed environmental data set S;

[0072] The preliminary evaluation module is used to obtain the turbidity variation coefficient according to the turbidity data set in the environmental data set S. , combined with the preset turbidity change threshold , assess changes in water quality;

[0073] The comprehensive evaluation module is used to obtain the particle dynamic index KL and the pollution index WR based on the particle data group and the organic pollutant data group in the environmental data set S, and combined with the turbidity change threshold , obtain the comprehensive water quality score Q, and compare and analyze the comprehensive water quality score Q with the water quality threshold W to evaluate the water quality status;

[0074] The water quality prediction module is used to construct a water quality prediction model, obtain the comprehensive water quality score Q(t+k) at a future time point (t+k), and obtain the normal fluctuation range of water quality in combination with historical environmental data. , the comprehensive water quality score Q(t+k) and the normal fluctuation range of water quality Conduct comparative analysis and regulate water quality.

[0075] In the embodiment, the comprehensiveness, accuracy and intelligence of water quality monitoring are achieved through the linkage of five modules: data acquisition, preprocessing, preliminary evaluation, comprehensive evaluation and water quality prediction. The data acquisition module uses turbidity sensors and intelligent water quality monitoring equipment to obtain turbidity data, particulate matter data and organic pollutant data in real time, constructs an environmental data set S, ensures the real-time and comprehensiveness of monitoring, and provides a rich data foundation for subsequent analysis. The preprocessing module performs missing value processing, smoothing, outlier detection and elimination, and data normalization on the environmental data set S, which improves the quality and consistency of the data, ensures that subsequent evaluations are based on high-quality data, and avoids interference of data noise on the results. The preliminary evaluation module calculates the turbidity variation coefficient based on the turbidity data set. , and combined with the turbidity change threshold , quickly judge whether the water quality fluctuation is abnormal, improve the monitoring response speed, the comprehensive evaluation module calculates the particle dynamic index KL and pollution index WR, and the turbidity change coefficient The fusion analysis of the water quality module obtains the comprehensive water quality score Q, accurately identifies the water quality status, and supports the marking and evaluation of high-risk areas. The water quality prediction module builds a water quality point (t+k) prediction model based on historical environmental data and real-time water quality data to predict the water quality score Q(t+k) at a future time point, combined with the normal fluctuation range of water quality. Trend analysis is carried out to achieve early warning and the generation of control suggestions. Compared with the existing technology, the present invention not only improves the accuracy and response efficiency of water quality monitoring, but also enhances the intelligence and adaptability of the system, providing scientific support for water quality risk management in complex water quality environments.

[0076] Example 2, please refer to Figure 1 , specifically: the data acquisition module includes a turbidity data acquisition unit, a particulate matter data acquisition unit and an organic pollutant data acquisition unit;

[0077] The turbidity data acquisition unit is used to deploy turbidity sensors and intelligent water quality monitoring equipment groups in the water area to be tested, and set the data acquisition time interval to , use the turbidity sensor to emit laser to the water area to be tested, monitor the scattered light signal of the laser, and convert the scattered light signal into an electrical signal to obtain the turbidity data of the water area to be tested, construct a turbidity data group, and transmit the constructed turbidity data group to the data processing center through the wireless network device on the turbidity sensor.

[0078] The particle data collection unit is used to collect data based on the intelligent water quality monitoring equipment group of the water area to be tested, combined with the set data collection time interval , collect the particle data of the water area to be tested in real time and construct a particle data group;

[0079] The organic pollutant data collection unit is used to collect the organic pollutant data of the water area to be tested in real time based on the intelligent water quality monitoring equipment group of the water area to be tested, and construct an organic pollutant data group;

[0080] The constructed particulate matter data set and organic pollutant data set are transmitted to the data processing center, and the environmental data set S is constructed according to the turbidity data set, the particulate matter data set and the organic pollutant data set;

[0081] The intelligent water quality monitoring equipment group includes a laser particle size analyzer, a COD online analyzer, an ultraviolet sensor, a TOC online analyzer and a DOC online detector.

[0082] In this embodiment, the accuracy, real-time and comprehensiveness of water quality data collection are improved through the turbidity data collection unit, the particulate matter data collection unit and the organic pollutant data collection unit. First, the turbidity data collection unit uses a turbidity sensor to monitor the turbidity of the water body in real time through the laser scattering principle, and transmits the data to the data processing center in real time through a wireless network device to construct a turbidity data group, which provides a basis for the rapid evaluation of water quality fluctuations. Secondly, the particulate matter data collection unit uses a laser particle size analyzer to perform fine measurements on the particle size distribution and volume percentage of particulate matter in the water, and updates the particulate matter data group in real time. This function can not only accurately evaluate the source and sedimentation characteristics of particulate matter, but also provide reliable data support for the calculation of the particle dynamic index KL. In addition, the organic pollutant data collection unit monitors the water area to be tested in real time through a COD online analyzer, an ultraviolet sensor, a TOC online analyzer and a DOC online detector, and constructs an organic pollutant data group, which can accurately reflect the concentration of organic pollutants in the water body and their decomposition ability, providing a strong data basis for the analysis of the pollution index and realizing multi-dimensional real-time monitoring of water quality conditions.

[0083] Example 3, please refer to Figure 1 Specifically: the preprocessing module is used to preprocess the environmental data set S, and the preprocessing steps include missing value processing, smoothing processing, outlier detection and elimination, and data normalization;

[0084] The missing value processing is to fill the missing values ​​in the collected data using linear interpolation;

[0085] The smoothing process is to use a sliding window to calculate the average value of each time point to reduce random fluctuations;

[0086] The outlier detection and elimination is to perform statistical analysis on the collected data, identify outliers, and eliminate them;

[0087] The data normalization refers to dimensionless processing of the collected data to eliminate the influence of different dimensions and normalize the data.

[0088] In this embodiment, through multiple processing steps of the environmental data set S, the integrity, consistency and reliability of the data are improved, providing a high-quality data foundation for subsequent water quality assessment and prediction. Specifically, the missing value processing fills the missing values ​​in the collected data through linear interpolation, which can restore the data integrity on the basis of retaining the data trend, avoiding the accuracy of the analysis results affected by missing data. The smoothing processing uses a sliding window method to calculate the average value of each time point, effectively eliminating random fluctuations in the data, enhancing the stability of the data, and retaining important trend information, laying the foundation for subsequent dynamic analysis. Outlier detection and elimination uses statistical analysis methods to identify and eliminate abnormal data that exceeds a reasonable range, avoiding the offset effect of outliers on the results, and ensuring the robustness of evaluation and prediction. Data normalization eliminates the influence of different parameter dimensions and scales through dimensionless processing, so that different data can be reasonably compared and calculated under the same analysis framework, improving the scientific nature of multi-parameter fusion analysis, improving the reliability and utilization value of data, thereby enhancing the accuracy of subsequent water quality assessment and the effectiveness of system prediction.

[0089] Example 4, please refer to Figure 1 , specifically: the preliminary evaluation module includes a turbidity data analysis unit and a turbidity data evaluation unit;

[0090] The turbidity data analysis unit is used to perform summary calculation based on the turbidity data group in the pre-processed environmental data set S to obtain the turbidity change coefficient of each data collection node ;

[0091] The turbidity variation coefficient The method of obtaining is:

[0092] ;

[0093] Where n is the total number of data collection times, is the turbidity value collected at the i-th time point, is the turbidity value collected at the i-1th time point, is the data collection time interval.

[0094] The turbidity data evaluation unit is used to preset the turbidity change threshold , and the turbidity variation coefficient obtained With the preset turbidity change threshold Conduct comparative analysis and evaluate water quality. The specific evaluation contents are as follows:

[0095] If the turbidity variation coefficient Less than turbidity change threshold ,Right now When the water quality fluctuation is within the normal range, the normal turbidity data monitoring is maintained;

[0096] If the turbidity variation coefficient Greater than or equal to the turbidity change threshold ,Right now ≥ When the water quality fluctuation is within the abnormal range, the data collection node where the water quality fluctuation is within the abnormal range is marked as an abnormal data collection node, and an alarm mechanism is triggered.

[0097] In this embodiment, through the cooperation of the turbidity data analysis unit and the turbidity data evaluation unit, the water quality fluctuation state can be quickly and accurately identified, providing an efficient first line of defense for water quality monitoring. The turbidity data analysis unit performs dynamic change calculation on the turbidity data group based on the pre-processed environmental data set S to obtain the turbidity change coefficient. Compared with the traditional method of monitoring only a single turbidity value, this module not only focuses on the instantaneous value, but also comprehensively considers the dynamic fluctuation trend of turbidity, making it more sensitive to water quality changes, especially suitable for early warning of sudden pollution events. In addition, by introducing the turbidity change threshold The turbidity data evaluation unit can automatically calculate the turbidity variation coefficient Turbidity change threshold Compare and analyze to quickly determine whether the water quality fluctuation is abnormal. Greater than or equal to the turbidity change threshold When abnormal data is collected, the system can automatically mark the abnormal data collection node and trigger the alarm mechanism, providing a clear focus analysis object for subsequent modules, improving the efficiency of abnormal state processing. This embodiment has the characteristics of rapid response and accurate judgment, which is helpful to quickly screen out potential problem areas in large-scale water area monitoring, optimize resource allocation and subsequent control strategies. Through this dynamic turbidity assessment method, the system can significantly improve the overall efficiency and intelligence level of water quality monitoring.

[0098] Example 5, please refer to Figure 1,Specifically: the comprehensive evaluation module includes a data analysis unit and a secondary evaluation unit;

[0099] The data analysis unit is used to perform summary analysis based on the particulate matter data group and the organic pollutant data group in the pre-processed environmental data set S to obtain the particulate matter dynamic index KL and the pollution index WR;

[0100] The particle data group includes the volume proportion p of particles of different particle sizes in each data collection node;

[0101] The volume proportion p of the particle size particles is measured by using a laser particle size analyzer to measure the particle size distribution, and the volume proportion of each type of particle size particles is calculated according to the particle size range;

[0102] The organic pollutant data group includes the chemical oxygen demand COD, ultraviolet absorption value UV254, total organic carbon TOC and dissolved organic carbon content DOC of each data collection node;

[0103] The chemical oxygen demand COD is obtained by a COD online analyzer;

[0104] The ultraviolet absorption value UV254 is obtained by an ultraviolet sensor;

[0105] The total organic carbon TOC is obtained by a TOC online analyzer;

[0106] The dissolved organic carbon content DOC is obtained by a DOC online detector;

[0107] The particle dynamic index KL is obtained as follows:

[0108] ;

[0109] In the formula, It is Volume proportion of particles of similar particle size, It is Average particle size of particles of similar particle size, is the average particle size of the total particles, m is the number of particle types, It is Particles of similar size;

[0110] The pollution index WR is obtained in the following way:

[0111] ;

[0112] In the formula, COD is chemical oxygen demand, UV254 is ultraviolet absorption value, TOC is total organic carbon, is the dissolved organic carbon content collected at the i-th time point, is the dissolved organic carbon content collected at the i-1th time point, is the data collection time interval, is the adjustment coefficient;

[0113] The adjustment factor By collecting chemical oxygen demand (COD), ultraviolet absorption value (UV254), total organic carbon (TOC) and dissolved organic carbon (DOC) in historical environmental data, a correlation model between the dynamic change rate of dissolved organic carbon (DOC) and the pollution index (WR) was constructed based on the linear regression method, and the mean square error (MSE) was used to optimize the adjustment coefficient. The value of , select the adjustment coefficient corresponding to the minimum value of MSE As the final output value;

[0114] The historical environmental data refers to the environmental data of the water area to be tested collected by the intelligent water quality monitoring system during past operations, including turbidity data, particulate matter data and organic pollutant data.

[0115] The secondary evaluation unit is used to obtain the particle dynamic index KL, pollution index WR and turbidity change coefficient. Perform summary calculations to obtain a comprehensive water quality score Q;

[0116] The comprehensive water quality score Q is obtained as follows:

[0117] ;

[0118] In the formula, , and They are the particle dynamic index KL, the pollution index WR and the turbidity variation coefficient. The specific value is set by the user according to the usage, and , is the correction constant;

[0119] The preset water quality threshold W is compared and analyzed with the comprehensive water quality score Q to evaluate the water quality status. The specific evaluation contents are as follows:

[0120] If the comprehensive water quality score Q is less than the water quality threshold W, that is, Q<W, the water quality is judged to be within a safe range, the water quality changes are continuously monitored, and the water quality data is recorded to generate a water quality monitoring report, which is stored in the water quality monitoring data center;

[0121] If the comprehensive water quality score Q is greater than or equal to the water quality threshold W, that is, Q≥W, the water quality is judged to be within the dangerous range, triggering the alarm mechanism, and marking the data collection nodes where the water quality is within the dangerous range. A distribution map of abnormal water quality areas is generated based on the marked data collection nodes, and the distribution map of abnormal water quality areas is sent to water quality monitoring personnel, and the water quality monitoring personnel are continuously warned until they respond.

[0122] In this embodiment, the particulate matter data group and the organic pollutant data group in the pre-processed environmental data set S are summarized and analyzed by the data analysis unit, and the particulate matter dynamic index KL and the pollution index WR are accurately calculated. The particulate matter data group obtains the volume proportion P of particles of different particle sizes through a laser particle size analyzer to fully reflect the distribution characteristics of the particulate matter. The organic pollutant data group collects chemical oxygen demand COD, ultraviolet absorption value UV254, total organic carbon TOC and dissolved organic carbon content DOC through a COD online analyzer, an ultraviolet sensor, a TOC online analyzer and a DOC online detector, which deeply reveals the composition and dynamic changes of organic pollution, realizes the deep integration of multi-dimensional data, effectively improves the comprehensiveness and accuracy of water quality assessment, and lays a solid foundation for subsequent water quality status judgment. In addition, a correlation model between the dynamic change rate of dissolved organic carbon and the pollution index WR is constructed by the linear regression method, and the mean square error MSE is used to optimize the adjustment coefficient in combination with historical environmental data. The value of can dynamically adjust the pollution index WR according to different environments, making the calculation of the pollution index WR more in line with the actual water quality changes, and can effectively capture sudden pollution events or long-term trend changes, thereby enhancing the adaptability and scientificity of the system. In addition, the optimization algorithm ensures the accuracy of the calculation of the pollution index WR, reduces calculation errors, and improves the overall evaluation effect.

[0123] Example 6, please refer to Figure 1 ,Specifically: the water quality prediction module is used to predict the water quality status of the ,data acquisition nodes whose water quality is within a safe range;

[0124] The water quality prediction module includes a model building unit and an early warning unit;

[0125] The model building unit is used to build a water quality prediction model based on an autoregressive integrated moving average algorithm, and extract historical environmental data from a water quality monitoring data center, use the extracted historical environmental data as training data to input the water quality prediction model, perform model training, and compare the predicted value of the water quality prediction model with the actual value in the historical environmental data to optimize the model;

[0126] The early warning unit is used to input the real-time collected environmental data into the trained water quality prediction model to obtain the comprehensive water quality score Q(t+k) at the future time point (t+k), and compare the obtained comprehensive water quality score Q(t+k) with the normal fluctuation range of water quality obtained according to historical environmental data. Conduct comparative analysis to assess the water quality risk at a future time point (t+k). If the comprehensive water quality score Q(t+k) is not within the normal fluctuation range of water quality, If the water quality fluctuation at the future time point (t+k) is within, it is determined that the water quality fluctuation is abnormal, triggering the early warning mechanism, and dispatching water quality monitoring personnel to the data collection node of the abnormal water quality fluctuation to control the water quality;

[0127] Said is the mean of the historical comprehensive water quality score Q;

[0128] Said is the standard deviation of the historical water quality comprehensive score Q.

[0129] In this embodiment, through model construction and water quality prediction, the initiative and accuracy of water quality monitoring are enhanced, and the efficiency of water quality management is significantly improved. The model construction unit uses the autoregressive integrated moving average algorithm ARIMA to construct a water quality prediction model, extracts historical environmental data from the water quality monitoring data center as training data, and dynamically trains and optimizes the model to ensure that the water quality prediction model can adapt to different water quality characteristics and dynamically changing environments in real time. The error between the predicted value of the water quality prediction model and the actual value in the historical data is compared, and the model parameters are continuously optimized to continuously improve the prediction accuracy. Compared with traditional prediction methods that rely on manual judgment, this system can achieve more efficient and scientific water quality trend analysis, and provide strong support for scientific decision-making in water quality management.

[0130] Example 7, please refer to Figure 2 , specifically: an intelligent water quality monitoring method based on turbidity sensor, comprising the following steps,

[0131] Step 1: Set up data collection nodes, deploy turbidity sensors and intelligent water quality monitoring equipment groups at the data collection nodes, collect environmental data of the data collection nodes in real time, and construct an environmental data set S;

[0132] Step 2: preprocess the constructed environmental data set S;

[0133] Step 3: Obtain the turbidity variation coefficient based on the turbidity data set in the environmental data set S , combined with the preset turbidity change threshold , assess changes in water quality;

[0134] Step 4: Based on the particle data set and organic pollutant data set in the environmental data set S, obtain the particle dynamic index KL and the pollution index WR, and combine the turbidity change threshold , obtain the comprehensive water quality score Q, and compare and analyze the comprehensive water quality score Q with the water quality threshold W to evaluate the water quality status;

[0135] Step 5: Build a water quality prediction model to obtain the comprehensive water quality score Q(t+k) at the future time point (t+k), and combine historical environmental data to obtain the normal fluctuation range of water quality , the comprehensive water quality score Q(t+k) and the normal fluctuation range of water quality Conduct comparative analysis and regulate water quality.

[0136] In this embodiment, real-time data collection ensures the comprehensiveness of multi-dimensional environmental information, data preprocessing improves the accuracy of data analysis, preliminary assessment quickly responds to water quality fluctuations, comprehensive assessment provides a comprehensive water quality status analysis, and water quality prediction provides proactive support for future risk prevention and control and water quality regulation, enabling the present invention to monitor and manage water quality comprehensively, accurately and intelligently.

[0137] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent water quality monitoring system based on turbidity sensor, characterized in that: It includes data acquisition module, pre-processing module, preliminary evaluation module, comprehensive evaluation module and water quality prediction module; The data acquisition module is used to set up data acquisition nodes, and deploy turbidity sensors and intelligent water quality monitoring equipment groups at the data acquisition nodes, collect environmental data of the data acquisition nodes in real time, and construct an environmental data set S; The preprocessing module is used to preprocess the constructed environmental data set S; The preliminary evaluation module is used to obtain the turbidity variation coefficient according to the turbidity data set in the environmental data set S. , combined with the preset turbidity change threshold , assess changes in water quality; The comprehensive evaluation module is used to obtain the particle dynamic index KL and the pollution index WR based on the particle data group and the organic pollutant data group in the environmental data set S, and combined with the turbidity change threshold , obtain the comprehensive water quality score Q, and compare and analyze the comprehensive water quality score Q with the water quality threshold W to evaluate the water quality status; The water quality prediction module is used to construct a water quality prediction model, obtain the comprehensive water quality score Q(t+k) at a future time point (t+k), and obtain the normal fluctuation range of water quality in combination with historical environmental data. , the comprehensive water quality score Q(t+k) and the normal fluctuation range of water quality Conduct comparative analysis and regulate water quality.

2. The intelligent water quality monitoring system based on turbidity sensor according to claim 1 is characterized in that: The data acquisition module includes a turbidity data acquisition unit, a particulate matter data acquisition unit and an organic pollutant data acquisition unit; The turbidity data acquisition unit is used to deploy turbidity sensors and intelligent water quality monitoring equipment groups in the water area to be tested, and set the data acquisition time interval to , use the turbidity sensor to emit laser to the water area to be tested, monitor the scattered light signal of the laser, and convert the scattered light signal into an electrical signal to obtain the turbidity data of the water area to be tested, construct a turbidity data group, and transmit the constructed turbidity data group to the data processing center through the wireless network device on the turbidity sensor.

3. The intelligent water quality monitoring system based on turbidity sensor according to claim 2 is characterized in that: The particle data collection unit is used to collect data based on the intelligent water quality monitoring equipment group of the water area to be tested, combined with the set data collection time interval , collect the particle data of the water area to be tested in real time and construct a particle data group; The organic pollutant data collection unit is used to collect the organic pollutant data of the water area to be tested in real time based on the intelligent water quality monitoring equipment group of the water area to be tested, and construct an organic pollutant data group; The constructed particulate matter data set and organic pollutant data set are transmitted to the data processing center, and the environmental data set S is constructed according to the turbidity data set, the particulate matter data set and the organic pollutant data set; The intelligent water quality monitoring equipment group includes a laser particle size analyzer, a COD online analyzer, an ultraviolet sensor, a TOC online analyzer and a DOC online detector.

4. The intelligent water quality monitoring system based on turbidity sensor according to claim 3 is characterized by: The preprocessing module is used to preprocess the environmental data set S, and the preprocessing steps include missing value processing, smoothing processing, outlier detection and elimination, and data normalization; The missing value processing is to fill the missing values ​​in the collected data using linear interpolation; The smoothing process is to use a sliding window to calculate the average value of each time point to reduce random fluctuations; The outlier detection and elimination is to perform statistical analysis on the collected data, identify outliers, and eliminate them; The data normalization refers to dimensionless processing of the collected data to eliminate the influence of different dimensions and normalize the data.

5. The intelligent water quality monitoring system based on turbidity sensor according to claim 4 is characterized in that: The preliminary evaluation module includes a turbidity data analysis unit and a turbidity data evaluation unit; The turbidity data analysis unit is used to perform summary calculation based on the turbidity data group in the pre-processed environmental data set S to obtain the turbidity change coefficient of each data collection node ; The turbidity variation coefficient The method of obtaining is: ； Where n is the total number of data collection times, is the turbidity value collected at the i-th time point, is the turbidity value collected at the i-1th time point, is the data collection time interval.

6. The intelligent water quality monitoring system based on turbidity sensor according to claim 5 is characterized in that: The turbidity data evaluation unit is used to preset the turbidity change threshold , and the turbidity variation coefficient obtained With the preset turbidity change threshold Conduct comparative analysis and evaluate water quality. The specific evaluation contents are as follows: If the turbidity variation coefficient Less than turbidity change threshold ,Right now When the water quality fluctuation is within the normal range, the normal turbidity data monitoring is maintained; If the turbidity variation coefficient Greater than or equal to the turbidity change threshold ,Right now When the water quality fluctuation is within the abnormal range, the data collection node where the water quality fluctuation is within the abnormal range is marked as an abnormal data collection node, and an alarm mechanism is triggered.

7. The intelligent water quality monitoring system based on turbidity sensor according to claim 6 is characterized by: The comprehensive evaluation module includes a data analysis unit and a secondary evaluation unit; The data analysis unit is used to perform summary analysis based on the particulate matter data group and the organic pollutant data group in the pre-processed environmental data set S to obtain the particulate matter dynamic index KL and the pollution index WR; The particle data group includes the volume proportion p of particles of different particle sizes in each data collection node; The volume proportion p of the particle size particles is measured by using a laser particle size analyzer to measure the particle size distribution, and the volume proportion of each type of particle size particles is calculated according to the particle size range; The organic pollutant data group includes the chemical oxygen demand COD, ultraviolet absorption value UV254, total organic carbon TOC and dissolved organic carbon content DOC of each data collection node; The chemical oxygen demand COD is obtained by a COD online analyzer; The ultraviolet absorption value UV254 is obtained by an ultraviolet sensor; The total organic carbon TOC is obtained by a TOC online analyzer; The dissolved organic carbon content DOC is obtained by a DOC online detector.

8. The intelligent water quality monitoring system based on turbidity sensor according to claim 7 is characterized in that: The secondary evaluation unit is used to obtain the particle dynamic index KL, pollution index WR and turbidity change coefficient. Perform summary calculations to obtain a comprehensive water quality score Q; The comprehensive water quality score Q is obtained as follows: ; Where α, β and γ are the particle dynamic index KL, pollution index WR and turbidity variation coefficient respectively. The weight coefficient of , c is the correction constant; The preset water quality threshold W is compared and analyzed with the comprehensive water quality score Q to evaluate the water quality status. The specific evaluation contents are as follows: If the comprehensive water quality score Q is less than the water quality threshold W, that is, Q<W, the water quality is judged to be within a safe range, the water quality changes are continuously monitored, and the water quality data is recorded to generate a water quality monitoring report, which is stored in the water quality monitoring data center; If the comprehensive water quality score Q is greater than or equal to the water quality threshold W, that is, Q≥W, the water quality is judged to be within the dangerous range, triggering the alarm mechanism, and marking the data collection nodes where the water quality is within the dangerous range. A distribution map of abnormal water quality areas is generated based on the marked data collection nodes, and the distribution map of abnormal water quality areas is sent to water quality monitoring personnel, and the water quality monitoring personnel are continuously warned until they respond.

9. The intelligent water quality monitoring system based on turbidity sensor according to claim 8, characterized in that: The water quality prediction module is used to predict the water quality status of data collection nodes whose water quality is within a safe range; The water quality prediction module includes a model building unit and an early warning unit; The model building unit is used to build a water quality prediction model based on an autoregressive integrated moving average algorithm, and extract historical environmental data from a water quality monitoring data center, use the extracted historical environmental data as training data to input the water quality prediction model, perform model training, and compare the predicted value of the water quality prediction model with the actual value in the historical environmental data to optimize the model; The early warning unit is used to input the real-time collected water quality data into the trained water quality prediction model to obtain the comprehensive water quality score Q(t+k) at the future time point (t+k), and compare the obtained comprehensive water quality score Q(t+k) with the normal fluctuation range of water quality obtained according to historical environmental data. Conduct comparative analysis to assess the water quality risk at a future time point (t+k). If the comprehensive water quality score Q(t+k) is not within the normal fluctuation range of water quality, If the water quality fluctuation at the future time point (t+k) is within t+k, it is determined that the water quality fluctuation is abnormal, triggering the early warning mechanism, and dispatching water quality monitoring personnel to the data collection node where the water quality fluctuation is abnormal to carry out water quality regulation.

10. An intelligent water quality monitoring method based on a turbidity sensor, used to implement an intelligent water quality monitoring system based on a turbidity sensor as described in any one of claims 1 to 9, characterized in that: The following steps are included: Step 1: Set up data collection nodes, deploy turbidity sensors and intelligent water quality monitoring equipment groups at the data collection nodes, collect environmental data of the data collection nodes in real time, and construct an environmental data set S; Step 2: preprocess the constructed environmental data set S; Step 3: Obtain the turbidity variation coefficient based on the turbidity data set in the environmental data set S , combined with the preset turbidity change threshold , assess changes in water quality; Step 4: Based on the particle data set and organic pollutant data set in the environmental data set S, obtain the particle dynamic index KL and the pollution index WR, and combine the turbidity change threshold , obtain the comprehensive water quality score Q, and compare and analyze the comprehensive water quality score Q with the water quality threshold W to evaluate the water quality status; Step 5: Build a water quality prediction model to obtain the comprehensive water quality score Q(t+k) at the future time point (t+k), and combine historical environmental data to obtain the normal fluctuation range of water quality , the comprehensive water quality score Q(t+k) and the normal fluctuation range of water quality Conduct comparative analysis and regulate water quality.

Images