Water quality monitoring data analysis method

By introducing rapid separation and decontamination mechanisms into the water quality monitoring equipment, the problem of filter plate blockage is solved, efficient water quality data collection and analysis is achieved, and the real-time and accuracy of water quality monitoring is improved.

CN118914489AInactive Publication Date: 2024-11-08SHANDONG GEO-SURVEYING & MAPPING INST
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202410958604.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-17
Publication Date
2024-11-08
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

During the filtration process of existing water quality monitoring equipment, the filter plate is prone to clogging, resulting in low filtration efficiency and inconvenient for real-time cleaning, affecting the accuracy of water quality data analysis.

Method used

The rapid separation mechanism and decontamination mechanism are adopted to drive the multi-layer filter bucket rotation and arc rack dirt push ring design through the motor to achieve rapid filtration and automatic cleaning, ensuring filtration efficiency and practicality.

Benefits of technology

It improves the water filtration efficiency and the practicality of the device, realizes the rapid and accurate collection and analysis of water quality data, and enhances the real-time and reliability of water quality monitoring.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118914489A_ABST
    Figure CN118914489A_ABST
Patent Text Reader

Abstract

The invention discloses a water quality monitoring data analysis method, which comprises a water quality data acquisition module, a water quality data processing module, a water quality data feature extraction module, a water quality monitoring model training module and a model application display module. Then, the water quality monitoring model is used for performing water quality prediction and analysis on real-time water quality monitoring data, the model can predict the future water quality change trend through a prediction algorithm based on historical data and real-time data, potential influence factors are analyzed, the effect of rapidly detecting the water quality is achieved, a rapid separation mechanism is arranged, and the water quality detection efficiency is improved. The motor is used for driving the multi-layer filter cone to rotate, water is rapidly filtered through centrifugal force, the water filtering efficiency is improved, meanwhile, by arranging the dirt removing mechanism, under the action of an arc-shaped rack, reciprocating movement of a dirt pushing ring is achieved, dirt in the multi-layer filter cone is pushed out, and the filtering efficiency of the multi-layer filter cone is guaranteed.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of water quality monitoring, and more specifically, to a water quality monitoring data analysis method. Background Art

[0002] Water quality monitoring data analysis involves multiple aspects to assess the quality of water bodies, detect potential pollution problems and support water resource management and protection. The following are the main aspects of water quality monitoring data analysis:

[0003] Analysis of basic water quality parameters: pH value: measures the acidity and alkalinity of water. Dissolved oxygen (DO): reflects the ability of water to support organisms. Temperature: affects the rate of biological and chemical reactions in water. Conductivity: reflects the concentration of solutes in water.

[0004] Pollutant concentration analysis: monitors the concentration of harmful substances such as heavy metals, organic matter, nutrients, etc. Including measuring the concentration of chemical substances such as ammonia nitrogen, nitrite, nitrate, etc.

[0005] Biological indicator analysis: Use biological indicators (such as algae, plankton, benthic organisms) to assess the health of aquatic ecosystems.

[0006] Water quality monitoring data analysis is an integrated process that combines multiple disciplines such as chemistry, biology, geosciences, and information technology to fully understand and manage water quality.

[0007] The document with prior art publication number CN219179383U provides an online monitoring device for discharge water quality. The device filters the sewage before the monitoring instrument body extracts, analyzes and monitors it to prevent granular diatoms and sand mixed in the sewage from entering the curved pipe, thereby preventing the monitoring instrument body from being unable to be used normally due to blockage. This design can not only extend the service life of the monitoring instrument body, but also reduce the impact of impurities on water quality data analysis.

[0008] Although the above-mentioned prior art solution can achieve the relevant beneficial effects through the structure of the prior art, it still has the following defects: when the device is used, the water to be tested is filtered through the filter plate, but the filtering method is simple and it is not convenient to clean the filter plate in real time, resulting in clogging of the filter plate, affecting the filtering efficiency, and having poor practicality.

[0009] In view of this, we propose a water quality monitoring data analysis method. Summary of the invention

[0010] 1. Technical issues to be solved

[0011] The purpose of the present application is to provide a water quality monitoring data analysis method, which solves the technical problems raised in the above-mentioned background technology and achieves the technical effect of facilitating real-time cleaning of the filter plate.

[0012] 2. Technical solution

[0013] The present invention provides a method for analyzing water quality monitoring data, comprising the following steps:

[0014] S1. Water quality data acquisition module: The water quality data acquisition module collects water quality data from the water to be monitored through sensor equipment, including various chemical parameters, etc.;

[0015] S2, water quality data processing module: the water quality data processing module cleans, organizes and standardizes the collected data, including removing abnormal values, missing values ​​and error values, and converting all data into a unified standard for subsequent processing;

[0016] S3, water quality data feature extraction module: the water quality data feature extraction module extracts features related to water quality from the preprocessed data, such as statistical features such as the average value, maximum value, minimum value, etc. of various water quality parameters, and relationship features between water quality parameters and other environmental parameters;

[0017] S4, water quality monitoring model training module: the water quality monitoring model training module selects a suitable machine learning model for monitoring water quality according to the water quality monitoring problem to be solved;

[0018] S5. Model application display module: The model application display module applies the trained model to real-time water quality monitoring data, performs water quality prediction and analysis, and visualizes the analysis results.

[0019] As an optional solution of the technical solution of the present application document, the water quality data acquisition module collects water quality data, including various chemical parameters, from the water to be monitored through sensor equipment, measures the acidity and alkalinity of the water through a pH sensor to understand the chemical properties of the water body, measures the organic matter content in the water through a total organic carbon (TOC) sensor to understand the organic matter pollution of the water body, and uses a heavy metal sensor to measure the heavy metal content in the water to understand the heavy metal pollution of the water body, etc.

[0020] As an optional solution of the technical solution of this application document, the water quality data processing module cleans, organizes and standardizes the collected data, including removing outliers, missing values ​​and erroneous values, and converting all data into a unified standard for subsequent processing. The data cleaning: for the processing of outliers, statistical methods such as box plots can be considered to identify and delete outliers, and for the processing of missing values, interpolation can be used to fill them;

[0021] The data collation: normalizing the collected data and converting all the data into the same unit and dimension;

[0022] Standardization: Standardization involves scaling the data to have zero mean and unit variance, which helps eliminate scale differences between data and makes comparisons between different features fairer.

[0023] As an optional solution of the technical solution of this application document, the water quality data feature extraction module extracts features related to water quality from the preprocessed data, such as statistical features such as the average value, maximum value, minimum value, etc. of various water quality parameters, and relationship features between water quality parameters and other environmental parameters. The statistical feature extraction: extracts statistical features such as the average value, maximum value, minimum value, etc. of various water quality parameters from the preprocessed water quality data. The statistical features can reflect the overall status and change trend of water quality;

[0024] The relationship feature extraction: analyzing the relationship features between water quality parameters and other environmental parameters, for example, being able to calculate the correlation coefficient between water quality parameters and other environmental parameters, etc., to reveal the relationship and influence between them.

[0025] As an optional solution to the technical solution of the present application document, the water quality monitoring model training module selects a regression model according to the water quality monitoring problem to be solved: it is used to predict the numerical value of water quality indicators. By training the regression model, a quantitative relationship between water quality indicators and environmental factors can be established, thereby predicting the changing trend of water quality and realizing water quality monitoring.

[0026] As an optional solution of the technical solution of this application document, the model application display module applies the trained machine learning model to real-time water quality monitoring data to perform water quality prediction and analysis. The model can predict future water quality change trends based on historical data and real-time data through prediction algorithms, analyze potential influencing factors, and visualize the analysis results to intuitively display water quality conditions and water quality prediction results. The visualization technology can include charts, etc., to help users better understand and analyze water quality data.

[0027] 3. Beneficial effects

[0028] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0029] 1. Since the present application adopts technical means such as a water quality data acquisition module, it effectively solves the technical problems in the prior art, and further realizes that after the water to be tested is filtered, multi-faceted data on water quality is collected through the water quality data acquisition module. Then the water quality monitoring model is used for real-time water quality monitoring data to predict and analyze water quality. The model can predict future water quality change trends based on historical data and real-time data through a prediction algorithm, and analyze potential influencing factors to achieve the effect of rapid water quality detection.

[0030] 2. This application improves the filtration efficiency of water by setting up a quick separation mechanism, using a motor to drive the multi-layer filter bucket to rotate, and quickly filtering the water through centrifugal force. At the same time, by setting up a dirt removal mechanism, under the action of the arc-shaped rack, the dirt pushing ring is moved back and forth, thereby pushing out the dirt in the multi-layer filter bucket, thereby ensuring the filtration efficiency of the multi-layer filter bucket.

[0031] 3. This application realizes the automation of the device by setting a contact rod and cooperating with a spring to automatically drive the opening and closing of the valve core. By setting a dirt pusher plate, the dirt in the water treatment box can be quickly cleaned, thereby improving the practicality of the device. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 A schematic diagram of the overall structure of a water quality monitoring data analysis method disclosed in a preferred embodiment of the present application and a water quality monitoring process;

[0033] Figure 2 This is a schematic diagram of the overall structure of a water quality monitoring data analysis method disclosed in a preferred embodiment of the present application;

[0034] Figure 3 A schematic cross-sectional view of the overall structure of a water quality monitoring data analysis method disclosed in a preferred embodiment of the present application;

[0035] Figure 4 A schematic cross-sectional view of a box cover and other structures of a water quality monitoring data analysis method disclosed in a preferred embodiment of the present application;

[0036] Figure 5 A schematic cross-sectional view of a water treatment box structure of a water quality monitoring data analysis method disclosed in a preferred embodiment of the present application;

[0037] Figure 6 A schematic cross-sectional view of the structure of a rapid separation mechanism and a decontamination mechanism of a water quality monitoring data analysis method disclosed in a preferred embodiment of the present application;

[0038] Explanation of the numbers in the figure: 1. Water treatment box; 2. Box cover; 3. Water inlet pipe; 4. Quick separation mechanism; 5. Dirt removal mechanism; 101. Dirt guide chute; 102. Dirt push plate; 103. Adjusting wheel; 104. Ring rack; 301. Valve body; 302. Valve core; 303. Opening and closing wheel; 201. Contact rod; 202. Rack; 203. Spring; 204. Arc rack; 401. Drain seat; 402. Driven wheel; 403. Driving wheel; 404. Motor; 405. Multi-layer filter bucket; 501. Reciprocating screw rod; 502. Dirt push ring; 503. Transmission wheel. DETAILED DESCRIPTION

[0039] The present application is further described in detail below in conjunction with the accompanying drawings.

[0040] Reference Figure 1 , a water quality monitoring data analysis method, comprising the following steps:

[0041] S1. Water quality data acquisition module: The water quality data acquisition module collects water quality data from the water to be monitored through sensor equipment, including various chemical parameters, etc.;

[0042] S2, water quality data processing module: The water quality data processing module cleans, organizes and standardizes the collected data, including removing outliers, missing values ​​and error values, and converting the data into a unified standard for subsequent processing;

[0043] S3, water quality data feature extraction module: the water quality data feature extraction module extracts features related to water quality from the preprocessed data, such as statistical features such as the average value, maximum value, minimum value, etc. of various water quality parameters, as well as the relationship features between water quality parameters and other environmental parameters;

[0044] S4, water quality monitoring model training module: the water quality monitoring model training module selects a suitable machine learning model for monitoring water quality according to the water quality monitoring problem to be solved;

[0045] S5. Model application display module: The model application display module applies the trained model to real-time water quality monitoring data to perform water quality prediction and analysis, and visualizes the analysis results.

[0046] The water quality data acquisition module collects water quality data from the monitored water through sensor equipment, including various chemical parameters, etc. Through the pH sensor: measure the acidity and alkalinity in the water to understand the chemical properties of the water body, through the total organic carbon TOC sensor: measure the organic matter content in the water to understand the organic pollution of the water body, and use the heavy metal sensor: measure the heavy metal content in the water to understand the heavy metal pollution of the water body, etc.

[0047] The water quality data processing module cleans, organizes and standardizes the collected data, including removing outliers, missing values ​​and erroneous values, and converting the data into a unified standard for subsequent processing. Data cleaning: For outlier processing, statistical methods such as box plots can be considered to identify and delete outliers. For missing values, interpolation can be used to fill them.

[0048] Data collation: Normalize the collected data and convert them into the same units and dimensions;

[0049] Standardization: Standardization involves scaling the data to have zero mean and unit variance, which helps eliminate scale differences between data and makes comparisons between different features fairer.

[0050] The water quality data feature extraction module extracts water quality-related features from the preprocessed data, such as the average, maximum, minimum and other statistical features of various water quality parameters, as well as the relationship features between water quality parameters and other environmental parameters. Statistical feature extraction: extracts the average, maximum, minimum and other statistical features of various water quality parameters from the preprocessed water quality data. The statistical features can reflect the overall status and changing trend of water quality.

[0051] Relationship feature extraction: Analyze the relationship characteristics between water quality parameters and other environmental parameters. For example, the correlation coefficient between water quality parameters and other environmental parameters can be calculated to reveal the relationship and influence between them.

[0052] The water quality monitoring model training module selects a regression model based on the water quality monitoring problem that needs to be solved: it is used to predict the values ​​of water quality indicators. By training the regression model, a quantitative relationship between water quality indicators and environmental factors can be established, thereby predicting the changing trend of water quality and realizing water quality monitoring.

[0053] The model application display module applies the trained machine learning model to real-time water quality monitoring data to predict and analyze water quality. The model can predict future water quality trends based on historical data and real-time data through prediction algorithms, analyze potential influencing factors, and visualize the analysis results to intuitively display water quality conditions and water quality prediction results. Visualization technology can include charts, etc. to help users better understand and analyze water quality data.

[0054] Reference Figure 2 and Figure 3 A water quality monitoring data analysis method includes a water treatment box 1, a box cover 2, a water inlet pipe 3, a quick separation mechanism 4, and a decontamination mechanism 5.

[0055] A box cover 2 is movably connected to the water treatment box 1, a water inlet pipe 3 is fixedly connected to the box cover 2, a quick separation mechanism 4 is rotatably connected to the water treatment box 1, and a dirt removal mechanism 5 is rotatably connected to the quick separation mechanism 4.

[0056] Reference Figure 5 A sewage guide groove 101 is fixedly connected to the inner wall of the water treatment box 1, a sewage pushing plate 102 is slidably provided in the water treatment box 1, and an adjusting wheel 103 is rotatably connected to the inner wall of one side of the water treatment box 1, and the adjusting wheel 103 is meshed with an annular rack 104 connected to the sewage pushing plate 102 for transmission.

[0057] Reference Figure 4 One end of the water inlet pipe 3 is connected and fixedly provided with a valve body 301, a valve core 302 is rotatably connected and provided inside the valve body 301, and one end of the valve core 302 extends to the outside of the valve body 301 and is connected and fixedly provided with an opening and closing wheel 303.

[0058] A contact rod 201 is provided on the box cover 2 for sliding fit, one end of which is fixedly connected to a rack 202 , which is meshed and driven with an opening and closing wheel 303 , and one end of the contact rod 201 is connected to the box cover 2 via a spring 203 .

[0059] Reference Figure 6 The quick separation mechanism 4 includes a drain seat 401, one end of which is rotatably connected to the water treatment box 1, a driven wheel 402 is fixedly connected to the outer end of the drain seat 401, a driving wheel 403 is meshed and driven on one side of the driven wheel 402, a motor 404 is fixedly connected to the driving wheel 403, the motor 404 is fixedly connected to the water treatment box 1, and a multi-layer filter 405 is movably inserted in the drain seat 401. Multiple sensors are installed in the output end of the drain seat 401.

[0060] The dirt removal mechanism 5 includes a plurality of reciprocating screw rods 501, which are rotatably connected to the multi-layer filter bucket 405, a dirt pushing ring 502 is threadedly connected to the outer wall of the reciprocating screw rod 501, a transmission wheel 503 is fixedly connected to one end of the reciprocating screw rod 501, a plurality of arc-shaped racks 204 are fixedly connected to the bottom of the box cover 2, the arc-shaped racks 204 are meshed with the transmission wheel 503 for transmission, and one of the dirt pushing rings 502 is movably contacted with the contact rod 201.

[0061] The implementation principle of a water quality monitoring data analysis method in the embodiment of the present application is as follows: when it is necessary to monitor and analyze the water quality, it is first necessary to filter out the larger impurities in the water, inject the water into the multi-layer filter bucket 405 through the water inlet pipe 3, and then use the motor 404 to drive the driving wheel 403 to rotate, so that the driving wheel 403 drives the drainage seat 401 connected to the driven wheel 402 to rotate, and at this time the drainage seat 401 will simultaneously drive the multi-layer filter bucket 405 to rotate, so as to quickly separate the water;

[0062] At this time, under the action of the arc-shaped rack 204, the reciprocating screw 501 connected to the transmission wheel 503 will rotate, so that the reciprocating screw 501 drives the dirt pushing ring 502 to move upward, and the dirt in the multi-layer filter bucket 405 is pushed out. Then, under the action of centrifugal force, the dirt will fall onto the dirt guide groove 101, and then the dirt pushing plate 102 connected to the annular rack 104 will rotate by rotating the adjusting wheel 103, so as to push out the dirt, and then the filtered water will be discharged for monitoring;

[0063] The water quality data acquisition module collects water quality data from the monitored water through sensor equipment, including various chemical parameters, etc. Through the pH sensor: measure the acidity and alkalinity in the water to understand the chemical properties of the water body, through the total organic carbon TOC sensor: measure the organic matter content in the water to understand the organic matter pollution of the water body, and use the heavy metal sensor: measure the heavy metal content in the water to understand the heavy metal pollution of the water body, etc.;

[0064] The water quality data processing module is used to clean, organize and standardize the collected data, including removing outliers, missing values ​​and erroneous values, and converting the data into a unified standard for subsequent processing. Data cleaning: For the processing of outliers, statistical methods such as box plots can be considered to identify and delete outliers. For the processing of missing values, interpolation methods can be used to fill them.

[0065] Data collation: Normalize the collected data and convert them into the same units and dimensions;

[0066] Standardization: Standardization involves scaling the data to have zero mean and unit variance, which helps eliminate scale differences between data and makes comparisons between different features fairer;

[0067] The water quality data feature extraction module extracts water quality-related features from the preprocessed data, such as the average, maximum, minimum and other statistical features of various water quality parameters, as well as the relationship features between water quality parameters and other environmental parameters. Statistical feature extraction: The statistical features such as the average, maximum, minimum and other statistical features of various water quality parameters are extracted from the preprocessed water quality data. The statistical features can reflect the overall status and changing trend of water quality.

[0068] Relationship feature extraction: Analyze the relationship characteristics between water quality parameters and other environmental parameters. For example, the correlation coefficient between water quality parameters and other environmental parameters can be calculated to reveal the relationship and influence between them.

[0069] Use the water quality monitoring model training module to select a regression model based on the water quality monitoring problem that needs to be solved: it is used to predict the values ​​of water quality indicators. By training the regression model, the quantitative relationship between water quality indicators and environmental factors can be established, thereby predicting the changing trend of water quality and realizing water quality monitoring;

[0070] The model application display module applies the trained machine learning model to real-time water quality monitoring data to predict and analyze water quality. The model can predict future water quality trends based on historical data and real-time data through prediction algorithms, analyze potential influencing factors, and visualize the analysis results to intuitively display water quality conditions and water quality prediction results. Visualization technology can include charts, etc. to help users better understand and analyze water quality data.

Claims

1. A water quality monitoring data analysis method, comprising the following steps: S1. Water quality data acquisition module: The water quality data acquisition module collects water quality data from the water to be monitored through sensor equipment, including various chemical parameters, etc.; S2, water quality data processing module: the water quality data processing module cleans, organizes and standardizes the collected data, including removing abnormal values, missing values ​​and error values, and converting all data into a unified standard for subsequent processing; S3, water quality data feature extraction module: the water quality data feature extraction module extracts features related to water quality from the preprocessed data, such as statistical features such as the average value, maximum value, minimum value, etc. of various water quality parameters, and relationship features between water quality parameters and other environmental parameters; S4, water quality monitoring model training module: the water quality monitoring model training module selects a suitable machine learning model for monitoring water quality according to the water quality monitoring problem to be solved; S5. Model application display module: The model application display module applies the trained model to real-time water quality monitoring data, performs water quality prediction and analysis, and visualizes the analysis results.

2. The water quality monitoring data analysis method according to claim 1, characterized in that: The water quality data acquisition module collects water quality data from the monitored water through sensor equipment, including various chemical parameters, etc. Through the pH sensor: measure the acidity and alkalinity in the water to understand the chemical properties of the water body, through the total organic carbon sensor: measure the organic matter content in the water to understand the organic matter pollution of the water body, and use the heavy metal sensor: measure the heavy metal content in the water to understand the heavy metal pollution of the water body, etc.

3. The water quality monitoring data analysis method according to claim 1, characterized in that: The water quality data processing module cleans, organizes and standardizes the collected data, including removing outliers, missing values ​​and erroneous values, and converting all data into a unified standard for subsequent processing. The data cleaning module: for outlier processing, statistical methods such as box plots can be considered to identify and delete outliers, and for missing values, interpolation can be used to fill them. The data collation: normalizing the collected data and converting all the data into the same unit and dimension; Standardization: Standardization involves scaling the data to have zero mean and unit variance, which helps eliminate scale differences between data and makes comparisons between different features fairer.

4. The water quality monitoring data analysis method according to claim 1, characterized in that: The water quality data feature extraction module extracts features related to water quality from the pre-processed data, such as statistical features such as the average value, maximum value, minimum value, etc. of various water quality parameters, and relationship features between water quality parameters and other environmental parameters. The statistical feature extraction: extracts statistical features such as the average value, maximum value, minimum value, etc. of various water quality parameters from the pre-processed water quality data. The statistical features can reflect the overall status and change trend of water quality; The relationship feature extraction: analyzing the relationship features between water quality parameters and other environmental parameters, for example, being able to calculate the correlation coefficient between water quality parameters and other environmental parameters, etc., to reveal the relationship and influence between them.

5. The water quality monitoring data analysis method according to claim 1, characterized in that: The water quality monitoring model training module selects a regression model according to the water quality monitoring problem to be solved: it is used to predict the values ​​of water quality indicators. By training the regression model, a quantitative relationship between water quality indicators and environmental factors can be established, thereby predicting the changing trend of water quality and realizing water quality monitoring.

6. The water quality monitoring data analysis method according to claim 1, characterized in that: The model application display module applies the trained machine learning model to real-time water quality monitoring data to perform water quality prediction and analysis. The model can predict future water quality change trends based on historical data and real-time data through prediction algorithms, analyze potential influencing factors, and visualize the analysis results to intuitively display water quality conditions and water quality prediction results. Visualization technology can include charts, etc. to help users better understand and analyze water quality data.

Citation Information

Patent Citations

  • Discharge water quality on-line monitoring equipment

    CN219179383U