Water conservancy business processing internet-of-things system and method
By deploying water quality sensors and machine learning models in the water conservancy business treatment Internet of Things system, real-time monitoring and early warning of water quality is achieved, the shortcomings in existing systems in water quality monitoring are solved, and the management efficiency and pollution control capabilities of water conservancy facilities are improved.
Patent Information
- Application Number
- CN202410958653.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-17
- Publication Date
- 2024-11-26
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing water conservancy business treatment IoT system has shortcomings in real-time monitoring of water quality, which leads to the possibility of polluted water sources flowing into farmland and fishery aquaculture areas, causing pollution and poor practicality.
A water conservancy business treatment Internet of Things system was designed, including water quality data acquisition module, pretreatment module, feature extraction module, detection model training module and remote monitoring and early warning control module. Water quality sensors are deployed through Internet of Things technology to collect and pre-process data. Use machine learning algorithms to build a water quality detection model, monitor and warning in real time, and control water conservancy equipment remotely.
Real-time monitoring and early warning of water quality is achieved, the inflow of harmful substances and sewage is reduced, the service life and operation and maintenance efficiency of water conservancy facilities are improved, and the real-time management capabilities of water quality are enhanced.
Smart Images

Figure CN119031015A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of water conservancy business processing, and more specifically, to an Internet of Things system and method for water conservancy business processing. Background Art
[0002] In the field of water conservancy business processing technology, the application of Internet of Things technology plays an important role in real-time monitoring, data collection, remote control and intelligent decision-making. The following are some key aspects of the Internet of Things related to water conservancy business processing:
[0003] Sensor network: Deploy various sensors, such as water quality sensors, water level sensors, flow sensors, etc., to build a sensor network to monitor various parameters of the water body in real time.
[0004] Data collection and communication: Use IoT technology to realize real-time collection and transmission of water conservancy facility data, ensuring that data such as water level, water quality, and flow can be uploaded to the cloud platform or data center in a timely and reliable manner.
[0005] Remote monitoring and control: Based on the Internet of Things platform, remote monitoring and control of water conservancy facilities can be achieved, including remote valve switching, adjustment of water pump operating status, etc., to improve operation and maintenance efficiency.
[0006] The document with prior art publication number CN108625344A provides a water conservancy flood control rapid gate with an Internet of Things early warning function. The device transmits the gate vibration frequency data received by the vibration sensor to a remote controller through the GPRS network and the communication PC under the action of the Internet of Things early warning system. When the signal data does not meet the set value, the system will issue an alarm to realize online real-time monitoring and early warning functions, making maintenance more timely and improving the service life of the gate.
[0007] 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, it is not convenient to monitor the water quality in real time, resulting in polluted water sources flowing into farmland and fishery breeding areas, causing pollution, and poor practicality.
[0008] In view of this, we propose an Internet of Things system and method for water conservancy business processing. Summary of the invention
[0009] 1. Technical problems to be solved
[0010] The purpose of this application is to provide an Internet of Things system and method for water conservancy business processing, which solves the technical problems raised in the above-mentioned background technology and achieves the technical effect of facilitating real-time monitoring of water quality.
[0011] 2. Technical solution
[0012] The embodiment of the present application provides an Internet of Things system and method for water conservancy business processing, including: a water quality data acquisition module, a water quality data preprocessing module, a water quality data feature extraction module, a water quality status detection model training module, and a remote monitoring and early warning control module.
[0013] Water quality data collection module: The water quality data collection module deploys water quality sensors, water level sensors, etc. in the water body, and collects water quality data through the Internet of Things connection;
[0014] Water quality data preprocessing module: The water quality data preprocessing module performs preprocessing operations on the collected raw data to improve the accuracy and reliability of the data;
[0015] Water quality data feature extraction module: The water quality data feature extraction module extracts features related to water quality from the processed data, such as the values of various water quality parameters and their changing trends;
[0016] Water quality condition detection model training module: The water quality condition detection model training module uses a machine learning algorithm to build a prediction model to predict water quality conditions based on the extracted features;
[0017] Remote monitoring and early warning control module: The remote monitoring and early warning control module automatically uploads the collected data to the cloud platform through the Internet of Things technology to monitor the water quality in real time.
[0018] As an optional solution to the technical solution of this application document, the water quality data acquisition module deploys water quality sensors, water level sensors, etc. in the water body, and collects water quality data through the Internet of Things connection, including measuring various water quality parameters, such as dissolved oxygen, pH value, turbidity, conductivity and other data, by connecting the water quality sensors and water level sensors to the Internet of Things so that data can be remotely collected and transmitted.
[0019] As an optional solution of the technical solution of this application document, the water quality data preprocessing module performs preprocessing operations on the collected raw data to improve the accuracy and reliability of the data, including data cleaning, data standardization, and data smoothing. The data cleaning includes deleting or filling missing values, deleting outliers, processing duplicate data, etc., to ensure the integrity and consistency of the data set;
[0020] The data standardization is to convert the data into a unified standard to eliminate the deviation caused by factors such as data dimension and order of magnitude;
[0021] The data smoothing: uses a mean filtering technique to remove noise and fluctuations in the data to reduce the impact of random errors and outliers on the analysis results.
[0022] As an optional solution of the technical solution of the present application document, the water quality data feature extraction module extracts features related to water quality from the processed data, such as the values of various water quality parameters and their changing trends, including the values, changing trends, and spatial distribution of water quality parameters. The values of the water quality parameters: the values of water quality parameters can reflect the quality of water, such as pH value, dissolved oxygen, nitrate, ammonia nitrogen, etc. The values of these parameters can be used to describe the chemical and biological properties of water;
[0023] The change trend: by analyzing the change trend of water quality parameters, it is possible to understand the change of water quality. For example, if the value of the water quality parameter is gradually decreasing, it may mean that the water quality is gradually getting worse; conversely, if the value of the water quality parameter is gradually increasing, it may mean that the water quality is gradually improving;
[0024] The spatial distribution: The water quality data obtained at multiple monitoring points can reflect the spatial distribution of water quality. For example, some pollutants may have higher concentrations in some areas and lower concentrations in other areas. By analyzing these spatial distribution data, the source and diffusion of pollutants can be understood.
[0025] As an optional solution to the technical solution of this application document, the water quality condition detection model training module uses the machine learning algorithm of the support vector machine to build a prediction model to predict the water quality condition based on the extracted features, classify the water quality status, deploy the model to the system, and predict new data in real time.
[0026] As an optional solution to the technical solution of this application document, the remote monitoring and early warning control module automatically uploads the collected data to the cloud platform through the Internet of Things technology to monitor the water quality conditions in real time, and conducts real-time analysis of the water quality data through the water quality condition detection model. When abnormal water quality is found, the system can automatically issue an early warning signal to remind the user to take timely measures and remotely control the switching of water conservancy equipment.
[0027] A water conservancy business processing Internet of Things system and method, comprising the following steps:
[0028] S1. When it is necessary to test the water quality of water in water conservancy canals, water quality sensors and water level sensors are deployed in the water body and connected through the Internet of Things to collect water quality data, including measuring various water quality parameters, such as dissolved oxygen, pH value, turbidity, conductivity and other data. Water quality sensors and water level sensors are connected to the Internet of Things so that data can be collected and transmitted remotely.
[0029] S2. Use the water quality data preprocessing module to preprocess the collected raw data to improve the accuracy and reliability of the data, including data cleaning, data standardization, data smoothing, data cleaning: delete or fill missing values, delete outliers, process duplicate data, etc., to ensure the integrity and consistency of the data set;
[0030] Data standardization: converting data into a unified standard to eliminate deviations caused by factors such as data dimension and magnitude;
[0031] Data smoothing: Use mean filtering to remove noise and fluctuations in the data to reduce the impact of random errors and outliers on the analysis results;
[0032] S3. Extract water quality-related features from the processed data through the water quality data feature extraction module, such as the values of various water quality parameters and their changing trends, including the values, changing trends, and spatial distribution of water quality parameters. The values of water quality parameters can reflect the quality of water, such as pH value, dissolved oxygen, nitrate, ammonia nitrogen, etc. The values of these parameters can be used to describe the chemical and biological characteristics of water;
[0033] Change trend: By analyzing the change trend of water quality parameters, we can understand the change of water quality. For example, if the value of water quality parameters is gradually decreasing, it may mean that the water quality is gradually getting worse; on the contrary, if the value of water quality parameters is gradually increasing, it may mean that the water quality is gradually improving.
[0034] Spatial distribution: Water quality data obtained at multiple monitoring points can reflect the spatial distribution of water quality. For example, some pollutants may have higher concentrations in some areas and lower concentrations in other areas. By analyzing these spatial distribution data, we can understand the source and diffusion of pollutants.
[0035] S4. Use the machine learning algorithm of support vector machine through the water quality detection model training module to build a prediction model to predict the water quality status based on the extracted features, classify the water quality status, deploy the model into the system, and predict new data in real time;
[0036] S5. Use the remote monitoring and early warning control module through the Internet of Things technology to automatically upload the collected data to the cloud platform to monitor the water quality in real time. Through the water quality detection model, the water quality data is analyzed in real time. When abnormal water quality is found, the system can automatically send out an early warning signal to remind users to take timely measures and remotely control the switch of water conservancy equipment.
[0037] 3. Beneficial effects
[0038] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
[0039] 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 during the use of the water conservancy canal gate, the sensor is placed in the water in the canal through a transmission detection mechanism to collect water quality data, and the water quality is analyzed through a water quality status detection model. Through the Internet of Things technology, the collected data is automatically uploaded to the cloud platform. When abnormal water quality is found, the system can automatically send out an early warning signal to remind the user to take timely measures, remotely control the opening and closing of the water conservancy canal gate, reduce the flow of sewage with harmful substances, and achieve real-time monitoring of water quality.
[0040] 2. This application arranges a rack on the gate, so that the transmission detection mechanism can be moved out and stored while the gate is opened and closed, and the water quality is automatically monitored in real time, thereby achieving the automation effect of the device. By arranging a protective cover with a spring, it not only protects the cleaning mechanism, but also facilitates opening for maintenance.
[0041] 3. This application sets up a cleaning mechanism. After the water quality is detected by the sensor, after the sensor is placed in the cleaning brush cover, the cleaning brush cover is rotated by the motor. At the same time, the pump body sucks the cleaning liquid and sprays it on the sensor to clean the dirt attached to the outer wall of the sensor, thereby ensuring the measurement accuracy of the sensor and improving the practicability of the device. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] Figure 1 A schematic diagram of the overall structure of a water quality monitoring process of an Internet of Things system and method for water conservancy business processing disclosed in a preferred embodiment of the present application;
[0043] Figure 2 This is a schematic diagram of the overall structure of a water conservancy business processing Internet of Things system and method disclosed in a preferred embodiment of the present application;
[0044] Figure 3 A schematic diagram of a gate structure of a water conservancy business processing Internet of Things system and method disclosed in a preferred embodiment of the present application;
[0045] Figure 4 A schematic diagram of the structure of a fixed base of a water conservancy business processing Internet of Things system and method disclosed in a preferred embodiment of the present application;
[0046] Figure 5 A schematic diagram of the structure of a transmission detection mechanism of a water conservancy business processing Internet of Things system and method disclosed in a preferred embodiment of the present application;
[0047] Figure 6 A schematic cross-sectional view of the cleaning mechanism structure of a water conservancy business processing Internet of Things system and method disclosed in a preferred embodiment of the present application;
[0048] Explanation of the numbers in the figure: 1. Gate frame; 2. Gate; 3. Fixed seat; 4. Transmission detection mechanism; 5. Cleaning mechanism; 201. Electric push rod; 202. Rack; 301. Cleaning liquid storage box; 302. Protective cover; 303. Spring; 401. Mounting seat; 402. Adjusting rod group; 403. Worm gear; 404. Worm; 405. Universal joint; 406. Gear; 501. Motor; 502. Driving wheel; 503. Driven wheel; 504. Liquid guide tube; 505. Cleaning brush cover; 506. Pump body. DETAILED DESCRIPTION
[0049] The present application is further described in detail below in conjunction with the accompanying drawings.
[0050] Reference Figure 1 , a water conservancy business processing Internet of Things system and method, including: a water quality data acquisition module, a water quality data preprocessing module, a water quality data feature extraction module, a water quality status detection model training module, and a remote monitoring and early warning control module,
[0051] Water quality data collection module: The water quality data collection module deploys water quality sensors, water level sensors, etc. in the water body, and collects water quality data through the Internet of Things connection;
[0052] Water quality data preprocessing module: The water quality data preprocessing module performs preprocessing operations on the collected raw data to improve the accuracy and reliability of the data;
[0053] Water quality data feature extraction module: The water quality data feature extraction module extracts water quality-related features from the processed data, such as the values of various water quality parameters and their changing trends;
[0054] Water quality condition detection model training module: The water quality condition detection model training module uses machine learning algorithms to build a prediction model to predict water quality conditions based on the extracted features;
[0055] Remote monitoring and early warning control module: The remote monitoring and early warning control module automatically uploads the collected data to the cloud platform through the Internet of Things technology to monitor the water quality in real time.
[0056] The water quality data acquisition module deploys water quality sensors, water level sensors, etc. in the water body, and collects water quality data through the Internet of Things connection, including measuring various water quality parameters, such as dissolved oxygen, pH value, turbidity, conductivity and other data. By connecting the water quality sensors and water level sensors to the Internet of Things, data can be collected and transmitted remotely.
[0057] The water quality data preprocessing module performs preprocessing operations on the collected raw data to improve the accuracy and reliability of the data, including data cleaning, data standardization, data smoothing, data cleaning: deleting or filling missing values, deleting outliers, processing duplicate data, etc., to ensure the integrity and consistency of the data set;
[0058] Data standardization: converting data into a unified standard to eliminate deviations caused by factors such as data dimension and magnitude;
[0059] Data smoothing: Use mean filtering to remove noise and fluctuations in the data to reduce the impact of random errors and outliers on the analysis results.
[0060] The water quality data feature extraction module extracts water quality-related features from the processed data, such as the values of various water quality parameters and their changing trends, including the values, changing trends, and spatial distribution of water quality parameters. The values of water quality parameters can reflect the quality of water, such as pH value, dissolved oxygen, nitrate, ammonia nitrogen, etc. The values of these parameters can be used to describe the chemical and biological characteristics of water;
[0061] Change trend: By analyzing the change trend of water quality parameters, we can understand the change of water quality. For example, if the value of water quality parameters is gradually decreasing, it may mean that the water quality is gradually getting worse; on the contrary, if the value of water quality parameters is gradually increasing, it may mean that the water quality is gradually improving.
[0062] Spatial distribution: Water quality data obtained at multiple monitoring points can reflect the spatial distribution of water quality. For example, some pollutants may have higher concentrations in some areas and lower concentrations in other areas. By analyzing these spatial distribution data, we can understand the source and diffusion of pollutants.
[0063] The water quality condition detection model training module uses the machine learning algorithm of the support vector machine to build a prediction model to predict the water quality condition based on the extracted features, classify the water quality status, deploy the model to the system, and predict new data in real time.
[0064] The remote monitoring and early warning control module automatically uploads the collected data to the cloud platform through the Internet of Things technology to monitor the water quality in real time. The water quality data is analyzed in real time through the water quality detection model. When abnormal water quality is found, the system can automatically issue an early warning signal to remind users to take timely measures and remotely control the switching of water conservancy equipment.
[0065] A water conservancy business processing Internet of Things system and method, comprising the following steps:
[0066] S1. When it is necessary to test the water quality of water in water conservancy canals, water quality sensors and water level sensors are deployed in the water body and connected through the Internet of Things to collect water quality data, including measuring various water quality parameters, such as dissolved oxygen, pH value, turbidity, conductivity and other data. Water quality sensors and water level sensors are connected to the Internet of Things so that data can be collected and transmitted remotely.
[0067] S2. Use the water quality data preprocessing module to preprocess the collected raw data to improve the accuracy and reliability of the data, including data cleaning, data standardization, data smoothing, data cleaning: delete or fill missing values, delete outliers, process duplicate data, etc., to ensure the integrity and consistency of the data set;
[0068] Data standardization: converting data into a unified standard to eliminate deviations caused by factors such as data dimension and magnitude;
[0069] Data smoothing: Use mean filtering to remove noise and fluctuations in the data to reduce the impact of random errors and outliers on the analysis results;
[0070] S3. Extract water quality-related features from the processed data through the water quality data feature extraction module, such as the values of various water quality parameters and their changing trends, including the values, changing trends, and spatial distribution of water quality parameters. The values of water quality parameters can reflect the quality of water, such as pH value, dissolved oxygen, nitrate, ammonia nitrogen, etc. The values of these parameters can be used to describe the chemical and biological characteristics of water;
[0071] Change trend: By analyzing the change trend of water quality parameters, we can understand the change of water quality. For example, if the value of water quality parameters is gradually decreasing, it may mean that the water quality is gradually getting worse; on the contrary, if the value of water quality parameters is gradually increasing, it may mean that the water quality is gradually improving.
[0072] Spatial distribution: Water quality data obtained at multiple monitoring points can reflect the spatial distribution of water quality. For example, some pollutants may have higher concentrations in some areas and lower concentrations in other areas. By analyzing these spatial distribution data, we can understand the source and diffusion of pollutants.
[0073] S4. Use the machine learning algorithm of support vector machine through the water quality detection model training module to build a prediction model to predict the water quality status based on the extracted features, classify the water quality status, deploy the model into the system, and predict new data in real time;
[0074] S5. Use the remote monitoring and early warning control module through the Internet of Things technology to automatically upload the collected data to the cloud platform to monitor the water quality in real time. Through the water quality detection model, the water quality data is analyzed in real time. When abnormal water quality is found, the system can automatically send out an early warning signal to remind users to take timely measures and remotely control the switch of water conservancy equipment.
[0075] Reference Figure 2 , a water conservancy business processing Internet of Things system and method, including a gate frame 1, a gate 2, a fixing seat 3, a transmission detection mechanism 4, and a cleaning mechanism 5,
[0076] A gate 2 is slidably provided on the gate frame 1 , a fixing seat 3 is connected and fixedly provided on the gate frame 1 , a transmission detection mechanism 4 is rotatably provided on the fixing seat 3 , and a cleaning mechanism 5 is connected and fixedly provided on the fixing seat 3 .
[0077] Reference Figure 3 An electric push rod 201 is fixedly connected to the gate 2, and the electric push rod 201 is connected and fixedly arranged through the gate frame 1. Two racks 202 are fixedly connected to the gate 2.
[0078] Reference Figure 4 A cleaning liquid storage box 301 is connected and fixedly arranged on the fixed seat 3, a protective cover 302 is slidably arranged on the fixed seat 3, and a spring 303 is connected and fixedly arranged between the protective cover 302 and the fixed seat 3.
[0079] Reference Figure 5 The transmission detection mechanism 4 includes a mounting seat 401, on which a plurality of sensors are mounted, and on which two adjusting rod groups 402 are rotatably connected, and the other end of the adjusting rod group 402 is rotatably connected to the inner wall of the fixing seat 3, and one end of the adjusting rod group 402 is connected and fixedly provided with a worm gear 403;
[0080] A worm 404 is meshed and driven on one side of the worm wheel 403 . The worm 404 is rotatably connected to the inner wall of the fixing seat 3 through a universal joint 405 . A gear 406 is fixedly connected to the other end of the universal joint 405 . The gear 406 is meshed and driven with the rack 202 .
[0081] Reference Figure 6 The cleaning mechanism 5 includes a motor 501, the output end of the motor 501 is connected and fixedly provided with a driving wheel 502, the driving wheel 502 is meshed and driven with a driven wheel 503, the driven wheel 503 is connected and fixedly provided with a liquid guide tube 504, the liquid guide tube 504 is rotatably connected to the inner wall of the fixed seat 3, and the other end of the liquid guide tube 504 is connected and fixedly provided with a cleaning brush cover 505;
[0082] One end of the liquid guiding tube 504 is rotatably connected to a pump body 506 , and an input end of the pump body 506 is communicated with the cleaning liquid storage box 301 .
[0083] The implementation principle of the IoT system and method for water conservancy business processing in the embodiment of the present application is as follows: when it is necessary to open the gate to release water, the electric push rod 201 is remotely controlled by the IoT to drive the gate 2 to open. At this time, the rack 202 on the gate 2 drives the universal joint 405 connected to the gear 406 to rotate, so that the universal joint 405 drives the worm 404 to rotate, thereby driving the adjustment rod group 402 connected to the worm gear 403, so that the adjustment rod group 402 drives the sensor on the mounting seat 401 to contact the water in the canal;
[0084] Then, water quality sensors and water level sensors are deployed in water bodies and connected through the Internet of Things to collect water quality data, including measuring various water quality parameters such as dissolved oxygen, pH value, turbidity, conductivity and other data. Water quality sensors and water level sensors are connected to the Internet of Things to enable remote collection and transmission of data.
[0085] Use the water quality data preprocessing module to preprocess the collected raw data to improve the accuracy and reliability of the data, including data cleaning, data standardization, data smoothing, data cleaning: delete or fill missing values, delete outliers, process duplicate data, etc., to ensure the integrity and consistency of the data set;
[0086] Data standardization: converting data into a unified standard to eliminate deviations caused by factors such as data dimension and magnitude;
[0087] Data smoothing: Use mean filtering to remove noise and fluctuations in the data to reduce the impact of random errors and outliers on the analysis results;
[0088] The water quality data feature extraction module extracts water quality-related features from the processed data, such as the values of various water quality parameters and their changing trends, including the values, changing trends, and spatial distribution of water quality parameters. The values of water quality parameters can reflect the quality of water, such as pH value, dissolved oxygen, nitrate, ammonia nitrogen, etc. The values of these parameters can be used to describe the chemical and biological characteristics of water;
[0089] Change trend: By analyzing the change trend of water quality parameters, we can understand the change of water quality. For example, if the value of water quality parameters is gradually decreasing, it may mean that the water quality is gradually getting worse; on the contrary, if the value of water quality parameters is gradually increasing, it may mean that the water quality is gradually improving.
[0090] Spatial distribution: Water quality data obtained at multiple monitoring points can reflect the spatial distribution of water quality. For example, some pollutants may have higher concentrations in some areas and lower concentrations in other areas. By analyzing these spatial distribution data, we can understand the source and diffusion of pollutants.
[0091] Through the water quality detection model training module, a prediction model is constructed using the support vector machine machine learning algorithm to predict water quality conditions based on the extracted features, classify water quality states, deploy the model into the system, and predict new data in real time;
[0092] The remote monitoring and early warning control module uses the Internet of Things technology to automatically upload the collected data to the cloud platform to monitor the water quality in real time. The water quality data is analyzed in real time through the water quality detection model. When abnormal water quality is found, the system can automatically send out an early warning signal to remind users to take timely measures and remotely control the switch of water conservancy equipment.
[0093] When the sensor is retracted, the sensor will be placed in the cleaning brush cover 505, and then the motor 501 will drive the driving wheel 502 to rotate, so that the driving wheel 502 drives the liquid guide tube 504 connected to the driven wheel 503 to rotate, and then the liquid guide tube 504 will drive the cleaning brush cover 505 to rotate to brush the sensor. At the same time, under the action of the pump body, the cleaning liquid in the cleaning liquid placement box 301 is drawn out to rinse the sensor.
Claims
1. A water conservancy business processing Internet of Things system and method, comprising: a water quality data acquisition module, a water quality data preprocessing module, a water quality data feature extraction module, a water quality status detection model training module, and a remote monitoring and early warning control module, characterized in that: Water quality data collection module: The water quality data collection module deploys water quality sensors, water level sensors, etc. in the water body, and collects water quality data through the Internet of Things connection; Water quality data preprocessing module: The water quality data preprocessing module performs preprocessing operations on the collected raw data to improve the accuracy and reliability of the data; Water quality data feature extraction module: The water quality data feature extraction module extracts features related to water quality from the processed data, such as the values of various water quality parameters and their changing trends; Water quality condition detection model training module: The water quality condition detection model training module uses a machine learning algorithm to build a prediction model to predict water quality conditions based on the extracted features; Remote monitoring and early warning control module: The remote monitoring and early warning control module automatically uploads the collected data to the cloud platform through the Internet of Things technology to monitor the water quality in real time.
2. The water conservancy business processing Internet of Things system and method according to claim 1 is characterized by: The water quality data acquisition module deploys water quality sensors, water level sensors, etc. in the water body, and collects water quality data through the Internet of Things connection, including measuring various water quality parameters, such as dissolved oxygen, pH value, turbidity, conductivity and other data. By connecting the water quality sensors and water level sensors to the Internet of Things, data can be remotely collected and transmitted.
3. The water conservancy business processing Internet of Things system and method according to claim 1 is characterized in that: The water quality data preprocessing module performs preprocessing operations on the collected raw data to improve the accuracy and reliability of the data, including data cleaning, data standardization, and data smoothing. The data cleaning includes deleting or filling missing values, deleting outliers, processing duplicate data, etc., to ensure the integrity and consistency of the data set; The data standardization is to convert the data into a unified standard to eliminate the deviation caused by factors such as data dimension and order of magnitude; The data smoothing: uses a mean filtering technique to remove noise and fluctuations in the data to reduce the impact of random errors and outliers on the analysis results.
4. The water conservancy business processing Internet of Things system and method according to claim 1 is characterized in that: The water quality data feature extraction module extracts features related to water quality from the processed data, such as the values of various water quality parameters and their changing trends, including the values, changing trends, and spatial distribution of water quality parameters. The values of water quality parameters: The values of water quality parameters can reflect the quality of water, such as pH value, dissolved oxygen, nitrate, ammonia nitrogen, etc. The values of these parameters can be used to describe the chemical and biological characteristics of water; The change trend: by analyzing the change trend of water quality parameters, it is possible to understand the change of water quality. For example, if the value of the water quality parameter is gradually decreasing, it may mean that the water quality is gradually getting worse; conversely, if the value of the water quality parameter is gradually increasing, it may mean that the water quality is gradually improving; The spatial distribution: The water quality data obtained at multiple monitoring points can reflect the spatial distribution of water quality. For example, some pollutants may have higher concentrations in some areas and lower concentrations in other areas. By analyzing these spatial distribution data, the source and diffusion of pollutants can be understood.
5. The water conservancy business processing Internet of Things system and method according to claim 1 is characterized by: The water quality condition detection model training module uses the machine learning algorithm of the support vector machine to build a prediction model to predict the water quality condition based on the extracted features, classify the water quality status, deploy the model to the system, and predict new data in real time.
6. The water conservancy business processing Internet of Things system and method according to claim 1 is characterized by: The remote monitoring and early warning control module automatically uploads the collected data to the cloud platform through the Internet of Things technology to monitor the water quality in real time. The water quality data is analyzed in real time through the water quality detection model. When abnormal water quality is found, the system can automatically send out an early warning signal to remind the user to take timely measures and remotely control the switching of water conservancy equipment.
7. A water conservancy business processing Internet of Things system and method, comprising the following steps: S1. When it is necessary to test the water quality of water in water conservancy canals, water quality sensors and water level sensors are deployed in the water body and connected through the Internet of Things to collect water quality data, including measuring various water quality parameters, such as dissolved oxygen, pH value, turbidity, conductivity and other data. Water quality sensors and water level sensors are connected to the Internet of Things so that data can be collected and transmitted remotely. S2. Use the water quality data preprocessing module to preprocess the collected raw data to improve the accuracy and reliability of the data, including data cleaning, data standardization, data smoothing, data cleaning: delete or fill missing values, delete outliers, process duplicate data, etc., to ensure the integrity and consistency of the data set; Data standardization: converting data into a unified standard to eliminate deviations caused by factors such as data dimension and magnitude; Data smoothing: Use mean filtering to remove noise and fluctuations in the data to reduce the impact of random errors and outliers on the analysis results; S3. Extract water quality-related features from the processed data through the water quality data feature extraction module, such as the values of various water quality parameters and their changing trends, including the values, changing trends, and spatial distribution of water quality parameters. The values of water quality parameters can reflect the quality of water, such as pH value, dissolved oxygen, nitrate, ammonia nitrogen, etc. The values of these parameters can be used to describe the chemical and biological characteristics of water; Change trend: By analyzing the change trend of water quality parameters, we can understand the change of water quality. For example, if the value of water quality parameters is gradually decreasing, it may mean that the water quality is gradually getting worse; on the contrary, if the value of water quality parameters is gradually increasing, it may mean that the water quality is gradually improving. Spatial distribution: Water quality data obtained at multiple monitoring points can reflect the spatial distribution of water quality. For example, some pollutants may have higher concentrations in some areas and lower concentrations in other areas. By analyzing these spatial distribution data, we can understand the source and diffusion of pollutants. S4. Use the machine learning algorithm of support vector machine through the water quality detection model training module to build a prediction model to predict the water quality status based on the extracted features, classify the water quality status, deploy the model into the system, and predict new data in real time; S5. Use the remote monitoring and early warning control module through the Internet of Things technology to automatically upload the collected data to the cloud platform to monitor the water quality in real time. Through the water quality detection model, the water quality data is analyzed in real time. When abnormal water quality is found, the system can automatically send out an early warning signal to remind users to take timely measures and remotely control the switch of water conservancy equipment.
Citation Information
Cited By
Water quality monitoring system for secondary water supply intelligent pump house
CN119492864A
A water quality monitoring system for a secondary water supply intelligent pump house
CN119492864B
Remote multi-parameter water quality detection system and water quality detection method
CN119985884A
